An integrated method for cancer classification and rule extraction from microarray data

PubMed Central

Huang, Liang-Tsung

2009-01-01

Different microarray techniques recently have been successfully used to investigate useful information for cancer diagnosis at the gene expression level due to their ability to measure thousands of gene expression levels in a massively parallel way. One important issue is to improve classification performance of microarray data. However, it would be ideal that influential genes and even interpretable rules can be explored at the same time to offer biological insight. Introducing the concepts of system design in software engineering, this paper has presented an integrated and effective method (named X-AI) for accurate cancer classification and the acquisition of knowledge from DNA microarray data. This method included a feature selector to systematically extract the relative important genes so as to reduce the dimension and retain as much as possible of the class discriminatory information. Next, diagonal quadratic discriminant analysis (DQDA) was combined to classify tumors, and generalized rule induction (GRI) was integrated to establish association rules which can give an understanding of the relationships between cancer classes and related genes. Two non-redundant datasets of acute leukemia were used to validate the proposed X-AI, showing significantly high accuracy for discriminating different classes. On the other hand, I have presented the abilities of X-AI to extract relevant genes, as well as to develop interpretable rules. Further, a web server has been established for cancer classification and it is freely available at . PMID:19272192

Application of machine learning on brain cancer multiclass classification

NASA Astrophysics Data System (ADS)

Panca, V.; Rustam, Z.

2017-07-01

Classification of brain cancer is a problem of multiclass classification. One approach to solve this problem is by first transforming it into several binary problems. The microarray gene expression dataset has the two main characteristics of medical data: extremely many features (genes) and only a few number of samples. The application of machine learning on microarray gene expression dataset mainly consists of two steps: feature selection and classification. In this paper, the features are selected using a method based on support vector machine recursive feature elimination (SVM-RFE) principle which is improved to solve multiclass classification, called multiple multiclass SVM-RFE. Instead of using only the selected features on a single classifier, this method combines the result of multiple classifiers. The features are divided into subsets and SVM-RFE is used on each subset. Then, the selected features on each subset are put on separate classifiers. This method enhances the feature selection ability of each single SVM-RFE. Twin support vector machine (TWSVM) is used as the method of the classifier to reduce computational complexity. While ordinary SVM finds single optimum hyperplane, the main objective Twin SVM is to find two non-parallel optimum hyperplanes. The experiment on the brain cancer microarray gene expression dataset shows this method could classify 71,4% of the overall test data correctly, using 100 and 1000 genes selected from multiple multiclass SVM-RFE feature selection method. Furthermore, the per class results show that this method could classify data of normal and MD class with 100% accuracy.

Applications of microarray technology in breast cancer research

PubMed Central

Cooper, Colin S

2001-01-01

Microarrays provide a versatile platform for utilizing information from the Human Genome Project to benefit human health. This article reviews the ways in which microarray technology may be used in breast cancer research. Its diverse applications include monitoring chromosome gains and losses, tumour classification, drug discovery and development, DNA resequencing, mutation detection and investigating the mechanism of tumour development. PMID:11305951

Leukemia and colon tumor detection based on microarray data classification using momentum backpropagation and genetic algorithm as a feature selection method

NASA Astrophysics Data System (ADS)

Wisesty, Untari N.; Warastri, Riris S.; Puspitasari, Shinta Y.

2018-03-01

Cancer is one of the major causes of mordibility and mortality problems in the worldwide. Therefore, the need of a system that can analyze and identify a person suffering from a cancer by using microarray data derived from the patient’s Deoxyribonucleic Acid (DNA). But on microarray data has thousands of attributes, thus making the challenges in data processing. This is often referred to as the curse of dimensionality. Therefore, in this study built a system capable of detecting a patient whether contracted cancer or not. The algorithm used is Genetic Algorithm as feature selection and Momentum Backpropagation Neural Network as a classification method, with data used from the Kent Ridge Bio-medical Dataset. Based on system testing that has been done, the system can detect Leukemia and Colon Tumor with best accuracy equal to 98.33% for colon tumor data and 100% for leukimia data. Genetic Algorithm as feature selection algorithm can improve system accuracy, which is from 64.52% to 98.33% for colon tumor data and 65.28% to 100% for leukemia data, and the use of momentum parameters can accelerate the convergence of the system in the training process of Neural Network.

Call for a Computer-Aided Cancer Detection and Classification Research Initiative in Oman.

PubMed

Mirzal, Andri; Chaudhry, Shafique Ahmad

2016-01-01

Cancer is a major health problem in Oman. It is reported that cancer incidence in Oman is the second highest after Saudi Arabia among Gulf Cooperation Council countries. Based on GLOBOCAN estimates, Oman is predicted to face an almost two-fold increase in cancer incidence in the period 2008-2020. However, cancer research in Oman is still in its infancy. This is due to the fact that medical institutions and infrastructure that play central roles in data collection and analysis are relatively new developments in Oman. We believe the country requires an organized plan and efforts to promote local cancer research. In this paper, we discuss current research progress in cancer diagnosis using machine learning techniques to optimize computer aided cancer detection and classification (CAD). We specifically discuss CAD using two major medical data, i.e., medical imaging and microarray gene expression profiling, because medical imaging like mammography, MRI, and PET have been widely used in Oman for assisting radiologists in early cancer diagnosis and microarray data have been proven to be a reliable source for differential diagnosis. We also discuss future cancer research directions and benefits to Oman economy for entering the cancer research and treatment business as it is a multi-billion dollar industry worldwide.

Recursive feature selection with significant variables of support vectors.

PubMed

Tsai, Chen-An; Huang, Chien-Hsun; Chang, Ching-Wei; Chen, Chun-Houh

2012-01-01

The development of DNA microarray makes researchers screen thousands of genes simultaneously and it also helps determine high- and low-expression level genes in normal and disease tissues. Selecting relevant genes for cancer classification is an important issue. Most of the gene selection methods use univariate ranking criteria and arbitrarily choose a threshold to choose genes. However, the parameter setting may not be compatible to the selected classification algorithms. In this paper, we propose a new gene selection method (SVM-t) based on the use of t-statistics embedded in support vector machine. We compared the performance to two similar SVM-based methods: SVM recursive feature elimination (SVMRFE) and recursive support vector machine (RSVM). The three methods were compared based on extensive simulation experiments and analyses of two published microarray datasets. In the simulation experiments, we found that the proposed method is more robust in selecting informative genes than SVMRFE and RSVM and capable to attain good classification performance when the variations of informative and noninformative genes are different. In the analysis of two microarray datasets, the proposed method yields better performance in identifying fewer genes with good prediction accuracy, compared to SVMRFE and RSVM.

Genetic Bee Colony (GBC) algorithm: A new gene selection method for microarray cancer classification.

PubMed

Alshamlan, Hala M; Badr, Ghada H; Alohali, Yousef A

2015-06-01

Naturally inspired evolutionary algorithms prove effectiveness when used for solving feature selection and classification problems. Artificial Bee Colony (ABC) is a relatively new swarm intelligence method. In this paper, we propose a new hybrid gene selection method, namely Genetic Bee Colony (GBC) algorithm. The proposed algorithm combines the used of a Genetic Algorithm (GA) along with Artificial Bee Colony (ABC) algorithm. The goal is to integrate the advantages of both algorithms. The proposed algorithm is applied to a microarray gene expression profile in order to select the most predictive and informative genes for cancer classification. In order to test the accuracy performance of the proposed algorithm, extensive experiments were conducted. Three binary microarray datasets are use, which include: colon, leukemia, and lung. In addition, another three multi-class microarray datasets are used, which are: SRBCT, lymphoma, and leukemia. Results of the GBC algorithm are compared with our recently proposed technique: mRMR when combined with the Artificial Bee Colony algorithm (mRMR-ABC). We also compared the combination of mRMR with GA (mRMR-GA) and Particle Swarm Optimization (mRMR-PSO) algorithms. In addition, we compared the GBC algorithm with other related algorithms that have been recently published in the literature, using all benchmark datasets. The GBC algorithm shows superior performance as it achieved the highest classification accuracy along with the lowest average number of selected genes. This proves that the GBC algorithm is a promising approach for solving the gene selection problem in both binary and multi-class cancer classification. Copyright © 2015 Elsevier Ltd. All rights reserved.

Hybrid genetic algorithm-neural network: feature extraction for unpreprocessed microarray data.

PubMed

Tong, Dong Ling; Schierz, Amanda C

2011-09-01

Suitable techniques for microarray analysis have been widely researched, particularly for the study of marker genes expressed to a specific type of cancer. Most of the machine learning methods that have been applied to significant gene selection focus on the classification ability rather than the selection ability of the method. These methods also require the microarray data to be preprocessed before analysis takes place. The objective of this study is to develop a hybrid genetic algorithm-neural network (GANN) model that emphasises feature selection and can operate on unpreprocessed microarray data. The GANN is a hybrid model where the fitness value of the genetic algorithm (GA) is based upon the number of samples correctly labelled by a standard feedforward artificial neural network (ANN). The model is evaluated by using two benchmark microarray datasets with different array platforms and differing number of classes (a 2-class oligonucleotide microarray data for acute leukaemia and a 4-class complementary DNA (cDNA) microarray dataset for SRBCTs (small round blue cell tumours)). The underlying concept of the GANN algorithm is to select highly informative genes by co-evolving both the GA fitness function and the ANN weights at the same time. The novel GANN selected approximately 50% of the same genes as the original studies. This may indicate that these common genes are more biologically significant than other genes in the datasets. The remaining 50% of the significant genes identified were used to build predictive models and for both datasets, the models based on the set of genes extracted by the GANN method produced more accurate results. The results also suggest that the GANN method not only can detect genes that are exclusively associated with a single cancer type but can also explore the genes that are differentially expressed in multiple cancer types. The results show that the GANN model has successfully extracted statistically significant genes from the unpreprocessed microarray data as well as extracting known biologically significant genes. We also show that assessing the biological significance of genes based on classification accuracy may be misleading and though the GANN's set of extra genes prove to be more statistically significant than those selected by other methods, a biological assessment of these genes is highly recommended to confirm their functionality. Copyright © 2011 Elsevier B.V. All rights reserved.

Semi-Supervised Projective Non-Negative Matrix Factorization for Cancer Classification.

PubMed

Zhang, Xiang; Guan, Naiyang; Jia, Zhilong; Qiu, Xiaogang; Luo, Zhigang

2015-01-01

Advances in DNA microarray technologies have made gene expression profiles a significant candidate in identifying different types of cancers. Traditional learning-based cancer identification methods utilize labeled samples to train a classifier, but they are inconvenient for practical application because labels are quite expensive in the clinical cancer research community. This paper proposes a semi-supervised projective non-negative matrix factorization method (Semi-PNMF) to learn an effective classifier from both labeled and unlabeled samples, thus boosting subsequent cancer classification performance. In particular, Semi-PNMF jointly learns a non-negative subspace from concatenated labeled and unlabeled samples and indicates classes by the positions of the maximum entries of their coefficients. Because Semi-PNMF incorporates statistical information from the large volume of unlabeled samples in the learned subspace, it can learn more representative subspaces and boost classification performance. We developed a multiplicative update rule (MUR) to optimize Semi-PNMF and proved its convergence. The experimental results of cancer classification for two multiclass cancer gene expression profile datasets show that Semi-PNMF outperforms the representative methods.

Implementation of mutual information and bayes theorem for classification microarray data

NASA Astrophysics Data System (ADS)

Dwifebri Purbolaksono, Mahendra; Widiastuti, Kurnia C.; Syahrul Mubarok, Mohamad; Adiwijaya; Aminy Ma’ruf, Firda

2018-03-01

Microarray Technology is one of technology which able to read the structure of gen. The analysis is important for this technology. It is for deciding which attribute is more important than the others. Microarray technology is able to get cancer information to diagnose a person’s gen. Preparation of microarray data is a huge problem and takes a long time. That is because microarray data contains high number of insignificant and irrelevant attributes. So, it needs a method to reduce the dimension of microarray data without eliminating important information in every attribute. This research uses Mutual Information to reduce dimension. System is built with Machine Learning approach specifically Bayes Theorem. This theorem uses a statistical and probability approach. By combining both methods, it will be powerful for Microarray Data Classification. The experiment results show that system is good to classify Microarray data with highest F1-score using Bayesian Network by 91.06%, and Naïve Bayes by 88.85%.

Deep learning for tissue microarray image-based outcome prediction in patients with colorectal cancer

NASA Astrophysics Data System (ADS)

Bychkov, Dmitrii; Turkki, Riku; Haglund, Caj; Linder, Nina; Lundin, Johan

2016-03-01

Recent advances in computer vision enable increasingly accurate automated pattern classification. In the current study we evaluate whether a convolutional neural network (CNN) can be trained to predict disease outcome in patients with colorectal cancer based on images of tumor tissue microarray samples. We compare the prognostic accuracy of CNN features extracted from the whole, unsegmented tissue microarray spot image, with that of CNN features extracted from the epithelial and non-epithelial compartments, respectively. The prognostic accuracy of visually assessed histologic grade is used as a reference. The image data set consists of digitized hematoxylin-eosin (H and E) stained tissue microarray samples obtained from 180 patients with colorectal cancer. The patient samples represent a variety of histological grades, have data available on a series of clinicopathological variables including long-term outcome and ground truth annotations performed by experts. The CNN features extracted from images of the epithelial tissue compartment significantly predicted outcome (hazard ratio (HR) 2.08; CI95% 1.04-4.16; area under the curve (AUC) 0.66) in a test set of 60 patients, as compared to the CNN features extracted from unsegmented images (HR 1.67; CI95% 0.84-3.31, AUC 0.57) and visually assessed histologic grade (HR 1.96; CI95% 0.99-3.88, AUC 0.61). As a conclusion, a deep-learning classifier can be trained to predict outcome of colorectal cancer based on images of H and E stained tissue microarray samples and the CNN features extracted from the epithelial compartment only resulted in a prognostic discrimination comparable to that of visually determined histologic grade.

Multiclass cancer diagnosis using tumor gene expression signatures

DOE PAGES

Ramaswamy, S.; Tamayo, P.; Rifkin, R.; ...

2001-12-11

The optimal treatment of patients with cancer depends on establishing accurate diagnoses by using a complex combination of clinical and histopathological data. In some instances, this task is difficult or impossible because of atypical clinical presentation or histopathology. To determine whether the diagnosis of multiple common adult malignancies could be achieved purely by molecular classification, we subjected 218 tumor samples, spanning 14 common tumor types, and 90 normal tissue samples to oligonucleotide microarray gene expression analysis. The expression levels of 16,063 genes and expressed sequence tags were used to evaluate the accuracy of a multiclass classifier based on a supportmore » vector machine algorithm. Overall classification accuracy was 78%, far exceeding the accuracy of random classification (9%). Poorly differentiated cancers resulted in low-confidence predictions and could not be accurately classified according to their tissue of origin, indicating that they are molecularly distinct entities with dramatically different gene expression patterns compared with their well differentiated counterparts. Taken together, these results demonstrate the feasibility of accurate, multiclass molecular cancer classification and suggest a strategy for future clinical implementation of molecular cancer diagnostics.« less

Diagnostic classification of cancer using DNA microarrays and artificial intelligence.

PubMed

Greer, Braden T; Khan, Javed

2004-05-01

The application of artificial intelligence (AI) to microarray data has been receiving much attention in recent years because of the possibility of automated diagnosis in the near future. Studies have been published predicting tumor type, estrogen receptor status, and prognosis using a variety of AI algorithms. The performance of intelligent computing decisions based on gene expression signatures is in some cases comparable to or better than the current clinical decision schemas. The goal of these tools is not to make clinicians obsolete, but rather to give clinicians one more tool in their armamentarium to accurately diagnose and hence better treat cancer patients. Several such applications are summarized in this chapter, and some of the common pitfalls are noted.

Parameters selection in gene selection using Gaussian kernel support vector machines by genetic algorithm.

PubMed

Mao, Yong; Zhou, Xiao-Bo; Pi, Dao-Ying; Sun, You-Xian; Wong, Stephen T C

2005-10-01

In microarray-based cancer classification, gene selection is an important issue owing to the large number of variables and small number of samples as well as its non-linearity. It is difficult to get satisfying results by using conventional linear statistical methods. Recursive feature elimination based on support vector machine (SVM RFE) is an effective algorithm for gene selection and cancer classification, which are integrated into a consistent framework. In this paper, we propose a new method to select parameters of the aforementioned algorithm implemented with Gaussian kernel SVMs as better alternatives to the common practice of selecting the apparently best parameters by using a genetic algorithm to search for a couple of optimal parameter. Fast implementation issues for this method are also discussed for pragmatic reasons. The proposed method was tested on two representative hereditary breast cancer and acute leukaemia datasets. The experimental results indicate that the proposed method performs well in selecting genes and achieves high classification accuracies with these genes.

Fully Automated Complementary DNA Microarray Segmentation using a Novel Fuzzy-based Algorithm.

PubMed

Saberkari, Hamidreza; Bahrami, Sheyda; Shamsi, Mousa; Amoshahy, Mohammad Javad; Ghavifekr, Habib Badri; Sedaaghi, Mohammad Hossein

2015-01-01

DNA microarray is a powerful approach to study simultaneously, the expression of 1000 of genes in a single experiment. The average value of the fluorescent intensity could be calculated in a microarray experiment. The calculated intensity values are very close in amount to the levels of expression of a particular gene. However, determining the appropriate position of every spot in microarray images is a main challenge, which leads to the accurate classification of normal and abnormal (cancer) cells. In this paper, first a preprocessing approach is performed to eliminate the noise and artifacts available in microarray cells using the nonlinear anisotropic diffusion filtering method. Then, the coordinate center of each spot is positioned utilizing the mathematical morphology operations. Finally, the position of each spot is exactly determined through applying a novel hybrid model based on the principle component analysis and the spatial fuzzy c-means clustering (SFCM) algorithm. Using a Gaussian kernel in SFCM algorithm will lead to improving the quality in complementary DNA microarray segmentation. The performance of the proposed algorithm has been evaluated on the real microarray images, which is available in Stanford Microarray Databases. Results illustrate that the accuracy of microarray cells segmentation in the proposed algorithm reaches to 100% and 98% for noiseless/noisy cells, respectively.

Multiclass classification for skin cancer profiling based on the integration of heterogeneous gene expression series.

PubMed

Gálvez, Juan Manuel; Castillo, Daniel; Herrera, Luis Javier; San Román, Belén; Valenzuela, Olga; Ortuño, Francisco Manuel; Rojas, Ignacio

2018-01-01

Most of the research studies developed applying microarray technology to the characterization of different pathological states of any disease may fail in reaching statistically significant results. This is largely due to the small repertoire of analysed samples, and to the limitation in the number of states or pathologies usually addressed. Moreover, the influence of potential deviations on the gene expression quantification is usually disregarded. In spite of the continuous changes in omic sciences, reflected for instance in the emergence of new Next-Generation Sequencing-related technologies, the existing availability of a vast amount of gene expression microarray datasets should be properly exploited. Therefore, this work proposes a novel methodological approach involving the integration of several heterogeneous skin cancer series, and a later multiclass classifier design. This approach is thus a way to provide the clinicians with an intelligent diagnosis support tool based on the use of a robust set of selected biomarkers, which simultaneously distinguishes among different cancer-related skin states. To achieve this, a multi-platform combination of microarray datasets from Affymetrix and Illumina manufacturers was carried out. This integration is expected to strengthen the statistical robustness of the study as well as the finding of highly-reliable skin cancer biomarkers. Specifically, the designed operation pipeline has allowed the identification of a small subset of 17 differentially expressed genes (DEGs) from which to distinguish among 7 involved skin states. These genes were obtained from the assessment of a number of potential batch effects on the gene expression data. The biological interpretation of these genes was inspected in the specific literature to understand their underlying information in relation to skin cancer. Finally, in order to assess their possible effectiveness in cancer diagnosis, a cross-validation Support Vector Machines (SVM)-based classification including feature ranking was performed. The accuracy attained exceeded the 92% in overall recognition of the 7 different cancer-related skin states. The proposed integration scheme is expected to allow the co-integration with other state-of-the-art technologies such as RNA-seq.

Gene selection for microarray cancer classification using a new evolutionary method employing artificial intelligence concepts.

PubMed

Dashtban, M; Balafar, Mohammadali

2017-03-01

Gene selection is a demanding task for microarray data analysis. The diverse complexity of different cancers makes this issue still challenging. In this study, a novel evolutionary method based on genetic algorithms and artificial intelligence is proposed to identify predictive genes for cancer classification. A filter method was first applied to reduce the dimensionality of feature space followed by employing an integer-coded genetic algorithm with dynamic-length genotype, intelligent parameter settings, and modified operators. The algorithmic behaviors including convergence trends, mutation and crossover rate changes, and running time were studied, conceptually discussed, and shown to be coherent with literature findings. Two well-known filter methods, Laplacian and Fisher score, were examined considering similarities, the quality of selected genes, and their influences on the evolutionary approach. Several statistical tests concerning choice of classifier, choice of dataset, and choice of filter method were performed, and they revealed some significant differences between the performance of different classifiers and filter methods over datasets. The proposed method was benchmarked upon five popular high-dimensional cancer datasets; for each, top explored genes were reported. Comparing the experimental results with several state-of-the-art methods revealed that the proposed method outperforms previous methods in DLBCL dataset. Copyright © 2017 Elsevier Inc. All rights reserved.

FSR: feature set reduction for scalable and accurate multi-class cancer subtype classification based on copy number.

PubMed

Wong, Gerard; Leckie, Christopher; Kowalczyk, Adam

2012-01-15

Feature selection is a key concept in machine learning for microarray datasets, where features represented by probesets are typically several orders of magnitude larger than the available sample size. Computational tractability is a key challenge for feature selection algorithms in handling very high-dimensional datasets beyond a hundred thousand features, such as in datasets produced on single nucleotide polymorphism microarrays. In this article, we present a novel feature set reduction approach that enables scalable feature selection on datasets with hundreds of thousands of features and beyond. Our approach enables more efficient handling of higher resolution datasets to achieve better disease subtype classification of samples for potentially more accurate diagnosis and prognosis, which allows clinicians to make more informed decisions in regards to patient treatment options. We applied our feature set reduction approach to several publicly available cancer single nucleotide polymorphism (SNP) array datasets and evaluated its performance in terms of its multiclass predictive classification accuracy over different cancer subtypes, its speedup in execution as well as its scalability with respect to sample size and array resolution. Feature Set Reduction (FSR) was able to reduce the dimensions of an SNP array dataset by more than two orders of magnitude while achieving at least equal, and in most cases superior predictive classification performance over that achieved on features selected by existing feature selection methods alone. An examination of the biological relevance of frequently selected features from FSR-reduced feature sets revealed strong enrichment in association with cancer. FSR was implemented in MATLAB R2010b and is available at http://ww2.cs.mu.oz.au/~gwong/FSR.

Customizing chemotherapy for colon cancer: the potential of gene expression profiling.

PubMed

Mariadason, John M; Arango, Diego; Augenlicht, Leonard H

2004-06-01

The value of gene expression profiling, or microarray analysis, for the classification and prognosis of multiple forms of cancer is now clearly established. For colon cancer, expression profiling can readily discriminate between normal and tumor tissue, and to some extent between tumors of different histopathological stage and prognosis. While a definitive in vivo study demonstrating the potential of this methodology for predicting response to chemotherapy is presently lacking, the ability of microarrays to distinguish other subtleties of colon cancer phenotype, as well as recent in vitro proof-of-principle experiments utilizing colon cancer cell lines, illustrate the potential of this methodology for predicting the probability of response to specific chemotherapeutic agents. This review discusses some of the recent advances in the use of microarray analysis for understanding and distinguishing colon cancer subtypes, and attempts to identify challenges that need to be overcome in order to achieve the goal of using gene expression profiling for customizing chemotherapy in colon cancer.

SVM Classifier - a comprehensive java interface for support vector machine classification of microarray data.

PubMed

Pirooznia, Mehdi; Deng, Youping

2006-12-12

Graphical user interface (GUI) software promotes novelty by allowing users to extend the functionality. SVM Classifier is a cross-platform graphical application that handles very large datasets well. The purpose of this study is to create a GUI application that allows SVM users to perform SVM training, classification and prediction. The GUI provides user-friendly access to state-of-the-art SVM methods embodied in the LIBSVM implementation of Support Vector Machine. We implemented the java interface using standard swing libraries. We used a sample data from a breast cancer study for testing classification accuracy. We achieved 100% accuracy in classification among the BRCA1-BRCA2 samples with RBF kernel of SVM. We have developed a java GUI application that allows SVM users to perform SVM training, classification and prediction. We have demonstrated that support vector machines can accurately classify genes into functional categories based upon expression data from DNA microarray hybridization experiments. Among the different kernel functions that we examined, the SVM that uses a radial basis kernel function provides the best performance. The SVM Classifier is available at http://mfgn.usm.edu/ebl/svm/.

Genetic programming based ensemble system for microarray data classification.

PubMed

Liu, Kun-Hong; Tong, Muchenxuan; Xie, Shu-Tong; Yee Ng, Vincent To

2015-01-01

Recently, more and more machine learning techniques have been applied to microarray data analysis. The aim of this study is to propose a genetic programming (GP) based new ensemble system (named GPES), which can be used to effectively classify different types of cancers. Decision trees are deployed as base classifiers in this ensemble framework with three operators: Min, Max, and Average. Each individual of the GP is an ensemble system, and they become more and more accurate in the evolutionary process. The feature selection technique and balanced subsampling technique are applied to increase the diversity in each ensemble system. The final ensemble committee is selected by a forward search algorithm, which is shown to be capable of fitting data automatically. The performance of GPES is evaluated using five binary class and six multiclass microarray datasets, and results show that the algorithm can achieve better results in most cases compared with some other ensemble systems. By using elaborate base classifiers or applying other sampling techniques, the performance of GPES may be further improved.

Genetic Programming Based Ensemble System for Microarray Data Classification

PubMed Central

Liu, Kun-Hong; Tong, Muchenxuan; Xie, Shu-Tong; Yee Ng, Vincent To

2015-01-01

Recently, more and more machine learning techniques have been applied to microarray data analysis. The aim of this study is to propose a genetic programming (GP) based new ensemble system (named GPES), which can be used to effectively classify different types of cancers. Decision trees are deployed as base classifiers in this ensemble framework with three operators: Min, Max, and Average. Each individual of the GP is an ensemble system, and they become more and more accurate in the evolutionary process. The feature selection technique and balanced subsampling technique are applied to increase the diversity in each ensemble system. The final ensemble committee is selected by a forward search algorithm, which is shown to be capable of fitting data automatically. The performance of GPES is evaluated using five binary class and six multiclass microarray datasets, and results show that the algorithm can achieve better results in most cases compared with some other ensemble systems. By using elaborate base classifiers or applying other sampling techniques, the performance of GPES may be further improved. PMID:25810748

Static micro-array isolation, dynamic time series classification, capture and enumeration of spiked breast cancer cells in blood: the nanotube-CTC chip

NASA Astrophysics Data System (ADS)

Khosravi, Farhad; Trainor, Patrick J.; Lambert, Christopher; Kloecker, Goetz; Wickstrom, Eric; Rai, Shesh N.; Panchapakesan, Balaji

2016-11-01

We demonstrate the rapid and label-free capture of breast cancer cells spiked in blood using nanotube-antibody micro-arrays. 76-element single wall carbon nanotube arrays were manufactured using photo-lithography, metal deposition, and etching techniques. Anti-epithelial cell adhesion molecule (anti-EpCAM), Anti-human epithelial growth factor receptor 2 (anti-Her2) and non-specific IgG antibodies were functionalized to the surface of the nanotube devices using 1-pyrene-butanoic acid succinimidyl ester. Following device functionalization, blood spiked with SKBR3, MCF7 and MCF10A cells (100/1000 cells per 5 μl per device, 170 elements totaling 0.85 ml of whole blood) were adsorbed on to the nanotube device arrays. Electrical signatures were recorded from each device to screen the samples for differences in interaction (specific or non-specific) between samples and devices. A zone classification scheme enabled the classification of all 170 elements in a single map. A kernel-based statistical classifier for the ‘liquid biopsy’ was developed to create a predictive model based on dynamic time warping series to classify device electrical signals that corresponded to plain blood (control) or SKBR3 spiked blood (case) on anti-Her2 functionalized devices with ˜90% sensitivity, and 90% specificity in capture of 1000 SKBR3 breast cancer cells in blood using anti-Her2 functionalized devices. Screened devices that gave positive electrical signatures were confirmed using optical/confocal microscopy to hold spiked cancer cells. Confocal microscopic analysis of devices that were classified to hold spiked blood based on their electrical signatures confirmed the presence of cancer cells through staining for DAPI (nuclei), cytokeratin (cancer cells) and CD45 (hematologic cells) with single cell sensitivity. We report 55%-100% cancer cell capture yield depending on the active device area for blood adsorption with mean of 62% (˜12 500 captured off 20 000 spiked cells in 0.1 ml blood) in this first nanotube-CTC chip study.

Similarity-balanced discriminant neighbor embedding and its application to cancer classification based on gene expression data.

PubMed

Zhang, Li; Qian, Liqiang; Ding, Chuntao; Zhou, Weida; Li, Fanzhang

2015-09-01

The family of discriminant neighborhood embedding (DNE) methods is typical graph-based methods for dimension reduction, and has been successfully applied to face recognition. This paper proposes a new variant of DNE, called similarity-balanced discriminant neighborhood embedding (SBDNE) and applies it to cancer classification using gene expression data. By introducing a novel similarity function, SBDNE deals with two data points in the same class and the different classes with different ways. The homogeneous and heterogeneous neighbors are selected according to the new similarity function instead of the Euclidean distance. SBDNE constructs two adjacent graphs, or between-class adjacent graph and within-class adjacent graph, using the new similarity function. According to these two adjacent graphs, we can generate the local between-class scatter and the local within-class scatter, respectively. Thus, SBDNE can maximize the between-class scatter and simultaneously minimize the within-class scatter to find the optimal projection matrix. Experimental results on six microarray datasets show that SBDNE is a promising method for cancer classification. Copyright © 2015 Elsevier Ltd. All rights reserved.

MicroRNAs in Prostate Cancer

DTIC Science & Technology

2008-11-01

microarray, gene expression, androgen 16. SECURITY CLASSIFICATION OF: 17. LIMITATION OF ABSTRACT 18 . NUMBER OF PAGES 19a. NAME OF RESPONSIBLE...Anindya Dutta; Yong Sun Lee; Hak Kyun Kim MicroRNAs are short single-stranded RNAs of 18 -22 bases length that are produced by the processing of...we hope to go to xenograft assays to demonstrate that microRNA alterations can suppress metastasis. REFERENCES: 1. Mattie, M.D., et al

Hybrid feature selection algorithm using symmetrical uncertainty and a harmony search algorithm

NASA Astrophysics Data System (ADS)

Salameh Shreem, Salam; Abdullah, Salwani; Nazri, Mohd Zakree Ahmad

2016-04-01

Microarray technology can be used as an efficient diagnostic system to recognise diseases such as tumours or to discriminate between different types of cancers in normal tissues. This technology has received increasing attention from the bioinformatics community because of its potential in designing powerful decision-making tools for cancer diagnosis. However, the presence of thousands or tens of thousands of genes affects the predictive accuracy of this technology from the perspective of classification. Thus, a key issue in microarray data is identifying or selecting the smallest possible set of genes from the input data that can achieve good predictive accuracy for classification. In this work, we propose a two-stage selection algorithm for gene selection problems in microarray data-sets called the symmetrical uncertainty filter and harmony search algorithm wrapper (SU-HSA). Experimental results show that the SU-HSA is better than HSA in isolation for all data-sets in terms of the accuracy and achieves a lower number of genes on 6 out of 10 instances. Furthermore, the comparison with state-of-the-art methods shows that our proposed approach is able to obtain 5 (out of 10) new best results in terms of the number of selected genes and competitive results in terms of the classification accuracy.

BCDForest: a boosting cascade deep forest model towards the classification of cancer subtypes based on gene expression data.

PubMed

Guo, Yang; Liu, Shuhui; Li, Zhanhuai; Shang, Xuequn

2018-04-11

The classification of cancer subtypes is of great importance to cancer disease diagnosis and therapy. Many supervised learning approaches have been applied to cancer subtype classification in the past few years, especially of deep learning based approaches. Recently, the deep forest model has been proposed as an alternative of deep neural networks to learn hyper-representations by using cascade ensemble decision trees. It has been proved that the deep forest model has competitive or even better performance than deep neural networks in some extent. However, the standard deep forest model may face overfitting and ensemble diversity challenges when dealing with small sample size and high-dimensional biology data. In this paper, we propose a deep learning model, so-called BCDForest, to address cancer subtype classification on small-scale biology datasets, which can be viewed as a modification of the standard deep forest model. The BCDForest distinguishes from the standard deep forest model with the following two main contributions: First, a named multi-class-grained scanning method is proposed to train multiple binary classifiers to encourage diversity of ensemble. Meanwhile, the fitting quality of each classifier is considered in representation learning. Second, we propose a boosting strategy to emphasize more important features in cascade forests, thus to propagate the benefits of discriminative features among cascade layers to improve the classification performance. Systematic comparison experiments on both microarray and RNA-Seq gene expression datasets demonstrate that our method consistently outperforms the state-of-the-art methods in application of cancer subtype classification. The multi-class-grained scanning and boosting strategy in our model provide an effective solution to ease the overfitting challenge and improve the robustness of deep forest model working on small-scale data. Our model provides a useful approach to the classification of cancer subtypes by using deep learning on high-dimensional and small-scale biology data.

Determination of Minimum Training Sample Size for Microarray-Based Cancer Outcome Prediction–An Empirical Assessment

PubMed Central

Cheng, Ningtao; Wu, Leihong; Cheng, Yiyu

2013-01-01

The promise of microarray technology in providing prediction classifiers for cancer outcome estimation has been confirmed by a number of demonstrable successes. However, the reliability of prediction results relies heavily on the accuracy of statistical parameters involved in classifiers. It cannot be reliably estimated with only a small number of training samples. Therefore, it is of vital importance to determine the minimum number of training samples and to ensure the clinical value of microarrays in cancer outcome prediction. We evaluated the impact of training sample size on model performance extensively based on 3 large-scale cancer microarray datasets provided by the second phase of MicroArray Quality Control project (MAQC-II). An SSNR-based (scale of signal-to-noise ratio) protocol was proposed in this study for minimum training sample size determination. External validation results based on another 3 cancer datasets confirmed that the SSNR-based approach could not only determine the minimum number of training samples efficiently, but also provide a valuable strategy for estimating the underlying performance of classifiers in advance. Once translated into clinical routine applications, the SSNR-based protocol would provide great convenience in microarray-based cancer outcome prediction in improving classifier reliability. PMID:23861920

Deep learning based tissue analysis predicts outcome in colorectal cancer.

PubMed

Bychkov, Dmitrii; Linder, Nina; Turkki, Riku; Nordling, Stig; Kovanen, Panu E; Verrill, Clare; Walliander, Margarita; Lundin, Mikael; Haglund, Caj; Lundin, Johan

2018-02-21

Image-based machine learning and deep learning in particular has recently shown expert-level accuracy in medical image classification. In this study, we combine convolutional and recurrent architectures to train a deep network to predict colorectal cancer outcome based on images of tumour tissue samples. The novelty of our approach is that we directly predict patient outcome, without any intermediate tissue classification. We evaluate a set of digitized haematoxylin-eosin-stained tumour tissue microarray (TMA) samples from 420 colorectal cancer patients with clinicopathological and outcome data available. The results show that deep learning-based outcome prediction with only small tissue areas as input outperforms (hazard ratio 2.3; CI 95% 1.79-3.03; AUC 0.69) visual histological assessment performed by human experts on both TMA spot (HR 1.67; CI 95% 1.28-2.19; AUC 0.58) and whole-slide level (HR 1.65; CI 95% 1.30-2.15; AUC 0.57) in the stratification into low- and high-risk patients. Our results suggest that state-of-the-art deep learning techniques can extract more prognostic information from the tissue morphology of colorectal cancer than an experienced human observer.

Learning a single-hidden layer feedforward neural network using a rank correlation-based strategy with application to high dimensional gene expression and proteomic spectra datasets in cancer detection.

PubMed

Belciug, Smaranda; Gorunescu, Florin

2018-06-08

Methods based on microarrays (MA), mass spectrometry (MS), and machine learning (ML) algorithms have evolved rapidly in recent years, allowing for early detection of several types of cancer. A pitfall of these approaches, however, is the overfitting of data due to large number of attributes and small number of instances -- a phenomenon known as the 'curse of dimensionality'. A potentially fruitful idea to avoid this drawback is to develop algorithms that combine fast computation with a filtering module for the attributes. The goal of this paper is to propose a statistical strategy to initiate the hidden nodes of a single-hidden layer feedforward neural network (SLFN) by using both the knowledge embedded in data and a filtering mechanism for attribute relevance. In order to attest its feasibility, the proposed model has been tested on five publicly available high-dimensional datasets: breast, lung, colon, and ovarian cancer regarding gene expression and proteomic spectra provided by cDNA arrays, DNA microarray, and MS. The novel algorithm, called adaptive SLFN (aSLFN), has been compared with four major classification algorithms: traditional ELM, radial basis function network (RBF), single-hidden layer feedforward neural network trained by backpropagation algorithm (BP-SLFN), and support vector-machine (SVM). Experimental results showed that the classification performance of aSLFN is competitive with the comparison models. Copyright © 2018. Published by Elsevier Inc.

Inference of combinatorial Boolean rules of synergistic gene sets from cancer microarray datasets.

PubMed

Park, Inho; Lee, Kwang H; Lee, Doheon

2010-06-15

Gene set analysis has become an important tool for the functional interpretation of high-throughput gene expression datasets. Moreover, pattern analyses based on inferred gene set activities of individual samples have shown the ability to identify more robust disease signatures than individual gene-based pattern analyses. Although a number of approaches have been proposed for gene set-based pattern analysis, the combinatorial influence of deregulated gene sets on disease phenotype classification has not been studied sufficiently. We propose a new approach for inferring combinatorial Boolean rules of gene sets for a better understanding of cancer transcriptome and cancer classification. To reduce the search space of the possible Boolean rules, we identify small groups of gene sets that synergistically contribute to the classification of samples into their corresponding phenotypic groups (such as normal and cancer). We then measure the significance of the candidate Boolean rules derived from each group of gene sets; the level of significance is based on the class entropy of the samples selected in accordance with the rules. By applying the present approach to publicly available prostate cancer datasets, we identified 72 significant Boolean rules. Finally, we discuss several identified Boolean rules, such as the rule of glutathione metabolism (down) and prostaglandin synthesis regulation (down), which are consistent with known prostate cancer biology. Scripts written in Python and R are available at http://biosoft.kaist.ac.kr/~ihpark/. The refined gene sets and the full list of the identified Boolean rules are provided in the Supplementary Material. Supplementary data are available at Bioinformatics online.

Multiclass classification of microarray data samples with a reduced number of genes

PubMed Central

2011-01-01

Background Multiclass classification of microarray data samples with a reduced number of genes is a rich and challenging problem in Bioinformatics research. The problem gets harder as the number of classes is increased. In addition, the performance of most classifiers is tightly linked to the effectiveness of mandatory gene selection methods. Critical to gene selection is the availability of estimates about the maximum number of genes that can be handled by any classification algorithm. Lack of such estimates may lead to either computationally demanding explorations of a search space with thousands of dimensions or classification models based on gene sets of unrestricted size. In the former case, unbiased but possibly overfitted classification models may arise. In the latter case, biased classification models unable to support statistically significant findings may be obtained. Results A novel bound on the maximum number of genes that can be handled by binary classifiers in binary mediated multiclass classification algorithms of microarray data samples is presented. The bound suggests that high-dimensional binary output domains might favor the existence of accurate and sparse binary mediated multiclass classifiers for microarray data samples. Conclusions A comprehensive experimental work shows that the bound is indeed useful to induce accurate and sparse multiclass classifiers for microarray data samples. PMID:21342522

Validation of the Lung Subtyping Panel in Multiple Fresh-Frozen and Formalin-Fixed, Paraffin-Embedded Lung Tumor Gene Expression Data Sets.

PubMed

Faruki, Hawazin; Mayhew, Gregory M; Fan, Cheng; Wilkerson, Matthew D; Parker, Scott; Kam-Morgan, Lauren; Eisenberg, Marcia; Horten, Bruce; Hayes, D Neil; Perou, Charles M; Lai-Goldman, Myla

2016-06-01

Context .- A histologic classification of lung cancer subtypes is essential in guiding therapeutic management. Objective .- To complement morphology-based classification of lung tumors, a previously developed lung subtyping panel (LSP) of 57 genes was tested using multiple public fresh-frozen gene-expression data sets and a prospectively collected set of formalin-fixed, paraffin-embedded lung tumor samples. Design .- The LSP gene-expression signature was evaluated in multiple lung cancer gene-expression data sets totaling 2177 patients collected from 4 platforms: Illumina RNAseq (San Diego, California), Agilent (Santa Clara, California) and Affymetrix (Santa Clara) microarrays, and quantitative reverse transcription-polymerase chain reaction. Gene centroids were calculated for each of 3 genomic-defined subtypes: adenocarcinoma, squamous cell carcinoma, and neuroendocrine, the latter of which encompassed both small cell carcinoma and carcinoid. Classification by LSP into 3 subtypes was evaluated in both fresh-frozen and formalin-fixed, paraffin-embedded tumor samples, and agreement with the original morphology-based diagnosis was determined. Results .- The LSP-based classifications demonstrated overall agreement with the original clinical diagnosis ranging from 78% (251 of 322) to 91% (492 of 538 and 869 of 951) in the fresh-frozen public data sets and 84% (65 of 77) in the formalin-fixed, paraffin-embedded data set. The LSP performance was independent of tissue-preservation method and gene-expression platform. Secondary, blinded pathology review of formalin-fixed, paraffin-embedded samples demonstrated concordance of 82% (63 of 77) with the original morphology diagnosis. Conclusions .- The LSP gene-expression signature is a reproducible and objective method for classifying lung tumors and demonstrates good concordance with morphology-based classification across multiple data sets. The LSP panel can supplement morphologic assessment of lung cancers, particularly when classification by standard methods is challenging.

A Java-based tool for the design of classification microarrays.

PubMed

Meng, Da; Broschat, Shira L; Call, Douglas R

2008-08-04

Classification microarrays are used for purposes such as identifying strains of bacteria and determining genetic relationships to understand the epidemiology of an infectious disease. For these cases, mixed microarrays, which are composed of DNA from more than one organism, are more effective than conventional microarrays composed of DNA from a single organism. Selection of probes is a key factor in designing successful mixed microarrays because redundant sequences are inefficient and limited representation of diversity can restrict application of the microarray. We have developed a Java-based software tool, called PLASMID, for use in selecting the minimum set of probe sequences needed to classify different groups of plasmids or bacteria. The software program was successfully applied to several different sets of data. The utility of PLASMID was illustrated using existing mixed-plasmid microarray data as well as data from a virtual mixed-genome microarray constructed from different strains of Streptococcus. Moreover, use of data from expression microarray experiments demonstrated the generality of PLASMID. In this paper we describe a new software tool for selecting a set of probes for a classification microarray. While the tool was developed for the design of mixed microarrays-and mixed-plasmid microarrays in particular-it can also be used to design expression arrays. The user can choose from several clustering methods (including hierarchical, non-hierarchical, and a model-based genetic algorithm), several probe ranking methods, and several different display methods. A novel approach is used for probe redundancy reduction, and probe selection is accomplished via stepwise discriminant analysis. Data can be entered in different formats (including Excel and comma-delimited text), and dendrogram, heat map, and scatter plot images can be saved in several different formats (including jpeg and tiff). Weights generated using stepwise discriminant analysis can be stored for analysis of subsequent experimental data. Additionally, PLASMID can be used to construct virtual microarrays with genomes from public databases, which can then be used to identify an optimal set of probes.

A comparative analysis of swarm intelligence techniques for feature selection in cancer classification.

PubMed

Gunavathi, Chellamuthu; Premalatha, Kandasamy

2014-01-01

Feature selection in cancer classification is a central area of research in the field of bioinformatics and used to select the informative genes from thousands of genes of the microarray. The genes are ranked based on T-statistics, signal-to-noise ratio (SNR), and F-test values. The swarm intelligence (SI) technique finds the informative genes from the top-m ranked genes. These selected genes are used for classification. In this paper the shuffled frog leaping with Lévy flight (SFLLF) is proposed for feature selection. In SFLLF, the Lévy flight is included to avoid premature convergence of shuffled frog leaping (SFL) algorithm. The SI techniques such as particle swarm optimization (PSO), cuckoo search (CS), SFL, and SFLLF are used for feature selection which identifies informative genes for classification. The k-nearest neighbour (k-NN) technique is used to classify the samples. The proposed work is applied on 10 different benchmark datasets and examined with SI techniques. The experimental results show that the results obtained from k-NN classifier through SFLLF feature selection method outperform PSO, CS, and SFL.

Classification of ductal carcinoma in situ by gene expression profiling.

PubMed

Hannemann, Juliane; Velds, Arno; Halfwerk, Johannes B G; Kreike, Bas; Peterse, Johannes L; van de Vijver, Marc J

2006-01-01

Ductal carcinoma in situ (DCIS) is characterised by the intraductal proliferation of malignant epithelial cells. Several histological classification systems have been developed, but assessing the histological type/grade of DCIS lesions is still challenging, making treatment decisions based on these features difficult. To obtain insight in the molecular basis of the development of different types of DCIS and its progression to invasive breast cancer, we have studied differences in gene expression between different types of DCIS and between DCIS and invasive breast carcinomas. Gene expression profiling using microarray analysis has been performed on 40 in situ and 40 invasive breast cancer cases. DCIS cases were classified as well- (n = 6), intermediately (n = 18), and poorly (n = 14) differentiated type. Of the 40 invasive breast cancer samples, five samples were grade I, 11 samples were grade II, and 24 samples were grade III. Using two-dimensional hierarchical clustering, the basal-like type, ERB-B2 type, and the luminal-type tumours originally described for invasive breast cancer could also be identified in DCIS. Using supervised classification, we identified a gene expression classifier of 35 genes, which differed between DCIS and invasive breast cancer; a classifier of 43 genes could be identified separating between well- and poorly differentiated DCIS samples.

Classification of ductal carcinoma in situ by gene expression profiling

PubMed Central

Hannemann, Juliane; Velds, Arno; Halfwerk, Johannes BG; Kreike, Bas; Peterse, Johannes L; van de Vijver, Marc J

2006-01-01

Introduction Ductal carcinoma in situ (DCIS) is characterised by the intraductal proliferation of malignant epithelial cells. Several histological classification systems have been developed, but assessing the histological type/grade of DCIS lesions is still challenging, making treatment decisions based on these features difficult. To obtain insight in the molecular basis of the development of different types of DCIS and its progression to invasive breast cancer, we have studied differences in gene expression between different types of DCIS and between DCIS and invasive breast carcinomas. Methods Gene expression profiling using microarray analysis has been performed on 40 in situ and 40 invasive breast cancer cases. Results DCIS cases were classified as well- (n = 6), intermediately (n = 18), and poorly (n = 14) differentiated type. Of the 40 invasive breast cancer samples, five samples were grade I, 11 samples were grade II, and 24 samples were grade III. Using two-dimensional hierarchical clustering, the basal-like type, ERB-B2 type, and the luminal-type tumours originally described for invasive breast cancer could also be identified in DCIS. Conclusion Using supervised classification, we identified a gene expression classifier of 35 genes, which differed between DCIS and invasive breast cancer; a classifier of 43 genes could be identified separating between well- and poorly differentiated DCIS samples. PMID:17069663

SoFoCles: feature filtering for microarray classification based on gene ontology.

PubMed

Papachristoudis, Georgios; Diplaris, Sotiris; Mitkas, Pericles A

2010-02-01

Marker gene selection has been an important research topic in the classification analysis of gene expression data. Current methods try to reduce the "curse of dimensionality" by using statistical intra-feature set calculations, or classifiers that are based on the given dataset. In this paper, we present SoFoCles, an interactive tool that enables semantic feature filtering in microarray classification problems with the use of external, well-defined knowledge retrieved from the Gene Ontology. The notion of semantic similarity is used to derive genes that are involved in the same biological path during the microarray experiment, by enriching a feature set that has been initially produced with legacy methods. Among its other functionalities, SoFoCles offers a large repository of semantic similarity methods that are used in order to derive feature sets and marker genes. The structure and functionality of the tool are discussed in detail, as well as its ability to improve classification accuracy. Through experimental evaluation, SoFoCles is shown to outperform other classification schemes in terms of classification accuracy in two real datasets using different semantic similarity computation approaches.

A comprehensive simulation study on classification of RNA-Seq data.

PubMed

Zararsız, Gökmen; Goksuluk, Dincer; Korkmaz, Selcuk; Eldem, Vahap; Zararsiz, Gozde Erturk; Duru, Izzet Parug; Ozturk, Ahmet

2017-01-01

RNA sequencing (RNA-Seq) is a powerful technique for the gene-expression profiling of organisms that uses the capabilities of next-generation sequencing technologies. Developing gene-expression-based classification algorithms is an emerging powerful method for diagnosis, disease classification and monitoring at molecular level, as well as providing potential markers of diseases. Most of the statistical methods proposed for the classification of gene-expression data are either based on a continuous scale (eg. microarray data) or require a normal distribution assumption. Hence, these methods cannot be directly applied to RNA-Seq data since they violate both data structure and distributional assumptions. However, it is possible to apply these algorithms with appropriate modifications to RNA-Seq data. One way is to develop count-based classifiers, such as Poisson linear discriminant analysis and negative binomial linear discriminant analysis. Another way is to bring the data closer to microarrays and apply microarray-based classifiers. In this study, we compared several classifiers including PLDA with and without power transformation, NBLDA, single SVM, bagging SVM (bagSVM), classification and regression trees (CART), and random forests (RF). We also examined the effect of several parameters such as overdispersion, sample size, number of genes, number of classes, differential-expression rate, and the transformation method on model performances. A comprehensive simulation study is conducted and the results are compared with the results of two miRNA and two mRNA experimental datasets. The results revealed that increasing the sample size, differential-expression rate and decreasing the dispersion parameter and number of groups lead to an increase in classification accuracy. Similar with differential-expression studies, the classification of RNA-Seq data requires careful attention when handling data overdispersion. We conclude that, as a count-based classifier, the power transformed PLDA and, as a microarray-based classifier, vst or rlog transformed RF and SVM classifiers may be a good choice for classification. An R/BIOCONDUCTOR package, MLSeq, is freely available at https://www.bioconductor.org/packages/release/bioc/html/MLSeq.html.

Fuzzy support vector machine for microarray imbalanced data classification

NASA Astrophysics Data System (ADS)

Ladayya, Faroh; Purnami, Santi Wulan; Irhamah

2017-11-01

DNA microarrays are data containing gene expression with small sample sizes and high number of features. Furthermore, imbalanced classes is a common problem in microarray data. This occurs when a dataset is dominated by a class which have significantly more instances than the other minority classes. Therefore, it is needed a classification method that solve the problem of high dimensional and imbalanced data. Support Vector Machine (SVM) is one of the classification methods that is capable of handling large or small samples, nonlinear, high dimensional, over learning and local minimum issues. SVM has been widely applied to DNA microarray data classification and it has been shown that SVM provides the best performance among other machine learning methods. However, imbalanced data will be a problem because SVM treats all samples in the same importance thus the results is bias for minority class. To overcome the imbalanced data, Fuzzy SVM (FSVM) is proposed. This method apply a fuzzy membership to each input point and reformulate the SVM such that different input points provide different contributions to the classifier. The minority classes have large fuzzy membership so FSVM can pay more attention to the samples with larger fuzzy membership. Given DNA microarray data is a high dimensional data with a very large number of features, it is necessary to do feature selection first using Fast Correlation based Filter (FCBF). In this study will be analyzed by SVM, FSVM and both methods by applying FCBF and get the classification performance of them. Based on the overall results, FSVM on selected features has the best classification performance compared to SVM.

LS Bound based gene selection for DNA microarray data.

PubMed

Zhou, Xin; Mao, K Z

2005-04-15

One problem with discriminant analysis of DNA microarray data is that each sample is represented by quite a large number of genes, and many of them are irrelevant, insignificant or redundant to the discriminant problem at hand. Methods for selecting important genes are, therefore, of much significance in microarray data analysis. In the present study, a new criterion, called LS Bound measure, is proposed to address the gene selection problem. The LS Bound measure is derived from leave-one-out procedure of LS-SVMs (least squares support vector machines), and as the upper bound for leave-one-out classification results it reflects to some extent the generalization performance of gene subsets. We applied this LS Bound measure for gene selection on two benchmark microarray datasets: colon cancer and leukemia. We also compared the LS Bound measure with other evaluation criteria, including the well-known Fisher's ratio and Mahalanobis class separability measure, and other published gene selection algorithms, including Weighting factor and SVM Recursive Feature Elimination. The strength of the LS Bound measure is that it provides gene subsets leading to more accurate classification results than the filter method while its computational complexity is at the level of the filter method. A companion website can be accessed at http://www.ntu.edu.sg/home5/pg02776030/lsbound/. The website contains: (1) the source code of the gene selection algorithm; (2) the complete set of tables and figures regarding the experimental study; (3) proof of the inequality (9). ekzmao@ntu.edu.sg.

Compact cancer biomarkers discovery using a swarm intelligence feature selection algorithm.

PubMed

Martinez, Emmanuel; Alvarez, Mario Moises; Trevino, Victor

2010-08-01

Biomarker discovery is a typical application from functional genomics. Due to the large number of genes studied simultaneously in microarray data, feature selection is a key step. Swarm intelligence has emerged as a solution for the feature selection problem. However, swarm intelligence settings for feature selection fail to select small features subsets. We have proposed a swarm intelligence feature selection algorithm based on the initialization and update of only a subset of particles in the swarm. In this study, we tested our algorithm in 11 microarray datasets for brain, leukemia, lung, prostate, and others. We show that the proposed swarm intelligence algorithm successfully increase the classification accuracy and decrease the number of selected features compared to other swarm intelligence methods. Copyright © 2010 Elsevier Ltd. All rights reserved.

Improved Sparse Multi-Class SVM and Its Application for Gene Selection in Cancer Classification

PubMed Central

Huang, Lingkang; Zhang, Hao Helen; Zeng, Zhao-Bang; Bushel, Pierre R.

2013-01-01

Background Microarray techniques provide promising tools for cancer diagnosis using gene expression profiles. However, molecular diagnosis based on high-throughput platforms presents great challenges due to the overwhelming number of variables versus the small sample size and the complex nature of multi-type tumors. Support vector machines (SVMs) have shown superior performance in cancer classification due to their ability to handle high dimensional low sample size data. The multi-class SVM algorithm of Crammer and Singer provides a natural framework for multi-class learning. Despite its effective performance, the procedure utilizes all variables without selection. In this paper, we propose to improve the procedure by imposing shrinkage penalties in learning to enforce solution sparsity. Results The original multi-class SVM of Crammer and Singer is effective for multi-class classification but does not conduct variable selection. We improved the method by introducing soft-thresholding type penalties to incorporate variable selection into multi-class classification for high dimensional data. The new methods were applied to simulated data and two cancer gene expression data sets. The results demonstrate that the new methods can select a small number of genes for building accurate multi-class classification rules. Furthermore, the important genes selected by the methods overlap significantly, suggesting general agreement among different variable selection schemes. Conclusions High accuracy and sparsity make the new methods attractive for cancer diagnostics with gene expression data and defining targets of therapeutic intervention. Availability: The source MATLAB code are available from http://math.arizona.edu/~hzhang/software.html. PMID:23966761

Identifying molecular features for prostate cancer with Gleason 7 based on microarray gene expression profiles.

PubMed

Bălăcescu, Loredana; Bălăcescu, O; Crişan, N; Fetica, B; Petruţ, B; Bungărdean, Cătălina; Rus, Meda; Tudoran, Oana; Meurice, G; Irimie, Al; Dragoş, N; Berindan-Neagoe, Ioana

2011-01-01

Prostate cancer represents the first leading cause of cancer among western male population, with different clinical behavior ranging from indolent to metastatic disease. Although many molecules and deregulated pathways are known, the molecular mechanisms involved in the development of prostate cancer are not fully understood. The aim of this study was to explore the molecular variation underlying the prostate cancer, based on microarray analysis and bioinformatics approaches. Normal and prostate cancer tissues were collected by macrodissection from prostatectomy pieces. All prostate cancer specimens used in our study were Gleason score 7. Gene expression microarray (Agilent Technologies) was used for Whole Human Genome evaluation. The bioinformatics and functional analysis were based on Limma and Ingenuity software. The microarray analysis identified 1119 differentially expressed genes between prostate cancer and normal prostate, which were up- or down-regulated at least 2-fold. P-values were adjusted for multiple testing using Benjamini-Hochberg method with a false discovery rate of 0.01. These genes were analyzed with Ingenuity Pathway Analysis software and were established 23 genetic networks. Our microarray results provide new information regarding the molecular networks in prostate cancer stratified as Gleason 7. These data highlighted gene expression profiles for better understanding of prostate cancer progression.

Use of Attribute Driven Incremental Discretization and Logic Learning Machine to build a prognostic classifier for neuroblastoma patients.

PubMed

Cangelosi, Davide; Muselli, Marco; Parodi, Stefano; Blengio, Fabiola; Becherini, Pamela; Versteeg, Rogier; Conte, Massimo; Varesio, Luigi

2014-01-01

Cancer patient's outcome is written, in part, in the gene expression profile of the tumor. We previously identified a 62-probe sets signature (NB-hypo) to identify tissue hypoxia in neuroblastoma tumors and showed that NB-hypo stratified neuroblastoma patients in good and poor outcome 1. It was important to develop a prognostic classifier to cluster patients into risk groups benefiting of defined therapeutic approaches. Novel classification and data discretization approaches can be instrumental for the generation of accurate predictors and robust tools for clinical decision support. We explored the application to gene expression data of Rulex, a novel software suite including the Attribute Driven Incremental Discretization technique for transforming continuous variables into simplified discrete ones and the Logic Learning Machine model for intelligible rule generation. We applied Rulex components to the problem of predicting the outcome of neuroblastoma patients on the bases of 62 probe sets NB-hypo gene expression signature. The resulting classifier consisted in 9 rules utilizing mainly two conditions of the relative expression of 11 probe sets. These rules were very effective predictors, as shown in an independent validation set, demonstrating the validity of the LLM algorithm applied to microarray data and patients' classification. The LLM performed as efficiently as Prediction Analysis of Microarray and Support Vector Machine, and outperformed other learning algorithms such as C4.5. Rulex carried out a feature selection by selecting a new signature (NB-hypo-II) of 11 probe sets that turned out to be the most relevant in predicting outcome among the 62 of the NB-hypo signature. Rules are easily interpretable as they involve only few conditions. Our findings provided evidence that the application of Rulex to the expression values of NB-hypo signature created a set of accurate, high quality, consistent and interpretable rules for the prediction of neuroblastoma patients' outcome. We identified the Rulex weighted classification as a flexible tool that can support clinical decisions. For these reasons, we consider Rulex to be a useful tool for cancer classification from microarray gene expression data.

Multiple biomarkers in molecular oncology. II. Molecular diagnostics applications in breast cancer management.

PubMed

Malinowski, Douglas P

2007-05-01

In recent years, the application of genomic and proteomic technologies to the problem of breast cancer prognosis and the prediction of therapy response have begun to yield encouraging results. Independent studies employing transcriptional profiling of primary breast cancer specimens using DNA microarrays have identified gene expression profiles that correlate with clinical outcome in primary breast biopsy specimens. Recent advances in microarray technology have demonstrated reproducibility, making clinical applications more achievable. In this regard, one such DNA microarray device based upon a 70-gene expression signature was recently cleared by the US FDA for application to breast cancer prognosis. These DNA microarrays often employ at least 70 gene targets for transcriptional profiling and prognostic assessment in breast cancer. The use of PCR-based methods utilizing a small subset of genes has recently demonstrated the ability to predict the clinical outcome in early-stage breast cancer. Furthermore, protein-based immunohistochemistry methods have progressed from using gene clusters and gene expression profiling to smaller subsets of expressed proteins to predict prognosis in early-stage breast cancer. Beyond prognostic applications, DNA microarray-based transcriptional profiling has demonstrated the ability to predict response to chemotherapy in early-stage breast cancer patients. In this review, recent advances in the use of multiple markers for prognosis of disease recurrence in early-stage breast cancer and the prediction of therapy response will be discussed.

Methylation-Sensitive Amplification Length Polymorphism (MS-AFLP) Microarrays for Epigenetic Analysis of Human Genomes.

PubMed

Alonso, Sergio; Suzuki, Koichi; Yamamoto, Fumiichiro; Perucho, Manuel

2018-01-01

Somatic, and in a minor scale also germ line, epigenetic aberrations are fundamental to carcinogenesis, cancer progression, and tumor phenotype. DNA methylation is the most extensively studied and arguably the best understood epigenetic mechanisms that become altered in cancer. Both somatic loss of methylation (hypomethylation) and gain of methylation (hypermethylation) are found in the genome of malignant cells. In general, the cancer cell epigenome is globally hypomethylated, while some regions-typically gene-associated CpG islands-become hypermethylated. Given the profound impact that DNA methylation exerts on the transcriptional profile and genomic stability of cancer cells, its characterization is essential to fully understand the complexity of cancer biology, improve tumor classification, and ultimately advance cancer patient management and treatment. A plethora of methods have been devised to analyze and quantify DNA methylation alterations. Several of the early-developed methods relied on the use of methylation-sensitive restriction enzymes, whose activity depends on the methylation status of their recognition sequences. Among these techniques, methylation-sensitive amplification length polymorphism (MS-AFLP) was developed in the early 2000s, and successfully adapted from its original gel electrophoresis fingerprinting format to a microarray format that notably increased its throughput and allowed the quantification of the methylation changes. This array-based platform interrogates over 9500 independent loci putatively amplified by the MS-AFLP technique, corresponding to the NotI sites mapped throughout the human genome.

Identifying differentially expressed genes in cancer patients using a non-parameter Ising model.

PubMed

Li, Xumeng; Feltus, Frank A; Sun, Xiaoqian; Wang, James Z; Luo, Feng

2011-10-01

Identification of genes and pathways involved in diseases and physiological conditions is a major task in systems biology. In this study, we developed a novel non-parameter Ising model to integrate protein-protein interaction network and microarray data for identifying differentially expressed (DE) genes. We also proposed a simulated annealing algorithm to find the optimal configuration of the Ising model. The Ising model was applied to two breast cancer microarray data sets. The results showed that more cancer-related DE sub-networks and genes were identified by the Ising model than those by the Markov random field model. Furthermore, cross-validation experiments showed that DE genes identified by Ising model can improve classification performance compared with DE genes identified by Markov random field model. Copyright © 2011 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

Robust diagnosis of non-Hodgkin lymphoma phenotypes validated on gene expression data from different laboratories.

PubMed

Bhanot, Gyan; Alexe, Gabriela; Levine, Arnold J; Stolovitzky, Gustavo

2005-01-01

A major challenge in cancer diagnosis from microarray data is the need for robust, accurate, classification models which are independent of the analysis techniques used and can combine data from different laboratories. We propose such a classification scheme originally developed for phenotype identification from mass spectrometry data. The method uses a robust multivariate gene selection procedure and combines the results of several machine learning tools trained on raw and pattern data to produce an accurate meta-classifier. We illustrate and validate our method by applying it to gene expression datasets: the oligonucleotide HuGeneFL microarray dataset of Shipp et al. (www.genome.wi.mit.du/MPR/lymphoma) and the Hu95Av2 Affymetrix dataset (DallaFavera's laboratory, Columbia University). Our pattern-based meta-classification technique achieves higher predictive accuracies than each of the individual classifiers , is robust against data perturbations and provides subsets of related predictive genes. Our techniques predict that combinations of some genes in the p53 pathway are highly predictive of phenotype. In particular, we find that in 80% of DLBCL cases the mRNA level of at least one of the three genes p53, PLK1 and CDK2 is elevated, while in 80% of FL cases, the mRNA level of at most one of them is elevated.

Classification of intramural metastases and lymph node metastases of esophageal cancer from gene expression based on boosting and projective adaptive resonance theory.

PubMed

Takahashi, Hiro; Aoyagi, Kazuhiko; Nakanishi, Yukihiro; Sasaki, Hiroki; Yoshida, Teruhiko; Honda, Hiroyuki

2006-07-01

Esophageal cancer is a well-known cancer with poorer prognosis than other cancers. An optimal and individualized treatment protocol based on accurate diagnosis is urgently needed to improve the treatment of cancer patients. For this purpose, it is important to develop a sophisticated algorithm that can manage a large amount of data, such as gene expression data from DNA microarrays, for optimal and individualized diagnosis. Marker gene selection is essential in the analysis of gene expression data. We have already developed a combination method of the use of the projective adaptive resonance theory and that of a boosted fuzzy classifier with the SWEEP operator denoted PART-BFCS. This method is superior to other methods, and has four features, namely fast calculation, accurate prediction, reliable prediction, and rule extraction. In this study, we applied this method to analyze microarray data obtained from esophageal cancer patients. A combination method of PART-BFCS and the U-test was also investigated. It was necessary to use a specific type of BFCS, namely, BFCS-1,2, because the esophageal cancer data were very complexity. PART-BFCS and PART-BFCS with the U-test models showed higher performances than two conventional methods, namely, k-nearest neighbor (kNN) and weighted voting (WV). The genes including CDK6 could be found by our methods and excellent IF-THEN rules could be extracted. The genes selected in this study have a high potential as new diagnosis markers for esophageal cancer. These results indicate that the new methods can be used in marker gene selection for the diagnosis of cancer patients.

Comparative study of joint analysis of microarray gene expression data in survival prediction and risk assessment of breast cancer patients

PubMed Central

2016-01-01

Abstract Microarray gene expression data sets are jointly analyzed to increase statistical power. They could either be merged together or analyzed by meta-analysis. For a given ensemble of data sets, it cannot be foreseen which of these paradigms, merging or meta-analysis, works better. In this article, three joint analysis methods, Z -score normalization, ComBat and the inverse normal method (meta-analysis) were selected for survival prognosis and risk assessment of breast cancer patients. The methods were applied to eight microarray gene expression data sets, totaling 1324 patients with two clinical endpoints, overall survival and relapse-free survival. The performance derived from the joint analysis methods was evaluated using Cox regression for survival analysis and independent validation used as bias estimation. Overall, Z -score normalization had a better performance than ComBat and meta-analysis. Higher Area Under the Receiver Operating Characteristic curve and hazard ratio were also obtained when independent validation was used as bias estimation. With a lower time and memory complexity, Z -score normalization is a simple method for joint analysis of microarray gene expression data sets. The derived findings suggest further assessment of this method in future survival prediction and cancer classification applications. PMID:26504096

Identifying predictive features in drug response using machine learning: opportunities and challenges.

PubMed

Vidyasagar, Mathukumalli

2015-01-01

This article reviews several techniques from machine learning that can be used to study the problem of identifying a small number of features, from among tens of thousands of measured features, that can accurately predict a drug response. Prediction problems are divided into two categories: sparse classification and sparse regression. In classification, the clinical parameter to be predicted is binary, whereas in regression, the parameter is a real number. Well-known methods for both classes of problems are briefly discussed. These include the SVM (support vector machine) for classification and various algorithms such as ridge regression, LASSO (least absolute shrinkage and selection operator), and EN (elastic net) for regression. In addition, several well-established methods that do not directly fall into machine learning theory are also reviewed, including neural networks, PAM (pattern analysis for microarrays), SAM (significance analysis for microarrays), GSEA (gene set enrichment analysis), and k-means clustering. Several references indicative of the application of these methods to cancer biology are discussed.

Molecular classification and molecular forecasting of breast cancer: ready for clinical application?

PubMed

Brenton, James D; Carey, Lisa A; Ahmed, Ahmed Ashour; Caldas, Carlos

2005-10-10

Profiling breast cancer with expression arrays has become common, and it has been suggested that the results from early studies will lead to understanding of the molecular differences between clinical cases and allow individualization of care. We critically review two main applications of expression profiling; studies unraveling novel breast cancer classifications and those that aim to identify novel markers for prediction of clinical outcome. Breast cancer may now be subclassified into luminal, basal, and HER2 subtypes with distinct differences in prognosis and response to therapy. However, profiling studies to identify predictive markers have suffered from methodologic problems that prevent general application of their results. Future work will need to reanalyze existing microarray data sets to identify more representative sets of candidate genes for use as prognostic signatures and will need to take into account the new knowledge of molecular subtypes of breast cancer when assessing predictive effects.

Multiple Biomarker Panels for Early Detection of Breast Cancer in Peripheral Blood

PubMed Central

Zhang, Fan; Deng, Youping; Drabier, Renee

2013-01-01

Detecting breast cancer at early stages can be challenging. Traditional mammography and tissue microarray that have been studied for early breast cancer detection and prediction have many drawbacks. Therefore, there is a need for more reliable diagnostic tools for early detection of breast cancer due to a number of factors and challenges. In the paper, we presented a five-marker panel approach based on SVM for early detection of breast cancer in peripheral blood and show how to use SVM to model the classification and prediction problem of early detection of breast cancer in peripheral blood. We found that the five-marker panel can improve the prediction performance (area under curve) in the testing data set from 0.5826 to 0.7879. Further pathway analysis showed that the top four five-marker panels are associated with signaling, steroid hormones, metabolism, immune system, and hemostasis, which are consistent with previous findings. Our prediction model can serve as a general model for multibiomarker panel discovery in early detection of other cancers. PMID:24371830

Multiple biomarker panels for early detection of breast cancer in peripheral blood.

PubMed

Zhang, Fan; Deng, Youping; Drabier, Renee

2013-01-01

Detecting breast cancer at early stages can be challenging. Traditional mammography and tissue microarray that have been studied for early breast cancer detection and prediction have many drawbacks. Therefore, there is a need for more reliable diagnostic tools for early detection of breast cancer due to a number of factors and challenges. In the paper, we presented a five-marker panel approach based on SVM for early detection of breast cancer in peripheral blood and show how to use SVM to model the classification and prediction problem of early detection of breast cancer in peripheral blood. We found that the five-marker panel can improve the prediction performance (area under curve) in the testing data set from 0.5826 to 0.7879. Further pathway analysis showed that the top four five-marker panels are associated with signaling, steroid hormones, metabolism, immune system, and hemostasis, which are consistent with previous findings. Our prediction model can serve as a general model for multibiomarker panel discovery in early detection of other cancers.

Cancer Biomarkers from Genome-Scale DNA Methylation: Comparison of Evolutionary and Semantic Analysis Methods

PubMed Central

Valavanis, Ioannis; Pilalis, Eleftherios; Georgiadis, Panagiotis; Kyrtopoulos, Soterios; Chatziioannou, Aristotelis

2015-01-01

DNA methylation profiling exploits microarray technologies, thus yielding a wealth of high-volume data. Here, an intelligent framework is applied, encompassing epidemiological genome-scale DNA methylation data produced from the Illumina’s Infinium Human Methylation 450K Bead Chip platform, in an effort to correlate interesting methylation patterns with cancer predisposition and, in particular, breast cancer and B-cell lymphoma. Feature selection and classification are employed in order to select, from an initial set of ~480,000 methylation measurements at CpG sites, predictive cancer epigenetic biomarkers and assess their classification power for discriminating healthy versus cancer related classes. Feature selection exploits evolutionary algorithms or a graph-theoretic methodology which makes use of the semantics information included in the Gene Ontology (GO) tree. The selected features, corresponding to methylation of CpG sites, attained moderate-to-high classification accuracies when imported to a series of classifiers evaluated by resampling or blindfold validation. The semantics-driven selection revealed sets of CpG sites performing similarly with evolutionary selection in the classification tasks. However, gene enrichment and pathway analysis showed that it additionally provides more descriptive sets of GO terms and KEGG pathways regarding the cancer phenotypes studied here. Results support the expediency of this methodology regarding its application in epidemiological studies. PMID:27600245

A consensus prognostic gene expression classifier for ER positive breast cancer

PubMed Central

Teschendorff, Andrew E; Naderi, Ali; Barbosa-Morais, Nuno L; Pinder, Sarah E; Ellis, Ian O; Aparicio, Sam; Brenton, James D; Caldas, Carlos

2006-01-01

Background A consensus prognostic gene expression classifier is still elusive in heterogeneous diseases such as breast cancer. Results Here we perform a combined analysis of three major breast cancer microarray data sets to hone in on a universally valid prognostic molecular classifier in estrogen receptor (ER) positive tumors. Using a recently developed robust measure of prognostic separation, we further validate the prognostic classifier in three external independent cohorts, confirming the validity of our molecular classifier in a total of 877 ER positive samples. Furthermore, we find that molecular classifiers may not outperform classical prognostic indices but that they can be used in hybrid molecular-pathological classification schemes to improve prognostic separation. Conclusion The prognostic molecular classifier presented here is the first to be valid in over 877 ER positive breast cancer samples and across three different microarray platforms. Larger multi-institutional studies will be needed to fully determine the added prognostic value of molecular classifiers when combined with standard prognostic factors. PMID:17076897

geneCommittee: a web-based tool for extensively testing the discriminatory power of biologically relevant gene sets in microarray data classification.

PubMed

Reboiro-Jato, Miguel; Arrais, Joel P; Oliveira, José Luis; Fdez-Riverola, Florentino

2014-01-30

The diagnosis and prognosis of several diseases can be shortened through the use of different large-scale genome experiments. In this context, microarrays can generate expression data for a huge set of genes. However, to obtain solid statistical evidence from the resulting data, it is necessary to train and to validate many classification techniques in order to find the best discriminative method. This is a time-consuming process that normally depends on intricate statistical tools. geneCommittee is a web-based interactive tool for routinely evaluating the discriminative classification power of custom hypothesis in the form of biologically relevant gene sets. While the user can work with different gene set collections and several microarray data files to configure specific classification experiments, the tool is able to run several tests in parallel. Provided with a straightforward and intuitive interface, geneCommittee is able to render valuable information for diagnostic analyses and clinical management decisions based on systematically evaluating custom hypothesis over different data sets using complementary classifiers, a key aspect in clinical research. geneCommittee allows the enrichment of microarrays raw data with gene functional annotations, producing integrated datasets that simplify the construction of better discriminative hypothesis, and allows the creation of a set of complementary classifiers. The trained committees can then be used for clinical research and diagnosis. Full documentation including common use cases and guided analysis workflows is freely available at http://sing.ei.uvigo.es/GC/.

GTA: a game theoretic approach to identifying cancer subnetwork markers.

PubMed

Farahmand, S; Goliaei, S; Ansari-Pour, N; Razaghi-Moghadam, Z

2016-03-01

The identification of genetic markers (e.g. genes, pathways and subnetworks) for cancer has been one of the most challenging research areas in recent years. A subset of these studies attempt to analyze genome-wide expression profiles to identify markers with high reliability and reusability across independent whole-transcriptome microarray datasets. Therefore, the functional relationships of genes are integrated with their expression data. However, for a more accurate representation of the functional relationships among genes, utilization of the protein-protein interaction network (PPIN) seems to be necessary. Herein, a novel game theoretic approach (GTA) is proposed for the identification of cancer subnetwork markers by integrating genome-wide expression profiles and PPIN. The GTA method was applied to three distinct whole-transcriptome breast cancer datasets to identify the subnetwork markers associated with metastasis. To evaluate the performance of our approach, the identified subnetwork markers were compared with gene-based, pathway-based and network-based markers. We show that GTA is not only capable of identifying robust metastatic markers, it also provides a higher classification performance. In addition, based on these GTA-based subnetworks, we identified a new bonafide candidate gene for breast cancer susceptibility.

Gene-expression signatures can distinguish gastric cancer grades and stages.

PubMed

Cui, Juan; Li, Fan; Wang, Guoqing; Fang, Xuedong; Puett, J David; Xu, Ying

2011-03-18

Microarray gene-expression data of 54 paired gastric cancer and adjacent noncancerous gastric tissues were analyzed, with the aim to establish gene signatures for cancer grades (well-, moderately-, poorly- or un-differentiated) and stages (I, II, III and IV), which have been determined by pathologists. Our statistical analysis led to the identification of a number of gene combinations whose expression patterns serve well as signatures of different grades and different stages of gastric cancer. A 19-gene signature was found to have discerning power between high- and low-grade gastric cancers in general, with overall classification accuracy at 79.6%. An expanded 198-gene panel allows the stratification of cancers into four grades and control, giving rise to an overall classification agreement of 74.2% between each grade designated by the pathologists and our prediction. Two signatures for cancer staging, consisting of 10 genes and 9 genes, respectively, provide high classification accuracies at 90.0% and 84.0%, among early-, advanced-stage cancer and control. Functional and pathway analyses on these signature genes reveal the significant relevance of the derived signatures to cancer grades and progression. To the best of our knowledge, this represents the first study on identification of genes whose expression patterns can serve as markers for cancer grades and stages.

A fuzzy neural network for intelligent data processing

NASA Astrophysics Data System (ADS)

Xie, Wei; Chu, Feng; Wang, Lipo; Lim, Eng Thiam

2005-03-01

In this paper, we describe an incrementally generated fuzzy neural network (FNN) for intelligent data processing. This FNN combines the features of initial fuzzy model self-generation, fast input selection, partition validation, parameter optimization and rule-base simplification. A small FNN is created from scratch -- there is no need to specify the initial network architecture, initial membership functions, or initial weights. Fuzzy IF-THEN rules are constantly combined and pruned to minimize the size of the network while maintaining accuracy; irrelevant inputs are detected and deleted, and membership functions and network weights are trained with a gradient descent algorithm, i.e., error backpropagation. Experimental studies on synthesized data sets demonstrate that the proposed Fuzzy Neural Network is able to achieve accuracy comparable to or higher than both a feedforward crisp neural network, i.e., NeuroRule, and a decision tree, i.e., C4.5, with more compact rule bases for most of the data sets used in our experiments. The FNN has achieved outstanding results for cancer classification based on microarray data. The excellent classification result for Small Round Blue Cell Tumors (SRBCTs) data set is shown. Compared with other published methods, we have used a much fewer number of genes for perfect classification, which will help researchers directly focus their attention on some specific genes and may lead to discovery of deep reasons of the development of cancers and discovery of drugs.

Screening Mammalian Cells on a Hydrogel: Functionalized Small Molecule Microarray.

PubMed

Zhu, Biwei; Jiang, Bo; Na, Zhenkun; Yao, Shao Q

2017-01-01

Mammalian cell-based microarray technology has gained wide attention, for its plethora of promising applications. The platform is able to provide simultaneous information on multiple parameters for a given target, or even multiple target proteins, in a complex biological system. Here we describe the preparation of mammalian cell-based microarrays using selectively captured of human prostate cancer cells (PC-3). This platform was then used in controlled drug release and measuring the associated drug effects on these cancer cells.

Deep Learning Accurately Predicts Estrogen Receptor Status in Breast Cancer Metabolomics Data.

PubMed

Alakwaa, Fadhl M; Chaudhary, Kumardeep; Garmire, Lana X

2018-01-05

Metabolomics holds the promise as a new technology to diagnose highly heterogeneous diseases. Conventionally, metabolomics data analysis for diagnosis is done using various statistical and machine learning based classification methods. However, it remains unknown if deep neural network, a class of increasingly popular machine learning methods, is suitable to classify metabolomics data. Here we use a cohort of 271 breast cancer tissues, 204 positive estrogen receptor (ER+), and 67 negative estrogen receptor (ER-) to test the accuracies of feed-forward networks, a deep learning (DL) framework, as well as six widely used machine learning models, namely random forest (RF), support vector machines (SVM), recursive partitioning and regression trees (RPART), linear discriminant analysis (LDA), prediction analysis for microarrays (PAM), and generalized boosted models (GBM). DL framework has the highest area under the curve (AUC) of 0.93 in classifying ER+/ER- patients, compared to the other six machine learning algorithms. Furthermore, the biological interpretation of the first hidden layer reveals eight commonly enriched significant metabolomics pathways (adjusted P-value <0.05) that cannot be discovered by other machine learning methods. Among them, protein digestion and absorption and ATP-binding cassette (ABC) transporters pathways are also confirmed in integrated analysis between metabolomics and gene expression data in these samples. In summary, deep learning method shows advantages for metabolomics based breast cancer ER status classification, with both the highest prediction accuracy (AUC = 0.93) and better revelation of disease biology. We encourage the adoption of feed-forward networks based deep learning method in the metabolomics research community for classification.

Evaluation of normalization methods for cDNA microarray data by k-NN classification

PubMed Central

Wu, Wei; Xing, Eric P; Myers, Connie; Mian, I Saira; Bissell, Mina J

2005-01-01

Background Non-biological factors give rise to unwanted variations in cDNA microarray data. There are many normalization methods designed to remove such variations. However, to date there have been few published systematic evaluations of these techniques for removing variations arising from dye biases in the context of downstream, higher-order analytical tasks such as classification. Results Ten location normalization methods that adjust spatial- and/or intensity-dependent dye biases, and three scale methods that adjust scale differences were applied, individually and in combination, to five distinct, published, cancer biology-related cDNA microarray data sets. Leave-one-out cross-validation (LOOCV) classification error was employed as the quantitative end-point for assessing the effectiveness of a normalization method. In particular, a known classifier, k-nearest neighbor (k-NN), was estimated from data normalized using a given technique, and the LOOCV error rate of the ensuing model was computed. We found that k-NN classifiers are sensitive to dye biases in the data. Using NONRM and GMEDIAN as baseline methods, our results show that single-bias-removal techniques which remove either spatial-dependent dye bias (referred later as spatial effect) or intensity-dependent dye bias (referred later as intensity effect) moderately reduce LOOCV classification errors; whereas double-bias-removal techniques which remove both spatial- and intensity effect reduce LOOCV classification errors even further. Of the 41 different strategies examined, three two-step processes, IGLOESS-SLFILTERW7, ISTSPLINE-SLLOESS and IGLOESS-SLLOESS, all of which removed intensity effect globally and spatial effect locally, appear to reduce LOOCV classification errors most consistently and effectively across all data sets. We also found that the investigated scale normalization methods do not reduce LOOCV classification error. Conclusion Using LOOCV error of k-NNs as the evaluation criterion, three double-bias-removal normalization strategies, IGLOESS-SLFILTERW7, ISTSPLINE-SLLOESS and IGLOESS-SLLOESS, outperform other strategies for removing spatial effect, intensity effect and scale differences from cDNA microarray data. The apparent sensitivity of k-NN LOOCV classification error to dye biases suggests that this criterion provides an informative measure for evaluating normalization methods. All the computational tools used in this study were implemented using the R language for statistical computing and graphics. PMID:16045803

Evaluation of normalization methods for cDNA microarray data by k-NN classification.

PubMed

Wu, Wei; Xing, Eric P; Myers, Connie; Mian, I Saira; Bissell, Mina J

2005-07-26

Non-biological factors give rise to unwanted variations in cDNA microarray data. There are many normalization methods designed to remove such variations. However, to date there have been few published systematic evaluations of these techniques for removing variations arising from dye biases in the context of downstream, higher-order analytical tasks such as classification. Ten location normalization methods that adjust spatial- and/or intensity-dependent dye biases, and three scale methods that adjust scale differences were applied, individually and in combination, to five distinct, published, cancer biology-related cDNA microarray data sets. Leave-one-out cross-validation (LOOCV) classification error was employed as the quantitative end-point for assessing the effectiveness of a normalization method. In particular, a known classifier, k-nearest neighbor (k-NN), was estimated from data normalized using a given technique, and the LOOCV error rate of the ensuing model was computed. We found that k-NN classifiers are sensitive to dye biases in the data. Using NONRM and GMEDIAN as baseline methods, our results show that single-bias-removal techniques which remove either spatial-dependent dye bias (referred later as spatial effect) or intensity-dependent dye bias (referred later as intensity effect) moderately reduce LOOCV classification errors; whereas double-bias-removal techniques which remove both spatial- and intensity effect reduce LOOCV classification errors even further. Of the 41 different strategies examined, three two-step processes, IGLOESS-SLFILTERW7, ISTSPLINE-SLLOESS and IGLOESS-SLLOESS, all of which removed intensity effect globally and spatial effect locally, appear to reduce LOOCV classification errors most consistently and effectively across all data sets. We also found that the investigated scale normalization methods do not reduce LOOCV classification error. Using LOOCV error of k-NNs as the evaluation criterion, three double-bias-removal normalization strategies, IGLOESS-SLFILTERW7, ISTSPLINE-SLLOESS and IGLOESS-SLLOESS, outperform other strategies for removing spatial effect, intensity effect and scale differences from cDNA microarray data. The apparent sensitivity of k-NN LOOCV classification error to dye biases suggests that this criterion provides an informative measure for evaluating normalization methods. All the computational tools used in this study were implemented using the R language for statistical computing and graphics.

A Deep Convolutional Neural Network for segmenting and classifying epithelial and stromal regions in histopathological images

PubMed Central

Xu, Jun; Luo, Xiaofei; Wang, Guanhao; Gilmore, Hannah; Madabhushi, Anant

2016-01-01

Epithelial (EP) and stromal (ST) are two types of tissues in histological images. Automated segmentation or classification of EP and ST tissues is important when developing computerized system for analyzing the tumor microenvironment. In this paper, a Deep Convolutional Neural Networks (DCNN) based feature learning is presented to automatically segment or classify EP and ST regions from digitized tumor tissue microarrays (TMAs). Current approaches are based on handcraft feature representation, such as color, texture, and Local Binary Patterns (LBP) in classifying two regions. Compared to handcrafted feature based approaches, which involve task dependent representation, DCNN is an end-to-end feature extractor that may be directly learned from the raw pixel intensity value of EP and ST tissues in a data driven fashion. These high-level features contribute to the construction of a supervised classifier for discriminating the two types of tissues. In this work we compare DCNN based models with three handcraft feature extraction based approaches on two different datasets which consist of 157 Hematoxylin and Eosin (H&E) stained images of breast cancer and 1376 immunohistological (IHC) stained images of colorectal cancer, respectively. The DCNN based feature learning approach was shown to have a F1 classification score of 85%, 89%, and 100%, accuracy (ACC) of 84%, 88%, and 100%, and Matthews Correlation Coefficient (MCC) of 86%, 77%, and 100% on two H&E stained (NKI and VGH) and IHC stained data, respectively. Our DNN based approach was shown to outperform three handcraft feature extraction based approaches in terms of the classification of EP and ST regions. PMID:28154470

A Deep Convolutional Neural Network for segmenting and classifying epithelial and stromal regions in histopathological images.

PubMed

Xu, Jun; Luo, Xiaofei; Wang, Guanhao; Gilmore, Hannah; Madabhushi, Anant

2016-05-26

Epithelial (EP) and stromal (ST) are two types of tissues in histological images. Automated segmentation or classification of EP and ST tissues is important when developing computerized system for analyzing the tumor microenvironment. In this paper, a Deep Convolutional Neural Networks (DCNN) based feature learning is presented to automatically segment or classify EP and ST regions from digitized tumor tissue microarrays (TMAs). Current approaches are based on handcraft feature representation, such as color, texture, and Local Binary Patterns (LBP) in classifying two regions. Compared to handcrafted feature based approaches, which involve task dependent representation, DCNN is an end-to-end feature extractor that may be directly learned from the raw pixel intensity value of EP and ST tissues in a data driven fashion. These high-level features contribute to the construction of a supervised classifier for discriminating the two types of tissues. In this work we compare DCNN based models with three handcraft feature extraction based approaches on two different datasets which consist of 157 Hematoxylin and Eosin (H&E) stained images of breast cancer and 1376 immunohistological (IHC) stained images of colorectal cancer, respectively. The DCNN based feature learning approach was shown to have a F1 classification score of 85%, 89%, and 100%, accuracy (ACC) of 84%, 88%, and 100%, and Matthews Correlation Coefficient (MCC) of 86%, 77%, and 100% on two H&E stained (NKI and VGH) and IHC stained data, respectively. Our DNN based approach was shown to outperform three handcraft feature extraction based approaches in terms of the classification of EP and ST regions.

Implementation of spectral clustering with partitioning around medoids (PAM) algorithm on microarray data of carcinoma

NASA Astrophysics Data System (ADS)

Cahyaningrum, Rosalia D.; Bustamam, Alhadi; Siswantining, Titin

2017-03-01

Technology of microarray became one of the imperative tools in life science to observe the gene expression levels, one of which is the expression of the genes of people with carcinoma. Carcinoma is a cancer that forms in the epithelial tissue. These data can be analyzed such as the identification expressions hereditary gene and also build classifications that can be used to improve diagnosis of carcinoma. Microarray data usually served in large dimension that most methods require large computing time to do the grouping. Therefore, this study uses spectral clustering method which allows to work with any object for reduces dimension. Spectral clustering method is a method based on spectral decomposition of the matrix which is represented in the form of a graph. After the data dimensions are reduced, then the data are partitioned. One of the famous partition method is Partitioning Around Medoids (PAM) which is minimize the objective function with exchanges all the non-medoid points into medoid point iteratively until converge. Objectivity of this research is to implement methods spectral clustering and partitioning algorithm PAM to obtain groups of 7457 genes with carcinoma based on the similarity value. The result in this study is two groups of genes with carcinoma.

Identification of Prostate Cancer Prognostic Markers

DTIC Science & Technology

2016-10-01

Technologies). For this, the oxygen consumption rate (OCR) in the PC-3 control and ECI1-overexpressing clones was measured following their maintenance...carnitine Carnitine β-oxydation Etomoxir Page 25 of 31 Figure 10: Mitochondrial Respiration in ECI1-overexpressing PC-3 Clones. Oxygen Consumption rate... FISH ), prognostic markers, biomarkers, tissue microarrays, autophagy 16. SECURITY CLASSIFICATION OF: 17. LIMITATION OF ABSTRACT 18. NUMBER OF PAGES

Gene masking - a technique to improve accuracy for cancer classification with high dimensionality in microarray data.

PubMed

Saini, Harsh; Lal, Sunil Pranit; Naidu, Vimal Vikash; Pickering, Vincel Wince; Singh, Gurmeet; Tsunoda, Tatsuhiko; Sharma, Alok

2016-12-05

High dimensional feature space generally degrades classification in several applications. In this paper, we propose a strategy called gene masking, in which non-contributing dimensions are heuristically removed from the data to improve classification accuracy. Gene masking is implemented via a binary encoded genetic algorithm that can be integrated seamlessly with classifiers during the training phase of classification to perform feature selection. It can also be used to discriminate between features that contribute most to the classification, thereby, allowing researchers to isolate features that may have special significance. This technique was applied on publicly available datasets whereby it substantially reduced the number of features used for classification while maintaining high accuracies. The proposed technique can be extremely useful in feature selection as it heuristically removes non-contributing features to improve the performance of classifiers.

On the statistical assessment of classifiers using DNA microarray data

PubMed Central

Ancona, N; Maglietta, R; Piepoli, A; D'Addabbo, A; Cotugno, R; Savino, M; Liuni, S; Carella, M; Pesole, G; Perri, F

2006-01-01

Background In this paper we present a method for the statistical assessment of cancer predictors which make use of gene expression profiles. The methodology is applied to a new data set of microarray gene expression data collected in Casa Sollievo della Sofferenza Hospital, Foggia – Italy. The data set is made up of normal (22) and tumor (25) specimens extracted from 25 patients affected by colon cancer. We propose to give answers to some questions which are relevant for the automatic diagnosis of cancer such as: Is the size of the available data set sufficient to build accurate classifiers? What is the statistical significance of the associated error rates? In what ways can accuracy be considered dependant on the adopted classification scheme? How many genes are correlated with the pathology and how many are sufficient for an accurate colon cancer classification? The method we propose answers these questions whilst avoiding the potential pitfalls hidden in the analysis and interpretation of microarray data. Results We estimate the generalization error, evaluated through the Leave-K-Out Cross Validation error, for three different classification schemes by varying the number of training examples and the number of the genes used. The statistical significance of the error rate is measured by using a permutation test. We provide a statistical analysis in terms of the frequencies of the genes involved in the classification. Using the whole set of genes, we found that the Weighted Voting Algorithm (WVA) classifier learns the distinction between normal and tumor specimens with 25 training examples, providing e = 21% (p = 0.045) as an error rate. This remains constant even when the number of examples increases. Moreover, Regularized Least Squares (RLS) and Support Vector Machines (SVM) classifiers can learn with only 15 training examples, with an error rate of e = 19% (p = 0.035) and e = 18% (p = 0.037) respectively. Moreover, the error rate decreases as the training set size increases, reaching its best performances with 35 training examples. In this case, RLS and SVM have error rates of e = 14% (p = 0.027) and e = 11% (p = 0.019). Concerning the number of genes, we found about 6000 genes (p < 0.05) correlated with the pathology, resulting from the signal-to-noise statistic. Moreover the performances of RLS and SVM classifiers do not change when 74% of genes is used. They progressively reduce up to e = 16% (p < 0.05) when only 2 genes are employed. The biological relevance of a set of genes determined by our statistical analysis and the major roles they play in colorectal tumorigenesis is discussed. Conclusions The method proposed provides statistically significant answers to precise questions relevant for the diagnosis and prognosis of cancer. We found that, with as few as 15 examples, it is possible to train statistically significant classifiers for colon cancer diagnosis. As for the definition of the number of genes sufficient for a reliable classification of colon cancer, our results suggest that it depends on the accuracy required. PMID:16919171

The Cross-Entropy Based Multi-Filter Ensemble Method for Gene Selection.

PubMed

Sun, Yingqiang; Lu, Chengbo; Li, Xiaobo

2018-05-17

The gene expression profile has the characteristics of a high dimension, low sample, and continuous type, and it is a great challenge to use gene expression profile data for the classification of tumor samples. This paper proposes a cross-entropy based multi-filter ensemble (CEMFE) method for microarray data classification. Firstly, multiple filters are used to select the microarray data in order to obtain a plurality of the pre-selected feature subsets with a different classification ability. The top N genes with the highest rank of each subset are integrated so as to form a new data set. Secondly, the cross-entropy algorithm is used to remove the redundant data in the data set. Finally, the wrapper method, which is based on forward feature selection, is used to select the best feature subset. The experimental results show that the proposed method is more efficient than other gene selection methods and that it can achieve a higher classification accuracy under fewer characteristic genes.

Genomic profiling using array comparative genomic hybridization define distinct subtypes of diffuse large b-cell lymphoma: a review of the literature

PubMed Central

2012-01-01

Diffuse large B-cell lymphoma (DLBCL) is the most common type of non-Hodgkin Lymphoma comprising of greater than 30% of adult non-Hodgkin Lymphomas. DLBCL represents a diverse set of lymphomas, defined as diffuse proliferation of large B lymphoid cells. Numerous cytogenetic studies including karyotypes and fluorescent in situ hybridization (FISH), as well as morphological, biological, clinical, microarray and sequencing technologies have attempted to categorize DLBCL into morphological variants, molecular and immunophenotypic subgroups, as well as distinct disease entities. Despite such efforts, most lymphoma remains undistinguishable and falls into DLBCL, not otherwise specified (DLBCL-NOS). The advent of microarray-based studies (chromosome, RNA, gene expression, etc) has provided a plethora of high-resolution data that could potentially facilitate the finer classification of DLBCL. This review covers the microarray data currently published for DLBCL. We will focus on these types of data; 1) array based CGH; 2) classical CGH; and 3) gene expression profiling studies. The aims of this review were three-fold: (1) to catalog chromosome loci that are present in at least 20% or more of distinct DLBCL subtypes; a detailed list of gains and losses for different subtypes was generated in a table form to illustrate specific chromosome loci affected in selected subtypes; (2) to determine common and distinct copy number alterations among the different subtypes and based on this information, characteristic and similar chromosome loci for the different subtypes were depicted in two separate chromosome ideograms; and, (3) to list re-classified subtypes and those that remained indistinguishable after review of the microarray data. To the best of our knowledge, this is the first effort to compile and review available literatures on microarray analysis data and their practical utility in classifying DLBCL subtypes. Although conventional cytogenetic methods such as Karyotypes and FISH have played a major role in classification schemes of lymphomas, better classification models are clearly needed to further understanding the biology, disease outcome and therapeutic management of DLBCL. In summary, microarray data reviewed here can provide better subtype specific classifications models for DLBCL. PMID:22967872

Biological classification with RNA-Seq data: Can alternatively spliced transcript expression enhance machine learning classifier?

PubMed

Johnson, Nathan T; Dhroso, Andi; Hughes, Katelyn J; Korkin, Dmitry

2018-06-25

The extent to which the genes are expressed in the cell can be simplistically defined as a function of one or more factors of the environment, lifestyle, and genetics. RNA sequencing (RNA-Seq) is becoming a prevalent approach to quantify gene expression, and is expected to gain better insights to a number of biological and biomedical questions, compared to the DNA microarrays. Most importantly, RNA-Seq allows to quantify expression at the gene and alternative splicing isoform levels. However, leveraging the RNA-Seq data requires development of new data mining and analytics methods. Supervised machine learning methods are commonly used approaches for biological data analysis, and have recently gained attention for their applications to the RNA-Seq data. In this work, we assess the utility of supervised learning methods trained on RNA-Seq data for a diverse range of biological classification tasks. We hypothesize that the isoform-level expression data is more informative for biological classification tasks than the gene-level expression data. Our large-scale assessment is done through utilizing multiple datasets, organisms, lab groups, and RNA-Seq analysis pipelines. Overall, we performed and assessed 61 biological classification problems that leverage three independent RNA-Seq datasets and include over 2,000 samples that come from multiple organisms, lab groups, and RNA-Seq analyses. These 61 problems include predictions of the tissue type, sex, or age of the sample, healthy or cancerous phenotypes and, the pathological tumor stage for the samples from the cancerous tissue. For each classification problem, the performance of three normalization techniques and six machine learning classifiers was explored. We find that for every single classification problem, the isoform-based classifiers outperform or are comparable with gene expression based methods. The top-performing supervised learning techniques reached a near perfect classification accuracy, demonstrating the utility of supervised learning for RNA-Seq based data analysis. Published by Cold Spring Harbor Laboratory Press for the RNA Society.

Upregulation of long non-coding RNA M26317 correlates with tumor progression and poor prognosis in gastric cancer.

PubMed

Li, Li; Wang, Yuan-Yu; Mou, Xiao Zhou; Ye, Zai-Yuan; Zhao, Zhong-Sheng

2018-04-23

To investigate the expression and clinical significance of long non-coding RNA (lnc RNA) in gastric cancer, we applied microarray analysis to obtain expression profiles of protein coding genes and lncRNAs in tumor and paired adjacent non-tumor tissues. We found that 41 lncRNAs were upregulated and 31 lncRNAs were downregulated more than 2-fold in gastric cancer versus noncancerous tissues (ratio>2.0, P<.01). We established a co-expression network of the differentially expressed lncRNAs and targeted coding genes that included 17 lncRNAs and 16 coding genes. As the results of microarray analysis showed that lncRNA M26317 was upregulated in gastric cancer tissues we examined the expression level of M26317 in 103 gastric cancer tissues by RT-PCR and 436 gastric cancer tissues by in situ hybridization. Our data confirmed that M26317 was upregulated in gastric cancer tissues. Moreover, expression of M26317 correlated with patient age, size of tumor, Lauren's classification, depth of invasion, lymph node and distant metastasis, TNM stage and poor prognosis (P<.05), but was not associated with gender, location of tumor, and differentiation (P>.05). M26317 may have an important role in malignant transformation and metastasis of gastric cancer. Copyright © 2018. Published by Elsevier Inc.

[Research progress in molecular classification of gastric cancer].

PubMed

Zhou, Menglong; Li, Guichao; Zhang, Zhen

2016-09-25

Gastric cancer(GC) is a highly heterogeneous malignancy. The present widely used histopathological classifications have gradually failed to meet the needs of individualized diagnosis and treatment. Development of technologies such as microarray and next-generation sequencing (NGS) has allowed GC to be studied at the molecular level. Mechanisms about tumorigenesis and progression of GC can be elucidated in the aspects of gene mutations, chromosomal alterations, transcriptional and epigenetic changes, on the basis of which GC can be divided into several subtypes. The classifications of Tan's, Lei's, TCGA and ACRG are relatively comprehensive. Especially the TCGA and ACRG classifications have large sample size and abundant molecular profiling data, thus, the genomic characteristics of GC can be depicted more accurately. However, significant differences between both classifications still exist so that they cannot be substituted for each other. So far there is no widely accepted molecular classification of GC. Compared with TCGA classification, ACRG system may have more clinical significance in Chinese GC patients since the samples are mostly from Asian population and show better association with prognosis. The molecular classification of GC may provide the theoretical and experimental basis for early diagnosis, therapeutic efficacy prediction and treatment stratification while their clinical application is still limited. Future work should involve the application of molecular classifications in the clinical settings for improving the medical management of GC.

Recursive SVM biomarker selection for early detection of breast cancer in peripheral blood.

PubMed

Zhang, Fan; Kaufman, Howard L; Deng, Youping; Drabier, Renee

2013-01-01

Breast cancer is worldwide the second most common type of cancer after lung cancer. Traditional mammography and Tissue Microarray has been studied for early cancer detection and cancer prediction. However, there is a need for more reliable diagnostic tools for early detection of breast cancer. This can be a challenge due to a number of factors and logistics. First, obtaining tissue biopsies can be difficult. Second, mammography may not detect small tumors, and is often unsatisfactory for younger women who typically have dense breast tissue. Lastly, breast cancer is not a single homogeneous disease but consists of multiple disease states, each arising from a distinct molecular mechanism and having a distinct clinical progression path which makes the disease difficult to detect and predict in early stages. In the paper, we present a Support Vector Machine based on Recursive Feature Elimination and Cross Validation (SVM-RFE-CV) algorithm for early detection of breast cancer in peripheral blood and show how to use SVM-RFE-CV to model the classification and prediction problem of early detection of breast cancer in peripheral blood.The training set which consists of 32 health and 33 cancer samples and the testing set consisting of 31 health and 34 cancer samples were randomly separated from a dataset of peripheral blood of breast cancer that is downloaded from Gene Express Omnibus. First, we identified the 42 differentially expressed biomarkers between "normal" and "cancer". Then, with the SVM-RFE-CV we extracted 15 biomarkers that yield zero cross validation score. Lastly, we compared the classification and prediction performance of SVM-RFE-CV with that of SVM and SVM Recursive Feature Elimination (SVM-RFE). We found that 1) the SVM-RFE-CV is suitable for analyzing noisy high-throughput microarray data, 2) it outperforms SVM-RFE in the robustness to noise and in the ability to recover informative features, and 3) it can improve the prediction performance (Area Under Curve) in the testing data set from 0.5826 to 0.7879. Further pathway analysis showed that the biomarkers are associated with Signaling, Hemostasis, Hormones, and Immune System, which are consistent with previous findings. Our prediction model can serve as a general model for biomarker discovery in early detection of other cancers. In the future, Polymerase Chain Reaction (PCR) is planned for validation of the ability of these potential biomarkers for early detection of breast cancer.

Simple and Flexible Classification of Gene Expression Microarrays Via Swirls and Ripples | Division of Cancer Prevention

Cancer.gov

By Stuart G. Baker The program requires Mathematica 7.01.0 The key function is Classify [datalist,options] where datalist={data, genename, dataname} data ={matrix for class 0, matrix for class 1}, matrix is gene expression by specimen genename a list of names of genes, dataname ={name of data set, name of class0, name of class1} |

Switching benchmarks in cancer of unknown primary: from autopsy to microarray.

PubMed

Pentheroudakis, George; Golfinopoulos, Vassilios; Pavlidis, Nicholas

2007-09-01

Cancer of unknown primary (CUP) is associated with unknown biology and dismal prognosis. Information on the primary site of origin is scant and has never been analysed. We systematically reviewed all published evidence on the CUP primary site identified by two different approaches, either autopsy or microarray gene expression profiling. Published reports on identification of CUP primary site by autopsy or microarray-based multigene expression platforms were retrieved and analysed for year of publication, primary site, patient age, gender, histology, rate of primary identification, manifestations and metastatic deposits, microarray chip technology, training and validation sets, mathematical modelling, classification accuracy and number of classifying genes. From 1944 to 2000, a total of 884 CUP patients (66% males) underwent autopsy in 12 studies after presenting with metastatic or systemic symptoms and succumbing to their disease. A primary was identified in 644 (73%) of them, mostly in the lung (27%), pancreas (24%), hepatobiliary tree (8%), kidneys (8%), bowel, genital system and stomach, as a small focus of adenocarcinoma or poorly differentiated carcinoma. An unpredictable systemic dissemination was evident with high frequency of lung (46%), nodal (35%), bone (17%), brain (16%) and uncommon (18%) deposits. Between the 1944-1980 and the 1980-2000 series, female representation increased, 'undetermined neoplasm' diagnosis became rarer, pancreatic primaries were found less often while colonic ones were identified more frequently. Four studies using microarray technology profiled more than 500 CUP cases using classifier set of genes (ranging from 10 to 495) and reported strikingly dissimilar frequencies of assigned primary sites (lung 11.5%, pancreas 12.5%, bowel 12%, breast 15%, hepatobiliary tree 8%, kidneys 6%, genital system 9%, bladder 5%) in 75-90% of the cases. Evolution in medical imaging technology, diet and lifestyle habits probably account for changing epidemiology of CUP primaries in autopsies. Discrepant assignment of primary sites by microarrays may be due to the presence of 'sanctuary sites' in autopsies, molecular misclassification and the postulated presence of a pro-metastatic genetic signature. In view of the absence of patient therapeutic or prognostic benefit with primary identification, gene expression profiling should be re-orientated towards unraveling the complex pathophysiology of metastases.

Comparisons of Robustness and Sensitivity between Cancer and Normal Cells by Microarray Data

PubMed Central

Chu, Liang-Hui; Chen, Bor-Sen

2008-01-01

Robustness is defined as the ability to uphold performance in face of perturbations and uncertainties, and sensitivity is a measure of the system deviations generated by perturbations to the system. While cancer appears as a robust but fragile system, few computational and quantitative evidences demonstrate robustness tradeoffs in cancer. Microarrays have been widely applied to decipher gene expression signatures in human cancer research, and quantification of global gene expression profiles facilitates precise prediction and modeling of cancer in systems biology. We provide several efficient computational methods based on system and control theory to compare robustness and sensitivity between cancer and normal cells by microarray data. Measurement of robustness and sensitivity by linear stochastic model is introduced in this study, which shows oscillations in feedback loops of p53 and demonstrates robustness tradeoffs that cancer is a robust system with some extreme fragilities. In addition, we measure sensitivity of gene expression to perturbations in other gene expression and kinetic parameters, discuss nonlinear effects in feedback loops of p53 and extend our method to robustness-based cancer drug design. PMID:19259409

MULTI-K: accurate classification of microarray subtypes using ensemble k-means clustering

PubMed Central

Kim, Eun-Youn; Kim, Seon-Young; Ashlock, Daniel; Nam, Dougu

2009-01-01

Background Uncovering subtypes of disease from microarray samples has important clinical implications such as survival time and sensitivity of individual patients to specific therapies. Unsupervised clustering methods have been used to classify this type of data. However, most existing methods focus on clusters with compact shapes and do not reflect the geometric complexity of the high dimensional microarray clusters, which limits their performance. Results We present a cluster-number-based ensemble clustering algorithm, called MULTI-K, for microarray sample classification, which demonstrates remarkable accuracy. The method amalgamates multiple k-means runs by varying the number of clusters and identifies clusters that manifest the most robust co-memberships of elements. In addition to the original algorithm, we newly devised the entropy-plot to control the separation of singletons or small clusters. MULTI-K, unlike the simple k-means or other widely used methods, was able to capture clusters with complex and high-dimensional structures accurately. MULTI-K outperformed other methods including a recently developed ensemble clustering algorithm in tests with five simulated and eight real gene-expression data sets. Conclusion The geometric complexity of clusters should be taken into account for accurate classification of microarray data, and ensemble clustering applied to the number of clusters tackles the problem very well. The C++ code and the data sets tested are available from the authors. PMID:19698124

Circular RNA and gene expression profiles in gastric cancer based on microarray chip technology.

PubMed

Sui, Weiguo; Shi, Zhoufang; Xue, Wen; Ou, Minglin; Zhu, Ying; Chen, Jiejing; Lin, Hua; Liu, Fuhua; Dai, Yong

2017-03-01

The aim of the present study was to screen gastric cancer (GC) tissue and adjacent tissue for differences in mRNA and circular (circRNA) expression, to analyze the differences in circRNA and mRNA expression, and to investigate the circRNA expression in gastric carcinoma and its mechanism. circRNA and mRNA differential expression profiles generated using Agilent microarray technology were analyzed in the GC tissues and adjacent tissues. qRT-PCR was used to verify the differential expression of circRNAs and mRNAs according to the interactions between circRNAs and miRNAs as well as the possible existence of miRNA and mRNA interactions. We found that: i) the circRNA expression profile revealed 1,285 significant differences in circRNA expression, with circRNA expression downregulated in 594 samples and upregulated in 691 samples via interactions with miRNAs. The qRT-PCR validation experiments showed that hsa_circRNA_400071, hsa_circRNA_000543 and hsa_circRNA_001959 expression was consistent with the microarray analysis results. ii) 29,112 genes were found in the GC tissues and adjacent tissues, including 5,460 differentially expressed genes. Among them, 2,390 differentially expressed genes were upregulated and 3,070 genes were downregulated. Gene Ontology (GO) analysis of the differentially expressed genes revealed these genes involved in biological process classification, cellular component classification and molecular function classification. Pathway analysis of the differentially expressed genes identified 83 significantly enriched genes, including 28 upregulated genes and 55 downregulated genes. iii) 69 differentially expressed circRNAs were found that might adsorb specific miRNAs to regulate the expression of their target gene mRNAs. The conclusions are: i) differentially expressed circRNAs had corresponding miRNA binding sites. These circRNAs regulated the expression of target genes through interactions with miRNAs and might become new molecular biomarkers for GC in the future. ii) Differentially expressed genes may be involved in the occurrence of GC via a variety of mechanisms. iii) CD44, CXXC5, MYH9, MALAT1 and other genes may have important implications for the occurrence and development of GC through the regulation, interaction, and mutual influence of circRNA-miRNA-mRNA via different mechanisms.

Differential prioritization between relevance and redundancy in correlation-based feature selection techniques for multiclass gene expression data.

PubMed

Ooi, Chia Huey; Chetty, Madhu; Teng, Shyh Wei

2006-06-23

Due to the large number of genes in a typical microarray dataset, feature selection looks set to play an important role in reducing noise and computational cost in gene expression-based tissue classification while improving accuracy at the same time. Surprisingly, this does not appear to be the case for all multiclass microarray datasets. The reason is that many feature selection techniques applied on microarray datasets are either rank-based and hence do not take into account correlations between genes, or are wrapper-based, which require high computational cost, and often yield difficult-to-reproduce results. In studies where correlations between genes are considered, attempts to establish the merit of the proposed techniques are hampered by evaluation procedures which are less than meticulous, resulting in overly optimistic estimates of accuracy. We present two realistically evaluated correlation-based feature selection techniques which incorporate, in addition to the two existing criteria involved in forming a predictor set (relevance and redundancy), a third criterion called the degree of differential prioritization (DDP). DDP functions as a parameter to strike the balance between relevance and redundancy, providing our techniques with the novel ability to differentially prioritize the optimization of relevance against redundancy (and vice versa). This ability proves useful in producing optimal classification accuracy while using reasonably small predictor set sizes for nine well-known multiclass microarray datasets. For multiclass microarray datasets, especially the GCM and NCI60 datasets, DDP enables our filter-based techniques to produce accuracies better than those reported in previous studies which employed similarly realistic evaluation procedures.

Feature Genes Selection Using Supervised Locally Linear Embedding and Correlation Coefficient for Microarray Classification

PubMed Central

Wang, Yun; Huang, Fangzhou

2018-01-01

The selection of feature genes with high recognition ability from the gene expression profiles has gained great significance in biology. However, most of the existing methods have a high time complexity and poor classification performance. Motivated by this, an effective feature selection method, called supervised locally linear embedding and Spearman's rank correlation coefficient (SLLE-SC2), is proposed which is based on the concept of locally linear embedding and correlation coefficient algorithms. Supervised locally linear embedding takes into account class label information and improves the classification performance. Furthermore, Spearman's rank correlation coefficient is used to remove the coexpression genes. The experiment results obtained on four public tumor microarray datasets illustrate that our method is valid and feasible. PMID:29666661

Feature Genes Selection Using Supervised Locally Linear Embedding and Correlation Coefficient for Microarray Classification.

PubMed

Xu, Jiucheng; Mu, Huiyu; Wang, Yun; Huang, Fangzhou

2018-01-01

The selection of feature genes with high recognition ability from the gene expression profiles has gained great significance in biology. However, most of the existing methods have a high time complexity and poor classification performance. Motivated by this, an effective feature selection method, called supervised locally linear embedding and Spearman's rank correlation coefficient (SLLE-SC 2 ), is proposed which is based on the concept of locally linear embedding and correlation coefficient algorithms. Supervised locally linear embedding takes into account class label information and improves the classification performance. Furthermore, Spearman's rank correlation coefficient is used to remove the coexpression genes. The experiment results obtained on four public tumor microarray datasets illustrate that our method is valid and feasible.

Gene selection for microarray data classification via subspace learning and manifold regularization.

PubMed

Tang, Chang; Cao, Lijuan; Zheng, Xiao; Wang, Minhui

2017-12-19

With the rapid development of DNA microarray technology, large amount of genomic data has been generated. Classification of these microarray data is a challenge task since gene expression data are often with thousands of genes but a small number of samples. In this paper, an effective gene selection method is proposed to select the best subset of genes for microarray data with the irrelevant and redundant genes removed. Compared with original data, the selected gene subset can benefit the classification task. We formulate the gene selection task as a manifold regularized subspace learning problem. In detail, a projection matrix is used to project the original high dimensional microarray data into a lower dimensional subspace, with the constraint that the original genes can be well represented by the selected genes. Meanwhile, the local manifold structure of original data is preserved by a Laplacian graph regularization term on the low-dimensional data space. The projection matrix can serve as an importance indicator of different genes. An iterative update algorithm is developed for solving the problem. Experimental results on six publicly available microarray datasets and one clinical dataset demonstrate that the proposed method performs better when compared with other state-of-the-art methods in terms of microarray data classification. Graphical Abstract The graphical abstract of this work.

Comparison of RNA-seq and microarray-based models for clinical endpoint prediction.

PubMed

Zhang, Wenqian; Yu, Ying; Hertwig, Falk; Thierry-Mieg, Jean; Zhang, Wenwei; Thierry-Mieg, Danielle; Wang, Jian; Furlanello, Cesare; Devanarayan, Viswanath; Cheng, Jie; Deng, Youping; Hero, Barbara; Hong, Huixiao; Jia, Meiwen; Li, Li; Lin, Simon M; Nikolsky, Yuri; Oberthuer, André; Qing, Tao; Su, Zhenqiang; Volland, Ruth; Wang, Charles; Wang, May D; Ai, Junmei; Albanese, Davide; Asgharzadeh, Shahab; Avigad, Smadar; Bao, Wenjun; Bessarabova, Marina; Brilliant, Murray H; Brors, Benedikt; Chierici, Marco; Chu, Tzu-Ming; Zhang, Jibin; Grundy, Richard G; He, Min Max; Hebbring, Scott; Kaufman, Howard L; Lababidi, Samir; Lancashire, Lee J; Li, Yan; Lu, Xin X; Luo, Heng; Ma, Xiwen; Ning, Baitang; Noguera, Rosa; Peifer, Martin; Phan, John H; Roels, Frederik; Rosswog, Carolina; Shao, Susan; Shen, Jie; Theissen, Jessica; Tonini, Gian Paolo; Vandesompele, Jo; Wu, Po-Yen; Xiao, Wenzhong; Xu, Joshua; Xu, Weihong; Xuan, Jiekun; Yang, Yong; Ye, Zhan; Dong, Zirui; Zhang, Ke K; Yin, Ye; Zhao, Chen; Zheng, Yuanting; Wolfinger, Russell D; Shi, Tieliu; Malkas, Linda H; Berthold, Frank; Wang, Jun; Tong, Weida; Shi, Leming; Peng, Zhiyu; Fischer, Matthias

2015-06-25

Gene expression profiling is being widely applied in cancer research to identify biomarkers for clinical endpoint prediction. Since RNA-seq provides a powerful tool for transcriptome-based applications beyond the limitations of microarrays, we sought to systematically evaluate the performance of RNA-seq-based and microarray-based classifiers in this MAQC-III/SEQC study for clinical endpoint prediction using neuroblastoma as a model. We generate gene expression profiles from 498 primary neuroblastomas using both RNA-seq and 44 k microarrays. Characterization of the neuroblastoma transcriptome by RNA-seq reveals that more than 48,000 genes and 200,000 transcripts are being expressed in this malignancy. We also find that RNA-seq provides much more detailed information on specific transcript expression patterns in clinico-genetic neuroblastoma subgroups than microarrays. To systematically compare the power of RNA-seq and microarray-based models in predicting clinical endpoints, we divide the cohort randomly into training and validation sets and develop 360 predictive models on six clinical endpoints of varying predictability. Evaluation of factors potentially affecting model performances reveals that prediction accuracies are most strongly influenced by the nature of the clinical endpoint, whereas technological platforms (RNA-seq vs. microarrays), RNA-seq data analysis pipelines, and feature levels (gene vs. transcript vs. exon-junction level) do not significantly affect performances of the models. We demonstrate that RNA-seq outperforms microarrays in determining the transcriptomic characteristics of cancer, while RNA-seq and microarray-based models perform similarly in clinical endpoint prediction. Our findings may be valuable to guide future studies on the development of gene expression-based predictive models and their implementation in clinical practice.

Predicting breast cancer using an expression values weighted clinical classifier.

PubMed

Thomas, Minta; De Brabanter, Kris; Suykens, Johan A K; De Moor, Bart

2014-12-31

Clinical data, such as patient history, laboratory analysis, ultrasound parameters-which are the basis of day-to-day clinical decision support-are often used to guide the clinical management of cancer in the presence of microarray data. Several data fusion techniques are available to integrate genomics or proteomics data, but only a few studies have created a single prediction model using both gene expression and clinical data. These studies often remain inconclusive regarding an obtained improvement in prediction performance. To improve clinical management, these data should be fully exploited. This requires efficient algorithms to integrate these data sets and design a final classifier. LS-SVM classifiers and generalized eigenvalue/singular value decompositions are successfully used in many bioinformatics applications for prediction tasks. While bringing up the benefits of these two techniques, we propose a machine learning approach, a weighted LS-SVM classifier to integrate two data sources: microarray and clinical parameters. We compared and evaluated the proposed methods on five breast cancer case studies. Compared to LS-SVM classifier on individual data sets, generalized eigenvalue decomposition (GEVD) and kernel GEVD, the proposed weighted LS-SVM classifier offers good prediction performance, in terms of test area under ROC Curve (AUC), on all breast cancer case studies. Thus a clinical classifier weighted with microarray data set results in significantly improved diagnosis, prognosis and prediction responses to therapy. The proposed model has been shown as a promising mathematical framework in both data fusion and non-linear classification problems.

Comparative study of classification algorithms for immunosignaturing data

PubMed Central

2012-01-01

Background High-throughput technologies such as DNA, RNA, protein, antibody and peptide microarrays are often used to examine differences across drug treatments, diseases, transgenic animals, and others. Typically one trains a classification system by gathering large amounts of probe-level data, selecting informative features, and classifies test samples using a small number of features. As new microarrays are invented, classification systems that worked well for other array types may not be ideal. Expression microarrays, arguably one of the most prevalent array types, have been used for years to help develop classification algorithms. Many biological assumptions are built into classifiers that were designed for these types of data. One of the more problematic is the assumption of independence, both at the probe level and again at the biological level. Probes for RNA transcripts are designed to bind single transcripts. At the biological level, many genes have dependencies across transcriptional pathways where co-regulation of transcriptional units may make many genes appear as being completely dependent. Thus, algorithms that perform well for gene expression data may not be suitable when other technologies with different binding characteristics exist. The immunosignaturing microarray is based on complex mixtures of antibodies binding to arrays of random sequence peptides. It relies on many-to-many binding of antibodies to the random sequence peptides. Each peptide can bind multiple antibodies and each antibody can bind multiple peptides. This technology has been shown to be highly reproducible and appears promising for diagnosing a variety of disease states. However, it is not clear what is the optimal classification algorithm for analyzing this new type of data. Results We characterized several classification algorithms to analyze immunosignaturing data. We selected several datasets that range from easy to difficult to classify, from simple monoclonal binding to complex binding patterns in asthma patients. We then classified the biological samples using 17 different classification algorithms. Using a wide variety of assessment criteria, we found ‘Naïve Bayes’ far more useful than other widely used methods due to its simplicity, robustness, speed and accuracy. Conclusions ‘Naïve Bayes’ algorithm appears to accommodate the complex patterns hidden within multilayered immunosignaturing microarray data due to its fundamental mathematical properties. PMID:22720696

A new classification method for MALDI imaging mass spectrometry data acquired on formalin-fixed paraffin-embedded tissue samples.

PubMed

Boskamp, Tobias; Lachmund, Delf; Oetjen, Janina; Cordero Hernandez, Yovany; Trede, Dennis; Maass, Peter; Casadonte, Rita; Kriegsmann, Jörg; Warth, Arne; Dienemann, Hendrik; Weichert, Wilko; Kriegsmann, Mark

2017-07-01

Matrix-assisted laser desorption/ionization imaging mass spectrometry (MALDI IMS) shows a high potential for applications in histopathological diagnosis, and in particular for supporting tumor typing and subtyping. The development of such applications requires the extraction of spectral fingerprints that are relevant for the given tissue and the identification of biomarkers associated with these spectral patterns. We propose a novel data analysis method based on the extraction of characteristic spectral patterns (CSPs) that allow automated generation of classification models for spectral data. Formalin-fixed paraffin embedded (FFPE) tissue samples from N=445 patients assembled on 12 tissue microarrays were analyzed. The method was applied to discriminate primary lung and pancreatic cancer, as well as adenocarcinoma and squamous cell carcinoma of the lung. A classification accuracy of 100% and 82.8%, resp., could be achieved on core level, assessed by cross-validation. The method outperformed the more conventional classification method based on the extraction of individual m/z values in the first application, while achieving a comparable accuracy in the second. LC-MS/MS peptide identification demonstrated that the spectral features present in selected CSPs correspond to peptides relevant for the respective classification. This article is part of a Special Issue entitled: MALDI Imaging, edited by Dr. Corinna Henkel and Prof. Peter Hoffmann. Copyright © 2016 Elsevier B.V. All rights reserved.

Tissues from population-based cancer registries: a novel approach to increasing research potential.

PubMed

Goodman, Marc T; Hernandez, Brenda Y; Hewitt, Stephen; Lynch, Charles F; Coté, Timothy R; Frierson, Henry F; Moskaluk, Christopher A; Killeen, Jeffrey L; Cozen, Wendy; Key, Charles R; Clegg, Limin; Reichman, Marsha; Hankey, Benjamin F; Edwards, Brenda

2005-07-01

Population-based cancer registries, such as those included in the Surveillance, Epidemiology, and End-Results (SEER) Program, offer tremendous research potential beyond traditional surveillance activities. We describe the expansion of SEER registries to gather formalin-fixed, paraffin-embedded tissue from cancer patients on a population basis. Population-based tissue banks have the advantage of providing an unbiased sampling frame for evaluating the public health impact of genes or protein targets that may be used for therapeutic or diagnostic purposes in defined communities. Such repositories provide a unique resource for testing new molecular classification schemes for cancer, validating new biologic markers of malignancy, prognosis and progression, assessing therapeutic targets, and measuring allele frequencies of cancer-associated genetic polymorphisms or germline mutations in representative samples. The assembly of tissue microarrays will allow for the use of rapid, large-scale protein-expression profiling of tumor samples while limiting depletion of this valuable resource. Access to biologic specimens through SEER registries will provide researchers with demographic, clinical, and risk factor information on cancer patients with assured data quality and completeness. Clinical outcome data, such as disease-free survival, can be correlated with previously validated prognostic markers. Furthermore, the anonymity of the study subject can be protected through rigorous standards of confidentiality. SEER-based tissue resources represent a step forward in true, population-based tissue repositories of tumors from US patients and may serve as a foundation for molecular epidemiology studies of cancer in this country.

cDNA microarray analysis of esophageal cancer: discoveries and prospects.

PubMed

Shimada, Yutaka; Sato, Fumiaki; Shimizu, Kazuharu; Tsujimoto, Gozoh; Tsukada, Kazuhiro

2009-07-01

Recent progress in molecular biology has revealed many genetic and epigenetic alterations that are involved in the development and progression of esophageal cancer. Microarray analysis has also revealed several genetic networks that are involved in esophageal cancer. However, clinical application of microarray techniques and use of microarray data have not yet occurred. In this review, we focus on the recent developments and problems with microarray analysis of esophageal cancer.

A Robust Unified Approach to Analyzing Methylation and Gene Expression Data

PubMed Central

Khalili, Abbas; Huang, Tim; Lin, Shili

2009-01-01

Microarray technology has made it possible to investigate expression levels, and more recently methylation signatures, of thousands of genes simultaneously, in a biological sample. Since more and more data from different biological systems or technological platforms are being generated at an incredible rate, there is an increasing need to develop statistical methods that are applicable to multiple data types and platforms. Motivated by such a need, a flexible finite mixture model that is applicable to methylation, gene expression, and potentially data from other biological systems, is proposed. Two major thrusts of this approach are to allow for a variable number of components in the mixture to capture non-biological variation and small biases, and to use a robust procedure for parameter estimation and probe classification. The method was applied to the analysis of methylation signatures of three breast cancer cell lines. It was also tested on three sets of expression microarray data to study its power and type I error rates. Comparison with a number of existing methods in the literature yielded very encouraging results; lower type I error rates and comparable/better power were achieved based on the limited study. Furthermore, the method also leads to more biologically interpretable results for the three breast cancer cell lines. PMID:20161265

A computational neural approach to support the discovery of gene function and classes of cancer.

PubMed

Azuaje, F

2001-03-01

Advances in molecular classification of tumours may play a central role in cancer treatment. Here, a novel approach to genome expression pattern interpretation is described and applied to the recognition of B-cell malignancies as a test set. Using cDNA microarrays data generated by a previous study, a neural network model known as simplified fuzzy ARTMAP is able to identify normal and diffuse large B-cell lymphoma (DLBCL) patients. Furthermore, it discovers the distinction between patients with molecularly distinct forms of DLBCL without previous knowledge of those subtypes.

An integrated approach for identifying wrongly labelled samples when performing classification in microarray data.

PubMed

Leung, Yuk Yee; Chang, Chun Qi; Hung, Yeung Sam

2012-01-01

Using hybrid approach for gene selection and classification is common as results obtained are generally better than performing the two tasks independently. Yet, for some microarray datasets, both classification accuracy and stability of gene sets obtained still have rooms for improvement. This may be due to the presence of samples with wrong class labels (i.e. outliers). Outlier detection algorithms proposed so far are either not suitable for microarray data, or only solve the outlier detection problem on their own. We tackle the outlier detection problem based on a previously proposed Multiple-Filter-Multiple-Wrapper (MFMW) model, which was demonstrated to yield promising results when compared to other hybrid approaches (Leung and Hung, 2010). To incorporate outlier detection and overcome limitations of the existing MFMW model, three new features are introduced in our proposed MFMW-outlier approach: 1) an unbiased external Leave-One-Out Cross-Validation framework is developed to replace internal cross-validation in the previous MFMW model; 2) wrongly labeled samples are identified within the MFMW-outlier model; and 3) a stable set of genes is selected using an L1-norm SVM that removes any redundant genes present. Six binary-class microarray datasets were tested. Comparing with outlier detection studies on the same datasets, MFMW-outlier could detect all the outliers found in the original paper (for which the data was provided for analysis), and the genes selected after outlier removal were proven to have biological relevance. We also compared MFMW-outlier with PRAPIV (Zhang et al., 2006) based on same synthetic datasets. MFMW-outlier gave better average precision and recall values on three different settings. Lastly, artificially flipped microarray datasets were created by removing our detected outliers and flipping some of the remaining samples' labels. Almost all the 'wrong' (artificially flipped) samples were detected, suggesting that MFMW-outlier was sufficiently powerful to detect outliers in high-dimensional microarray datasets.

Topology based data analysis identifies a subgroup of breast cancers with a unique mutational profile and excellent survival.

PubMed

Nicolau, Monica; Levine, Arnold J; Carlsson, Gunnar

2011-04-26

High-throughput biological data, whether generated as sequencing, transcriptional microarrays, proteomic, or other means, continues to require analytic methods that address its high dimensional aspects. Because the computational part of data analysis ultimately identifies shape characteristics in the organization of data sets, the mathematics of shape recognition in high dimensions continues to be a crucial part of data analysis. This article introduces a method that extracts information from high-throughput microarray data and, by using topology, provides greater depth of information than current analytic techniques. The method, termed Progression Analysis of Disease (PAD), first identifies robust aspects of cluster analysis, then goes deeper to find a multitude of biologically meaningful shape characteristics in these data. Additionally, because PAD incorporates a visualization tool, it provides a simple picture or graph that can be used to further explore these data. Although PAD can be applied to a wide range of high-throughput data types, it is used here as an example to analyze breast cancer transcriptional data. This identified a unique subgroup of Estrogen Receptor-positive (ER(+)) breast cancers that express high levels of c-MYB and low levels of innate inflammatory genes. These patients exhibit 100% survival and no metastasis. No supervised step beyond distinction between tumor and healthy patients was used to identify this subtype. The group has a clear and distinct, statistically significant molecular signature, it highlights coherent biology but is invisible to cluster methods, and does not fit into the accepted classification of Luminal A/B, Normal-like subtypes of ER(+) breast cancers. We denote the group as c-MYB(+) breast cancer.

Prediction of cancer proteins by integrating protein interaction, domain frequency, and domain interaction data using machine learning algorithms.

PubMed

Huang, Chien-Hung; Peng, Huai-Shun; Ng, Ka-Lok

2015-01-01

Many proteins are known to be associated with cancer diseases. It is quite often that their precise functional role in disease pathogenesis remains unclear. A strategy to gain a better understanding of the function of these proteins is to make use of a combination of different aspects of proteomics data types. In this study, we extended Aragues's method by employing the protein-protein interaction (PPI) data, domain-domain interaction (DDI) data, weighted domain frequency score (DFS), and cancer linker degree (CLD) data to predict cancer proteins. Performances were benchmarked based on three kinds of experiments as follows: (I) using individual algorithm, (II) combining algorithms, and (III) combining the same classification types of algorithms. When compared with Aragues's method, our proposed methods, that is, machine learning algorithm and voting with the majority, are significantly superior in all seven performance measures. We demonstrated the accuracy of the proposed method on two independent datasets. The best algorithm can achieve a hit ratio of 89.4% and 72.8% for lung cancer dataset and lung cancer microarray study, respectively. It is anticipated that the current research could help understand disease mechanisms and diagnosis.

Prediction of Cancer Proteins by Integrating Protein Interaction, Domain Frequency, and Domain Interaction Data Using Machine Learning Algorithms

PubMed Central

2015-01-01

Many proteins are known to be associated with cancer diseases. It is quite often that their precise functional role in disease pathogenesis remains unclear. A strategy to gain a better understanding of the function of these proteins is to make use of a combination of different aspects of proteomics data types. In this study, we extended Aragues's method by employing the protein-protein interaction (PPI) data, domain-domain interaction (DDI) data, weighted domain frequency score (DFS), and cancer linker degree (CLD) data to predict cancer proteins. Performances were benchmarked based on three kinds of experiments as follows: (I) using individual algorithm, (II) combining algorithms, and (III) combining the same classification types of algorithms. When compared with Aragues's method, our proposed methods, that is, machine learning algorithm and voting with the majority, are significantly superior in all seven performance measures. We demonstrated the accuracy of the proposed method on two independent datasets. The best algorithm can achieve a hit ratio of 89.4% and 72.8% for lung cancer dataset and lung cancer microarray study, respectively. It is anticipated that the current research could help understand disease mechanisms and diagnosis. PMID:25866773

Prediction of cancer class with majority voting genetic programming classifier using gene expression data.

PubMed

Paul, Topon Kumar; Iba, Hitoshi

2009-01-01

In order to get a better understanding of different types of cancers and to find the possible biomarkers for diseases, recently, many researchers are analyzing the gene expression data using various machine learning techniques. However, due to a very small number of training samples compared to the huge number of genes and class imbalance, most of these methods suffer from overfitting. In this paper, we present a majority voting genetic programming classifier (MVGPC) for the classification of microarray data. Instead of a single rule or a single set of rules, we evolve multiple rules with genetic programming (GP) and then apply those rules to test samples to determine their labels with majority voting technique. By performing experiments on four different public cancer data sets, including multiclass data sets, we have found that the test accuracies of MVGPC are better than those of other methods, including AdaBoost with GP. Moreover, some of the more frequently occurring genes in the classification rules are known to be associated with the types of cancers being studied in this paper.

Derivation of an artificial gene to improve classification accuracy upon gene selection.

PubMed

Seo, Minseok; Oh, Sejong

2012-02-01

Classification analysis has been developed continuously since 1936. This research field has advanced as a result of development of classifiers such as KNN, ANN, and SVM, as well as through data preprocessing areas. Feature (gene) selection is required for very high dimensional data such as microarray before classification work. The goal of feature selection is to choose a subset of informative features that reduces processing time and provides higher classification accuracy. In this study, we devised a method of artificial gene making (AGM) for microarray data to improve classification accuracy. Our artificial gene was derived from a whole microarray dataset, and combined with a result of gene selection for classification analysis. We experimentally confirmed a clear improvement of classification accuracy after inserting artificial gene. Our artificial gene worked well for popular feature (gene) selection algorithms and classifiers. The proposed approach can be applied to any type of high dimensional dataset. Copyright © 2011 Elsevier Ltd. All rights reserved.

A signature inferred from Drosophila mitotic genes predicts survival of breast cancer patients.

PubMed

Damasco, Christian; Lembo, Antonio; Somma, Maria Patrizia; Gatti, Maurizio; Di Cunto, Ferdinando; Provero, Paolo

2011-02-28

The classification of breast cancer patients into risk groups provides a powerful tool for the identification of patients who will benefit from aggressive systemic therapy. The analysis of microarray data has generated several gene expression signatures that improve diagnosis and allow risk assessment. There is also evidence that cell proliferation-related genes have a high predictive power within these signatures. We thus constructed a gene expression signature (the DM signature) using the human orthologues of 108 Drosophila melanogaster genes required for either the maintenance of chromosome integrity (36 genes) or mitotic division (72 genes). The DM signature has minimal overlap with the extant signatures and is highly predictive of survival in 5 large breast cancer datasets. In addition, we show that the DM signature outperforms many widely used breast cancer signatures in predictive power, and performs comparably to other proliferation-based signatures. For most genes of the DM signature, an increased expression is negatively correlated with patient survival. The genes that provide the highest contribution to the predictive power of the DM signature are those involved in cytokinesis. This finding highlights cytokinesis as an important marker in breast cancer prognosis and as a possible target for antimitotic therapies.

Crowdsourcing the General Public for Large Scale Molecular Pathology Studies in Cancer

PubMed Central

Candido dos Reis, Francisco J.; Lynn, Stuart; Ali, H. Raza; Eccles, Diana; Hanby, Andrew; Provenzano, Elena; Caldas, Carlos; Howat, William J.; McDuffus, Leigh-Anne; Liu, Bin; Daley, Frances; Coulson, Penny; Vyas, Rupesh J.; Harris, Leslie M.; Owens, Joanna M.; Carton, Amy F.M.; McQuillan, Janette P.; Paterson, Andy M.; Hirji, Zohra; Christie, Sarah K.; Holmes, Amber R.; Schmidt, Marjanka K.; Garcia-Closas, Montserrat; Easton, Douglas F.; Bolla, Manjeet K.; Wang, Qin; Benitez, Javier; Milne, Roger L.; Mannermaa, Arto; Couch, Fergus; Devilee, Peter; Tollenaar, Robert A.E.M.; Seynaeve, Caroline; Cox, Angela; Cross, Simon S.; Blows, Fiona M.; Sanders, Joyce; de Groot, Renate; Figueroa, Jonine; Sherman, Mark; Hooning, Maartje; Brenner, Hermann; Holleczek, Bernd; Stegmaier, Christa; Lintott, Chris; Pharoah, Paul D.P.

2015-01-01

Background Citizen science, scientific research conducted by non-specialists, has the potential to facilitate biomedical research using available large-scale data, however validating the results is challenging. The Cell Slider is a citizen science project that intends to share images from tumors with the general public, enabling them to score tumor markers independently through an internet-based interface. Methods From October 2012 to June 2014, 98,293 Citizen Scientists accessed the Cell Slider web page and scored 180,172 sub-images derived from images of 12,326 tissue microarray cores labeled for estrogen receptor (ER). We evaluated the accuracy of Citizen Scientist's ER classification, and the association between ER status and prognosis by comparing their test performance against trained pathologists. Findings The area under ROC curve was 0.95 (95% CI 0.94 to 0.96) for cancer cell identification and 0.97 (95% CI 0.96 to 0.97) for ER status. ER positive tumors scored by Citizen Scientists were associated with survival in a similar way to that scored by trained pathologists. Survival probability at 15 years were 0.78 (95% CI 0.76 to 0.80) for ER-positive and 0.72 (95% CI 0.68 to 0.77) for ER-negative tumors based on Citizen Scientists classification. Based on pathologist classification, survival probability was 0.79 (95% CI 0.77 to 0.81) for ER-positive and 0.71 (95% CI 0.67 to 0.74) for ER-negative tumors. The hazard ratio for death was 0.26 (95% CI 0.18 to 0.37) at diagnosis and became greater than one after 6.5 years of follow-up for ER scored by Citizen Scientists, and 0.24 (95% CI 0.18 to 0.33) at diagnosis increasing thereafter to one after 6.7 (95% CI 4.1 to 10.9) years of follow-up for ER scored by pathologists. Interpretation Crowdsourcing of the general public to classify cancer pathology data for research is viable, engages the public and provides accurate ER data. Crowdsourced classification of research data may offer a valid solution to problems of throughput requiring human input. PMID:26288840

Identifying significant genetic regulatory networks in the prostate cancer from microarray data based on transcription factor analysis and conditional independency.

PubMed

Yeh, Hsiang-Yuan; Cheng, Shih-Wu; Lin, Yu-Chun; Yeh, Cheng-Yu; Lin, Shih-Fang; Soo, Von-Wun

2009-12-21

Prostate cancer is a world wide leading cancer and it is characterized by its aggressive metastasis. According to the clinical heterogeneity, prostate cancer displays different stages and grades related to the aggressive metastasis disease. Although numerous studies used microarray analysis and traditional clustering method to identify the individual genes during the disease processes, the important gene regulations remain unclear. We present a computational method for inferring genetic regulatory networks from micorarray data automatically with transcription factor analysis and conditional independence testing to explore the potential significant gene regulatory networks that are correlated with cancer, tumor grade and stage in the prostate cancer. To deal with missing values in microarray data, we used a K-nearest-neighbors (KNN) algorithm to determine the precise expression values. We applied web services technology to wrap the bioinformatics toolkits and databases to automatically extract the promoter regions of DNA sequences and predicted the transcription factors that regulate the gene expressions. We adopt the microarray datasets consists of 62 primary tumors, 41 normal prostate tissues from Stanford Microarray Database (SMD) as a target dataset to evaluate our method. The predicted results showed that the possible biomarker genes related to cancer and denoted the androgen functions and processes may be in the development of the prostate cancer and promote the cell death in cell cycle. Our predicted results showed that sub-networks of genes SREBF1, STAT6 and PBX1 are strongly related to a high extent while ETS transcription factors ELK1, JUN and EGR2 are related to a low extent. Gene SLC22A3 may explain clinically the differentiation associated with the high grade cancer compared with low grade cancer. Enhancer of Zeste Homolg 2 (EZH2) regulated by RUNX1 and STAT3 is correlated to the pathological stage. We provide a computational framework to reconstruct the genetic regulatory network from the microarray data using biological knowledge and constraint-based inferences. Our method is helpful in verifying possible interaction relations in gene regulatory networks and filtering out incorrect relations inferred by imperfect methods. We predicted not only individual gene related to cancer but also discovered significant gene regulation networks. Our method is also validated in several enriched published papers and databases and the significant gene regulatory networks perform critical biological functions and processes including cell adhesion molecules, androgen and estrogen metabolism, smooth muscle contraction, and GO-annotated processes. Those significant gene regulations and the critical concept of tumor progression are useful to understand cancer biology and disease treatment.

New bandwidth selection criterion for Kernel PCA: approach to dimensionality reduction and classification problems.

PubMed

Thomas, Minta; De Brabanter, Kris; De Moor, Bart

2014-05-10

DNA microarrays are potentially powerful technology for improving diagnostic classification, treatment selection, and prognostic assessment. The use of this technology to predict cancer outcome has a history of almost a decade. Disease class predictors can be designed for known disease cases and provide diagnostic confirmation or clarify abnormal cases. The main input to this class predictors are high dimensional data with many variables and few observations. Dimensionality reduction of these features set significantly speeds up the prediction task. Feature selection and feature transformation methods are well known preprocessing steps in the field of bioinformatics. Several prediction tools are available based on these techniques. Studies show that a well tuned Kernel PCA (KPCA) is an efficient preprocessing step for dimensionality reduction, but the available bandwidth selection method for KPCA was computationally expensive. In this paper, we propose a new data-driven bandwidth selection criterion for KPCA, which is related to least squares cross-validation for kernel density estimation. We propose a new prediction model with a well tuned KPCA and Least Squares Support Vector Machine (LS-SVM). We estimate the accuracy of the newly proposed model based on 9 case studies. Then, we compare its performances (in terms of test set Area Under the ROC Curve (AUC) and computational time) with other well known techniques such as whole data set + LS-SVM, PCA + LS-SVM, t-test + LS-SVM, Prediction Analysis of Microarrays (PAM) and Least Absolute Shrinkage and Selection Operator (Lasso). Finally, we assess the performance of the proposed strategy with an existing KPCA parameter tuning algorithm by means of two additional case studies. We propose, evaluate, and compare several mathematical/statistical techniques, which apply feature transformation/selection for subsequent classification, and consider its application in medical diagnostics. Both feature selection and feature transformation perform well on classification tasks. Due to the dynamic selection property of feature selection, it is hard to define significant features for the classifier, which predicts classes of future samples. Moreover, the proposed strategy enjoys a distinctive advantage with its relatively lesser time complexity.

A hybrid gene selection approach for microarray data classification using cellular learning automata and ant colony optimization.

PubMed

Vafaee Sharbaf, Fatemeh; Mosafer, Sara; Moattar, Mohammad Hossein

2016-06-01

This paper proposes an approach for gene selection in microarray data. The proposed approach consists of a primary filter approach using Fisher criterion which reduces the initial genes and hence the search space and time complexity. Then, a wrapper approach which is based on cellular learning automata (CLA) optimized with ant colony method (ACO) is used to find the set of features which improve the classification accuracy. CLA is applied due to its capability to learn and model complicated relationships. The selected features from the last phase are evaluated using ROC curve and the most effective while smallest feature subset is determined. The classifiers which are evaluated in the proposed framework are K-nearest neighbor; support vector machine and naïve Bayes. The proposed approach is evaluated on 4 microarray datasets. The evaluations confirm that the proposed approach can find the smallest subset of genes while approaching the maximum accuracy. Copyright © 2016 Elsevier Inc. All rights reserved.

Estrogen receptor-beta expression in invasive breast cancer in relation to molecular phenotype: results from the Nurses' Health Study.

PubMed

Marotti, Jonathan D; Collins, Laura C; Hu, Rong; Tamimi, Rulla M

2010-02-01

The expression of estrogen receptor-alpha (ER-alpha) and related genes has emerged as one of the major determinants of molecular classification of invasive breast cancers. Expression of a second ER, estrogen receptor-beta (ER-beta), has not been previously evaluated in a large population-based study. Therefore, we examined ER-beta expression in a large population of women with breast cancer to assess its relationship to molecular categories of invasive breast cancer. We constructed tissue microarrays from paraffin blocks of 3093 breast cancers that developed in women enrolled in the Nurses' Health Study. Tissue microarray sections were immunostained for ER-alpha, progesterone receptor (PR), human epidermal growth factor receptor 2 (HER2), cytokeratin 5/6, epidermal growth factor receptor (EGFR) and with a monoclonal antibody to ER-beta. Cancers were categorized as luminal A (ER-alpha+ and/or PR+ and HER2-); luminal B (ER-alpha+ and/or PR+ and HER2+); HER2 (ER-alpha- and PR- and HER2+); and basal-like (ER-alpha-, PR-, HER2- and EGFR or cytokeratin 5/6+). The relationship between expression of ER-beta and molecular class of invasive breast cancer was analyzed. Overall, 68% of breast carcinomas were ER-beta+. Expression of ER-beta was significantly associated with expression of ER-alpha (P<0.0001) and PR (P<0.0001), and was inversely related to expression of HER2 (P=0.004), CK5/6 (P=0.02) and EGFR (P=0.006). Among 2170 invasive cancers with complete immunophenotypic data, 73% were luminal A, 5% luminal B, 6 % HER2 and 11% basal-like. ER-beta expression was significantly related to molecular category (P<0.0001) and was more common in luminal A (72% of cases) and B (68% of cases) than in HER2 or basal-like types. However, despite their being defined by the absence of ER-alpha expression, 55% of HER2-type and 60% of basal-like cancers showed expression of ER-beta. The role of ER-beta in the development and progression of breast cancers defined by lack of expression of ER-alpha merits further investigation.

Supervised group Lasso with applications to microarray data analysis

PubMed Central

Ma, Shuangge; Song, Xiao; Huang, Jian

2007-01-01

Background A tremendous amount of efforts have been devoted to identifying genes for diagnosis and prognosis of diseases using microarray gene expression data. It has been demonstrated that gene expression data have cluster structure, where the clusters consist of co-regulated genes which tend to have coordinated functions. However, most available statistical methods for gene selection do not take into consideration the cluster structure. Results We propose a supervised group Lasso approach that takes into account the cluster structure in gene expression data for gene selection and predictive model building. For gene expression data without biological cluster information, we first divide genes into clusters using the K-means approach and determine the optimal number of clusters using the Gap method. The supervised group Lasso consists of two steps. In the first step, we identify important genes within each cluster using the Lasso method. In the second step, we select important clusters using the group Lasso. Tuning parameters are determined using V-fold cross validation at both steps to allow for further flexibility. Prediction performance is evaluated using leave-one-out cross validation. We apply the proposed method to disease classification and survival analysis with microarray data. Conclusion We analyze four microarray data sets using the proposed approach: two cancer data sets with binary cancer occurrence as outcomes and two lymphoma data sets with survival outcomes. The results show that the proposed approach is capable of identifying a small number of influential gene clusters and important genes within those clusters, and has better prediction performance than existing methods. PMID:17316436

Development of a two-stage gene selection method that incorporates a novel hybrid approach using the cuckoo optimization algorithm and harmony search for cancer classification.

PubMed

Elyasigomari, V; Lee, D A; Screen, H R C; Shaheed, M H

2017-03-01

For each cancer type, only a few genes are informative. Due to the so-called 'curse of dimensionality' problem, the gene selection task remains a challenge. To overcome this problem, we propose a two-stage gene selection method called MRMR-COA-HS. In the first stage, the minimum redundancy and maximum relevance (MRMR) feature selection is used to select a subset of relevant genes. The selected genes are then fed into a wrapper setup that combines a new algorithm, COA-HS, using the support vector machine as a classifier. The method was applied to four microarray datasets, and the performance was assessed by the leave one out cross-validation method. Comparative performance assessment of the proposed method with other evolutionary algorithms suggested that the proposed algorithm significantly outperforms other methods in selecting a fewer number of genes while maintaining the highest classification accuracy. The functions of the selected genes were further investigated, and it was confirmed that the selected genes are biologically relevant to each cancer type. Copyright © 2017. Published by Elsevier Inc.

Expression analysis of URI/RMP gene in endometrioid adenocarcinoma by tissue microarray immunohistochemistry.

PubMed

Gu, Junxia; Liang, Yuting; Qiao, Longwei; Li, Xiaoyun; Li, Xingang; Lu, Yaojuan; Zheng, Qiping

2013-01-01

Multiple studies have recently demonstrated the oncogenic property of URI (or RMP, a member of the prefoldin family of molecular chaperones) during progression of hepatocellular carcinoma, ovarian cancer, and possibly prostate cancer. Most recently, we have shown that URI/RMP is up-regulated in cervical cancer, another reproductive system tumor beside ovarian and prostate cancers. To investigate if URI/RMP also plays a role in other reproductive system tumors, especially in endometrioid adenocarcinoma, we analyzed URI/RMP expression in a TMA (tissue microarray) containing tissues from 30 cases of endometrioid adenocarcinoma (which covers tumor tissues from Grade I through Grade III) and adjacent endometrium by immunohistochemistry (IHC) and densitometry analysis using image-pro plus 6.0 software. Our results showed that the mean density of URI/RMP expression in cancerous tissue is slightly higher than that of the adjacent endometrial tissue, though not statistically significant (p>0.05). There is no significant difference either between the mean density of Grade III cancerous tissue and that of Grade I and II cancers. Notably, we detected significantly higher signal intensity in cancerous tissue of all 7 Grade III cases than that of their adjacent endometrial tissue (p<0.05), suggesting a correlation of URI/RMP expression with the differentiation and pathological classification of endometrioid adenocarcinoma. Together, our results demonstrate the heterogeneous expression of URI/RMP in endometrioid adenocarcinoma. The higher level of URI/RMP expression in high-grade endometrioid adenocarcinomas compared to tissues of adjacent endometrium or gland suggests a diagnostic and possibly, a prognostic value of URI/RMP in endometrioid adenocarcinoma.

Expression analysis of URI/RMP gene in endometrioid adenocarcinoma by tissue microarray immunohistochemistry

PubMed Central

Gu, Junxia; Liang, Yuting; Qiao, Longwei; Li, Xiaoyun; Li, Xingang; Lu, Yaojuan; Zheng, Qiping

2013-01-01

Multiple studies have recently demonstrated the oncogenic property of URI (or RMP, a member of the prefoldin family of molecular chaperones) during progression of hepatocellular carcinoma, ovarian cancer, and possibly prostate cancer. Most recently, we have shown that URI/RMP is up-regulated in cervical cancer, another reproductive system tumor beside ovarian and prostate cancers. To investigate if URI/RMP also plays a role in other reproductive system tumors, especially in endometrioid adenocarcinoma, we analyzed URI/RMP expression in a TMA (tissue microarray) containing tissues from 30 cases of endometrioid adenocarcinoma (which covers tumor tissues from Grade I through Grade III) and adjacent endometrium by immunohistochemistry (IHC) and densitometry analysis using image-pro plus 6.0 software. Our results showed that the mean density of URI/RMP expression in cancerous tissue is slightly higher than that of the adjacent endometrial tissue, though not statistically significant (p>0.05). There is no significant difference either between the mean density of Grade III cancerous tissue and that of Grade I and II cancers. Notably, we detected significantly higher signal intensity in cancerous tissue of all 7 Grade III cases than that of their adjacent endometrial tissue (p<0.05), suggesting a correlation of URI/RMP expression with the differentiation and pathological classification of endometrioid adenocarcinoma. Together, our results demonstrate the heterogeneous expression of URI/RMP in endometrioid adenocarcinoma. The higher level of URI/RMP expression in high-grade endometrioid adenocarcinomas compared to tissues of adjacent endometrium or gland suggests a diagnostic and possibly, a prognostic value of URI/RMP in endometrioid adenocarcinoma. PMID:24228101

IKKε and TBK1 expression in gastric cancer.

PubMed

Lee, Seung Eun; Hong, Mineui; Cho, Junhun; Lee, Jeeyun; Kim, Kyoung-Mee

2017-03-07

Inhibitor of kappa B kinase epsilon (IKKε) and TANK-binding kinase 1 (TBK1) are non-canonical IKKs. IKKε and TBK1 share the kinase domain and are similar in their ability to activate the nuclear factor-kappa B signaling pathway. IKKε and TBK1 are overexpressed through multiple mechanisms in various human cancers. However, the expression of IKKε and TBK1 in gastric cancer and their role in prognosis have not been studied.To investigate overexpression of the IKKε and TBK1 proteins in gastric cancer and their relationship with clinicopathologic factors, we performed immunohistochemical staining using a tissue microarray. Tissue microarray samples were obtained from 1,107 gastric cancer patients who underwent R0 gastrectomy with extensive lymph node dissection and adjuvant chemotherapy.We identified expression of IKKε in 150 (13.6%) and TBK1 in 38 (3.4%) gastric cancers. Furthermore, co-expression of IKKε and TBK1 was identified in 1.5% of cases. Co-expression of IKKε and TBK1 was associated with differentiated intestinal histology and earlier T stage. In a multivariate binary logistic regression model, intestinal histologic type by Lauren classification and early AJCC stage were significant predictors for expression of IKKε and TBK1 proteins in gastric cancer. Changes in IKKε and TBK1 expression may be involved in the development of intestinal-type gastric cancer. The overexpression of IKKε and TBK1 should be considered in selected patients with intestinal-type gastric cancer.In conclusion, this is the first large-scale study investigating the relationships between expression of IKKε and TBK1 and clinicopathologic features of gastric cancer. The role of IKKε and TBK1 in intestinal-type gastric cancer pathogenesis should be elucidated by further investigation.

Different CHEK2 germline mutations are associated with distinct immunophenotypic molecular subtypes of breast cancer.

PubMed

Domagala, Pawel; Wokolorczyk, Dominika; Cybulski, Cezary; Huzarski, Tomasz; Lubinski, Jan; Domagala, Wenancjusz

2012-04-01

Germline mutations in BRCA1 were already linked to basal-like subtype of immunophenotypic molecular classification of breast cancer (BC). However, it is not known whether mutations in other BC susceptibility genes are associated with molecular subtypes of this cancer. We tested the hypothesis that distinct mutations in another BC susceptibility gene involved in DNA repair, i.e., CHEK2 may be associated with particular immunophenotypic molecular subtypes of this cancer. Two groups of patients: 1255 with BCs and 5496 healthy controls were genotyped for four CHEK2 mutations (I157T and three truncating mutations: 1100delC, IVS2 + 1G > A, del5395). BCs were tested by immunohistochemistry on tissue microarrays for ER, PR, HER-2, EGFR, and CK5/6 and were assigned to appropriate subtypes of immunophenotypic molecular classification. There was a significant association between CHEK2 mutations and the immunophenotypic molecular classification (P = 0.004). CHEK2-associated cancers were predominantly luminal (108/117 = 92.3%). CHEK2-I157T variant was associated with the luminal A subtype (P = 0.01), whereas CHEK2-truncating mutations were associated with the luminal B subtype (P = 0.005). Comparing the prevalence of CHEK2 mutations in BC with controls revealed that carriers of an I157T variant had OR of 1.80 for luminal A subtype and carriers of truncating mutations had OR of 6.26 for luminal B subtype of BC. To our knowledge, this is the first study showing that specific mutations in the same susceptibility gene are associated with different immunophenotypic molecular subtypes of BC. This association represents independent evidence supporting the biological significance of immunophenotypic molecular classification of BC.

Rapid Characterization of Candidate Biomarkers for Pancreatic Cancer Using Cell Microarrays (CMAs)

PubMed Central

Kim, Min-Sik; Kuppireddy, Sarada V.; Sakamuri, Sruthi; Singal, Mukul; Getnet, Derese; Harsha, H. C.; Goel, Renu; Balakrishnan, Lavanya; Jacob, Harrys K. C.; Kashyap, Manoj K.; Tankala, Shantal G.; Maitra, Anirban; Iacobuzio-Donahue, Christine A.; Jaffee, Elizabeth; Goggins, Michael G.; Velculescu, Victor E.; Hruban, Ralph H.; Pandey, Akhilesh

2013-01-01

Tissue microarrays have become a valuable tool for high-throughput analysis using immunohistochemical labeling. However, the large majority of biochemical studies are carried out in cell lines to further characterize candidate biomarkers or therapeutic targets with subsequent studies in animals or using primary tissues. Thus, cell line-based microarrays could be a useful screening tool in some situations. Here, we constructed a cell microarray (CMA) containing a panel of 40 pancreatic cancer cell lines available from American Type Culture Collection in addition to those locally available at Johns Hopkins. As proof of principle, we performed immunocytochemical labeling of an epithelial cell adhesion molecule (Ep-CAM), a molecule generally expressed in the epithelium, on this pancreatic cancer CMA. In addition, selected molecules that have been previously shown to be differentially expressed in pancreatic cancer in the literature were validated. For example, we observed strong labeling of CA19-9 antigen, a prognostic and predictive marker for pancreatic cancer. We also carried out a bioinformatics analysis of a literature curated catalog of pancreatic cancer biomarkers developed previously by our group and identified two candidate biomarkers, HLA class I and transmembrane protease, serine 4 (TMPRSS4), and examined their expression in the cell lines represented on the pancreatic cancer CMAs. Our results demonstrate the utility of CMAs as a useful resource for rapid screening of molecules of interest and suggest that CMAs can become a universal standard platform in cancer research. PMID:22985314

EgoNet: identification of human disease ego-network modules

PubMed Central

2014-01-01

Background Mining novel biomarkers from gene expression profiles for accurate disease classification is challenging due to small sample size and high noise in gene expression measurements. Several studies have proposed integrated analyses of microarray data and protein-protein interaction (PPI) networks to find diagnostic subnetwork markers. However, the neighborhood relationship among network member genes has not been fully considered by those methods, leaving many potential gene markers unidentified. The main idea of this study is to take full advantage of the biological observation that genes associated with the same or similar diseases commonly reside in the same neighborhood of molecular networks. Results We present EgoNet, a novel method based on egocentric network-analysis techniques, to exhaustively search and prioritize disease subnetworks and gene markers from a large-scale biological network. When applied to a triple-negative breast cancer (TNBC) microarray dataset, the top selected modules contain both known gene markers in TNBC and novel candidates, such as RAD51 and DOK1, which play a central role in their respective ego-networks by connecting many differentially expressed genes. Conclusions Our results suggest that EgoNet, which is based on the ego network concept, allows the identification of novel biomarkers and provides a deeper understanding of their roles in complex diseases. PMID:24773628

Classification of Microarray Data Using Kernel Fuzzy Inference System

PubMed Central

Kumar Rath, Santanu

2014-01-01

The DNA microarray classification technique has gained more popularity in both research and practice. In real data analysis, such as microarray data, the dataset contains a huge number of insignificant and irrelevant features that tend to lose useful information. Classes with high relevance and feature sets with high significance are generally referred for the selected features, which determine the samples classification into their respective classes. In this paper, kernel fuzzy inference system (K-FIS) algorithm is applied to classify the microarray data (leukemia) using t-test as a feature selection method. Kernel functions are used to map original data points into a higher-dimensional (possibly infinite-dimensional) feature space defined by a (usually nonlinear) function ϕ through a mathematical process called the kernel trick. This paper also presents a comparative study for classification using K-FIS along with support vector machine (SVM) for different set of features (genes). Performance parameters available in the literature such as precision, recall, specificity, F-measure, ROC curve, and accuracy are considered to analyze the efficiency of the classification model. From the proposed approach, it is apparent that K-FIS model obtains similar results when compared with SVM model. This is an indication that the proposed approach relies on kernel function. PMID:27433543

A prognostic classifier for patients with colorectal cancer liver metastasis, based on AURKA, PTGS2 and MMP9.

PubMed

Goos, Jeroen A C M; Coupé, Veerle M H; van de Wiel, Mark A; Diosdado, Begoña; Delis-Van Diemen, Pien M; Hiemstra, Annemieke C; de Cuba, Erienne M V; Beliën, Jeroen A M; Menke-van der Houven van Oordt, C Willemien; Geldof, Albert A; Meijer, Gerrit A; Hoekstra, Otto S; Fijneman, Remond J A

2016-01-12

Prognosis of patients with colorectal cancer liver metastasis (CRCLM) is estimated based on clinicopathological models. Stratifying patients based on tumor biology may have additional value. Tissue micro-arrays (TMAs), containing resected CRCLM and corresponding primary tumors from a multi-institutional cohort of 507 patients, were immunohistochemically stained for 18 candidate biomarkers. Cross-validated hazard rate ratios (HRRs) for overall survival (OS) and the proportion of HRRs with opposite effect (P(HRR < 1) or P(HRR > 1)) were calculated. A classifier was constructed by classification and regression tree (CART) analysis and its prognostic value determined by permutation analysis. Correlations between protein expression in primary tumor-CRCLM pairs were calculated. Based on their putative prognostic value, EGFR (P(HRR < 1) = .02), AURKA (P(HRR < 1) = .02), VEGFA (P(HRR < 1) = .02), PTGS2 (P(HRR < 1) = .01), SLC2A1 (P(HRR > 1) < 01), HIF1α (P(HRR > 1) = .06), KCNQ1 (P(HRR > 1) = .09), CEA (P (HRR > 1) = .05) and MMP9 (P(HRR < 1) = .07) were included in the CART analysis (n = 201). The resulting classifier was based on AURKA, PTGS2 and MMP9 expression and was associated with OS (HRR 2.79, p < .001), also after multivariate analysis (HRR 3.57, p < .001). The prognostic value of the biomarker-based classifier was superior to the clinicopathological model (p = .001). Prognostic value was highest for colon cancer patients (HRR 5.71, p < .001) and patients not treated with systemic therapy (HRR 3.48, p < .01). Classification based on protein expression in primary tumors could be based on AURKA expression only (HRR 2.59, p = .04). A classifier was generated for patients with CRCLM with improved prognostic value compared to the standard clinicopathological prognostic parameters, which may aid selection of patients who may benefit from adjuvant systemic therapy.

Identification of an Efficient Gene Expression Panel for Glioblastoma Classification

PubMed Central

Zelaya, Ivette; Laks, Dan R.; Zhao, Yining; Kawaguchi, Riki; Gao, Fuying; Kornblum, Harley I.; Coppola, Giovanni

2016-01-01

We present here a novel genetic algorithm-based random forest (GARF) modeling technique that enables a reduction in the complexity of large gene disease signatures to highly accurate, greatly simplified gene panels. When applied to 803 glioblastoma multiforme samples, this method allowed the 840-gene Verhaak et al. gene panel (the standard in the field) to be reduced to a 48-gene classifier, while retaining 90.91% classification accuracy, and outperforming the best available alternative methods. Additionally, using this approach we produced a 32-gene panel which allows for better consistency between RNA-seq and microarray-based classifications, improving cross-platform classification retention from 69.67% to 86.07%. A webpage producing these classifications is available at http://simplegbm.semel.ucla.edu. PMID:27855170

Characterizing biomarkers in osteosarcoma metastasis based on an ego-network.

PubMed

Liu, Zhen; Song, Yan

2017-06-01

To characterize biomarkers that underlie osteosarcoma (OS) metastasis based on an ego-network. From the microarray data, we obtained 13,326 genes. By combining PPI data and microarray data, 10,520 shared genes were found and constructed into ego-networks. 17 significant ego-networks were identified with p < 0.05. In the pathway enrichment analysis, seven ego-networks were identified with the most significant pathway. These significant ego-modules were potential biomarkers that reveal the potential mechanisms in OS metastasis, which may contribute to understanding cancer prognoses and providing new perspectives in the treatment of cancer.

voomDDA: discovery of diagnostic biomarkers and classification of RNA-seq data.

PubMed

Zararsiz, Gokmen; Goksuluk, Dincer; Klaus, Bernd; Korkmaz, Selcuk; Eldem, Vahap; Karabulut, Erdem; Ozturk, Ahmet

2017-01-01

RNA-Seq is a recent and efficient technique that uses the capabilities of next-generation sequencing technology for characterizing and quantifying transcriptomes. One important task using gene-expression data is to identify a small subset of genes that can be used to build diagnostic classifiers particularly for cancer diseases. Microarray based classifiers are not directly applicable to RNA-Seq data due to its discrete nature. Overdispersion is another problem that requires careful modeling of mean and variance relationship of the RNA-Seq data. In this study, we present voomDDA classifiers: variance modeling at the observational level (voom) extensions of the nearest shrunken centroids (NSC) and the diagonal discriminant classifiers. VoomNSC is one of these classifiers and brings voom and NSC approaches together for the purpose of gene-expression based classification. For this purpose, we propose weighted statistics and put these weighted statistics into the NSC algorithm. The VoomNSC is a sparse classifier that models the mean-variance relationship using the voom method and incorporates voom's precision weights into the NSC classifier via weighted statistics. A comprehensive simulation study was designed and four real datasets are used for performance assessment. The overall results indicate that voomNSC performs as the sparsest classifier. It also provides the most accurate results together with power-transformed Poisson linear discriminant analysis, rlog transformed support vector machines and random forests algorithms. In addition to prediction purposes, the voomNSC classifier can be used to identify the potential diagnostic biomarkers for a condition of interest. Through this work, statistical learning methods proposed for microarrays can be reused for RNA-Seq data. An interactive web application is freely available at http://www.biosoft.hacettepe.edu.tr/voomDDA/.

Identifying significant genetic regulatory networks in the prostate cancer from microarray data based on transcription factor analysis and conditional independency

PubMed Central

2009-01-01

Background Prostate cancer is a world wide leading cancer and it is characterized by its aggressive metastasis. According to the clinical heterogeneity, prostate cancer displays different stages and grades related to the aggressive metastasis disease. Although numerous studies used microarray analysis and traditional clustering method to identify the individual genes during the disease processes, the important gene regulations remain unclear. We present a computational method for inferring genetic regulatory networks from micorarray data automatically with transcription factor analysis and conditional independence testing to explore the potential significant gene regulatory networks that are correlated with cancer, tumor grade and stage in the prostate cancer. Results To deal with missing values in microarray data, we used a K-nearest-neighbors (KNN) algorithm to determine the precise expression values. We applied web services technology to wrap the bioinformatics toolkits and databases to automatically extract the promoter regions of DNA sequences and predicted the transcription factors that regulate the gene expressions. We adopt the microarray datasets consists of 62 primary tumors, 41 normal prostate tissues from Stanford Microarray Database (SMD) as a target dataset to evaluate our method. The predicted results showed that the possible biomarker genes related to cancer and denoted the androgen functions and processes may be in the development of the prostate cancer and promote the cell death in cell cycle. Our predicted results showed that sub-networks of genes SREBF1, STAT6 and PBX1 are strongly related to a high extent while ETS transcription factors ELK1, JUN and EGR2 are related to a low extent. Gene SLC22A3 may explain clinically the differentiation associated with the high grade cancer compared with low grade cancer. Enhancer of Zeste Homolg 2 (EZH2) regulated by RUNX1 and STAT3 is correlated to the pathological stage. Conclusions We provide a computational framework to reconstruct the genetic regulatory network from the microarray data using biological knowledge and constraint-based inferences. Our method is helpful in verifying possible interaction relations in gene regulatory networks and filtering out incorrect relations inferred by imperfect methods. We predicted not only individual gene related to cancer but also discovered significant gene regulation networks. Our method is also validated in several enriched published papers and databases and the significant gene regulatory networks perform critical biological functions and processes including cell adhesion molecules, androgen and estrogen metabolism, smooth muscle contraction, and GO-annotated processes. Those significant gene regulations and the critical concept of tumor progression are useful to understand cancer biology and disease treatment. PMID:20025723

Empirical evaluation of data normalization methods for molecular classification.

PubMed

Huang, Huei-Chung; Qin, Li-Xuan

2018-01-01

Data artifacts due to variations in experimental handling are ubiquitous in microarray studies, and they can lead to biased and irreproducible findings. A popular approach to correct for such artifacts is through post hoc data adjustment such as data normalization. Statistical methods for data normalization have been developed and evaluated primarily for the discovery of individual molecular biomarkers. Their performance has rarely been studied for the development of multi-marker molecular classifiers-an increasingly important application of microarrays in the era of personalized medicine. In this study, we set out to evaluate the performance of three commonly used methods for data normalization in the context of molecular classification, using extensive simulations based on re-sampling from a unique pair of microRNA microarray datasets for the same set of samples. The data and code for our simulations are freely available as R packages at GitHub. In the presence of confounding handling effects, all three normalization methods tended to improve the accuracy of the classifier when evaluated in an independent test data. The level of improvement and the relative performance among the normalization methods depended on the relative level of molecular signal, the distributional pattern of handling effects (e.g., location shift vs scale change), and the statistical method used for building the classifier. In addition, cross-validation was associated with biased estimation of classification accuracy in the over-optimistic direction for all three normalization methods. Normalization may improve the accuracy of molecular classification for data with confounding handling effects; however, it cannot circumvent the over-optimistic findings associated with cross-validation for assessing classification accuracy.

Application of wavelet transformation and adaptive neighborhood based modified backpropagation (ANMBP) for classification of brain cancer

NASA Astrophysics Data System (ADS)

Werdiningsih, Indah; Zaman, Badrus; Nuqoba, Barry

2017-08-01

This paper presents classification of brain cancer using wavelet transformation and Adaptive Neighborhood Based Modified Backpropagation (ANMBP). Three stages of the processes, namely features extraction, features reduction, and classification process. Wavelet transformation is used for feature extraction and ANMBP is used for classification process. The result of features extraction is feature vectors. Features reduction used 100 energy values per feature and 10 energy values per feature. Classifications of brain cancer are normal, alzheimer, glioma, and carcinoma. Based on simulation results, 10 energy values per feature can be used to classify brain cancer correctly. The correct classification rate of proposed system is 95 %. This research demonstrated that wavelet transformation can be used for features extraction and ANMBP can be used for classification of brain cancer.

Prognostic significance of membrane-associated mucins 1 and 4 in gastric adenocarcinoma.

PubMed

Hwang, Ilseon; Kang, Yu Na; Kim, Jin Young; DO, Young Rok; Song, Hong Suk; Park, Keon Uk

2012-08-01

Aberrant expression of mucins is likely associated with cancer biology as alterations in the expression and/or glycosylation patterns of various mucins have been noted. Expression of the mucin family in gastric cancers has been reported in numerous studies, but the results are conflicting. Therefore, we investigated the potential use of mucin (MUC)1 and 4 as prognostic markers in gastric cancer according to histological subtype. Three-hundred and sixty-five gastric adenocarcinoma patients who underwent surgical resection were selected for this study. Among the 365 gastric cancer samples tested here, 34% consisted of early gastric cancer and 66% were advanced. In terms of location, 68.7% of the cohort had intestinal-type cancer and 30.7% had diffuse-type. We constructed tissue microarrays with formalin-fixed paraffin-embedded blocks of gastric cancer and these micro-arrays were evaluated for phenotypic expression of MUC1/4 using monoclonal antibodies. Two-hundred and ninety-two patients (92.7%) were positive for MUC1 and 216 (60.5%) were positive for MUC4. MUC1 expression was not correlated with any other clinicopathological variables such as age, gender, depth of invasion, lymph node metastasis, Lauren classification or recurrence. However, loss of MUC4 expression was significantly correlated with recurrence (p=0.033). MUC4 expression was also significantly correlated with better disease-free survival (p=0.049) and particularly in the intestinal-type (p=0.018). Our present findings demonstrated that loss of MUC4 expression can be used as a prognostic marker in gastric cancer. Loss of MUC4 expression is a prognostic indicator of increased recurrence and poor disease-free survival in patients with gastric cancer.

Robust gene selection methods using weighting schemes for microarray data analysis.

PubMed

Kang, Suyeon; Song, Jongwoo

2017-09-02

A common task in microarray data analysis is to identify informative genes that are differentially expressed between two different states. Owing to the high-dimensional nature of microarray data, identification of significant genes has been essential in analyzing the data. However, the performances of many gene selection techniques are highly dependent on the experimental conditions, such as the presence of measurement error or a limited number of sample replicates. We have proposed new filter-based gene selection techniques, by applying a simple modification to significance analysis of microarrays (SAM). To prove the effectiveness of the proposed method, we considered a series of synthetic datasets with different noise levels and sample sizes along with two real datasets. The following findings were made. First, our proposed methods outperform conventional methods for all simulation set-ups. In particular, our methods are much better when the given data are noisy and sample size is small. They showed relatively robust performance regardless of noise level and sample size, whereas the performance of SAM became significantly worse as the noise level became high or sample size decreased. When sufficient sample replicates were available, SAM and our methods showed similar performance. Finally, our proposed methods are competitive with traditional methods in classification tasks for microarrays. The results of simulation study and real data analysis have demonstrated that our proposed methods are effective for detecting significant genes and classification tasks, especially when the given data are noisy or have few sample replicates. By employing weighting schemes, we can obtain robust and reliable results for microarray data analysis.

Microarray Meta-Analysis Identifies Acute Lung Injury Biomarkers in Donor Lungs That Predict Development of Primary Graft Failure in Recipients

PubMed Central

Haitsma, Jack J.; Furmli, Suleiman; Masoom, Hussain; Liu, Mingyao; Imai, Yumiko; Slutsky, Arthur S.; Beyene, Joseph; Greenwood, Celia M. T.; dos Santos, Claudia

2012-01-01

Objectives To perform a meta-analysis of gene expression microarray data from animal studies of lung injury, and to identify an injury-specific gene expression signature capable of predicting the development of lung injury in humans. Methods We performed a microarray meta-analysis using 77 microarray chips across six platforms, two species and different animal lung injury models exposed to lung injury with or/and without mechanical ventilation. Individual gene chips were classified and grouped based on the strategy used to induce lung injury. Effect size (change in gene expression) was calculated between non-injurious and injurious conditions comparing two main strategies to pool chips: (1) one-hit and (2) two-hit lung injury models. A random effects model was used to integrate individual effect sizes calculated from each experiment. Classification models were built using the gene expression signatures generated by the meta-analysis to predict the development of lung injury in human lung transplant recipients. Results Two injury-specific lists of differentially expressed genes generated from our meta-analysis of lung injury models were validated using external data sets and prospective data from animal models of ventilator-induced lung injury (VILI). Pathway analysis of gene sets revealed that both new and previously implicated VILI-related pathways are enriched with differentially regulated genes. Classification model based on gene expression signatures identified in animal models of lung injury predicted development of primary graft failure (PGF) in lung transplant recipients with larger than 80% accuracy based upon injury profiles from transplant donors. We also found that better classifier performance can be achieved by using meta-analysis to identify differentially-expressed genes than using single study-based differential analysis. Conclusion Taken together, our data suggests that microarray analysis of gene expression data allows for the detection of “injury" gene predictors that can classify lung injury samples and identify patients at risk for clinically relevant lung injury complications. PMID:23071521

Cancer survival analysis using semi-supervised learning method based on Cox and AFT models with L1/2 regularization.

PubMed

Liang, Yong; Chai, Hua; Liu, Xiao-Ying; Xu, Zong-Ben; Zhang, Hai; Leung, Kwong-Sak

2016-03-01

One of the most important objectives of the clinical cancer research is to diagnose cancer more accurately based on the patients' gene expression profiles. Both Cox proportional hazards model (Cox) and accelerated failure time model (AFT) have been widely adopted to the high risk and low risk classification or survival time prediction for the patients' clinical treatment. Nevertheless, two main dilemmas limit the accuracy of these prediction methods. One is that the small sample size and censored data remain a bottleneck for training robust and accurate Cox classification model. In addition to that, similar phenotype tumours and prognoses are actually completely different diseases at the genotype and molecular level. Thus, the utility of the AFT model for the survival time prediction is limited when such biological differences of the diseases have not been previously identified. To try to overcome these two main dilemmas, we proposed a novel semi-supervised learning method based on the Cox and AFT models to accurately predict the treatment risk and the survival time of the patients. Moreover, we adopted the efficient L1/2 regularization approach in the semi-supervised learning method to select the relevant genes, which are significantly associated with the disease. The results of the simulation experiments show that the semi-supervised learning model can significant improve the predictive performance of Cox and AFT models in survival analysis. The proposed procedures have been successfully applied to four real microarray gene expression and artificial evaluation datasets. The advantages of our proposed semi-supervised learning method include: 1) significantly increase the available training samples from censored data; 2) high capability for identifying the survival risk classes of patient in Cox model; 3) high predictive accuracy for patients' survival time in AFT model; 4) strong capability of the relevant biomarker selection. Consequently, our proposed semi-supervised learning model is one more appropriate tool for survival analysis in clinical cancer research.

Design and evaluation of Actichip, a thematic microarray for the study of the actin cytoskeleton

PubMed Central

Muller, Jean; Mehlen, André; Vetter, Guillaume; Yatskou, Mikalai; Muller, Arnaud; Chalmel, Frédéric; Poch, Olivier; Friederich, Evelyne; Vallar, Laurent

2007-01-01

Background The actin cytoskeleton plays a crucial role in supporting and regulating numerous cellular processes. Mutations or alterations in the expression levels affecting the actin cytoskeleton system or related regulatory mechanisms are often associated with complex diseases such as cancer. Understanding how qualitative or quantitative changes in expression of the set of actin cytoskeleton genes are integrated to control actin dynamics and organisation is currently a challenge and should provide insights in identifying potential targets for drug discovery. Here we report the development of a dedicated microarray, the Actichip, containing 60-mer oligonucleotide probes for 327 genes selected for transcriptome analysis of the human actin cytoskeleton. Results Genomic data and sequence analysis features were retrieved from GenBank and stored in an integrative database called Actinome. From these data, probes were designed using a home-made program (CADO4MI) allowing sequence refinement and improved probe specificity by combining the complementary information recovered from the UniGene and RefSeq databases. Actichip performance was analysed by hybridisation with RNAs extracted from epithelial MCF-7 cells and human skeletal muscle. Using thoroughly standardised procedures, we obtained microarray images with excellent quality resulting in high data reproducibility. Actichip displayed a large dynamic range extending over three logs with a limit of sensitivity between one and ten copies of transcript per cell. The array allowed accurate detection of small changes in gene expression and reliable classification of samples based on the expression profiles of tissue-specific genes. When compared to two other oligonucleotide microarray platforms, Actichip showed similar sensitivity and concordant expression ratios. Moreover, Actichip was able to discriminate the highly similar actin isoforms whereas the two other platforms did not. Conclusion Our data demonstrate that Actichip is a powerful alternative to commercial high density microarrays for cytoskeleton gene profiling in normal or pathological samples. Actichip is available upon request. PMID:17727702

Intra-tumor heterogeneity in breast cancer has limited impact on transcriptomic-based molecular profiling.

PubMed

Karthik, Govindasamy-Muralidharan; Rantalainen, Mattias; Stålhammar, Gustav; Lövrot, John; Ullah, Ikram; Alkodsi, Amjad; Ma, Ran; Wedlund, Lena; Lindberg, Johan; Frisell, Jan; Bergh, Jonas; Hartman, Johan

2017-11-29

Transcriptomic profiling of breast tumors provides opportunity for subtyping and molecular-based patient stratification. In diagnostic applications the specimen profiled should be representative of the expression profile of the whole tumor and ideally capture properties of the most aggressive part of the tumor. However, breast cancers commonly exhibit intra-tumor heterogeneity at molecular, genomic and in phenotypic level, which can arise during tumor evolution. Currently it is not established to what extent a random sampling approach may influence molecular breast cancer diagnostics. In this study we applied RNA-sequencing to quantify gene expression in 43 pieces (2-5 pieces per tumor) from 12 breast tumors (Cohort 1). We determined molecular subtype and transcriptomic grade for all tumor pieces and analysed to what extent pieces originating from the same tumors are concordant or discordant with each other. Additionally, we validated our finding in an independent cohort consisting of 19 pieces (2-6 pieces per tumor) from 6 breast tumors (Cohort 2) profiled using microarray technique. Exome sequencing was also performed on this cohort, to investigate the extent of intra-tumor genomic heterogeneity versus the intra-tumor molecular subtype classifications. Molecular subtyping was consistent in 11 out of 12 tumors and transcriptomic grade assignments were consistent in 11 out of 12 tumors as well. Molecular subtype predictions revealed consistent subtypes in four out of six patients in this cohort 2. Interestingly, we observed extensive intra-tumor genomic heterogeneity in these tumor pieces but not in their molecular subtype classifications. Our results suggest that macroscopic intra-tumoral transcriptomic heterogeneity is limited and unlikely to have an impact on molecular diagnostics for most patients.

Empirical evaluation of data normalization methods for molecular classification

PubMed Central

Huang, Huei-Chung

2018-01-01

Background Data artifacts due to variations in experimental handling are ubiquitous in microarray studies, and they can lead to biased and irreproducible findings. A popular approach to correct for such artifacts is through post hoc data adjustment such as data normalization. Statistical methods for data normalization have been developed and evaluated primarily for the discovery of individual molecular biomarkers. Their performance has rarely been studied for the development of multi-marker molecular classifiers—an increasingly important application of microarrays in the era of personalized medicine. Methods In this study, we set out to evaluate the performance of three commonly used methods for data normalization in the context of molecular classification, using extensive simulations based on re-sampling from a unique pair of microRNA microarray datasets for the same set of samples. The data and code for our simulations are freely available as R packages at GitHub. Results In the presence of confounding handling effects, all three normalization methods tended to improve the accuracy of the classifier when evaluated in an independent test data. The level of improvement and the relative performance among the normalization methods depended on the relative level of molecular signal, the distributional pattern of handling effects (e.g., location shift vs scale change), and the statistical method used for building the classifier. In addition, cross-validation was associated with biased estimation of classification accuracy in the over-optimistic direction for all three normalization methods. Conclusion Normalization may improve the accuracy of molecular classification for data with confounding handling effects; however, it cannot circumvent the over-optimistic findings associated with cross-validation for assessing classification accuracy. PMID:29666754

Pathohistological classification systems in gastric cancer: Diagnostic relevance and prognostic value

PubMed Central

Berlth, Felix; Bollschweiler, Elfriede; Drebber, Uta; Hoelscher, Arnulf H; Moenig, Stefan

2014-01-01

Several pathohistological classification systems exist for the diagnosis of gastric cancer. Many studies have investigated the correlation between the pathohistological characteristics in gastric cancer and patient characteristics, disease specific criteria and overall outcome. It is still controversial as to which classification system imparts the most reliable information, and therefore, the choice of system may vary in clinical routine. In addition to the most common classification systems, such as the Laurén and the World Health Organization (WHO) classifications, other authors have tried to characterize and classify gastric cancer based on the microscopic morphology and in reference to the clinical outcome of the patients. In more than 50 years of systematic classification of the pathohistological characteristics of gastric cancer, there is no sole classification system that is consistently used worldwide in diagnostics and research. However, several national guidelines for the treatment of gastric cancer refer to the Laurén or the WHO classifications regarding therapeutic decision-making, which underlines the importance of a reliable classification system for gastric cancer. The latest results from gastric cancer studies indicate that it might be useful to integrate DNA- and RNA-based features of gastric cancer into the classification systems to establish prognostic relevance. This article reviews the diagnostic relevance and the prognostic value of different pathohistological classification systems in gastric cancer. PMID:24914328

Computational selection of antibody-drug conjugate targets for breast cancer

PubMed Central

Fauteux, François; Hill, Jennifer J.; Jaramillo, Maria L.; Pan, Youlian; Phan, Sieu; Famili, Fazel; O'Connor-McCourt, Maureen

2016-01-01

The selection of therapeutic targets is a critical aspect of antibody-drug conjugate research and development. In this study, we applied computational methods to select candidate targets overexpressed in three major breast cancer subtypes as compared with a range of vital organs and tissues. Microarray data corresponding to over 8,000 tissue samples were collected from the public domain. Breast cancer samples were classified into molecular subtypes using an iterative ensemble approach combining six classification algorithms and three feature selection techniques, including a novel kernel density-based method. This feature selection method was used in conjunction with differential expression and subcellular localization information to assemble a primary list of targets. A total of 50 cell membrane targets were identified, including one target for which an antibody-drug conjugate is in clinical use, and six targets for which antibody-drug conjugates are in clinical trials for the treatment of breast cancer and other solid tumors. In addition, 50 extracellular proteins were identified as potential targets for non-internalizing strategies and alternative modalities. Candidate targets linked with the epithelial-to-mesenchymal transition were identified by analyzing differential gene expression in epithelial and mesenchymal tumor-derived cell lines. Overall, these results show that mining human gene expression data has the power to select and prioritize breast cancer antibody-drug conjugate targets, and the potential to lead to new and more effective cancer therapeutics. PMID:26700623

A DNA microarray-based methylation-sensitive (MS)-AFLP hybridization method for genetic and epigenetic analyses.

PubMed

Yamamoto, F; Yamamoto, M

2004-07-01

We previously developed a PCR-based DNA fingerprinting technique named the Methylation Sensitive (MS)-AFLP method, which permits comparative genome-wide scanning of methylation status with a manageable number of fingerprinting experiments. The technique uses the methylation sensitive restriction enzyme NotI in the context of the existing Amplified Fragment Length Polymorphism (AFLP) method. Here we report the successful conversion of this gel electrophoresis-based DNA fingerprinting technique into a DNA microarray hybridization technique (DNA Microarray MS-AFLP). By performing a total of 30 (15 x 2 reciprocal labeling) DNA Microarray MS-AFLP hybridization experiments on genomic DNA from two breast and three prostate cancer cell lines in all pairwise combinations, and Southern hybridization experiments using more than 100 different probes, we have demonstrated that the DNA Microarray MS-AFLP is a reliable method for genetic and epigenetic analyses. No statistically significant differences were observed in the number of differences between the breast-prostate hybridization experiments and the breast-breast or prostate-prostate comparisons.

Cancer-cell intrinsic gene expression signatures overcome intratumoural heterogeneity bias in colorectal cancer patient classification

PubMed Central

Dunne, Philip D.; Alderdice, Matthew; O'Reilly, Paul G.; Roddy, Aideen C.; McCorry, Amy M. B.; Richman, Susan; Maughan, Tim; McDade, Simon S.; Johnston, Patrick G.; Longley, Daniel B.; Kay, Elaine; McArt, Darragh G.; Lawler, Mark

2017-01-01

Stromal-derived intratumoural heterogeneity (ITH) has been shown to undermine molecular stratification of patients into appropriate prognostic/predictive subgroups. Here, using several clinically relevant colorectal cancer (CRC) gene expression signatures, we assessed the susceptibility of these signatures to the confounding effects of ITH using gene expression microarray data obtained from multiple tumour regions of a cohort of 24 patients, including central tumour, the tumour invasive front and lymph node metastasis. Sample clustering alongside correlative assessment revealed variation in the ability of each signature to cluster samples according to patient-of-origin rather than region-of-origin within the multi-region dataset. Signatures focused on cancer-cell intrinsic gene expression were found to produce more clinically useful, patient-centred classifiers, as exemplified by the CRC intrinsic signature (CRIS), which robustly clustered samples by patient-of-origin rather than region-of-origin. These findings highlight the potential of cancer-cell intrinsic signatures to reliably stratify CRC patients by minimising the confounding effects of stromal-derived ITH. PMID:28561046

Microarray-based screening of heat shock protein inhibitors.

PubMed

Schax, Emilia; Walter, Johanna-Gabriela; Märzhäuser, Helene; Stahl, Frank; Scheper, Thomas; Agard, David A; Eichner, Simone; Kirschning, Andreas; Zeilinger, Carsten

2014-06-20

Based on the importance of heat shock proteins (HSPs) in diseases such as cancer, Alzheimer's disease or malaria, inhibitors of these chaperons are needed. Today's state-of-the-art techniques to identify HSP inhibitors are performed in microplate format, requiring large amounts of proteins and potential inhibitors. In contrast, we have developed a miniaturized protein microarray-based assay to identify novel inhibitors, allowing analysis with 300 pmol of protein. The assay is based on competitive binding of fluorescence-labeled ATP and potential inhibitors to the ATP-binding site of HSP. Therefore, the developed microarray enables the parallel analysis of different ATP-binding proteins on a single microarray. We have demonstrated the possibility of multiplexing by immobilizing full-length human HSP90α and HtpG of Helicobacter pylori on microarrays. Fluorescence-labeled ATP was competed by novel geldanamycin/reblastatin derivatives with IC50 values in the range of 0.5 nM to 4 μM and Z(*)-factors between 0.60 and 0.96. Our results demonstrate the potential of a target-oriented multiplexed protein microarray to identify novel inhibitors for different members of the HSP90 family. Copyright © 2014 Elsevier B.V. All rights reserved.

Micro-array isolation of circulating tumor cells (CTCs): the droplet biopsy chip

NASA Astrophysics Data System (ADS)

Panchapakesan, B.

2017-08-01

We present a new method for circulating tumor cell capture based on micro-array isolation from droplets. Called droplet biopsy, our technique uses a 76-element array of carbon nanotube devices functionalized with anti-EpCAM and antiHer2 antibodies for immunocapture of spiked breast cancer cells in the blood. This droplet biopsy chip can enable capture of CTCs based on both positive and negative selection strategy. Negative selection is achieved through depletion of contaminating leukocytes through the differential settling of blood into layers. We report 55%-100% cancer cell capture yield in this first droplet biopsy chip study. The droplet biopsy is an enabling idea where one can capture CTCs based on multiple biomarkers in a single blood sample.

The function of BTG3 in colorectal cancer cells and its possible signaling pathway.

PubMed

Lv, Chi; Wang, Heling; Tong, Yuxin; Yin, Hongzhuan; Wang, Dalu; Yan, Zhaopeng; Liang, Yichao; Wu, Di; Su, Qi

2018-02-01

B-cell translocation gene 3 (BTG3) has been identified as a candidate driver gene for various cancers, but its specific role in colorectal cancer (CRC) is poorly understood. We aimed to investigate the relationship between expression of BTG3 and clinicopathological features and prognosis, as well as to explore the effects and the role of a possible BTG3 molecular mechanism on aggressive colorectal cancer behavior. BTG3 expression was assessed by immunohistochemistry (IHC) on specimens from 140 patients with CRC. The association of BTG3 expression with clinicopathological features was examined. To confirm the biological role of BTG3 in CRC, two CRC cell lines expressing BTG3 were used and BTG3 expression was knocked down by shRNA. CCK-8, cell cycle, apoptosis, migration, and invasion assays were performed. The influence of BTG3 knockdown was further investigated by genomic microarray to uncover the potential molecular mechanisms underlying BTG3-mediated CRC development and progression. BTG3 was downregulated in colorectal cancer tissues and positively correlated with pathological classification (p = 0.037), depth of invasion (p = 0.016), distant metastasis (p = 0.024), TNM stage (p = 0.007), and overall survival (OS) and disease-free survival (DFS). BTG3 knockdown promoted cell proliferation, migration, invasion, relieved G2 arrest, and inhibited apoptosis in HCT116 and LoVo cells. A genomic microarray analysis showed that numerous tumor-associated signaling pathways and oncogenes were altered by BTG3 knockdown. At the mRNA level, nine genes referred to the extracellular-regulated kinase/mitogen-activated protein kinase pathway were differentially expressed. Western blotting revealed that BTG3 knockdown upregulated PAK2, RPS6KA5, YWHAB, and signal transducer and activator of transcription (STAT)3 protein levels, but downregulated RAP1A, DUSP6, and STAT1 protein expression, which was consistent with the genomic microarray data. BTG3 expression might contribute to CRC carcinogenesis. BTG3 knockdown might strengthen the aggressive colorectal cancer behavior.

Differential gene expression detection and sample classification using penalized linear regression models.

PubMed

Wu, Baolin

2006-02-15

Differential gene expression detection and sample classification using microarray data have received much research interest recently. Owing to the large number of genes p and small number of samples n (p > n), microarray data analysis poses big challenges for statistical analysis. An obvious problem owing to the 'large p small n' is over-fitting. Just by chance, we are likely to find some non-differentially expressed genes that can classify the samples very well. The idea of shrinkage is to regularize the model parameters to reduce the effects of noise and produce reliable inferences. Shrinkage has been successfully applied in the microarray data analysis. The SAM statistics proposed by Tusher et al. and the 'nearest shrunken centroid' proposed by Tibshirani et al. are ad hoc shrinkage methods. Both methods are simple, intuitive and prove to be useful in empirical studies. Recently Wu proposed the penalized t/F-statistics with shrinkage by formally using the (1) penalized linear regression models for two-class microarray data, showing good performance. In this paper we systematically discussed the use of penalized regression models for analyzing microarray data. We generalize the two-class penalized t/F-statistics proposed by Wu to multi-class microarray data. We formally derive the ad hoc shrunken centroid used by Tibshirani et al. using the (1) penalized regression models. And we show that the penalized linear regression models provide a rigorous and unified statistical framework for sample classification and differential gene expression detection.

Multi-task feature selection in microarray data by binary integer programming.

PubMed

Lan, Liang; Vucetic, Slobodan

2013-12-20

A major challenge in microarray classification is that the number of features is typically orders of magnitude larger than the number of examples. In this paper, we propose a novel feature filter algorithm to select the feature subset with maximal discriminative power and minimal redundancy by solving a quadratic objective function with binary integer constraints. To improve the computational efficiency, the binary integer constraints are relaxed and a low-rank approximation to the quadratic term is applied. The proposed feature selection algorithm was extended to solve multi-task microarray classification problems. We compared the single-task version of the proposed feature selection algorithm with 9 existing feature selection methods on 4 benchmark microarray data sets. The empirical results show that the proposed method achieved the most accurate predictions overall. We also evaluated the multi-task version of the proposed algorithm on 8 multi-task microarray datasets. The multi-task feature selection algorithm resulted in significantly higher accuracy than when using the single-task feature selection methods.

Cancer classification in the genomic era: five contemporary problems.

PubMed

Song, Qingxuan; Merajver, Sofia D; Li, Jun Z

2015-10-19

Classification is an everyday instinct as well as a full-fledged scientific discipline. Throughout the history of medicine, disease classification is central to how we develop knowledge, make diagnosis, and assign treatment. Here, we discuss the classification of cancer and the process of categorizing cancer subtypes based on their observed clinical and biological features. Traditionally, cancer nomenclature is primarily based on organ location, e.g., "lung cancer" designates a tumor originating in lung structures. Within each organ-specific major type, finer subgroups can be defined based on patient age, cell type, histological grades, and sometimes molecular markers, e.g., hormonal receptor status in breast cancer or microsatellite instability in colorectal cancer. In the past 15+ years, high-throughput technologies have generated rich new data regarding somatic variations in DNA, RNA, protein, or epigenomic features for many cancers. These data, collected for increasingly large tumor cohorts, have provided not only new insights into the biological diversity of human cancers but also exciting opportunities to discover previously unrecognized cancer subtypes. Meanwhile, the unprecedented volume and complexity of these data pose significant challenges for biostatisticians, cancer biologists, and clinicians alike. Here, we review five related issues that represent contemporary problems in cancer taxonomy and interpretation. (1) How many cancer subtypes are there? (2) How can we evaluate the robustness of a new classification system? (3) How are classification systems affected by intratumor heterogeneity and tumor evolution? (4) How should we interpret cancer subtypes? (5) Can multiple classification systems co-exist? While related issues have existed for a long time, we will focus on those aspects that have been magnified by the recent influx of complex multi-omics data. Exploration of these problems is essential for data-driven refinement of cancer classification and the successful application of these concepts in precision medicine.

Cancer Pain: A Critical Review of Mechanism-based Classification and Physical Therapy Management in Palliative Care

PubMed Central

Kumar, Senthil P

2011-01-01

Mechanism-based classification and physical therapy management of pain is essential to effectively manage painful symptoms in patients attending palliative care. The objective of this review is to provide a detailed review of mechanism-based classification and physical therapy management of patients with cancer pain. Cancer pain can be classified based upon pain symptoms, pain mechanisms and pain syndromes. Classification based upon mechanisms not only addresses the underlying pathophysiology but also provides us with an understanding behind patient's symptoms and treatment responses. Existing evidence suggests that the five mechanisms – central sensitization, peripheral sensitization, sympathetically maintained pain, nociceptive and cognitive-affective – operate in patients with cancer pain. Summary of studies showing evidence for physical therapy treatment methods for cancer pain follows with suggested therapeutic implications. Effective palliative physical therapy care using a mechanism-based classification model should be tailored to suit each patient's findings, using a biopsychosocial model of pain. PMID:21976851

Discriminant analysis for fast multiclass data classification through regularized kernel function approximation.

PubMed

Ghorai, Santanu; Mukherjee, Anirban; Dutta, Pranab K

2010-06-01

In this brief we have proposed the multiclass data classification by computationally inexpensive discriminant analysis through vector-valued regularized kernel function approximation (VVRKFA). VVRKFA being an extension of fast regularized kernel function approximation (FRKFA), provides the vector-valued response at single step. The VVRKFA finds a linear operator and a bias vector by using a reduced kernel that maps a pattern from feature space into the low dimensional label space. The classification of patterns is carried out in this low dimensional label subspace. A test pattern is classified depending on its proximity to class centroids. The effectiveness of the proposed method is experimentally verified and compared with multiclass support vector machine (SVM) on several benchmark data sets as well as on gene microarray data for multi-category cancer classification. The results indicate the significant improvement in both training and testing time compared to that of multiclass SVM with comparable testing accuracy principally in large data sets. Experiments in this brief also serve as comparison of performance of VVRKFA with stratified random sampling and sub-sampling.

Highly sensitive detection of multiple tumor markers for lung cancer using gold nanoparticle probes and microarrays.

PubMed

Gao, Wanlei; Wang, Wentao; Yao, Shihua; Wu, Shan; Zhang, Honglian; Zhang, Jishen; Jing, Fengxiang; Mao, Hongju; Jin, Qinghui; Cong, Hui; Jia, Chunping; Zhang, Guojun; Zhao, Jianlong

2017-03-15

Assay of multiple serum tumor markers such as carcinoembryonic antigen (CEA), cytokeratin 19 fragment antigen (CYFRA21-1), and neuron specific enolase (NSE), is important for the early diagnosis of lung cancer. Dickkopf-1 (DKK1), a novel serological and histochemical biomarker, was recently reported to be preferentially expressed in lung cancer. Four target proteins were sandwiched by capture antibodies attached to microarrays and detection antibodies carried on modified gold nanoparticles. Optical signals generated by the sandwich structures were amplified by gold deposition with HAuCl 4 and H 2 O 2 , and were observable by microscopy or the naked eye. The four tumor markers were subsequently measured in 106 lung cancer patients and 42 healthy persons. The assay was capable of detecting multiple biomarkers in serum sample at concentration of <1 ng mL -1 in 1 h. Combined detection of the four tumor markers highly improved the sensitivity (to 87.74%) for diagnosis of lung cancer compared with sensitivity of single markers. A rapid, highly sensitive co-detection method for multiple biomarkers based on gold nanoparticles and microarrays was developed. In clinical use, it would be expected to improve the early diagnosis of lung cancer. Copyright © 2016 Elsevier B.V. All rights reserved.

A lymphocyte spatial distribution graph-based method for automated classification of recurrence risk on lung cancer images

NASA Astrophysics Data System (ADS)

Garciá-Arteaga, Juan D.; Corredor, Germán.; Wang, Xiangxue; Velcheti, Vamsidhar; Madabhushi, Anant; Romero, Eduardo

2017-11-01

Tumor-infiltrating lymphocytes occurs when various classes of white blood cells migrate from the blood stream towards the tumor, infiltrating it. The presence of TIL is predictive of the response of the patient to therapy. In this paper, we show how the automatic detection of lymphocytes in digital H and E histopathological images and the quantitative evaluation of the global lymphocyte configuration, evaluated through global features extracted from non-parametric graphs, constructed from the lymphocytes' detected positions, can be correlated to the patient's outcome in early-stage non-small cell lung cancer (NSCLC). The method was assessed on a tissue microarray cohort composed of 63 NSCLC cases. From the evaluated graphs, minimum spanning trees and K-nn showed the highest predictive ability, yielding F1 Scores of 0.75 and 0.72 and accuracies of 0.67 and 0.69, respectively. The predictive power of the proposed methodology indicates that graphs may be used to develop objective measures of the infiltration grade of tumors, which can, in turn, be used by pathologists to improve the decision making and treatment planning processes.

Global gene expression profiling of oral cavity cancers suggests molecular heterogeneity within anatomic subsites

PubMed Central

Severino, Patricia; Alvares, Adriana M; Michaluart, Pedro; Okamoto, Oswaldo K; Nunes, Fabio D; Moreira-Filho, Carlos A; Tajara, Eloiza H

2008-01-01

Background Oral squamous cell carcinoma (OSCC) is a frequent neoplasm, which is usually aggressive and has unpredictable biological behavior and unfavorable prognosis. The comprehension of the molecular basis of this variability should lead to the development of targeted therapies as well as to improvements in specificity and sensitivity of diagnosis. Results Samples of primary OSCCs and their corresponding surgical margins were obtained from male patients during surgery and their gene expression profiles were screened using whole-genome microarray technology. Hierarchical clustering and Principal Components Analysis were used for data visualization and One-way Analysis of Variance was used to identify differentially expressed genes. Samples clustered mostly according to disease subsite, suggesting molecular heterogeneity within tumor stages. In order to corroborate our results, two publicly available datasets of microarray experiments were assessed. We found significant molecular differences between OSCC anatomic subsites concerning groups of genes presently or potentially important for drug development, including mRNA processing, cytoskeleton organization and biogenesis, metabolic process, cell cycle and apoptosis. Conclusion Our results corroborate literature data on molecular heterogeneity of OSCCs. Differences between disease subsites and among samples belonging to the same TNM class highlight the importance of gene expression-based classification and challenge the development of targeted therapies. PMID:19014556

Tabu search and binary particle swarm optimization for feature selection using microarray data.

PubMed

Chuang, Li-Yeh; Yang, Cheng-Huei; Yang, Cheng-Hong

2009-12-01

Gene expression profiles have great potential as a medical diagnosis tool because they represent the state of a cell at the molecular level. In the classification of cancer type research, available training datasets generally have a fairly small sample size compared to the number of genes involved. This fact poses an unprecedented challenge to some classification methodologies due to training data limitations. Therefore, a good selection method for genes relevant for sample classification is needed to improve the predictive accuracy, and to avoid incomprehensibility due to the large number of genes investigated. In this article, we propose to combine tabu search (TS) and binary particle swarm optimization (BPSO) for feature selection. BPSO acts as a local optimizer each time the TS has been run for a single generation. The K-nearest neighbor method with leave-one-out cross-validation and support vector machine with one-versus-rest serve as evaluators of the TS and BPSO. The proposed method is applied and compared to the 11 classification problems taken from the literature. Experimental results show that our method simplifies features effectively and either obtains higher classification accuracy or uses fewer features compared to other feature selection methods.

Multiclassifier information fusion methods for microarray pattern recognition

NASA Astrophysics Data System (ADS)

Braun, Jerome J.; Glina, Yan; Judson, Nicholas; Herzig-Marx, Rachel

2004-04-01

This paper addresses automatic recognition of microarray patterns, a capability that could have a major significance for medical diagnostics, enabling development of diagnostic tools for automatic discrimination of specific diseases. The paper presents multiclassifier information fusion methods for microarray pattern recognition. The input space partitioning approach based on fitness measures that constitute an a-priori gauging of classification efficacy for each subspace is investigated. Methods for generation of fitness measures, generation of input subspaces and their use in the multiclassifier fusion architecture are presented. In particular, two-level quantification of fitness that accounts for the quality of each subspace as well as the quality of individual neighborhoods within the subspace is described. Individual-subspace classifiers are Support Vector Machine based. The decision fusion stage fuses the information from mulitple SVMs along with the multi-level fitness information. Final decision fusion stage techniques, including weighted fusion as well as Dempster-Shafer theory based fusion are investigated. It should be noted that while the above methods are discussed in the context of microarray pattern recognition, they are applicable to a broader range of discrimination problems, in particular to problems involving a large number of information sources irreducible to a low-dimensional feature space.

Employing image processing techniques for cancer detection using microarray images.

PubMed

Dehghan Khalilabad, Nastaran; Hassanpour, Hamid

2017-02-01

Microarray technology is a powerful genomic tool for simultaneously studying and analyzing the behavior of thousands of genes. The analysis of images obtained from this technology plays a critical role in the detection and treatment of diseases. The aim of the current study is to develop an automated system for analyzing data from microarray images in order to detect cancerous cases. The proposed system consists of three main phases, namely image processing, data mining, and the detection of the disease. The image processing phase performs operations such as refining image rotation, gridding (locating genes) and extracting raw data from images the data mining includes normalizing the extracted data and selecting the more effective genes. Finally, via the extracted data, cancerous cell is recognized. To evaluate the performance of the proposed system, microarray database is employed which includes Breast cancer, Myeloid Leukemia and Lymphomas from the Stanford Microarray Database. The results indicate that the proposed system is able to identify the type of cancer from the data set with an accuracy of 95.45%, 94.11%, and 100%, respectively. Copyright © 2017 Elsevier Ltd. All rights reserved.

Spectral analysis of two-signed microarray expression data.

PubMed

Higham, Desmond J; Kalna, Gabriela; Vass, J Keith

2007-06-01

We give a simple and informative derivation of a spectral algorithm for clustering and reordering complementary DNA microarray expression data. Here, expression levels of a set of genes are recorded simultaneously across a number of samples, with a positive weight reflecting up-regulation and a negative weight reflecting down-regulation. We give theoretical support for the algorithm based on a biologically justified hypothesis about the structure of the data, and illustrate its use on public domain data in the context of unsupervised tumour classification. The algorithm is derived by considering a discrete optimization problem and then relaxing to the continuous realm. We prove that in the case where the data have an inherent 'checkerboard' sign pattern, the algorithm will automatically reveal that pattern. Further, our derivation shows that the algorithm may be regarded as imposing a random graph model on the expression levels and then clustering from a maximum likelihood perspective. This indicates that the output will be tolerant to perturbations and will reveal 'near-checkerboard' patterns when these are present in the data. It is interesting to note that the checkerboard structure is revealed by the first (dominant) singular vectors--previous work on spectral methods has focussed on the case of nonnegative edge weights, where only the second and higher singular vectors are relevant. We illustrate the algorithm on real and synthetic data, and then use it in a tumour classification context on three different cancer data sets. Our results show that respecting the two-signed nature of the data (thereby distinguishing between up-regulation and down-regulation) reveals structures that cannot be gleaned from the absolute value data (where up- and down-regulation are both regarded as 'changes').

Customized oligonucleotide microarray gene expression-based classification of neuroblastoma patients outperforms current clinical risk stratification.

PubMed

Oberthuer, André; Berthold, Frank; Warnat, Patrick; Hero, Barbara; Kahlert, Yvonne; Spitz, Rüdiger; Ernestus, Karen; König, Rainer; Haas, Stefan; Eils, Roland; Schwab, Manfred; Brors, Benedikt; Westermann, Frank; Fischer, Matthias

2006-11-01

To develop a gene expression-based classifier for neuroblastoma patients that reliably predicts courses of the disease. Two hundred fifty-one neuroblastoma specimens were analyzed using a customized oligonucleotide microarray comprising 10,163 probes for transcripts with differential expression in clinical subgroups of the disease. Subsequently, the prediction analysis for microarrays (PAM) was applied to a first set of patients with maximally divergent clinical courses (n = 77). The classification accuracy was estimated by a complete 10-times-repeated 10-fold cross validation, and a 144-gene predictor was constructed from this set. This classifier's predictive power was evaluated in an independent second set (n = 174) by comparing results of the gene expression-based classification with those of risk stratification systems of current trials from Germany, Japan, and the United States. The first set of patients was accurately predicted by PAM (cross-validated accuracy, 99%). Within the second set, the PAM classifier significantly separated cohorts with distinct courses (3-year event-free survival [EFS] 0.86 +/- 0.03 [favorable; n = 115] v 0.52 +/- 0.07 [unfavorable; n = 59] and 3-year overall survival 0.99 +/- 0.01 v 0.84 +/- 0.05; both P < .0001) and separated risk groups of current neuroblastoma trials into subgroups with divergent outcome (NB2004: low-risk 3-year EFS 0.86 +/- 0.04 v 0.25 +/- 0.15, P < .0001; intermediate-risk 1.00 v 0.57 +/- 0.19, P = .018; high-risk 0.81 +/- 0.10 v 0.56 +/- 0.08, P = .06). In a multivariate Cox regression model, the PAM predictor classified patients of the second set more accurately than risk stratification of current trials from Germany, Japan, and the United States (P < .001; hazard ratio, 4.756 [95% CI, 2.544 to 8.893]). Integration of gene expression-based class prediction of neuroblastoma patients may improve risk estimation of current neuroblastoma trials.

Gene Expression-Based Survival Prediction in Lung Adenocarcinoma: A Multi-Site, Blinded Validation Study

PubMed Central

Shedden, Kerby; Taylor, Jeremy M.G.; Enkemann, Steve A.; Tsao, Ming S.; Yeatman, Timothy J.; Gerald, William L.; Eschrich, Steve; Jurisica, Igor; Venkatraman, Seshan E.; Meyerson, Matthew; Kuick, Rork; Dobbin, Kevin K.; Lively, Tracy; Jacobson, James W.; Beer, David G.; Giordano, Thomas J.; Misek, David E.; Chang, Andrew C.; Zhu, Chang Qi; Strumpf, Dan; Hanash, Samir; Shepherd, Francis A.; Ding, Kuyue; Seymour, Lesley; Naoki, Katsuhiko; Pennell, Nathan; Weir, Barbara; Verhaak, Roel; Ladd-Acosta, Christine; Golub, Todd; Gruidl, Mike; Szoke, Janos; Zakowski, Maureen; Rusch, Valerie; Kris, Mark; Viale, Agnes; Motoi, Noriko; Travis, William; Sharma, Anupama

2009-01-01

Although prognostic gene expression signatures for survival in early stage lung cancer have been proposed, for clinical application it is critical to establish their performance across different subject populations and in different laboratories. Here we report a large, training-testing, multi-site blinded validation study to characterize the performance of several prognostic models based on gene expression for 442 lung adenocarcinomas. The hypotheses proposed examined whether microarray measurements of gene expression either alone or combined with basic clinical covariates (stage, age, sex) can be used to predict overall survival in lung cancer subjects. Several models examined produced risk scores that substantially correlated with actual subject outcome. Most methods performed better with clinical data, supporting the combined use of clinical and molecular information when building prognostic models for early stage lung cancer. This study also provides the largest available set of microarray data with extensive pathological and clinical annotation for lung adenocarcinomas. PMID:18641660

A Prognostic Gene Expression Profile That Predicts Circulating Tumor Cell Presence in Breast Cancer Patients

PubMed Central

Molloy, Timothy J.; Roepman, Paul; Naume, Bjørn; van't Veer, Laura J.

2012-01-01

The detection of circulating tumor cells (CTCs) in the peripheral blood and microarray gene expression profiling of the primary tumor are two promising new technologies able to provide valuable prognostic data for patients with breast cancer. Meta-analyses of several established prognostic breast cancer gene expression profiles in large patient cohorts have demonstrated that despite sharing few genes, their delineation of patients into “good prognosis” or “poor prognosis” are frequently very highly correlated, and combining prognostic profiles does not increase prognostic power. In the current study, we aimed to develop a novel profile which provided independent prognostic data by building a signature predictive of CTC status rather than outcome. Microarray gene expression data from an initial training cohort of 72 breast cancer patients for which CTC status had been determined in a previous study using a multimarker QPCR-based assay was used to develop a CTC-predictive profile. The generated profile was validated in two independent datasets of 49 and 123 patients and confirmed to be both predictive of CTC status, and independently prognostic. Importantly, the “CTC profile” also provided prognostic information independent of the well-established and powerful ‘70-gene’ prognostic breast cancer signature. This profile therefore has the potential to not only add prognostic information to currently-available microarray tests but in some circumstances even replace blood-based prognostic CTC tests at time of diagnosis for those patients already undergoing testing by multigene assays. PMID:22384245

Molecular cancer classification using a meta-sample-based regularized robust coding method.

PubMed

Wang, Shu-Lin; Sun, Liuchao; Fang, Jianwen

2014-01-01

Previous studies have demonstrated that machine learning based molecular cancer classification using gene expression profiling (GEP) data is promising for the clinic diagnosis and treatment of cancer. Novel classification methods with high efficiency and prediction accuracy are still needed to deal with high dimensionality and small sample size of typical GEP data. Recently the sparse representation (SR) method has been successfully applied to the cancer classification. Nevertheless, its efficiency needs to be improved when analyzing large-scale GEP data. In this paper we present the meta-sample-based regularized robust coding classification (MRRCC), a novel effective cancer classification technique that combines the idea of meta-sample-based cluster method with regularized robust coding (RRC) method. It assumes that the coding residual and the coding coefficient are respectively independent and identically distributed. Similar to meta-sample-based SR classification (MSRC), MRRCC extracts a set of meta-samples from the training samples, and then encodes a testing sample as the sparse linear combination of these meta-samples. The representation fidelity is measured by the l2-norm or l1-norm of the coding residual. Extensive experiments on publicly available GEP datasets demonstrate that the proposed method is more efficient while its prediction accuracy is equivalent to existing MSRC-based methods and better than other state-of-the-art dimension reduction based methods.

[Evaluation of traditional pathological classification at molecular classification era for gastric cancer].

PubMed

Yu, Yingyan

2014-01-01

Histopathological classification is in a pivotal position in both basic research and clinical diagnosis and treatment of gastric cancer. Currently, there are different classification systems in basic science and clinical application. In medical literatures, different classifications are used including Lauren and WHO systems, which have confused many researchers. Lauren classification has been proposed for half a century, but is still used worldwide. It shows many advantages of simple, easy handling with prognostic significance. The WHO classification scheme is better than Lauren classification in that it is continuously being revised according to the progress of gastric cancer, and is always used in the clinical and pathological diagnosis of common scenarios. Along with the progression of genomics, transcriptomics, proteomics, metabolomics researches, molecular classification of gastric cancer becomes the current hot topics. The traditional therapeutic approach based on phenotypic characteristics of gastric cancer will most likely be replaced with a gene variation mode. The gene-targeted therapy against the same molecular variation seems more reasonable than traditional chemical treatment based on the same morphological change.

Multiplexed Analysis of Serum Breast and Ovarian Cancer Markers by Means of Suspension Bead-quantum Dot Microarrays

NASA Astrophysics Data System (ADS)

Brazhnik, Kristina; Sokolova, Zinaida; Baryshnikova, Maria; Bilan, Regina; Nabiev, Igor; Sukhanova, Alyona

Multiplexed analysis of cancer markers is crucial for early tumor diagnosis and screening. We have designed lab-on-a-bead microarray for quantitative detection of three breast cancer markers in human serum. Quantum dots were used as bead-bound fluorescent tags for identifying each marker by means of flow cytometry. Antigen-specific beads reliably detected CA 15-3, CEA, and CA 125 in serum samples, providing clear discrimination between the samples with respect to the antigen levels. The novel microarray is advantageous over the routine single-analyte ones due to the simultaneous detection of various markers. Therefore the developed microarray is a promising tool for serum tumor marker profiling.

Classification of a large microarray data set: Algorithm comparison and analysis of drug signatures

PubMed Central

Natsoulis, Georges; El Ghaoui, Laurent; Lanckriet, Gert R.G.; Tolley, Alexander M.; Leroy, Fabrice; Dunlea, Shane; Eynon, Barrett P.; Pearson, Cecelia I.; Tugendreich, Stuart; Jarnagin, Kurt

2005-01-01

A large gene expression database has been produced that characterizes the gene expression and physiological effects of hundreds of approved and withdrawn drugs, toxicants, and biochemical standards in various organs of live rats. In order to derive useful biological knowledge from this large database, a variety of supervised classification algorithms were compared using a 597-microarray subset of the data. Our studies show that several types of linear classifiers based on Support Vector Machines (SVMs) and Logistic Regression can be used to derive readily interpretable drug signatures with high classification performance. Both methods can be tuned to produce classifiers of drug treatments in the form of short, weighted gene lists which upon analysis reveal that some of the signature genes have a positive contribution (act as “rewards” for the class-of-interest) while others have a negative contribution (act as “penalties”) to the classification decision. The combination of reward and penalty genes enhances performance by keeping the number of false positive treatments low. The results of these algorithms are combined with feature selection techniques that further reduce the length of the drug signatures, an important step towards the development of useful diagnostic biomarkers and low-cost assays. Multiple signatures with no genes in common can be generated for the same classification end-point. Comparison of these gene lists identifies biological processes characteristic of a given class. PMID:15867433

Practical protocols for fast histopathology by Fourier transform infrared spectroscopic imaging

NASA Astrophysics Data System (ADS)

Keith, Frances N.; Reddy, Rohith K.; Bhargava, Rohit

2008-02-01

Fourier transform infrared (FT-IR) spectroscopic imaging is an emerging technique that combines the molecular selectivity of spectroscopy with the spatial specificity of optical microscopy. We demonstrate a new concept in obtaining high fidelity data using commercial array detectors coupled to a microscope and Michelson interferometer. Next, we apply the developed technique to rapidly provide automated histopathologic information for breast cancer. Traditionally, disease diagnoses are based on optical examinations of stained tissue and involve a skilled recognition of morphological patterns of specific cell types (histopathology). Consequently, histopathologic determinations are a time consuming, subjective process with innate intra- and inter-operator variability. Utilizing endogenous molecular contrast inherent in vibrational spectra, specially designed tissue microarrays and pattern recognition of specific biochemical features, we report an integrated algorithm for automated classifications. The developed protocol is objective, statistically significant and, being compatible with current tissue processing procedures, holds potential for routine clinical diagnoses. We first demonstrate that the classification of tissue type (histology) can be accomplished in a manner that is robust and rigorous. Since data quality and classifier performance are linked, we quantify the relationship through our analysis model. Last, we demonstrate the application of the minimum noise fraction (MNF) transform to improve tissue segmentation.

Hyperspectral microscopic analysis of normal, benign and carcinoma microarray tissue sections

NASA Astrophysics Data System (ADS)

Maggioni, Mauro; Davis, Gustave L.; Warner, Frederick J.; Geshwind, Frank B.; Coppi, Andreas C.; DeVerse, Richard A.; Coifman, Ronald R.

2006-02-01

We apply a unique micro-optoelectromechanical tuned light source and new algorithms to the hyper-spectral microscopic analysis of human colon biopsies. The tuned light prototype (Plain Sight Systems Inc.) transmits any combination of light frequencies, range 440nm 700nm, trans-illuminating H and E stained tissue sections of normal (N), benign adenoma (B) and malignant carcinoma (M) colon biopsies, through a Nikon Biophot microscope. Hyper-spectral photomicrographs, randomly collected 400X magnication, are obtained with a CCD camera (Sensovation) from 59 different patient biopsies (20 N, 19 B, 20 M) mounted as a microarray on a single glass slide. The spectra of each pixel are normalized and analyzed to discriminate among tissue features: gland nuclei, gland cytoplasm and lamina propria/lumens. Spectral features permit the automatic extraction of 3298 nuclei with classification as N, B or M. When nuclei are extracted from each of the 59 biopsies the average classification among N, B and M nuclei is 97.1%; classification of the biopsies, based on the average nuclei classification, is 100%. However, when the nuclei are extracted from a subset of biopsies, and the prediction is made on nuclei in the remaining biopsies, there is a marked decrement in performance to 60% across the 3 classes. Similarly the biopsy classification drops to 54%. In spite of these classification differences, which we believe are due to instrument and biopsy normalization issues, hyper-spectral analysis has the potential to achieve diagnostic efficiency needed for objective microscopic diagnosis.

Classification of cancerous cells based on the one-class problem approach

NASA Astrophysics Data System (ADS)

Murshed, Nabeel A.; Bortolozzi, Flavio; Sabourin, Robert

1996-03-01

One of the most important factors in reducing the effect of cancerous diseases is the early diagnosis, which requires a good and a robust method. With the advancement of computer technologies and digital image processing, the development of a computer-based system has become feasible. In this paper, we introduce a new approach for the detection of cancerous cells. This approach is based on the one-class problem approach, through which the classification system need only be trained with patterns of cancerous cells. This reduces the burden of the training task by about 50%. Based on this approach, a computer-based classification system is developed, based on the Fuzzy ARTMAP neural networks. Experimental results were performed using a set of 542 patterns taken from a sample of breast cancer. Results of the experiment show 98% correct identification of cancerous cells and 95% correct identification of non-cancerous cells.

Characterization of 1,577 Primary Prostate Cancers Reveals Novel Biological and Clinicopathological Insights into Molecular Subtypes

PubMed Central

Tomlins, Scott A.; Alshalalfa, Mohammed; Davicioni, Elai; Erho, Nicholas; Yousefi, Kasra; Zhao, Shuang; Haddad, Zaid; Den, Robert B.; Dicker, Adam P.; Trock, Bruce; DeMarzo, Angelo; Ross, Ashley; Schaeffer, Edward M.; Klein, Eric A.; Magi-Galluzzi, Cristina; Karnes, Jeffery R.; Jenkins, Robert B.; Feng, Felix Y.

2015-01-01

Background Prostate cancer (PCa) molecular subtypes have been defined by essentially mutually exclusive events, including ETS gene fusions (most commonly involving ERG) and SPINK1 over-expression. Clinical assessment may aid in disease stratification, complementing available prognostic tests. Objective To determine the analytical validity and clinicopatholgical associations of microarray-based molecular subtyping. Design, Setting and Participants We analyzed Affymetrix GeneChip expression profiles for 1,577 patients from eight radical prostatectomy (RP) cohorts, including 1,351 cases assessed using the Decipher prognostic assay (performed in a CLIA-certified laboratory). A microarray-based (m-) random forest ERG classification model was trained and validated. Outlier expression analysis was used to predict other mutually exclusive non-ERG ETS gene rearrangements (ETS+) or SPINK1 over-expression (SPINK1+). Outcome Measurements Associations with clinical features and outcomes by multivariable logistic regression analysis and receiver operating curves. Results and Limitations The m-ERG classifier showed 95% accuracy in an independent validation subset (n=155 samples). Across cohorts, 45%, 9%, 8% and 38% of PCa were classified as m-ERG+, m-ETS+, m-SPINK1+, and triple negative (m-ERG−/m-ETS−/m-SPINK1−), respectively. Gene expression profiling supports three underlying molecularly defined groups (m-ERG+, m-ETS+ and m-SPINK1+/triple negative). On multivariable analysis, m-ERG+ tumors were associated with lower preoperative serum PSA and Gleason scores, but enriched for extraprostatic extension (p<0.001). m-ETS+ tumors were associated with seminal vesicle invasion (p=0.01), while m-SPINK1+/triple negative tumors had higher Gleason scores and were more frequent in Black/African American patients (p<0.001). Clinical outcomes were not significantly different between subtypes. Conclusions A clinically available prognostic test (Decipher) can also assess PCa molecular subtypes, obviating the need for additional testing. Clinicopathological differences were found among subtypes based on global expression patterns. PMID:25964175

Expression profiling in canine osteosarcoma: identification of biomarkers and pathways associated with outcome

PubMed Central

2010-01-01

Background Osteosarcoma (OSA) spontaneously arises in the appendicular skeleton of large breed dogs and shares many physiological and molecular biological characteristics with human OSA. The standard treatment for OSA in both species is amputation or limb-sparing surgery, followed by chemotherapy. Unfortunately, OSA is an aggressive cancer with a high metastatic rate. Characterization of OSA with regard to its metastatic potential and chemotherapeutic resistance will improve both prognostic capabilities and treatment modalities. Methods We analyzed archived primary OSA tissue from dogs treated with limb amputation followed by doxorubicin or platinum-based drug chemotherapy. Samples were selected from two groups: dogs with disease free intervals (DFI) of less than 100 days (n = 8) and greater than 300 days (n = 7). Gene expression was assessed with Affymetrix Canine 2.0 microarrays and analyzed with a two-tailed t-test. A subset of genes was confirmed using qRT-PCR and used in classification analysis to predict prognosis. Systems-based gene ontology analysis was conducted on genes selected using a standard J5 metric. The genes identified using this approach were converted to their human homologues and assigned to functional pathways using the GeneGo MetaCore platform. Results Potential biomarkers were identified using gene expression microarray analysis and 11 differentially expressed (p < 0.05) genes were validated with qRT-PCR (n = 10/group). Statistical classification models using the qRT-PCR profiles predicted patient outcomes with 100% accuracy in the training set and up to 90% accuracy upon stratified cross validation. Pathway analysis revealed alterations in pathways associated with oxidative phosphorylation, hedgehog and parathyroid hormone signaling, cAMP/Protein Kinase A (PKA) signaling, immune responses, cytoskeletal remodeling and focal adhesion. Conclusions This profiling study has identified potential new biomarkers to predict patient outcome in OSA and new pathways that may be targeted for therapeutic intervention. PMID:20860831

Bioinformatics approaches for cross-species liver cancer analysis based on microarray gene expression profiling

PubMed Central

Fang, H; Tong, W; Perkins, R; Shi, L; Hong, H; Cao, X; Xie, Q; Yim, SH; Ward, JM; Pitot, HC; Dragan, YP

2005-01-01

Background The completion of the sequencing of human, mouse and rat genomes and knowledge of cross-species gene homologies enables studies of differential gene expression in animal models. These types of studies have the potential to greatly enhance our understanding of diseases such as liver cancer in humans. Genes co-expressed across multiple species are most likely to have conserved functions. We have used various bioinformatics approaches to examine microarray expression profiles from liver neoplasms that arise in albumin-SV40 transgenic rats to elucidate genes, chromosome aberrations and pathways that might be associated with human liver cancer. Results In this study, we first identified 2223 differentially expressed genes by comparing gene expression profiles for two control, two adenoma and two carcinoma samples using an F-test. These genes were subsequently mapped to the rat chromosomes using a novel visualization tool, the Chromosome Plot. Using the same plot, we further mapped the significant genes to orthologous chromosomal locations in human and mouse. Many genes expressed in rat 1q that are amplified in rat liver cancer map to the human chromosomes 10, 11 and 19 and to the mouse chromosomes 7, 17 and 19, which have been implicated in studies of human and mouse liver cancer. Using Comparative Genomics Microarray Analysis (CGMA), we identified regions of potential aberrations in human. Lastly, a pathway analysis was conducted to predict altered human pathways based on statistical analysis and extrapolation from the rat data. All of the identified pathways have been known to be important in the etiology of human liver cancer, including cell cycle control, cell growth and differentiation, apoptosis, transcriptional regulation, and protein metabolism. Conclusion The study demonstrates that the hepatic gene expression profiles from the albumin-SV40 transgenic rat model revealed genes, pathways and chromosome alterations consistent with experimental and clinical research in human liver cancer. The bioinformatics tools presented in this paper are essential for cross species extrapolation and mapping of microarray data, its analysis and interpretation. PMID:16026603

Distinct types of primary cutaneous large B-cell lymphoma identified by gene expression profiling.

PubMed

Hoefnagel, Juliette J; Dijkman, Remco; Basso, Katia; Jansen, Patty M; Hallermann, Christian; Willemze, Rein; Tensen, Cornelis P; Vermeer, Maarten H

2005-05-01

In the European Organization for Research and Treatment of Cancer (EORTC) classification 2 types of primary cutaneous large B-cell lymphoma (PCLBCL) are distinguished: primary cutaneous follicle center cell lymphomas (PCFCCL) and PCLBCL of the leg (PCLBCL-leg). Distinction between both groups is considered important because of differences in prognosis (5-year survival > 95% and 52%, respectively) and the first choice of treatment (radiotherapy or systemic chemotherapy, respectively), but is not generally accepted. To establish a molecular basis for this subdivision in the EORTC classification, we investigated the gene expression profiles of 21 PCLBCLs by oligonucleotide microarray analysis. Hierarchical clustering based on a B-cell signature (7450 genes) classified PCLBCL into 2 distinct subgroups consisting of, respectively, 8 PCFCCLs and 13 PCLBCLsleg. PCLBCLs-leg showed increased expression of genes associated with cell proliferation; the proto-oncogenes Pim-1, Pim-2, and c-Myc; and the transcription factors Mum1/IRF4 and Oct-2. In the group of PCFCCL high expression of SPINK2 was observed. Further analysis suggested that PCFCCLs and PCLBCLs-leg have expression profiles similar to that of germinal center B-cell-like and activated B-cell-like diffuse large B-cell lymphoma, respectively. The results of this study suggest that different pathogenetic mechanisms are involved in the development of PCFCCLs and PCLBCLs-leg and provide molecular support for the subdivision used in the EORTC classification.

Multi-factorial analysis of class prediction error: estimating optimal number of biomarkers for various classification rules.

PubMed

Khondoker, Mizanur R; Bachmann, Till T; Mewissen, Muriel; Dickinson, Paul; Dobrzelecki, Bartosz; Campbell, Colin J; Mount, Andrew R; Walton, Anthony J; Crain, Jason; Schulze, Holger; Giraud, Gerard; Ross, Alan J; Ciani, Ilenia; Ember, Stuart W J; Tlili, Chaker; Terry, Jonathan G; Grant, Eilidh; McDonnell, Nicola; Ghazal, Peter

2010-12-01

Machine learning and statistical model based classifiers have increasingly been used with more complex and high dimensional biological data obtained from high-throughput technologies. Understanding the impact of various factors associated with large and complex microarray datasets on the predictive performance of classifiers is computationally intensive, under investigated, yet vital in determining the optimal number of biomarkers for various classification purposes aimed towards improved detection, diagnosis, and therapeutic monitoring of diseases. We investigate the impact of microarray based data characteristics on the predictive performance for various classification rules using simulation studies. Our investigation using Random Forest, Support Vector Machines, Linear Discriminant Analysis and k-Nearest Neighbour shows that the predictive performance of classifiers is strongly influenced by training set size, biological and technical variability, replication, fold change and correlation between biomarkers. Optimal number of biomarkers for a classification problem should therefore be estimated taking account of the impact of all these factors. A database of average generalization errors is built for various combinations of these factors. The database of generalization errors can be used for estimating the optimal number of biomarkers for given levels of predictive accuracy as a function of these factors. Examples show that curves from actual biological data resemble that of simulated data with corresponding levels of data characteristics. An R package optBiomarker implementing the method is freely available for academic use from the Comprehensive R Archive Network (http://www.cran.r-project.org/web/packages/optBiomarker/).

Same-day genomic and epigenomic diagnosis of brain tumors using real-time nanopore sequencing.

PubMed

Euskirchen, Philipp; Bielle, Franck; Labreche, Karim; Kloosterman, Wigard P; Rosenberg, Shai; Daniau, Mailys; Schmitt, Charlotte; Masliah-Planchon, Julien; Bourdeaut, Franck; Dehais, Caroline; Marie, Yannick; Delattre, Jean-Yves; Idbaih, Ahmed

2017-11-01

Molecular classification of cancer has entered clinical routine to inform diagnosis, prognosis, and treatment decisions. At the same time, new tumor entities have been identified that cannot be defined histologically. For central nervous system tumors, the current World Health Organization classification explicitly demands molecular testing, e.g., for 1p/19q-codeletion or IDH mutations, to make an integrated histomolecular diagnosis. However, a plethora of sophisticated technologies is currently needed to assess different genomic and epigenomic alterations and turnaround times are in the range of weeks, which makes standardized and widespread implementation difficult and hinders timely decision making. Here, we explored the potential of a pocket-size nanopore sequencing device for multimodal and rapid molecular diagnostics of cancer. Low-pass whole genome sequencing was used to simultaneously generate copy number (CN) and methylation profiles from native tumor DNA in the same sequencing run. Single nucleotide variants in IDH1, IDH2, TP53, H3F3A, and the TERT promoter region were identified using deep amplicon sequencing. Nanopore sequencing yielded ~0.1X genome coverage within 6 h and resulting CN and epigenetic profiles correlated well with matched microarray data. Diagnostically relevant alterations, such as 1p/19q codeletion, and focal amplifications could be recapitulated. Using ad hoc random forests, we could perform supervised pan-cancer classification to distinguish gliomas, medulloblastomas, and brain metastases of different primary sites. Single nucleotide variants in IDH1, IDH2, and H3F3A were identified using deep amplicon sequencing within minutes of sequencing. Detection of TP53 and TERT promoter mutations shows that sequencing of entire genes and GC-rich regions is feasible. Nanopore sequencing allows same-day detection of structural variants, point mutations, and methylation profiling using a single device with negligible capital cost. It outperforms hybridization-based and current sequencing technologies with respect to time to diagnosis and required laboratory equipment and expertise, aiming to make precision medicine possible for every cancer patient, even in resource-restricted settings.

Analysis of gene expression profile induced by EMP-1 in esophageal cancer cells using cDNA Microarray

PubMed Central

Wang, Hai-Tao; Kong, Jian-Ping; Ding, Fang; Wang, Xiu-Qin; Wang, Ming-Rong; Liu, Lian-Xin; Wu, Min; Liu, Zhi-Hua

2003-01-01

AIM: To obtain human esophageal cancer cell EC9706 stably expressed epithelial membrane protein-1 (EMP-1) with integrated eukaryotic plasmid harboring the open reading frame (ORF) of human EMP-1, and then to study the mechanism by which EMP-1 exerts its diverse cellular action on cell proliferation and altered gene profile by exploring the effect of EMP-1. METHODS: The authors first constructed pcDNA3.1/myc-his expression vector harboring the ORF of EMP-1 and then transfected it into human esophageal carcinoma cell line EC9706. The positive clones were analyzed by Western blot and RT-PCR. Moreover, the cell growth curve was observed and the cell cycle was checked by FACS technique. Using cDNA microarray technology, the authors compared the gene expression pattern in positive clones with control. To confirm the gene expression profile, semi-quantitative RT-PCR was carried out for 4 of the randomly picked differentially expressed genes. For those differentially expressed genes, classification was performed according to their function and cellular component. RESULTS: Human EMP-1 gene can be stably expressed in EC9706 cell line transfected with human EMP-1. The authors found the cell growth decreased, among which S phase was arrested and G1 phase was prolonged in the transfected positive clones. By cDNA microarray analysis, 35 genes showed an over 2.0 fold change in expression level after transfection, with 28 genes being consistently up-regulated and 7 genes being down-regulated. Among the classified genes, almost half of the induced genes (13 out of 28 genes) were related to cell signaling, cell communication and particularly to adhesion. CONCLUSION: Overexpression of human EMP-1 gene can inhibit the proliferation of EC9706 cell with S phase arrested and G1 phase prolonged. The cDNA microarray analysis suggested that EMP-1 may be one of regulators involved in cell signaling, cell communication and adhesion regulators. PMID:12632483

Analysis of gene expression profile induced by EMP-1 in esophageal cancer cells using cDNA Microarray.

PubMed

Wang, Hai-Tao; Kong, Jian-Ping; Ding, Fang; Wang, Xiu-Qin; Wang, Ming-Rong; Liu, Lian-Xin; Wu, Min; Liu, Zhi-Hua

2003-03-01

To obtain human esophageal cancer cell EC9706 stably expressed epithelial membrane protein-1 (EMP-1) with integrated eukaryotic plasmid harboring the open reading frame (ORF) of human EMP-1, and then to study the mechanism by which EMP-1 exerts its diverse cellular action on cell proliferation and altered gene profile by exploring the effect of EMP-1. The authors first constructed pcDNA3.1/myc-his expression vector harboring the ORF of EMP-1 and then transfected it into human esophageal carcinoma cell line EC9706. The positive clones were analyzed by Western blot and RT-PCR. Moreover, the cell growth curve was observed and the cell cycle was checked by FACS technique. Using cDNA microarray technology, the authors compared the gene expression pattern in positive clones with control. To confirm the gene expression profile, semi-quantitative RT-PCR was carried out for 4 of the randomly picked differentially expressed genes. For those differentially expressed genes, classification was performed according to their function and cellular component. Human EMP-1 gene can be stably expressed in EC9706 cell line transfected with human EMP-1. The authors found the cell growth decreased, among which S phase was arrested and G1 phase was prolonged in the transfected positive clones. By cDNA microarray analysis, 35 genes showed an over 2.0 fold change in expression level after transfection, with 28 genes being consistently up-regulated and 7 genes being down-regulated. Among the classified genes, almost half of the induced genes (13 out of 28 genes) were related to cell signaling, cell communication and particularly to adhesion. Overexpression of human EMP-1 gene can inhibit the proliferation of EC9706 cell with S phase arrested and G1 phase prolonged. The cDNA microarray analysis suggested that EMP-1 may be one of regulators involved in cell signaling, cell communication and adhesion regulators.

Microfluidic extraction and microarray detection of biomarkers from cancer tissue slides

NASA Astrophysics Data System (ADS)

Nguyen, H. T.; Dupont, L. N.; Jean, A. M.; Géhin, T.; Chevolot, Y.; Laurenceau, E.; Gijs, M. A. M.

2018-03-01

We report here a new microfluidic method allowing for the quantification of human epidermal growth factor receptor 2 (HER2) expression levels from formalin-fixed breast cancer tissues. After partial extraction of proteins from the tissue slide, the extract is routed to an antibody (Ab) microarray for HER2 titration by fluorescence. Then the HER2-expressing cell area is evaluated by immunofluorescence (IF) staining of the tissue slide and used to normalize the fluorescent HER2 signal measured from the Ab microarray. The number of HER2 gene copies measured by fluorescence in situ hybridization (FISH) on an adjacent tissue slide is concordant with the normalized HER2 expression signal. This work is the first study implementing biomarker extraction and detection from cancer tissue slides using microfluidics in combination with a microarray system, paving the way for further developments towards multiplex and precise quantification of cancer biomarkers.

A multiple kernel support vector machine scheme for feature selection and rule extraction from gene expression data of cancer tissue.

PubMed

Chen, Zhenyu; Li, Jianping; Wei, Liwei

2007-10-01

Recently, gene expression profiling using microarray techniques has been shown as a promising tool to improve the diagnosis and treatment of cancer. Gene expression data contain high level of noise and the overwhelming number of genes relative to the number of available samples. It brings out a great challenge for machine learning and statistic techniques. Support vector machine (SVM) has been successfully used to classify gene expression data of cancer tissue. In the medical field, it is crucial to deliver the user a transparent decision process. How to explain the computed solutions and present the extracted knowledge becomes a main obstacle for SVM. A multiple kernel support vector machine (MK-SVM) scheme, consisting of feature selection, rule extraction and prediction modeling is proposed to improve the explanation capacity of SVM. In this scheme, we show that the feature selection problem can be translated into an ordinary multiple parameters learning problem. And a shrinkage approach: 1-norm based linear programming is proposed to obtain the sparse parameters and the corresponding selected features. We propose a novel rule extraction approach using the information provided by the separating hyperplane and support vectors to improve the generalization capacity and comprehensibility of rules and reduce the computational complexity. Two public gene expression datasets: leukemia dataset and colon tumor dataset are used to demonstrate the performance of this approach. Using the small number of selected genes, MK-SVM achieves encouraging classification accuracy: more than 90% for both two datasets. Moreover, very simple rules with linguist labels are extracted. The rule sets have high diagnostic power because of their good classification performance.

Association of HADHA expression with the risk of breast cancer: targeted subset analysis and meta-analysis of microarray data

PubMed Central

2012-01-01

Background The role of n-3 fatty acids in prevention of breast cancer is well recognized, but the underlying molecular mechanisms are still unclear. In view of the growing need for early detection of breast cancer, Graham et al. (2010) studied the microarray gene expression in histologically normal epithelium of subjects with or without breast cancer. We conducted a secondary analysis of this dataset with a focus on the genes (n = 47) involved in fat and lipid metabolism. We used stepwise multivariate logistic regression analyses, volcano plots and false discovery rates for association analyses. We also conducted meta-analyses of other microarray studies using random effects models for three outcomes--risk of breast cancer (380 breast cancer patients and 240 normal subjects), risk of metastasis (430 metastatic compared to 1104 non-metastatic breast cancers) and risk of recurrence (484 recurring versus 890 non-recurring breast cancers). Results The HADHA gene [hydroxyacyl-CoA dehydrogenase/3-ketoacyl-CoA thiolase/enoyl-CoA hydratase (trifunctional protein), alpha subunit] was significantly under-expressed in breast cancer; more so in those with estrogen receptor-negative status. Our meta-analysis showed an 18.4%-26% reduction in HADHA expression in breast cancer. Also, there was an inconclusive but consistent under-expression of HADHA in subjects with metastatic and recurring breast cancers. Conclusions Involvement of mitochondria and the mitochondrial trifunctional protein (encoded by HADHA gene) in breast carcinogenesis is known. Our results lend additional support to the possibility of this involvement. Further, our results suggest that targeted subset analysis of large genome-based datasets can provide interesting association signals. PMID:22240105

Development of a Native Fractionation Antigen Microarray for Autoantibody Profiling in Breast Cancer

DTIC Science & Technology

2011-10-01

Antigen Microarray for Autoantibody Profiling in Breast Cancer PRINCIPAL INVESTIGATOR: Brian C.-S. Liu, Ph.D...Profiling in Breast Cancer 5b. GRANT NUMBER W81XWH-09-1-0684 5c. PROGRAM ELEMENT NUMBER 6. AUTHOR(S) 5d. PROJECT NUMBER Brian C.-S. Liu...NOTES 14. ABSTRACT The humoral response of a cancer patient may allow earlier detection of cancer than current methods allow. If so, the serum

Cell-of-Origin in Diffuse Large B-Cell Lymphoma: Are the Assays Ready for the Clinic?

PubMed

Scott, David W

2015-01-01

Diffuse large B-cell lymphoma (DLBCL) is the most common lymphoma worldwide and consists of a heterogeneous group of cancers classified together on the basis of shared morphology, immunophenotype, and aggressive clinical behavior. It is now recognized that this malignancy comprises at least two distinct molecular subtypes identified by gene expression profiling: the activated B-cell-like (ABC) and the germinal center B-cell-like (GCB) groups-the cell-of-origin (COO) classification. These two groups have different genetic mutation landscapes, pathobiology, and outcomes following treatment. Evidence is accumulating that novel agents have selective activity in one or the other COO group, making COO a predictive biomarker. Thus, there is now a pressing need for accurate and robust methods to assign COO, to support clinical trials, and ultimately guide treatment decisions for patients. The "gold standard" methods for COO are based on gene expression profiling (GEP) of RNA from fresh frozen tissue using microarray technology, which is an impractical solution when formalin-fixed paraffin-embedded tissue (FFPET) biopsies are the standard diagnostic material. This review outlines the history of the COO classification before examining the practical implementation of COO assays applicable to FFPET biopsies. The immunohistochemistry (IHC)-based algorithms and gene expression-based assays suitable for the highly degraded RNA from FFPET are discussed. Finally, the technical and practical challenges that still need to be addressed are outlined before robust gene expression-based assays are used in the routine management of patients with DLBCL.

Identification of suitable genes contributes to lung adenocarcinoma clustering by multiple meta-analysis methods.

PubMed

Yang, Ze-Hui; Zheng, Rui; Gao, Yuan; Zhang, Qiang

2016-09-01

With the widespread application of high-throughput technology, numerous meta-analysis methods have been proposed for differential expression profiling across multiple studies. We identified the suitable differentially expressed (DE) genes that contributed to lung adenocarcinoma (ADC) clustering based on seven popular multiple meta-analysis methods. Seven microarray expression profiles of ADC and normal controls were extracted from the ArrayExpress database. The Bioconductor was used to perform the data preliminary preprocessing. Then, DE genes across multiple studies were identified. Hierarchical clustering was applied to compare the classification performance for microarray data samples. The classification efficiency was compared based on accuracy, sensitivity and specificity. Across seven datasets, 573 ADC cases and 222 normal controls were collected. After filtering out unexpressed and noninformative genes, 3688 genes were remained for further analysis. The classification efficiency analysis showed that DE genes identified by sum of ranks method separated ADC from normal controls with the best accuracy, sensitivity and specificity of 0.953, 0.969 and 0.932, respectively. The gene set with the highest classification accuracy mainly participated in the regulation of response to external stimulus (P = 7.97E-04), cyclic nucleotide-mediated signaling (P = 0.01), regulation of cell morphogenesis (P = 0.01) and regulation of cell proliferation (P = 0.01). Evaluation of DE genes identified by different meta-analysis methods in classification efficiency provided a new perspective to the choice of the suitable method in a given application. Varying meta-analysis methods always present varying abilities, so synthetic consideration should be taken when providing meta-analysis methods for particular research. © 2015 John Wiley & Sons Ltd.

Microarray analysis of genes associated with cell surface NIS protein levels in breast cancer.

PubMed

Beyer, Sasha J; Zhang, Xiaoli; Jimenez, Rafael E; Lee, Mei-Ling T; Richardson, Andrea L; Huang, Kun; Jhiang, Sissy M

2011-10-11

Na+/I- symporter (NIS)-mediated iodide uptake allows radioiodine therapy for thyroid cancer. NIS is also expressed in breast tumors, raising potential for radionuclide therapy of breast cancer. However, NIS expression in most breast cancers is low and may not be sufficient for radionuclide therapy. We aimed to identify biomarkers associated with NIS expression such that mechanisms underlying NIS modulation in human breast tumors may be elucidated. Published oligonucleotide microarray data within the National Center for Biotechnology Information Gene Expression Omnibus database were analyzed to identify gene expression tightly correlated with NIS mRNA level among human breast tumors. NIS immunostaining was performed in a tissue microarray composed of 28 human breast tumors which had corresponding oligonucleotide microarray data available for each tumor such that gene expression associated with cell surface NIS protein level could be identified. NIS mRNA levels do not vary among breast tumors or when compared to normal breast tissues when detected by Affymetrix oligonucleotide microarray platforms. Cell surface NIS protein levels are much more variable than their corresponding NIS mRNA levels. Despite a limited number of breast tumors examined, our analysis identified cysteinyl-tRNA synthetase as a biomarker that is highly associated with cell surface NIS protein levels in the ER-positive breast cancer subtype. Further investigation on genes associated with cell surface NIS protein levels within each breast cancer molecular subtype may lead to novel targets for selectively increasing NIS expression/function in a subset of breast cancers patients.

Data Mining Algorithms for Classification of Complex Biomedical Data

ERIC Educational Resources Information Center

Lan, Liang

2012-01-01

In my dissertation, I will present my research which contributes to solve the following three open problems from biomedical informatics: (1) Multi-task approaches for microarray classification; (2) Multi-label classification of gene and protein prediction from multi-source biological data; (3) Spatial scan for movement data. In microarray…

Construction of diagnosis system and gene regulatory networks based on microarray analysis.

PubMed

Hong, Chun-Fu; Chen, Ying-Chen; Chen, Wei-Chun; Tu, Keng-Chang; Tsai, Meng-Hsiun; Chan, Yung-Kuan; Yu, Shyr Shen

2018-05-01

A microarray analysis generally contains expression data of thousands of genes, but most of them are irrelevant to the disease of interest, making analyzing the genes concerning specific diseases complicated. Therefore, filtering out a few essential genes as well as their regulatory networks is critical, and a disease can be easily diagnosed just depending on the expression profiles of a few critical genes. In this study, a target gene screening (TGS) system, which is a microarray-based information system that integrates F-statistics, pattern recognition matching, a two-layer K-means classifier, a Parameter Detection Genetic Algorithm (PDGA), a genetic-based gene selector (GBG selector) and the association rule, was developed to screen out a small subset of genes that can discriminate malignant stages of cancers. During the first stage, F-statistic, pattern recognition matching, and a two-layer K-means classifier were applied in the system to filter out the 20 critical genes most relevant to ovarian cancer from 9600 genes, and the PDGA was used to decide the fittest values of the parameters for these critical genes. Among the 20 critical genes, 15 are associated with cancer progression. In the second stage, we further employed a GBG selector and the association rule to screen out seven target gene sets, each with only four to six genes, and each of which can precisely identify the malignancy stage of ovarian cancer based on their expression profiles. We further deduced the gene regulatory networks of the 20 critical genes by applying the Pearson correlation coefficient to evaluate the correlationship between the expression of each gene at the same stages and at different stages. Correlationships between gene pairs were calculated, and then, three regulatory networks were deduced. Their correlationships were further confirmed by the Ingenuity pathway analysis. The prognostic significances of the genes identified via regulatory networks were examined using online tools, and most represented biomarker candidates. In summary, our proposed system provides a new strategy to identify critical genes or biomarkers, as well as their regulatory networks, from microarray data. Copyright © 2018. Published by Elsevier Inc.

The Microarray Revolution: Perspectives from Educators

ERIC Educational Resources Information Center

Brewster, Jay L.; Beason, K. Beth; Eckdahl, Todd T.; Evans, Irene M.

2004-01-01

In recent years, microarray analysis has become a key experimental tool, enabling the analysis of genome-wide patterns of gene expression. This review approaches the microarray revolution with a focus upon four topics: 1) the early development of this technology and its application to cancer diagnostics; 2) a primer of microarray research,…

Advances in cell-free protein array methods.

PubMed

Yu, Xiaobo; Petritis, Brianne; Duan, Hu; Xu, Danke; LaBaer, Joshua

2018-01-01

Cell-free protein microarrays represent a special form of protein microarray which display proteins made fresh at the time of the experiment, avoiding storage and denaturation. They have been used increasingly in basic and translational research over the past decade to study protein-protein interactions, the pathogen-host relationship, post-translational modifications, and antibody biomarkers of different human diseases. Their role in the first blood-based diagnostic test for early stage breast cancer highlights their value in managing human health. Cell-free protein microarrays will continue to evolve to become widespread tools for research and clinical management. Areas covered: We review the advantages and disadvantages of different cell-free protein arrays, with an emphasis on the methods that have been studied in the last five years. We also discuss the applications of each microarray method. Expert commentary: Given the growing roles and impact of cell-free protein microarrays in research and medicine, we discuss: 1) the current technical and practical limitations of cell-free protein microarrays; 2) the biomarker discovery and verification pipeline using protein microarrays; and 3) how cell-free protein microarrays will advance over the next five years, both in their technology and applications.

Gene features selection for three-class disease classification via multiple orthogonal partial least square discriminant analysis and S-plot using microarray data.

PubMed

Yang, Mingxing; Li, Xiumin; Li, Zhibin; Ou, Zhimin; Liu, Ming; Liu, Suhuan; Li, Xuejun; Yang, Shuyu

2013-01-01

DNA microarray analysis is characterized by obtaining a large number of gene variables from a small number of observations. Cluster analysis is widely used to analyze DNA microarray data to make classification and diagnosis of disease. Because there are so many irrelevant and insignificant genes in a dataset, a feature selection approach must be employed in data analysis. The performance of cluster analysis of this high-throughput data depends on whether the feature selection approach chooses the most relevant genes associated with disease classes. Here we proposed a new method using multiple Orthogonal Partial Least Squares-Discriminant Analysis (mOPLS-DA) models and S-plots to select the most relevant genes to conduct three-class disease classification and prediction. We tested our method using Golub's leukemia microarray data. For three classes with subtypes, we proposed hierarchical orthogonal partial least squares-discriminant analysis (OPLS-DA) models and S-plots to select features for two main classes and their subtypes. For three classes in parallel, we employed three OPLS-DA models and S-plots to choose marker genes for each class. The power of feature selection to classify and predict three-class disease was evaluated using cluster analysis. Further, the general performance of our method was tested using four public datasets and compared with those of four other feature selection methods. The results revealed that our method effectively selected the most relevant features for disease classification and prediction, and its performance was better than that of the other methods.

Performance of automated scoring of ER, PR, HER2, CK5/6 and EGFR in breast cancer tissue microarrays in the Breast Cancer Association Consortium

PubMed Central

Howat, William J; Blows, Fiona M; Provenzano, Elena; Brook, Mark N; Morris, Lorna; Gazinska, Patrycja; Johnson, Nicola; McDuffus, Leigh‐Anne; Miller, Jodi; Sawyer, Elinor J; Pinder, Sarah; van Deurzen, Carolien H M; Jones, Louise; Sironen, Reijo; Visscher, Daniel; Caldas, Carlos; Daley, Frances; Coulson, Penny; Broeks, Annegien; Sanders, Joyce; Wesseling, Jelle; Nevanlinna, Heli; Fagerholm, Rainer; Blomqvist, Carl; Heikkilä, Päivi; Ali, H Raza; Dawson, Sarah‐Jane; Figueroa, Jonine; Lissowska, Jolanta; Brinton, Louise; Mannermaa, Arto; Kataja, Vesa; Kosma, Veli‐Matti; Cox, Angela; Brock, Ian W; Cross, Simon S; Reed, Malcolm W; Couch, Fergus J; Olson, Janet E; Devillee, Peter; Mesker, Wilma E; Seyaneve, Caroline M; Hollestelle, Antoinette; Benitez, Javier; Perez, Jose Ignacio Arias; Menéndez, Primitiva; Bolla, Manjeet K; Easton, Douglas F; Schmidt, Marjanka K; Pharoah, Paul D; Sherman, Mark E

2014-01-01

Abstract Breast cancer risk factors and clinical outcomes vary by tumour marker expression. However, individual studies often lack the power required to assess these relationships, and large‐scale analyses are limited by the need for high throughput, standardized scoring methods. To address these limitations, we assessed whether automated image analysis of immunohistochemically stained tissue microarrays can permit rapid, standardized scoring of tumour markers from multiple studies. Tissue microarray sections prepared in nine studies containing 20 263 cores from 8267 breast cancers stained for two nuclear (oestrogen receptor, progesterone receptor), two membranous (human epidermal growth factor receptor 2 and epidermal growth factor receptor) and one cytoplasmic (cytokeratin 5/6) marker were scanned as digital images. Automated algorithms were used to score markers in tumour cells using the Ariol system. We compared automated scores against visual reads, and their associations with breast cancer survival. Approximately 65–70% of tissue microarray cores were satisfactory for scoring. Among satisfactory cores, agreement between dichotomous automated and visual scores was highest for oestrogen receptor (Kappa = 0.76), followed by human epidermal growth factor receptor 2 (Kappa = 0.69) and progesterone receptor (Kappa = 0.67). Automated quantitative scores for these markers were associated with hazard ratios for breast cancer mortality in a dose‐response manner. Considering visual scores of epidermal growth factor receptor or cytokeratin 5/6 as the reference, automated scoring achieved excellent negative predictive value (96–98%), but yielded many false positives (positive predictive value = 30–32%). For all markers, we observed substantial heterogeneity in automated scoring performance across tissue microarrays. Automated analysis is a potentially useful tool for large‐scale, quantitative scoring of immunohistochemically stained tissue microarrays available in consortia. However, continued optimization, rigorous marker‐specific quality control measures and standardization of tissue microarray designs, staining and scoring protocols is needed to enhance results. PMID:27499890

Lauren classification and individualized chemotherapy in gastric cancer.

PubMed

Ma, Junli; Shen, Hong; Kapesa, Linda; Zeng, Shan

2016-05-01

Gastric cancer is one of the most common malignancies worldwide. During the last 50 years, the histological classification of gastric carcinoma has been largely based on Lauren's criteria, in which gastric cancer is classified into two major histological subtypes, namely intestinal type and diffuse type adenocarcinoma. This classification was introduced in 1965, and remains currently widely accepted and employed, since it constitutes a simple and robust classification approach. The two histological subtypes of gastric cancer proposed by the Lauren classification exhibit a number of distinct clinical and molecular characteristics, including histogenesis, cell differentiation, epidemiology, etiology, carcinogenesis, biological behaviors and prognosis. Gastric cancer exhibits varied sensitivity to chemotherapy drugs and significant heterogeneity; therefore, the disease may be a target for individualized therapy. The Lauren classification may provide the basis for individualized treatment for advanced gastric cancer, which is increasingly gaining attention in the scientific field. However, few studies have investigated individualized treatment that is guided by pathological classification. The aim of the current review is to analyze the two major histological subtypes of gastric cancer, as proposed by the Lauren classification, and to discuss the implications of this for personalized chemotherapy.

FREQUENT SUBGRAPH MINING OF PERSONALIZED SIGNALING PATHWAY NETWORKS GROUPS PATIENTS WITH FREQUENTLY DYSREGULATED DISEASE PATHWAYS AND PREDICTS PROGNOSIS.

PubMed

Durmaz, Arda; Henderson, Tim A D; Brubaker, Douglas; Bebek, Gurkan

2017-01-01

Large scale genomics studies have generated comprehensive molecular characterization of numerous cancer types. Subtypes for many tumor types have been established; however, these classifications are based on molecular characteristics of a small gene sets with limited power to detect dysregulation at the patient level. We hypothesize that frequent graph mining of pathways to gather pathways functionally relevant to tumors can characterize tumor types and provide opportunities for personalized therapies. In this study we present an integrative omics approach to group patients based on their altered pathway characteristics and show prognostic differences within breast cancer (p < 9:57E - 10) and glioblastoma multiforme (p < 0:05) patients. We were able validate this approach in secondary RNA-Seq datasets with p < 0:05 and p < 0:01 respectively. We also performed pathway enrichment analysis to further investigate the biological relevance of dysregulated pathways. We compared our approach with network-based classifier algorithms and showed that our unsupervised approach generates more robust and biologically relevant clustering whereas previous approaches failed to report specific functions for similar patient groups or classify patients into prognostic groups. These results could serve as a means to improve prognosis for future cancer patients, and to provide opportunities for improved treatment options and personalized interventions. The proposed novel graph mining approach is able to integrate PPI networks with gene expression in a biologically sound approach and cluster patients in to clinically distinct groups. We have utilized breast cancer and glioblastoma multiforme datasets from microarray and RNA-Seq platforms and identified disease mechanisms differentiating samples. Supplementary methods, figures, tables and code are available at https://github.com/bebeklab/dysprog.

Use of lectin microarray to differentiate gastric cancer from gastric ulcer

PubMed Central

Huang, Wei-Li; Li, Yang-Guang; Lv, Yong-Chen; Guan, Xiao-Hui; Ji, Hui-Fan; Chi, Bao-Rong

2014-01-01

AIM: To investigate the feasibility of lectin microarray for differentiating gastric cancer from gastric ulcer. METHODS: Twenty cases of human gastric cancer tissue and 20 cases of human gastric ulcer tissue were collected and processed. Protein was extracted from the frozen tissues and stored. The lectins were dissolved in buffer, and the sugar-binding specificities of lectins and the layout of the lectin microarray were summarized. The median of the effective data points for each lectin was globally normalized to the sum of medians of all effective data points for each lectin in one block. Formalin-fixed paraffin-embedded gastric cancer tissues and their corresponding gastric ulcer tissues were subjected to Ag retrieval. Biotinylated lectin was used as the primary antibody and HRP-streptavidin as the secondary antibody. The glycopatterns of glycoprotein in gastric cancer and gastric ulcer specimens were determined by lectin microarray, and then validated by lectin histochemistry. Data are presented as mean ± SD for the indicated number of independent experiments. RESULTS: The glycosylation level of gastric cancer was significantly higher than that in ulcer. In gastric cancer, most of the lectin binders showed positive signals and the intensity of the signals was stronger, whereas the opposite was the case for ulcers. Significant differences in the pathological score of the two lectins were apparent between ulcer and gastric cancer tissues using the same lectin. For MPL and VVA, all types of gastric cancer detected showed stronger staining and a higher positive rate in comparison with ulcer, especially in the case of signet ring cell carcinoma and intra-mucosal carcinoma. GalNAc bound to MPL showed a significant increase. A statistically significant association between MPL and gastric cancer was observed. As with MPL, there were significant differences in VVA staining between gastric cancer and ulcer. CONCLUSION: Lectin microarray can differentiate the different glycopatterns in gastric cancer and gastric ulcer, and the lectins MPL and VVA can be used as biomarkers. PMID:24833877

Transcriptomic markers meet the real world: finding diagnostic signatures of corticosteroid treatment in commercial beef samples

PubMed Central

2012-01-01

Background The use of growth-promoters in beef cattle, despite the EU ban, remains a frequent practice. The use of transcriptomic markers has already proposed to identify indirect evidence of anabolic hormone treatment. So far, such approach has been tested in experimentally treated animals. Here, for the first time commercial samples were analyzed. Results Quantitative determination of Dexamethasone (DEX) residues in the urine collected at the slaughterhouse was performed by Liquid Chromatography-Mass Spectrometry (LC-MS). DNA-microarray technology was used to obtain transcriptomic profiles of skeletal muscle in commercial samples and negative controls. LC-MS confirmed the presence of low level of DEX residues in the urine of the commercial samples suspect for histological classification. Principal Component Analysis (PCA) on microarray data identified two clusters of samples. One cluster included negative controls and a subset of commercial samples, while a second cluster included part of the specimens collected at the slaughterhouse together with positives for corticosteroid treatment based on thymus histology and LC-MS. Functional analysis of the differentially expressed genes (3961) between the two groups provided further evidence that animals clustering with positive samples might have been treated with corticosteroids. These suspect samples could be reliably classified with a specific classification tool (Prediction Analysis of Microarray) using just two genes. Conclusions Despite broad variation observed in gene expression profiles, the present study showed that DNA-microarrays can be used to find transcriptomic signatures of putative anabolic treatments and that gene expression markers could represent a useful screening tool. PMID:23110699

Development and validation of a Luminex assay for detection of a predictive biomarker for PROSTVAC-VF therapy

PubMed Central

Lucas, Julie L.; Tacheny, Erin A.; Ferris, Allison; Galusha, Michelle; Srivastava, Apurva K.; Ganguly, Aniruddha; Williams, P. Mickey; Sachs, Michael C.; Thurin, Magdalena; Tricoli, James V.; Ricker, Winnie; Gildersleeve, Jeffrey C.

2017-01-01

Cancer therapies can provide substantially improved survival in some patients while other seemingly similar patients receive little or no benefit. Strategies to identify patients likely to respond well to a given therapy could significantly improve health care outcomes by maximizing clinical benefits while reducing toxicities and adverse effects. Using a glycan microarray assay, we recently reported that pretreatment serum levels of IgM specific to blood group A trisaccharide (BG-Atri) correlate positively with overall survival of cancer patients on PROSTVAC-VF therapy. The results suggested anti-BG-Atri IgM measured prior to treatment could serve as a biomarker for identifying patients likely to benefit from PROSTVAC-VF. For continued development and clinical application of serum IgM specific to BG-Atri as a predictive biomarker, a clinical assay was needed. In this study, we developed and validated a Luminex-based clinical assay for measuring serum IgM specific to BG-Atri. IgM levels were measured with the Luminex assay and compared to levels measured using the microarray for 126 healthy individuals and 77 prostate cancer patients. This assay provided reproducible and consistent results with low %CVs, and tolerance ranges were established for the assay. IgM levels measured using the Luminex assay were found to be highly correlated to the microarray results with R values of 0.93–0.95. This assay is a Laboratory Developed Test (LDT) and is suitable for evaluating thousands of serum samples in CLIA certified laboratories that have validated the assay. In addition, the study demonstrates that discoveries made using neoglycoprotein-based microarrays can be readily migrated to a clinical assay. PMID:28771597

Implementation of spectral clustering on microarray data of carcinoma using k-means algorithm

NASA Astrophysics Data System (ADS)

Frisca, Bustamam, Alhadi; Siswantining, Titin

2017-03-01

Clustering is one of data analysis methods that aims to classify data which have similar characteristics in the same group. Spectral clustering is one of the most popular modern clustering algorithms. As an effective clustering technique, spectral clustering method emerged from the concepts of spectral graph theory. Spectral clustering method needs partitioning algorithm. There are some partitioning methods including PAM, SOM, Fuzzy c-means, and k-means. Based on the research that has been done by Capital and Choudhury in 2013, when using Euclidian distance k-means algorithm provide better accuracy than PAM algorithm. So in this paper we use k-means as our partition algorithm. The major advantage of spectral clustering is in reducing data dimension, especially in this case to reduce the dimension of large microarray dataset. Microarray data is a small-sized chip made of a glass plate containing thousands and even tens of thousands kinds of genes in the DNA fragments derived from doubling cDNA. Application of microarray data is widely used to detect cancer, for the example is carcinoma, in which cancer cells express the abnormalities in his genes. The purpose of this research is to classify the data that have high similarity in the same group and the data that have low similarity in the others. In this research, Carcinoma microarray data using 7457 genes. The result of partitioning using k-means algorithm is two clusters.

A New Direction of Cancer Classification: Positive Effect of Low-Ranking MicroRNAs.

PubMed

Li, Feifei; Piao, Minghao; Piao, Yongjun; Li, Meijing; Ryu, Keun Ho

2014-10-01

Many studies based on microRNA (miRNA) expression profiles showed a new aspect of cancer classification. Because one characteristic of miRNA expression data is the high dimensionality, feature selection methods have been used to facilitate dimensionality reduction. The feature selection methods have one shortcoming thus far: they just consider the problem of where feature to class is 1:1 or n:1. However, because one miRNA may influence more than one type of cancer, human miRNA is considered to be ranked low in traditional feature selection methods and are removed most of the time. In view of the limitation of the miRNA number, low-ranking miRNAs are also important to cancer classification. We considered both high- and low-ranking features to cover all problems (1:1, n:1, 1:n, and m:n) in cancer classification. First, we used the correlation-based feature selection method to select the high-ranking miRNAs, and chose the support vector machine, Bayes network, decision tree, k-nearest-neighbor, and logistic classifier to construct cancer classification. Then, we chose Chi-square test, information gain, gain ratio, and Pearson's correlation feature selection methods to build the m:n feature subset, and used the selected miRNAs to determine cancer classification. The low-ranking miRNA expression profiles achieved higher classification accuracy compared with just using high-ranking miRNAs in traditional feature selection methods. Our results demonstrate that the m:n feature subset made a positive impression of low-ranking miRNAs in cancer classification.

The cross-validated AUC for MCP-logistic regression with high-dimensional data.

PubMed

Jiang, Dingfeng; Huang, Jian; Zhang, Ying

2013-10-01

We propose a cross-validated area under the receiving operator characteristic (ROC) curve (CV-AUC) criterion for tuning parameter selection for penalized methods in sparse, high-dimensional logistic regression models. We use this criterion in combination with the minimax concave penalty (MCP) method for variable selection. The CV-AUC criterion is specifically designed for optimizing the classification performance for binary outcome data. To implement the proposed approach, we derive an efficient coordinate descent algorithm to compute the MCP-logistic regression solution surface. Simulation studies are conducted to evaluate the finite sample performance of the proposed method and its comparison with the existing methods including the Akaike information criterion (AIC), Bayesian information criterion (BIC) or Extended BIC (EBIC). The model selected based on the CV-AUC criterion tends to have a larger predictive AUC and smaller classification error than those with tuning parameters selected using the AIC, BIC or EBIC. We illustrate the application of the MCP-logistic regression with the CV-AUC criterion on three microarray datasets from the studies that attempt to identify genes related to cancers. Our simulation studies and data examples demonstrate that the CV-AUC is an attractive method for tuning parameter selection for penalized methods in high-dimensional logistic regression models.

Discrimination of Influenza Infection (A/2009 H1N1) from Prior Exposure by Antibody Protein Microarray Analysis

PubMed Central

te Beest, Dennis; de Bruin, Erwin; Imholz, Sandra; Wallinga, Jacco; Teunis, Peter; Koopmans, Marion; van Boven, Michiel

2014-01-01

Reliable discrimination of recent influenza A infection from previous exposure using hemagglutination inhibition (HI) or virus neutralization tests is currently not feasible. This is due to low sensitivity of the tests and the interference of antibody responses generated by previous infections. Here we investigate the diagnostic characteristics of a newly developed antibody (HA1) protein microarray using data from cross-sectional serological studies carried out before and after the pandemic of 2009. The data are analysed by mixture models, providing a probabilistic classification of sera (susceptible, prior-exposed, recently infected). Estimated sensitivity and specificity for identifying A/2009 infections are low using HI (66% and 51%), and high when using A/2009 microarray data alone or together with A/1918 microarray data (96% and 95%). As a heuristic, a high A/2009 to A/1918 antibody ratio (>1.05) is indicative of recent infection, while a low ratio is indicative of a pre-existing response, even if the A/2009 titer is high. We conclude that highly sensitive and specific classification of individual sera is possible using the protein microarray, thereby enabling precise estimation of age-specific infection attack rates in the population even if sample sizes are small. PMID:25405997

Bayesian hierarchical modeling for subject-level response classification in peptide microarray immunoassays

PubMed Central

Imholte, Gregory; Gottardo, Raphael

2017-01-01

Summary The peptide microarray immunoassay simultaneously screens sample serum against thousands of peptides, determining the presence of antibodies bound to array probes. Peptide microarrays tiling immunogenic regions of pathogens (e.g. envelope proteins of a virus) are an important high throughput tool for querying and mapping antibody binding. Because of the assay’s many steps, from probe synthesis to incubation, peptide microarray data can be noisy with extreme outliers. In addition, subjects may produce different antibody profiles in response to an identical vaccine stimulus or infection, due to variability among subjects’ immune systems. We present a robust Bayesian hierarchical model for peptide microarray experiments, pepBayes, to estimate the probability of antibody response for each subject/peptide combination. Heavy-tailed error distributions accommodate outliers and extreme responses, and tailored random effect terms automatically incorporate technical effects prevalent in the assay. We apply our model to two vaccine trial datasets to demonstrate model performance. Our approach enjoys high sensitivity and specificity when detecting vaccine induced antibody responses. A simulation study shows an adaptive thresholding classification method has appropriate false discovery rate control with high sensitivity, and receiver operating characteristics generated on vaccine trial data suggest that pepBayes clearly separates responses from non-responses. PMID:27061097

Evaluating concentration estimation errors in ELISA microarray experiments

DOE Office of Scientific and Technical Information (OSTI.GOV)

Daly, Don S.; White, Amanda M.; Varnum, Susan M.

Enzyme-linked immunosorbent assay (ELISA) is a standard immunoassay to predict a protein concentration in a sample. Deploying ELISA in a microarray format permits simultaneous prediction of the concentrations of numerous proteins in a small sample. These predictions, however, are uncertain due to processing error and biological variability. Evaluating prediction error is critical to interpreting biological significance and improving the ELISA microarray process. Evaluating prediction error must be automated to realize a reliable high-throughput ELISA microarray system. Methods: In this paper, we present a statistical method based on propagation of error to evaluate prediction errors in the ELISA microarray process. Althoughmore » propagation of error is central to this method, it is effective only when comparable data are available. Therefore, we briefly discuss the roles of experimental design, data screening, normalization and statistical diagnostics when evaluating ELISA microarray prediction errors. We use an ELISA microarray investigation of breast cancer biomarkers to illustrate the evaluation of prediction errors. The illustration begins with a description of the design and resulting data, followed by a brief discussion of data screening and normalization. In our illustration, we fit a standard curve to the screened and normalized data, review the modeling diagnostics, and apply propagation of error.« less

In-depth characterization of breast cancer tumor-promoting cell transcriptome by RNA sequencing and microarrays

PubMed Central

Soldà, Giulia; Merlino, Giuseppe; Fina, Emanuela; Brini, Elena; Moles, Anna; Cappelletti, Vera; Daidone, Maria Grazia

2016-01-01

Numerous studies have reported the existence of tumor-promoting cells (TPC) with self-renewal potential and a relevant role in drug resistance. However, pathways and modifications involved in the maintenance of such tumor subpopulations are still only partially understood. Sequencing-based approaches offer the opportunity for a detailed study of TPC including their transcriptome modulation. Using microarrays and RNA sequencing approaches, we compared the transcriptional profiles of parental MCF7 breast cancer cells with MCF7-derived TPC (i.e. MCFS). Data were explored using different bioinformatic approaches, and major findings were experimentally validated. The different analytical pipelines (Lifescope and Cufflinks based) yielded similar although not identical results. RNA sequencing data partially overlapped microarray results and displayed a higher dynamic range, although overall the two approaches concordantly predicted pathway modifications. Several biological functions were altered in TPC, ranging from production of inflammatory cytokines (i.e., IL-8 and MCP-1) to proliferation and response to steroid hormones. More than 300 non-coding RNAs were defined as differentially expressed, and 2,471 potential splicing events were identified. A consensus signature of genes up-regulated in TPC was derived and was found to be significantly associated with insensitivity to fulvestrant in a public breast cancer patient dataset. Overall, we obtained a detailed portrait of the transcriptome of a breast cancer TPC line, highlighted the role of non-coding RNAs and differential splicing, and identified a gene signature with a potential as a context-specific biomarker in patients receiving endocrine treatment. PMID:26556871

Missing-value estimation using linear and non-linear regression with Bayesian gene selection.

PubMed

Zhou, Xiaobo; Wang, Xiaodong; Dougherty, Edward R

2003-11-22

Data from microarray experiments are usually in the form of large matrices of expression levels of genes under different experimental conditions. Owing to various reasons, there are frequently missing values. Estimating these missing values is important because they affect downstream analysis, such as clustering, classification and network design. Several methods of missing-value estimation are in use. The problem has two parts: (1) selection of genes for estimation and (2) design of an estimation rule. We propose Bayesian variable selection to obtain genes to be used for estimation, and employ both linear and nonlinear regression for the estimation rule itself. Fast implementation issues for these methods are discussed, including the use of QR decomposition for parameter estimation. The proposed methods are tested on data sets arising from hereditary breast cancer and small round blue-cell tumors. The results compare very favorably with currently used methods based on the normalized root-mean-square error. The appendix is available from http://gspsnap.tamu.edu/gspweb/zxb/missing_zxb/ (user: gspweb; passwd: gsplab).

Applicability of the Proposed Japanese Model for the Classification of Gastric Cancer Location: The "PROTRADIST" Retrospective Study.

PubMed

Marano, Luigi; Petrillo, Marianna; Pezzella, Modestino; Patriti, Alberto; Braccio, Bartolomeo; Esposito, Giuseppe; Grassia, Michele; Romano, Angela; Torelli, Francesco; De Luca, Raffaele; Fabozzi, Alessio; Falco, Giuseppe; Di Martino, Natale

2017-06-01

The extension of lymphadenectomy for surgical treatment of gastric cancer remains discordant among European and Japanese surgeons. Kinami et al. (Kinami S, Fujimura T, Ojima E, et al. PTD classification: proposal for a new classification of gastric cancer location based on physiological lymphatic flow. Int. J. Clin. Oncol. 2008;13:320-329) proposed a new experimental classification, the "Proximal zone, Transitional zone, Distal zone" (PTD) classification, based on the physiological lymphatic flow of gastric cancer site. The aim of the present retrospective study is to assess the applicability of PTD Japanese model in gastric cancer patients of our Western surgical department. Two groups of patients with histologically documented adenocarcinoma of the stomach were retrospectively obtained: In the first group were categorized 89 patients with T1a-T1b tumor invasion; and in the second group were 157 patients with T2-T3 category. The data collected were then categorized according to the PTD classification. In the T1a-T1b group there were no lymph node metastases within the r-GA or r-GEA compartments for tumors located in the P portion, and similarly there were no lymphatic metastases within the l-GEA or p-GA compartments for tumors located in the D portion. On the contrary, in the T2-T3 group the lymph node metastases presented a diffused spreading with no statistical significance between the two classification models. Our results show that the PTD classification based on physiological lymphatic flow of the gastric cancer site is a more physiological and clinical version than the Upper, Medium And Lower classification. It represents a valuable and applicable model of cancer location that could be a guide to a tailored surgical approach in Italian patients with neoplasm confined to submucosa. Nevertheless, in order to confirm our findings, larger and prospective studies are needed.

Intratumoral heterogeneity as a source of discordance in breast cancer biomarker classification.

PubMed

Allott, Emma H; Geradts, Joseph; Sun, Xuezheng; Cohen, Stephanie M; Zirpoli, Gary R; Khoury, Thaer; Bshara, Wiam; Chen, Mengjie; Sherman, Mark E; Palmer, Julie R; Ambrosone, Christine B; Olshan, Andrew F; Troester, Melissa A

2016-06-28

Spatial heterogeneity in biomarker expression may impact breast cancer classification. The aims of this study were to estimate the frequency of spatial heterogeneity in biomarker expression within tumors, to identify technical and biological factors contributing to spatial heterogeneity, and to examine the impact of discordant biomarker status within tumors on clinical record agreement. Tissue microarrays (TMAs) were constructed using two to four cores (1.0 mm) for each of 1085 invasive breast cancers from the Carolina Breast Cancer Study, which is part of the AMBER Consortium. Immunohistochemical staining for estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2) was quantified using automated digital imaging analysis. The biomarker status for each core and for each case was assigned using clinical thresholds. Cases with core-to-core biomarker discordance were manually reviewed to distinguish intratumoral biomarker heterogeneity from misclassification of biomarker status by the automated algorithm. The impact of core-to-core biomarker discordance on case-level agreement between TMAs and the clinical record was evaluated. On the basis of automated analysis, discordant biomarker status between TMA cores occurred in 9 %, 16 %, and 18 % of cases for ER, PR, and HER2, respectively. Misclassification of benign epithelium and/or ductal carcinoma in situ as invasive carcinoma by the automated algorithm was implicated in discordance among cores. However, manual review of discordant cases confirmed spatial heterogeneity as a source of discordant biomarker status between cores in 2 %, 7 %, and 8 % of cases for ER, PR, and HER2, respectively. Overall, agreement between TMA and clinical record was high for ER (94 %), PR (89 %), and HER2 (88 %), but it was reduced in cases with core-to-core discordance (agreement 70 % for ER, 61 % for PR, and 57 % for HER2). Intratumoral biomarker heterogeneity may impact breast cancer classification accuracy, with implications for clinical management. Both manually confirmed biomarker heterogeneity and misclassification of biomarker status by automated image analysis contribute to discordant biomarker status between TMA cores. Given that manually confirmed heterogeneity is uncommon (<10 % of cases), large studies are needed to study the impact of heterogeneous biomarker expression on breast cancer classification and outcomes.

Characterization of 1577 primary prostate cancers reveals novel biological and clinicopathologic insights into molecular subtypes.

PubMed

Tomlins, Scott A; Alshalalfa, Mohammed; Davicioni, Elai; Erho, Nicholas; Yousefi, Kasra; Zhao, Shuang; Haddad, Zaid; Den, Robert B; Dicker, Adam P; Trock, Bruce J; DeMarzo, Angelo M; Ross, Ashley E; Schaeffer, Edward M; Klein, Eric A; Magi-Galluzzi, Cristina; Karnes, R Jeffrey; Jenkins, Robert B; Feng, Felix Y

2015-10-01

Prostate cancer (PCa) molecular subtypes have been defined by essentially mutually exclusive events, including ETS gene fusions (most commonly involving ERG) and SPINK1 overexpression. Clinical assessment may aid in disease stratification, complementing available prognostic tests. To determine the analytical validity and clinicopatholgic associations of microarray-based molecular subtyping. We analyzed Affymetrix GeneChip expression profiles for 1577 patients from eight radical prostatectomy cohorts, including 1351 cases assessed using the Decipher prognostic assay (GenomeDx Biosciences, San Diego, CA, USA) performed in a laboratory with Clinical Laboratory Improvements Amendment certification. A microarray-based (m-) random forest ERG classification model was trained and validated. Outlier expression analysis was used to predict other mutually exclusive non-ERG ETS gene rearrangements (ETS(+)) or SPINK1 overexpression (SPINK1(+)). Associations with clinical features and outcomes by multivariate logistic regression analysis and receiver operating curves. The m-ERG classifier showed 95% accuracy in an independent validation subset (155 samples). Across cohorts, 45% of PCas were classified as m-ERG(+), 9% as m-ETS(+), 8% as m-SPINK1(+), and 38% as triple negative (m-ERG(-)/m-ETS(-)/m-SPINK1(-)). Gene expression profiling supports three underlying molecularly defined groups: m-ERG(+), m-ETS(+), and m-SPINK1(+)/triple negative. On multivariate analysis, m-ERG(+) tumors were associated with lower preoperative serum prostate-specific antigen and Gleason scores, but greater extraprostatic extension (p<0.001). m-ETS(+) tumors were associated with seminal vesicle invasion (p=0.01), while m-SPINK1(+)/triple negative tumors had higher Gleason scores and were more frequent in Black/African American patients (p<0.001). Clinical outcomes were not significantly different among subtypes. A clinically available prognostic test (Decipher) can also assess PCa molecular subtypes, obviating the need for additional testing. Clinicopathologic differences were found among subtypes based on global expression patterns. Molecular subtyping of prostate cancer can be achieved using extra data generated from a clinical-grade, genome-wide expression-profiling prognostic assay (Decipher). Transcriptomic and clinical analysis support three distinct molecular subtypes: (1) m-ERG(+), (2) m-ETS(+), and (3) m-SPINK1(+)/triple negative (m-ERG(-)/m-ETS(-)/m-SPINK1(-)). Incorporation of subtyping into a clinically available assay may facilitate additional applications beyond routine prognosis. Copyright © 2015 European Association of Urology. Published by Elsevier B.V. All rights reserved.

OY-TES-1 may regulate the malignant behavior of liver cancer via NANOG, CD9, CCND2 and CDCA3: a bioinformatic analysis combine with RNAi and oligonucleotide microarray.

PubMed

Hu, Qiping; Fu, Jun; Luo, Bin; Huang, Miao; Guo, Wenwen; Lin, Yongda; Xie, Xiaoxun; Xiao, Shaowen

2015-04-01

Given its tumor-specific expression, including liver cancer, OY-TES-1 is a potential molecular marker for the diagnosis and immunotherapy of liver cancers. However, investigations of the mechanisms and the role of OY-TES-1 in liver cancer are rare. In the present study, based on a comprehensive bioinformatic analysis combined with RNA interference (RNAi) and oligonucleotide microarray, we report for the first time that downregulation of OY-TES-1 resulted in significant changes in expression of NANOG, CD9, CCND2 and CDCA3 in the liver cancer cell line BEL-7404. NANOG, CD9, CCND2 and CDCA3 may be involved in cell proliferation, migration, invasion and apoptosis, yet also may be functionally related to each other and OY-TES-1. Among these molecules, we identified that NANOG, containing a Kazal-2 binding motif and homeobox, may be the most likely candidate protein interacting with OY-TES-1 in liver cancer. Thus, the present study may provide important information for further investigation of the roles of OY-TES-1 in liver cancer.

Hydrogel droplet microarrays with trapped antibody-functionalized beads for multiplexed protein analysis.

PubMed

Li, Huiyan; Leulmi, Rym Feriel; Juncker, David

2011-02-07

Antibody microarrays are a powerful tool for rapid, multiplexed profiling of proteins. 3D microarray substrates have been developed to improve binding capacity, assay sensitivity, and mass transport, however, they often rely on photopolymers which are difficult to manufacture and have a small pore size that limits mass transport and demands long incubation time. Here, we present a novel 3D antibody microarray format based on the entrapment of antibody-coated microbeads within alginate droplets that were spotted onto a glass slide using an inkjet. Owing to the low concentration of alginate used, the gels were highly porous to proteins, and together with the 3D architecture helped enhance mass transport during the assays. The spotting parameters were optimized for the attachment of the alginate to the substrate. Beads with 0.2 µm, 0.5 µm and 1 µm diameter were tested and 1 µm beads were selected based on their superior retention within the hydrogel. The beads were found to be distributed within the entire volume of the gel droplet using confocal microscopy. The assay time and the concentration of beads in the gels were investigated for maximal binding signal using one-step immunoassays. As a proof of concept, six proteins including cytokines (TNFα, IL-8 and MIP/CCL4), breast cancer biomarkers (CEA and HER2) and one cancer-related protein (ENG) were profiled in multiplex using sandwich assays down to pg mL(-1) concentrations with 1 h incubation without agitation in both buffer solutions and 10% serum. These results illustrate the potential of beads-in-gel microarrays for highly sensitive and multiplexed protein analysis.

Kernel-imbedded Gaussian processes for disease classification using microarray gene expression data

PubMed Central

Zhao, Xin; Cheung, Leo Wang-Kit

2007-01-01

Background Designing appropriate machine learning methods for identifying genes that have a significant discriminating power for disease outcomes has become more and more important for our understanding of diseases at genomic level. Although many machine learning methods have been developed and applied to the area of microarray gene expression data analysis, the majority of them are based on linear models, which however are not necessarily appropriate for the underlying connection between the target disease and its associated explanatory genes. Linear model based methods usually also bring in false positive significant features more easily. Furthermore, linear model based algorithms often involve calculating the inverse of a matrix that is possibly singular when the number of potentially important genes is relatively large. This leads to problems of numerical instability. To overcome these limitations, a few non-linear methods have recently been introduced to the area. Many of the existing non-linear methods have a couple of critical problems, the model selection problem and the model parameter tuning problem, that remain unsolved or even untouched. In general, a unified framework that allows model parameters of both linear and non-linear models to be easily tuned is always preferred in real-world applications. Kernel-induced learning methods form a class of approaches that show promising potentials to achieve this goal. Results A hierarchical statistical model named kernel-imbedded Gaussian process (KIGP) is developed under a unified Bayesian framework for binary disease classification problems using microarray gene expression data. In particular, based on a probit regression setting, an adaptive algorithm with a cascading structure is designed to find the appropriate kernel, to discover the potentially significant genes, and to make the optimal class prediction accordingly. A Gibbs sampler is built as the core of the algorithm to make Bayesian inferences. Simulation studies showed that, even without any knowledge of the underlying generative model, the KIGP performed very close to the theoretical Bayesian bound not only in the case with a linear Bayesian classifier but also in the case with a very non-linear Bayesian classifier. This sheds light on its broader usability to microarray data analysis problems, especially to those that linear methods work awkwardly. The KIGP was also applied to four published microarray datasets, and the results showed that the KIGP performed better than or at least as well as any of the referred state-of-the-art methods did in all of these cases. Conclusion Mathematically built on the kernel-induced feature space concept under a Bayesian framework, the KIGP method presented in this paper provides a unified machine learning approach to explore both the linear and the possibly non-linear underlying relationship between the target features of a given binary disease classification problem and the related explanatory gene expression data. More importantly, it incorporates the model parameter tuning into the framework. The model selection problem is addressed in the form of selecting a proper kernel type. The KIGP method also gives Bayesian probabilistic predictions for disease classification. These properties and features are beneficial to most real-world applications. The algorithm is naturally robust in numerical computation. The simulation studies and the published data studies demonstrated that the proposed KIGP performs satisfactorily and consistently. PMID:17328811

Gene selection for cancer classification with the help of bees.

PubMed

Moosa, Johra Muhammad; Shakur, Rameen; Kaykobad, Mohammad; Rahman, Mohammad Sohel

2016-08-10

Development of biologically relevant models from gene expression data notably, microarray data has become a topic of great interest in the field of bioinformatics and clinical genetics and oncology. Only a small number of gene expression data compared to the total number of genes explored possess a significant correlation with a certain phenotype. Gene selection enables researchers to obtain substantial insight into the genetic nature of the disease and the mechanisms responsible for it. Besides improvement of the performance of cancer classification, it can also cut down the time and cost of medical diagnoses. This study presents a modified Artificial Bee Colony Algorithm (ABC) to select minimum number of genes that are deemed to be significant for cancer along with improvement of predictive accuracy. The search equation of ABC is believed to be good at exploration but poor at exploitation. To overcome this limitation we have modified the ABC algorithm by incorporating the concept of pheromones which is one of the major components of Ant Colony Optimization (ACO) algorithm and a new operation in which successive bees communicate to share their findings. The proposed algorithm is evaluated using a suite of ten publicly available datasets after the parameters are tuned scientifically with one of the datasets. Obtained results are compared to other works that used the same datasets. The performance of the proposed method is proved to be superior. The method presented in this paper can provide subset of genes leading to more accurate classification results while the number of selected genes is smaller. Additionally, the proposed modified Artificial Bee Colony Algorithm could conceivably be applied to problems in other areas as well.

New Web-Based Tools Make Systems Pharmacology More Accessible Using Data from the NCI-60 | Center for Cancer Research

Cancer.gov

High-throughput biological techniques, like microarrays and drug screens, generate an enormous amount of data that may be critically important for cancer researchers and clinicians. Being able to manipulate the data to extract those pieces of interest, however, can require computational or bioinformatics skills beyond those of the average scientist.

Automatic image analysis and spot classification for detection of pathogenic Escherichia coli on glass slide DNA microarrays

USDA-ARS?s Scientific Manuscript database

A computer algorithm was created to inspect scanned images from DNA microarray slides developed to rapidly detect and genotype E. Coli O157 virulent strains. The algorithm computes centroid locations for signal and background pixels in RGB space and defines a plane perpendicular to the line connect...

Classifying breast cancer surgery: a novel, complexity-based system for oncological, oncoplastic and reconstructive procedures, and proof of principle by analysis of 1225 operations in 1166 patients.

PubMed

Hoffmann, Jürgen; Wallwiener, Diethelm

2009-04-08

One of the basic prerequisites for generating evidence-based data is the availability of classification systems. Attempts to date to classify breast cancer operations have focussed on specific problems, e.g. the avoidance of secondary corrective surgery for surgical defects, rather than taking a generic approach. Starting from an existing, simpler empirical scheme based on the complexity of breast surgical procedures, which was used in-house primarily in operative report-writing, a novel classification of ablative and breast-conserving procedures initially needed to be developed and elaborated systematically. To obtain proof of principle, a prospectively planned analysis of patient records for all major breast cancer-related operations performed at our breast centre in 2005 and 2006 was conducted using the new classification. Data were analysed using basic descriptive statistics such as frequency tables. A novel two-type, six-tier classification system comprising 12 main categories, 13 subcategories and 39 sub-subcategories of oncological, oncoplastic and reconstructive breast cancer-related surgery was successfully developed. Our system permitted unequivocal classification, without exception, of all 1225 procedures performed in 1166 breast cancer patients in 2005 and 2006. Breast cancer-related surgical procedures can be generically classified according to their surgical complexity. Analysis of all major procedures performed at our breast centre during the study period provides proof of principle for this novel classification system. We envisage various applications for this classification, including uses in randomised clinical trials, guideline development, specialist surgical training, continuing professional development as well as quality of care and public health research.

Quantum Cascade Laser-Based Infrared Microscopy for Label-Free and Automated Cancer Classification in Tissue Sections.

PubMed

Kuepper, Claus; Kallenbach-Thieltges, Angela; Juette, Hendrik; Tannapfel, Andrea; Großerueschkamp, Frederik; Gerwert, Klaus

2018-05-16

A feasibility study using a quantum cascade laser-based infrared microscope for the rapid and label-free classification of colorectal cancer tissues is presented. Infrared imaging is a reliable, robust, automated, and operator-independent tissue classification method that has been used for differential classification of tissue thin sections identifying tumorous regions. However, long acquisition time by the so far used FT-IR-based microscopes hampered the clinical translation of this technique. Here, the used quantum cascade laser-based microscope provides now infrared images for precise tissue classification within few minutes. We analyzed 110 patients with UICC-Stage II and III colorectal cancer, showing 96% sensitivity and 100% specificity of this label-free method as compared to histopathology, the gold standard in routine clinical diagnostics. The main hurdle for the clinical translation of IR-Imaging is overcome now by the short acquisition time for high quality diagnostic images, which is in the same time range as frozen sections by pathologists.

Wavelet-based identification of DNA focal genomic aberrations from single nucleotide polymorphism arrays

PubMed Central

2011-01-01

Background Copy number aberrations (CNAs) are an important molecular signature in cancer initiation, development, and progression. However, these aberrations span a wide range of chromosomes, making it hard to distinguish cancer related genes from other genes that are not closely related to cancer but are located in broadly aberrant regions. With the current availability of high-resolution data sets such as single nucleotide polymorphism (SNP) microarrays, it has become an important issue to develop a computational method to detect driving genes related to cancer development located in the focal regions of CNAs. Results In this study, we introduce a novel method referred to as the wavelet-based identification of focal genomic aberrations (WIFA). The use of the wavelet analysis, because it is a multi-resolution approach, makes it possible to effectively identify focal genomic aberrations in broadly aberrant regions. The proposed method integrates multiple cancer samples so that it enables the detection of the consistent aberrations across multiple samples. We then apply this method to glioblastoma multiforme and lung cancer data sets from the SNP microarray platform. Through this process, we confirm the ability to detect previously known cancer related genes from both cancer types with high accuracy. Also, the application of this approach to a lung cancer data set identifies focal amplification regions that contain known oncogenes, though these regions are not reported using a recent CNAs detecting algorithm GISTIC: SMAD7 (chr18q21.1) and FGF10 (chr5p12). Conclusions Our results suggest that WIFA can be used to reveal cancer related genes in various cancer data sets. PMID:21569311

Integrated analysis of chromosome copy number variation and gene expression in cervical carcinoma

PubMed Central

Yan, Deng; Yi, Song; Chiu, Wang Chi; Qin, Liu Gui; Kin, Wong Hoi; Kwok Hung, Chung Tony; Linxiao, Han; Wai, Choy Kwong; Yi, Sui; Tao, Yang; Tao, Tang

2017-01-01

Objective This study was conducted to explore chromosomal copy number variations (CNV) and transcript expression and to examine pathways in cervical pathogenesis using genome-wide high resolution microarrays. Methods Genome-wide chromosomal CNVs were investigated in 6 cervical cancer cell lines by Human Genome CGH Microarray Kit (4x44K). Gene expression profiles in cervical cancer cell lines, primary cervical carcinoma and normal cervical epithelium tissues were also studied using the Whole Human Genome Microarray Kit (4x44K). Results Fifty common chromosomal CNVs were identified in the cervical cancer cell lines. Correlation analysis revealed that gene up-regulation or down-regulation is significantly correlated with genomic amplification (P=0.009) or deletion (P=0.006) events. Expression profiles were identified through cluster analysis. Gene annotation analysis pinpointed cell cycle pathways was significantly (P=1.15E-08) affected in cervical cancer. Common CNVs were associated with cervical cancer. Conclusion Chromosomal CNVs may contribute to their transcript expression in cervical cancer. PMID:29312578

Integrated analysis of chromosome copy number variation and gene expression in cervical carcinoma.

PubMed

Yan, Deng; Yi, Song; Chiu, Wang Chi; Qin, Liu Gui; Kin, Wong Hoi; Kwok Hung, Chung Tony; Linxiao, Han; Wai, Choy Kwong; Yi, Sui; Tao, Yang; Tao, Tang

2017-12-12

This study was conducted to explore chromosomal copy number variations (CNV) and transcript expression and to examine pathways in cervical pathogenesis using genome-wide high resolution microarrays. Genome-wide chromosomal CNVs were investigated in 6 cervical cancer cell lines by Human Genome CGH Microarray Kit (4x44K). Gene expression profiles in cervical cancer cell lines, primary cervical carcinoma and normal cervical epithelium tissues were also studied using the Whole Human Genome Microarray Kit (4x44K). Fifty common chromosomal CNVs were identified in the cervical cancer cell lines. Correlation analysis revealed that gene up-regulation or down-regulation is significantly correlated with genomic amplification ( P =0.009) or deletion ( P =0.006) events. Expression profiles were identified through cluster analysis. Gene annotation analysis pinpointed cell cycle pathways was significantly ( P =1.15E-08) affected in cervical cancer. Common CNVs were associated with cervical cancer. Chromosomal CNVs may contribute to their transcript expression in cervical cancer.

A Versatile Microarray Platform for Capturing Rare Cells

NASA Astrophysics Data System (ADS)

Brinkmann, Falko; Hirtz, Michael; Haller, Anna; Gorges, Tobias M.; Vellekoop, Michael J.; Riethdorf, Sabine; Müller, Volkmar; Pantel, Klaus; Fuchs, Harald

2015-10-01

Analyses of rare events occurring at extremely low frequencies in body fluids are still challenging. We established a versatile microarray-based platform able to capture single target cells from large background populations. As use case we chose the challenging application of detecting circulating tumor cells (CTCs) - about one cell in a billion normal blood cells. After incubation with an antibody cocktail, targeted cells are extracted on a microarray in a microfluidic chip. The accessibility of our platform allows for subsequent recovery of targets for further analysis. The microarray facilitates exclusion of false positive capture events by co-localization allowing for detection without fluorescent labelling. Analyzing blood samples from cancer patients with our platform reached and partly outreached gold standard performance, demonstrating feasibility for clinical application. Clinical researchers free choice of antibody cocktail without need for altered chip manufacturing or incubation protocol, allows virtual arbitrary targeting of capture species and therefore wide spread applications in biomedical sciences.

Differential blood-based diagnosis between benign prostatic hyperplasia and prostate cancer: miRNA as source for biomarkers independent of PSA level, Gleason score, or TNM status.

PubMed

Leidinger, Petra; Hart, Martin; Backes, Christina; Rheinheimer, Stefanie; Keck, Bastian; Wullich, Bernd; Keller, Andreas; Meese, Eckart

2016-08-01

Since the benefit of prostate-specific antigen (PSA) screening remains controversial, new non-invasive biomarkers for prostate carcinoma (PCa) are still required. There is evidence that microRNAs (miRNAs) in whole peripheral blood can separate patients with localized prostate cancer from healthy individuals. However, the potential of blood-based miRNAs for the differential diagnosis of PCa and benign prostatic hyperplasia (BPH) has not been tested. We compared the miRNome from blood of PCa and BPH patients and further investigated the influence of the tumor volume, tumor-node-metastasis (TNM) classification, Gleason score, pretreatment risk status, and the pretreatment PSA value on the miRNA pattern. By microarray approach, we identified seven miRNAs that were significantly deregulated in PCa patients compared to BPH patients. Using quantitative real time PCR (qRT-PCR), we confirmed downregulation of hsa-miR-221* (now hsa-miR-221-5p) and hsa-miR-708* (now hsa-miR-708-3p) in PCa compared to BPH. Clinical parameters like PSA level, Gleason score, or TNM status seem to have only limited impact on the overall abundance of miRNAs in patients' blood, suggesting a no influence of these factors on the expression of deregulated miRNAs.

Tumor immunology.

PubMed

Mocellin, Simone; Lise, Mario; Nitti, Donato

2007-01-01

Advances in tumor immunology are supporting the clinical implementation of several immunological approaches to cancer in the clinical setting. However, the alternate success of current immunotherapeutic regimens underscores the fact that the molecular mechanisms underlying immune-mediated tumor rejection are still poorly understood. Given the complexity of the immune system network and the multidimensionality of tumor/host interactions, the comprehension of tumor immunology might greatly benefit from high-throughput microarray analysis, which can portrait the molecular kinetics of immune response on a genome-wide scale, thus accelerating the discovery pace and ultimately catalyzing the development of new hypotheses in cell biology. Although in its infancy, the implementation of microarray technology in tumor immunology studies has already provided investigators with novel data and intriguing new hypotheses on the molecular cascade leading to an effective immune response against cancer. Although the general principles of microarray-based gene profiling have rapidly spread in the scientific community, the need for mastering this technique to produce meaningful data and correctly interpret the enormous output of information generated by this technology is critical and represents a tremendous challenge for investigators, as outlined in the first section of this book. In the present Chapter, we report on some of the most significant results obtained with the application of DNA microarray in this oncology field.

Role of PELP1 in EGFR-ER Signaling Crosstalk in Ovarian Cancer Cells

DTIC Science & Technology

2009-04-01

expression of genes involved in metastasis using a focused microarray approach. We have used Human Tumor Metastasis Microarray (Oligo GE array from...ovarian cancer progression. Analysis of human genome databases and SAGE data suggested deregulation of PELP1 expression in ovarian cancer cells...PI3K, and STAT3 in the cytosol. PELP1/MNAR regulates meiosis via its interactions with heterotimeric Gbc protein, androgen receptor (AR), and by

Regression-Based Approach For Feature Selection In Classification Issues. Application To Breast Cancer Detection And Recurrence

NASA Astrophysics Data System (ADS)

Belciug, Smaranda; Serbanescu, Mircea-Sebastian

2015-09-01

Feature selection is considered a key factor in classifications/decision problems. It is currently used in designing intelligent decision systems to choose the best features which allow the best performance. This paper proposes a regression-based approach to select the most important predictors to significantly increase the classification performance. Application to breast cancer detection and recurrence using publically available datasets proved the efficiency of this technique.

From High-Throughput Microarray-Based Screening to Clinical Application: The Development of a Second Generation Multigene Test for Breast Cancer Prognosis

PubMed Central

Brase, Jan C.; Kronenwett, Ralf; Petry, Christoph; Denkert, Carsten; Schmidt, Marcus

2013-01-01

Several multigene tests have been developed for breast cancer patients to predict the individual risk of recurrence. Most of the first generation tests rely on proliferation-associated genes and are commonly carried out in central reference laboratories. Here, we describe the development of a second generation multigene assay, the EndoPredict test, a prognostic multigene expression test for estrogen receptor (ER) positive, human epidermal growth factor receptor (HER2) negative (ER+/HER2−) breast cancer patients. The EndoPredict gene signature was initially established in a large high-throughput microarray-based screening study. The key steps for biomarker identification are discussed in detail, in comparison to the establishment of other multigene signatures. After biomarker selection, genes and algorithms were transferred to a diagnostic platform (reverse transcription quantitative PCR (RT-qPCR)) to allow for assaying formalin-fixed, paraffin-embedded (FFPE) samples. A comprehensive analytical validation was performed and a prospective proficiency testing study with seven pathological laboratories finally proved that EndoPredict can be reliably used in the decentralized setting. Three independent large clinical validation studies (n = 2,257) demonstrated that EndoPredict offers independent prognostic information beyond current clinicopathological parameters and clinical guidelines. The review article summarizes several important steps that should be considered for the development process of a second generation multigene test and offers a means for transferring a microarray signature from the research laboratory to clinical practice. PMID:27605191

Epithelial cancer detection by oblique-incidence optical spectroscopy

NASA Astrophysics Data System (ADS)

Garcia-Uribe, Alejandro; Balareddy, Karthik C.; Zou, Jun; Wang, Kenneth K.; Duvic, Madeleine; Wang, Lihong V.

2009-02-01

This paper presents a study on non-invasive detection of two common epithelial cancers (skin and esophagus) based on oblique incidence diffuse reflectance spectroscopy (OIDRS). An OIDRS measurement system, which combines fiber optics and MEMS technologies, was developed. In our pilot studies, a total number of 137 cases have been measured in-vivo for skin cancer detection and a total number of 20 biopsy samples have been measured ex-vivo for esophageal cancer detection. To automatically differentiate the cancerous cases from benign ones, a statistical software classification program was also developed. An overall classification accuracy of 90% and 100% has been achieved for skin and esophageal cancer classification, respectively.

The functional cancer map: a systems-level synopsis of genetic deregulation in cancer.

PubMed

Krupp, Markus; Maass, Thorsten; Marquardt, Jens U; Staib, Frank; Bauer, Tobias; König, Rainer; Biesterfeld, Stefan; Galle, Peter R; Tresch, Achim; Teufel, Andreas

2011-06-30

Cancer cells are characterized by massive dysegulation of physiological cell functions with considerable disruption of transcriptional regulation. Genome-wide transcriptome profiling can be utilized for early detection and molecular classification of cancers. Accurate discrimination of functionally different tumor types may help to guide selection of targeted therapy in translational research. Concise grouping of tumor types in cancer maps according to their molecular profile may further be helpful for the development of new therapeutic modalities or open new avenues for already established therapies. Complete available human tumor data of the Stanford Microarray Database was downloaded and filtered for relevance, adequacy and reliability. A total of 649 tumor samples from more than 1400 experiments and 58 different tissues were analyzed. Next, a method to score deregulation of KEGG pathway maps in different tumor entities was established, which was then used to convert hundreds of gene expression profiles into corresponding tumor-specific pathway activity profiles. Based on the latter, we defined a measure for functional similarity between tumor entities, which yielded to phylogeny of tumors. We provide a comprehensive, easy-to-interpret functional cancer map that characterizes tumor types with respect to their biological and functional behavior. Consistently, multiple pathways commonly associated with tumor progression were revealed as common features in the majority of the tumors. However, several pathways previously not linked to carcinogenesis were identified in multiple cancers suggesting an essential role of these pathways in cancer biology. Among these pathways were 'ECM-receptor interaction', 'Complement and Coagulation cascades', and 'PPAR signaling pathway'. The functional cancer map provides a systematic view on molecular similarities across different cancers by comparing tumors on the level of pathway activity. This work resulted in identification of novel superimposed functional pathways potentially linked to cancer biology. Therefore, our work may serve as a starting point for rationalizing combination of tumor therapeutics as well as for expanding the application of well-established targeted tumor therapies.

A Unique Procedure to Identify Cell Surface Markers Through a Spherical Self-Organizing Map Applied to DNA Microarray Analysis.

PubMed

Sugii, Yuh; Kasai, Tomonari; Ikeda, Masashi; Vaidyanath, Arun; Kumon, Kazuki; Mizutani, Akifumi; Seno, Akimasa; Tokutaka, Heizo; Kudoh, Takayuki; Seno, Masaharu

2016-01-01

To identify cell-specific markers, we designed a DNA microarray platform with oligonucleotide probes for human membrane-anchored proteins. Human glioma cell lines were analyzed using microarray and compared with normal and fetal brain tissues. For the microarray analysis, we employed a spherical self-organizing map, which is a clustering method suitable for the conversion of multidimensional data into two-dimensional data and displays the relationship on a spherical surface. Based on the gene expression profile, the cell surface characteristics were successfully mirrored onto the spherical surface, thereby distinguishing normal brain tissue from the disease model based on the strength of gene expression. The clustered glioma-specific genes were further analyzed by polymerase chain reaction procedure and immunocytochemical staining of glioma cells. Our platform and the following procedure were successfully demonstrated to categorize the genes coding for cell surface proteins that are specific to glioma cells. Our assessment demonstrates that a spherical self-organizing map is a valuable tool for distinguishing cell surface markers and can be employed in marker discovery studies for the treatment of cancer.

Functional genomics annotation of a statistical epistasis network associated with bladder cancer susceptibility.

PubMed

Hu, Ting; Pan, Qinxin; Andrew, Angeline S; Langer, Jillian M; Cole, Michael D; Tomlinson, Craig R; Karagas, Margaret R; Moore, Jason H

2014-04-11

Several different genetic and environmental factors have been identified as independent risk factors for bladder cancer in population-based studies. Recent studies have turned to understanding the role of gene-gene and gene-environment interactions in determining risk. We previously developed the bioinformatics framework of statistical epistasis networks (SEN) to characterize the global structure of interacting genetic factors associated with a particular disease or clinical outcome. By applying SEN to a population-based study of bladder cancer among Caucasians in New Hampshire, we were able to identify a set of connected genetic factors with strong and significant interaction effects on bladder cancer susceptibility. To support our statistical findings using networks, in the present study, we performed pathway enrichment analyses on the set of genes identified using SEN, and found that they are associated with the carcinogen benzo[a]pyrene, a component of tobacco smoke. We further carried out an mRNA expression microarray experiment to validate statistical genetic interactions, and to determine if the set of genes identified in the SEN were differentially expressed in a normal bladder cell line and a bladder cancer cell line in the presence or absence of benzo[a]pyrene. Significant nonrandom sets of genes from the SEN were found to be differentially expressed in response to benzo[a]pyrene in both the normal bladder cells and the bladder cancer cells. In addition, the patterns of gene expression were significantly different between these two cell types. The enrichment analyses and the gene expression microarray results support the idea that SEN analysis of bladder in population-based studies is able to identify biologically meaningful statistical patterns. These results bring us a step closer to a systems genetic approach to understanding cancer susceptibility that integrates population and laboratory-based studies.

Interpretation of Genomic Data Questions and Answers

PubMed Central

Simon, Richard

2008-01-01

Using a question and answer format we describe important aspects of using genomic technologies in cancer research. The main challenges are not managing the mass of data, but rather the design, analysis and accurate reporting of studies that result in increased biological knowledge and medical utility. Many analysis issues address the use of expression microarrays but are also applicable to other whole genome assays. Microarray based clinical investigations have generated both unrealistic hyperbole and excessive skepticism. Genomic technologies are tremendously powerful and will play instrumental roles in elucidating the mechanisms of oncogenesis and in devlopingan era of predictive medicine in which treatments are tailored to individual tumors. Achieving these goals involves challenges in re-thinking many paradigms for the conduct of basic and clinical cancer research and for the organization of interdisciplinary collaboration. PMID:18582627

MO-DE-207B-03: Improved Cancer Classification Using Patient-Specific Biological Pathway Information Via Gene Expression Data

DOE Office of Scientific and Technical Information (OSTI.GOV)

Young, M; Craft, D

Purpose: To develop an efficient, pathway-based classification system using network biology statistics to assist in patient-specific response predictions to radiation and drug therapies across multiple cancer types. Methods: We developed PICS (Pathway Informed Classification System), a novel two-step cancer classification algorithm. In PICS, a matrix m of mRNA expression values for a patient cohort is collapsed into a matrix p of biological pathways. The entries of p, which we term pathway scores, are obtained from either principal component analysis (PCA), normal tissue centroid (NTC), or gene expression deviation (GED). The pathway score matrix is clustered using both k-means and hierarchicalmore » clustering, and a clustering is judged by how well it groups patients into distinct survival classes. The most effective pathway scoring/clustering combination, per clustering p-value, thus generates various ‘signatures’ for conventional and functional cancer classification. Results: PICS successfully regularized large dimension gene data, separated normal and cancerous tissues, and clustered a large patient cohort spanning six cancer types. Furthermore, PICS clustered patient cohorts into distinct, statistically-significant survival groups. For a suboptimally-debulked ovarian cancer set, the pathway-classified Kaplan-Meier survival curve (p = .00127) showed significant improvement over that of a prior gene expression-classified study (p = .0179). For a pancreatic cancer set, the pathway-classified Kaplan-Meier survival curve (p = .00141) showed significant improvement over that of a prior gene expression-classified study (p = .04). Pathway-based classification confirmed biomarkers for the pyrimidine, WNT-signaling, glycerophosphoglycerol, beta-alanine, and panthothenic acid pathways for ovarian cancer. Despite its robust nature, PICS requires significantly less run time than current pathway scoring methods. Conclusion: This work validates the PICS method to improve cancer classification using biological pathways. Patients are classified with greater specificity and physiological relevance as compared to current gene-specific approaches. Focus now moves to utilizing PICS for pan-cancer patient-specific treatment response prediction.« less

Evaluation of a low density DNA microarray for small B-cell non-Hodgkin lymphoma differential diagnosis.

PubMed

Gillet, Jean-Pierre; Molina, Thierry Jo; Jamart, Jacques; Gaulard, Philippe; Leroy, Karen; Briere, Josette; Theate, Ivan; Thieblemont, Catherine; Bosly, Andre; Herin, Michel; Hamels, Jacques; Remacle, Jose

2009-03-01

Lymphomas are classified according to the World Health Organisation (WHO) classification which defines subtypes on the basis of clinical, morphological, immunophenotypic, molecular and cytogenetic criteria. Differential diagnosis of the subtypes is sometimes difficult, especially for small B-cell lymphoma (SBCL). Standardisation of molecular genetic assays using multiple gene expression analysis by microarrays could be a useful complement to the current diagnosis. The aim of the present study was to develop a low density DNA microarray for the analysis of 107 genes associated with B-cell non-Hodgkin lymphoma and to evaluate its performance in the diagnosis of SBCL. A predictive tool based on Fisher discriminant analysis using a training set of 40 patients including four different subtypes (follicular lymphoma n = 15, mantle cell lymphoma n = 7, B-cell chronic lymphocytic leukemia n = 6 and splenic marginal zone lymphoma n = 12) was designed. A short additional preliminary analysis to gauge the accuracy of this signature was then performed on an external set of nine patients. Using this model, eight of nine of those samples were classified successfully. This pilot study demonstrates that such a microarray tool may be a promising diagnostic approach for small B-cell non-Hodgkin lymphoma.

Hidden Markov Model-Based CNV Detection Algorithms for Illumina Genotyping Microarrays.

PubMed

Seiser, Eric L; Innocenti, Federico

2014-01-01

Somatic alterations in DNA copy number have been well studied in numerous malignancies, yet the role of germline DNA copy number variation in cancer is still emerging. Genotyping microarrays generate allele-specific signal intensities to determine genotype, but may also be used to infer DNA copy number using additional computational approaches. Numerous tools have been developed to analyze Illumina genotype microarray data for copy number variant (CNV) discovery, although commonly utilized algorithms freely available to the public employ approaches based upon the use of hidden Markov models (HMMs). QuantiSNP, PennCNV, and GenoCN utilize HMMs with six copy number states but vary in how transition and emission probabilities are calculated. Performance of these CNV detection algorithms has been shown to be variable between both genotyping platforms and data sets, although HMM approaches generally outperform other current methods. Low sensitivity is prevalent with HMM-based algorithms, suggesting the need for continued improvement in CNV detection methodologies.

Gene Discovery in Bladder Cancer Progression using cDNA Microarrays

PubMed Central

Sanchez-Carbayo, Marta; Socci, Nicholas D.; Lozano, Juan Jose; Li, Wentian; Charytonowicz, Elizabeth; Belbin, Thomas J.; Prystowsky, Michael B.; Ortiz, Angel R.; Childs, Geoffrey; Cordon-Cardo, Carlos

2003-01-01

To identify gene expression changes along progression of bladder cancer, we compared the expression profiles of early-stage and advanced bladder tumors using cDNA microarrays containing 17,842 known genes and expressed sequence tags. The application of bootstrapping techniques to hierarchical clustering segregated early-stage and invasive transitional carcinomas into two main clusters. Multidimensional analysis confirmed these clusters and more importantly, it separated carcinoma in situ from papillary superficial lesions and subgroups within early-stage and invasive tumors displaying different overall survival. Additionally, it recognized early-stage tumors showing gene profiles similar to invasive disease. Different techniques including standard t-test, single-gene logistic regression, and support vector machine algorithms were applied to identify relevant genes involved in bladder cancer progression. Cytokeratin 20, neuropilin-2, p21, and p33ING1 were selected among the top ranked molecular targets differentially expressed and validated by immunohistochemistry using tissue microarrays (n = 173). Their expression patterns were significantly associated with pathological stage, tumor grade, and altered retinoblastoma (RB) expression. Moreover, p33ING1 expression levels were significantly associated with overall survival. Analysis of the annotation of the most significant genes revealed the relevance of critical genes and pathways during bladder cancer progression, including the overexpression of oncogenic genes such as DEK in superficial tumors or immune response genes such as Cd86 antigen in invasive disease. Gene profiling successfully classified bladder tumors based on their progression and clinical outcome. The present study has identified molecular biomarkers of potential clinical significance and critical molecular targets associated with bladder cancer progression. PMID:12875971

Biomarker selection and classification of "-omics" data using a two-step bayes classification framework.

PubMed

Assawamakin, Anunchai; Prueksaaroon, Supakit; Kulawonganunchai, Supasak; Shaw, Philip James; Varavithya, Vara; Ruangrajitpakorn, Taneth; Tongsima, Sissades

2013-01-01

Identification of suitable biomarkers for accurate prediction of phenotypic outcomes is a goal for personalized medicine. However, current machine learning approaches are either too complex or perform poorly. Here, a novel two-step machine-learning framework is presented to address this need. First, a Naïve Bayes estimator is used to rank features from which the top-ranked will most likely contain the most informative features for prediction of the underlying biological classes. The top-ranked features are then used in a Hidden Naïve Bayes classifier to construct a classification prediction model from these filtered attributes. In order to obtain the minimum set of the most informative biomarkers, the bottom-ranked features are successively removed from the Naïve Bayes-filtered feature list one at a time, and the classification accuracy of the Hidden Naïve Bayes classifier is checked for each pruned feature set. The performance of the proposed two-step Bayes classification framework was tested on different types of -omics datasets including gene expression microarray, single nucleotide polymorphism microarray (SNParray), and surface-enhanced laser desorption/ionization time-of-flight (SELDI-TOF) proteomic data. The proposed two-step Bayes classification framework was equal to and, in some cases, outperformed other classification methods in terms of prediction accuracy, minimum number of classification markers, and computational time.

Improved analytical methods for microarray-based genome-composition analysis

PubMed Central

Kim, Charles C; Joyce, Elizabeth A; Chan, Kaman; Falkow, Stanley

2002-01-01

Background Whereas genome sequencing has given us high-resolution pictures of many different species of bacteria, microarrays provide a means of obtaining information on genome composition for many strains of a given species. Genome-composition analysis using microarrays, or 'genomotyping', can be used to categorize genes into 'present' and 'divergent' categories based on the level of hybridization signal. This typically involves selecting a signal value that is used as a cutoff to discriminate present (high signal) and divergent (low signal) genes. Current methodology uses empirical determination of cutoffs for classification into these categories, but this methodology is subject to several problems that can result in the misclassification of many genes. Results We describe a method that depends on the shape of the signal-ratio distribution and does not require empirical determination of a cutoff. Moreover, the cutoff is determined on an array-to-array basis, accounting for variation in strain composition and hybridization quality. The algorithm also provides an estimate of the probability that any given gene is present, which provides a measure of confidence in the categorical assignments. Conclusions Many genes previously classified as present using static methods are in fact divergent on the basis of microarray signal; this is corrected by our algorithm. We have reassigned hundreds of genes from previous genomotyping studies of Helicobacter pylori and Campylobacter jejuni strains, and expect that the algorithm should be widely applicable to genomotyping data. PMID:12429064

Spectral biclustering of microarray data: coclustering genes and conditions.

PubMed

Kluger, Yuval; Basri, Ronen; Chang, Joseph T; Gerstein, Mark

2003-04-01

Global analyses of RNA expression levels are useful for classifying genes and overall phenotypes. Often these classification problems are linked, and one wants to find "marker genes" that are differentially expressed in particular sets of "conditions." We have developed a method that simultaneously clusters genes and conditions, finding distinctive "checkerboard" patterns in matrices of gene expression data, if they exist. In a cancer context, these checkerboards correspond to genes that are markedly up- or downregulated in patients with particular types of tumors. Our method, spectral biclustering, is based on the observation that checkerboard structures in matrices of expression data can be found in eigenvectors corresponding to characteristic expression patterns across genes or conditions. In addition, these eigenvectors can be readily identified by commonly used linear algebra approaches, in particular the singular value decomposition (SVD), coupled with closely integrated normalization steps. We present a number of variants of the approach, depending on whether the normalization over genes and conditions is done independently or in a coupled fashion. We then apply spectral biclustering to a selection of publicly available cancer expression data sets, and examine the degree to which the approach is able to identify checkerboard structures. Furthermore, we compare the performance of our biclustering methods against a number of reasonable benchmarks (e.g., direct application of SVD or normalized cuts to raw data).

Advances in metaheuristics for gene selection and classification of microarray data.

PubMed

Duval, Béatrice; Hao, Jin-Kao

2010-01-01

Gene selection aims at identifying a (small) subset of informative genes from the initial data in order to obtain high predictive accuracy for classification. Gene selection can be considered as a combinatorial search problem and thus be conveniently handled with optimization methods. In this article, we summarize some recent developments of using metaheuristic-based methods within an embedded approach for gene selection. In particular, we put forward the importance and usefulness of integrating problem-specific knowledge into the search operators of such a method. To illustrate the point, we explain how ranking coefficients of a linear classifier such as support vector machine (SVM) can be profitably used to reinforce the search efficiency of Local Search and Evolutionary Search metaheuristic algorithms for gene selection and classification.

Microarray-based identification of differentially expressed genes in extramammary Paget’s disease

PubMed Central

Lin, Jin-Ran; Liang, Jun; Zhang, Qiao-An; Huang, Qiong; Wang, Shang-Shang; Qin, Hai-Hong; Chen, Lian-Jun; Xu, Jin-Hua

2015-01-01

Extramammary Paget’s disease (EMPD) is a rare cutaneous malignancy accounting for approximately 1-2% of vulvar cancers. The rarity of this disease has caused difficulties in characterization and the molecular mechanism underlying EMPD development remains largely unclear. Here we used microarray analysis to identify differentially expressed genes in EMPD of the scrotum comparing with normal epithelium from healthy donors. Agilent single-channel microarray was used to compare the gene expression between 6 EMPD specimens and 6 normal scrotum epithelium samples. A total of 799 up-regulated genes and 723 down-regulated genes were identified in EMPD tissues. Real-time PCR was conducted to verify the differential expression of some representative genes, including ERBB4, TCF3, PAPSS2, PIK3R3, PRLR, SULT1A1, TCF7L1, and CREB3L4. Generally, the real-time PCR results were consistent with microarray data, and the expression of ERBB4, PRLR, TCF3, PIK3R3, SULT1A1, and TCF7L1 was significantly overexpressed in EMPD (P<0.05). Moreover, the overexpression of PRLR in EMPD, a receptor for the anterior pituitary hormone prolactin (PRL), was confirmed by immunohistochemistry. These data demonstrate that the differentially expressed genes from the microarray-based identification are tightly associated with EMPD occurrence. PMID:26221264

Single Cell Characterization of Prostate Cancer-Circulating Tumor Cells

DTIC Science & Technology

2013-09-01

prostate cancer using RT- PCR [8] and EGFR mutations in non-small cell lung cancer [45]. Microarray-based assessments of gene expression have been carried...analysis. DAPI negative putative CTCs were isolated in 1 ul of 10% Superblock/PBS with a pipetteman into a 0.2 ml PCR tube containing 2.5 ul of 5...Sequencing kit (Clontech). cDNA was amplified using the Advantage 2 PCR kit (Clontech) for 18–25 cycles prior to conversion into a Illumina compatible DNA

Glycoprofiling of Early Gastric Cancer Using Lectin Microarray Technology.

PubMed

Li, Taijie; Mo, Cuiju; Qin, Xue; Li, Shan; Liu, Yinkun; Liu, Zhiming

2018-01-01

Recently, studies have reported that protein glycosylation plays an important role in the occurrence and development of cancer. Gastric cancer is a common cancer with high morbidity and mortality owing to most gastric cancers are discovered only at an advanced stage. Here, we aim to discover novel specific serum glycanbased biomarkers for gastric cancer. A lectin microarray with 50 kinds of tumor-associated lectin was used to detect the glycan profiles of serum samples between early gastric cancer and healthy controls. Then lectin blot was performed to validate the differences. The result of the lectin microarray showed that the signal intensities of 13 lectins showed significant differences between the healthy controls and early gastric cancer. Compared to the healthy, the normalized fluorescent intensities of the lectins PWA, LEL, and STL were significantly increased, and it implied that their specifically recognized GlcNAc showed an especially elevated expression in early gastric cancer. Moreover, the binding affinity of the lectins EEL, RCA-II, RCA-I, VAL, DSA, PHA-L, UEA, and CAL were higher in the early gastric cancer than in healthy controls. These glycan structures containing GalNAc, terminal Galβ 1-4 GlcNAc, Tri/tetraantennary N-glycan, β-1, 6GlcNAc branching structure, α-linked fucose residues, and Tn antigen were elevated in gastric cancer. While the two lectins CFL GNL reduced their binding ability. In addition, their specifically recognized N-acetyl-D-galactosamine structure and (α-1,3) mannose residues were decreased in early gastric cancer. Furthermore, lectin blot results of LEL, STL, PHA-L, RCA-I were consistent with the results of the lectin microarray. The findings of our study clarify the specific alterations for glycosylation during the pathogenesis of gastric cancer. The specific high expression of GlcNAc structure may act as a potential early diagnostic marker for gastric cancer.

Influence of nuclei segmentation on breast cancer malignancy classification

NASA Astrophysics Data System (ADS)

Jelen, Lukasz; Fevens, Thomas; Krzyzak, Adam

2009-02-01

Breast Cancer is one of the most deadly cancers affecting middle-aged women. Accurate diagnosis and prognosis are crucial to reduce the high death rate. Nowadays there are numerous diagnostic tools for breast cancer diagnosis. In this paper we discuss a role of nuclear segmentation from fine needle aspiration biopsy (FNA) slides and its influence on malignancy classification. Classification of malignancy plays a very important role during the diagnosis process of breast cancer. Out of all cancer diagnostic tools, FNA slides provide the most valuable information about the cancer malignancy grade which helps to choose an appropriate treatment. This process involves assessing numerous nuclear features and therefore precise segmentation of nuclei is very important. In this work we compare three powerful segmentation approaches and test their impact on the classification of breast cancer malignancy. The studied approaches involve level set segmentation, fuzzy c-means segmentation and textural segmentation based on co-occurrence matrix. Segmented nuclei were used to extract nuclear features for malignancy classification. For classification purposes four different classifiers were trained and tested with previously extracted features. The compared classifiers are Multilayer Perceptron (MLP), Self-Organizing Maps (SOM), Principal Component-based Neural Network (PCA) and Support Vector Machines (SVM). The presented results show that level set segmentation yields the best results over the three compared approaches and leads to a good feature extraction with a lowest average error rate of 6.51% over four different classifiers. The best performance was recorded for multilayer perceptron with an error rate of 3.07% using fuzzy c-means segmentation.

An efficient method to identify differentially expressed genes in microarray experiments

PubMed Central

Qin, Huaizhen; Feng, Tao; Harding, Scott A.; Tsai, Chung-Jui; Zhang, Shuanglin

2013-01-01

Motivation Microarray experiments typically analyze thousands to tens of thousands of genes from small numbers of biological replicates. The fact that genes are normally expressed in functionally relevant patterns suggests that gene-expression data can be stratified and clustered into relatively homogenous groups. Cluster-wise dimensionality reduction should make it feasible to improve screening power while minimizing information loss. Results We propose a powerful and computationally simple method for finding differentially expressed genes in small microarray experiments. The method incorporates a novel stratification-based tight clustering algorithm, principal component analysis and information pooling. Comprehensive simulations show that our method is substantially more powerful than the popular SAM and eBayes approaches. We applied the method to three real microarray datasets: one from a Populus nitrogen stress experiment with 3 biological replicates; and two from public microarray datasets of human cancers with 10 to 40 biological replicates. In all three analyses, our method proved more robust than the popular alternatives for identification of differentially expressed genes. Availability The C++ code to implement the proposed method is available upon request for academic use. PMID:18453554

Gene expression profiling and pathway analysis in MCF-7 and MDA-MB-231 human breast cancer cell lines treated with dioscin

USDA-ARS?s Scientific Manuscript database

The long-term goal of our study is to understand the genetic and epigenetic mechanisms of breast cancer metastasis in human and to discover new possible genetic markers for use in clinical practice. We have used microarray technology (Human OneArray microarray, phylanxbiotech.com) to compare gene ex...

Immunological Targeting of Tumor Initiating Prostate Cancer Cells

DTIC Science & Technology

2014-10-01

clinically using well-accepted immuno-competent animal models. 2) Keywords: Prostate Cancer, Lymphocyte, Vaccine, Antibody 3) Overall Project Summary...castrate animals . Task 1: Identify and verify antigenic targets from CAstrate Resistant Luminal Epithelial Cells (CRLEC) (months 1-16... animals per group will be processed to derive sufficient RNA for microarray analysis; the experiment will be repeated x 3. Microarray analysis will

EDRN Biomarker Reference Lab: Pacific Northwest National Laboratory — EDRN Public Portal

Cancer.gov

The purpose of this project is to develop antibody microarrays incorporating three major improvements compared to previous antibody microarray platforms, and to produce and disseminate these antibody microarray technologies for the Early Detection Research Network (EDRN) and the research community focusing on early detection, and risk assessment of cancer.

Molecular Classification and Correlates in Colorectal Cancer

PubMed Central

Ogino, Shuji; Goel, Ajay

2008-01-01

Molecular classification of colorectal cancer is evolving. As our understanding of colorectal carcinogenesis improves, we are incorporating new knowledge into the classification system. In particular, global genomic status [microsatellite instability (MSI) status and chromosomal instability (CIN) status] and epigenomic status [CpG island methylator phenotype (CIMP) status] play a significant role in determining clinical, pathological and biological characteristics of colorectal cancer. In this review, we discuss molecular classification and molecular correlates based on MSI status and CIMP status in colorectal cancer. Studying molecular correlates is important in cancer research because it can 1) provide clues to pathogenesis, 2) propose or support the existence of a new molecular subtype, 3) alert investigators to be aware of potential confounding factors in association studies, and 4) suggest surrogate markers in clinical or research settings. PMID:18165277

Heterogeneous activation of the TGFβ pathway in glioblastomas identified by gene expression-based classification using TGFβ-responsive genes

PubMed Central

Xu, Xie L; Kapoun, Ann M

2009-01-01

Background TGFβ has emerged as an attractive target for the therapeutic intervention of glioblastomas. Aberrant TGFβ overproduction in glioblastoma and other high-grade gliomas has been reported, however, to date, none of these reports has systematically examined the components of TGFβ signaling to gain a comprehensive view of TGFβ activation in large cohorts of human glioma patients. Methods TGFβ activation in mammalian cells leads to a transcriptional program that typically affects 5–10% of the genes in the genome. To systematically examine the status of TGFβ activation in high-grade glial tumors, we compiled a gene set of transcriptional response to TGFβ stimulation from tissue culture and in vivo animal studies. These genes were used to examine the status of TGFβ activation in high-grade gliomas including a large cohort of glioblastomas. Unsupervised and supervised classification analysis was performed in two independent, publicly available glioma microarray datasets. Results Unsupervised and supervised classification using the TGFβ-responsive gene list in two independent glial tumor gene expression data sets revealed various levels of TGFβ activation in these tumors. Among glioblastomas, one of the most devastating human cancers, two subgroups were identified that showed distinct TGFβ activation patterns as measured from transcriptional responses. Approximately 62% of glioblastoma samples analyzed showed strong TGFβ activation, while the rest showed a weak TGFβ transcriptional response. Conclusion Our findings suggest heterogeneous TGFβ activation in glioblastomas, which may cause potential differences in responses to anti-TGFβ therapies in these two distinct subgroups of glioblastomas patients. PMID:19192267

Impact of miR-155 and miR-126 as novel biomarkers on the assessment of disease progression and prognosis in adult T-cell leukemia.

PubMed

Ishihara, Kaori; Sasaki, Daisuke; Tsuruda, Kazuto; Inokuchi, Naoko; Nagai, Kazuhiro; Hasegawa, Hiroo; Yanagihara, Katsunori; Kamihira, Shimeru

2012-12-01

Micro RNAs (miRNAs) provide new insight in the development of cancer, but little is known about their clinical relevance as biomarkers in the assessment of diagnosis, classification, progression and prognosis of various cancers. To explore a potential novel biomarker, we examined the cellular and plasma miRNA profiles in adult T-cell leukemia (ATL) characterized by diverse clinical features. Using CD4-positive cells isolated from 2 non-infected healthy individuals, 3 chronic ATL patients and 3 acute ATL patients, cellular miRNAs were profiled by microarray. The microarray screened 5 miRNAs namely miR-155, let-7g, miR-126, miR-130a and let-7b because of the large difference in their expression in diseased vs. that of healthy controls. The expression levels of before 5 miRNAs re-quantified by reverse transcription quantifiable polymerase chain reaction (RT-qPCR) were not always accordant in cells and plasma. The high and low plasma levels of miR-155 and miR-126 changed with ATL stage. The present study revealed that there is a quantitative discrepancy between cellular and plasma miRNAs. The elevation of plasma miR-155 and the reduction in miR-126 correlated with poor prognosis, indicating their usefulness as a novel biomarker for the assessment of disease stage. Copyright © 2012 Elsevier Ltd. All rights reserved.

Reliable Entity Subtyping in Non-small Cell Lung Cancer by Matrix-assisted Laser Desorption/Ionization Imaging Mass Spectrometry on Formalin-fixed Paraffin-embedded Tissue Specimens*

PubMed Central

Kriegsmann, Mark; Casadonte, Rita; Kriegsmann, Jörg; Dienemann, Hendrik; Schirmacher, Peter; Hendrik Kobarg, Jan; Schwamborn, Kristina; Stenzinger, Albrecht; Warth, Arne; Weichert, Wilko

2016-01-01

Histopathological subtyping of non-small cell lung cancer (NSCLC) into adenocarcinoma (ADC), and squamous cell carcinoma (SqCC) is of utmost relevance for treatment stratification. However, current immunohistochemistry (IHC) based typing approaches on biopsies are imperfect, therefore novel analytical methods for reliable subtyping are needed. We analyzed formalin-fixed paraffin-embedded tissue cores of NSCLC by Matrix-assisted laser desorption/ionization (MALDI) imaging on tissue microarrays to identify and validate discriminating MALDI imaging profiles for NSCLC subtyping. 110 ADC and 98 SqCC were used to train a Linear Discriminant Analysis (LDA) model. Results were validated on a separate set of 58 ADC and 60 SqCC. Selected differentially expressed proteins were identified by tandem mass spectrometry and validated by IHC. The LDA classification model incorporated 339 m/z values. In the validation cohort, in 117 cases (99.1%) MALDI classification on tissue cores was in accordance with the pathological diagnosis made on resection specimen. Overall, three cases in the combined cohorts were discordant, after reevaluation two were initially misclassified by pathology whereas one was classified incorrectly by MALDI. Identification of differentially expressed peptides detected well-known IHC discriminators (CK5, CK7), but also less well known differentially expressed proteins (CK15, HSP27). In conclusion, MALDI imaging on NSCLC tissue cores as small biopsy equivalents is capable to discriminate lung ADC and SqCC with a very high accuracy. In addition, replacing multislide IHC by an one-slide MALDI approach may also save tissue for subsequent predictive molecular testing. We therefore advocate to pursue routine diagnostic implementation strategies for MALDI imaging in solid tumor typing. PMID:27473201

Reliable Entity Subtyping in Non-small Cell Lung Cancer by Matrix-assisted Laser Desorption/Ionization Imaging Mass Spectrometry on Formalin-fixed Paraffin-embedded Tissue Specimens.

PubMed

Kriegsmann, Mark; Casadonte, Rita; Kriegsmann, Jörg; Dienemann, Hendrik; Schirmacher, Peter; Hendrik Kobarg, Jan; Schwamborn, Kristina; Stenzinger, Albrecht; Warth, Arne; Weichert, Wilko

2016-10-01

Histopathological subtyping of non-small cell lung cancer (NSCLC) into adenocarcinoma (ADC), and squamous cell carcinoma (SqCC) is of utmost relevance for treatment stratification. However, current immunohistochemistry (IHC) based typing approaches on biopsies are imperfect, therefore novel analytical methods for reliable subtyping are needed. We analyzed formalin-fixed paraffin-embedded tissue cores of NSCLC by Matrix-assisted laser desorption/ionization (MALDI) imaging on tissue microarrays to identify and validate discriminating MALDI imaging profiles for NSCLC subtyping. 110 ADC and 98 SqCC were used to train a Linear Discriminant Analysis (LDA) model. Results were validated on a separate set of 58 ADC and 60 SqCC. Selected differentially expressed proteins were identified by tandem mass spectrometry and validated by IHC. The LDA classification model incorporated 339 m/z values. In the validation cohort, in 117 cases (99.1%) MALDI classification on tissue cores was in accordance with the pathological diagnosis made on resection specimen. Overall, three cases in the combined cohorts were discordant, after reevaluation two were initially misclassified by pathology whereas one was classified incorrectly by MALDI. Identification of differentially expressed peptides detected well-known IHC discriminators (CK5, CK7), but also less well known differentially expressed proteins (CK15, HSP27). In conclusion, MALDI imaging on NSCLC tissue cores as small biopsy equivalents is capable to discriminate lung ADC and SqCC with a very high accuracy. In addition, replacing multislide IHC by an one-slide MALDI approach may also save tissue for subsequent predictive molecular testing. We therefore advocate to pursue routine diagnostic implementation strategies for MALDI imaging in solid tumor typing. © 2016 by The American Society for Biochemistry and Molecular Biology, Inc.

Investigating the epigenetic effects of a prototype smoke-derived carcinogen in human cells.

PubMed

Tommasi, Stella; Kim, Sang-in; Zhong, Xueyan; Wu, Xiwei; Pfeifer, Gerd P; Besaratinia, Ahmad

2010-05-12

Global loss of DNA methylation and locus/gene-specific gain of DNA methylation are two distinct hallmarks of carcinogenesis. Aberrant DNA methylation is implicated in smoking-related lung cancer. In this study, we have comprehensively investigated the modulation of DNA methylation consequent to chronic exposure to a prototype smoke-derived carcinogen, benzo[a]pyrene diol epoxide (B[a]PDE), in genomic regions of significance in lung cancer, in normal human cells. We have used a pulldown assay for enrichment of the CpG methylated fraction of cellular DNA combined with microarray platforms, followed by extensive validation through conventional bisulfite-based analysis. Here, we demonstrate strikingly similar patterns of DNA methylation in non-transformed B[a]PDE-treated cells vs control using high-throughput microarray-based DNA methylation profiling confirmed by conventional bisulfite-based DNA methylation analysis. The absence of aberrant DNA methylation in our model system within a timeframe that precedes cellular transformation suggests that following carcinogen exposure, other as yet unknown factors (secondary to carcinogen treatment) may help initiate global loss of DNA methylation and region-specific gain of DNA methylation, which can, in turn, contribute to lung cancer development. Unveiling the initiating events that cause aberrant DNA methylation in lung cancer has tremendous public health relevance, as it can help define future strategies for early detection and prevention of this highly lethal disease.

Investigating the Epigenetic Effects of a Prototype Smoke-Derived Carcinogen in Human Cells

PubMed Central

Tommasi, Stella; Kim, Sang-in; Zhong, Xueyan; Wu, Xiwei; Pfeifer, Gerd P.; Besaratinia, Ahmad

2010-01-01

Global loss of DNA methylation and locus/gene-specific gain of DNA methylation are two distinct hallmarks of carcinogenesis. Aberrant DNA methylation is implicated in smoking-related lung cancer. In this study, we have comprehensively investigated the modulation of DNA methylation consequent to chronic exposure to a prototype smoke-derived carcinogen, benzo[a]pyrene diol epoxide (B[a]PDE), in genomic regions of significance in lung cancer, in normal human cells. We have used a pulldown assay for enrichment of the CpG methylated fraction of cellular DNA combined with microarray platforms, followed by extensive validation through conventional bisulfite-based analysis. Here, we demonstrate strikingly similar patterns of DNA methylation in non-transformed B[a]PDE-treated cells vs control using high-throughput microarray-based DNA methylation profiling confirmed by conventional bisulfite-based DNA methylation analysis. The absence of aberrant DNA methylation in our model system within a timeframe that precedes cellular transformation suggests that following carcinogen exposure, other as yet unknown factors (secondary to carcinogen treatment) may help initiate global loss of DNA methylation and region-specific gain of DNA methylation, which can, in turn, contribute to lung cancer development. Unveiling the initiating events that cause aberrant DNA methylation in lung cancer has tremendous public health relevance, as it can help define future strategies for early detection and prevention of this highly lethal disease. PMID:20485678

Network regularised Cox regression and multiplex network models to predict disease comorbidities and survival of cancer.

PubMed

Xu, Haoming; Moni, Mohammad Ali; Liò, Pietro

2015-12-01

In cancer genomics, gene expression levels provide important molecular signatures for all types of cancer, and this could be very useful for predicting the survival of cancer patients. However, the main challenge of gene expression data analysis is high dimensionality, and microarray is characterised by few number of samples with large number of genes. To overcome this problem, a variety of penalised Cox proportional hazard models have been proposed. We introduce a novel network regularised Cox proportional hazard model and a novel multiplex network model to measure the disease comorbidities and to predict survival of the cancer patient. Our methods are applied to analyse seven microarray cancer gene expression datasets: breast cancer, ovarian cancer, lung cancer, liver cancer, renal cancer and osteosarcoma. Firstly, we applied a principal component analysis to reduce the dimensionality of original gene expression data. Secondly, we applied a network regularised Cox regression model on the reduced gene expression datasets. By using normalised mutual information method and multiplex network model, we predict the comorbidities for the liver cancer based on the integration of diverse set of omics and clinical data, and we find the diseasome associations (disease-gene association) among different cancers based on the identified common significant genes. Finally, we evaluated the precision of the approach with respect to the accuracy of survival prediction using ROC curves. We report that colon cancer, liver cancer and renal cancer share the CXCL5 gene, and breast cancer, ovarian cancer and renal cancer share the CCND2 gene. Our methods are useful to predict survival of the patient and disease comorbidities more accurately and helpful for improvement of the care of patients with comorbidity. Software in Matlab and R is available on our GitHub page: https://github.com/ssnhcom/NetworkRegularisedCox.git. Copyright © 2015. Published by Elsevier Ltd.

Establishing glucose- and ABA-regulated transcription networks in Arabidopsis by microarray analysis and promoter classification using a Relevance Vector Machine.

PubMed

Li, Yunhai; Lee, Kee Khoon; Walsh, Sean; Smith, Caroline; Hadingham, Sophie; Sorefan, Karim; Cawley, Gavin; Bevan, Michael W

2006-03-01

Establishing transcriptional regulatory networks by analysis of gene expression data and promoter sequences shows great promise. We developed a novel promoter classification method using a Relevance Vector Machine (RVM) and Bayesian statistical principles to identify discriminatory features in the promoter sequences of genes that can correctly classify transcriptional responses. The method was applied to microarray data obtained from Arabidopsis seedlings treated with glucose or abscisic acid (ABA). Of those genes showing >2.5-fold changes in expression level, approximately 70% were correctly predicted as being up- or down-regulated (under 10-fold cross-validation), based on the presence or absence of a small set of discriminative promoter motifs. Many of these motifs have known regulatory functions in sugar- and ABA-mediated gene expression. One promoter motif that was not known to be involved in glucose-responsive gene expression was identified as the strongest classifier of glucose-up-regulated gene expression. We show it confers glucose-responsive gene expression in conjunction with another promoter motif, thus validating the classification method. We were able to establish a detailed model of glucose and ABA transcriptional regulatory networks and their interactions, which will help us to understand the mechanisms linking metabolism with growth in Arabidopsis. This study shows that machine learning strategies coupled to Bayesian statistical methods hold significant promise for identifying functionally significant promoter sequences.

Classification of microscopic images of breast tissue

NASA Astrophysics Data System (ADS)

Ballerini, Lucia; Franzen, Lennart

2004-05-01

Breast cancer is the most common form of cancer among women. The diagnosis is usually performed by the pathologist, that subjectively evaluates tissue samples. The aim of our research is to develop techniques for the automatic classification of cancerous tissue, by analyzing histological samples of intact tissue taken with a biopsy. In our study, we considered 200 images presenting four different conditions: normal tissue, fibroadenosis, ductal cancer and lobular cancer. Methods to extract features have been investigated and described. One method is based on granulometries, which are size-shape descriptors widely used in mathematical morphology. Applications of granulometries lead to distribution functions whose moments are used as features. A second method is based on fractal geometry, that seems very suitable to quantify biological structures. The fractal dimension of binary images has been computed using the euclidean distance mapping. Image classification has then been performed using the extracted features as input of a back-propagation neural network. A new method that combines genetic algorithms and morphological filters has been also investigated. In this case, the classification is based on a correlation measure. Very encouraging results have been obtained with pilot experiments using a small subset of images as training set. Experimental results indicate the effectiveness of the proposed methods. Cancerous tissue was correctly classified in 92.5% of the cases.

Crowdsourcing for translational research: analysis of biomarker expression using cancer microarrays

PubMed Central

Lawson, Jonathan; Robinson-Vyas, Rupesh J; McQuillan, Janette P; Paterson, Andy; Christie, Sarah; Kidza-Griffiths, Matthew; McDuffus, Leigh-Anne; Moutasim, Karwan A; Shaw, Emily C; Kiltie, Anne E; Howat, William J; Hanby, Andrew M; Thomas, Gareth J; Smittenaar, Peter

2017-01-01

Background: Academic pathology suffers from an acute and growing lack of workforce resource. This especially impacts on translational elements of clinical trials, which can require detailed analysis of thousands of tissue samples. We tested whether crowdsourcing – enlisting help from the public – is a sufficiently accurate method to score such samples. Methods: We developed a novel online interface to train and test lay participants on cancer detection and immunohistochemistry scoring in tissue microarrays. Lay participants initially performed cancer detection on lung cancer images stained for CD8, and we measured how extending a basic tutorial by annotated example images and feedback-based training affected cancer detection accuracy. We then applied this tutorial to additional cancer types and immunohistochemistry markers – bladder/ki67, lung/EGFR, and oesophageal/CD8 – to establish accuracy compared with experts. Using this optimised tutorial, we then tested lay participants' accuracy on immunohistochemistry scoring of lung/EGFR and bladder/p53 samples. Results: We observed that for cancer detection, annotated example images and feedback-based training both improved accuracy compared with a basic tutorial only. Using this optimised tutorial, we demonstrate highly accurate (>0.90 area under curve) detection of cancer in samples stained with nuclear, cytoplasmic and membrane cell markers. We also observed high Spearman correlations between lay participants and experts for immunohistochemistry scoring (0.91 (0.78, 0.96) and 0.97 (0.91, 0.99) for lung/EGFR and bladder/p53 samples, respectively). Conclusions: These results establish crowdsourcing as a promising method to screen large data sets for biomarkers in cancer pathology research across a range of cancers and immunohistochemical stains. PMID:27959886

A data-analytic strategy for protein biomarker discovery: profiling of high-dimensional proteomic data for cancer detection.

PubMed

Yasui, Yutaka; Pepe, Margaret; Thompson, Mary Lou; Adam, Bao-Ling; Wright, George L; Qu, Yinsheng; Potter, John D; Winget, Marcy; Thornquist, Mark; Feng, Ziding

2003-07-01

With recent advances in mass spectrometry techniques, it is now possible to investigate proteins over a wide range of molecular weights in small biological specimens. This advance has generated data-analytic challenges in proteomics, similar to those created by microarray technologies in genetics, namely, discovery of 'signature' protein profiles specific to each pathologic state (e.g. normal vs. cancer) or differential profiles between experimental conditions (e.g. treated by a drug of interest vs. untreated) from high-dimensional data. We propose a data-analytic strategy for discovering protein biomarkers based on such high-dimensional mass spectrometry data. A real biomarker-discovery project on prostate cancer is taken as a concrete example throughout the paper: the project aims to identify proteins in serum that distinguish cancer, benign hyperplasia, and normal states of prostate using the Surface Enhanced Laser Desorption/Ionization (SELDI) technology, a recently developed mass spectrometry technique. Our data-analytic strategy takes properties of the SELDI mass spectrometer into account: the SELDI output of a specimen contains about 48,000 (x, y) points where x is the protein mass divided by the number of charges introduced by ionization and y is the protein intensity of the corresponding mass per charge value, x, in that specimen. Given high coefficients of variation and other characteristics of protein intensity measures (y values), we reduce the measures of protein intensities to a set of binary variables that indicate peaks in the y-axis direction in the nearest neighborhoods of each mass per charge point in the x-axis direction. We then account for a shifting (measurement error) problem of the x-axis in SELDI output. After this pre-analysis processing of data, we combine the binary predictors to generate classification rules for cancer, benign hyperplasia, and normal states of prostate. Our approach is to apply the boosting algorithm to select binary predictors and construct a summary classifier. We empirically evaluate sensitivity and specificity of the resulting summary classifiers with a test dataset that is independent from the training dataset used to construct the summary classifiers. The proposed method performed nearly perfectly in distinguishing cancer and benign hyperplasia from normal. In the classification of cancer vs. benign hyperplasia, however, an appreciable proportion of the benign specimens were classified incorrectly as cancer. We discuss practical issues associated with our proposed approach to the analysis of SELDI output and its application in cancer biomarker discovery.

Network-based de-noising improves prediction from microarray data.

PubMed

Kato, Tsuyoshi; Murata, Yukio; Miura, Koh; Asai, Kiyoshi; Horton, Paul B; Koji, Tsuda; Fujibuchi, Wataru

2006-03-20

Prediction of human cell response to anti-cancer drugs (compounds) from microarray data is a challenging problem, due to the noise properties of microarrays as well as the high variance of living cell responses to drugs. Hence there is a strong need for more practical and robust methods than standard methods for real-value prediction. We devised an extended version of the off-subspace noise-reduction (de-noising) method to incorporate heterogeneous network data such as sequence similarity or protein-protein interactions into a single framework. Using that method, we first de-noise the gene expression data for training and test data and also the drug-response data for training data. Then we predict the unknown responses of each drug from the de-noised input data. For ascertaining whether de-noising improves prediction or not, we carry out 12-fold cross-validation for assessment of the prediction performance. We use the Pearson's correlation coefficient between the true and predicted response values as the prediction performance. De-noising improves the prediction performance for 65% of drugs. Furthermore, we found that this noise reduction method is robust and effective even when a large amount of artificial noise is added to the input data. We found that our extended off-subspace noise-reduction method combining heterogeneous biological data is successful and quite useful to improve prediction of human cell cancer drug responses from microarray data.

Prediction of clinical behaviour and treatment for cancers.

PubMed

Futschik, Matthias E; Sullivan, Mike; Reeve, Anthony; Kasabov, Nikola

2003-01-01

Prediction of clinical behaviour and treatment for cancers is based on the integration of clinical and pathological parameters. Recent reports have demonstrated that gene expression profiling provides a powerful new approach for determining disease outcome. If clinical and microarray data each contain independent information then it should be possible to combine these datasets to gain more accurate prognostic information. Here, we have used existing clinical information and microarray data to generate a combined prognostic model for outcome prediction for diffuse large B-cell lymphoma (DLBCL). A prediction accuracy of 87.5% was achieved. This constitutes a significant improvement compared to the previously most accurate prognostic model with an accuracy of 77.6%. The model introduced here may be generally applicable to the combination of various types of molecular and clinical data for improving medical decision support systems and individualising patient care.

Ensemble stump classifiers and gene expression signatures in lung cancer.

PubMed

Frey, Lewis; Edgerton, Mary; Fisher, Douglas; Levy, Shawn

2007-01-01

Microarray data sets for cancer tumor tissue generally have very few samples, each sample having thousands of probes (i.e., continuous variables). The sparsity of samples makes it difficult for machine learning techniques to discover probes relevant to the classification of tumor tissue. By combining data from different platforms (i.e., data sources), data sparsity is reduced, but this typically requires normalizing data from the different platforms, which can be non-trivial. This paper proposes a variant on the idea of ensemble learners to circumvent the need for normalization. To facilitate comprehension we build ensembles of very simple classifiers known as decision stumps--decision trees of one test each. The Ensemble Stump Classifier (ESC) identifies an mRNA signature having three probes and high accuracy for distinguishing between adenocarcinoma and squamous cell carcinoma of the lung across four data sets. In terms of accuracy, ESC outperforms a decision tree classifier on all four data sets, outperforms ensemble decision trees on three data sets, and simple stump classifiers on two data sets.

A Minimum Spanning Forest Based Method for Noninvasive Cancer Detection with Hyperspectral Imaging

PubMed Central

Pike, Robert; Lu, Guolan; Wang, Dongsheng; Chen, Zhuo Georgia; Fei, Baowei

2016-01-01

Goal The purpose of this paper is to develop a classification method that combines both spectral and spatial information for distinguishing cancer from healthy tissue on hyperspectral images in an animal model. Methods An automated algorithm based on a minimum spanning forest (MSF) and optimal band selection has been proposed to classify healthy and cancerous tissue on hyperspectral images. A support vector machine (SVM) classifier is trained to create a pixel-wise classification probability map of cancerous and healthy tissue. This map is then used to identify markers that are used to compute mutual information for a range of bands in the hyperspectral image and thus select the optimal bands. An MSF is finally grown to segment the image using spatial and spectral information. Conclusion The MSF based method with automatically selected bands proved to be accurate in determining the tumor boundary on hyperspectral images. Significance Hyperspectral imaging combined with the proposed classification technique has the potential to provide a noninvasive tool for cancer detection. PMID:26285052

A 15-gene signature for prediction of colon cancer recurrence and prognosis based on SVM.

PubMed

Xu, Guangru; Zhang, Minghui; Zhu, Hongxing; Xu, Jinhua

2017-03-10

To screen the gene signature for distinguishing patients with high risks from those with low-risks for colon cancer recurrence and predicting their prognosis. Five microarray datasets of colon cancer samples were collected from Gene Expression Omnibus database and one was obtained from The Cancer Genome Atlas (TCGA). After preprocessing, data in GSE17537 were analyzed using the Linear Models for Microarray data (LIMMA) method to identify the differentially expressed genes (DEGs). The DEGs further underwent PPI network-based neighborhood scoring and support vector machine (SVM) analyses to screen the feature genes associated with recurrence and prognosis, which were then validated by four datasets GSE38832, GSE17538, GSE28814 and TCGA using SVM and Cox regression analyses. A total of 1207 genes were identified as DEGs between recurrence and no-recurrence samples, including 726 downregulated and 481 upregulated genes. Using SVM analysis and five gene expression profile data confirmation, a 15-gene signature (HES5, ZNF417, GLRA2, OR8D2, HOXA7, FABP6, MUSK, HTR6, GRIP2, KLRK1, VEGFA, AKAP12, RHEB, NCRNA00152 and PMEPA1) were identified as a predictor of recurrence risk and prognosis for colon cancer patients. Our identified 15-gene signature may be useful to classify colon cancer patients with different prognosis and some genes in this signature may represent new therapeutic targets. Copyright © 2016. Published by Elsevier B.V.

Evidence That Selenium Binding Protein 1 Is a Tumor Suppressor in Prostate Cancer

PubMed Central

Ansong, Emmanuel; Ying, Qi; Ekoue, Dede N.; Deaton, Ryan; Hall, Andrew R.; Kajdacsy-Balla, Andre; Yang, Wancai; Gann, Peter H.; Diamond, Alan M.

2015-01-01

Selenium-Binding Protein 1 (SBP1, SELENBP1, hSP56) is a selenium-associated protein shown to be at lower levels in tumors, and its lower levels are frequently predictive of a poor clinical outcome. Distinguishing indolent from aggressive prostate cancer is a major challenge in disease management. Associations between SBP1 levels, tumor grade, and disease recurrence following prostatectomy were investigated by duplex immunofluorescence imaging using a tissue microarray containing tissue from 202 prostate cancer patients who experienced biochemical (PSA) recurrence after prostatectomy and 202 matched control patients whose cancer did not recur. Samples were matched by age, ethnicity, pathological stage and Gleason grade, and images were quantified using the Vectra multispectral imaging system. Fluorescent labels were targeted for SBP1 and cytokeratins 8/18 to restrict scoring to tumor cells, and cell-by-cell quantification of SBP1 in the nucleus and cytoplasm was performed. Nuclear SBP1 levels and the nuclear to cytoplasm ratio were inversely associated with tumor grade using linear regression analysis. Following classification of samples into quartiles based on the SBP1 levels among controls, tumors in the lowest quartile were more than twice as likely to recur compared to those in any other quartile. Inducible ectopic SBP1 expression reduced the ability of HCT-116 human tumor cells to grow in soft agar, a measure of transformation, without affecting proliferation. Cells expressing SBP1 also demonstrated a robust induction in the phosphorylation of the p53 tumor suppressor at serine 15. These data indicate that loss of SBP1 may play an independent contributing role in prostate cancer progression and its levels might be useful in distinguishing indolent from aggressive disease. PMID:25993660

Label-free capture of breast cancer cells spiked in buffy coats using carbon nanotube antibody micro-arrays

NASA Astrophysics Data System (ADS)

Khosravi, Farhad; Trainor, Patrick; Rai, Shesh N.; Kloecker, Goetz; Wickstrom, Eric; Panchapakesan, Balaji

2016-04-01

We demonstrate the rapid and label-free capture of breast cancer cells spiked in buffy coats using nanotube-antibody micro-arrays. Single wall carbon nanotube arrays were manufactured using photo-lithography, metal deposition, and etching techniques. Anti-epithelial cell adhesion molecule (EpCAM) antibodies were functionalized to the surface of the nanotube devices using 1-pyrene-butanoic acid succinimidyl ester functionalization method. Following functionalization, plain buffy coat and MCF7 cell spiked buffy coats were adsorbed on to the nanotube device and electrical signatures were recorded for differences in interaction between samples. A statistical classifier for the ‘liquid biopsy’ was developed to create a predictive model based on dynamic time warping to classify device electrical signals that corresponded to plain (control) or spiked buffy coats (case). In training test, the device electrical signals originating from buffy versus spiked buffy samples were classified with ˜100% sensitivity, ˜91% specificity and ˜96% accuracy. In the blinded test, the signals were classified with ˜91% sensitivity, ˜82% specificity and ˜86% accuracy. A heatmap was generated to visually capture the relationship between electrical signatures and the sample condition. Confocal microscopic analysis of devices that were classified as spiked buffy coats based on their electrical signatures confirmed the presence of cancer cells, their attachment to the device and overexpression of EpCAM receptors. The cell numbers were counted to be ˜1-17 cells per 5 μl per device suggesting single cell sensitivity in spiked buffy coats that is scalable to higher volumes using the micro-arrays.

EFEMP1 as a novel DNA methylation marker for prostate cancer: array-based DNA methylation and expression profiling.

PubMed

Kim, Yong-June; Yoon, Hyung-Yoon; Kim, Seon-Kyu; Kim, Young-Won; Kim, Eun-Jung; Kim, Isaac Yi; Kim, Wun-Jae

2011-07-01

Abnormal DNA methylation is associated with many human cancers. The aim of the present study was to identify novel methylation markers in prostate cancer (PCa) by microarray analysis and to test whether these markers could discriminate normal and PCa cells. Microarray-based DNA methylation and gene expression profiling was carried out using a panel of PCa cell lines and a control normal prostate cell line. The methylation status of candidate genes in prostate cell lines was confirmed by real-time reverse transcriptase-PCR, bisulfite sequencing analysis, and treatment with a demethylation agent. DNA methylation and gene expression analysis in 203 human prostate specimens, including 106 PCa and 97 benign prostate hyperplasia (BPH), were carried out. Further validation using microarray gene expression data from the Gene Expression Omnibus (GEO) was carried out. Epidermal growth factor-containing fibulin-like extracellular matrix protein 1 (EFEMP1) was identified as a lead candidate methylation marker for PCa. The gene expression level of EFEMP1 was significantly higher in tissue samples from patients with BPH than in those with PCa (P < 0.001). The sensitivity and specificity of EFEMP1 methylation status in discriminating between PCa and BPH reached 95.3% (101 of 106) and 86.6% (84 of 97), respectively. From the GEO data set, we confirmed that the expression level of EFEMP1 was significantly different between PCa and BPH. Genome-wide characterization of DNA methylation profiles enabled the identification of EFEMP1 aberrant methylation patterns in PCa. EFEMP1 might be a useful indicator for the detection of PCa.

An unsupervised hierarchical dynamic self-organizing approach to cancer class discovery and marker gene identification in microarray data.

PubMed

Hsu, Arthur L; Tang, Sen-Lin; Halgamuge, Saman K

2003-11-01

Current Self-Organizing Maps (SOMs) approaches to gene expression pattern clustering require the user to predefine the number of clusters likely to be expected. Hierarchical clustering methods used in this area do not provide unique partitioning of data. We describe an unsupervised dynamic hierarchical self-organizing approach, which suggests an appropriate number of clusters, to perform class discovery and marker gene identification in microarray data. In the process of class discovery, the proposed algorithm identifies corresponding sets of predictor genes that best distinguish one class from other classes. The approach integrates merits of hierarchical clustering with robustness against noise known from self-organizing approaches. The proposed algorithm applied to DNA microarray data sets of two types of cancers has demonstrated its ability to produce the most suitable number of clusters. Further, the corresponding marker genes identified through the unsupervised algorithm also have a strong biological relationship to the specific cancer class. The algorithm tested on leukemia microarray data, which contains three leukemia types, was able to determine three major and one minor cluster. Prediction models built for the four clusters indicate that the prediction strength for the smaller cluster is generally low, therefore labelled as uncertain cluster. Further analysis shows that the uncertain cluster can be subdivided further, and the subdivisions are related to two of the original clusters. Another test performed using colon cancer microarray data has automatically derived two clusters, which is consistent with the number of classes in data (cancerous and normal). JAVA software of dynamic SOM tree algorithm is available upon request for academic use. A comparison of rectangular and hexagonal topologies for GSOM is available from http://www.mame.mu.oz.au/mechatronics/journalinfo/Hsu2003supp.pdf

geneCBR: a translational tool for multiple-microarray analysis and integrative information retrieval for aiding diagnosis in cancer research.

PubMed

Glez-Peña, Daniel; Díaz, Fernando; Hernández, Jesús M; Corchado, Juan M; Fdez-Riverola, Florentino

2009-06-18

Bioinformatics and medical informatics are two research fields that serve the needs of different but related communities. Both domains share the common goal of providing new algorithms, methods and technological solutions to biomedical research, and contributing to the treatment and cure of diseases. Although different microarray techniques have been successfully used to investigate useful information for cancer diagnosis at the gene expression level, the true integration of existing methods into day-to-day clinical practice is still a long way off. Within this context, case-based reasoning emerges as a suitable paradigm specially intended for the development of biomedical informatics applications and decision support systems, given the support and collaboration involved in such a translational development. With the goals of removing barriers against multi-disciplinary collaboration and facilitating the dissemination and transfer of knowledge to real practice, case-based reasoning systems have the potential to be applied to translational research mainly because their computational reasoning paradigm is similar to the way clinicians gather, analyze and process information in their own practice of clinical medicine. In addressing the issue of bridging the existing gap between biomedical researchers and clinicians who work in the domain of cancer diagnosis, prognosis and treatment, we have developed and made accessible a common interactive framework. Our geneCBR system implements a freely available software tool that allows the use of combined techniques that can be applied to gene selection, clustering, knowledge extraction and prediction for aiding diagnosis in cancer research. For biomedical researches, geneCBR expert mode offers a core workbench for designing and testing new techniques and experiments. For pathologists or oncologists, geneCBR diagnostic mode implements an effective and reliable system that can diagnose cancer subtypes based on the analysis of microarray data using a CBR architecture. For programmers, geneCBR programming mode includes an advanced edition module for run-time modification of previous coded techniques. geneCBR is a new translational tool that can effectively support the integrative work of programmers, biomedical researches and clinicians working together in a common framework. The code is freely available under the GPL license and can be obtained at http://www.genecbr.org.

High-throughput microarray technology in diagnostics of enterobacteria based on genome-wide probe selection and regression analysis.

PubMed

Friedrich, Torben; Rahmann, Sven; Weigel, Wilfried; Rabsch, Wolfgang; Fruth, Angelika; Ron, Eliora; Gunzer, Florian; Dandekar, Thomas; Hacker, Jörg; Müller, Tobias; Dobrindt, Ulrich

2010-10-21

The Enterobacteriaceae comprise a large number of clinically relevant species with several individual subspecies. Overlapping virulence-associated gene pools and the high overall genome plasticity often interferes with correct enterobacterial strain typing and risk assessment. Array technology offers a fast, reproducible and standardisable means for bacterial typing and thus provides many advantages for bacterial diagnostics, risk assessment and surveillance. The development of highly discriminative broad-range microbial diagnostic microarrays remains a challenge, because of marked genome plasticity of many bacterial pathogens. We developed a DNA microarray for strain typing and detection of major antimicrobial resistance genes of clinically relevant enterobacteria. For this purpose, we applied a global genome-wide probe selection strategy on 32 available complete enterobacterial genomes combined with a regression model for pathogen classification. The discriminative power of the probe set was further tested in silico on 15 additional complete enterobacterial genome sequences. DNA microarrays based on the selected probes were used to type 92 clinical enterobacterial isolates. Phenotypic tests confirmed the array-based typing results and corroborate that the selected probes allowed correct typing and prediction of major antibiotic resistances of clinically relevant Enterobacteriaceae, including the subspecies level, e.g. the reliable distinction of different E. coli pathotypes. Our results demonstrate that the global probe selection approach based on longest common factor statistics as well as the design of a DNA microarray with a restricted set of discriminative probes enables robust discrimination of different enterobacterial variants and represents a proof of concept that can be adopted for diagnostics of a wide range of microbial pathogens. Our approach circumvents misclassifications arising from the application of virulence markers, which are highly affected by horizontal gene transfer. Moreover, a broad range of pathogens have been covered by an efficient probe set size enabling the design of high-throughput diagnostics.

A probabilistic approach to segmentation and classification of neoplasia in uterine cervix images using color and geometric features

NASA Astrophysics Data System (ADS)

Srinivasan, Yeshwanth; Hernes, Dana; Tulpule, Bhakti; Yang, Shuyu; Guo, Jiangling; Mitra, Sunanda; Yagneswaran, Sriraja; Nutter, Brian; Jeronimo, Jose; Phillips, Benny; Long, Rodney; Ferris, Daron

2005-04-01

Automated segmentation and classification of diagnostic markers in medical imagery are challenging tasks. Numerous algorithms for segmentation and classification based on statistical approaches of varying complexity are found in the literature. However, the design of an efficient and automated algorithm for precise classification of desired diagnostic markers is extremely image-specific. The National Library of Medicine (NLM), in collaboration with the National Cancer Institute (NCI), is creating an archive of 60,000 digitized color images of the uterine cervix. NLM is developing tools for the analysis and dissemination of these images over the Web for the study of visual features correlated with precancerous neoplasia and cancer. To enable indexing of images of the cervix, it is essential to develop algorithms for the segmentation of regions of interest, such as acetowhitened regions, and automatic identification and classification of regions exhibiting mosaicism and punctation. Success of such algorithms depends, primarily, on the selection of relevant features representing the region of interest. We present color and geometric features based statistical classification and segmentation algorithms yielding excellent identification of the regions of interest. The distinct classification of the mosaic regions from the non-mosaic ones has been obtained by clustering multiple geometric and color features of the segmented sections using various morphological and statistical approaches. Such automated classification methodologies will facilitate content-based image retrieval from the digital archive of uterine cervix and have the potential of developing an image based screening tool for cervical cancer.

Alteration of gene expression in the colon of colorectal cancer model rat by dietary sodium gluconate.

PubMed

Kameue, Chiyoko; Tsukahara, Takamitsu; Ushida, Kazunari

2006-03-01

Butyrate induces apoptosis of various cancer cell lines in a p53-independent manner and inhibits the proliferation of cancer cells. In a previous report, we reported a significant reduction in tumor incidence in rat colon as a result of dietary sodium gluconate (GNA). The stimulation of apoptosis through enhanced butyrate production in the large intestine was involved in the antitumorigenic effect of GNA. In the present study, a cDNA microarray analysis was performed to investigate the particular mechanism involved in the antitumorigenic effect of GNA. Some up-regulated genes suggested by microarray analysis were further evaluated using real-time PCR. A microarray revealed that GNA regulates the expression of retinoic acid receptor (RAR) and retinoid X receptor (RXR), and several genes known as the target of retinoids in cancer cells. In other words, the antitumorigenic effect of GNA may involve the regulation of the retinoid signaling pathway by butyrate in a retinoid-independent manner.

Carbohydrate Microarrays Identify Blood Group Precursor Cryptic Epitopes as Potential Immunological Targets of Breast Cancer

PubMed Central

Wang, Denong; Tang, Jin; Liu, Shaoyi

2015-01-01

Using carbohydrate microarrays, we explored potential natural ligands of antitumor monoclonal antibody HAE3. This antibody was raised against a murine mammary tumor antigen but was found to cross-react with a number of human epithelial tumors in tissues. Our carbohydrate microarray analysis reveals that HAE3 is specific for an O-glycan cryptic epitope that is normally hidden in the cores of blood group substances. Using HAE3 to screen tumor cell surface markers by flow cytometry, we found that the HAE3 glycoepitope, gpHAE3, was highly expressed by a number of human breast cancer cell lines, including some triple-negative cancers that lack the estrogen, progesterone, and Her2/neu receptors. Taken together, we demonstrate that HAE3 recognizes a conserved cryptic glycoepitope of blood group precursors, which is nevertheless selectively expressed and surface-exposed in certain breast tumor cells. The potential of this class of O-glycan cryptic antigens in breast cancer subtyping and targeted immunotherapy warrants further investigation. PMID:26539555

A study of metaheuristic algorithms for high dimensional feature selection on microarray data

NASA Astrophysics Data System (ADS)

Dankolo, Muhammad Nasiru; Radzi, Nor Haizan Mohamed; Sallehuddin, Roselina; Mustaffa, Noorfa Haszlinna

2017-11-01

Microarray systems enable experts to examine gene profile at molecular level using machine learning algorithms. It increases the potentials of classification and diagnosis of many diseases at gene expression level. Though, numerous difficulties may affect the efficiency of machine learning algorithms which includes vast number of genes features comprised in the original data. Many of these features may be unrelated to the intended analysis. Therefore, feature selection is necessary to be performed in the data pre-processing. Many feature selection algorithms are developed and applied on microarray which including the metaheuristic optimization algorithms. This paper discusses the application of the metaheuristics algorithms for feature selection in microarray dataset. This study reveals that, the algorithms have yield an interesting result with limited resources thereby saving computational expenses of machine learning algorithms.

Symbolic rule-based classification of lung cancer stages from free-text pathology reports.

PubMed

Nguyen, Anthony N; Lawley, Michael J; Hansen, David P; Bowman, Rayleen V; Clarke, Belinda E; Duhig, Edwina E; Colquist, Shoni

2010-01-01

To classify automatically lung tumor-node-metastases (TNM) cancer stages from free-text pathology reports using symbolic rule-based classification. By exploiting report substructure and the symbolic manipulation of systematized nomenclature of medicine-clinical terms (SNOMED CT) concepts in reports, statements in free text can be evaluated for relevance against factors relating to the staging guidelines. Post-coordinated SNOMED CT expressions based on templates were defined and populated by concepts in reports, and tested for subsumption by staging factors. The subsumption results were used to build logic according to the staging guidelines to calculate the TNM stage. The accuracy measure and confusion matrices were used to evaluate the TNM stages classified by the symbolic rule-based system. The system was evaluated against a database of multidisciplinary team staging decisions and a machine learning-based text classification system using support vector machines. Overall accuracy on a corpus of pathology reports for 718 lung cancer patients against a database of pathological TNM staging decisions were 72%, 78%, and 94% for T, N, and M staging, respectively. The system's performance was also comparable to support vector machine classification approaches. A system to classify lung TNM stages from free-text pathology reports was developed, and it was verified that the symbolic rule-based approach using SNOMED CT can be used for the extraction of key lung cancer characteristics from free-text reports. Future work will investigate the applicability of using the proposed methodology for extracting other cancer characteristics and types.

An Integrated Analysis of miRNA and mRNA Expressions in Non-Small Cell Lung Cancers

PubMed Central

Ma, Lina; Huang, Yanyan; Zhu, Wangyu; Zhou, Shiquan; Zhou, Jihang; Zeng, Fang; Liu, Xiaoguang; Zhang, Yongkui; Yu, Jun

2011-01-01

Using DNA microarrays, we generated both mRNA and miRNA expression data from 6 non-small cell lung cancer (NSCLC) tissues and their matching normal control from adjacent tissues to identify potential miRNA markers for diagnostics. We demonstrated that hsa-miR-96 is significantly and consistently up-regulated in all 6 NSCLCs. We validated this result in an independent set of 35 paired tumors and their adjacent normal tissues, as well as their sera that are collected before surgical resection or chemotherapy, and the results suggested that hsa-miR-96 may play an important role in NSCLC development and has great potential to be used as a noninvasive marker for diagnosing NSCLC. We predicted potential miRNA target mRNAs based on different methods (TargetScan and miRanda). Further classification of miRNA regulated genes based on their relationship with miRNAs revealed that hsa-miR-96 and certain other miRNAs tend to down-regulate their target mRNAs in NSCLC development, which have expression levels permissive to direct interaction between miRNAs and their target mRNAs. In addition, we identified a significant correlation of miRNA regulation with genes coincide with high density of CpG islands, which suggests that miRNA may represent a primary regulatory mechanism governing basic cellular functions and cell differentiations, and such mechanism may be complementary to DNA methylation in repressing or activating gene expression. PMID:22046296

Classification of TP53 Mutations and HPV Predict Survival in Advanced Larynx Cancer

PubMed Central

Scheel, Adam; Bellile, Emily; McHugh, Jonathan B.; Walline, Heather M.; Prince, Mark E.; Urba, Susan; Wolf, Gregory T.; Eisbruch, Avraham; Worden, Francis; Carey, Thomas E.; Bradford, Carol

2016-01-01

OBJECTIVE Assess TP53 functional mutations in the context of other biomarkers in advanced larynx cancer. STUDY DESIGN Prospective analysis of pretreatment tumor TP53, HPV, Bcl-xL and cyclin D1 status in stage III and IV larynx cancer patients in a clinical trial. METHODS TP53 exons 4-9 from 58 tumors were sequenced. Mutations were grouped using three classifications based on their expected function. Each functional group was analyzed for response to induction chemotherapy, time to surgery, survival, HPV status, p16INK4a, Bcl-xl and cyclin D1 expression. RESULTS TP53 Mutations were found in 22/58 (37.9%) patients with advanced larynx cancer, including missense mutations in 13/58 (22.4%) patients, nonsense mutations in 4/58 (6.9%), and deletions in 5/58 (8.6%). High risk HPV was found in 20/52 (38.5%) tumors. A classification based on crystal Evolutionary Action score of p53 (EAp53) distinguished missense mutations with high risk for decreased survival from low risk mutations (p=0.0315). A model including this TP53 classification, HPV status, cyclin D1 and Bcl-xL staining significantly predicts survival (p=0.0017). CONCLUSION EAp53 functional classification of TP53 mutants and biomarkers predict survival in advanced larynx cancer. PMID:27345657

Microarray-based cancer prediction using soft computing approach.

PubMed

Wang, Xiaosheng; Gotoh, Osamu

2009-05-26

One of the difficulties in using gene expression profiles to predict cancer is how to effectively select a few informative genes to construct accurate prediction models from thousands or ten thousands of genes. We screen highly discriminative genes and gene pairs to create simple prediction models involved in single genes or gene pairs on the basis of soft computing approach and rough set theory. Accurate cancerous prediction is obtained when we apply the simple prediction models for four cancerous gene expression datasets: CNS tumor, colon tumor, lung cancer and DLBCL. Some genes closely correlated with the pathogenesis of specific or general cancers are identified. In contrast with other models, our models are simple, effective and robust. Meanwhile, our models are interpretable for they are based on decision rules. Our results demonstrate that very simple models may perform well on cancerous molecular prediction and important gene markers of cancer can be detected if the gene selection approach is chosen reasonably.

Minimising Immunohistochemical False Negative ER Classification Using a Complementary 23 Gene Expression Signature of ER Status

PubMed Central

Li, Qiyuan; Eklund, Aron C.; Juul, Nicolai; Haibe-Kains, Benjamin; Workman, Christopher T.; Richardson, Andrea L.; Szallasi, Zoltan; Swanton, Charles

2010-01-01

Background Expression of the oestrogen receptor (ER) in breast cancer predicts benefit from endocrine therapy. Minimising the frequency of false negative ER status classification is essential to identify all patients with ER positive breast cancers who should be offered endocrine therapies in order to improve clinical outcome. In routine oncological practice ER status is determined by semi-quantitative methods such as immunohistochemistry (IHC) or other immunoassays in which the ER expression level is compared to an empirical threshold[1], [2]. The clinical relevance of gene expression-based ER subtypes as compared to IHC-based determination has not been systematically evaluated. Here we attempt to reduce the frequency of false negative ER status classification using two gene expression approaches and compare these methods to IHC based ER status in terms of predictive and prognostic concordance with clinical outcome. Methodology/Principal Findings Firstly, ER status was discriminated by fitting the bimodal expression of ESR1 to a mixed Gaussian model. The discriminative power of ESR1 suggested bimodal expression as an efficient way to stratify breast cancer; therefore we identified a set of genes whose expression was both strongly bimodal, mimicking ESR expression status, and highly expressed in breast epithelial cell lines, to derive a 23-gene ER expression signature-based classifier. We assessed our classifiers in seven published breast cancer cohorts by comparing the gene expression-based ER status to IHC-based ER status as a predictor of clinical outcome in both untreated and tamoxifen treated cohorts. In untreated breast cancer cohorts, the 23 gene signature-based ER status provided significantly improved prognostic power compared to IHC-based ER status (P = 0.006). In tamoxifen-treated cohorts, the 23 gene ER expression signature predicted clinical outcome (HR = 2.20, P = 0.00035). These complementary ER signature-based strategies estimated that between 15.1% and 21.8% patients of IHC-based negative ER status would be classified with ER positive breast cancer. Conclusion/Significance Expression-based ER status classification may complement IHC to minimise false negative ER status classification and optimise patient stratification for endocrine therapies. PMID:21152022

CAMUR: Knowledge extraction from RNA-seq cancer data through equivalent classification rules.

PubMed

Cestarelli, Valerio; Fiscon, Giulia; Felici, Giovanni; Bertolazzi, Paola; Weitschek, Emanuel

2016-03-01

Nowadays, knowledge extraction methods from Next Generation Sequencing data are highly requested. In this work, we focus on RNA-seq gene expression analysis and specifically on case-control studies with rule-based supervised classification algorithms that build a model able to discriminate cases from controls. State of the art algorithms compute a single classification model that contains few features (genes). On the contrary, our goal is to elicit a higher amount of knowledge by computing many classification models, and therefore to identify most of the genes related to the predicted class. We propose CAMUR, a new method that extracts multiple and equivalent classification models. CAMUR iteratively computes a rule-based classification model, calculates the power set of the genes present in the rules, iteratively eliminates those combinations from the data set, and performs again the classification procedure until a stopping criterion is verified. CAMUR includes an ad-hoc knowledge repository (database) and a querying tool.We analyze three different types of RNA-seq data sets (Breast, Head and Neck, and Stomach Cancer) from The Cancer Genome Atlas (TCGA) and we validate CAMUR and its models also on non-TCGA data. Our experimental results show the efficacy of CAMUR: we obtain several reliable equivalent classification models, from which the most frequent genes, their relationships, and the relation with a particular cancer are deduced. dmb.iasi.cnr.it/camur.php emanuel@iasi.cnr.it Supplementary data are available at Bioinformatics online. © The Author 2015. Published by Oxford University Press.

Image classification of human carcinoma cells using complex wavelet-based covariance descriptors.

PubMed

Keskin, Furkan; Suhre, Alexander; Kose, Kivanc; Ersahin, Tulin; Cetin, A Enis; Cetin-Atalay, Rengul

2013-01-01

Cancer cell lines are widely used for research purposes in laboratories all over the world. Computer-assisted classification of cancer cells can alleviate the burden of manual labeling and help cancer research. In this paper, we present a novel computerized method for cancer cell line image classification. The aim is to automatically classify 14 different classes of cell lines including 7 classes of breast and 7 classes of liver cancer cells. Microscopic images containing irregular carcinoma cell patterns are represented by subwindows which correspond to foreground pixels. For each subwindow, a covariance descriptor utilizing the dual-tree complex wavelet transform (DT-[Formula: see text]WT) coefficients and several morphological attributes are computed. Directionally selective DT-[Formula: see text]WT feature parameters are preferred primarily because of their ability to characterize edges at multiple orientations which is the characteristic feature of carcinoma cell line images. A Support Vector Machine (SVM) classifier with radial basis function (RBF) kernel is employed for final classification. Over a dataset of 840 images, we achieve an accuracy above 98%, which outperforms the classical covariance-based methods. The proposed system can be used as a reliable decision maker for laboratory studies. Our tool provides an automated, time- and cost-efficient analysis of cancer cell morphology to classify different cancer cell lines using image-processing techniques, which can be used as an alternative to the costly short tandem repeat (STR) analysis. The data set used in this manuscript is available as supplementary material through http://signal.ee.bilkent.edu.tr/cancerCellLineClassificationSampleImages.html.

Image Classification of Human Carcinoma Cells Using Complex Wavelet-Based Covariance Descriptors

PubMed Central

Keskin, Furkan; Suhre, Alexander; Kose, Kivanc; Ersahin, Tulin; Cetin, A. Enis; Cetin-Atalay, Rengul

2013-01-01

Cancer cell lines are widely used for research purposes in laboratories all over the world. Computer-assisted classification of cancer cells can alleviate the burden of manual labeling and help cancer research. In this paper, we present a novel computerized method for cancer cell line image classification. The aim is to automatically classify 14 different classes of cell lines including 7 classes of breast and 7 classes of liver cancer cells. Microscopic images containing irregular carcinoma cell patterns are represented by subwindows which correspond to foreground pixels. For each subwindow, a covariance descriptor utilizing the dual-tree complex wavelet transform (DT-WT) coefficients and several morphological attributes are computed. Directionally selective DT-WT feature parameters are preferred primarily because of their ability to characterize edges at multiple orientations which is the characteristic feature of carcinoma cell line images. A Support Vector Machine (SVM) classifier with radial basis function (RBF) kernel is employed for final classification. Over a dataset of 840 images, we achieve an accuracy above 98%, which outperforms the classical covariance-based methods. The proposed system can be used as a reliable decision maker for laboratory studies. Our tool provides an automated, time- and cost-efficient analysis of cancer cell morphology to classify different cancer cell lines using image-processing techniques, which can be used as an alternative to the costly short tandem repeat (STR) analysis. The data set used in this manuscript is available as supplementary material through http://signal.ee.bilkent.edu.tr/cancerCellLineClassificationSampleImages.html. PMID:23341908

Microarray-based DNA methylation study of Ewing's sarcoma of the bone.

PubMed

Park, Hye-Rim; Jung, Woon-Won; Kim, Hyun-Sook; Park, Yong-Koo

2014-10-01

Alterations in DNA methylation patterns are a hallmark of malignancy. However, the majority of epigenetic studies of Ewing's sarcoma have focused on the analysis of only a few candidate genes. Comprehensive studies are thus lacking and are required. The aim of the present study was to identify novel methylation markers in Ewing's sarcoma using microarray analysis. The current study reports the microarray-based DNA methylation study of 1,505 CpG sites of 807 cancer-related genes from 69 Ewing's sarcoma samples. The Illumina GoldenGate Methylation Cancer Panel I microarray was used, and with the appropriate controls (n=14), a total of 92 hypermethylated genes were identified in the Ewing's sarcoma samples. The majority of the hypermethylated genes were associated with cell adhesion, cell regulation, development and signal transduction. The overall methylation mean values were compared between patients who survived and those that did not. The overall methylation mean was significantly higher in the patients who did not survive (0.25±0.03) than in those who did (0.22±0.05) (P=0.0322). However, the overall methylation mean was not found to significantly correlate with age, gender or tumor location. GDF10 , OSM , APC and HOXA11 were the most significant differentially-methylated genes, however, their methylation levels were not found to significantly correlate with the survival rate. The DNA methylation profile of Ewing's sarcoma was characterized and 92 genes that were significantly hypermethylated were detected. A trend towards a more aggressive behavior was identified in the methylated group. The results of this study indicated that methylation may be significant in the development of Ewing's sarcoma.

Microarray-based DNA methylation study of Ewing’s sarcoma of the bone

PubMed Central

PARK, HYE-RIM; JUNG, WOON-WON; KIM, HYUN-SOOK; PARK, YONG-KOO

2014-01-01

Alterations in DNA methylation patterns are a hallmark of malignancy. However, the majority of epigenetic studies of Ewing’s sarcoma have focused on the analysis of only a few candidate genes. Comprehensive studies are thus lacking and are required. The aim of the present study was to identify novel methylation markers in Ewing’s sarcoma using microarray analysis. The current study reports the microarray-based DNA methylation study of 1,505 CpG sites of 807 cancer-related genes from 69 Ewing’s sarcoma samples. The Illumina GoldenGate Methylation Cancer Panel I microarray was used, and with the appropriate controls (n=14), a total of 92 hypermethylated genes were identified in the Ewing’s sarcoma samples. The majority of the hypermethylated genes were associated with cell adhesion, cell regulation, development and signal transduction. The overall methylation mean values were compared between patients who survived and those that did not. The overall methylation mean was significantly higher in the patients who did not survive (0.25±0.03) than in those who did (0.22±0.05) (P=0.0322). However, the overall methylation mean was not found to significantly correlate with age, gender or tumor location. GDF10, OSM, APC and HOXA11 were the most significant differentially-methylated genes, however, their methylation levels were not found to significantly correlate with the survival rate. The DNA methylation profile of Ewing’s sarcoma was characterized and 92 genes that were significantly hypermethylated were detected. A trend towards a more aggressive behavior was identified in the methylated group. The results of this study indicated that methylation may be significant in the development of Ewing’s sarcoma. PMID:25202378

Molecular classification of gastric adenocarcinoma: translating new insights from the cancer genome atlas research network.

PubMed

Sunakawa, Yu; Lenz, Heinz-Josef

2015-04-01

Gastric cancer is a heterogenous cancer, which may be classified into several distinct subtypes based on pathology and epidemiology, each with different initiating pathological processes and each possibly having different tumor biology. A classification of gastric cancer should be important to select patients who can benefit from the targeted therapies or to precisely predict prognosis. The Cancer Genome Atlas (TCGA) study collaborated with previous reports regarding subtyping gastric cancer but also proposed a refined classification based on molecular characteristics. The addition of the new molecular classification strategy to a current classical subtyping may be a promising option, particularly stratification by Epstein-Barr virus (EBV) and microsatellite instability (MSI) statuses. According to TCGA study, EBV gastric cancer patients may benefit the programmed cell death protein 1 (PD-1)/programmed death-ligand 1 (PD-L1) antibodies or phosphoinositide 3-kinase (PI3K) inhibitors which are now being developed. The discoveries of predictive biomarkers should improve patient care and individualized medicine in the management since the targeted therapies may have the potential to change the landscape of gastric cancer treatment, moreover leading to both better understanding of the heterogeneity and better outcomes. Patient enrichment by predictive biomarkers for new treatment strategies will be critical to improve clinical outcomes. Additionally, liquid biopsies will be able to enable us to monitor in real-time molecular escape mechanism, resulting in better treatment strategies.

Gene Set−Based Integrative Analysis Revealing Two Distinct Functional Regulation Patterns in Four Common Subtypes of Epithelial Ovarian Cancer

PubMed Central

Chang, Chia-Ming; Chuang, Chi-Mu; Wang, Mong-Lien; Yang, Yi-Ping; Chuang, Jen-Hua; Yang, Ming-Jie; Yen, Ming-Shyen; Chiou, Shih-Hwa; Chang, Cheng-Chang

2016-01-01

Clear cell (CCC), endometrioid (EC), mucinous (MC) and high-grade serous carcinoma (SC) are the four most common subtypes of epithelial ovarian carcinoma (EOC). The widely accepted dualistic model of ovarian carcinogenesis divided EOCs into type I and II categories based on the molecular features. However, this hypothesis has not been experimentally demonstrated. We carried out a gene set-based analysis by integrating the microarray gene expression profiles downloaded from the publicly available databases. These quantified biological functions of EOCs were defined by 1454 Gene Ontology (GO) term and 674 Reactome pathway gene sets. The pathogenesis of the four EOC subtypes was investigated by hierarchical clustering and exploratory factor analysis. The patterns of functional regulation among the four subtypes containing 1316 cases could be accurately classified by machine learning. The results revealed that the ERBB and PI3K-related pathways played important roles in the carcinogenesis of CCC, EC and MC; while deregulation of cell cycle was more predominant in SC. The study revealed that two different functional regulation patterns exist among the four EOC subtypes, which were compatible with the type I and II classifications proposed by the dualistic model of ovarian carcinogenesis. PMID:27527159

Radiomics biomarkers for accurate tumor progression prediction of oropharyngeal cancer

NASA Astrophysics Data System (ADS)

Hadjiiski, Lubomir; Chan, Heang-Ping; Cha, Kenny H.; Srinivasan, Ashok; Wei, Jun; Zhou, Chuan; Prince, Mark; Papagerakis, Silvana

2017-03-01

Accurate tumor progression prediction for oropharyngeal cancers is crucial for identifying patients who would best be treated with optimized treatment and therefore minimize the risk of under- or over-treatment. An objective decision support system that can merge the available radiomics, histopathologic and molecular biomarkers in a predictive model based on statistical outcomes of previous cases and machine learning may assist clinicians in making more accurate assessment of oropharyngeal tumor progression. In this study, we evaluated the feasibility of developing individual and combined predictive models based on quantitative image analysis from radiomics, histopathology and molecular biomarkers for oropharyngeal tumor progression prediction. With IRB approval, 31, 84, and 127 patients with head and neck CT (CT-HN), tumor tissue microarrays (TMAs) and molecular biomarker expressions, respectively, were collected. For 8 of the patients all 3 types of biomarkers were available and they were sequestered in a test set. The CT-HN lesions were automatically segmented using our level sets based method. Morphological, texture and molecular based features were extracted from CT-HN and TMA images, and selected features were merged by a neural network. The classification accuracy was quantified using the area under the ROC curve (AUC). Test AUCs of 0.87, 0.74, and 0.71 were obtained with the individual predictive models based on radiomics, histopathologic, and molecular features, respectively. Combining the radiomics and molecular models increased the test AUC to 0.90. Combining all 3 models increased the test AUC further to 0.94. This preliminary study demonstrates that the individual domains of biomarkers are useful and the integrated multi-domain approach is most promising for tumor progression prediction.

High Dimensional Classification Using Features Annealed Independence Rules.

PubMed

Fan, Jianqing; Fan, Yingying

2008-01-01

Classification using high-dimensional features arises frequently in many contemporary statistical studies such as tumor classification using microarray or other high-throughput data. The impact of dimensionality on classifications is largely poorly understood. In a seminal paper, Bickel and Levina (2004) show that the Fisher discriminant performs poorly due to diverging spectra and they propose to use the independence rule to overcome the problem. We first demonstrate that even for the independence classification rule, classification using all the features can be as bad as the random guessing due to noise accumulation in estimating population centroids in high-dimensional feature space. In fact, we demonstrate further that almost all linear discriminants can perform as bad as the random guessing. Thus, it is paramountly important to select a subset of important features for high-dimensional classification, resulting in Features Annealed Independence Rules (FAIR). The conditions under which all the important features can be selected by the two-sample t-statistic are established. The choice of the optimal number of features, or equivalently, the threshold value of the test statistics are proposed based on an upper bound of the classification error. Simulation studies and real data analysis support our theoretical results and demonstrate convincingly the advantage of our new classification procedure.

Functional proteomic analysis reveals the involvement of KIAA1199 in breast cancer growth, motility and invasiveness

PubMed Central

2014-01-01

Background KIAA1199 is a recently identified novel gene that is up-regulated in human cancer with poor survival. Our proteomic study on signaling polarity in chemotactic cells revealed KIAA1199 as a novel protein target that may be involved in cellular chemotaxis and motility. In the present study, we examined the functional significance of KIAA1199 expression in breast cancer growth, motility and invasiveness. Methods We validated the previous microarray observation by tissue microarray immunohistochemistry using a TMA slide containing 12 breast tumor tissue cores and 12 corresponding normal tissues. We performed the shRNA-mediated knockdown of KIAA1199 in MDA-MB-231 and HS578T cells to study the role of this protein in cell proliferation, migration and apoptosis in vitro. We studied the effects of KIAA1199 knockdown in vivo in two groups of mice (n = 5). We carried out the SILAC LC-MS/MS based proteomic studies on the involvement of KIAA1199 in breast cancer. Results KIAA1199 mRNA and protein was significantly overexpressed in breast tumor specimens and cell lines as compared with non-neoplastic breast tissues from large-scale microarray and studies of breast cancer cell lines and tumors. To gain deeper insights into the novel role of KIAA1199 in breast cancer, we modulated KIAA1199 expression using shRNA-mediated knockdown in two breast cancer cell lines (MDA-MB-231 and HS578T), expressing higher levels of KIAA1199. The KIAA1199 knockdown cells showed reduced motility and cell proliferation in vitro. Moreover, when the knockdown cells were injected into the mammary fat pads of female athymic nude mice, there was a significant decrease in tumor incidence and growth. In addition, quantitative proteomic analysis revealed that knockdown of KIAA1199 in breast cancer (MDA-MB-231) cells affected a broad range of cellular functions including apoptosis, metabolism and cell motility. Conclusions Our findings indicate that KIAA1199 may play an important role in breast tumor growth and invasiveness, and that it may represent a novel target for biomarker development and a novel therapeutic target for breast cancer. PMID:24628760

Probabilistic classifiers with high-dimensional data

PubMed Central

Kim, Kyung In; Simon, Richard

2011-01-01

For medical classification problems, it is often desirable to have a probability associated with each class. Probabilistic classifiers have received relatively little attention for small n large p classification problems despite of their importance in medical decision making. In this paper, we introduce 2 criteria for assessment of probabilistic classifiers: well-calibratedness and refinement and develop corresponding evaluation measures. We evaluated several published high-dimensional probabilistic classifiers and developed 2 extensions of the Bayesian compound covariate classifier. Based on simulation studies and analysis of gene expression microarray data, we found that proper probabilistic classification is more difficult than deterministic classification. It is important to ensure that a probabilistic classifier is well calibrated or at least not “anticonservative” using the methods developed here. We provide this evaluation for several probabilistic classifiers and also evaluate their refinement as a function of sample size under weak and strong signal conditions. We also present a cross-validation method for evaluating the calibration and refinement of any probabilistic classifier on any data set. PMID:21087946

A common molecular signature of intestinal-type gastric carcinoma indicates processes related to gastric carcinogenesis.

PubMed

Binato, Renata; Santos, Everton Cruz; Boroni, Mariana; Demachki, Samia; Assumpção, Paulo; Abdelhay, Eliana

2018-01-26

Gastric carcinoma (GC) is one of the most aggressive cancers and the second leading cause of cancer death in the world. According to the Lauren classification, this adenocarcinoma is divided into two subtypes, intestinal and diffuse, which differ in their clinical, epidemiological and molecular features. Several studies have attempted to delineate the molecular signature of gastric cancer to develop new and non-invasive screening tests that improve diagnosis and lead to new treatment strategies. However, a consensus signature has not yet been identified for each condition. Thus, this work aimed to analyze the gene expression profile of Brazilian intestinal-type GC tissues using microarrays and compare the results to those of non-tumor tissue samples. Moreover, we compared our intestinal-type gastric carcinoma profile with those obtained from populations worldwide to assess their similarity. The results identified a molecular signature for intestinal-type GC and revealed that 38 genes differentially expressed in Brazilian intestinal-type gastric carcinoma samples can successfully distinguish gastric tumors from non-tumor tissue in the global population. These differentially expressed genes participate in biological processes important to cell homeostasis. Furthermore, Kaplan-Meier analysis suggested that 7 of these genes could individually be able to predict overall survival in intestinal-type gastric cancer patients.

AucPR: an AUC-based approach using penalized regression for disease prediction with high-dimensional omics data.

PubMed

Yu, Wenbao; Park, Taesung

2014-01-01

It is common to get an optimal combination of markers for disease classification and prediction when multiple markers are available. Many approaches based on the area under the receiver operating characteristic curve (AUC) have been proposed. Existing works based on AUC in a high-dimensional context depend mainly on a non-parametric, smooth approximation of AUC, with no work using a parametric AUC-based approach, for high-dimensional data. We propose an AUC-based approach using penalized regression (AucPR), which is a parametric method used for obtaining a linear combination for maximizing the AUC. To obtain the AUC maximizer in a high-dimensional context, we transform a classical parametric AUC maximizer, which is used in a low-dimensional context, into a regression framework and thus, apply the penalization regression approach directly. Two kinds of penalization, lasso and elastic net, are considered. The parametric approach can avoid some of the difficulties of a conventional non-parametric AUC-based approach, such as the lack of an appropriate concave objective function and a prudent choice of the smoothing parameter. We apply the proposed AucPR for gene selection and classification using four real microarray and synthetic data. Through numerical studies, AucPR is shown to perform better than the penalized logistic regression and the nonparametric AUC-based method, in the sense of AUC and sensitivity for a given specificity, particularly when there are many correlated genes. We propose a powerful parametric and easily-implementable linear classifier AucPR, for gene selection and disease prediction for high-dimensional data. AucPR is recommended for its good prediction performance. Beside gene expression microarray data, AucPR can be applied to other types of high-dimensional omics data, such as miRNA and protein data.

A Perspective on DNA Microarrays in Pathology Research and Practice

PubMed Central

Pollack, Jonathan R.

2007-01-01

DNA microarray technology matured in the mid-1990s, and the past decade has witnessed a tremendous growth in its application. DNA microarrays have provided powerful tools for pathology researchers seeking to describe, classify, and understand human disease. There has also been great expectation that the technology would advance the practice of pathology. This review highlights some of the key contributions of DNA microarrays to experimental pathology, focusing in the area of cancer research. Also discussed are some of the current challenges in translating utility to clinical practice. PMID:17600117

A novel feature extraction approach for microarray data based on multi-algorithm fusion

PubMed Central

Jiang, Zhu; Xu, Rong

2015-01-01

Feature extraction is one of the most important and effective method to reduce dimension in data mining, with emerging of high dimensional data such as microarray gene expression data. Feature extraction for gene selection, mainly serves two purposes. One is to identify certain disease-related genes. The other is to find a compact set of discriminative genes to build a pattern classifier with reduced complexity and improved generalization capabilities. Depending on the purpose of gene selection, two types of feature extraction algorithms including ranking-based feature extraction and set-based feature extraction are employed in microarray gene expression data analysis. In ranking-based feature extraction, features are evaluated on an individual basis, without considering inter-relationship between features in general, while set-based feature extraction evaluates features based on their role in a feature set by taking into account dependency between features. Just as learning methods, feature extraction has a problem in its generalization ability, which is robustness. However, the issue of robustness is often overlooked in feature extraction. In order to improve the accuracy and robustness of feature extraction for microarray data, a novel approach based on multi-algorithm fusion is proposed. By fusing different types of feature extraction algorithms to select the feature from the samples set, the proposed approach is able to improve feature extraction performance. The new approach is tested against gene expression dataset including Colon cancer data, CNS data, DLBCL data, and Leukemia data. The testing results show that the performance of this algorithm is better than existing solutions. PMID:25780277

A novel feature extraction approach for microarray data based on multi-algorithm fusion.

PubMed

Jiang, Zhu; Xu, Rong

2015-01-01

Feature extraction is one of the most important and effective method to reduce dimension in data mining, with emerging of high dimensional data such as microarray gene expression data. Feature extraction for gene selection, mainly serves two purposes. One is to identify certain disease-related genes. The other is to find a compact set of discriminative genes to build a pattern classifier with reduced complexity and improved generalization capabilities. Depending on the purpose of gene selection, two types of feature extraction algorithms including ranking-based feature extraction and set-based feature extraction are employed in microarray gene expression data analysis. In ranking-based feature extraction, features are evaluated on an individual basis, without considering inter-relationship between features in general, while set-based feature extraction evaluates features based on their role in a feature set by taking into account dependency between features. Just as learning methods, feature extraction has a problem in its generalization ability, which is robustness. However, the issue of robustness is often overlooked in feature extraction. In order to improve the accuracy and robustness of feature extraction for microarray data, a novel approach based on multi-algorithm fusion is proposed. By fusing different types of feature extraction algorithms to select the feature from the samples set, the proposed approach is able to improve feature extraction performance. The new approach is tested against gene expression dataset including Colon cancer data, CNS data, DLBCL data, and Leukemia data. The testing results show that the performance of this algorithm is better than existing solutions.

Gene selection and cancer type classification of diffuse large-B-cell lymphoma using a bivariate mixture model for two-species data.

PubMed

Su, Yuhua; Nielsen, Dahlia; Zhu, Lei; Richards, Kristy; Suter, Steven; Breen, Matthew; Motsinger-Reif, Alison; Osborne, Jason

2013-01-05

: A bivariate mixture model utilizing information across two species was proposed to solve the fundamental problem of identifying differentially expressed genes in microarray experiments. The model utility was illustrated using a dog and human lymphoma data set prepared by a group of scientists in the College of Veterinary Medicine at North Carolina State University. A small number of genes were identified as being differentially expressed in both species and the human genes in this cluster serve as a good predictor for classifying diffuse large-B-cell lymphoma (DLBCL) patients into two subgroups, the germinal center B-cell-like diffuse large B-cell lymphoma and the activated B-cell-like diffuse large B-cell lymphoma. The number of human genes that were observed to be significantly differentially expressed (21) from the two-species analysis was very small compared to the number of human genes (190) identified with only one-species analysis (human data). The genes may be clinically relevant/important, as this small set achieved low misclassification rates of DLBCL subtypes. Additionally, the two subgroups defined by this cluster of human genes had significantly different survival functions, indicating that the stratification based on gene-expression profiling using the proposed mixture model provided improved insight into the clinical differences between the two cancer subtypes.

Spectral Biclustering of Microarray Data: Coclustering Genes and Conditions

PubMed Central

Kluger, Yuval; Basri, Ronen; Chang, Joseph T.; Gerstein, Mark

2003-01-01

Global analyses of RNA expression levels are useful for classifying genes and overall phenotypes. Often these classification problems are linked, and one wants to find “marker genes” that are differentially expressed in particular sets of “conditions.” We have developed a method that simultaneously clusters genes and conditions, finding distinctive “checkerboard” patterns in matrices of gene expression data, if they exist. In a cancer context, these checkerboards correspond to genes that are markedly up- or downregulated in patients with particular types of tumors. Our method, spectral biclustering, is based on the observation that checkerboard structures in matrices of expression data can be found in eigenvectors corresponding to characteristic expression patterns across genes or conditions. In addition, these eigenvectors can be readily identified by commonly used linear algebra approaches, in particular the singular value decomposition (SVD), coupled with closely integrated normalization steps. We present a number of variants of the approach, depending on whether the normalization over genes and conditions is done independently or in a coupled fashion. We then apply spectral biclustering to a selection of publicly available cancer expression data sets, and examine the degree to which the approach is able to identify checkerboard structures. Furthermore, we compare the performance of our biclustering methods against a number of reasonable benchmarks (e.g., direct application of SVD or normalized cuts to raw data). PMID:12671006

Dual-color Proteomic Profiling of Complex Samples with a Microarray of 810 Cancer-related Antibodies*

PubMed Central

Schröder, Christoph; Jacob, Anette; Tonack, Sarah; Radon, Tomasz P.; Sill, Martin; Zucknick, Manuela; Rüffer, Sven; Costello, Eithne; Neoptolemos, John P.; Crnogorac-Jurcevic, Tatjana; Bauer, Andrea; Fellenberg, Kurt; Hoheisel, Jörg D.

2010-01-01

Antibody microarrays have the potential to enable comprehensive proteomic analysis of small amounts of sample material. Here, protocols are presented for the production, quality assessment, and reproducible application of antibody microarrays in a two-color mode with an array of 1,800 features, representing 810 antibodies that were directed at 741 cancer-related proteins. In addition to measures of array quality, we implemented indicators for the accuracy and significance of dual-color detection. Dual-color measurements outperform a single-color approach concerning assay reproducibility and discriminative power. In the analysis of serum samples, depletion of high-abundance proteins did not improve technical assay quality. On the contrary, depletion introduced a strong bias in protein representation. In an initial study, we demonstrated the applicability of the protocols to proteins derived from urine samples. We identified differences between urine samples from pancreatic cancer patients and healthy subjects and between sexes. This study demonstrates that biomedically relevant data can be produced. As demonstrated by the thorough quality analysis, the dual-color antibody array approach proved to be competitive with other proteomic techniques and comparable in performance to transcriptional microarray analyses. PMID:20164060

Molecular classification of gastric cancer.

PubMed

Röcken, Christoph

2017-03-01

Gastric cancer is among the most common cancers worldwide. Despite declining incidences, the prognosis remains dismal in Western countries and is better in Asian countries with national cancer screening programs. Complete endoscopic or surgical resection of the primary tumor with or without lymphadenectomy offers the only chance of cure in the early stage of the disease. Survival of more locally advanced gastric cancers was improved by the introduction of perioperative, adjuvant and palliative chemotherapy. However, the identification and usage of novel predictive and diagnostic targets is urgently needed. Areas covered: Recent comprehensive molecular profiling of gastric cancer proposed four molecular subtypes, i.e. Epstein-Barr virus-associated, microsatellite instable, chromosomal instable and genomically stable carcinomas. The new molecular classification will spur clinical trials exploring novel targeted therapeutics. This review summarizes recent advancements of the molecular classification, and based on that, putative pitfalls for the development of tissue-based companion diagnostics, i.e. prevalence of actionable targets and therapeutic efficacy, tumor heterogeneity and tumor evolution, impact of ethnicity on gastric cancer biology, and standards of care in the East and West. Expert commentary: The overall low prevalence of actionable targets and tumor heterogeneity are the two main obstacles of precision medicine for gastric cancer.

Application of Protein Microarrays for Multiplexed Detection of Antibodies to Tumor Antigens in Breast Cancer

PubMed Central

Anderson, Karen S.; Ramachandran, Niroshan; Wong, Jessica; Raphael, Jacob V.; Hainsworth, Eugenie; Demirkan, Gokhan; Cramer, Daniel; Aronzon, Diana; Hodi, F. Stephen; Harris, Lyndsay; Logvinenko, Tanya; LaBaer, Joshua

2012-01-01

There is strong preclinical evidence that cancer, including breast cancer, undergoes immune surveillance. This continual monitoring, by both the innate and the adaptive immune systems, recognizes changes in protein expression, mutation, folding, glycosylation, and degradation. Local immune responses to tumor antigens are amplified in draining lymph nodes, and then enter the systemic circulation. The antibody response to tumor antigens, such as p53 protein, are robust, stable, and easily detected in serum, may exist in greater concentrations than their cognate antigens, and are potential highly specific biomarkers for cancer. However, antibodies have limited sensitivities as single analytes, and differences in protein purification and assay characteristics have limited their clinical application. For example, p53 autoantibodies in the sera are highly specific for cancer patients, but are only detected in the sera of 10-20% of patients with breast cancer. Detection of p53 autoantibodies is dependent on tumor burden, p53 mutation, rapidly decreases with effective therapy, but is relatively independent of breast cancer subtype. Although antibodies to hundreds of other tumor antigens have been identified in the sera of breast cancer patients, very little is known about the specificity and clinical impact of the antibody immune repertoire to breast cancer. Recent advances in proteomic technologies have the potential for rapid identification of immune response signatures for breast cancer diagnosis and monitoring. We have adapted programmable protein microarrays for the specific detection of autoantibodies in breast cancer. Here, we present the first demonstration of the application of programmable protein microarray ELISAs for the rapid identification of breast cancer autoantibodies. PMID:18311903

Hidden discriminative features extraction for supervised high-order time series modeling.

PubMed

Nguyen, Ngoc Anh Thi; Yang, Hyung-Jeong; Kim, Sunhee

2016-11-01

In this paper, an orthogonal Tucker-decomposition-based extraction of high-order discriminative subspaces from a tensor-based time series data structure is presented, named as Tensor Discriminative Feature Extraction (TDFE). TDFE relies on the employment of category information for the maximization of the between-class scatter and the minimization of the within-class scatter to extract optimal hidden discriminative feature subspaces that are simultaneously spanned by every modality for supervised tensor modeling. In this context, the proposed tensor-decomposition method provides the following benefits: i) reduces dimensionality while robustly mining the underlying discriminative features, ii) results in effective interpretable features that lead to an improved classification and visualization, and iii) reduces the processing time during the training stage and the filtering of the projection by solving the generalized eigenvalue issue at each alternation step. Two real third-order tensor-structures of time series datasets (an epilepsy electroencephalogram (EEG) that is modeled as channel×frequency bin×time frame and a microarray data that is modeled as gene×sample×time) were used for the evaluation of the TDFE. The experiment results corroborate the advantages of the proposed method with averages of 98.26% and 89.63% for the classification accuracies of the epilepsy dataset and the microarray dataset, respectively. These performance averages represent an improvement on those of the matrix-based algorithms and recent tensor-based, discriminant-decomposition approaches; this is especially the case considering the small number of samples that are used in practice. Copyright © 2016 Elsevier Ltd. All rights reserved.

Diagnostic classification scheme in Iranian breast cancer patients using a decision tree.

PubMed

Malehi, Amal Saki

2014-01-01

The objective of this study was to determine a diagnostic classification scheme using a decision tree based model. The study was conducted as a retrospective case-control study in Imam Khomeini hospital in Tehran during 2001 to 2009. Data, including demographic and clinical-pathological characteristics, were uniformly collected from 624 females, 312 of them were referred with positive diagnosis of breast cancer (cases) and 312 healthy women (controls). The decision tree was implemented to develop a diagnostic classification scheme using CART 6.0 Software. The AUC (area under curve), was measured as the overall performance of diagnostic classification of the decision tree. Five variables as main risk factors of breast cancer and six subgroups as high risk were identified. The results indicated that increasing age, low age at menarche, single and divorced statues, irregular menarche pattern and family history of breast cancer are the important diagnostic factors in Iranian breast cancer patients. The sensitivity and specificity of the analysis were 66% and 86.9% respectively. The high AUC (0.82) also showed an excellent classification and diagnostic performance of the model. Decision tree based model appears to be suitable for identifying risk factors and high or low risk subgroups. It can also assists clinicians in making a decision, since it can identify underlying prognostic relationships and understanding the model is very explicit.

The 7th lung cancer TNM classification and staging system: Review of the changes and implications.

PubMed

Mirsadraee, Saeed; Oswal, Dilip; Alizadeh, Yalda; Caulo, Andrea; van Beek, Edwin

2012-04-28

Lung cancer is the most common cause of death from cancer in males, accounting for more than 1.4 million deaths in 2008. It is a growing concern in China, Asia and Africa as well. Accurate staging of the disease is an important part of the management as it provides estimation of patient's prognosis and identifies treatment sterategies. It also helps to build a database for future staging projects. A major revision of lung cancer staging has been announced with effect from January 2010. The new classification is based on a larger surgical and non-surgical cohort of patients, and thus more accurate in terms of outcome prediction compared to the previous classification. There are several original papers regarding this new classification which give comprehensive description of the methodology, the changes in the staging and the statistical analysis. This overview is a simplified description of the changes in the new classification and their potential impact on patients' treatment and prognosis.

ELISA microarray technology as a high-throughput system for cancer biomarker validation

DOE Office of Scientific and Technical Information (OSTI.GOV)

Zangar, Richard C.; Daly, Don S.; White, Amanda M.

A large gap currently exists between the ability to discover potential biomarkers and the ability to assess the real value of these proteins for cancer screening. One major challenge in biomarker validation is the inherent variability in biomarker levels. This variability stems from the diversity across the human population and the considerable molecular heterogeneity between individual tumors, even those that originate from a single tissue. Another major challenge with cancer screening is that most cancers are rare in the general population, meaning that the specificity of an assay must be very high if the number of false positive is notmore » going to be much greater than the number of true positives. Because of these challenges with biomarker validation, it is necessary to analysis of thousands of samples before a clear idea of the utility of a screening assay can be determined. Enzyme-linked immunosorbent assay (ELISA) microarray technology can simultaneously quantify levels of multiple proteins and has the potential to accelerate biomarker validation. In this review, we discuss current ELISA microarray technology and the enabling advances needed to achieve the reproducibility and throughput that are required to evaluate cancer biomarkers.« less

[Technology of analysis of epigenetic and structural changes of epithelial tumors genome with NotI-microarrays by the example of human chromosome].

PubMed

Pavlova, T V; Kashuba, V I; Muravenko, O V; Yenamandra, S P; Ivanova, T A; Zabarovskaia, V I; Rakhmanaliev, E R; Petrenko, L A; Pronina, I V; Loginov, V I; Iurkevich, O Iu; Kiselev, L L; Zelenin, A V; Zabarovskiĭ, E R

2009-01-01

New comparative genome hybridization technology on NotI-microarrays is presented (Karolinska Institute International Patent WO02/086163). The method is based on comparative genome hybridization of NotI-probes from tumor and normal genomic DNA with the principle of new DNA NotI-microarrays. Using this method 181 NotI linking loci from human chromosome 3 were analyzed in 200 malignant tumor samples from different organs: kidney, lung, breast, ovary, cervical, prostate. Most frequently (more than in 30%) aberrations--deletions, methylation,--were identified in NotI-sites located in MINT24, BHLHB2, RPL15, RARbeta1, ITGA9, RBSP3, VHL, ZIC4 genes, that suggests they probably are involved in cancer development. Methylation of these genomic loci was confirmed by methylation-specific PCR and bisulfite sequencing. The results demonstrate perspective of using this method to solve some oncogenomic problems.

Epigenetics of prostate cancer and the prospect of identification of novel drug targets by RNAi screening of epigenetic enzymes.

PubMed

Björkman, Mari; Rantala, Juha; Nees, Matthias; Kallioniemi, Olli

2010-10-01

Alterations in epigenetic processes probably underlie most human malignancies. Novel genome-wide techniques, such as chromatin immunoprecipitation and high-throughput sequencing, have become state-of-the-art methods to map the epigenomic landscape of development and disease, such as in cancers. Despite these advances, the functional significance of epigenetic enzymes in cancer progression, such as prostate cancer, remain incompletely understood. A comprehensive mapping and functional understanding of the cancer epigenome will hopefully help to facilitate development of novel cancer therapy targets and improve future diagnostics. The authors have developed a novel cell microarray-based high-content siRNA screening technique suitable to address the putative functional role and impact of all known putative and novel epigenetic enzymes in cancer, including prostate cancer.

Detection of gastric cancer-associated microRNAs on microRNA microarray comparing pre- and post-operative plasma

PubMed Central

Konishi, H; Ichikawa, D; Komatsu, S; Shiozaki, A; Tsujiura, M; Takeshita, H; Morimura, R; Nagata, H; Arita, T; Kawaguchi, T; Hirashima, S; Fujiwara, H; Okamoto, K; Otsuji, E

2012-01-01

Background: Recently, it was reported that plasma microRNAs (miRNAs) are low-invasive useful biomarkers for cancer. We attempted to isolate gastric cancer (GC)-associated miRNAs comparing pre- and post-operative paired plasma, thereby excluding the possible effects of individual variability. Methods: This study was divided into four steps: (1) microarray analysis comparing pre- and post-operative plasma; (2) validation of candidate miRNAs by quantitative RT–PCR; (3) validation study of selected miRNAs using paired plasma; and (4) comparison of the levels of selected miRNAs in plasma between healthy controls and patients. Results: From the results of microarray analysis, nine candidate miRNAs the levels of which were markedly decreased in post-operative plasma were selected for further studies. After confirmation of their post-operative marked reduction, two candidate miRNAs, miR-451 and miR-486, were selected as plasma biomarkers, considering the abundance in plasma, and marked decrease in post-operative samples. In validation, the two miRNAs were found to decrease in post-operative plasma in 90 and 93% of patients (both P<0.01). In comparison with healthy controls, the levels of both miRNAs were found to be significantly higher in patients, and the area under the curve values were high at 0.96 and 0.92. Conclusion: Plasma miR-451 and miR-486 could be useful blood-based biomarkers for screening GC. PMID:22262318

Spectral-spatial classification using tensor modeling for cancer detection with hyperspectral imaging

NASA Astrophysics Data System (ADS)

Lu, Guolan; Halig, Luma; Wang, Dongsheng; Chen, Zhuo Georgia; Fei, Baowei

2014-03-01

As an emerging technology, hyperspectral imaging (HSI) combines both the chemical specificity of spectroscopy and the spatial resolution of imaging, which may provide a non-invasive tool for cancer detection and diagnosis. Early detection of malignant lesions could improve both survival and quality of life of cancer patients. In this paper, we introduce a tensor-based computation and modeling framework for the analysis of hyperspectral images to detect head and neck cancer. The proposed classification method can distinguish between malignant tissue and healthy tissue with an average sensitivity of 96.97% and an average specificity of 91.42% in tumor-bearing mice. The hyperspectral imaging and classification technology has been demonstrated in animal models and can have many potential applications in cancer research and management.

Porous Silicon Antibody Microarrays for Quantitative Analysis: Measurement of Free and Total PSA in Clinical Plasma Samples

PubMed Central

Tojo, Axel; Malm, Johan; Marko-Varga, György; Lilja, Hans; Laurell, Thomas

2014-01-01

The antibody microarrays have become widespread, but their use for quantitative analyses in clinical samples has not yet been established. We investigated an immunoassay based on nanoporous silicon antibody microarrays for quantification of total prostate-specific-antigen (PSA) in 80 clinical plasma samples, and provide quantitative data from a duplex microarray assay that simultaneously quantifies free and total PSA in plasma. To further develop the assay the porous silicon chips was placed into a standard 96-well microtiter plate for higher throughput analysis. The samples analyzed by this quantitative microarray were 80 plasma samples obtained from men undergoing clinical PSA testing (dynamic range: 0.14-44ng/ml, LOD: 0.14ng/ml). The second dataset, measuring free PSA (dynamic range: 0.40-74.9ng/ml, LOD: 0.47ng/ml) and total PSA (dynamic range: 0.87-295ng/ml, LOD: 0.76ng/ml), was also obtained from the clinical routine. The reference for the quantification was a commercially available assay, the ProStatus PSA Free/Total DELFIA. In an analysis of 80 plasma samples the microarray platform performs well across the range of total PSA levels. This assay might have the potential to substitute for the large-scale microtiter plate format in diagnostic applications. The duplex assay paves the way for a future quantitative multiplex assay, which analyses several prostate cancer biomarkers simultaneously. PMID:22921878

A metadata-aware application for remote scoring and exchange of tissue microarray images

PubMed Central

2013-01-01

Background The use of tissue microarrays (TMA) and advances in digital scanning microscopy has enabled the collection of thousands of tissue images. There is a need for software tools to annotate, query and share this data amongst researchers in different physical locations. Results We have developed an open source web-based application for remote scoring of TMA images, which exploits the value of Microsoft Silverlight Deep Zoom to provide a intuitive interface for zooming and panning around digital images. We use and extend existing XML-based standards to ensure that the data collected can be archived and that our system is interoperable with other standards-compliant systems. Conclusion The application has been used for multi-centre scoring of TMA slides composed of tissues from several Phase III breast cancer trials and ten different studies participating in the International Breast Cancer Association Consortium (BCAC). The system has enabled researchers to simultaneously score large collections of TMA and export the standardised data to integrate with pathological and clinical outcome data, thereby facilitating biomarker discovery. PMID:23635078

Applying Multivariate Adaptive Splines to Identify Genes With Expressions Varying After Diagnosis in Microarray Experiments.

PubMed

Duan, Fenghai; Xu, Ye

2017-01-01

To analyze a microarray experiment to identify the genes with expressions varying after the diagnosis of breast cancer. A total of 44 928 probe sets in an Affymetrix microarray data publicly available on Gene Expression Omnibus from 249 patients with breast cancer were analyzed by the nonparametric multivariate adaptive splines. Then, the identified genes with turning points were grouped by K-means clustering, and their network relationship was subsequently analyzed by the Ingenuity Pathway Analysis. In total, 1640 probe sets (genes) were reliably identified to have turning points along with the age at diagnosis in their expression profiling, of which 927 expressed lower after turning points and 713 expressed higher after the turning points. K-means clustered them into 3 groups with turning points centering at 54, 62.5, and 72, respectively. The pathway analysis showed that the identified genes were actively involved in various cancer-related functions or networks. In this article, we applied the nonparametric multivariate adaptive splines method to a publicly available gene expression data and successfully identified genes with expressions varying before and after breast cancer diagnosis.

Biomarker Identification for Prostate Cancer and Lymph Node Metastasis from Microarray Data and Protein Interaction Network Using Gene Prioritization Method

PubMed Central

Arias, Carlos Roberto; Yeh, Hsiang-Yuan; Soo, Von-Wun

2012-01-01

Finding a genetic disease-related gene is not a trivial task. Therefore, computational methods are needed to present clues to the biomedical community to explore genes that are more likely to be related to a specific disease as biomarker. We present biomarker identification problem using gene prioritization method called gene prioritization from microarray data based on shortest paths, extended with structural and biological properties and edge flux using voting scheme (GP-MIDAS-VXEF). The method is based on finding relevant interactions on protein interaction networks, then scoring the genes using shortest paths and topological analysis, integrating the results using a voting scheme and a biological boosting. We applied two experiments, one is prostate primary and normal samples and the other is prostate primary tumor with and without lymph nodes metastasis. We used 137 truly prostate cancer genes as benchmark. In the first experiment, GP-MIDAS-VXEF outperforms all the other state-of-the-art methods in the benchmark by retrieving the truest related genes from the candidate set in the top 50 scores found. We applied the same technique to infer the significant biomarkers in prostate cancer with lymph nodes metastasis which is not established well. PMID:22654636

Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classification

PubMed Central

Hou, Le; Samaras, Dimitris; Kurc, Tahsin M.; Gao, Yi; Davis, James E.; Saltz, Joel H.

2016-01-01

Convolutional Neural Networks (CNN) are state-of-the-art models for many image classification tasks. However, to recognize cancer subtypes automatically, training a CNN on gigapixel resolution Whole Slide Tissue Images (WSI) is currently computationally impossible. The differentiation of cancer subtypes is based on cellular-level visual features observed on image patch scale. Therefore, we argue that in this situation, training a patch-level classifier on image patches will perform better than or similar to an image-level classifier. The challenge becomes how to intelligently combine patch-level classification results and model the fact that not all patches will be discriminative. We propose to train a decision fusion model to aggregate patch-level predictions given by patch-level CNNs, which to the best of our knowledge has not been shown before. Furthermore, we formulate a novel Expectation-Maximization (EM) based method that automatically locates discriminative patches robustly by utilizing the spatial relationships of patches. We apply our method to the classification of glioma and non-small-cell lung carcinoma cases into subtypes. The classification accuracy of our method is similar to the inter-observer agreement between pathologists. Although it is impossible to train CNNs on WSIs, we experimentally demonstrate using a comparable non-cancer dataset of smaller images that a patch-based CNN can outperform an image-based CNN. PMID:27795661

Development and external validation of a risk-prediction model to predict 5-year overall survival in advanced larynx cancer.

PubMed

Petersen, Japke F; Stuiver, Martijn M; Timmermans, Adriana J; Chen, Amy; Zhang, Hongzhen; O'Neill, James P; Deady, Sandra; Vander Poorten, Vincent; Meulemans, Jeroen; Wennerberg, Johan; Skroder, Carl; Day, Andrew T; Koch, Wayne; van den Brekel, Michiel W M

2018-05-01

TNM-classification inadequately estimates patient-specific overall survival (OS). We aimed to improve this by developing a risk-prediction model for patients with advanced larynx cancer. Cohort study. We developed a risk prediction model to estimate the 5-year OS rate based on a cohort of 3,442 patients with T3T4N0N+M0 larynx cancer. The model was internally validated using bootstrapping samples and externally validated on patient data from five external centers (n = 770). The main outcome was performance of the model as tested by discrimination, calibration, and the ability to distinguish risk groups based on tertiles from the derivation dataset. The model performance was compared to a model based on T and N classification only. We included age, gender, T and N classification, and subsite as prognostic variables in the standard model. After external validation, the standard model had a significantly better fit than a model based on T and N classification alone (C statistic, 0.59 vs. 0.55, P < .001). The model was able to distinguish well among three risk groups based on tertiles of the risk score. Adding treatment modality to the model did not decrease the predictive power. As a post hoc analysis, we tested the added value of comorbidity as scored by American Society of Anesthesiologists score in a subsample, which increased the C statistic to 0.68. A risk prediction model for patients with advanced larynx cancer, consisting of readily available clinical variables, gives more accurate estimations of the estimated 5-year survival rate when compared to a model based on T and N classification alone. 2c. Laryngoscope, 128:1140-1145, 2018. © 2017 The American Laryngological, Rhinological and Otological Society, Inc.

PTM Microarray: Request for Year 3 Set-Aside Funds — EDRN Public Portal

Cancer.gov

We hypothesize that PTMs on proteins that are secreted by the breast will provide a more sensitive method for detecting breast cancer than analysis of the parent protein. We will antibody microarrays to have examine 9 circulating proteins, each of which is known to be actively secreted by the breast, for several structurally and functionally distinct PTMs. We will determine if these modified proteins have the potential to used in the early detection of breast cancer.

[Changes of 2015 WHO Histological Classification of Lung Cancer 
and the Clinical Significance].

PubMed

Yang, Xin; Lin, Dongmei

2016-06-20

Due in part to remarkable advances over the past decade in our understanding of lung cancer, particularly in area of medical oncology, molecular biology, and radiology, there is a pressing need for a revised classification, based not on pathology alone, but rather on an integrated multidisciplinary approach to classification of lung cancer. The 2015 World Health Organization (WHO) Classification of Tumors of the Lung, Pleura, Thymus and Heart has just been published with numerous important changes from the 2004 WHO classification. The revised classification has been greatly improved in helping advance the field, increasing the impact of research, improving patient care and assisting in predicting outcome. The most significant changes will be summarized in this paper as follows: (1) main changes of lung adenocarcinoma as proposed by the 2011 International Association for the Study of Lung Cancer/American Thoracic Society/European Respiratory Society (IASLC/ATS/ERS) classification, (2) reclassifying squamous cell carcinomas into keratinizing, nonkeratinizing, and basaloid subtypes with the nonkeratinizing tumors requiring immunohistochemistry proof of squamous differentiation, (3) restricting the diagnosis of large cell carcinoma only to resected tumors that lack any clear morphologic or immunohistochemical differentiation with reclassification of the remaining former large cell carcinoma subtypes into different categories, (4) grouping of neuroendocrine tumors together in one category, (5) and the current viewpoint of histologic grading of lung cancer.

APPLICATION OF CDNA MICROARRAY TO THE STUDY OF ARSENIC TOXICOLOGY AND CARCINOGENESIS

EPA Science Inventory

Arsenic (As) is a common environmental toxicant and known human carcinogen. Epidemiological studies link As exposure to various disorders and cancers. However, the molecular mechanisms for As toxicity and carcinogenicity are not completely known. The cDNA microarray, a high-th...

Aided diagnosis methods of breast cancer based on machine learning

NASA Astrophysics Data System (ADS)

Zhao, Yue; Wang, Nian; Cui, Xiaoyu

2017-08-01

In the field of medicine, quickly and accurately determining whether the patient is malignant or benign is the key to treatment. In this paper, K-Nearest Neighbor, Linear Discriminant Analysis, Logistic Regression were applied to predict the classification of thyroid,Her-2,PR,ER,Ki67,metastasis and lymph nodes in breast cancer, in order to recognize the benign and malignant breast tumors and achieve the purpose of aided diagnosis of breast cancer. The results showed that the highest classification accuracy of LDA was 88.56%, while the classification effect of KNN and Logistic Regression were better than that of LDA, the best accuracy reached 96.30%.

Superpixel-based spectral classification for the detection of head and neck cancer with hyperspectral imaging

NASA Astrophysics Data System (ADS)

Chung, Hyunkoo; Lu, Guolan; Tian, Zhiqiang; Wang, Dongsheng; Chen, Zhuo Georgia; Fei, Baowei

2016-03-01

Hyperspectral imaging (HSI) is an emerging imaging modality for medical applications. HSI acquires two dimensional images at various wavelengths. The combination of both spectral and spatial information provides quantitative information for cancer detection and diagnosis. This paper proposes using superpixels, principal component analysis (PCA), and support vector machine (SVM) to distinguish regions of tumor from healthy tissue. The classification method uses 2 principal components decomposed from hyperspectral images and obtains an average sensitivity of 93% and an average specificity of 85% for 11 mice. The hyperspectral imaging technology and classification method can have various applications in cancer research and management.

[Role of contemporary pathological diagnostics in the personalized treatment of cancer].

PubMed

Tímár, József

2013-03-01

Due to the developments of pathology in the past decades (immunohistochemistry and molecular pathology) classification of cancers changed fundamentally, laying a ground for personalized management of cancer patients. Our picture of cancer is more complex today, identifying the genetic basis of the morphological variants. On the other hand, this picture has a much higher resolution enabling us to subclassify similar histological cancer types based on molecular markers. This redefined classification of cancers helps us to better predict the possible biological behavior of the disease and/or the therapeutic sensitivity, opening the way toward a more personalized treatment of this disease. The redefined molecular classification of cancer may affect the universal application of treatment protocols. To achieve this goal molecular diagnostics must be an integral and reimbursed part of the routine pathological diagnostics. On the other hand, it is time to extend the multidisciplinary team with molecular pathologist to improve the decision making process of the management of cancer patients.

Separation and Analysis of Adherent and Non-Adherent Cancer Cells Using a Single-Cell Microarray Chip.

PubMed

Yamamura, Shohei; Yamada, Eriko; Kimura, Fukiko; Miyajima, Kumiko; Shigeto, Hajime

2017-10-21

A new single-cell microarray chip was designed and developed to separate and analyze single adherent and non-adherent cancer cells. The single-cell microarray chip is made of polystyrene with over 60,000 microchambers of 10 different size patterns (31-40 µm upper diameter, 11-20 µm lower diameter). A drop of suspension of adherent carcinoma (NCI-H1650) and non-adherent leukocyte (CCRF-CEM) cells was placed onto the chip, and single-cell occupancy of NCI-H1650 and CCRF-CEM was determined to be 79% and 84%, respectively. This was achieved by controlling the chip design and surface treatment. Analysis of protein expression in single NCI-H1650 and CCRF-CEM cells was performed on the single-cell microarray chip by multi-antibody staining. Additionally, with this system, we retrieved positive single cells from the microchambers by a micromanipulator. Thus, this system demonstrates the potential for easy and accurate separation and analysis of various types of single cells.

BRCA-Monet: a breast cancer specific drug treatment mode-of-action network for treatment effective prediction using large scale microarray database

PubMed Central

2013-01-01

Background Connectivity map (cMap) is a recent developed dataset and algorithm for uncovering and understanding the treatment effect of small molecules on different cancer cell lines. It is widely used but there are still remaining challenges for accurate predictions. Method Here, we propose BRCA-MoNet, a network of drug mode of action (MoA) specific to breast cancer, which is constructed based on the cMap dataset. A drug signature selection algorithm fitting the characteristic of cMap data, a quality control scheme as well as a novel query algorithm based on BRCA-MoNet are developed for more effective prediction of drug effects. Result BRCA-MoNet was applied to three independent data sets obtained from the GEO database: Estrodial treated MCF7 cell line, BMS-754807 treated MCF7 cell line, and a breast cancer patient microarray dataset. In the first case, BRCA-MoNet could identify drug MoAs likely to share same and reverse treatment effect. In the second case, the result demonstrated the potential of BRCA-MoNet to reposition drugs and predict treatment effects for drugs not in cMap data. In the third case, a possible procedure of personalized drug selection is showcased. Conclusions The results clearly demonstrated that the proposed BRCA-MoNet approach can provide increased prediction power to cMap and thus will be useful for identification of new therapeutic candidates. Website: The web based application is developed and can be access through the following link http://compgenomics.utsa.edu/BRCAMoNet/ PMID:24564956

A note on the stability and discriminability of graph-based features for classification problems in digital pathology

NASA Astrophysics Data System (ADS)

Cruz-Roa, Angel; Xu, Jun; Madabhushi, Anant

2015-01-01

Nuclear architecture or the spatial arrangement of individual cancer nuclei on histopathology images has been shown to be associated with different grades and differential risk for a number of solid tumors such as breast, prostate, and oropharyngeal. Graph-based representations of individual nuclei (nuclei representing the graph nodes) allows for mining of quantitative metrics to describe tumor morphology. These graph features can be broadly categorized into global and local depending on the type of graph construction method. While a number of local graph (e.g. Cell Cluster Graphs) and global graph (e.g. Voronoi, Delaunay Triangulation, Minimum Spanning Tree) features have been shown to associated with cancer grade, risk, and outcome for different cancer types, the sensitivity of the preceding segmentation algorithms in identifying individual nuclei can have a significant bearing on the discriminability of the resultant features. This therefore begs the question as to which features while being discriminative of cancer grade and aggressiveness are also the most resilient to the segmentation errors. These properties are particularly desirable in the context of digital pathology images, where the method of slide preparation, staining, and type of nuclear segmentation algorithm employed can all dramatically affect the quality of the nuclear graphs and corresponding features. In this paper we evaluated the trade off between discriminability and stability of both global and local graph-based features in conjunction with a few different segmentation algorithms and in the context of two different histopathology image datasets of breast cancer from whole-slide images (WSI) and tissue microarrays (TMA). Specifically in this paper we investigate a few different performance measures including stability, discriminability and stability vs discriminability trade off, all of which are based on p-values from the Kruskal-Wallis one-way analysis of variance for local and global graph features. Apart from identifying the set of local and global features that satisfied the trade off between stability and discriminability, our most interesting finding was that a simple segmentation method was sufficient to identify the most discriminant features for invasive tumour detection in TMAs, whereas for tumour grading in WSI, the graph based features were more sensitive to the accuracy of the segmentation algorithm employed.

A protein and mRNA expression-based classification of gastric cancer.

PubMed

Setia, Namrata; Agoston, Agoston T; Han, Hye S; Mullen, John T; Duda, Dan G; Clark, Jeffrey W; Deshpande, Vikram; Mino-Kenudson, Mari; Srivastava, Amitabh; Lennerz, Jochen K; Hong, Theodore S; Kwak, Eunice L; Lauwers, Gregory Y

2016-07-01

The overall survival of gastric carcinoma patients remains poor despite improved control over known risk factors and surveillance. This highlights the need for new classifications, driven towards identification of potential therapeutic targets. Using sophisticated molecular technologies and analysis, three groups recently provided genetic and epigenetic molecular classifications of gastric cancer (The Cancer Genome Atlas, 'Singapore-Duke' study, and Asian Cancer Research Group). Suggested by these classifications, here, we examined the expression of 14 biomarkers in a cohort of 146 gastric adenocarcinomas and performed unsupervised hierarchical clustering analysis using less expensive and widely available immunohistochemistry and in situ hybridization. Ultimately, we identified five groups of gastric cancers based on Epstein-Barr virus (EBV) positivity, microsatellite instability, aberrant E-cadherin, and p53 expression; the remaining cases constituted a group characterized by normal p53 expression. In addition, the five categories correspond to the reported molecular subgroups by virtue of clinicopathologic features. Furthermore, evaluation between these clusters and survival using the Cox proportional hazards model showed a trend for superior survival in the EBV and microsatellite-instable related adenocarcinomas. In conclusion, we offer as a proposal a simplified algorithm that is able to reproduce the recently proposed molecular subgroups of gastric adenocarcinoma, using immunohistochemical and in situ hybridization techniques.

Improved Classification of Lung Cancer Using Radial Basis Function Neural Network with Affine Transforms of Voss Representation.

PubMed

Adetiba, Emmanuel; Olugbara, Oludayo O

2015-01-01

Lung cancer is one of the diseases responsible for a large number of cancer related death cases worldwide. The recommended standard for screening and early detection of lung cancer is the low dose computed tomography. However, many patients diagnosed die within one year, which makes it essential to find alternative approaches for screening and early detection of lung cancer. We present computational methods that can be implemented in a functional multi-genomic system for classification, screening and early detection of lung cancer victims. Samples of top ten biomarker genes previously reported to have the highest frequency of lung cancer mutations and sequences of normal biomarker genes were respectively collected from the COSMIC and NCBI databases to validate the computational methods. Experiments were performed based on the combinations of Z-curve and tetrahedron affine transforms, Histogram of Oriented Gradient (HOG), Multilayer perceptron and Gaussian Radial Basis Function (RBF) neural networks to obtain an appropriate combination of computational methods to achieve improved classification of lung cancer biomarker genes. Results show that a combination of affine transforms of Voss representation, HOG genomic features and Gaussian RBF neural network perceptibly improves classification accuracy, specificity and sensitivity of lung cancer biomarker genes as well as achieving low mean square error.

Study design requirements for RNA sequencing-based breast cancer diagnostics.

PubMed

Mer, Arvind Singh; Klevebring, Daniel; Grönberg, Henrik; Rantalainen, Mattias

2016-02-01

Sequencing-based molecular characterization of tumors provides information required for individualized cancer treatment. There are well-defined molecular subtypes of breast cancer that provide improved prognostication compared to routine biomarkers. However, molecular subtyping is not yet implemented in routine breast cancer care. Clinical translation is dependent on subtype prediction models providing high sensitivity and specificity. In this study we evaluate sample size and RNA-sequencing read requirements for breast cancer subtyping to facilitate rational design of translational studies. We applied subsampling to ascertain the effect of training sample size and the number of RNA sequencing reads on classification accuracy of molecular subtype and routine biomarker prediction models (unsupervised and supervised). Subtype classification accuracy improved with increasing sample size up to N = 750 (accuracy = 0.93), although with a modest improvement beyond N = 350 (accuracy = 0.92). Prediction of routine biomarkers achieved accuracy of 0.94 (ER) and 0.92 (Her2) at N = 200. Subtype classification improved with RNA-sequencing library size up to 5 million reads. Development of molecular subtyping models for cancer diagnostics requires well-designed studies. Sample size and the number of RNA sequencing reads directly influence accuracy of molecular subtyping. Results in this study provide key information for rational design of translational studies aiming to bring sequencing-based diagnostics to the clinic.

Mitochondrial electron transport chain identified as a novel molecular target of SPIO nanoparticles mediated cancer-specific cytotoxicity.

PubMed

He, Chengyong; Jiang, Shengwei; Jin, Haijing; Chen, Shuzhen; Lin, Gan; Yao, Huan; Wang, Xiaoyong; Mi, Peng; Ji, Zhiliang; Lin, Yuchun; Lin, Zhongning; Liu, Gang

2016-03-01

Superparamagnetic iron oxide nanoparticles (SPIONs) are highly cytotoxic and target cancer cells with high specificity; however, the mechanism by which SPIONs induce cancer cell-specific cytotoxicity remains unclear. Herein, the molecular mechanism of SPION-induced cancer cell-specific cytotoxicity to cancer cells is clarified through DNA microarray and bioinformatics analyses. SPIONs can interference with the mitochondrial electron transport chain (METC) in cancer cells, which further affects the production of ATP, mitochondrial membrane potential, and microdistribution of calcium, and induces cell apoptosis. Additionally, SPIONs induce the formation of reactive oxygen species in mitochondria; these reactive oxygen species trigger cancer-specific cytotoxicity due to the lower antioxidative capacity of cancer cells. Moreover, the DNA microarray and gene ontology analyses revealed that SPIONs elevate the expression of metallothioneins in both normal and cancer cells but decrease the expression of METC genes in cancer cells. Overall, these results suggest that SPIONs induce cancer cell death by targeting the METC, which is helpful for designing anti-cancer nanotheranostics and evaluating the safety of future nanomedicines. Copyright © 2016 Elsevier Ltd. All rights reserved.

DeepGene: an advanced cancer type classifier based on deep learning and somatic point mutations.

PubMed

Yuan, Yuchen; Shi, Yi; Li, Changyang; Kim, Jinman; Cai, Weidong; Han, Zeguang; Feng, David Dagan

2016-12-23

With the developments of DNA sequencing technology, large amounts of sequencing data have become available in recent years and provide unprecedented opportunities for advanced association studies between somatic point mutations and cancer types/subtypes, which may contribute to more accurate somatic point mutation based cancer classification (SMCC). However in existing SMCC methods, issues like high data sparsity, small volume of sample size, and the application of simple linear classifiers, are major obstacles in improving the classification performance. To address the obstacles in existing SMCC studies, we propose DeepGene, an advanced deep neural network (DNN) based classifier, that consists of three steps: firstly, the clustered gene filtering (CGF) concentrates the gene data by mutation occurrence frequency, filtering out the majority of irrelevant genes; secondly, the indexed sparsity reduction (ISR) converts the gene data into indexes of its non-zero elements, thereby significantly suppressing the impact of data sparsity; finally, the data after CGF and ISR is fed into a DNN classifier, which extracts high-level features for accurate classification. Experimental results on our curated TCGA-DeepGene dataset, which is a reformulated subset of the TCGA dataset containing 12 selected types of cancer, show that CGF, ISR and DNN all contribute in improving the overall classification performance. We further compare DeepGene with three widely adopted classifiers and demonstrate that DeepGene has at least 24% performance improvement in terms of testing accuracy. Based on deep learning and somatic point mutation data, we devise DeepGene, an advanced cancer type classifier, which addresses the obstacles in existing SMCC studies. Experiments indicate that DeepGene outperforms three widely adopted existing classifiers, which is mainly attributed to its deep learning module that is able to extract the high level features between combinatorial somatic point mutations and cancer types.

Classification of TP53 mutations and HPV predict survival in advanced larynx cancer.

PubMed

Scheel, Adam; Bellile, Emily; McHugh, Jonathan B; Walline, Heather M; Prince, Mark E; Urba, Susan; Wolf, Gregory T; Eisbruch, Avraham; Worden, Francis; Carey, Thomas E; Bradford, Carol

2016-09-01

Assess tumor suppressor p53 (TP53) functional mutations in the context of other biomarkers in advanced larynx cancer. Prospective analysis of pretreatment tumor TP53, human papillomavirus (HPV), Bcl-xL, and cyclin D1 status in stage III and IV larynx cancer patients in a clinical trial. TP53 exons 4 through 9 from 58 tumors were sequenced. Mutations were grouped using three classifications based on their expected function. Each functional group was analyzed for response to induction chemotherapy, time to surgery, survival, HPV status, p16INK4a, Bcl-xl, and cyclin D1 expression. TP53 mutations were found in 22 of 58 (37.9%) patients with advanced larynx cancer, including missense mutations in 13 of 58 (22.4%) patients, nonsense mutations in four of 58 (6.9%), and deletions in five of 58 (8.6%). High-risk HPV was found in 20 of 52 (38.5%) tumors. A classification based on Evolutionary Action score of p53 (EAp53) distinguished missense mutations with high risk for decreased survival from low-risk mutations (P = 0.0315). A model including this TP53 classification, HPV status, cyclin D1, and Bcl-xL staining significantly predicts survival (P = 0.0017). EAp53 functional classification of TP53 mutants and biomarkers predict survival in advanced larynx cancer. NA. Laryngoscope, 126:E292-E299, 2016. © 2016 The American Laryngological, Rhinological and Otological Society, Inc.

A comparison of blood vessel features and local binary patterns for colorectal polyp classification

NASA Astrophysics Data System (ADS)

Gross, Sebastian; Stehle, Thomas; Behrens, Alexander; Auer, Roland; Aach, Til; Winograd, Ron; Trautwein, Christian; Tischendorf, Jens

2009-02-01

Colorectal cancer is the third leading cause of cancer deaths in the United States of America for both women and men. By means of early detection, the five year survival rate can be up to 90%. Polyps can to be grouped into three different classes: hyperplastic, adenomatous, and carcinomatous polyps. Hyperplastic polyps are benign and are not likely to develop into cancer. Adenomas, on the other hand, are known to grow into cancer (adenoma-carcinoma sequence). Carcinomas are fully developed cancers and can be easily distinguished from adenomas and hyperplastic polyps. A recent narrow band imaging (NBI) study by Tischendorf et al. has shown that hyperplastic polyps and adenomas can be discriminated by their blood vessel structure. We designed a computer-aided system for the differentiation between hyperplastic and adenomatous polyps. Our development aim is to provide the medical practitioner with an additional objective interpretation of the available image data as well as a confidence measure for the classification. We propose classification features calculated on the basis of the extracted blood vessel structure. We use the combined length of the detected blood vessels, the average perimeter of the vessels and their average gray level value. We achieve a successful classification rate of more than 90% on 102 polyps from our polyp data base. The classification results based on these features are compared to the results of Local Binary Patterns (LBP). The results indicate that the implemented features are superior to LBP.

BRCA-Monet: a breast cancer specific drug treatment mode-of-action network for treatment effective prediction using large scale microarray database.

PubMed

Ma, Chifeng; Chen, Hung-I; Flores, Mario; Huang, Yufei; Chen, Yidong

2013-01-01

Connectivity map (cMap) is a recent developed dataset and algorithm for uncovering and understanding the treatment effect of small molecules on different cancer cell lines. It is widely used but there are still remaining challenges for accurate predictions. Here, we propose BRCA-MoNet, a network of drug mode of action (MoA) specific to breast cancer, which is constructed based on the cMap dataset. A drug signature selection algorithm fitting the characteristic of cMap data, a quality control scheme as well as a novel query algorithm based on BRCA-MoNet are developed for more effective prediction of drug effects. BRCA-MoNet was applied to three independent data sets obtained from the GEO database: Estrodial treated MCF7 cell line, BMS-754807 treated MCF7 cell line, and a breast cancer patient microarray dataset. In the first case, BRCA-MoNet could identify drug MoAs likely to share same and reverse treatment effect. In the second case, the result demonstrated the potential of BRCA-MoNet to reposition drugs and predict treatment effects for drugs not in cMap data. In the third case, a possible procedure of personalized drug selection is showcased. The results clearly demonstrated that the proposed BRCA-MoNet approach can provide increased prediction power to cMap and thus will be useful for identification of new therapeutic candidates.

Addressable droplet microarrays for single cell protein analysis.

PubMed

Salehi-Reyhani, Ali; Burgin, Edward; Ces, Oscar; Willison, Keith R; Klug, David R

2014-11-07

Addressable droplet microarrays are potentially attractive as a way to achieve miniaturised, reduced volume, high sensitivity analyses without the need to fabricate microfluidic devices or small volume chambers. We report a practical method for producing oil-encapsulated addressable droplet microarrays which can be used for such analyses. To demonstrate their utility, we undertake a series of single cell analyses, to determine the variation in copy number of p53 proteins in cells of a human cancer cell line.

The Role of Proteomics in the Diagnosis and Treatment of Women's Cancers: Current Trends in Technology and Future Opportunities

PubMed Central

Breuer, Eun-Kyoung Yim; Murph, Mandi M.

2011-01-01

Technological and scientific innovations over the last decade have greatly contributed to improved diagnostics, predictive models, and prognosis among cancers affecting women. In fact, an explosion of information in these areas has almost assured future generations that outcomes in cancer will continue to improve. Herein we discuss the current status of breast, cervical, and ovarian cancers as it relates to screening, disease diagnosis, and treatment options. Among the differences in these cancers, it is striking that breast cancer has multiple predictive tests based upon tumor biomarkers and sophisticated, individualized options for prescription therapeutics while ovarian cancer lacks these tools. In addition, cervical cancer leads the way in innovative, cancer-preventative vaccines and multiple screening options to prevent disease progression. For each of these malignancies, emerging proteomic technologies based upon mass spectrometry, stable isotope labeling with amino acids, high-throughput ELISA, tissue or protein microarray techniques, and click chemistry in the pursuit of activity-based profiling can pioneer the next generation of discovery. We will discuss six of the latest techniques to understand proteomics in cancer and highlight research utilizing these techniques with the goal of improvement in the management of women's cancers. PMID:21886869

IGF-1R and ErbB3/HER3 contribute to enhanced proliferation and carcinogenesis in trastuzumab-resistant ovarian cancer model

DOE Office of Scientific and Technical Information (OSTI.GOV)

Jia, Yanhan; Department of Immunology, Institute of Basic Medical Sciences, Beijing 100850; Zhang, Yan

2013-07-12

Highlights: •We established trastuzumab-resistant cell line SKOV3/T. •SKOV3/T enhances proliferation and in vivo carcinogenesis. •IGF-1R and HER3 genes were up-regulated in SKOV3/T based on microarray analysis. •Targeting IGF-1R and/or HER3 inhibited the proliferation of SKOV3/T. •Therapies targeting IGF-1R and HER3 might be effective in ovarian cancer. -- Abstract: Trastuzumab (Herceptin®) has demonstrated clinical potential in several types of HER2-overexpressing human cancers. However, primary and acquired resistance occurs in many HER2-positive patients with regimens. To investigate the possible mechanism of acquired therapeutic resistance to trastuzumab, we have developed a preclinical model of human ovarian cancer cells, SKOV3/T, with the distinctive featuremore » of stronger carcinogenesis. The differences in gene expression between parental and the resistant cells were explored by microarray analysis, of which IGF-1R and HER3 were detected to be key molecules in action. Their correctness was validated by follow-up experiments of RT-PCR, shRNA-mediated knockdown, downstream signal activation, cell cycle distribution and survival. These results suggest that IGF-1R and HER3 differentially regulate trastuzumab resistance and could be promising targets for trastuzumab therapy in ovarian cancer.« less

A new hybrid method based on fuzzy-artificial immune system and k-nn algorithm for breast cancer diagnosis.

PubMed

Sahan, Seral; Polat, Kemal; Kodaz, Halife; Güneş, Salih

2007-03-01

The use of machine learning tools in medical diagnosis is increasing gradually. This is mainly because the effectiveness of classification and recognition systems has improved in a great deal to help medical experts in diagnosing diseases. Such a disease is breast cancer, which is a very common type of cancer among woman. As the incidence of this disease has increased significantly in the recent years, machine learning applications to this problem have also took a great attention as well as medical consideration. This study aims at diagnosing breast cancer with a new hybrid machine learning method. By hybridizing a fuzzy-artificial immune system with k-nearest neighbour algorithm, a method was obtained to solve this diagnosis problem via classifying Wisconsin Breast Cancer Dataset (WBCD). This data set is a very commonly used data set in the literature relating the use of classification systems for breast cancer diagnosis and it was used in this study to compare the classification performance of our proposed method with regard to other studies. We obtained a classification accuracy of 99.14%, which is the highest one reached so far. The classification accuracy was obtained via 10-fold cross validation. This result is for WBCD but it states that this method can be used confidently for other breast cancer diagnosis problems, too.

Prognostication in eye cancer: the latest tumor, node, metastasis classification and beyond

PubMed Central

Kivelä, T; Kujala, E

2013-01-01

The tumour, node, metastasis (TNM) classification is a universal cancer staging system, which has been used for five decades. The current seventh edition became effective in 2010 and covers six ophthalmic sites: eyelids, conjunctiva, uvea, retina, orbit, and lacrimal gland; and five cancer types: carcinoma, sarcoma, melanoma, retinoblastoma, and lymphoma. The TNM categories are based on the anatomic extent of the primary tumour (T), regional lymph node metastases (N), and systemic metastases (M). The T categories of ophthalmic cancers are based on the size of the primary tumour and any invasion of periocular structures. The anatomic category is used to determine the TNM stage that correlates with survival. Such staging is currently implemented only for carcinoma of the eyelid and melanoma of the uvea. The classification of ciliary body and choroidal melanoma is the only one based on clinical evidence so far: a database of 7369 patients analysed by the European Ophthalmic Oncology Group. It spans a prognosis from 96% 5-year survival for stage I to 97% 5-year mortality for stage IV. The most accurate criterion for prognostication in uveal melanoma is, however, analysis of chromosomal alterations and gene expression. When such data are available, the TNM stage may be used for further stratification. Prognosis in retinoblastoma is frequently assigned by using an international classification, which predicts conservation of the eye and vision, and an international staging separate from the TNM system, which predicts survival. The TNM cancer staging manual is a useful tool for all ophthalmologists managing eye cancer. PMID:23258307

Intratumoral immune cells expressing PD-1/PD-L1 and their prognostic implications in cancer: a meta-analysis.

PubMed

Kim, Younghoon; Wen, Xianyu; Cho, Nam Yun; Kang, Gyeong Hoon

2018-05-01

The prognostic value of immune cells expressing programmed cell death 1 (PD-1) and PD-1 ligand 1 (PD-L1) in cancer are controversial, and the potential differential impact of using tissue microarrays and whole tissue sections to assess the positivity of immune cells has not been addressed. The current study included 30 eligible studies with 7251 patients that evaluated the relationship between tumor-infiltrating lymphocytes expressing PD-1/PD-L1 and overall survival and disease-free survival, or progression-free survival. Subgroup analysis was based on the tissue type of cancer and the type of tissue sampling (tissue microarray or whole tissue section). In the meta-analysis, PD-1-positive and PD-L1-positive tumor-infiltrating lymphocytes had a positive effect on disease-free survival or progression-free survival (hazard ratio [HR] 0.732; 95% confidence interval [CI] 0.565, 0.947; and HR 0.727; 95% CI 0.584, 0.905, respectively). PD-L1-positive tumor-infiltrating lymphocytes had a positive impact on overall survival in studies using tissue microarray (HR 0.586; 95% CI 0.476, 0.721), but had a poor impact when only whole tissue sections were considered (HR 1.558; 95% CI 1.232, 1.969). Lung cancer was associated with good overall survival and disease-free survival (HR 0.639; 95% CI 0.491, 0.831; and HR 0.693; 95% CI 0.538, 0.891, respectively) for PD-1-positive tumor-infiltrating lymphocytes, and colorectal cancer showed favorable disease-free survival (HR 0.471; 95% CI 0.308, 0.722) for PD-L1-positive tumor-infiltrating lymphocytes. Immune cells expressing PD-1 and PD-L1 within tumors are associated with the prognosis. However, the correlation may vary among different tumor types and by the type of tissue sampling used for the assessment.

A Global Covariance Descriptor for Nuclear Atypia Scoring in Breast Histopathology Images.

PubMed

Khan, Adnan Mujahid; Sirinukunwattana, Korsuk; Rajpoot, Nasir

2015-09-01

Nuclear atypia scoring is a diagnostic measure commonly used to assess tumor grade of various cancers, including breast cancer. It provides a quantitative measure of deviation in visual appearance of cell nuclei from those in normal epithelial cells. In this paper, we present a novel image-level descriptor for nuclear atypia scoring in breast cancer histopathology images. The method is based on the region covariance descriptor that has recently become a popular method in various computer vision applications. The descriptor in its original form is not suitable for classification of histopathology images as cancerous histopathology images tend to possess diversely heterogeneous regions in a single field of view. Our proposed image-level descriptor, which we term as the geodesic mean of region covariance descriptors, possesses all the attractive properties of covariance descriptors lending itself to tractable geodesic-distance-based k-nearest neighbor classification using efficient kernels. The experimental results suggest that the proposed image descriptor yields high classification accuracy compared to a variety of widely used image-level descriptors.

A novel approach for discovering condition-specific correlations of gene expressions within biological pathways by using cloud computing technology.

PubMed

Chang, Tzu-Hao; Wu, Shih-Lin; Wang, Wei-Jen; Horng, Jorng-Tzong; Chang, Cheng-Wei

2014-01-01

Microarrays are widely used to assess gene expressions. Most microarray studies focus primarily on identifying differential gene expressions between conditions (e.g., cancer versus normal cells), for discovering the major factors that cause diseases. Because previous studies have not identified the correlations of differential gene expression between conditions, crucial but abnormal regulations that cause diseases might have been disregarded. This paper proposes an approach for discovering the condition-specific correlations of gene expressions within biological pathways. Because analyzing gene expression correlations is time consuming, an Apache Hadoop cloud computing platform was implemented. Three microarray data sets of breast cancer were collected from the Gene Expression Omnibus, and pathway information from the Kyoto Encyclopedia of Genes and Genomes was applied for discovering meaningful biological correlations. The results showed that adopting the Hadoop platform considerably decreased the computation time. Several correlations of differential gene expressions were discovered between the relapse and nonrelapse breast cancer samples, and most of them were involved in cancer regulation and cancer-related pathways. The results showed that breast cancer recurrence might be highly associated with the abnormal regulations of these gene pairs, rather than with their individual expression levels. The proposed method was computationally efficient and reliable, and stable results were obtained when different data sets were used. The proposed method is effective in identifying meaningful biological regulation patterns between conditions.

Sequence variant classification and reporting: recommendations for improving the interpretation of cancer susceptibility genetic test results

PubMed Central

Plon, Sharon E.; Eccles, Diana M.; Easton, Douglas; Foulkes, William D.; Genuardi, Maurizio; Greenblatt, Marc S.; Hogervorst, Frans B.L.; Hoogerbrugge, Nicoline; Spurdle, Amanda B.; Tavtigian, Sean

2011-01-01

Genetic testing of cancer susceptibility genes is now widely applied in clinical practice to predict risk of developing cancer. In general, sequence-based testing of germline DNA is used to determine whether an individual carries a change that is clearly likely to disrupt normal gene function. Genetic testing may detect changes that are clearly pathogenic, clearly neutral or variants of unclear clinical significance. Such variants present a considerable challenge to the diagnostic laboratory and the receiving clinician in terms of interpretation and clear presentation of the implications of the result to the patient. There does not appear to be a consistent approach to interpreting and reporting the clinical significance of variants either among genes or among laboratories. The potential for confusion among clinicians and patients is considerable and misinterpretation may lead to inappropriate clinical consequences. In this article we review the current state of sequence-based genetic testing, describe other standardized reporting systems used in oncology and propose a standardized classification system for application to sequence based results for cancer predisposition genes. We suggest a system of five classes of variants based on the degree of likelihood of pathogenicity. Each class is associated with specific recommendations for clinical management of at-risk relatives that will depend on the syndrome. We propose that panels of experts on each cancer predisposition syndrome facilitate the classification scheme and designate appropriate surveillance and cancer management guidelines. The international adoption of a standardized reporting system should improve the clinical utility of sequence-based genetic tests to predict cancer risk. PMID:18951446

Deep convolutional neural networks for automatic classification of gastric carcinoma using whole slide images in digital histopathology.

PubMed

Sharma, Harshita; Zerbe, Norman; Klempert, Iris; Hellwich, Olaf; Hufnagl, Peter

2017-11-01

Deep learning using convolutional neural networks is an actively emerging field in histological image analysis. This study explores deep learning methods for computer-aided classification in H&E stained histopathological whole slide images of gastric carcinoma. An introductory convolutional neural network architecture is proposed for two computerized applications, namely, cancer classification based on immunohistochemical response and necrosis detection based on the existence of tumor necrosis in the tissue. Classification performance of the developed deep learning approach is quantitatively compared with traditional image analysis methods in digital histopathology requiring prior computation of handcrafted features, such as statistical measures using gray level co-occurrence matrix, Gabor filter-bank responses, LBP histograms, gray histograms, HSV histograms and RGB histograms, followed by random forest machine learning. Additionally, the widely known AlexNet deep convolutional framework is comparatively analyzed for the corresponding classification problems. The proposed convolutional neural network architecture reports favorable results, with an overall classification accuracy of 0.6990 for cancer classification and 0.8144 for necrosis detection. Copyright © 2017 Elsevier Ltd. All rights reserved.

Screening for Pancreatic Cancer

PubMed Central

Brand, Randall E.

2007-01-01

Despite improvements in the clinical and surgical management of pancreatic cancer, limited strides have been made in the early detection of this highly lethal malignancy. The majority of localized pancreatic tumors are asymptomatic, and the recognized presenting symptoms of pancreatic adenocarcinoma are often vague and heterogeneous in nature. These factors, coupled with the lack of a sensitive and noninvasive screening method, have made population-based screening for pancreatic cancer impossible. Nevertheless, at least two large institutions have performed multimodality-screening protocols for individuals with high risk of pancreatic cancer based on genetic predisposition and strong family history. Abnormalities noted during these screening protocols prompted further investigation or surgery that resulted in the discovery of benign, potentially malignant, and malignant pancreatic lesions. In addition to ductal epithelial pancreatic intraepithelial neoplasia, greater sensitivity has recently been achieved in the identification and characterization of precancerous mucinous pancreatic tumors. Advancements in proteomics and DNA microarray technology may confirm serum-based biomarkers that could be incorporated into future screening algorithms for pancreatic cancer. PMID:21960811

Upregulation of the ESR1 Gene and ESR Ratio (ESR1/ESR2) is Associated with a Worse Prognosis in Papillary Thyroid Carcinoma: The Impact of the Estrogen Receptor α/β Expression on Clinical Outcomes in Papillary Thyroid Carcinoma Patients.

PubMed

Yi, Jin Wook; Kim, Su-Jin; Kim, Jong Kyu; Seong, Chan Yong; Yu, Hyeong Won; Chai, Young Jun; Choi, June Young; Lee, Kyu Eun

2017-11-01

A gender disparity exists with respect to the incidence of papillary thyroid cancer (PTC), suggesting that sex hormones such as estrogen play a role in PTC development and progression. In this study, we compared estrogen receptor gene expression patterns in PTCs to determine the clinical significance of estrogen gene expression in PTC. We analyzed ESR1 and ESR2 messenger RNA expression counts using data from The Cancer Genome Atlas (TCGA). To validate the results of TCGA analysis, we analyzed microarray data (GSE 54958) from the Gene Expression Omnibus. ESR1 gene expression and ESR ratio (ESR1/ESR2) were significantly higher in PTC tissues than in paired normal thyroid tissues (mean 659.427 vs. 264.045 for ESR1, 92.017 vs. 19.064 for ESR ratio). Among female patients, ESR1 expression and ESR ratio were negatively correlated with increased age. ESR1 expression and ESR ratio were higher in patients with classic PTC, lymphovascular invasion, BRAF V600E mutation, and radioiodine therapy. Classification analysis demonstrated that higher ESR1 expression and a higher ESR ratio faced a worse overall survival (hazard ratio 6.348 for ESR1, 4.031 for ESR ratio). Validation microarray analysis demonstrated that ESR1 expression and ESR ratio were higher in tumor tissues, classic PTC, and BRAF V600E . Higher ESR1 expression and a higher ESR ratio were associated with aggressive prognostic factors and worse overall survival in female PTC patients. Our results suggest that ESR1 and ESR ratio can be used as prognostic markers to predict female patient survival and have potential as a therapeutic target.

Gene Expression Profiling of Gastric Cancer

PubMed Central

Marimuthu, Arivusudar; Jacob, Harrys K.C.; Jakharia, Aniruddha; Subbannayya, Yashwanth; Keerthikumar, Shivakumar; Kashyap, Manoj Kumar; Goel, Renu; Balakrishnan, Lavanya; Dwivedi, Sutopa; Pathare, Swapnali; Dikshit, Jyoti Bajpai; Maharudraiah, Jagadeesha; Singh, Sujay; Sameer Kumar, Ghantasala S; Vijayakumar, M.; Veerendra Kumar, Kariyanakatte Veeraiah; Premalatha, Chennagiri Shrinivasamurthy; Tata, Pramila; Hariharan, Ramesh; Roa, Juan Carlos; Prasad, T.S.K; Chaerkady, Raghothama; Kumar, Rekha Vijay; Pandey, Akhilesh

2015-01-01

Gastric cancer is the second leading cause of cancer death worldwide, both in men and women. A genomewide gene expression analysis was carried out to identify differentially expressed genes in gastric adenocarcinoma tissues as compared to adjacent normal tissues. We used Agilent’s whole human genome oligonucleotide microarray platform representing ~41,000 genes to carry out gene expression analysis. Two-color microarray analysis was employed to directly compare the expression of genes between tumor and normal tissues. Through this approach, we identified several previously known candidate genes along with a number of novel candidate genes in gastric cancer. Testican-1 (SPOCK1) was one of the novel molecules that was 10-fold upregulated in tumors. Using tissue microarrays, we validated the expression of testican-1 by immunohistochemical staining. It was overexpressed in 56% (160/282) of the cases tested. Pathway analysis led to the identification of several networks in which SPOCK1 was among the topmost networks of interacting genes. By gene enrichment analysis, we identified several genes involved in cell adhesion and cell proliferation to be significantly upregulated while those corresponding to metabolic pathways were significantly downregulated. The differentially expressed genes identified in this study are candidate biomarkers for gastric adenoacarcinoma. PMID:27030788

Multi-walled carbon nanotube-induced gene signatures in the mouse lung: potential predictive value for human lung cancer risk and prognosis

PubMed Central

Guo, Nancy L; Wan, Ying-Wooi; Denvir, James; Porter, Dale W; Pacurari, Maricica; Wolfarth, Michael G; Castranova, Vincent; Qian, Yong

2012-01-01

Concerns over the potential for multi-walled carbon nanotubes (MWCNT) to induce lung carcinogenesis have emerged. This study sought to (1) identify gene expression signatures in the mouse lungs following pharyngeal aspiration of well-dispersed MWCNT and (2) determine if these genes were associated with human lung cancer risk and progression. Genome-wide mRNA expression profiles were analyzed in mouse lungs (n=160) exposed to 0, 10, 20, 40, or 80 µg of MWCNT by pharyngeal aspiration at 1, 7, 28, and 56 days post-exposure. By using pairwise-Statistical Analysis of Microarray (SAM) and linear modeling, 24 genes were selected, which have significant changes in at least two time points, have a more than 1.5 fold change at all doses, and are significant in the linear model for the dose or the interaction of time and dose. Additionally, a 38-gene set was identified as related to cancer from 330 genes differentially expressed at day 56 post-exposure in functional pathway analysis. Using the expression profiles of the cancer-related gene set in 8 mice at day 56 post-exposure to 10 µg of MWCNT, a nearest centroid classification accurately predicts human lung cancer survival with a significant hazard ratio in training set (n=256) and test set (n=186). Furthermore, both gene signatures were associated with human lung cancer risk (n=164) with significant odds ratios. These results may lead to development of a surveillance approach for early detection of lung cancer and prognosis associated with MWCNT in the workplace. PMID:22891886

Cervical cancer survival prediction using hybrid of SMOTE, CART and smooth support vector machine

NASA Astrophysics Data System (ADS)

Purnami, S. W.; Khasanah, P. M.; Sumartini, S. H.; Chosuvivatwong, V.; Sriplung, H.

2016-04-01

According to the WHO, every two minutes there is one patient who died from cervical cancer. The high mortality rate is due to the lack of awareness of women for early detection. There are several factors that supposedly influence the survival of cervical cancer patients, including age, anemia status, stage, type of treatment, complications and secondary disease. This study wants to classify/predict cervical cancer survival based on those factors. Various classifications methods: classification and regression tree (CART), smooth support vector machine (SSVM), three order spline SSVM (TSSVM) were used. Since the data of cervical cancer are imbalanced, synthetic minority oversampling technique (SMOTE) is used for handling imbalanced dataset. Performances of these methods are evaluated using accuracy, sensitivity and specificity. Results of this study show that balancing data using SMOTE as preprocessing can improve performance of classification. The SMOTE-SSVM method provided better result than SMOTE-TSSVM and SMOTE-CART.

Clinical application of modified bag-of-features coupled with hybrid neural-based classifier in dengue fever classification using gene expression data.

PubMed

Chatterjee, Sankhadeep; Dey, Nilanjan; Shi, Fuqian; Ashour, Amira S; Fong, Simon James; Sen, Soumya

2018-04-01

Dengue fever detection and classification have a vital role due to the recent outbreaks of different kinds of dengue fever. Recently, the advancement in the microarray technology can be employed for such classification process. Several studies have established that the gene selection phase takes a significant role in the classifier performance. Subsequently, the current study focused on detecting two different variations, namely, dengue fever (DF) and dengue hemorrhagic fever (DHF). A modified bag-of-features method has been proposed to select the most promising genes in the classification process. Afterward, a modified cuckoo search optimization algorithm has been engaged to support the artificial neural (ANN-MCS) to classify the unknown subjects into three different classes namely, DF, DHF, and another class containing convalescent and normal cases. The proposed method has been compared with other three well-known classifiers, namely, multilayer perceptron feed-forward network (MLP-FFN), artificial neural network (ANN) trained with cuckoo search (ANN-CS), and ANN trained with PSO (ANN-PSO). Experiments have been carried out with different number of clusters for the initial bag-of-features-based feature selection phase. After obtaining the reduced dataset, the hybrid ANN-MCS model has been employed for the classification process. The results have been compared in terms of the confusion matrix-based performance measuring metrics. The experimental results indicated a highly statistically significant improvement with the proposed classifier over the traditional ANN-CS model.

Combining multiple decisions: applications to bioinformatics

NASA Astrophysics Data System (ADS)

Yukinawa, N.; Takenouchi, T.; Oba, S.; Ishii, S.

2008-01-01

Multi-class classification is one of the fundamental tasks in bioinformatics and typically arises in cancer diagnosis studies by gene expression profiling. This article reviews two recent approaches to multi-class classification by combining multiple binary classifiers, which are formulated based on a unified framework of error-correcting output coding (ECOC). The first approach is to construct a multi-class classifier in which each binary classifier to be aggregated has a weight value to be optimally tuned based on the observed data. In the second approach, misclassification of each binary classifier is formulated as a bit inversion error with a probabilistic model by making an analogy to the context of information transmission theory. Experimental studies using various real-world datasets including cancer classification problems reveal that both of the new methods are superior or comparable to other multi-class classification methods.

Cell-surface marker discovery for lung cancer

PubMed Central

Cohen, Allison S.; Khalil, Farah K.; Welsh, Eric A.; Schabath, Matthew B.; Enkemann, Steven A.; Davis, Andrea; Zhou, Jun-Min; Boulware, David C.; Kim, Jongphil; Haura, Eric B.; Morse, David L.

2017-01-01

Lung cancer is the leading cause of cancer deaths in the United States. Novel lung cancer targeted therapeutic and molecular imaging agents are needed to improve outcomes and enable personalized care. Since these agents typically cannot cross the plasma membrane while carrying cytotoxic payload or imaging contrast, discovery of cell-surface targets is a necessary initial step. Herein, we report the discovery and characterization of lung cancer cell-surface markers for use in development of targeted agents. To identify putative cell-surface markers, existing microarray gene expression data from patient specimens were analyzed to select markers with differential expression in lung cancer compared to normal lung. Greater than 200 putative cell-surface markers were identified as being overexpressed in lung cancers. Ten cell-surface markers (CA9, CA12, CXorf61, DSG3, FAT2, GPR87, KISS1R, LYPD3, SLC7A11 and TMPRSS4) were selected based on differential mRNA expression in lung tumors vs. non-neoplastic lung samples and other normal tissues, and other considerations involving known biology and targeting moieties. Protein expression was confirmed by immunohistochemistry (IHC) staining and scoring of patient tumor and normal tissue samples. As further validation, marker expression was determined in lung cancer cell lines using microarray data and Kaplan–Meier survival analyses were performed for each of the markers using patient clinical data. High expression for six of the markers (CA9, CA12, CXorf61, GPR87, LYPD3, and SLC7A11) was significantly associated with worse survival. These markers should be useful for the development of novel targeted imaging probes or therapeutics for use in personalized care of lung cancer patients. PMID:29371917

An Optimization-Driven Analysis Pipeline to Uncover Biomarkers and Signaling Paths: Cervix Cancer.

PubMed

Lorenzo, Enery; Camacho-Caceres, Katia; Ropelewski, Alexander J; Rosas, Juan; Ortiz-Mojer, Michael; Perez-Marty, Lynn; Irizarry, Juan; Gonzalez, Valerie; Rodríguez, Jesús A; Cabrera-Rios, Mauricio; Isaza, Clara

2015-06-01

Establishing how a series of potentially important genes might relate to each other is relevant to understand the origin and evolution of illnesses, such as cancer. High-throughput biological experiments have played a critical role in providing information in this regard. A special challenge, however, is that of trying to conciliate information from separate microarray experiments to build a potential genetic signaling path. This work proposes a two-step analysis pipeline, based on optimization, to approach meta-analysis aiming to build a proxy for a genetic signaling path.

Alteration of gene expression and DNA methylation in drug-resistant gastric cancer.

PubMed

Maeda, Osamu; Ando, Takafumi; Ohmiya, Naoki; Ishiguro, Kazuhiro; Watanabe, Osamu; Miyahara, Ryoji; Hibi, Yoko; Nagai, Taku; Yamada, Kiyofumi; Goto, Hidemi

2014-04-01

The mechanisms of drug resistance in cancer are not fully elucidated. To study the drug resistance of gastric cancer, we analyzed gene expression and DNA methylation profiles of 5-fluorouracil (5-FU)- and cisplatin (CDDP)-resistant gastric cancer cells and biopsy specimens. Drug-resistant gastric cancer cells were established with culture for >10 months in a medium containing 5-FU or CDDP. Endoscopic biopsy specimens were obtained from gastric cancer patients who underwent chemotherapy with oral fluoropyrimidine S-1 and CDDP. Gene expression and DNA methylation analyses were performed using microarray, and validated using real-time PCR and pyrosequencing, respectively. Out of 17,933 genes, 541 genes commonly increased and 569 genes decreased in both 5-FU- and CDDP-resistant AGS cells. Genes with expression changed by drugs were related to GO term 'extracellular region' and 'p53 signaling pathway' in both 5-FU- and CDDP-treated cells. Expression of 15 genes including KLK13 increased and 12 genes including ETV7 decreased, in both drug-resistant cells and biopsy specimens of two patients after chemotherapy. Out of 10,365 genes evaluated with both expression microarray and methylation microarray, 74 genes were hypermethylated and downregulated, or hypomethylated and upregulated in either 5-FU-resistant or CDDP-resistant cells. Of these genes, expression of 21 genes including FSCN1, CPT1C and NOTCH3, increased from treatment with a demethylating agent. There are alterations of gene expression and DNA methylation in drug-resistant gastric cancer; they may be related to mechanisms of drug resistance and may be useful as biomarkers of gastric cancer drug sensitivity.

Cancer of the esophagus and esophagogastric junction: data-driven staging for the seventh edition of the American Joint Committee on Cancer/International Union Against Cancer Cancer Staging Manuals.

PubMed

Rice, Thomas W; Rusch, Valerie W; Ishwaran, Hemant; Blackstone, Eugene H

2010-08-15

Previous American Joint Committee on Cancer/International Union Against Cancer (AJCC/UICC) stage groupings for esophageal cancer have not been data driven or harmonized with stomach cancer. At the request of the AJCC, worldwide data from 3 continents were assembled to develop data-driven, harmonized esophageal staging for the seventh edition of the AJCC/UICC cancer staging manuals. All-cause mortality among 4627 patients with esophageal and esophagogastric junction cancer who underwent surgery alone (no preoperative or postoperative adjuvant therapy) was analyzed by using novel random forest methodology to produce stage groups for which survival was monotonically decreasing, distinctive, and homogeneous. For lymph node-negative pN0M0 cancers, risk-adjusted 5-year survival was dominated by pathologic tumor classification (pT) but was modulated by histopathologic cell type, histologic grade, and location. For lymph node-positive, pN+M0 cancers, the number of cancer-positive lymph nodes (a new pN classification) dominated survival. Resulting stage groupings departed from a simple, logical arrangement of TNM. Stage groupings for stage I and II adenocarcinoma were based on pT, pN, and histologic grade; and groupings for squamous cell carcinoma were based on pT, pN, histologic grade, and location. Stage III was similar for histopathologic cell types and was based only on pT and pN. Stage 0 and stage IV, by definition, were categorized as tumor in situ (Tis) (high-grade dysplasia) and pM1, respectively. The prognosis for patients with esophageal and esophagogastric junction cancer depends on the complex interplay of TNM classifications as well as nonanatomic factors, including histopathologic cell type, histologic grade, and cancer location. These features were incorporated into a data-driven staging of these cancers for the seventh edition of the AJCC/UICC cancer staging manuals. Copyright (c) 2010 American Cancer Society.

Apparently low reproducibility of true differential expression discoveries in microarray studies.

PubMed

Zhang, Min; Yao, Chen; Guo, Zheng; Zou, Jinfeng; Zhang, Lin; Xiao, Hui; Wang, Dong; Yang, Da; Gong, Xue; Zhu, Jing; Li, Yanhui; Li, Xia

2008-09-15

Differentially expressed gene (DEG) lists detected from different microarray studies for a same disease are often highly inconsistent. Even in technical replicate tests using identical samples, DEG detection still shows very low reproducibility. It is often believed that current small microarray studies will largely introduce false discoveries. Based on a statistical model, we show that even in technical replicate tests using identical samples, it is highly likely that the selected DEG lists will be very inconsistent in the presence of small measurement variations. Therefore, the apparently low reproducibility of DEG detection from current technical replicate tests does not indicate low quality of microarray technology. We also demonstrate that heterogeneous biological variations existing in real cancer data will further reduce the overall reproducibility of DEG detection. Nevertheless, in small subsamples from both simulated and real data, the actual false discovery rate (FDR) for each DEG list tends to be low, suggesting that each separately determined list may comprise mostly true DEGs. Rather than simply counting the overlaps of the discovery lists from different studies for a complex disease, novel metrics are needed for evaluating the reproducibility of discoveries characterized with correlated molecular changes. Supplementaty information: Supplementary data are available at Bioinformatics online.

Computer-aided detection of early cancer in the esophagus using HD endoscopy images

NASA Astrophysics Data System (ADS)

van der Sommen, Fons; Zinger, Svitlana; Schoon, Erik J.; de With, Peter H. N.

2013-02-01

Esophageal cancer is the fastest rising type of cancer in the Western world. The recent development of High-Definition (HD) endoscopy has enabled the specialist physician to identify cancer at an early stage. Nevertheless, it still requires considerable effort and training to be able to recognize these irregularities associated with early cancer. As a first step towards a Computer-Aided Detection (CAD) system that supports the physician in finding these early stages of cancer, we propose an algorithm that is able to identify irregularities in the esophagus automatically, based on HD endoscopic images. The concept employs tile-based processing, so our system is not only able to identify that an endoscopic image contains early cancer, but it can also locate it. The identification is based on the following steps: (1) preprocessing, (2) feature extraction with dimensionality reduction, (3) classification. We evaluate the detection performance in RGB, HSI and YCbCr color space using the Color Histogram (CH) and Gabor features and we compare with other well-known features to describe texture. For classification, we employ a Support Vector Machine (SVM) and evaluate its performance using different parameters and kernel functions. In experiments, our system achieves a classification accuracy of 95.9% on 50×50 pixel tiles of tumorous and normal tissue and reaches an Area Under the Curve (AUC) of 0.990. In 22 clinical examples our algorithm was able to identify all (pre-)cancerous regions and annotate those regions reasonably well. The experimental and clinical validation are considered promising for a CAD system that supports the physician in finding early stage cancer.

MicroRNA-integrated and network-embedded gene selection with diffusion distance.

PubMed

Huang, Di; Zhou, Xiaobo; Lyon, Christopher J; Hsueh, Willa A; Wong, Stephen T C

2010-10-29

Gene network information has been used to improve gene selection in microarray-based studies by selecting marker genes based both on their expression and the coordinate expression of genes within their gene network under a given condition. Here we propose a new network-embedded gene selection model. In this model, we first address the limitations of microarray data. Microarray data, although widely used for gene selection, measures only mRNA abundance, which does not always reflect the ultimate gene phenotype, since it does not account for post-transcriptional effects. To overcome this important (critical in certain cases) but ignored-in-almost-all-existing-studies limitation, we design a new strategy to integrate together microarray data with the information of microRNA, the major post-transcriptional regulatory factor. We also handle the challenges led by gene collaboration mechanism. To incorporate the biological facts that genes without direct interactions may work closely due to signal transduction and that two genes may be functionally connected through multi paths, we adopt the concept of diffusion distance. This concept permits us to simulate biological signal propagation and therefore to estimate the collaboration probability for all gene pairs, directly or indirectly-connected, according to multi paths connecting them. We demonstrate, using type 2 diabetes (DM2) as an example, that the proposed strategies can enhance the identification of functional gene partners, which is the key issue in a network-embedded gene selection model. More importantly, we show that our gene selection model outperforms related ones. Genes selected by our model 1) have improved classification capability; 2) agree with biological evidence of DM2-association; and 3) are involved in many well-known DM2-associated pathways.

Perspectives on current tumor-node-metastasis (TNM) staging of cancers of the colon and rectum.

PubMed

Hu, Huankai; Krasinskas, Alyssa; Willis, Joseph

2011-08-01

Improvements in classifications of cancers based on discovery and validation of important histopathological parameters and new molecular markers continue unabated. Though still not perfect, recent updates of classification schemes in gastrointestinal oncology by the American Joint Commission on Cancer (tumor-node-metastasis [TNM] staging) and the World Health Organization further stratify patients and guide optimization of treatment strategies and better predict patient outcomes. These updates recognize the heterogeneity of patient populations with significant subgrouping of each tumor stage and use of tumor deposits to significantly "up-stage" some cancers; change staging parameters for subsets of IIIB and IIIC cancers; and introduce of several new subtypes of colon carcinomas. By the nature of the process, recent discoveries that are important to improving even routine standards of patient care, especially new advances in molecular medicine, are not incorporated into these systems. Nonetheless, these classifications significantly advance clinical standards and are welcome enhancements to our current methods of cancer reporting. Copyright © 2011 Elsevier Inc. All rights reserved.

Entropy-based gene ranking without selection bias for the predictive classification of microarray data.

PubMed

Furlanello, Cesare; Serafini, Maria; Merler, Stefano; Jurman, Giuseppe

2003-11-06

We describe the E-RFE method for gene ranking, which is useful for the identification of markers in the predictive classification of array data. The method supports a practical modeling scheme designed to avoid the construction of classification rules based on the selection of too small gene subsets (an effect known as the selection bias, in which the estimated predictive errors are too optimistic due to testing on samples already considered in the feature selection process). With E-RFE, we speed up the recursive feature elimination (RFE) with SVM classifiers by eliminating chunks of uninteresting genes using an entropy measure of the SVM weights distribution. An optimal subset of genes is selected according to a two-strata model evaluation procedure: modeling is replicated by an external stratified-partition resampling scheme, and, within each run, an internal K-fold cross-validation is used for E-RFE ranking. Also, the optimal number of genes can be estimated according to the saturation of Zipf's law profiles. Without a decrease of classification accuracy, E-RFE allows a speed-up factor of 100 with respect to standard RFE, while improving on alternative parametric RFE reduction strategies. Thus, a process for gene selection and error estimation is made practical, ensuring control of the selection bias, and providing additional diagnostic indicators of gene importance.

Development and potential applications of microarrays based on fluorescent nanocrystal-encoded beads for multiplexed cancer diagnostics

NASA Astrophysics Data System (ADS)

Brazhnik, Kristina; Grinevich, Regina; Efimov, Anton E.; Nabiev, Igor; Sukhanova, Alyona

2014-05-01

Advanced multiplexed assays have recently become an indispensable tool for clinical diagnostics. These techniques provide simultaneous quantitative determination of multiple biomolecules in a single sample quickly and accurately. The development of multiplex suspension arrays is currently of particular interest for clinical applications. Optical encoding of microparticles is the most available and easy-to-use technique. This technology uses fluorophores incorporated into microbeads to obtain individual optical codes. Fluorophore-encoded beads can be rapidly analyzed using classical flow cytometry or microfluidic techniques. We have developed a new generation of highly sensitive and specific diagnostic systems for detection of cancer antigens in human serum samples based on microbeads encoded with fluorescent quantum dots (QDs). The designed suspension microarray system was validated for quantitative detection of (1) free and total prostate specific antigen (PSA) in the serum of patients with prostate cancer and (2) carcinoembryonic antigen (CEA) and cancer antigen 15-3 (CA 15-3) in the serum of patients with breast cancer. The serum samples from healthy donors were used as a control. The antigen detection is based on the formation of an immune complex of a specific capture antibody (Ab), a target antigen (Ag), and a detector Ab on the surface of the encoded particles. The capture Ab is bound to the polymer shell of microbeads via an adapter molecule, for example, protein A. Protein A binds a monoclonal Ab in a highly oriented manner due to specific interaction with the Fc-region of the Ab molecule. Each antigen can be recognized and detected due to a specific microbead population carrying the unique fluorescent code. 100 and 231 serum samples from patients with different stages of prostate cancer and breast cancer, respectively, and those from healthy donors were examined using the designed suspension system. The data were validated by comparing with the results of the "gold standard" enzyme-linked immunosorbent assay (ELISA). They have shown that our approach is a good alternative to the diagnostics of cancer markers using conventional assays, especially in early diagnostic applications.

Identification of novel and known oocyte-specific genes using complementary DNA subtraction and microarray analysis in three different species.

PubMed

Vallée, Maud; Gravel, Catherine; Palin, Marie-France; Reghenas, Hélène; Stothard, Paul; Wishart, David S; Sirard, Marc-André

2005-07-01

The main objective of the present study was to identify novel oocyte-specific genes in three different species: bovine, mouse, and Xenopus laevis. To achieve this goal, two powerful technologies were combined: a polymerase chain reaction (PCR)-based cDNA subtraction, and cDNA microarrays. Three subtractive libraries consisting of 3456 clones were established and enriched for oocyte-specific transcripts. Sequencing analysis of the positive insert-containing clones resulted in the following classification: 53% of the clones corresponded to known cDNAs, 26% were classified as uncharacterized cDNAs, and a final 9% were classified as novel sequences. All these clones were used for cDNA microarray preparation. Results from these microarray analyses revealed that in addition to already known oocyte-specific genes, such as GDF9, BMP15, and ZP, known genes with unknown function in the oocyte were identified, such as a MLF1-interacting protein (MLF1IP), B-cell translocation gene 4 (BTG4), and phosphotyrosine-binding protein (xPTB). Furthermore, 15 novel oocyte-specific genes were validated by reverse transcription-PCR to confirm their preferential expression in the oocyte compared to somatic tissues. The results obtained in the present study confirmed that microarray analysis is a robust technique to identify true positives from the suppressive subtractive hybridization experiment. Furthermore, obtaining oocyte-specific genes from three species simultaneously allowed us to look at important genes that are conserved across species. Further characterization of these novel oocyte-specific genes will lead to a better understanding of the molecular mechanisms related to the unique functions found in the oocyte.

Towards the integration, annotation and association of historical microarray experiments with RNA-seq.

PubMed

Chavan, Shweta S; Bauer, Michael A; Peterson, Erich A; Heuck, Christoph J; Johann, Donald J

2013-01-01

Transcriptome analysis by microarrays has produced important advances in biomedicine. For instance in multiple myeloma (MM), microarray approaches led to the development of an effective disease subtyping via cluster assignment, and a 70 gene risk score. Both enabled an improved molecular understanding of MM, and have provided prognostic information for the purposes of clinical management. Many researchers are now transitioning to Next Generation Sequencing (NGS) approaches and RNA-seq in particular, due to its discovery-based nature, improved sensitivity, and dynamic range. Additionally, RNA-seq allows for the analysis of gene isoforms, splice variants, and novel gene fusions. Given the voluminous amounts of historical microarray data, there is now a need to associate and integrate microarray and RNA-seq data via advanced bioinformatic approaches. Custom software was developed following a model-view-controller (MVC) approach to integrate Affymetrix probe set-IDs, and gene annotation information from a variety of sources. The tool/approach employs an assortment of strategies to integrate, cross reference, and associate microarray and RNA-seq datasets. Output from a variety of transcriptome reconstruction and quantitation tools (e.g., Cufflinks) can be directly integrated, and/or associated with Affymetrix probe set data, as well as necessary gene identifiers and/or symbols from a diversity of sources. Strategies are employed to maximize the annotation and cross referencing process. Custom gene sets (e.g., MM 70 risk score (GEP-70)) can be specified, and the tool can be directly assimilated into an RNA-seq pipeline. A novel bioinformatic approach to aid in the facilitation of both annotation and association of historic microarray data, in conjunction with richer RNA-seq data, is now assisting with the study of MM cancer biology.

Histological, molecular and functional subtypes of breast cancers

PubMed Central

Malhotra, Gautam K; Zhao, Xiangshan; Band, Hamid

2010-01-01

Increased understanding of the molecular heterogeneity that is intrinsic to the various subtypes of breast cancer will likely shape the future of breast cancer diagnosis, prognosis and treatment. Advances in the field over the last several decades have been remarkable and have clearly translated into better patient care as evidenced by the earlier detection, better prognosis and new targeted therapies. There have been two recent advances in the breast cancer research field that have lead to paradigm shifts: first, the identification of intrinsic breast tumor subtypes, which has changed the way we think about breast cancer and second, the recent characterization of cancer stem cells (CSCs), which are suspected to be responsible for tumor initiation, recurrence and resistance to therapy. These findings have opened new exciting avenues to think about breast cancer therapeutic strategies. While these advances constitute major paradigm shifts within the research realm, the clinical arena has yet to adopt and apply our understanding of the molecular basis of the disease to early diagnosis, prognosis and therapy of breast cancers. Here, we will review the current clinical approach to classification of breast cancers, newer molecular-based classification schemes and potential future of biomarkers representing a functional classification of breast cancer. PMID:21057215

Circular RNA Expression Profile of Pancreatic Ductal Adenocarcinoma Revealed by Microarray.

PubMed

Li, Haimin; Hao, Xiaokun; Wang, Huimin; Liu, Zhengcai; He, Yong; Pu, Meng; Zhang, Hongtao; Yu, Hengchao; Duan, Juanli; Qu, Shibin

2016-01-01

Circular RNAs (circRNAs) are a special novel type of a stable, diverse and conserved noncoding RNA in mammalian cells. Particularly in cancer, circRNAs have been reported to be widely involved in the physiological/pathological process of life. However, it is unclear whether circRNAs are specifically involved in pancreatic ductal adenocarcinoma (PDAC). We investigated the expression profile of circRNAs in six PDAC cancer samples and paired adjacent normal tissues using microarray. A high-throughput circRNA microarray was used to identify dysregulated circular RNAs in six PDAC patients. Bioinformatic analyses were applied to study these differentially expressed circRNAs. Furthermore, quantitative reverse transcription polymerase chain reaction (qRT-PCR) was performed to confirm these results. We revealed and confirmed that a number of circRNAs were dysregulated, which suggests a potential role in pancreatic cancer. this study demonstrates that clusters of circRNAs are aberrantly expressed in PDAC compared with normal samples and provides new potential targets for the future treatment of PDAC and novel insights into PDAC biology. © 2016 The Author(s) Published by S. Karger AG, Basel.

Association between gastric cancer and the Kyoto classification of gastritis.

PubMed

Shichijo, Satoki; Hirata, Yoshihiro; Niikura, Ryota; Hayakawa, Yoku; Yamada, Atsuo; Koike, Kazuhiko

2017-09-01

Histological gastritis is associated with gastric cancer, but its diagnosis requires biopsy. Many classifications of endoscopic gastritis are available, but not all are useful for risk stratification of gastric cancer. The Kyoto Classification of Gastritis was proposed at the 85th Congress of the Japan Gastroenterological Endoscopy Society. This cross-sectional study evaluated the usefulness of the Kyoto Classification of Gastritis for risk stratification of gastric cancer. From August 2013 to September 2014, esophagogastroduodenoscopy was performed and the gastric findings evaluated according to the Kyoto Classification of Gastritis in a total of 4062 patients. The following five endoscopic findings were selected based on previous reports: atrophy, intestinal metaplasia, enlarged folds, nodularity, and diffuse redness. A total of 3392 patients (1746 [51%] men and 1646 [49%] women) were analyzed. Among them, 107 gastric cancers were diagnosed. Atrophy was found in 2585 (78%) and intestinal metaplasia in 924 (27%). Enlarged folds, nodularity, and diffuse redness were found in 197 (5.8%), 22 (0.6%), and 573 (17%), respectively. In univariate analyses, the severity of atrophy, intestinal metaplasia, diffuse redness, age, and male sex were associated with gastric cancer. In a multivariate analysis, atrophy and male sex were found to be independent risk factors. Younger age and severe atrophy were determined to be associated with diffuse-type gastric cancer. Endoscopic detection of atrophy was associated with the risk of gastric cancer. Thus, patients with severe atrophy should be examined carefully and may require intensive follow-up. © 2017 Journal of Gastroenterology and Hepatology Foundation and John Wiley & Sons Australia, Ltd.

Cell type classifiers for breast cancer microscopic images based on fractal dimension texture analysis of image color layers.

PubMed

Jitaree, Sirinapa; Phinyomark, Angkoon; Boonyaphiphat, Pleumjit; Phukpattaranont, Pornchai

2015-01-01

Having a classifier of cell types in a breast cancer microscopic image (BCMI), obtained with immunohistochemical staining, is required as part of a computer-aided system that counts the cancer cells in such BCMI. Such quantitation by cell counting is very useful in supporting decisions and planning of the medical treatment of breast cancer. This study proposes and evaluates features based on texture analysis by fractal dimension (FD), for the classification of histological structures in a BCMI into either cancer cells or non-cancer cells. The cancer cells include positive cells (PC) and negative cells (NC), while the normal cells comprise stromal cells (SC) and lymphocyte cells (LC). The FD feature values were calculated with the box-counting method from binarized images, obtained by automatic thresholding with Otsu's method of the grayscale images for various color channels. A total of 12 color channels from four color spaces (RGB, CIE-L*a*b*, HSV, and YCbCr) were investigated, and the FD feature values from them were used with decision tree classifiers. The BCMI data consisted of 1,400, 1,200, and 800 images with pixel resolutions 128 × 128, 192 × 192, and 256 × 256, respectively. The best cross-validated classification accuracy was 93.87%, for distinguishing between cancer and non-cancer cells, obtained using the Cr color channel with window size 256. The results indicate that the proposed algorithm, based on fractal dimension features extracted from a color channel, performs well in the automatic classification of the histology in a BCMI. This might support accurate automatic cell counting in a computer-assisted system for breast cancer diagnosis. © Wiley Periodicals, Inc.

Thermogram breast cancer prediction approach based on Neutrosophic sets and fuzzy c-means algorithm.

PubMed

Gaber, Tarek; Ismail, Gehad; Anter, Ahmed; Soliman, Mona; Ali, Mona; Semary, Noura; Hassanien, Aboul Ella; Snasel, Vaclav

2015-08-01

The early detection of breast cancer makes many women survive. In this paper, a CAD system classifying breast cancer thermograms to normal and abnormal is proposed. This approach consists of two main phases: automatic segmentation and classification. For the former phase, an improved segmentation approach based on both Neutrosophic sets (NS) and optimized Fast Fuzzy c-mean (F-FCM) algorithm was proposed. Also, post-segmentation process was suggested to segment breast parenchyma (i.e. ROI) from thermogram images. For the classification, different kernel functions of the Support Vector Machine (SVM) were used to classify breast parenchyma into normal or abnormal cases. Using benchmark database, the proposed CAD system was evaluated based on precision, recall, and accuracy as well as a comparison with related work. The experimental results showed that our system would be a very promising step toward automatic diagnosis of breast cancer using thermograms as the accuracy reached 100%.

Chilean Gastric Cancer Task Force

PubMed Central

Owen, Gareth I.; Pinto, Mauricio P.; Retamal, Ignacio N.; Fernádez, María F.; Cisternas, Betzabe; Mondaca, Sebastian; Sanchez, Cesar; Galindo, Hector; Nervi, Bruno; Ibañez, Carolina; Acevedo, Francisco; Madrid, Jorge; Peña, José; Bravo, Maria Loreto; Maturana, Maria Jose; Cordova-Delgado, Miguel; Romero, Diego; de la Jara, Nathaly; Torres, Javiera; Rodriguez-Fernandez, Maria; Espinoza, Manuel; Balmaceda, Carlos; Freire, Matías; Gárate-Calderón, Valentina; Crovari, Fernando; Jimenez-Fonseca, Paula; Carmona-Bayonas, Alberto; Zwenger, Ariel; Armisen, Ricardo; Corvalan, Alejandro H.; Garrido, Marcelo

2018-01-01

Abstract Gastric cancer (GC) is the world's second-leading cause of neoplastic mortality. Genetic alterations, response to treatments, and mortality rates are highly heterogeneous across different regions. Within Latin America, GC is the leading cause of cancer death in Chile, affecting 17.6 per 100,000 people and causing >3000 deaths/y. Clinical outcomes and response to “one size fits all” therapies are highly heterogeneous and thus a better stratification of patients may aid cancer treatment and response. The Gastric Cancer Task Force is a Chilean collaborative, noninterventional study that seeks to stratify gastric adenocarcinomas using clinical outcomes and genomic, epigenomic, and protein alterations in a cohort of 200 patients. Tumor samples from the Pathology Department and the Cancer Center at UC-Christus healthcare network, Pontificia Universidad Católica de Chile will be analyzed using a panel of 143 known cancer genes (Oncomine Comprehensive Assay) at the Center of Excellence in Precision Medicine in Santiago, Chile. In addition, promoter methylation for selected genes will be performed along with tissue microarray for clinically relevant proteins (e.g., PD-L1, Erb-2, VEGFR2, among others) and Helicobacter pylori and Epstein–Barr virus status. Obtained data will be correlated to 120 clinical parameters retrieve from medical records, including general patient information, cancer history, laboratory studies, comorbidity index, chemotherapy, targeted therapies, efficacy, and follow-up. The development of a clinically meaningful classification that encompasses comprehensive clinical and molecular parameters may improve patient treatment, predict clinical outcomes, aid patient selection/stratification for clinical trials and may offer insights into future preventive and/or therapeutic strategies in patients from Latin America region. Trial registration: ClinicalTrials.gov Identifier: NCT03158571, Registered on May 18, 2017. PMID:29668600

A new locally weighted K-means for cancer-aided microarray data analysis.

PubMed

Iam-On, Natthakan; Boongoen, Tossapon

2012-11-01

Cancer has been identified as the leading cause of death. It is predicted that around 20-26 million people will be diagnosed with cancer by 2020. With this alarming rate, there is an urgent need for a more effective methodology to understand, prevent and cure cancer. Microarray technology provides a useful basis of achieving this goal, with cluster analysis of gene expression data leading to the discrimination of patients, identification of possible tumor subtypes and individualized treatment. Amongst clustering techniques, k-means is normally chosen for its simplicity and efficiency. However, it does not account for the different importance of data attributes. This paper presents a new locally weighted extension of k-means, which has proven more accurate across many published datasets than the original and other extensions found in the literature.

NRF2-regulated metabolic gene signature as a prognostic biomarker in non-small cell lung cancer

PubMed Central

Namani, Akhileshwar; Cui, Qin Qin; Wu, Yihe; Wang, Hongyan; Wang, Xiu Jun; Tang, Xiuwen

2017-01-01

Mutations in Kelch-like ECH-associated protein 1 (KEAP1) cause the aberrant activation of nuclear factor erythroid-derived 2-like 2 (NRF2), which leads to oncogenesis and drug resistance in lung cancer cells. Our study was designed to identify the genes involved in lung cancer progression targeted by NRF2. A series of microarray experiments in normal and cancer cells, as well as in animal models, have revealed regulatory genes downstream of NRF2 that are involved in wide variety of pathways. Specifically, we carried out individual and combinatorial microarray analysis of KEAP1 overexpression and NRF2 siRNA-knockdown in a KEAP1 mutant-A549 non-small cell lung cancer (NSCLC) cell line. As a result, we identified a list of genes which were mainly involved in metabolic functions in NSCLC by using functional annotation analysis. In addition, we carried out in silico analysis to characterize the antioxidant responsive element sequences in the promoter regions of known and putative NRF2-regulated metabolic genes. We further identified an NRF2-regulated metabolic gene signature (NRMGS) by correlating the microarray data with lung adenocarcinoma RNA-Seq gene expression data from The Cancer Genome Atlas followed by qRT-PCR validation, and finally showed that higher expression of the signature conferred a poor prognosis in 8 independent NSCLC cohorts. Our findings provide novel prognostic biomarkers for NSCLC. PMID:29050246

Identification of Differentially Expressed IGFBP5-Related Genes in Breast Cancer Tumor Tissues Using cDNA Microarray Experiments.

PubMed

Akkiprik, Mustafa; Peker, İrem; Özmen, Tolga; Amuran, Gökçe Güllü; Güllüoğlu, Bahadır M; Kaya, Handan; Özer, Ayşe

2015-11-10

IGFBP5 is an important regulatory protein in breast cancer progression. We tried to identify differentially expressed genes (DEGs) between breast tumor tissues with IGFBP5 overexpression and their adjacent normal tissues. In this study, thirty-eight breast cancer and adjacent normal breast tissue samples were used to determine IGFBP5 expression by qPCR. cDNA microarrays were applied to the highest IGFBP5 overexpressed tumor samples compared to their adjacent normal breast tissue. Microarray analysis revealed that a total of 186 genes were differentially expressed in breast cancer compared with normal breast tissues. Of the 186 genes, 169 genes were downregulated and 17 genes were upregulated in the tumor samples. KEGG pathway analyses showed that protein digestion and absorption, focal adhesion, salivary secretion, drug metabolism-cytochrome P450, and phenylalanine metabolism pathways are involved. Among these DEGs, the prominent top two genes (MMP11 and COL1A1) which potentially correlated with IGFBP5 were selected for validation using real time RT-qPCR. Only COL1A1 expression showed a consistent upregulation with IGFBP5 expression and COL1A1 and MMP11 were significantly positively correlated. We concluded that the discovery of coordinately expressed genes related with IGFBP5 might contribute to understanding of the molecular mechanism of the function of IGFBP5 in breast cancer. Further functional studies on DEGs and association with IGFBP5 may identify novel biomarkers for clinical applications in breast cancer.

Dual-modal cancer detection based on optical pH sensing and Raman spectroscopy

NASA Astrophysics Data System (ADS)

Kim, Soogeun; Lee, Seung Ho; Min, Sun Young; Byun, Kyung Min; Lee, Soo Yeol

2017-10-01

A dual-modal approach using Raman spectroscopy and optical pH sensing was investigated to discriminate between normal and cancerous tissues. Raman spectroscopy has demonstrated the potential for in vivo cancer detection. However, Raman spectroscopy has suffered from strong fluorescence background of biological samples and subtle spectral differences between normal and disease tissues. To overcome those issues, pH sensing is adopted to Raman spectroscopy as a dual-modal approach. Based on the fact that the pH level in cancerous tissues is lower than that in normal tissues due to insufficient vasculature formation, the dual-modal approach combining the chemical information of Raman spectrum and the metabolic information of pH level can improve the specificity of cancer diagnosis. From human breast tissue samples, Raman spectra and pH levels are measured using fiber-optic-based Raman and pH probes, respectively. The pH sensing is based on the dependence of pH level on optical transmission spectrum. Multivariate statistical analysis is performed to evaluate the classification capability of the dual-modal method. The analytical results show that the dual-modal method based on Raman spectroscopy and optical pH sensing can improve the performance of cancer classification.

Evaluation of a Web-Based App Demonstrating an Exclusionary Algorithmic Approach to TNM Cancer Staging

PubMed Central

2015-01-01

Background TNM staging plays a critical role in the evaluation and management of a range of different types of cancers. The conventional combinatorial approach to the determination of an anatomic stage relies on the identification of distinct tumor (T), node (N), and metastasis (M) classifications to generate a TNM grouping. This process is inherently inefficient due to the need for scrupulous review of the criteria specified for each classification to ensure accurate assignment. An exclusionary approach to TNM staging based on sequential constraint of options may serve to minimize the number of classifications that need to be reviewed to accurately determine an anatomic stage. Objective Our aim was to evaluate the usability and utility of a Web-based app configured to demonstrate an exclusionary approach to TNM staging. Methods Internal medicine residents, surgery residents, and oncology fellows engaged in clinical training were asked to evaluate a Web-based app developed as an instructional aid incorporating (1) an exclusionary algorithm that polls tabulated classifications and sorts them into ranked order based on frequency counts, (2) reconfiguration of classification criteria to generate disambiguated yes/no questions that function as selection and exclusion prompts, and (3) a selectable grid of TNM groupings that provides dynamic graphic demonstration of the effects of sequentially selecting or excluding specific classifications. Subjects were asked to evaluate the performance of this app after completing exercises simulating the staging of different types of cancers encountered during training. Results Survey responses indicated high levels of agreement with statements supporting the usability and utility of this app. Subjects reported that its user interface provided a clear display with intuitive controls and that the exclusionary approach to TNM staging it demonstrated represented an efficient process of assignment that helped to clarify distinctions between tumor, node, and metastasis classifications. High overall usefulness ratings were bolstered by supplementary comments suggesting that this app might be readily adopted for use in clinical practice. Conclusions A Web-based app that utilizes an exclusionary algorithm to prompt the assignment of tumor, node, and metastasis classifications may serve as an effective instructional aid demonstrating an efficient and informative approach to TNM staging. PMID:28410163

A review on data mining and continuous optimization applications in computational biology and medicine.

PubMed

Weber, Gerhard-Wilhelm; Ozöğür-Akyüz, Süreyya; Kropat, Erik

2009-06-01

An emerging research area in computational biology and biotechnology is devoted to mathematical modeling and prediction of gene-expression patterns; it nowadays requests mathematics to deeply understand its foundations. This article surveys data mining and machine learning methods for an analysis of complex systems in computational biology. It mathematically deepens recent advances in modeling and prediction by rigorously introducing the environment and aspects of errors and uncertainty into the genetic context within the framework of matrix and interval arithmetics. Given the data from DNA microarray experiments and environmental measurements, we extract nonlinear ordinary differential equations which contain parameters that are to be determined. This is done by a generalized Chebychev approximation and generalized semi-infinite optimization. Then, time-discretized dynamical systems are studied. By a combinatorial algorithm which constructs and follows polyhedra sequences, the region of parametric stability is detected. In addition, we analyze the topological landscape of gene-environment networks in terms of structural stability. As a second strategy, we will review recent model selection and kernel learning methods for binary classification which can be used to classify microarray data for cancerous cells or for discrimination of other kind of diseases. This review is practically motivated and theoretically elaborated; it is devoted to a contribution to better health care, progress in medicine, a better education, and more healthy living conditions.

New Image-Based Techniques for Prostate Biopsy and Treatment

DTIC Science & Technology

2012-04-01

C-arm fluoroscopy, MICCAI 2011, Toronto, Canada, 2011. 4) Poster Presentation: Prostate Cancer Probability Estimation Based on DCE- DTI Features...and P. Kozlowski, “Prostate Cancer Probability Estimation Based on DCE- DTI Features and Support Vector Machine Classification,” Annual Meeting of... DTI ), which characterize the de-phasing of the MR signal caused by molecular diffusion. Prostate cancer causes a pathological change in the tissue

Identifying Nursing Interventions in a Cancer Screening Program Using Nursing Interventions Classification Taxonomy.

PubMed

Benito, Llucia; Lluch, María Teresa; Falcó, Anna Marta; García, Montse; Puig, Montse

2017-04-01

This study aimed to investigate which Nursing Interventions Classification (NIC) labels correspond to specific nursing interventions provided during cancer screening to establish a nursing documentation system. This descriptive study was conducted to identify and classify the interventions that cancer screening nurses perform based on an initial list. The initial list was grouped into 15 interventions that corresponded to four domains and eight classes. The study found expert consensus regarding the duties of cancer screening nurses and identified 15 interventions that should be implemented in clinical practice for cancer screening care, according to the NIC taxonomy. This study is the first step in developing indicators to assess nursing performance in cancer screening, and it helps to establish the core competency requirements for cancer screening nurses. © 2015 NANDA International, Inc.

Fluorescent marker-based and marker-free discrimination between healthy and cancerous human tissues using hyper-spectral imaging

NASA Astrophysics Data System (ADS)

Arnold, Thomas; De Biasio, Martin; Leitner, Raimund

2015-06-01

Two problems are addressed in this paper (i) the fluorescent marker-based and the (ii) marker-free discrimination between healthy and cancerous human tissues. For both applications the performance of hyper-spectral methods are quantified. Fluorescent marker-based tissue classification uses a number of fluorescent markers to dye specific parts of a human cell. The challenge is that the emission spectra of the fluorescent dyes overlap considerably. They are, furthermore disturbed by the inherent auto-fluorescence of human tissue. This results in ambiguities and decreased image contrast causing difficulties for the treatment decision. The higher spectral resolution introduced by tunable-filter-based spectral imaging in combination with spectral unmixing techniques results in an improvement of the image contrast and therefore more reliable information for the physician to choose the treatment decision. Marker-free tissue classification is based solely on the subtle spectral features of human tissue without the use of artificial markers. The challenge in this case is that the spectral differences between healthy and cancerous tissues are subtle and embedded in intra- and inter-patient variations of these features. The contributions of this paper are (i) the evaluation of hyper-spectral imaging in combination with spectral unmixing techniques for fluorescence marker-based tissue classification, (ii) the evaluation of spectral imaging for marker-free intra surgery tissue classification. Within this paper, we consider real hyper-spectral fluorescence and endoscopy data sets to emphasize the practical capability of the proposed methods. It is shown that the combination of spectral imaging with multivariate statistical methods can improve the sensitivity and specificity of the detection and the staging of cancerous tissues compared to standard procedures.

Classification of ground glass opacity lesion characteristic based on texture feature using lung CT image

NASA Astrophysics Data System (ADS)

Sebatubun, M. M.; Haryawan, C.; Windarta, B.

2018-03-01

Lung cancer causes a high mortality rate in the world than any other cancers. That can be minimised if the symptoms and cancer cells have been detected early. One of the techniques used to detect lung cancer is by computed tomography (CT) scan. CT scan images have been used in this study to identify one of the lesion characteristics named ground glass opacity (GGO). It has been used to determine the level of malignancy of the lesion. There were three phases in identifying GGO: image cropping, feature extraction using grey level co-occurrence matrices (GLCM) and classification using Naïve Bayes Classifier. In order to improve the classification results, the most significant feature was sought by feature selection using gain ratio evaluation. Based on the results obtained, the most significant features could be identified by using feature selection method used in this research. The accuracy rate increased from 83.33% to 91.67%, the sensitivity from 82.35% to 94.11% and the specificity from 84.21% to 89.47%.

Genomic screening for targets regulated by berberine in breast cancer cells.

PubMed

Wen, Chun-Jie; Wu, Lan-Xiang; Fu, Li-Juan; Yu, Jing; Zhang, Yi-Wen; Zhang, Xue; Zhou, Hong-Hao

2013-01-01

Berberine, a common isoquinoline alkaloid, has been shown to possess anti-cancer activities. However, the underlying molecular mechanisms are still not completely understood. In the current study, we investigated the effects of berberine on cell growth, colony formation, cell cycle distribution, and whether it improved the anticancer efficiency of cisplatin and doxorubicin in human breast cancer estrogen receptor positive (ER+) MCF-7 cells and estrogen receptor negative (ER-) MDA-MB-231 cells. Notably, berberine treatment significantly inhibited cell growth and colony formation in the two cell lines, berberine in combination with cisplatin exerting synergistic growth inhibitory effects. Accompanied by decreased growth, berberine induced G1 phase arrest in MCF-7 but not MDA-MB-231 cells. To provide a more detailed understanding of the mechanisms of action of berberine, we performed genome-wide expression profiling of berberine-treated cells using cDNA microarrays. This revealed that there were 3,397 and 2,706 genes regulated by berberine in MCF-7 and MDA-MB-231 cells, respectively. Fene oncology (GO) analysis identified that many of the target genes were involved in regulation of the cell cycle, cell migration, apoptosis, and drug responses. To confirm the microarray data, qPCR analysis was conducted for 10 selected genes based on previously reported associations with breast cancer and GO analysis. In conclusion, berberine exhibits inhibitory effects on breast cancer cells proliferation, which is likely mediated by alteration of gene expression profiles.

Nonlinear multi-photon laser wave-mixing optical detection in microarrays and microchips for ultrasensitive detection and separation of biomarkers for cancer and neurodegenerative diseases

NASA Astrophysics Data System (ADS)

Iwabuchi, Manna; Hetu, Marcel; Maxwell, Eric; Pradel, Jean S.; Ramos, Sashary; Tong, William G.

2015-09-01

Multi-photon degenerate four-wave mixing is demonstrated as an ultrasensitive absorption-based optical method for detection, separation and identification of biomarker proteins in the development of early diagnostic methods for HIV- 1, cancer and neurodegenerative diseases using compact, portable microarrays and capillary- or microchip-based chemical separation systems that offer high chemical specificity levels. The wave-mixing signal has a quadratic dependence on concentration, and hence, it allows more reliable monitoring of smaller changes in analyte properties. Our wave-mixing detection sensitivity is comparable or better than those of current methods including enzyme-linked immunoassay for clinical diagnostic and screening. Detection sensitivity is excellent since the wave-mixing signal is a coherent laser-like beam that can be collected with virtually 100% collection efficiency with high S/N. Our analysis time is short (1-15 minutes) for molecular weight-based protein separation as compared to that of a conventional separation technique, e.g., sodium dodecyl sulfate-polyacrylamide gel electrophoresis. When ultrasensitive wavemixing detection is paired with high-resolution capillary- or microchip-based separation systems, biomarkers can be separated and identified at the zepto- and yocto-mole levels for a wide range of analytes. Specific analytes can be captured in a microchannel through the use of antibody-antigen interactions that provide better chemical specificity as compared to size-based separation alone. The technique can also be combined with immune-precipitation and a multichannel capillary array for high-throughput analysis of more complex protein samples. Wave mixing allows the use of chromophores and absorption-modifying tags, in addition to conventional fluorophores, for online detection of immunecomplexes related to cancer.

A New Microarray Substrate for Ultra-Sensitive Genotyping of KRAS and BRAF Gene Variants in Colorectal Cancer

PubMed Central

Pinzani, Pamela; Mancini, Irene; Vinci, Serena; Chiari, Marcella; Orlando, Claudio; Cremonesi, Laura; Ferrari, Maurizio

2013-01-01

Molecular diagnostics of human cancers may increase accuracy in prognosis, facilitate the selection of the optimal therapeutic regimen, improve patient outcome, reduce costs of treatment and favour development of personalized approaches to patient care. Moreover sensitivity and specificity are fundamental characteristics of any diagnostic method. We developed a highly sensitive microarray for the detection of common KRAS and BRAF oncogenic mutations. In colorectal cancer, KRAS and BRAF mutations have been shown to identify a cluster of patients that does not respond to anti-EGFR therapies; the identification of these mutations is therefore clinically extremely important. To verify the technical characteristics of the microarray system for the correct identification of the KRAS mutational status at the two hotspot codons 12 and 13 and of the BRAFV600E mutation in colorectal tumor, we selected 75 samples previously characterized by conventional and CO-amplification at Lower Denaturation temperature-PCR (COLD-PCR) followed by High Resolution Melting analysis and direct sequencing. Among these samples, 60 were collected during surgery and immediately steeped in RNAlater while the 15 remainders were formalin-fixed and paraffin-embedded (FFPE) tissues. The detection limit of the proposed method was different for the 7 KRAS mutations tested and for the V600E BRAF mutation. In particular, the microarray system has been able to detect a minimum of about 0.01% of mutated alleles in a background of wild-type DNA. A blind validation displayed complete concordance of results. The excellent agreement of the results showed that the new microarray substrate is highly specific in assigning the correct genotype without any enrichment strategy. PMID:23536897

Training sample selection based on self-training for liver cirrhosis classification using ultrasound images

NASA Astrophysics Data System (ADS)

Fujita, Yusuke; Mitani, Yoshihiro; Hamamoto, Yoshihiko; Segawa, Makoto; Terai, Shuji; Sakaida, Isao

2017-03-01

Ultrasound imaging is a popular and non-invasive tool used in the diagnoses of liver disease. Cirrhosis is a chronic liver disease and it can advance to liver cancer. Early detection and appropriate treatment are crucial to prevent liver cancer. However, ultrasound image analysis is very challenging, because of the low signal-to-noise ratio of ultrasound images. To achieve the higher classification performance, selection of training regions of interest (ROIs) is very important that effect to classification accuracy. The purpose of our study is cirrhosis detection with high accuracy using liver ultrasound images. In our previous works, training ROI selection by MILBoost and multiple-ROI classification based on the product rule had been proposed, to achieve high classification performance. In this article, we propose self-training method to select training ROIs effectively. Evaluation experiments were performed to evaluate effect of self-training, using manually selected ROIs and also automatically selected ROIs. Experimental results show that self-training for manually selected ROIs achieved higher classification performance than other approaches, including our conventional methods. The manually ROI definition and sample selection are important to improve classification accuracy in cirrhosis detection using ultrasound images.

Feature Selection with Conjunctions of Decision Stumps and Learning from Microarray Data.

PubMed

Shah, M; Marchand, M; Corbeil, J

2012-01-01

One of the objectives of designing feature selection learning algorithms is to obtain classifiers that depend on a small number of attributes and have verifiable future performance guarantees. There are few, if any, approaches that successfully address the two goals simultaneously. To the best of our knowledge, such algorithms that give theoretical bounds on the future performance have not been proposed so far in the context of the classification of gene expression data. In this work, we investigate the premise of learning a conjunction (or disjunction) of decision stumps in Occam's Razor, Sample Compression, and PAC-Bayes learning settings for identifying a small subset of attributes that can be used to perform reliable classification tasks. We apply the proposed approaches for gene identification from DNA microarray data and compare our results to those of the well-known successful approaches proposed for the task. We show that our algorithm not only finds hypotheses with a much smaller number of genes while giving competitive classification accuracy but also having tight risk guarantees on future performance, unlike other approaches. The proposed approaches are general and extensible in terms of both designing novel algorithms and application to other domains.

Comparison of hand-craft feature based SVM and CNN based deep learning framework for automatic polyp classification.

PubMed

Younghak Shin; Balasingham, Ilangko

2017-07-01

Colonoscopy is a standard method for screening polyps by highly trained physicians. Miss-detected polyps in colonoscopy are potential risk factor for colorectal cancer. In this study, we investigate an automatic polyp classification framework. We aim to compare two different approaches named hand-craft feature method and convolutional neural network (CNN) based deep learning method. Combined shape and color features are used for hand craft feature extraction and support vector machine (SVM) method is adopted for classification. For CNN approach, three convolution and pooling based deep learning framework is used for classification purpose. The proposed framework is evaluated using three public polyp databases. From the experimental results, we have shown that the CNN based deep learning framework shows better classification performance than the hand-craft feature based methods. It achieves over 90% of classification accuracy, sensitivity, specificity and precision.

Prognostic Significance of Progesterone Receptor–Positive Tumor Cells Within Immunohistochemically Defined Luminal A Breast Cancer

PubMed Central

Prat, Aleix; Cheang, Maggie Chon U.; Martín, Miguel; Parker, Joel S.; Carrasco, Eva; Caballero, Rosalía; Tyldesley, Scott; Gelmon, Karen; Bernard, Philip S.; Nielsen, Torsten O.; Perou, Charles M.

2013-01-01

Purpose Current immunohistochemical (IHC)-based definitions of luminal A and B breast cancers are imperfect when compared with multigene expression-based assays. In this study, we sought to improve the IHC subtyping by examining the pathologic and gene expression characteristics of genomically defined luminal A and B subtypes. Patients and Methods Gene expression and pathologic features were collected from primary tumors across five independent cohorts: British Columbia Cancer Agency (BCCA) tamoxifen-treated only, Grupo Español de Investigación en Cáncer de Mama 9906 trial, BCCA no systemic treatment cohort, PAM50 microarray training data set, and a combined publicly available microarray data set. Optimal cutoffs of percentage of progesterone receptor (PR) –positive tumor cells to predict survival were derived and independently tested. Multivariable Cox models were used to test the prognostic significance. Results Clinicopathologic comparisons among luminal A and B subtypes consistently identified higher rates of PR positivity, human epidermal growth factor receptor 2 (HER2) negativity, and histologic grade 1 in luminal A tumors. Quantitative PR gene and protein expression were also found to be significantly higher in luminal A tumors. An empiric cutoff of more than 20% of PR-positive tumor cells was statistically chosen and proved significant for predicting survival differences within IHC-defined luminal A tumors independently of endocrine therapy administration. Finally, no additional prognostic value within hormonal receptor (HR) –positive/HER2-negative disease was observed with the use of the IHC4 score when intrinsic IHC-based subtypes were used that included the more than 20% PR-positive tumor cells and vice versa. Conclusion Semiquantitative IHC expression of PR adds prognostic value within the current IHC-based luminal A definition by improving the identification of good outcome breast cancers. The new proposed IHC-based definition of luminal A tumors is HR positive/HER2 negative/Ki-67 less than 14%, and PR more than 20%. PMID:23233704

COMPARATIVE MICROARRAY EXPRESSION ANALYSIS OF SELECTED CANCER RELEVANT GENES IN HYPERTENSIVE RESISTANT VERSUS SUSCEPTIBLE RODENT STRAINS

EPA Science Inventory

Hypertension and cancer are prevalent diseases. Epidemiological studies suggest that hypertension may increase the long term risk of cancer. Identification of resistance and/or susceptibility genes using rodent models could provide important insights into the management and treat...

The clinical value of lncRNA NEAT1 in digestive system malignancies: A comprehensive investigation based on 57 microarray and RNA-seq datasets.

PubMed

Xiong, Dan-Dan; Feng, Zhen-Bo; Cen, Wei-Luan; Zeng, Jing-Jing; Liang, Lu; Tang, Rui-Xue; Gan, Xiao-Ning; Liang, Hai-Wei; Li, Zu-Yun; Chen, Gang; Luo, Dian-Zhong

2017-03-14

This comprehensive investigation was performed to evaluate the expression level and potential clinical value of NEAT1 in digestive system malignancies. A total of 57 lncRNA datasets of microarray or RNA-seq and 5 publications were included. The pooled standard mean deviation (SMD) indicated that NEAT1 was down-regulated in esophageal carcinoma (ESCA, SMD = -0.35, 95% CI: -0.5~-0.20, P < 0.0001) and hepatocellular carcinoma (HCC, SMD = -0.47, 95% CI: -0.60~-0.34, P < 0.0001), while in pancreatic cancer (PC), NEAT1 was up-regulated (SMD = 0.45, 95% CI: 0.2~0.71, P = 0.001). However, NEAT1 expression in gastric cancer (GC), colorectal cancer (CRC), biliary tract cancer (BTC) and gallbladder carcinoma (GBC) showed no significant difference between cancer and control groups. The pooled area under the curve values for ESCA, GC, CRC, PC and HCC were 0.60, 0.89, 0.81, 0.77 and 0.69, respectively. Furthermore, our result demonstrated that a high expression of NEAT1 predicted an unfavorable prognosis in patients with digestive system malignancies (HR: 1.50, 95% CI: 1.28-1.76, P < 0.0001). Our study suggests that NEAT1 may play different roles in the initiation and progression of digestive system cancers and could be a potential diagnostic and prognostic biomarker in patients with digestive system carcinomas. Further and stricter studies with a larger number of cases are necessary to strengthen our conclusions.

The clinical value of lncRNA NEAT1 in digestive system malignancies: A comprehensive investigation based on 57 microarray and RNA-seq datasets

PubMed Central

Cen, Wei-Luan; Zeng, Jing-Jing; Liang, Lu; Tang, Rui-Xue; Gan, Xiao-Ning; Liang, Hai-Wei; Li, Zu-Yun; Chen, Gang; Luo, Dian-Zhong

2017-01-01

This comprehensive investigation was performed to evaluate the expression level and potential clinical value of NEAT1 in digestive system malignancies. A total of 57 lncRNA datasets of microarray or RNA-seq and 5 publications were included. The pooled standard mean deviation (SMD) indicated that NEAT1 was down-regulated in esophageal carcinoma (ESCA, SMD = −0.35, 95% CI: −0.5~-0.20, P < 0.0001) and hepatocellular carcinoma (HCC, SMD = −0.47, 95% CI: −0.60~-0.34, P < 0.0001), while in pancreatic cancer (PC), NEAT1 was up-regulated (SMD = 0.45, 95% CI: 0.2~0.71, P = 0.001). However, NEAT1 expression in gastric cancer (GC), colorectal cancer (CRC), biliary tract cancer (BTC) and gallbladder carcinoma (GBC) showed no significant difference between cancer and control groups. The pooled area under the curve values for ESCA, GC, CRC, PC and HCC were 0.60, 0.89, 0.81, 0.77 and 0.69, respectively. Furthermore, our result demonstrated that a high expression of NEAT1 predicted an unfavorable prognosis in patients with digestive system malignancies (HR: 1.50, 95% CI: 1.28-1.76, P < 0.0001). Our study suggests that NEAT1 may play different roles in the initiation and progression of digestive system cancers and could be a potential diagnostic and prognostic biomarker in patients with digestive system carcinomas. Further and stricter studies with a larger number of cases are necessary to strengthen our conclusions. PMID:28118609

Transfer of chromosome 3 fragments suppresses tumorigenicity of an ovarian cancer cell line monoallelic for chromosome 3p.

PubMed

Cody, N A L; Ouellet, V; Manderson, E N; Quinn, M C J; Filali-Mouhim, A; Tellis, P; Zietarska, M; Provencher, D M; Mes-Masson, A-M; Chevrette, M; Tonin, P N

2007-01-25

Multiple chromosome 3p tumor suppressor genes (TSG) have been proposed in the pathogenesis of ovarian cancer based on complex patterns of 3p loss. To attain functional evidence in support of TSGs and identify candidate regions, we applied a chromosome transfer method involving cell fusions of the tumorigenic OV90 human ovarian cancer cell line, monoallelic for 3p and an irradiated mouse cell line containing a human chromosome 3 in order to derive OV90 hybrids containing normal 3p fragments. The resulting hybrids showed complete or incomplete suppression of tumorigenicity in nude mouse xenograft assays, and varied in their ability to form colonies in soft agarose and three-dimensional spheroids in a manner consistent with alteration of their in vivo tumorigenic phenotypes. Expression microarray analysis identified a set of common differentially expressed genes, such as SPARC, DAB2 and VEGF, some of which have been shown implicated in ovarian cancer. Genotyping assays revealed that they harbored normal 3p fragments, some of which overlapped candidate TSG regions (3p25-p26, 3p24 and 3p14-pcen) identified previously in loss of heterozygosity analyses of ovarian cancers. However, only the 3p12-pcen region was acquired in common by all hybrids where expression microarray analysis identified differentially expressed genes. The correlation of 3p12-pcen transfer and tumor suppression with a concerted re-programming of the cellular transcriptome suggest that the putative TSG may have affected key underlying events in ovarian cancer.

ELISA-BASE: An Integrated Bioinformatics Tool for Analyzing and Tracking ELISA Microarray Data

DOE Office of Scientific and Technical Information (OSTI.GOV)

White, Amanda M.; Collett, James L.; Seurynck-Servoss, Shannon L.

ELISA-BASE is an open-source database for capturing, organizing and analyzing protein enzyme-linked immunosorbent assay (ELISA) microarray data. ELISA-BASE is an extension of the BioArray Soft-ware Environment (BASE) database system, which was developed for DNA microarrays. In order to make BASE suitable for protein microarray experiments, we developed several plugins for importing and analyzing quantitative ELISA microarray data. Most notably, our Protein Microarray Analysis Tool (ProMAT) for processing quantita-tive ELISA data is now available as a plugin to the database.

Normed kernel function-based fuzzy possibilistic C-means (NKFPCM) algorithm for high-dimensional breast cancer database classification with feature selection is based on Laplacian Score

NASA Astrophysics Data System (ADS)

Lestari, A. W.; Rustam, Z.

2017-07-01

In the last decade, breast cancer has become the focus of world attention as this disease is one of the primary leading cause of death for women. Therefore, it is necessary to have the correct precautions and treatment. In previous studies, Fuzzy Kennel K-Medoid algorithm has been used for multi-class data. This paper proposes an algorithm to classify the high dimensional data of breast cancer using Fuzzy Possibilistic C-means (FPCM) and a new method based on clustering analysis using Normed Kernel Function-Based Fuzzy Possibilistic C-Means (NKFPCM). The objective of this paper is to obtain the best accuracy in classification of breast cancer data. In order to improve the accuracy of the two methods, the features candidates are evaluated using feature selection, where Laplacian Score is used. The results show the comparison accuracy and running time of FPCM and NKFPCM with and without feature selection.

A genome-wide 20 K citrus microarray for gene expression analysis

PubMed Central

Martinez-Godoy, M Angeles; Mauri, Nuria; Juarez, Jose; Marques, M Carmen; Santiago, Julia; Forment, Javier; Gadea, Jose

2008-01-01

Background Understanding of genetic elements that contribute to key aspects of citrus biology will impact future improvements in this economically important crop. Global gene expression analysis demands microarray platforms with a high genome coverage. In the last years, genome-wide EST collections have been generated in citrus, opening the possibility to create new tools for functional genomics in this crop plant. Results We have designed and constructed a publicly available genome-wide cDNA microarray that include 21,081 putative unigenes of citrus. As a functional companion to the microarray, a web-browsable database [1] was created and populated with information about the unigenes represented in the microarray, including cDNA libraries, isolated clones, raw and processed nucleotide and protein sequences, and results of all the structural and functional annotation of the unigenes, like general description, BLAST hits, putative Arabidopsis orthologs, microsatellites, putative SNPs, GO classification and PFAM domains. We have performed a Gene Ontology comparison with the full set of Arabidopsis proteins to estimate the genome coverage of the microarray. We have also performed microarray hybridizations to check its usability. Conclusion This new cDNA microarray replaces the first 7K microarray generated two years ago and allows gene expression analysis at a more global scale. We have followed a rational design to minimize cross-hybridization while maintaining its utility for different citrus species. Furthermore, we also provide access to a website with full structural and functional annotation of the unigenes represented in the microarray, along with the ability to use this site to directly perform gene expression analysis using standard tools at different publicly available servers. Furthermore, we show how this microarray offers a good representation of the citrus genome and present the usefulness of this genomic tool for global studies in citrus by using it to catalogue genes expressed in citrus globular embryos. PMID:18598343

Investigating the different mechanisms of genotoxic and non-genotoxic carcinogens by a gene set analysis.

PubMed

Lee, Won Jun; Kim, Sang Cheol; Lee, Seul Ji; Lee, Jeongmi; Park, Jeong Hill; Yu, Kyung-Sang; Lim, Johan; Kwon, Sung Won

2014-01-01

Based on the process of carcinogenesis, carcinogens are classified as either genotoxic or non-genotoxic. In contrast to non-genotoxic carcinogens, many genotoxic carcinogens have been reported to cause tumor in carcinogenic bioassays in animals. Thus evaluating the genotoxicity potential of chemicals is important to discriminate genotoxic from non-genotoxic carcinogens for health care and pharmaceutical industry safety. Additionally, investigating the difference between the mechanisms of genotoxic and non-genotoxic carcinogens could provide the foundation for a mechanism-based classification for unknown compounds. In this study, we investigated the gene expression of HepG2 cells treated with genotoxic or non-genotoxic carcinogens and compared their mechanisms of action. To enhance our understanding of the differences in the mechanisms of genotoxic and non-genotoxic carcinogens, we implemented a gene set analysis using 12 compounds for the training set (12, 24, 48 h) and validated significant gene sets using 22 compounds for the test set (24, 48 h). For a direct biological translation, we conducted a gene set analysis using Globaltest and selected significant gene sets. To validate the results, training and test compounds were predicted by the significant gene sets using a prediction analysis for microarrays (PAM). Finally, we obtained 6 gene sets, including sets enriched for genes involved in the adherens junction, bladder cancer, p53 signaling pathway, pathways in cancer, peroxisome and RNA degradation. Among the 6 gene sets, the bladder cancer and p53 signaling pathway sets were significant at 12, 24 and 48 h. We also found that the DDB2, RRM2B and GADD45A, genes related to the repair and damage prevention of DNA, were consistently up-regulated for genotoxic carcinogens. Our results suggest that a gene set analysis could provide a robust tool in the investigation of the different mechanisms of genotoxic and non-genotoxic carcinogens and construct a more detailed understanding of the perturbation of significant pathways.

Investigating the Different Mechanisms of Genotoxic and Non-Genotoxic Carcinogens by a Gene Set Analysis

PubMed Central

Lee, Won Jun; Kim, Sang Cheol; Lee, Seul Ji; Lee, Jeongmi; Park, Jeong Hill; Yu, Kyung-Sang; Lim, Johan; Kwon, Sung Won

2014-01-01

Based on the process of carcinogenesis, carcinogens are classified as either genotoxic or non-genotoxic. In contrast to non-genotoxic carcinogens, many genotoxic carcinogens have been reported to cause tumor in carcinogenic bioassays in animals. Thus evaluating the genotoxicity potential of chemicals is important to discriminate genotoxic from non-genotoxic carcinogens for health care and pharmaceutical industry safety. Additionally, investigating the difference between the mechanisms of genotoxic and non-genotoxic carcinogens could provide the foundation for a mechanism-based classification for unknown compounds. In this study, we investigated the gene expression of HepG2 cells treated with genotoxic or non-genotoxic carcinogens and compared their mechanisms of action. To enhance our understanding of the differences in the mechanisms of genotoxic and non-genotoxic carcinogens, we implemented a gene set analysis using 12 compounds for the training set (12, 24, 48 h) and validated significant gene sets using 22 compounds for the test set (24, 48 h). For a direct biological translation, we conducted a gene set analysis using Globaltest and selected significant gene sets. To validate the results, training and test compounds were predicted by the significant gene sets using a prediction analysis for microarrays (PAM). Finally, we obtained 6 gene sets, including sets enriched for genes involved in the adherens junction, bladder cancer, p53 signaling pathway, pathways in cancer, peroxisome and RNA degradation. Among the 6 gene sets, the bladder cancer and p53 signaling pathway sets were significant at 12, 24 and 48 h. We also found that the DDB2, RRM2B and GADD45A, genes related to the repair and damage prevention of DNA, were consistently up-regulated for genotoxic carcinogens. Our results suggest that a gene set analysis could provide a robust tool in the investigation of the different mechanisms of genotoxic and non-genotoxic carcinogens and construct a more detailed understanding of the perturbation of significant pathways. PMID:24497971

DFP: a Bioconductor package for fuzzy profile identification and gene reduction of microarray data

PubMed Central

Glez-Peña, Daniel; Álvarez, Rodrigo; Díaz, Fernando; Fdez-Riverola, Florentino

2009-01-01

Background Expression profiling assays done by using DNA microarray technology generate enormous data sets that are not amenable to simple analysis. The greatest challenge in maximizing the use of this huge amount of data is to develop algorithms to interpret and interconnect results from different genes under different conditions. In this context, fuzzy logic can provide a systematic and unbiased way to both (i) find biologically significant insights relating to meaningful genes, thereby removing the need for expert knowledge in preliminary steps of microarray data analyses and (ii) reduce the cost and complexity of later applied machine learning techniques being able to achieve interpretable models. Results DFP is a new Bioconductor R package that implements a method for discretizing and selecting differentially expressed genes based on the application of fuzzy logic. DFP takes advantage of fuzzy membership functions to assign linguistic labels to gene expression levels. The technique builds a reduced set of relevant genes (FP, Fuzzy Pattern) able to summarize and represent each underlying class (pathology). A last step constructs a biased set of genes (DFP, Discriminant Fuzzy Pattern) by intersecting existing fuzzy patterns in order to detect discriminative elements. In addition, the software provides new functions and visualisation tools that summarize achieved results and aid in the interpretation of differentially expressed genes from multiple microarray experiments. Conclusion DFP integrates with other packages of the Bioconductor project, uses common data structures and is accompanied by ample documentation. It has the advantage that its parameters are highly configurable, facilitating the discovery of biologically relevant connections between sets of genes belonging to different pathologies. This information makes it possible to automatically filter irrelevant genes thereby reducing the large volume of data supplied by microarray experiments. Based on these contributions GENECBR, a successful tool for cancer diagnosis using microarray datasets, has recently been released. PMID:19178723

Augmenting Microarray Data with Literature-Based Knowledge to Enhance Gene Regulatory Network Inference

PubMed Central

Kilicoglu, Halil; Shin, Dongwook; Rindflesch, Thomas C.

2014-01-01

Gene regulatory networks are a crucial aspect of systems biology in describing molecular mechanisms of the cell. Various computational models rely on random gene selection to infer such networks from microarray data. While incorporation of prior knowledge into data analysis has been deemed important, in practice, it has generally been limited to referencing genes in probe sets and using curated knowledge bases. We investigate the impact of augmenting microarray data with semantic relations automatically extracted from the literature, with the view that relations encoding gene/protein interactions eliminate the need for random selection of components in non-exhaustive approaches, producing a more accurate model of cellular behavior. A genetic algorithm is then used to optimize the strength of interactions using microarray data and an artificial neural network fitness function. The result is a directed and weighted network providing the individual contribution of each gene to its target. For testing, we used invasive ductile carcinoma of the breast to query the literature and a microarray set containing gene expression changes in these cells over several time points. Our model demonstrates significantly better fitness than the state-of-the-art model, which relies on an initial random selection of genes. Comparison to the component pathways of the KEGG Pathways in Cancer map reveals that the resulting networks contain both known and novel relationships. The p53 pathway results were manually validated in the literature. 60% of non-KEGG relationships were supported (74% for highly weighted interactions). The method was then applied to yeast data and our model again outperformed the comparison model. Our results demonstrate the advantage of combining gene interactions extracted from the literature in the form of semantic relations with microarray analysis in generating contribution-weighted gene regulatory networks. This methodology can make a significant contribution to understanding the complex interactions involved in cellular behavior and molecular physiology. PMID:24921649

Augmenting microarray data with literature-based knowledge to enhance gene regulatory network inference.

PubMed

Chen, Guocai; Cairelli, Michael J; Kilicoglu, Halil; Shin, Dongwook; Rindflesch, Thomas C

2014-06-01

Gene regulatory networks are a crucial aspect of systems biology in describing molecular mechanisms of the cell. Various computational models rely on random gene selection to infer such networks from microarray data. While incorporation of prior knowledge into data analysis has been deemed important, in practice, it has generally been limited to referencing genes in probe sets and using curated knowledge bases. We investigate the impact of augmenting microarray data with semantic relations automatically extracted from the literature, with the view that relations encoding gene/protein interactions eliminate the need for random selection of components in non-exhaustive approaches, producing a more accurate model of cellular behavior. A genetic algorithm is then used to optimize the strength of interactions using microarray data and an artificial neural network fitness function. The result is a directed and weighted network providing the individual contribution of each gene to its target. For testing, we used invasive ductile carcinoma of the breast to query the literature and a microarray set containing gene expression changes in these cells over several time points. Our model demonstrates significantly better fitness than the state-of-the-art model, which relies on an initial random selection of genes. Comparison to the component pathways of the KEGG Pathways in Cancer map reveals that the resulting networks contain both known and novel relationships. The p53 pathway results were manually validated in the literature. 60% of non-KEGG relationships were supported (74% for highly weighted interactions). The method was then applied to yeast data and our model again outperformed the comparison model. Our results demonstrate the advantage of combining gene interactions extracted from the literature in the form of semantic relations with microarray analysis in generating contribution-weighted gene regulatory networks. This methodology can make a significant contribution to understanding the complex interactions involved in cellular behavior and molecular physiology.

DFP: a Bioconductor package for fuzzy profile identification and gene reduction of microarray data.

PubMed

Glez-Peña, Daniel; Alvarez, Rodrigo; Díaz, Fernando; Fdez-Riverola, Florentino

2009-01-29

Expression profiling assays done by using DNA microarray technology generate enormous data sets that are not amenable to simple analysis. The greatest challenge in maximizing the use of this huge amount of data is to develop algorithms to interpret and interconnect results from different genes under different conditions. In this context, fuzzy logic can provide a systematic and unbiased way to both (i) find biologically significant insights relating to meaningful genes, thereby removing the need for expert knowledge in preliminary steps of microarray data analyses and (ii) reduce the cost and complexity of later applied machine learning techniques being able to achieve interpretable models. DFP is a new Bioconductor R package that implements a method for discretizing and selecting differentially expressed genes based on the application of fuzzy logic. DFP takes advantage of fuzzy membership functions to assign linguistic labels to gene expression levels. The technique builds a reduced set of relevant genes (FP, Fuzzy Pattern) able to summarize and represent each underlying class (pathology). A last step constructs a biased set of genes (DFP, Discriminant Fuzzy Pattern) by intersecting existing fuzzy patterns in order to detect discriminative elements. In addition, the software provides new functions and visualisation tools that summarize achieved results and aid in the interpretation of differentially expressed genes from multiple microarray experiments. DFP integrates with other packages of the Bioconductor project, uses common data structures and is accompanied by ample documentation. It has the advantage that its parameters are highly configurable, facilitating the discovery of biologically relevant connections between sets of genes belonging to different pathologies. This information makes it possible to automatically filter irrelevant genes thereby reducing the large volume of data supplied by microarray experiments. Based on these contributions GENECBR, a successful tool for cancer diagnosis using microarray datasets, has recently been released.

MR Imaging Based Treatment Planning for Radiotherapy of Prostate Cancer

DTIC Science & Technology

2008-02-01

Radiotherapy, MR-based treatment planning, dosimetry, Monte Carlo dose verification, Prostate Cancer, MRI -based DRRs 16. SECURITY CLASSIFICATION...AcQPlan system Version 5 was used for the study , which is capable of performing dose calculation on both CT and MRI . A four field 3D conformal planning...prostate motion studies for 3DCRT and IMRT of prostate cancer; (2) to investigate and improve the accuracy of MRI -based treatment planning dose calculation

Classification of cancer cell lines using matrix-assisted laser desorption/ionization time‑of‑flight mass spectrometry and statistical analysis.

PubMed

Serafim, Vlad; Shah, Ajit; Puiu, Maria; Andreescu, Nicoleta; Coricovac, Dorina; Nosyrev, Alexander; Spandidos, Demetrios A; Tsatsakis, Aristides M; Dehelean, Cristina; Pinzaru, Iulia

2017-10-01

Over the past decade, matrix-assisted laser desorption/ionization time‑of‑flight mass spectrometry (MALDI‑TOF MS) has been established as a valuable platform for microbial identification, and it is also frequently applied in biology and clinical studies to identify new markers expressed in pathological conditions. The aim of the present study was to assess the potential of using this approach for the classification of cancer cell lines as a quantifiable method for the proteomic profiling of cellular organelles. Intact protein extracts isolated from different tumor cell lines (human and murine) were analyzed using MALDI‑TOF MS and the obtained mass lists were processed using principle component analysis (PCA) within Bruker Biotyper® software. Furthermore, reference spectra were created for each cell line and were used for classification. Based on the intact protein profiles, we were able to differentiate and classify six cancer cell lines: two murine melanoma (B16‑F0 and B164A5), one human melanoma (A375), two human breast carcinoma (MCF7 and MDA‑MB‑231) and one human liver carcinoma (HepG2). The cell lines were classified according to cancer type and the species they originated from, as well as by their metastatic potential, offering the possibility to differentiate non‑invasive from invasive cells. The obtained results pave the way for developing a broad‑based strategy for the identification and classification of cancer cells.

On-the-spot lung cancer differential diagnosis by label-free, molecular vibrational imaging and knowledge-based classification

NASA Astrophysics Data System (ADS)

Gao, Liang; Li, Fuhai; Thrall, Michael J.; Yang, Yaliang; Xing, Jiong; Hammoudi, Ahmad A.; Zhao, Hong; Massoud, Yehia; Cagle, Philip T.; Fan, Yubo; Wong, Kelvin K.; Wang, Zhiyong; Wong, Stephen T. C.

2011-09-01

We report the development and application of a knowledge-based coherent anti-Stokes Raman scattering (CARS) microscopy system for label-free imaging, pattern recognition, and classification of cells and tissue structures for differentiating lung cancer from non-neoplastic lung tissues and identifying lung cancer subtypes. A total of 1014 CARS images were acquired from 92 fresh frozen lung tissue samples. The established pathological workup and diagnostic cellular were used as prior knowledge for establishment of a knowledge-based CARS system using a machine learning approach. This system functions to separate normal, non-neoplastic, and subtypes of lung cancer tissues based on extracted quantitative features describing fibrils and cell morphology. The knowledge-based CARS system showed the ability to distinguish lung cancer from normal and non-neoplastic lung tissue with 91% sensitivity and 92% specificity. Small cell carcinomas were distinguished from nonsmall cell carcinomas with 100% sensitivity and specificity. As an adjunct to submitting tissue samples to routine pathology, our novel system recognizes the patterns of fibril and cell morphology, enabling medical practitioners to perform differential diagnosis of lung lesions in mere minutes. The demonstration of the strategy is also a necessary step toward in vivo point-of-care diagnosis of precancerous and cancerous lung lesions with a fiber-based CARS microendoscope.

Advanced Cancer Genomics Institute: Genetic Signatures and Therapeutic Targets in Cancer Progression

DTIC Science & Technology

2015-04-01

ORGANIZATION REPORT NUMBER Roswell Park Cancer Institute Elm and Carlton Streets Buffalo, NY 14263 9. SPONSORING / MONITORING AGENCY NAME(S) AND...AD- and CR-CaP cases. Roswell Park already has produced a 5- slide tumor microarray containing 722 CaP/matched normal biopsy samples for follow

A preliminary result of three-dimensional microarray technology to gene analysis with endoscopic ultrasound-guided fine-needle aspiration specimens and pancreatic juices

PubMed Central

2010-01-01

Background Analysis of gene expression and gene mutation may add information to be different from ordinary pathological tissue diagnosis. Since samples obtained endoscopically are very small, it is desired that more sensitive technology is developed for gene analysis. We investigated whether gene expression and gene mutation analysis by newly developed ultra-sensitive three-dimensional (3D) microarray is possible using small amount samples from endoscopic ultrasound-guided fine-needle aspiration (EUS-FNA) specimens and pancreatic juices. Methods Small amount samples from 17 EUS-FNA specimens and 16 pancreatic juices were obtained. After nucleic acid extraction, the samples were amplified with labeling and analyzed by the 3D microarray. Results The analyzable rate with the microarray was 46% (6/13) in EUS-FNA specimens of RNAlater® storage, and RNA degradations were observed in all the samples of frozen storage. In pancreatic juices, the analyzable rate was 67% (4/6) in frozen storage samples and 20% (2/10) in RNAlater® storage. EUS-FNA specimens were classified into cancer and non-cancer by gene expression analysis and K-ras codon 12 mutations were also detected using the 3D microarray. Conclusions Gene analysis from small amount samples obtained endoscopically was possible by newly developed 3D microarray technology. High quality RNA from EUS-FNA samples were obtained and remained in good condition only using RNA stabilizer. In contrast, high quality RNA from pancreatic juice samples were obtained only in frozen storage without RNA stabilizer. PMID:20416107

Mammographic features and subsequent risk of breast cancer: a comparison of qualitative and quantitative evaluations in the Guernsey prospective studies.

PubMed

Torres-Mejía, Gabriela; De Stavola, Bianca; Allen, Diane S; Pérez-Gavilán, Juan J; Ferreira, Jorge M; Fentiman, Ian S; Dos Santos Silva, Isabel

2005-05-01

Mammographic features are known to be associated with breast cancer but the magnitude of the effect differs markedly from study to study. Methods to assess mammographic features range from subjective qualitative classifications to computer-automated quantitative measures. We used data from the UK Guernsey prospective studies to examine the relative value of these methods in predicting breast cancer risk. In all, 3,211 women ages > or =35 years who had a mammogram taken in 1986 to 1989 were followed-up to the end of October 2003, with 111 developing breast cancer during this period. Mammograms were classified using the subjective qualitative Wolfe classification and several quantitative mammographic features measured using computer-based techniques. Breast cancer risk was positively associated with high-grade Wolfe classification, percent breast density and area of dense tissue, and negatively associated with area of lucent tissue, fractal dimension, and lacunarity. Inclusion of the quantitative measures in the same model identified area of dense tissue and lacunarity as the best predictors of breast cancer, with risk increasing by 59% [95% confidence interval (95% CI), 29-94%] per SD increase in total area of dense tissue but declining by 39% (95% CI, 53-22%) per SD increase in lacunarity, after adjusting for each other and for other confounders. Comparison of models that included both the qualitative Wolfe classification and these two quantitative measures to models that included either the qualitative or the two quantitative variables showed that they all made significant contributions to prediction of breast cancer risk. These findings indicate that breast cancer risk is affected not only by the amount of mammographic density but also by the degree of heterogeneity of the parenchymal pattern and, presumably, by other features captured by the Wolfe classification.

Pathological Bases for a Robust Application of Cancer Molecular Classification

PubMed Central

Diaz-Cano, Salvador J.

2015-01-01

Any robust classification system depends on its purpose and must refer to accepted standards, its strength relying on predictive values and a careful consideration of known factors that can affect its reliability. In this context, a molecular classification of human cancer must refer to the current gold standard (histological classification) and try to improve it with key prognosticators for metastatic potential, staging and grading. Although organ-specific examples have been published based on proteomics, transcriptomics and genomics evaluations, the most popular approach uses gene expression analysis as a direct correlate of cellular differentiation, which represents the key feature of the histological classification. RNA is a labile molecule that varies significantly according with the preservation protocol, its transcription reflect the adaptation of the tumor cells to the microenvironment, it can be passed through mechanisms of intercellular transference of genetic information (exosomes), and it is exposed to epigenetic modifications. More robust classifications should be based on stable molecules, at the genetic level represented by DNA to improve reliability, and its analysis must deal with the concept of intratumoral heterogeneity, which is at the origin of tumor progression and is the byproduct of the selection process during the clonal expansion and progression of neoplasms. The simultaneous analysis of multiple DNA targets and next generation sequencing offer the best practical approach for an analytical genomic classification of tumors. PMID:25898411

Discretization of Gene Expression Data Unmasks Molecular Subgroups Recurring in Different Human Cancer Types.

PubMed

Beleut, Manfred; Soeldner, Robert; Egorov, Mark; Guenther, Rolf; Dehler, Silvia; Morys-Wortmann, Corinna; Moch, Holger; Henco, Karsten; Schraml, Peter

2016-01-01

Despite the individually different molecular alterations in tumors, the malignancy associated biological traits are strikingly similar. Results of a previous study using renal cell carcinoma (RCC) as a model pointed towards cancer-related features, which could be visualized as three groups by microarray based gene expression analysis. In this study, we used a mathematic model to verify the presence of these groups in RCC as well as in other cancer types. We developed an algorithm for gene-expression deviation profiling for analyzing gene expression data of a total of 8397 patients with 13 different cancer types and normal tissues. We revealed three common Cancer Transcriptomic Profiles (CTPs) which recurred in all investigated tumors. Additionally, CTPs remained robust regardless of the functions or numbers of genes analyzed. CTPs may represent common genetic fingerprints, which potentially reflect the closely related biological traits of human cancers.

Clinical application of a microfluidic chip for immunocapture and quantification of circulating exosomes to assist breast cancer diagnosis and molecular classification.

PubMed

Fang, Shimeng; Tian, Hongzhu; Li, Xiancheng; Jin, Dong; Li, Xiaojie; Kong, Jing; Yang, Chun; Yang, Xuesong; Lu, Yao; Luo, Yong; Lin, Bingcheng; Niu, Weidong; Liu, Tingjiao

2017-01-01

Increasing attention has been attracted by exosomes in blood-based diagnosis because cancer cells release more exosomes in serum than normal cells and these exosomes overexpress a certain number of cancer-related biomarkers. However, capture and biomarker analysis of exosomes for clinical application are technically challenging. In this study, we developed a microfluidic chip for immunocapture and quantification of circulating exosomes from small sample volume and applied this device in clinical study. Circulating EpCAM-positive exosomes were measured in 6 cases breast cancer patients and 3 healthy controls to assist diagnosis. A significant increase in the EpCAM-positive exosome level in these patients was detected, compared to healthy controls. Furthermore, we quantified circulating HER2-positive exosomes in 19 cases of breast cancer patients for molecular classification. We demonstrated that the exosomal HER2 expression levels were almost consistent with that in tumor tissues assessed by immunohistochemical staining. The microfluidic chip might provide a new platform to assist breast cancer diagnosis and molecular classification.

Morphological feature extraction for the classification of digital images of cancerous tissues.

PubMed

Thiran, J P; Macq, B

1996-10-01

This paper presents a new method for automatic recognition of cancerous tissues from an image of a microscopic section. Based on the shape and the size analysis of the observed cells, this method provides the physician with nonsubjective numerical values for four criteria of malignancy. This automatic approach is based on mathematical morphology, and more specifically on the use of Geodesy. This technique is used first to remove the background noise from the image and then to operate a segmentation of the nuclei of the cells and an analysis of their shape, their size, and their texture. From the values of the extracted criteria, an automatic classification of the image (cancerous or not) is finally operated.

Overview of the 8th Edition TNM Classification for Head and Neck Cancer.

PubMed

Huang, Shao Hui; O'Sullivan, Brian

2017-07-01

The main purpose of the TNM system is to provide an anatomic-based classification to adequately depict cancer prognosis. Accurate cancer staging is important for treatment selection and outcome prediction, research design, and cancer control activities. To maintain clinical relevance, periodical updates to TNM are necessary. The recently published 8th edition TNM classification institutes the following changes to the staging of head and neck (excluding thyroid cancer): new stage classifications [HPV-related oropharyngeal cancer (HPV+ OPC) and soft tissue sarcoma of the head and neck (HN-STS)] and modification of T and N categories [T and N categories for nasopharyngeal cancer (NPC), T categories for oral cavity squamous cell carcinomas (OSCC), N categories for non-viral related head and neck cancer and unknown primary (CUP), and T categories for head and neck cutaneous carcinoma]. These changes reflect better understanding tumor biology and clinical behavior (e.g., HPV+ OPC and HN-STS), improved outcomes associated with technical advances in diagnosis and treatment (e.g., NPC), evolving knowledge about additional prognostic factors and risk stratification from research and observation (e.g., inclusion of depth of invasion variable for OSCC, inclusion of extranodal extension variable for all non-viral head and neck cancer, and reintroduction of size criteria for non-Merkel cell cutaneous carcinoma of the head and neck). This review summarizes the changes and potential advantages and limitations/caveats associated with them. Further evidence is needed to evaluate whether these changes would result in improvement in TNM stage performance to better serve the needs for clinical care, research, and cancer control.

Confocal Raman imaging for cancer cell classification

NASA Astrophysics Data System (ADS)

Mathieu, Evelien; Van Dorpe, Pol; Stakenborg, Tim; Liu, Chengxun; Lagae, Liesbet

2014-05-01

We propose confocal Raman imaging as a label-free single cell characterization method that can be used as an alternative for conventional cell identification techniques that typically require labels, long incubation times and complex sample preparation. In this study it is investigated whether cancer and blood cells can be distinguished based on their Raman spectra. 2D Raman scans are recorded of 114 single cells, i.e. 60 breast (MCF-7), 5 cervix (HeLa) and 39 prostate (LNCaP) cancer cells and 10 monocytes (from healthy donors). For each cell an average spectrum is calculated and principal component analysis is performed on all average cell spectra. The main features of these principal components indicate that the information for cell identification based on Raman spectra mainly comes from the fatty acid composition in the cell. Based on the second and third principal component, blood cells could be distinguished from cancer cells; and prostate cancer cells could be distinguished from breast and cervix cancer cells. However, it was not possible to distinguish breast and cervix cancer cells. The results obtained in this study, demonstrate the potential of confocal Raman imaging for cell type classification and identification purposes.

Classification of breast cancer cytological specimen using convolutional neural network

NASA Astrophysics Data System (ADS)

Żejmo, Michał; Kowal, Marek; Korbicz, Józef; Monczak, Roman

2017-01-01

The paper presents a deep learning approach for automatic classification of breast tumors based on fine needle cytology. The main aim of the system is to distinguish benign from malignant cases based on microscopic images. Experiment was carried out on cytological samples derived from 50 patients (25 benign cases + 25 malignant cases) diagnosed in Regional Hospital in Zielona Góra. To classify microscopic images, we used convolutional neural networks (CNN) of two types: GoogLeNet and AlexNet. Due to the very large size of images of cytological specimen (on average 200000 × 100000 pixels), they were divided into smaller patches of size 256 × 256 pixels. Breast cancer classification usually is based on morphometric features of nuclei. Therefore, training and validation patches were selected using Support Vector Machine (SVM) so that suitable amount of cell material was depicted. Neural classifiers were tuned using GPU accelerated implementation of gradient descent algorithm. Training error was defined as a cross-entropy classification loss. Classification accuracy was defined as the percentage ratio of successfully classified validation patches to the total number of validation patches. The best accuracy rate of 83% was obtained by GoogLeNet model. We observed that more misclassified patches belong to malignant cases.

Feasibility of using tissue microarray cores of paraffin-embedded breast cancer tissue for measurement of gene expression: a proof-of-concept study.

PubMed

Drury, Suzanne; Salter, Janine; Baehner, Frederick L; Shak, Steven; Dowsett, Mitch

2010-06-01

To determine whether 0.6 mm cores of formalin-fixed paraffin-embedded (FFPE) tissue, as commonly used to construct immunohistochemical tissue microarrays, may be a valid alternative to tissue sections as source material for quantitative real-time PCR-based transcriptional profiling of breast cancer. Four matched 0.6 mm cores of invasive breast tumour and two 10 microm whole sections were taken from eight FFPE blocks. RNA was extracted and reverse transcribed, and TaqMan assays were performed on the 21 genes of the Oncotype DX Breast Cancer assay. Expression of the 16 recurrence-related genes was normalised to the set of five reference genes, and the recurrence score (RS) was calculated. RNA yield was lower from 0.6 mm cores than from 10 microm whole sections, but was still more than sufficient to perform the assay. RS and single gene data from cores were highly comparable with those from whole sections (RS p=0.005). Greater variability was seen between cores than between sections. FFPE sections are preferable to 0.6 mm cores for RNA profiling in order to maximise RNA yield and to allow for standard histopathological assessment. However, 0.6 mm cores are sufficient and would be appropriate to use for large cohort studies.

Comprehensive Assessments of RNA-seq by the SEQC Consortium: FDA-Led Efforts Advance Precision Medicine.

PubMed

Xu, Joshua; Gong, Binsheng; Wu, Leihong; Thakkar, Shraddha; Hong, Huixiao; Tong, Weida

2016-03-15

Studies on gene expression in response to therapy have led to the discovery of pharmacogenomics biomarkers and advances in precision medicine. Whole transcriptome sequencing (RNA-seq) is an emerging tool for profiling gene expression and has received wide adoption in the biomedical research community. However, its value in regulatory decision making requires rigorous assessment and consensus between various stakeholders, including the research community, regulatory agencies, and industry. The FDA-led SEquencing Quality Control (SEQC) consortium has made considerable progress in this direction, and is the subject of this review. Specifically, three RNA-seq platforms (Illumina HiSeq, Life Technologies SOLiD, and Roche 454) were extensively evaluated at multiple sites to assess cross-site and cross-platform reproducibility. The results demonstrated that relative gene expression measurements were consistently comparable across labs and platforms, but not so for the measurement of absolute expression levels. As part of the quality evaluation several studies were included to evaluate the utility of RNA-seq in clinical settings and safety assessment. The neuroblastoma study profiled tumor samples from 498 pediatric neuroblastoma patients by both microarray and RNA-seq. RNA-seq offers more utilities than microarray in determining the transcriptomic characteristics of cancer. However, RNA-seq and microarray-based models were comparable in clinical endpoint prediction, even when including additional features unique to RNA-seq beyond gene expression. The toxicogenomics study compared microarray and RNA-seq profiles of the liver samples from rats exposed to 27 different chemicals representing multiple toxicity modes of action. Cross-platform concordance was dependent on chemical treatment and transcript abundance. Though both RNA-seq and microarray are suitable for developing gene expression based predictive models with comparable prediction performance, RNA-seq offers advantages over microarray in profiling genes with low expression. The rat BodyMap study provided a comprehensive rat transcriptomic body map by performing RNA-Seq on 320 samples from 11 organs in either sex of juvenile, adolescent, adult and aged Fischer 344 rats. Lastly, the transferability study demonstrated that signature genes of predictive models are reciprocally transferable between microarray and RNA-seq data for model development using a comprehensive approach with two large clinical data sets. This result suggests continued usefulness of legacy microarray data in the coming RNA-seq era. In conclusion, the SEQC project enhances our understanding of RNA-seq and provides valuable guidelines for RNA-seq based clinical application and safety evaluation to advance precision medicine.

Autoantibodies to aberrantly glycosylated MUC1 in early stage breast cancer are associated with a better prognosis

PubMed Central

2011-01-01

Introduction Detection of serum biomarkers for early diagnosis of breast cancer remains an important goal. Changes in the structure of O-linked glycans occur in all breast cancers resulting in the expression of glycoproteins that are antigenically distinct. Indeed, the serum assay widely used for monitoring disease progression in breast cancer (CA15.3), detects a glycoprotein (MUC1), but elevated levels of the antigen cannot be detected in early stage patients. However, since the immune system acts to amplify the antigenic signal, antibodies can be detected in sera long before the antigen. We have exploited the change in O-glycosylation to measure autoantibody responses to cancer-associated glycoforms of MUC1 in sera from early stage breast cancer patients. Methods We used a microarray platform of 60mer MUC1 glycopeptides, to confirm the presence of autoantibodies to cancer associated glycoforms of MUC1 in a proportion of early breast cancer patients (54/198). Five positive sera were selected for detailed definition of the reactive epitopes using on chip glycosylation technology and a panel of glycopeptides based on a single MUC1 tandem repeat carrying specific glycans at specific sites. Based on these results, larger amounts of an extended repertoire of defined MUC1 glycopeptides were synthesised, printed on microarrays, and screened with sera from a large cohort of breast cancer patients (n = 395), patients with benign breast disease (n = 108) and healthy controls (n = 99). All sera were collected in the 1970s and 1980s and complete clinical follow-up of breast cancer patients is available. Results The presence and level of autoantibodies was significantly higher in the sera from cancer patients compared with the controls, and a highly significant correlation with age was observed. High levels of a subset of autoantibodies to the core3MUC1 (GlcNAcβ1-3GalNAc-MUC1) and STnMUC1 (NeuAcα2,6GalNAc-MUC1) glycoforms were significantly associated with reduced incidence and increased time to metastasis. Conclusions Autoantibodies to specific cancer associated glycoforms of MUC1 are found more frequently and at higher levels in early stage breast cancer patients than in women with benign breast disease or healthy women. Association of strong antibody response with reduced rate and delay in metastases suggests that autoantibodies can affect disease progression. PMID:21385452

Automated noninvasive classification of renal cancer on multiphase CT

DOE Office of Scientific and Technical Information (OSTI.GOV)

Linguraru, Marius George; Wang, Shijun; Shah, Furhawn

2011-10-15

Purpose: To explore the added value of the shape of renal lesions for classifying renal neoplasms. To investigate the potential of computer-aided analysis of contrast-enhanced computed-tomography (CT) to quantify and classify renal lesions. Methods: A computer-aided clinical tool based on adaptive level sets was employed to analyze 125 renal lesions from contrast-enhanced abdominal CT studies of 43 patients. There were 47 cysts and 78 neoplasms: 22 Von Hippel-Lindau (VHL), 16 Birt-Hogg-Dube (BHD), 19 hereditary papillary renal carcinomas (HPRC), and 21 hereditary leiomyomatosis and renal cell cancers (HLRCC). The technique quantified the three-dimensional size and enhancement of lesions. Intrapatient and interphasemore » registration facilitated the study of lesion serial enhancement. The histograms of curvature-related features were used to classify the lesion types. The areas under the curve (AUC) were calculated for receiver operating characteristic curves. Results: Tumors were robustly segmented with 0.80 overlap (0.98 correlation) between manual and semi-automated quantifications. The method further identified morphological discrepancies between the types of lesions. The classification based on lesion appearance, enhancement and morphology between cysts and cancers showed AUC = 0.98; for BHD + VHL (solid cancers) vs. HPRC + HLRCC AUC = 0.99; for VHL vs. BHD AUC = 0.82; and for HPRC vs. HLRCC AUC = 0.84. All semi-automated classifications were statistically significant (p < 0.05) and superior to the analyses based solely on serial enhancement. Conclusions: The computer-aided clinical tool allowed the accurate quantification of cystic, solid, and mixed renal tumors. Cancer types were classified into four categories using their shape and enhancement. Comprehensive imaging biomarkers of renal neoplasms on abdominal CT may facilitate their noninvasive classification, guide clinical management, and monitor responses to drugs or interventions.« less

Cardiovascular, diabetes, and cancer strips: evidences, mechanisms, and classifications

PubMed Central

Wu, Qing-Hua; Hu, Da-Yi

2014-01-01

Objectives To report and name firstly that there are cardiovascular disease (CVD), diabetes mellitus (DM) and cancers (CDC) strips; and disclose their mechanisms, classifications, and clinical significances. Study design Narrative and systematic review study and interpretive analysis. Methods Data sources and study selection: to collect and present related evidences on CDC strips from evidence-based, open-access, both Chinese- and English-language literatures in recent 10 years on clinical trials from PubMed according to keywords “CVD, DM and cancers” as well as authors’ extensive clinical experience with the treatment of more than fifty thousands of patients with CVD, diabetes and cancers over the past decades, and analyze their related mechanisms and categories which based on authors’ previous works. Data extraction: data were mainly extracted from 48 articles which are listed in the reference section of this review. Qualitative, quantitative and mixed data were included, narratively and systematically reviewed. Results With several conceptual and technical breakthrough, authors present related evidences on CDC strips, these are, CVD and DM, DM and cancers, cancers and CVD linked, respectively; And “Bad SEED” +/– “bad soil” theory or doctrine may explain this phenomenon due to “internal environmental injure, abnormal or unbalance” in human body resulting from the role of risk factors (RFs) related multi-pathways and multi-targets, which including organ & tissue (e.g., vascular-specific), cell and gene-based mechanisms. Their classifications include main strips/type B, and Branches/type A as showed by tables and figures in this article. Conclusions There are CDC strips and related mechanisms and classifications. CDC strips may help us to understand, prevent, and control related common non-communicable diseases (NCDs) as well as these high risk strips. PMID:25276377

Predicting features of breast cancer with gene expression patterns.

PubMed

Lu, Xuesong; Lu, Xin; Wang, Zhigang C; Iglehart, J Dirk; Zhang, Xuegong; Richardson, Andrea L

2008-03-01

Data from gene expression arrays hold an enormous amount of biological information. We sought to determine if global gene expression in primary breast cancers contained information about biologic, histologic, and anatomic features of the disease in individual patients. Microarray data from the tumors of 129 patients were analyzed for the ability to predict biomarkers [estrogen receptor (ER) and HER2], histologic features [grade and lymphatic-vascular invasion (LVI)], and stage parameters (tumor size and lymph node metastasis). Multiple statistical predictors were used and the prediction accuracy was determined by cross-validation error rate; multidimensional scaling (MDS) allowed visualization of the predicted states under study. Models built from gene expression data accurately predict ER and HER2 status, and divide tumor grade into high-grade and low-grade clusters; intermediate-grade tumors are not a unique group. In contrast, gene expression data is inaccurate at predicting tumor size, lymph node status or LVI. The best model for prediction of nodal status included tumor size, LVI status and pathologically defined tumor subtype (based on combinations of ER, HER2, and grade); the addition of microarray-based prediction to this model failed to improve the prediction accuracy. Global gene expression supports a binary division of ER, HER2, and grade, clearly separating tumors into two categories; intermediate values for these bio-indicators do not define intermediate tumor subsets. Results are consistent with a model of regional metastasis that depends on inherent biologic differences in metastatic propensity between breast cancer subtypes, upon which time and chance then operate.

Metastatic breast carcinomas display genomic and transcriptomic heterogeneity

PubMed Central

Weigelt, Britta; Ng, Charlotte KY; Shen, Ronglai; Popova, Tatiana; Schizas, Michail; Natrajan, Rachael; Mariani, Odette; Stern, Marc-Henri; Norton, Larry; Vincent-Salomon, Anne; Reis-Filho, Jorge S

2015-01-01

Metaplastic breast carcinoma is a rare and aggressive histologic type of breast cancer, preferentially displaying a triple-negative phenotype. We sought to define the transcriptomic heterogeneity of metaplastic breast cancers on the basis of current gene expression microarray-based classifiers, and to determine whether these tumors display gene copy number profiles consistent with those of BRCA1-associated breast cancers. Twenty-eight consecutive triple-negative metaplastic breast carcinomas were reviewed, and the metaplastic component present in each frozen specimen was defined (ie, spindle cell, squamous, chondroid metaplasia). RNA and DNA extracted from frozen sections with tumor cell content >60% were subjected to gene expression (Illumina HumanHT-12 v4) and copy number profiling (Affymetrix SNP 6.0), respectively. Using the best practice PAM50/claudin-low microarray-based classifier, all metaplastic breast carcinomas with spindle cell metaplasia were of claudin-low subtype, whereas those with squamous or chondroid metaplasia were preferentially of basal-like subtype. Triple-negative breast cancer subtyping using a dedicated website (http://cbc.mc.vanderbilt.edu/tnbc/) revealed that all metaplastic breast carcinomas with chondroid metaplasia were of mesenchymal-like subtype, spindle cell carcinomas preferentially of unstable or mesenchymal stem-like subtype, and those with squamous metaplasia were of multiple subtypes. None of the cases was classified as immunomodulatory or luminal androgen receptor subtype. Integrative clustering, combining gene expression and gene copy number data, revealed that metaplastic breast carcinomas with spindle cell and chondroid metaplasia were preferentially classified as of integrative clusters 4 and 9, respectively, whereas those with squamous metaplasia were classified into six different clusters. Eight of the 26 metaplastic breast cancers subjected to SNP6 analysis were classified as BRCA1-like. The diversity of histologic features of metaplastic breast carcinomas is reflected at the transcriptomic level, and an association between molecular subtypes and histology was observed. BRCA1-like genomic profiles were found only in a subset (31%) of metaplastic breast cancers, and were not associated with a specific molecular or histologic subtype. PMID:25412848

Filtered selection coupled with support vector machines generate a functionally relevant prediction model for colorectal cancer

PubMed Central

Gabere, Musa Nur; Hussein, Mohamed Aly; Aziz, Mohammad Azhar

2016-01-01

Purpose There has been considerable interest in using whole-genome expression profiles for the classification of colorectal cancer (CRC). The selection of important features is a crucial step before training a classifier. Methods In this study, we built a model that uses support vector machine (SVM) to classify cancer and normal samples using Affymetrix exon microarray data obtained from 90 samples of 48 patients diagnosed with CRC. From the 22,011 genes, we selected the 20, 30, 50, 100, 200, 300, and 500 genes most relevant to CRC using the minimum-redundancy–maximum-relevance (mRMR) technique. With these gene sets, an SVM model was designed using four different kernel types (linear, polynomial, radial basis function [RBF], and sigmoid). Results The best model, which used 30 genes and RBF kernel, outperformed other combinations; it had an accuracy of 84% for both ten fold and leave-one-out cross validations in discriminating the cancer samples from the normal samples. With this 30 genes set from mRMR, six classifiers were trained using random forest (RF), Bayes net (BN), multilayer perceptron (MLP), naïve Bayes (NB), reduced error pruning tree (REPT), and SVM. Two hybrids, mRMR + SVM and mRMR + BN, were the best models when tested on other datasets, and they achieved a prediction accuracy of 95.27% and 91.99%, respectively, compared to other mRMR hybrid models (mRMR + RF, mRMR + NB, mRMR + REPT, and mRMR + MLP). Ingenuity pathway analysis was used to analyze the functions of the 30 genes selected for this model and their potential association with CRC: CDH3, CEACAM7, CLDN1, IL8, IL6R, MMP1, MMP7, and TGFB1 were predicted to be CRC biomarkers. Conclusion This model could be used to further develop a diagnostic tool for predicting CRC based on gene expression data from patient samples. PMID:27330311

Pro-oncogene Pokemon promotes breast cancer progression by upregulating survivin expression.

PubMed

Zu, Xuyu; Ma, Jun; Liu, Hongxia; Liu, Feng; Tan, Chunyan; Yu, Lingling; Wang, Jue; Xie, Zhenhua; Cao, Deliang; Jiang, Yuyang

2011-03-10

Pokemon is an oncogenic transcription factor involved in cell growth, differentiation and oncogenesis, but little is known about its role in human breast cancer. In this study, we aimed to reveal the role of Pokemon in breast cancer progression and patient survival and to understand its underlying mechanisms. Tissue microarray analysis of breast cancer tissues from patients with complete clinicopathological data and more than 20 years of follow-up were used to evaluate Pokemon expression and its correlation with the progression and prognosis of the disease. DNA microarray analysis of MCF-7 cells that overexpress Pokemon was used to identify Pokemon target genes. Chromatin immunoprecipitation (ChIP) and site-directed mutagenesis were utilized to determine how Pokemon regulates survivin expression, a target gene. Pokemon was found to be overexpressed in 158 (86.8%) of 182 breast cancer tissues, and its expression was correlated with tumor size (P = 0.0148) and lymph node metastasis (P = 0.0014). Pokemon expression led to worse overall (n = 175, P = 0.01) and disease-related (n = 79, P = 0.0134) patient survival. DNA microarray analyses revealed that in MCF-7 breast cancer cells, Pokemon regulates the expression of at least 121 genes involved in several signaling and metabolic pathways, including anti-apoptotic survivin. In clinical specimens, Pokemon and survivin expression were highly correlated (n = 49, r = 0.6799, P < 0.0001). ChIP and site-directed mutagenesis indicated that Pokemon induces survivin expression by binding to the GT boxes in its promoter. Pokemon promotes breast cancer progression by upregulating survivin expression and thus may be a potential target for the treatment of this malignancy.

Pro-oncogene Pokemon promotes breast cancer progression by upregulating survivin expression

PubMed Central

2011-01-01

Introduction Pokemon is an oncogenic transcription factor involved in cell growth, differentiation and oncogenesis, but little is known about its role in human breast cancer. In this study, we aimed to reveal the role of Pokemon in breast cancer progression and patient survival and to understand its underlying mechanisms. Methods Tissue microarray analysis of breast cancer tissues from patients with complete clinicopathological data and more than 20 years of follow-up were used to evaluate Pokemon expression and its correlation with the progression and prognosis of the disease. DNA microarray analysis of MCF-7 cells that overexpress Pokemon was used to identify Pokemon target genes. Chromatin immunoprecipitation (ChIP) and site-directed mutagenesis were utilized to determine how Pokemon regulates survivin expression, a target gene. Results Pokemon was found to be overexpressed in 158 (86.8%) of 182 breast cancer tissues, and its expression was correlated with tumor size (P = 0.0148) and lymph node metastasis (P = 0.0014). Pokemon expression led to worse overall (n = 175, P = 0.01) and disease-related (n = 79, P = 0.0134) patient survival. DNA microarray analyses revealed that in MCF-7 breast cancer cells, Pokemon regulates the expression of at least 121 genes involved in several signaling and metabolic pathways, including anti-apoptotic survivin. In clinical specimens, Pokemon and survivin expression were highly correlated (n = 49, r = 0.6799, P < 0.0001). ChIP and site-directed mutagenesis indicated that Pokemon induces survivin expression by binding to the GT boxes in its promoter. Conclusions Pokemon promotes breast cancer progression by upregulating survivin expression and thus may be a potential target for the treatment of this malignancy. PMID:21392388

Identification of consensus biomarkers for predicting non-genotoxic hepatocarcinogens

PubMed Central

Huang, Shan-Han; Tung, Chun-Wei

2017-01-01

The assessment of non-genotoxic hepatocarcinogens (NGHCs) is currently relying on two-year rodent bioassays. Toxicogenomics biomarkers provide a potential alternative method for the prioritization of NGHCs that could be useful for risk assessment. However, previous studies using inconsistently classified chemicals as the training set and a single microarray dataset concluded no consensus biomarkers. In this study, 4 consensus biomarkers of A2m, Ca3, Cxcl1, and Cyp8b1 were identified from four large-scale microarray datasets of the one-day single maximum tolerated dose and a large set of chemicals without inconsistent classifications. Machine learning techniques were subsequently applied to develop prediction models for NGHCs. The final bagging decision tree models were constructed with an average AUC performance of 0.803 for an independent test. A set of 16 chemicals with controversial classifications were reclassified according to the consensus biomarkers. The developed prediction models and identified consensus biomarkers are expected to be potential alternative methods for prioritization of NGHCs for further experimental validation. PMID:28117354

A Rational Approach for Discovering and Validating Cancer Markers in Very Small Samples Using Mass Spectrometry and ELISA Microarrays

DOE PAGES

Zangar, Richard C.; Varnum, Susan M.; Covington, Chandice Y.; ...

2004-01-01

Identifying useful markers of cancer can be problematic due to limited amounts of sample. Some samples such as nipple aspirate fluid (NAF) or early-stage tumors are inherently small. Other samples such as serum are collected in larger volumes but archives of these samples are very valuable and only small amounts of each sample may be available for a single study. Also, given the diverse nature of cancer and the inherent variability in individual protein levels, it seems likely that the best approach to screen for cancer will be to determine the profile of a battery of proteins. As a result,more » a major challenge in identifying protein markers of disease is the ability to screen many proteins using very small amounts of sample. In this review, we outline some technological advances in proteomics that greatly advance this capability. Specifically, we propose a strategy for identifying markers of breast cancer in NAF that utilizes mass spectrometry (MS) to simultaneously screen hundreds or thousands of proteins in each sample. The best potential markers identified by the MS analysis can then be extensively characterized using an ELISA microarray assay. Because the microarray analysis is quantitative and large numbers of samples can be efficiently analyzed, this approach offers the ability to rapidly assess a battery of selected proteins in a manner that is directly relevant to traditional clinical assays.« less

Next-generation sequencing for endocrine cancers: Recent advances and challenges.

PubMed

Suresh, Padmanaban S; Venkatesh, Thejaswini; Tsutsumi, Rie; Shetty, Abhishek

2017-05-01

Contemporary molecular biology research tools have enriched numerous areas of biomedical research that address challenging diseases, including endocrine cancers (pituitary, thyroid, parathyroid, adrenal, testicular, ovarian, and neuroendocrine cancers). These tools have placed several intriguing clues before the scientific community. Endocrine cancers pose a major challenge in health care and research despite considerable attempts by researchers to understand their etiology. Microarray analyses have provided gene signatures from many cells, tissues, and organs that can differentiate healthy states from diseased ones, and even show patterns that correlate with stages of a disease. Microarray data can also elucidate the responses of endocrine tumors to therapeutic treatments. The rapid progress in next-generation sequencing methods has overcome many of the initial challenges of these technologies, and their advantages over microarray techniques have enabled them to emerge as valuable aids for clinical research applications (prognosis, identification of drug targets, etc.). A comprehensive review describing the recent advances in next-generation sequencing methods and their application in the evaluation of endocrine and endocrine-related cancers is lacking. The main purpose of this review is to illustrate the concepts that collectively constitute our current view of the possibilities offered by next-generation sequencing technological platforms, challenges to relevant applications, and perspectives on the future of clinical genetic testing of patients with endocrine tumors. We focus on recent discoveries in the use of next-generation sequencing methods for clinical diagnosis of endocrine tumors in patients and conclude with a discussion on persisting challenges and future objectives.

Dual-modal cancer detection based on optical pH sensing and Raman spectroscopy.

PubMed

Kim, Soogeun; Lee, Seung Ho; Min, Sun Young; Byun, Kyung Min; Lee, Soo Yeol

2017-10-01

A dual-modal approach using Raman spectroscopy and optical pH sensing was investigated to discriminate between normal and cancerous tissues. Raman spectroscopy has demonstrated the potential for in vivo cancer detection. However, Raman spectroscopy has suffered from strong fluorescence background of biological samples and subtle spectral differences between normal and disease tissues. To overcome those issues, pH sensing is adopted to Raman spectroscopy as a dual-modal approach. Based on the fact that the pH level in cancerous tissues is lower than that in normal tissues due to insufficient vasculature formation, the dual-modal approach combining the chemical information of Raman spectrum and the metabolic information of pH level can improve the specificity of cancer diagnosis. From human breast tissue samples, Raman spectra and pH levels are measured using fiber-optic-based Raman and pH probes, respectively. The pH sensing is based on the dependence of pH level on optical transmission spectrum. Multivariate statistical analysis is performed to evaluate the classification capability of the dual-modal method. The analytical results show that the dual-modal method based on Raman spectroscopy and optical pH sensing can improve the performance of cancer classification. (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE).

Tumor Acquisition for Biomarker Research in Lung Cancer

PubMed Central

Stevenson, Marvaretta; Christensen, Jared; Shoemaker, Debra; Foster, Traci; Barry, William T.; Tong, Betty C.; Wahidi, Momen; Shofer, Scott; Datto, Michael; Ginsburg, Geoffrey; Crawford, Jeffrey; D’Amico, Thomas; Ready, Neal

2015-01-01

The biopsy collection data from two lung cancer trials that required fresh tumor samples be obtained for microarray analysis were reviewed. In the trial for advanced disease, microarray data were obtained on 50 patient samples, giving an overall success rate of 60.2%. The majority of the specimens were obtained through CT-guided lung biopsies (N=30). In the trial for early-stage patients, 28 tissue specimens were collected from excess tumor after surgical resection with a success rate of 85.7%. This tissue procurement program documents the feasibility in obtaining fresh tumor specimens prospectively that could be used for molecular testing. PMID:24810245

The classification of lung cancers and their degree of malignancy by FTIR, PCA-LDA analysis, and a physics-based computational model.

PubMed

Kaznowska, E; Depciuch, J; Łach, K; Kołodziej, M; Koziorowska, A; Vongsvivut, J; Zawlik, I; Cholewa, M; Cebulski, J

2018-08-15

Lung cancer has the highest mortality rate of all malignant tumours. The current effects of cancer treatment, as well as its diagnostics, are unsatisfactory. Therefore it is very important to introduce modern diagnostic tools, which will allow for rapid classification of lung cancers and their degree of malignancy. For this purpose, the authors propose the use of Fourier Transform InfraRed (FTIR) spectroscopy combined with Principal Component Analysis-Linear Discriminant Analysis (PCA-LDA) and a physics-based computational model. The results obtained for lung cancer tissues, adenocarcinoma and squamous cell carcinoma FTIR spectra, show a shift in wavenumbers compared to control tissue FTIR spectra. Furthermore, in the FTIR spectra of adenocarcinoma there are no peaks corresponding to glutamate or phospholipid functional groups. Moreover, in the case of G2 and G3 malignancy of adenocarcinoma lung cancer, the absence of an OH groups peak was noticed. Thus, it seems that FTIR spectroscopy is a valuable tool to classify lung cancer and to determine the degree of its malignancy. Copyright © 2018 Elsevier B.V. All rights reserved.

Inhibition of Breast Cancer Progression by Blocking Heterocellular Contact Between Epithelial Cells and Fibroblasts

DTIC Science & Technology

2013-04-01

by employing a microfluidic -based compartmentalized 3D co-culture platform enabling both contact-free and contact-associated co-cultures. 15...SUBJECT TERMS Heterocellular contact between cancer cells and stromal fibroblasts, Microfluidics , 3D 16. SECURITY CLASSIFICATION OF: 17. LIMITATION...and human mammary fibroblasts (HMFs) in breast cancer progression by employing a microfluidic - based compartmentalized 3D co-culture platform

A "TNM" classification system for cancer pain: the Edmonton Classification System for Cancer Pain (ECS-CP).

PubMed

Fainsinger, Robin L; Nekolaichuk, Cheryl L

2008-06-01

The purpose of this paper is to provide an overview of the development of a "TNM" cancer pain classification system for advanced cancer patients, the Edmonton Classification System for Cancer Pain (ECS-CP). Until we have a common international language to discuss cancer pain, understanding differences in clinical and research experience in opioid rotation and use remains problematic. The complexity of the cancer pain experience presents unique challenges for the classification of pain. To date, no universally accepted pain classification measure can accurately predict the complexity of pain management, particularly for patients with cancer pain that is difficult to treat. In response to this gap in clinical assessment, the Edmonton Staging System (ESS), a classification system for cancer pain, was developed. Difficulties in definitions and interpretation of some aspects of the ESS restricted acceptance and widespread use. Construct, inter-rater reliability, and predictive validity evidence have contributed to the development of the ECS-CP. The five features of the ECS-CP--Pain Mechanism, Incident Pain, Psychological Distress, Addictive Behavior and Cognitive Function--have demonstrated value in predicting pain management complexity. The development of a standardized classification system that is comprehensive, prognostic and simple to use could provide a common language for clinical management and research of cancer pain. An international study to assess the inter-rater reliability and predictive value of the ECS-CP is currently in progress.

Ugene, a newly identified protein that is commonly over-expressed in cancer, and that binds uracil DNA-glycosylase

PubMed Central

Guo, Chunguang; Zhang, Xiaodong; Fink, Stephen P; Platzer, Petra; Wilson, Keith; Willson, James K. V.; Wang, Zhenghe; Markowitz, Sanford D

2008-01-01

Expression microarrays identified a novel transcript, designated as Ugene, whose expression is absent in normal colon and colon adenomas, but that is commonly induced in malignant colon cancers. These findings were validated by real-time PCR and Northern blot analysis in an independent panel of colon cancer cases. In addition, Ugene expression was found to be elevated in many other common cancer types, including, breast, lung, uterus, and ovary. Immunofluorescence of V5-tagged Ugene revealed it to have a nuclear localization. In a pull-down assay, uracil DNA-glycosylase 2 (UNG2), an important enzyme in the base excision repair pathway, was identified as a partner protein that binds to Ugene. Co-immunoprecipitation and Western blot analysis confirmed the binding between the endogenous Ugene and UNG2 proteins. Using deletion constructs, we find that Ugene binds to the first 25 amino acids of the UNG2 NH2-terminus. We suggest Ugene induction in cancer may contribute to the cancer phenotype by interacting with the base excision repair pathway. PMID:18676834

Two-dimensional shape classification using generalized Fourier representation and neural networks

NASA Astrophysics Data System (ADS)

Chodorowski, Artur; Gustavsson, Tomas; Mattsson, Ulf

2000-04-01

A shape-based classification method is developed based upon the Generalized Fourier Representation (GFR). GFR can be regarded as an extension of traditional polar Fourier descriptors, suitable for description of closed objects, both convex and concave, with or without holes. Explicit relations of GFR coefficients to regular moments, moment invariants and affine moment invariants are given in the paper. The dual linear relation between GFR coefficients and regular moments was used to compare shape features derive from GFR descriptors and Hu's moment invariants. the GFR was then applied to a clinical problem within oral medicine and used to represent the contours of the lesions in the oral cavity. The lesions studied were leukoplakia and different forms of lichenoid reactions. Shape features were extracted from GFR coefficients in order to classify potentially cancerous oral lesions. Alternative classifiers were investigated based on a multilayer perceptron with different architectures and extensions. The overall classification accuracy for recognition of potentially cancerous oral lesions when using neural network classifier was 85%, while the classification between leukoplakia and reticular lichenoid reactions gave 96% (5-fold cross-validated) recognition rate.

Cell Proliferation (KI-67) Expression Is Associated with Poorer Prognosis in Nigerian Compared to British Breast Cancer Women

PubMed Central

Agboola, Ayodeji O. J.; Banjo, Adekumbiola A. F.; Anunobi, Charles C.; Salami, Babatunde; Agboola, Mopelola Deji; Musa, Adewale A.; Nolan, Christopher C.; Rakha, Emad A.; Ellis, Ian O.; Green, Andrew R.

2013-01-01

Background. Black women with breast cancer (BC) in Nigeria have higher mortality rate compared with British women. This study investigated prognostic features of cell proliferation biomarker (Ki-67) in Nigerian breast cancer women. Materials and Methods. The protein expression of Ki-67 was investigated in series of 308 Nigerian women, prepared as a tissue microarray (TMA), using immunohistochemistry. Clinic-pathological parameters, biomarkers, and patient outcome of tumours expressing Ki-67 in Nigerian women were correlated with UK grade-matched series. Results. A significantly larger proportion of breast tumours from Nigerian women showed high Ki-67 expression. Those tumours were significantly correlated with negative expression of the steroid hormone receptors (ER and PgR), p21, p27, E-cadherin, BRCA-1, and Bcl-2 (all P < 0.001), but positively associated with EGFR (P = 0.003), p53, basal cytokeratins: CK56, CK14, triple negative, and basal phenotype using Nielsen's classification (all P < 0.001) compared to UK women. Multivariate analyses showed that race was also associated with BCSS independent of tumour size, lymph node status, and ER status. Conclusion. Ki-67 expression was observed to have contributed to the difference in the BCSS in Nigerian compared with British BC women. Therefore, targeting Ki-67 in the indigenous black women with BC might improve the patient outcome in the black women with BC. PMID:23691362

Classification of mislabelled microarrays using robust sparse logistic regression.

PubMed

Bootkrajang, Jakramate; Kabán, Ata

2013-04-01

Previous studies reported that labelling errors are not uncommon in microarray datasets. In such cases, the training set may become misleading, and the ability of classifiers to make reliable inferences from the data is compromised. Yet, few methods are currently available in the bioinformatics literature to deal with this problem. The few existing methods focus on data cleansing alone, without reference to classification, and their performance crucially depends on some tuning parameters. In this article, we develop a new method to detect mislabelled arrays simultaneously with learning a sparse logistic regression classifier. Our method may be seen as a label-noise robust extension of the well-known and successful Bayesian logistic regression classifier. To account for possible mislabelling, we formulate a label-flipping process as part of the classifier. The regularization parameter is automatically set using Bayesian regularization, which not only saves the computation time that cross-validation would take, but also eliminates any unwanted effects of label noise when setting the regularization parameter. Extensive experiments with both synthetic data and real microarray datasets demonstrate that our approach is able to counter the bad effects of labelling errors in terms of predictive performance, it is effective at identifying marker genes and simultaneously it detects mislabelled arrays to high accuracy. The code is available from http://cs.bham.ac.uk/∼jxb008. Supplementary data are available at Bioinformatics online.

Enhancing Breast Cancer Recurrence Algorithms Through Selective Use of Medical Record Data.

PubMed

Kroenke, Candyce H; Chubak, Jessica; Johnson, Lisa; Castillo, Adrienne; Weltzien, Erin; Caan, Bette J

2016-03-01

The utility of data-based algorithms in research has been questioned because of errors in identification of cancer recurrences. We adapted previously published breast cancer recurrence algorithms, selectively using medical record (MR) data to improve classification. We evaluated second breast cancer event (SBCE) and recurrence-specific algorithms previously published by Chubak and colleagues in 1535 women from the Life After Cancer Epidemiology (LACE) and 225 women from the Women's Health Initiative cohorts and compared classification statistics to published values. We also sought to improve classification with minimal MR examination. We selected pairs of algorithms-one with high sensitivity/high positive predictive value (PPV) and another with high specificity/high PPV-using MR information to resolve discrepancies between algorithms, properly classifying events based on review; we called this "triangulation." Finally, in LACE, we compared associations between breast cancer survival risk factors and recurrence using MR data, single Chubak algorithms, and triangulation. The SBCE algorithms performed well in identifying SBCE and recurrences. Recurrence-specific algorithms performed more poorly than published except for the high-specificity/high-PPV algorithm, which performed well. The triangulation method (sensitivity = 81.3%, specificity = 99.7%, PPV = 98.1%, NPV = 96.5%) improved recurrence classification over two single algorithms (sensitivity = 57.1%, specificity = 95.5%, PPV = 71.3%, NPV = 91.9%; and sensitivity = 74.6%, specificity = 97.3%, PPV = 84.7%, NPV = 95.1%), with 10.6% MR review. Triangulation performed well in survival risk factor analyses vs analyses using MR-identified recurrences. Use of multiple recurrence algorithms in administrative data, in combination with selective examination of MR data, may improve recurrence data quality and reduce research costs. © The Author 2015. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

Enhancing Breast Cancer Recurrence Algorithms Through Selective Use of Medical Record Data

PubMed Central

Chubak, Jessica; Johnson, Lisa; Castillo, Adrienne; Weltzien, Erin; Caan, Bette J.

2016-01-01

Abstract Background: The utility of data-based algorithms in research has been questioned because of errors in identification of cancer recurrences. We adapted previously published breast cancer recurrence algorithms, selectively using medical record (MR) data to improve classification. Methods: We evaluated second breast cancer event (SBCE) and recurrence-specific algorithms previously published by Chubak and colleagues in 1535 women from the Life After Cancer Epidemiology (LACE) and 225 women from the Women’s Health Initiative cohorts and compared classification statistics to published values. We also sought to improve classification with minimal MR examination. We selected pairs of algorithms—one with high sensitivity/high positive predictive value (PPV) and another with high specificity/high PPV—using MR information to resolve discrepancies between algorithms, properly classifying events based on review; we called this “triangulation.” Finally, in LACE, we compared associations between breast cancer survival risk factors and recurrence using MR data, single Chubak algorithms, and triangulation. Results: The SBCE algorithms performed well in identifying SBCE and recurrences. Recurrence-specific algorithms performed more poorly than published except for the high-specificity/high-PPV algorithm, which performed well. The triangulation method (sensitivity = 81.3%, specificity = 99.7%, PPV = 98.1%, NPV = 96.5%) improved recurrence classification over two single algorithms (sensitivity = 57.1%, specificity = 95.5%, PPV = 71.3%, NPV = 91.9%; and sensitivity = 74.6%, specificity = 97.3%, PPV = 84.7%, NPV = 95.1%), with 10.6% MR review. Triangulation performed well in survival risk factor analyses vs analyses using MR-identified recurrences. Conclusions: Use of multiple recurrence algorithms in administrative data, in combination with selective examination of MR data, may improve recurrence data quality and reduce research costs. PMID:26582243

Revision concepts and distinctive points of the new Japanese classification for biliary tract cancers in comparison with the 7(th) edition of the Union for International Cancer Control and the American Joint Committee on Cancer staging system.

PubMed

Ohtsuka, Masayuki; Miyakawa, Shuichi; Nagino, Masato; Takada, Tadahiro; Miyazaki, Masaru

2015-03-01

The 3(rd) English edition of the Japanese classification of the biliary tract cancers (JC) is now available in this journal. The primary aim of this revision is to provide all clinicians and researchers with a common language of cancer staging at an international level. On the other hand, there are several important issues that should be solved for the optimization of the staging system. Revision concepts and major revision points of the 3(rd) English edition of the JC were reviewed. Furthermore, comparing with the 7(th) edition of staging system developed by the Union for International Cancer Control (UICC) and the American Joint Committee on Cancer (AJCC), distinctive points in the JC was discussed. In this edition of the JC, the same stage groupings as those in the UICC/AJCC staging system were basically adopted. T, N, and M categories were also identical in principle with those in the UICC/AJCC staging system, although slight modifications were proposed as the "Japanese rules". As distinctive points, perihilar cholangiocarcinomas and ampullary region carcinomas were clearly defined. Intraepithelial tumor was discriminated from invasive carcinoma at ductal resection margins. Classifications of site-specific surgical margin status remained in this edition. Histological classification was based on that in the former editions of the JC, but adopted some parts of the World Health Organization classification. The JC now share its staging system of the biliary tact carcinomas with the UICC/AJCC staging system. Future validation of the "Japanese rules" could provide important evidence to make globally standardized staging system. © 2015 Japanese Society of Hepato-Biliary-Pancreatic Surgery.

Recursive Partitioning Analysis for New Classification of Patients With Esophageal Cancer Treated by Chemoradiotherapy

DOE Office of Scientific and Technical Information (OSTI.GOV)

Nomura, Motoo, E-mail: excell@hkg.odn.ne.jp; Department of Clinical Oncology, Aichi Cancer Center Hospital, Nagoya; Department of Radiation Oncology, Aichi Cancer Center Hospital, Nagoya

2012-11-01

Background: The 7th edition of the American Joint Committee on Cancer staging system does not include lymph node size in the guidelines for staging patients with esophageal cancer. The objectives of this study were to determine the prognostic impact of the maximum metastatic lymph node diameter (ND) on survival and to develop and validate a new staging system for patients with esophageal squamous cell cancer who were treated with definitive chemoradiotherapy (CRT). Methods: Information on 402 patients with esophageal cancer undergoing CRT at two institutions was reviewed. Univariate and multivariate analyses of data from one institution were used to assessmore » the impact of clinical factors on survival, and recursive partitioning analysis was performed to develop the new staging classification. To assess its clinical utility, the new classification was validated using data from the second institution. Results: By multivariate analysis, gender, T, N, and ND stages were independently and significantly associated with survival (p < 0.05). The resulting new staging classification was based on the T and ND. The four new stages led to good separation of survival curves in both the developmental and validation datasets (p < 0.05). Conclusions: Our results showed that lymph node size is a strong independent prognostic factor and that the new staging system, which incorporated lymph node size, provided good prognostic power, and discriminated effectively for patients with esophageal cancer undergoing CRT.« less

Comprehensive analysis of differentially expressed profiles of lncRNAs and construction of miR-133b mediated ceRNA network in colorectal cancer.

PubMed

Wu, Hao; Wu, Runliu; Chen, Miao; Li, Daojiang; Dai, Jing; Zhang, Yi; Gao, Kai; Yu, Jun; Hu, Gui; Guo, Yihang; Lin, Changwei; Li, Xiaorong

2017-03-28

Growing evidence suggests that long non-coding RNAs (lncRNAs) play a key role in tumorigenesis. However, the mechanism remains largely unknown. Thousands of significantly dysregulated lncRNAs and mRNAs were identified by microarray. Furthermore, a miR-133b-meditated lncRNA-mRNA ceRNA network was revealed, a subset of which was validated in 14 paired CRC patient tumor/non-tumor samples. Gene set enrichment analysis (GSEA) results demonstrated that lncRNAs ENST00000520055 and ENST00000535511 shared KEGG pathways with miR-133b target genes. We used microarrays to survey the lncRNA and mRNA expression profiles of colorectal cancer and para-cancer tissues. Gene Ontology (GO) and KEGG pathway enrichment analyses were performed to explore the functions of the significantly dysregulated genes. An innovate method was employed that combined analyses of two microarray data sets to construct a miR-133b-mediated lncRNA-mRNA competing endogenous RNAs (ceRNA) network. Quantitative RT-PCR analysis was used to validate part of this network. GSEA was used to predict the potential functions of these lncRNAs. This study identifies and validates a new method to investigate the miR-133b-mediated lncRNA-mRNA ceRNA network and lays the foundation for future investigation into the role of lncRNAs in colorectal cancer.

Pulsed terahertz imaging of breast cancer in freshly excised murine tumors

NASA Astrophysics Data System (ADS)

Bowman, Tyler; Chavez, Tanny; Khan, Kamrul; Wu, Jingxian; Chakraborty, Avishek; Rajaram, Narasimhan; Bailey, Keith; El-Shenawee, Magda

2018-02-01

This paper investigates terahertz (THz) imaging and classification of freshly excised murine xenograft breast cancer tumors. These tumors are grown via injection of E0771 breast adenocarcinoma cells into the flank of mice maintained on high-fat diet. Within 1 h of excision, the tumor and adjacent tissues are imaged using a pulsed THz system in the reflection mode. The THz images are classified using a statistical Bayesian mixture model with unsupervised and supervised approaches. Correlation with digitized pathology images is conducted using classification images assigned by a modal class decision rule. The corresponding receiver operating characteristic curves are obtained based on the classification results. A total of 13 tumor samples obtained from 9 tumors are investigated. The results show good correlation of THz images with pathology results in all samples of cancer and fat tissues. For tumor samples of cancer, fat, and muscle tissues, THz images show reasonable correlation with pathology where the primary challenge lies in the overlapping dielectric properties of cancer and muscle tissues. The use of a supervised regression approach shows improvement in the classification images although not consistently in all tissue regions. Advancing THz imaging of breast tumors from mice and the development of accurate statistical models will ultimately progress the technique for the assessment of human breast tumor margins.

Artificial intelligence in hematology.

PubMed

Zini, Gina

2005-10-01

Artificial intelligence (AI) is a computer based science which aims to simulate human brain faculties using a computational system. A brief history of this new science goes from the creation of the first artificial neuron in 1943 to the first artificial neural network application to genetic algorithms. The potential for a similar technology in medicine has immediately been identified by scientists and researchers. The possibility to store and process all medical knowledge has made this technology very attractive to assist or even surpass clinicians in reaching a diagnosis. Applications of AI in medicine include devices applied to clinical diagnosis in neurology and cardiopulmonary diseases, as well as the use of expert or knowledge-based systems in routine clinical use for diagnosis, therapeutic management and for prognostic evaluation. Biological applications include genome sequencing or DNA gene expression microarrays, modeling gene networks, analysis and clustering of gene expression data, pattern recognition in DNA and proteins, protein structure prediction. In the field of hematology the first devices based on AI have been applied to the routine laboratory data management. New tools concern the differential diagnosis in specific diseases such as anemias, thalassemias and leukemias, based on neural networks trained with data from peripheral blood analysis. A revolution in cancer diagnosis, including the diagnosis of hematological malignancies, has been the introduction of the first microarray based and bioinformatic approach for molecular diagnosis: a systematic approach based on the monitoring of simultaneous expression of thousands of genes using DNA microarray, independently of previous biological knowledge, analysed using AI devices. Using gene profiling, the traditional diagnostic pathways move from clinical to molecular based diagnostic systems.

A hybrid approach to select features and classify diseases based on medical data

NASA Astrophysics Data System (ADS)

AbdelLatif, Hisham; Luo, Jiawei

2018-03-01

Feature selection is popular problem in the classification of diseases in clinical medicine. Here, we developing a hybrid methodology to classify diseases, based on three medical datasets, Arrhythmia, Breast cancer, and Hepatitis datasets. This methodology called k-means ANOVA Support Vector Machine (K-ANOVA-SVM) uses K-means cluster with ANOVA statistical to preprocessing data and selection the significant features, and Support Vector Machines in the classification process. To compare and evaluate the performance, we choice three classification algorithms, decision tree Naïve Bayes, Support Vector Machines and applied the medical datasets direct to these algorithms. Our methodology was a much better classification accuracy is given of 98% in Arrhythmia datasets, 92% in Breast cancer datasets and 88% in Hepatitis datasets, Compare to use the medical data directly with decision tree Naïve Bayes, and Support Vector Machines. Also, the ROC curve and precision with (K-ANOVA-SVM) Achieved best results than other algorithms

Hybrid analysis for indicating patients with breast cancer using temperature time series.

PubMed

Silva, Lincoln F; Santos, Alair Augusto S M D; Bravo, Renato S; Silva, Aristófanes C; Muchaluat-Saade, Débora C; Conci, Aura

2016-07-01

Breast cancer is the most common cancer among women worldwide. Diagnosis and treatment in early stages increase cure chances. The temperature of cancerous tissue is generally higher than that of healthy surrounding tissues, making thermography an option to be considered in screening strategies of this cancer type. This paper proposes a hybrid methodology for analyzing dynamic infrared thermography in order to indicate patients with risk of breast cancer, using unsupervised and supervised machine learning techniques, which characterizes the methodology as hybrid. The dynamic infrared thermography monitors or quantitatively measures temperature changes on the examined surface, after a thermal stress. In the dynamic infrared thermography execution, a sequence of breast thermograms is generated. In the proposed methodology, this sequence is processed and analyzed by several techniques. First, the region of the breasts is segmented and the thermograms of the sequence are registered. Then, temperature time series are built and the k-means algorithm is applied on these series using various values of k. Clustering formed by k-means algorithm, for each k value, is evaluated using clustering validation indices, generating values treated as features in the classification model construction step. A data mining tool was used to solve the combined algorithm selection and hyperparameter optimization (CASH) problem in classification tasks. Besides the classification algorithm recommended by the data mining tool, classifiers based on Bayesian networks, neural networks, decision rules and decision tree were executed on the data set used for evaluation. Test results support that the proposed analysis methodology is able to indicate patients with breast cancer. Among 39 tested classification algorithms, K-Star and Bayes Net presented 100% classification accuracy. Furthermore, among the Bayes Net, multi-layer perceptron, decision table and random forest classification algorithms, an average accuracy of 95.38% was obtained. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Characterization of aldehyde dehydrogenase 1 high ovarian cancer cells: Towards targeted stem cell therapy.

PubMed

Sharrow, Allison C; Perkins, Brandy; Collector, Michael I; Yu, Wayne; Simons, Brian W; Jones, Richard J

2016-08-01

The cancer stem cell (CSC) paradigm hypothesizes that successful clinical eradication of CSCs may lead to durable remission for patients with ovarian cancer. Despite mounting evidence in support of ovarian CSCs, their phenotype and clinical relevance remain unclear. We and others have found high aldehyde dehydrogenase 1 (ALDH(high)) expression in a variety of normal and malignant stem cells, and sought to better characterize ALDH(high) cells in ovarian cancer. We compared ALDH(high) to ALDH(low) cells in two ovarian cancer models representing distinct subtypes: FNAR-C1 cells, derived from a spontaneous rat endometrioid carcinoma, and the human SKOV3 cell line (described as both serous and clear cell subtypes). We assessed these populations for stem cell features then analyzed expression by microarray and qPCR. ALDH(high) cells displayed CSC properties, including: smaller size, quiescence, regenerating the phenotypic diversity of the cell lines in vitro, lack of contact inhibition, nonadherent growth, multi-drug resistance, and in vivo tumorigenicity. Microarray and qPCR analysis of the expression of markers reported by others to enrich for ovarian CSCs revealed that ALDH(high) cells of both models showed downregulation of CD24, but inconsistent expression of CD44, KIT and CD133. However, the following druggable targets were consistently expressed in the ALDH(high) cells from both models: mTOR signaling, her-2/neu, CD47 and FGF18/FGFR3. Based on functional characterization, ALDH(high) ovarian cancer cells represent an ovarian CSC population. Differential gene expression identified druggable targets that have the potential for therapeutic efficacy against ovarian CSCs from multiple subtypes. Copyright © 2016 Elsevier Inc. All rights reserved.

Carbon ion irradiation of the human prostate cancer cell line PC3: A whole genome microarray study

PubMed Central

SUETENS, ANNELIES; MOREELS, MARJAN; QUINTENS, ROEL; CHIRIOTTI, SABINA; TABURY, KEVIN; MICHAUX, ARLETTE; GRÉGOIRE, VINCENT; BAATOUT, SARAH

2014-01-01

Hadrontherapy is a form of external radiation therapy, which uses beams of charged particles such as carbon ions. Compared to conventional radiotherapy with photons, the main advantage of carbon ion therapy is the precise dose localization along with an increased biological effectiveness. The first results obtained from prostate cancer patients treated with carbon ion therapy showed good local tumor control and survival rates. In view of this advanced treatment modality we investigated the effects of irradiation with different beam qualities on gene expression changes in the PC3 prostate adenocarcinoma cell line. For this purpose, PC3 cells were irradiated with various doses (0.0, 0.5 and 2.0 Gy) of carbon ions (LET=33.7 keV/μm) at the beam of the Grand Accélérateur National d’Ions Lourds (Caen, France). Comparative experiments with X-rays were performed at the Belgian Nuclear Research Centre. Genome-wide gene expression was analyzed using microarrays. Our results show a downregulation in many genes involved in cell cycle and cell organization processes after 2.0 Gy irradiation. This effect was more pronounced after carbon ion irradiation compared with X-rays. Furthermore, we found a significant downregulation of many genes related to cell motility. Several of these changes were confirmed using qPCR. In addition, recurrence-free survival analysis of prostate cancer patients based on one of these motility genes (FN1) revealed that patients with low expression levels had a prolonged recurrence-free survival time, indicating that this gene may be a potential prognostic biomarker for prostate cancer. Understanding how different radiation qualities affect the cellular behavior of prostate cancer cells is important to improve the clinical outcome of cancer radiation therapy. PMID:24504141

Differential receptor dependencies: expression and significance of muscarinic M1 receptors in the biology of prostate cancer.

PubMed

Mannan Baig, Abdul; Khan, Naveed A; Effendi, Vardah; Rana, Zohaib; Ahmad, H R; Abbas, Farhat

2017-01-01

Recent reports on acetylcholine muscarinic receptor subtype 3 (CHRM3) have shown its growth-promoting role in prostate cancer. Additional studies report the proliferative effect of the cholinergic agonist carbachol on prostate cancer by its agonistic action on CHRM3. This study shows that the type 1 acetylcholine muscarinic receptor (CHRM1) contributes toward the proliferation and growth of prostate cancer. We used growth and cytotoxic assays, the prostate cancer microarray database and CHRM downstream pathways' homology of CHRM subtypes to uncover multiple signals leading to the growth of prostate cancer. Growth assays showed that pilocarpine stimulates the proliferation of prostate cancer. Moreover, it shows that carbachol exerts an additional agonistic action on nicotinic cholinergic receptor of prostate cancer cells that can be blocked by tubocurarine. With the use of selective CHRM1 antagonists such as pirenzepine and dicyclomine, a considerable inhibition of proliferation of prostate cancer cell lines was observed in dose ranging from 15-60 µg/ml of dicyclomine. The microarray database of prostate cancer shows a dominant expression of CHRM1 in prostate cancer compared with other cholinergic subtypes. The bioinformatics of prostate cancer and CHRM pathways show that the downstream signalling include PIP3-AKT-CaM-mediated growth in LNCaP and PC3 cells. Our study suggests that antagonism of CHRM1 may be a potential therapeutic target against prostate cancer.

Protein and glycomic plasma markers for early detection of adenoma and colon cancer.

PubMed

Rho, Jung-Hyun; Ladd, Jon J; Li, Christopher I; Potter, John D; Zhang, Yuzheng; Shelley, David; Shibata, David; Coppola, Domenico; Yamada, Hiroyuki; Toyoda, Hidenori; Tada, Toshifumi; Kumada, Takashi; Brenner, Dean E; Hanash, Samir M; Lampe, Paul D

2018-03-01

To discover and confirm blood-based colon cancer early-detection markers. We created a high-density antibody microarray to detect differences in protein levels in plasma from individuals diagnosed with colon cancer <3 years after blood was drawn (ie, prediagnostic) and cancer-free, matched controls. Potential markers were tested on plasma samples from people diagnosed with adenoma or cancer, compared with controls. Components of an optimal 5-marker panel were tested via immunoblotting using a third sample set, Luminex assay in a large fourth sample set and immunohistochemistry (IHC) on tissue microarrays. In the prediagnostic samples, we found 78 significantly (t-test) increased proteins, 32 of which were confirmed in the diagnostic samples. From these 32, optimal 4-marker panels of BAG family molecular chaperone regulator 4 (BAG4), interleukin-6 receptor subunit beta (IL6ST), von Willebrand factor (VWF) and CD44 or epidermal growth factor receptor (EGFR) were established. Each panel member and the panels also showed increases in the diagnostic adenoma and cancer samples in independent third and fourth sample sets via immunoblot and Luminex, respectively. IHC results showed increased levels of BAG4, IL6ST and CD44 in adenoma and cancer tissues. Inclusion of EGFR and CD44 sialyl Lewis-A and Lewis-X content increased the panel performance. The protein/glycoprotein panel was statistically significantly higher in colon cancer samples, characterised by a range of area under the curves from 0.90 (95% CI 0.82 to 0.98) to 0.86 (95% CI 0.83 to 0.88), for the larger second and fourth sets, respectively. A panel including BAG4, IL6ST, VWF, EGFR and CD44 protein/glycomics performed well for detection of early stages of colon cancer and should be further examined in larger studies. Published by the BMJ Publishing Group Limited. For permission to use (where not already granted under a licence) please go to http://www.bmj.com/company/products-services/rights-and-licensing/.

CrossLink: a novel method for cross-condition classification of cancer subtypes.

PubMed

Ma, Chifeng; Sastry, Konduru S; Flore, Mario; Gehani, Salah; Al-Bozom, Issam; Feng, Yusheng; Serpedin, Erchin; Chouchane, Lotfi; Chen, Yidong; Huang, Yufei

2016-08-22

We considered the prediction of cancer classes (e.g. subtypes) using patient gene expression profiles that contain both systematic and condition-specific biases when compared with the training reference dataset. The conventional normalization-based approaches cannot guarantee that the gene signatures in the reference and prediction datasets always have the same distribution for all different conditions as the class-specific gene signatures change with the condition. Therefore, the trained classifier would work well under one condition but not under another. To address the problem of current normalization approaches, we propose a novel algorithm called CrossLink (CL). CL recognizes that there is no universal, condition-independent normalization mapping of signatures. In contrast, it exploits the fact that the signature is unique to its associated class under any condition and thus employs an unsupervised clustering algorithm to discover this unique signature. We assessed the performance of CL for cross-condition predictions of PAM50 subtypes of breast cancer by using a simulated dataset modeled after TCGA BRCA tumor samples with a cross-validation scheme, and datasets with known and unknown PAM50 classification. CL achieved prediction accuracy >73 %, highest among other methods we evaluated. We also applied the algorithm to a set of breast cancer tumors derived from Arabic population to assign a PAM50 classification to each tumor based on their gene expression profiles. A novel algorithm CrossLink for cross-condition prediction of cancer classes was proposed. In all test datasets, CL showed robust and consistent improvement in prediction performance over other state-of-the-art normalization and classification algorithms.

A comparative study of breast cancer diagnosis based on neural network ensemble via improved training algorithms.

PubMed

Azami, Hamed; Escudero, Javier

2015-08-01

Breast cancer is one of the most common types of cancer in women all over the world. Early diagnosis of this kind of cancer can significantly increase the chances of long-term survival. Since diagnosis of breast cancer is a complex problem, neural network (NN) approaches have been used as a promising solution. Considering the low speed of the back-propagation (BP) algorithm to train a feed-forward NN, we consider a number of improved NN trainings for the Wisconsin breast cancer dataset: BP with momentum, BP with adaptive learning rate, BP with adaptive learning rate and momentum, Polak-Ribikre conjugate gradient algorithm (CGA), Fletcher-Reeves CGA, Powell-Beale CGA, scaled CGA, resilient BP (RBP), one-step secant and quasi-Newton methods. An NN ensemble, which is a learning paradigm to combine a number of NN outputs, is used to improve the accuracy of the classification task. Results demonstrate that NN ensemble-based classification methods have better performance than NN-based algorithms. The highest overall average accuracy is 97.68% obtained by NN ensemble trained by RBP for 50%-50% training-test evaluation method.

Recurrent neural networks for breast lesion classification based on DCE-MRIs

NASA Astrophysics Data System (ADS)

Antropova, Natasha; Huynh, Benjamin; Giger, Maryellen

2018-02-01

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) plays a significant role in breast cancer screening, cancer staging, and monitoring response to therapy. Recently, deep learning methods are being rapidly incorporated in image-based breast cancer diagnosis and prognosis. However, most of the current deep learning methods make clinical decisions based on 2-dimentional (2D) or 3D images and are not well suited for temporal image data. In this study, we develop a deep learning methodology that enables integration of clinically valuable temporal components of DCE-MRIs into deep learning-based lesion classification. Our work is performed on a database of 703 DCE-MRI cases for the task of distinguishing benign and malignant lesions, and uses the area under the ROC curve (AUC) as the performance metric in conducting that task. We train a recurrent neural network, specifically a long short-term memory network (LSTM), on sequences of image features extracted from the dynamic MRI sequences. These features are extracted with VGGNet, a convolutional neural network pre-trained on a large dataset of natural images ImageNet. The features are obtained from various levels of the network, to capture low-, mid-, and high-level information about the lesion. Compared to a classification method that takes as input only images at a single time-point (yielding an AUC = 0.81 (se = 0.04)), our LSTM method improves lesion classification with an AUC of 0.85 (se = 0.03).

The prognostic efficacy and improvements of the 7th edition Union for International Cancer Control tumor-node-metastasis classifications for Chinese patients with gastric cancer: Results based on a retrospective three-decade population study.

PubMed

Gu, Huizi; Li, Dongmei; Zhu, Haitao; Zhang, Hao; Yu, Ying; Qin, Dongxue; Yi, Mei; Li, Xiang; Lu, Ping

2017-03-01

This study aimed to evaluate survival trends for patients with gastric cancer in northeast China in the most recent three decades and analyze the applicability of the UICC tumor-node-metastasis (TNM) classification 7th edition for Chinese patients with gastric cancer. A review of all inpatient and outpatient records of patients with gastric cancer was conducted in the first hospital of China Medical University and the Liaoning Cancer Hospital and Institute. All patients who met the inclusion criteria and were seen from January 1980 through December 2009 were included in the study. The primary outcome was 5-year survival, which was analyzed according to decade of diagnosis and TNM classifications. From 1980 through 2009, the 5-year survival rates for patients with gastric cancer (n=2414) increased from 39.1% to 57.3%. Decade of diagnosis was significantly associated with patient survival (p = 0.013), and the 5-year survival rate in the 2000s was remarkably higher than that in the 1980s and 1990s (p = 0.004 and 0.049, respectively). When classified according to the UICC TNM classification of gastric cancer 7th edition, the prognoses of stage IIIA and stage IIIB patients were not significantly different (p = 0.077). However, if stage T4b and stage N0 patients were classified as stage IIIA, the prognoses of stage IIIA and stage IIIB patients were significantly different (p < 0.001). Hence, there was a significant difference in survival during the three time periods in Northeast China. Classifying stage T4b and stage N0 patients as stage IIIA according to the 7th edition of UICC gastric cancer TNM classifications better stratified Chinese patients and predicted prognoses.

Recent time trends in cancer of the oesophagus and gastric cardia in the region of Calvados in France, 1978-1995: a population based study.

PubMed

Desoubeaux, N; Le Prieur, A; Launoy, G; Maurel, J; Lefevre, H; Guillois, J M; Gignoux, M

1999-12-01

The incidence of oesophageal cancer differs from country to country, and even between areas of the same country. Many studies in recent years have shown an upward trend of a particular histologic type: adenocarcinoma of the oesophagus. It is difficult to precisely locate adenocarcinomas situated at the junction between the oesophagus and the gastric cardia. Clear criteria to define and classify such tumours are essential in order to analyse their evolution. The present study describes the changing incidence of cancers of the oesophagus and gastric cardia according to histologic type from 1978 to 1995 in Calvados, the highest-risk French region with two different topographic classifications of adenocarcinomas: one based on Misumi's criteria and the other based on local extension of cancer. In total, 1835 cancers of the oesophagus and gastric cardia were diagnosed in this period. Incidence rates for oesophageal and gastric cardia cancers standardized on the world population were 24.4/10(5) and 2.4/10(5) in men and 1.4/10(5) and 0.4/10(5) in women, respectively. The time trend in the incidence of squamous cell cancers was downward in men -0.74 (P < 10(-6)) and stable in women +0.04 (P = 0.65). Regarding adenocarcinomas, with the classification based on Misumi's categories, there was a slight but significant upward trend for oesophageal adenocarcinoma in men [mean annual variation of +0.09 (P < 10(-5))] while the tendency was downward and significant for gastric cardia adenocarcinoma [mean annual variation of -0.09 (P < 10(-4))]. When adenocarcinomas of the oesophagus and those of the gastric cardia with oesophageal involvement are taken together (second classification), there was an upward trend which was not significant in men and was significant in women. There was no such upward trend in adenocarcinomas limited to the gastric cardia and/or involving the stomach. Because of the difficulties in determining accurate localization routinely in population-based studies, it seems sensible to preclude classification biases in recommending the grouping together of gastric cardia adenocarcinomas with oesophageal adenocarcinomas, at least with those among the latter occurring in the lower third of the oesophagus.

Automatic classification of ovarian cancer types from cytological images using deep convolutional neural networks.

PubMed

Wu, Miao; Yan, Chuanbo; Liu, Huiqiang; Liu, Qian

2018-06-29

Ovarian cancer is one of the most common gynecologic malignancies. Accurate classification of ovarian cancer types (serous carcinoma, mucous carcinoma, endometrioid carcinoma, transparent cell carcinoma) is an essential part in the different diagnosis. Computer-aided diagnosis (CADx) can provide useful advice for pathologists to determine the diagnosis correctly. In our study, we employed a Deep Convolutional Neural Networks (DCNN) based on AlexNet to automatically classify the different types of ovarian cancers from cytological images. The DCNN consists of five convolutional layers, three max pooling layers, and two full reconnect layers. Then we trained the model by two group input data separately, one was original image data and the other one was augmented image data including image enhancement and image rotation. The testing results are obtained by the method of 10-fold cross-validation, showing that the accuracy of classification models has been improved from 72.76 to 78.20% by using augmented images as training data. The developed scheme was useful for classifying ovarian cancers from cytological images. © 2018 The Author(s).

Cross-platform method for identifying candidate network biomarkers for prostate cancer.

PubMed

Jin, G; Zhou, X; Cui, K; Zhang, X-S; Chen, L; Wong, S T C

2009-11-01

Discovering biomarkers using mass spectrometry (MS) and microarray expression profiles is a promising strategy in molecular diagnosis. Here, the authors proposed a new pipeline for biomarker discovery that integrates disease information for proteins and genes, expression profiles in both genomic and proteomic levels, and protein-protein interactions (PPIs) to discover high confidence network biomarkers. Using this pipeline, a total of 474 molecules (genes and proteins) related to prostate cancer were identified and a prostate-cancer-related network (PCRN) was derived from the integrative information. Thus, a set of candidate network biomarkers were identified from multiple expression profiles composed by eight microarray datasets and one proteomics dataset. The network biomarkers with PPIs can accurately distinguish the prostate patients from the normal ones, which potentially provide more reliable hits of biomarker candidates than conventional biomarker discovery methods.

Application of linear discriminant analysis and Attenuated Total Reflectance Fourier Transform Infrared microspectroscopy for diagnosis of colon cancer.

PubMed

Khanmohammadi, Mohammadreza; Bagheri Garmarudi, Amir; Samani, Simin; Ghasemi, Keyvan; Ashuri, Ahmad

2011-06-01

Attenuated Total Reflectance Fourier Transform Infrared (ATR-FTIR) microspectroscopy was applied for detection of colon cancer according to the spectral features of colon tissues. Supervised classification models can be trained to identify the tissue type based on the spectroscopic fingerprint. A total of 78 colon tissues were used in spectroscopy studies. Major spectral differences were observed in 1,740-900 cm(-1) spectral region. Several chemometric methods such as analysis of variance (ANOVA), cluster analysis (CA) and linear discriminate analysis (LDA) were applied for classification of IR spectra. Utilizing the chemometric techniques, clear and reproducible differences were observed between the spectra of normal and cancer cases, suggesting that infrared microspectroscopy in conjunction with spectral data processing would be useful for diagnostic classification. Using LDA technique, the spectra were classified into cancer and normal tissue classes with an accuracy of 95.8%. The sensitivity and specificity was 100 and 93.1%, respectively.

Elastic SCAD as a novel penalization method for SVM classification tasks in high-dimensional data.

PubMed

Becker, Natalia; Toedt, Grischa; Lichter, Peter; Benner, Axel

2011-05-09

Classification and variable selection play an important role in knowledge discovery in high-dimensional data. Although Support Vector Machine (SVM) algorithms are among the most powerful classification and prediction methods with a wide range of scientific applications, the SVM does not include automatic feature selection and therefore a number of feature selection procedures have been developed. Regularisation approaches extend SVM to a feature selection method in a flexible way using penalty functions like LASSO, SCAD and Elastic Net.We propose a novel penalty function for SVM classification tasks, Elastic SCAD, a combination of SCAD and ridge penalties which overcomes the limitations of each penalty alone.Since SVM models are extremely sensitive to the choice of tuning parameters, we adopted an interval search algorithm, which in comparison to a fixed grid search finds rapidly and more precisely a global optimal solution. Feature selection methods with combined penalties (Elastic Net and Elastic SCAD SVMs) are more robust to a change of the model complexity than methods using single penalties. Our simulation study showed that Elastic SCAD SVM outperformed LASSO (L1) and SCAD SVMs. Moreover, Elastic SCAD SVM provided sparser classifiers in terms of median number of features selected than Elastic Net SVM and often better predicted than Elastic Net in terms of misclassification error.Finally, we applied the penalization methods described above on four publicly available breast cancer data sets. Elastic SCAD SVM was the only method providing robust classifiers in sparse and non-sparse situations. The proposed Elastic SCAD SVM algorithm provides the advantages of the SCAD penalty and at the same time avoids sparsity limitations for non-sparse data. We were first to demonstrate that the integration of the interval search algorithm and penalized SVM classification techniques provides fast solutions on the optimization of tuning parameters.The penalized SVM classification algorithms as well as fixed grid and interval search for finding appropriate tuning parameters were implemented in our freely available R package 'penalizedSVM'.We conclude that the Elastic SCAD SVM is a flexible and robust tool for classification and feature selection tasks for high-dimensional data such as microarray data sets.

Elastic SCAD as a novel penalization method for SVM classification tasks in high-dimensional data

PubMed Central

2011-01-01

Background Classification and variable selection play an important role in knowledge discovery in high-dimensional data. Although Support Vector Machine (SVM) algorithms are among the most powerful classification and prediction methods with a wide range of scientific applications, the SVM does not include automatic feature selection and therefore a number of feature selection procedures have been developed. Regularisation approaches extend SVM to a feature selection method in a flexible way using penalty functions like LASSO, SCAD and Elastic Net. We propose a novel penalty function for SVM classification tasks, Elastic SCAD, a combination of SCAD and ridge penalties which overcomes the limitations of each penalty alone. Since SVM models are extremely sensitive to the choice of tuning parameters, we adopted an interval search algorithm, which in comparison to a fixed grid search finds rapidly and more precisely a global optimal solution. Results Feature selection methods with combined penalties (Elastic Net and Elastic SCAD SVMs) are more robust to a change of the model complexity than methods using single penalties. Our simulation study showed that Elastic SCAD SVM outperformed LASSO (L1) and SCAD SVMs. Moreover, Elastic SCAD SVM provided sparser classifiers in terms of median number of features selected than Elastic Net SVM and often better predicted than Elastic Net in terms of misclassification error. Finally, we applied the penalization methods described above on four publicly available breast cancer data sets. Elastic SCAD SVM was the only method providing robust classifiers in sparse and non-sparse situations. Conclusions The proposed Elastic SCAD SVM algorithm provides the advantages of the SCAD penalty and at the same time avoids sparsity limitations for non-sparse data. We were first to demonstrate that the integration of the interval search algorithm and penalized SVM classification techniques provides fast solutions on the optimization of tuning parameters. The penalized SVM classification algorithms as well as fixed grid and interval search for finding appropriate tuning parameters were implemented in our freely available R package 'penalizedSVM'. We conclude that the Elastic SCAD SVM is a flexible and robust tool for classification and feature selection tasks for high-dimensional data such as microarray data sets. PMID:21554689

Integrated genomic and immunophenotypic classification of pancreatic cancer reveals three distinct subtypes with prognostic/predictive significance.

PubMed

Wartenberg, Martin; Cibin, Silvia; Zlobec, Inti; Vassella, Erik; Eppenberger-Castori, Serenella M M; Terracciano, Luigi; Eichmann, Micha; Worni, Mathias; Gloor, Beat; Perren, Aurel; Karamitopoulou, Eva

2018-04-16

Current clinical classification of pancreatic ductal adenocarcinoma (PDAC) is unable to predict prognosis or response to chemo- or immunotherapy and does not take into account the host reaction to PDAC-cells. Our aim is to classify PDAC according to host- and tumor-related factors into clinically/biologically relevant subtypes by integrating molecular and microenvironmental findings. A well-characterized PDAC-cohort (n=110) underwent next-generation sequencing with a hotspot cancer panel, while Next-generation Tissue-Microarrays were immunostained for CD3, CD4, CD8, CD20, PD-L1, p63, hyaluronan-mediated motility receptor (RHAMM) and DNA mismatch-repair proteins. Previous data on FOXP3 were integrated. Immune-cell counts and protein expression were correlated with tumor-derived driver mutations, clinicopathologic features (TNM 8. 2017), survival and epithelial-mesenchymal-transition (EMT)-like tumor budding.  Results: Three PDAC-subtypes were identified: the "immune-escape" (54%), poor in T- and B-cells and enriched in FOXP3+Tregs, with high-grade budding, frequent CDKN2A- , SMAD4- and PIK3CA-mutations and poor outcome; the "immune-rich" (35%), rich in T- and B-cells and poorer in FOXP3+Tregs, with infrequent budding, lower CDKN2A- and PIK3CA-mutation rate and better outcome and a subpopulation with tertiary lymphoid tissue (TLT), mutations in DNA damage response genes (STK11, ATM) and the best outcome; and the "immune-exhausted" (11%) with immunogenic microenvironment and two subpopulations: one with PD-L1-expression and high PIK3CA-mutation rate and a microsatellite-unstable subpopulation with high prevalence of JAK3-mutations. The combination of low budding, low stromal FOXP3-counts, presence of TLTs and absence of CDKN2A-mutations confers significant survival advantage in PDAC-patients. Immune host responses correlate with tumor characteristics leading to morphologically recognizable PDAC-subtypes with prognostic/predictive significance. Copyright ©2018, American Association for Cancer Research.

Long noncoding RNA OR3A4 promotes metastasis and tumorigenicity in gastric cancer

PubMed Central

Guo, Xiaobo; Yang, Ziguo; Zhi, Qiaoming; Wang, Dan; Guo, Lei; Li, Guimei; Miao, Ruizhen; Shi, Yulong; Kuang, Yuting

2016-01-01

The contribution of long noncoding RNAs (lncRNAs) to metastasis of gastric cancer remains largely unknown. We used microarray analysis to identify lncRNAs differentially expressed between normal gastric tissues and gastric cancer tissues and validated these differences in quantitative real-time (qRT)-PCR experiments. The expression levels of lncRNA olfactory receptor, family 3, subfamily A, member 4 (OR3A4) were significantly associated with lymphatic metastasis, the depth of cancer invasion, and distal metastasis in 130 paired gastric cancer tissues. The effects of OR3A4 were assessed by overexpressing and silencing OR3A4 in gastric cancer cells. OR3A4 promoted cancer cell growth, angiogenesis, metastasis, and tumorigenesis in vitro and in vivo. Global microarray analysis combined with RT-PCR, RNA immunoprecipitation, and RNA pull-down analyses after OR3A4 transfection demonstrated that OR3A4 influenced biologic functions in gastric cancer cells via regulating the activation of PDLIM2, MACC1, NTN4, and GNB2L1. Our results reveal OR3A4 as an oncogenic lncRNA that promotes tumor progression, Therefore, lncRNAs might function as key regulatory hubs in gastric cancer progression. PMID:26863570

Multiclass cancer classification using a feature subset-based ensemble from microRNA expression profiles.

PubMed

Piao, Yongjun; Piao, Minghao; Ryu, Keun Ho

2017-01-01

Cancer classification has been a crucial topic of research in cancer treatment. In the last decade, messenger RNA (mRNA) expression profiles have been widely used to classify different types of cancers. With the discovery of a new class of small non-coding RNAs; known as microRNAs (miRNAs), various studies have shown that the expression patterns of miRNA can also accurately classify human cancers. Therefore, there is a great demand for the development of machine learning approaches to accurately classify various types of cancers using miRNA expression data. In this article, we propose a feature subset-based ensemble method in which each model is learned from a different projection of the original feature space to classify multiple cancers. In our method, the feature relevance and redundancy are considered to generate multiple feature subsets, the base classifiers are learned from each independent miRNA subset, and the average posterior probability is used to combine the base classifiers. To test the performance of our method, we used bead-based and sequence-based miRNA expression datasets and conducted 10-fold and leave-one-out cross validations. The experimental results show that the proposed method yields good results and has higher prediction accuracy than popular ensemble methods. The Java program and source code of the proposed method and the datasets in the experiments are freely available at https://sourceforge.net/projects/mirna-ensemble/. Copyright © 2016 Elsevier Ltd. All rights reserved.

Serrated colorectal cancer: Molecular classification, prognosis, and response to chemotherapy

PubMed Central

Murcia, Oscar; Juárez, Miriam; Hernández-Illán, Eva; Egoavil, Cecilia; Giner-Calabuig, Mar; Rodríguez-Soler, María; Jover, Rodrigo

2016-01-01

Molecular advances support the existence of an alternative pathway of colorectal carcinogenesis that is based on the hypermethylation of specific DNA regions that silences tumor suppressor genes. This alternative pathway has been called the serrated pathway due to the serrated appearance of tumors in histological analysis. New classifications for colorectal cancer (CRC) were proposed recently based on genetic profiles that show four types of molecular alterations: BRAF gene mutations, KRAS gene mutations, microsatellite instability, and hypermethylation of CpG islands. This review summarizes what is known about the serrated pathway of CRC, including CRC molecular and clinical features, prognosis, and response to chemotherapy. PMID:27053844

The Prostate Cancer Biorepository Network (PCBN)

DTIC Science & Technology

2016-10-01

site includes blood (serum, plasma, and buffy coat), prostatectomy tissues (frozen), biopsies and metastatic tissue from rapid autopsies (paraffin...embedded material and tissue microarrays (TMAs)), prostate cancer patient derived xenografts (PDX) and derived specimens (DNA and RNA) from prostate...Genitourinary Cancer Biorepository set up a rapid autopsy program to provide access to metastatic tissue and create patient derived xenograft (PDX

The road map towards providing a robust Raman spectroscopy-based cancer diagnostic platform and integration into clinic

NASA Astrophysics Data System (ADS)

Lau, Katherine; Isabelle, Martin; Lloyd, Gavin R.; Old, Oliver; Shepherd, Neil; Bell, Ian M.; Dorney, Jennifer; Lewis, Aaran; Gaifulina, Riana; Rodriguez-Justo, Manuel; Kendall, Catherine; Stone, Nicolas; Thomas, Geraint; Reece, David

2016-03-01

Despite the demonstrated potential as an accurate cancer diagnostic tool, Raman spectroscopy (RS) is yet to be adopted by the clinic for histopathology reviews. The Stratified Medicine through Advanced Raman Technologies (SMART) consortium has begun to address some of the hurdles in its adoption for cancer diagnosis. These hurdles include awareness and acceptance of the technology, practicality of integration into the histopathology workflow, data reproducibility and availability of transferrable models. We have formed a consortium, in joint efforts, to develop optimised protocols for tissue sample preparation, data collection and analysis. These protocols will be supported by provision of suitable hardware and software tools to allow statistically sound classification models to be built and transferred for use on different systems. In addition, we are building a validated gastrointestinal (GI) cancers model, which can be trialled as part of the histopathology workflow at hospitals, and a classification tool. At the end of the project, we aim to deliver a robust Raman based diagnostic platform to enable clinical researchers to stage cancer, define tumour margin, build cancer diagnostic models and discover novel disease bio markers.

Overexpression of Plasminogen Activator Inhibitor-1 in Advanced Gastric Cancer with Aggressive Lymph Node Metastasis

PubMed Central

Suh, Yun-Suhk; Yu, Jieun; Kim, Byung Chul; Choi, Boram; Han, Tae-Su; Ahn, Hye Seong; Kong, Seong-Ho; Lee, Hyuk-Joon; Kim, Woo Ho; Yang, Han-Kwang

2015-01-01

Purpose The purpose of this study is to investigate differentially expressed genes using DNA microarray between advanced gastric cancer (AGC) with aggressive lymph node (LN) metastasis and that with a more advanced tumor stage but without LN metastasis. Materials and Methods Five sample pairs of gastric cancer tissue and normal gastric mucosa were taken from three patients with T3N3 stage (highN) and two with T4N0 stage (lowN). Data from triplicate DNA microarray experiments were analyzed, and candidate genes were identified using a volcano plot that showed ≥ 2-fold differential expression and were significant by Welch's t test (p < 0.05) between highN and lowN. Those selected genes were validated independently by reverse-transcriptase–polymerase chain reaction (RT-PCR) using five AGC patients, and tissue-microarray (TMA) comprising 47 AGC patients. Results CFTR, LAMC2, SERPINE2, F2R, MMP7, FN1, TIMP1, plasminogen activator inhibitor-1 (PAI-1), ITGB8, SDS, and TMPRSS4 were commonly up-regulated over 2-fold in highN. REG3A, CD24, ITLN1, and WBP5 were commonly down-regulated over 2-fold in lowN. Among these genes, overexpression of PAI-1 was validated by RT-PCR, and TMA showed 16.7% (7/42) PAI-1 expression in T3N3, but none (0/5) in T4N0 (p=0.393). Conclusion DNA microarray analysis and validation by RT-PCR and TMA showed that overexpression of PAI-1 is related to aggressive LN metastasis in AGC. PMID:25687870

Changes in classification of genetic variants in BRCA1 and BRCA2.

PubMed

Kast, Karin; Wimberger, Pauline; Arnold, Norbert

2018-02-01

Classification of variants of unknown significance (VUS) in the breast cancer genes BRCA1 and BRCA2 changes with accumulating evidence for clinical relevance. In most cases down-staging towards neutral variants without clinical significance is possible. We searched the database of the German Consortium for Hereditary Breast and Ovarian Cancer (GC-HBOC) for changes in classification of genetic variants as an update to our earlier publication on genetic variants in the Centre of Dresden. Changes between 2015 and 2017 were recorded. In the group of variants of unclassified significance (VUS, Class 3, uncertain), only changes of classification towards neutral genetic variants were noted. In BRCA1, 25% of the Class 3 variants (n = 2/8) changed to Class 2 (likely benign) and Class 1 (benign). In BRCA2, in 50% of the Class 3 variants (n = 16/32), a change to Class 2 (n = 10/16) or Class 1 (n = 6/16) was observed. No change in classification was noted in Class 4 (likely pathogenic) and Class 5 (pathogenic) genetic variants in both genes. No up-staging from Class 1, Class 2 or Class 3 to more clinical significance was observed. All variants with a change in classification in our cohort were down-staged towards no clinical significance by a panel of experts of the German Consortium for Hereditary Breast and Ovarian Cancer (GC-HBOC). Prevention in families with Class 3 variants should be based on pedigree based risks and should not be guided by the presence of a VUS.

Cancer Therapy (Preclinical and Clinical): A Decimal Classification, (Categories 51.1, 51.2, and 51.3).

ERIC Educational Resources Information Center

Schneider, John H.

This hierarchical decimal classification of information related to cancer therapy in humans and animals (preceeded by a few general categories) is a working draft of categories taken from an extensive classification of biomedical information. Because the classification identifies very small areas of cancer information, it can be used for precise…

Development of a high-throughput microfluidic integrated microarray for the detection of chimeric bioweapons.

DOE Office of Scientific and Technical Information (OSTI.GOV)

Sheppod, Timothy; Satterfield, Brent; Hukari, Kyle W.

2006-10-01

The advancement of DNA cloning has significantly augmented the potential threat of a focused bioweapon assault, such as a terrorist attack. With current DNA cloning techniques, toxin genes from the most dangerous (but environmentally labile) bacterial or viral organism can now be selected and inserted into robust organism to produce an infinite number of deadly chimeric bioweapons. In order to neutralize such a threat, accurate detection of the expressed toxin genes, rather than classification on strain or genealogical decent of these organisms, is critical. The development of a high-throughput microarray approach will enable the detection of unknowns chimeric bioweapons. Themore » development of a high-throughput microarray approach will enable the detection of unknown bioweapons. We have developed a unique microfluidic approach to capture and concentrate these threat genes (mRNA's) upto a 30 fold concentration. These captured oligonucleotides can then be used to synthesize in situ oligonucleotide copies (cDNA probes) of the captured genes. An integrated microfluidic architecture will enable us to control flows of reagents, perform clean-up steps and finally elute nanoliter volumes of synthesized oligonucleotides probes. The integrated approach has enabled a process where chimeric or conventional bioweapons can rapidly be identified based on their toxic function, rather than being restricted to information that may not identify the critical nature of the threat.« less

Prediction of gene expression in embryonic structures of Drosophila melanogaster.

PubMed

Samsonova, Anastasia A; Niranjan, Mahesan; Russell, Steven; Brazma, Alvis

2007-07-01

Understanding how sets of genes are coordinately regulated in space and time to generate the diversity of cell types that characterise complex metazoans is a major challenge in modern biology. The use of high-throughput approaches, such as large-scale in situ hybridisation and genome-wide expression profiling via DNA microarrays, is beginning to provide insights into the complexities of development. However, in many organisms the collection and annotation of comprehensive in situ localisation data is a difficult and time-consuming task. Here, we present a widely applicable computational approach, integrating developmental time-course microarray data with annotated in situ hybridisation studies, that facilitates the de novo prediction of tissue-specific expression for genes that have no in vivo gene expression localisation data available. Using a classification approach, trained with data from microarray and in situ hybridisation studies of gene expression during Drosophila embryonic development, we made a set of predictions on the tissue-specific expression of Drosophila genes that have not been systematically characterised by in situ hybridisation experiments. The reliability of our predictions is confirmed by literature-derived annotations in FlyBase, by overrepresentation of Gene Ontology biological process annotations, and, in a selected set, by detailed gene-specific studies from the literature. Our novel organism-independent method will be of considerable utility in enriching the annotation of gene function and expression in complex multicellular organisms.

Prediction of Gene Expression in Embryonic Structures of Drosophila melanogaster

PubMed Central

Samsonova, Anastasia A; Niranjan, Mahesan; Russell, Steven; Brazma, Alvis

2007-01-01

Understanding how sets of genes are coordinately regulated in space and time to generate the diversity of cell types that characterise complex metazoans is a major challenge in modern biology. The use of high-throughput approaches, such as large-scale in situ hybridisation and genome-wide expression profiling via DNA microarrays, is beginning to provide insights into the complexities of development. However, in many organisms the collection and annotation of comprehensive in situ localisation data is a difficult and time-consuming task. Here, we present a widely applicable computational approach, integrating developmental time-course microarray data with annotated in situ hybridisation studies, that facilitates the de novo prediction of tissue-specific expression for genes that have no in vivo gene expression localisation data available. Using a classification approach, trained with data from microarray and in situ hybridisation studies of gene expression during Drosophila embryonic development, we made a set of predictions on the tissue-specific expression of Drosophila genes that have not been systematically characterised by in situ hybridisation experiments. The reliability of our predictions is confirmed by literature-derived annotations in FlyBase, by overrepresentation of Gene Ontology biological process annotations, and, in a selected set, by detailed gene-specific studies from the literature. Our novel organism-independent method will be of considerable utility in enriching the annotation of gene function and expression in complex multicellular organisms. PMID:17658945

A systematic approach to prioritize drug targets using machine learning, a molecular descriptor-based classification model, and high-throughput screening of plant derived molecules: a case study in oral cancer.

PubMed

Randhawa, Vinay; Kumar Singh, Anil; Acharya, Vishal

2015-12-01

Systems-biology inspired identification of drug targets and machine learning-based screening of small molecules which modulate their activity have the potential to revolutionize modern drug discovery by complementing conventional methods. To utilize the effectiveness of such pipelines, we first analyzed the dysregulated gene pairs between control and tumor samples and then implemented an ensemble-based feature selection approach to prioritize targets in oral squamous cell carcinoma (OSCC) for therapeutic exploration. Based on the structural information of known inhibitors of CXCR4-one of the best targets identified in this study-a feature selection was implemented for the identification of optimal structural features (molecular descriptor) based on which a classification model was generated. Furthermore, the CXCR4-centered descriptor-based classification model was finally utilized to screen a repository of plant derived small-molecules to obtain potential inhibitors. The application of our methodology may assist effective selection of the best targets which may have previously been overlooked, that in turn will lead to the development of new oral cancer medications. The small molecules identified in this study can be ideal candidates for trials as potential novel anti-oral cancer agents. Importantly, distinct steps of this whole study may provide reference for the analysis of other complex human diseases.

Questioning the utility of pooling samples in microarray experiments with cell lines.

PubMed

Lusa, L; Cappelletti, V; Gariboldi, M; Ferrario, C; De Cecco, L; Reid, J F; Toffanin, S; Gallus, G; McShane, L M; Daidone, M G; Pierotti, M A

2006-01-01

We describe a microarray experiment using the MCF-7 breast cancer cell line in two different experimental conditions for which the same number of independent pools as the number of individual samples was hybridized on Affymetrix GeneChips. Unexpectedly, when using individual samples, the number of probe sets found to be differentially expressed between treated and untreated cells was about three times greater than that found using pools. These findings indicate that pooling samples in microarray experiments where the biological variability is expected to be small might not be helpful and could even decrease one's ability to identify differentially expressed genes.

Novel harmonic regularization approach for variable selection in Cox's proportional hazards model.

PubMed

Chu, Ge-Jin; Liang, Yong; Wang, Jia-Xuan

2014-01-01

Variable selection is an important issue in regression and a number of variable selection methods have been proposed involving nonconvex penalty functions. In this paper, we investigate a novel harmonic regularization method, which can approximate nonconvex Lq  (1/2 < q < 1) regularizations, to select key risk factors in the Cox's proportional hazards model using microarray gene expression data. The harmonic regularization method can be efficiently solved using our proposed direct path seeking approach, which can produce solutions that closely approximate those for the convex loss function and the nonconvex regularization. Simulation results based on the artificial datasets and four real microarray gene expression datasets, such as real diffuse large B-cell lymphoma (DCBCL), the lung cancer, and the AML datasets, show that the harmonic regularization method can be more accurate for variable selection than existing Lasso series methods.

Systematic gene microarray analysis of the lncRNA expression profiles in human uterine cervix carcinoma.

PubMed

Chen, Jie; Fu, Ziyi; Ji, Chenbo; Gu, Pingqing; Xu, Pengfei; Yu, Ningzhu; Kan, Yansheng; Wu, Xiaowei; Shen, Rong; Shen, Yan

2015-05-01

The human uterine cervix carcinoma is one of the most well-known malignancy reproductive system cancers, which threatens women health globally. However, the mechanisms of the oncogenesis and development process of cervix carcinoma are not yet fully understood. Long non-coding RNAs (lncRNAs) have been proved to play key roles in various biological processes, especially development of cancer. The function and mechanism of lncRNAs on cervix carcinoma is still rarely reported. We selected 3 cervix cancer and normal cervix tissues separately, then performed lncRNA microarray to detect the differentially expressed lncRNAs. Subsequently, we explored the potential function of these dysregulated lncRNAs through online bioinformatics databases. Finally, quantity real-time PCR was carried out to confirm the expression levels of these dysregulated lncRNAs in cervix cancer and normal tissues. We uncovered the profiles of differentially expressed lncRNAs between normal and cervix carcinoma tissues by using the microarray techniques, and found 1622 upregulated and 3026 downregulated lncRNAs (fold-change>2.0) in cervix carcinoma compared to the normal cervical tissue. Furthermore, we found HOXA11-AS might participate in cervix carcinogenesis by regulating HOXA11, which is involved in regulating biological processes of cervix cancer. This study afforded expression profiles of lncRNAs between cervix carcinoma tissue and normal cervical tissue, which could provide database for further research about the function and mechanism of key-lncRNAs in cervix carcinoma, and might be helpful to explore potential diagnosis factors and therapeutic targets for cervix carcinoma. Copyright © 2015 Elsevier Masson SAS. All rights reserved.

Prediction of response to preoperative chemoradiotherapy and establishment of individualized therapy in advanced rectal cancer.

PubMed

Nakao, Toshihiro; Iwata, Takashi; Hotchi, Masanori; Yoshikawa, Kozo; Higashijima, Jun; Nishi, Masaaki; Takasu, Chie; Eto, Shohei; Teraoku, Hiroki; Shimada, Mitsuo

2015-10-01

Preoperative chemoradiotherapy (CRT) has become the standard treatment for patients with locally advanced rectal cancer. However, no specific biomarker has been identified to predict a response to preoperative CRT. The aim of the present study was to assess the gene expression patterns of patients with advanced rectal cancer to predict their responses to preoperative CRT. Fifty-nine rectal cancer patients were subjected to preoperative CRT. Patients were randomly assigned to receive CRT with tegafur/gimeracil/oteracil (S-1 group, n=30) or tegafur-uracil (UFT group, n=29). Gene expression changes were studied with cDNA and miRNA microarray. The association between gene expression and response to CRT was evaluated. cDNA microarray showed that 184 genes were significantly differentially expressed between the responders and the non‑responders in the S-1 group. Comparatively, 193 genes were significantly differentially expressed in the responders in the UFT group. TBX18 upregulation was common to both groups whereas BTNL8, LOC375010, ADH1B, HRASLS2, LOC284232, GCNT3 and ALDH1A2 were significantly differentially lower in both groups when compared with the non-responders. Using miRNA microarray, we found that 7 and 16 genes were significantly differentially expressed between the responders and non-responders in the S-1 and UFT groups, respectively. miR-223 was significantly higher in the responders in the S-1 group and tended to be higher in the responders in the UFT group. The present study identified several genes likely to be useful for establishing individualized therapies for patients with rectal cancer.

Distinct Microbial Signatures Associated With Different Breast Cancer Types

PubMed Central

Banerjee, Sagarika; Tian, Tian; Wei, Zhi; Shih, Natalie; Feldman, Michael D.; Peck, Kristen N.; DeMichele, Angela M.; Alwine, James C.; Robertson, Erle S.

2018-01-01

A dysbiotic microbiome can potentially contribute to the pathogenesis of many different diseases including cancer. Breast cancer is the second leading cause of cancer death in women. Thus, we investigated the diversity of the microbiome in the four major types of breast cancer: endocrine receptor (ER) positive, triple positive, Her2 positive and triple negative breast cancers. Using a whole genome and transcriptome amplification and a pan-pathogen microarray (PathoChip) strategy, we detected unique and common viral, bacterial, fungal and parasitic signatures for each of the breast cancer types. These were validated by PCR and Sanger sequencing. Hierarchical cluster analysis of the breast cancer samples, based on their detected microbial signatures, showed distinct patterns for the triple negative and triple positive samples, while the ER positive and Her2 positive samples shared similar microbial signatures. These signatures, unique or common to the different breast cancer types, provide a new line of investigation to gain further insights into prognosis, treatment strategies and clinical outcome, as well as better understanding of the role of the micro-organisms in the development and progression of breast cancer. PMID:29867857

Molecular profiles of pre- and postoperative breast cancer tumours reveal differentially expressed genes.

PubMed

Riis, Margit L H; Lüders, Torben; Markert, Elke K; Haakensen, Vilde D; Nesbakken, Anne-Jorun; Kristensen, Vessela N; Bukholm, Ida R K

2012-01-01

Gene expression studies on breast cancer have generally been performed on tissue obtained at the time of surgery. In this study, we have compared the gene expression profiles in preoperative tissue (core needle biopsies) while tumor is still in its normal milieu to postoperative tissue from the same tumor obtained during surgery. Thirteen patients were included of which eleven had undergone sentinel node diagnosis procedure before operation. Microarray gene expression analysis was performed using total RNA from all the samples. Paired significance analysis of microarrays revealed 228 differently expressed genes, including several early response stress-related genes such as members of the fos and jun families as well as genes of which the expression has previously been associated with cancer. The expression profiles found in the analyses of breast cancer tissue must be evaluated with caution. Different profiles may simply be the result of differences in the surgical trauma and timing of when samples are taken and not necessarily associated with tumor biology.

Molecular Profiles of Pre- and Postoperative Breast Cancer Tumours Reveal Differentially Expressed Genes

PubMed Central

Riis, Margit L. H.; Lüders, Torben; Markert, Elke K.; Haakensen, Vilde D.; Nesbakken, Anne-Jorun; Kristensen, Vessela N.; Bukholm, Ida R. K.

2012-01-01

Gene expression studies on breast cancer have generally been performed on tissue obtained at the time of surgery. In this study, we have compared the gene expression profiles in preoperative tissue (core needle biopsies) while tumor is still in its normal milieu to postoperative tissue from the same tumor obtained during surgery. Thirteen patients were included of which eleven had undergone sentinel node diagnosis procedure before operation. Microarray gene expression analysis was performed using total RNA from all the samples. Paired significance analysis of microarrays revealed 228 differently expressed genes, including several early response stress-related genes such as members of the fos and jun families as well as genes of which the expression has previously been associated with cancer. The expression profiles found in the analyses of breast cancer tissue must be evaluated with caution. Different profiles may simply be the result of differences in the surgical trauma and timing of when samples are taken and not necessarily associated with tumor biology. PMID:23227362

Impact of S100A8 expression on kidney cancer progression and molecular docking studies for kidney cancer therapeutics.

PubMed

Mirza, Zeenat; Schulten, Hans-Juergen; Farsi, Hasan Ma; Al-Maghrabi, Jaudah A; Gari, Mamdooh A; Chaudhary, Adeel Ga; Abuzenadah, Adel M; Al-Qahtani, Mohammed H; Karim, Sajjad

2014-04-01

The proinflammatory protein S100A8, which is expressed in myeloid cells under physiological conditions, is strongly expressed in human cancer tissues. Its role in tumor cell differentiation and tumor progression is largely unclear and virtually unstudied in kidney cancer. In the present study, we investigated whether S100A8 could be a potential anticancer drug target and therapeutic biomarker for kidney cancer, and the underlying molecular mechanisms by exploiting its interaction profile with drugs. Microarray-based transcriptomics experiments using Affymetrix HuGene 1.0 ST arrays were applied to renal cell carcinoma specimens from Saudi patients for identification of significant genes associated with kidney cancer. In addition, we retrieved selected expression data from the National Center for Biotechnology Information Gene Expression Omnibus database for comparative analysis and confirmation of S100A8 expression. Ingenuity Pathway Analysis (IPA) was used to elucidate significant molecular networks and pathways associated with kidney cancer. The probable polar and non-polar interactions of possible S100A8 inhibitors (aspirin, celecoxib, dexamethasone and diclofenac) were examined by performing molecular docking and binding free energy calculations. Detailed analysis of bound structures and their binding free energies was carried out for S100A8, its known partner (S100A9), and S100A8-S100A9 complex (calprotectin). In our microarray experiments, we identified 1,335 significantly differentially expressed genes, including S100A8, in kidney cancer using a cut-off of p<0.05 and fold-change of 2. Functional analysis of kidney cancer-associated genes showed overexpression of genes involved in cell-cycle progression, DNA repair, cell death, tumor morphology and tissue development. Pathway analysis showed significant disruption of pathways of atherosclerosis signaling, liver X receptor/retinoid X receptor (LXR/RXR) activation, notch signaling, and interleukin-12 (IL-12) signaling. We identified S100A8 as a prospective biomarker for kidney cancer and in silico analysis showed that aspirin, celecoxib, dexamethasone and diclofenac binds to S100A8 and may inhibit downstream signaling in kidney cancer. The present study provides an initial overview of differentially expressed genes in kidney cancer of Saudi Arabian patients using whole-transcript, high-density expression arrays. Our analysis suggests distinct transcriptomic signatures, with significantly high levels of S100A8, and underlying molecular mechanisms contributing to kidney cancer progression. Our docking-based findings shed insight into S100A8 protein as an attractive anticancer target for therapeutic intervention in kidney cancer. To our knowledge, this is the first structure-based docking study for the selected protein targets using the chosen ligands.

Case base classification on digital mammograms: improving the performance of case base classifier

NASA Astrophysics Data System (ADS)

Raman, Valliappan; Then, H. H.; Sumari, Putra; Venkatesa Mohan, N.

2011-10-01

Breast cancer continues to be a significant public health problem in the world. Early detection is the key for improving breast cancer prognosis. The aim of the research presented here is in twofold. First stage of research involves machine learning techniques, which segments and extracts features from the mass of digital mammograms. Second level is on problem solving approach which includes classification of mass by performance based case base classifier. In this paper we build a case-based Classifier in order to diagnose mammographic images. We explain different methods and behaviors that have been added to the classifier to improve the performance of the classifier. Currently the initial Performance base Classifier with Bagging is proposed in the paper and it's been implemented and it shows an improvement in specificity and sensitivity.

Multiple-input multiple-output causal strategies for gene selection.

PubMed

Bontempi, Gianluca; Haibe-Kains, Benjamin; Desmedt, Christine; Sotiriou, Christos; Quackenbush, John

2011-11-25

Traditional strategies for selecting variables in high dimensional classification problems aim to find sets of maximally relevant variables able to explain the target variations. If these techniques may be effective in generalization accuracy they often do not reveal direct causes. The latter is essentially related to the fact that high correlation (or relevance) does not imply causation. In this study, we show how to efficiently incorporate causal information into gene selection by moving from a single-input single-output to a multiple-input multiple-output setting. We show in synthetic case study that a better prioritization of causal variables can be obtained by considering a relevance score which incorporates a causal term. In addition we show, in a meta-analysis study of six publicly available breast cancer microarray datasets, that the improvement occurs also in terms of accuracy. The biological interpretation of the results confirms the potential of a causal approach to gene selection. Integrating causal information into gene selection algorithms is effective both in terms of prediction accuracy and biological interpretation.

Classification algorithm of lung lobe for lung disease cases based on multislice CT images

NASA Astrophysics Data System (ADS)

Matsuhiro, M.; Kawata, Y.; Niki, N.; Nakano, Y.; Mishima, M.; Ohmatsu, H.; Tsuchida, T.; Eguchi, K.; Kaneko, M.; Moriyama, N.

2011-03-01

With the development of multi-slice CT technology, to obtain an accurate 3D image of lung field in a short time is possible. To support that, a lot of image processing methods need to be developed. In clinical setting for diagnosis of lung cancer, it is important to study and analyse lung structure. Therefore, classification of lung lobe provides useful information for lung cancer analysis. In this report, we describe algorithm which classify lungs into lung lobes for lung disease cases from multi-slice CT images. The classification algorithm of lung lobes is efficiently carried out using information of lung blood vessel, bronchus, and interlobar fissure. Applying the classification algorithms to multi-slice CT images of 20 normal cases and 5 lung disease cases, we demonstrate the usefulness of the proposed algorithms.

Cross-Disciplinary Analysis of Lymph Node Classification in Lung Cancer on CT Scanning.

PubMed

El-Sherief, Ahmed H; Lau, Charles T; Obuchowski, Nancy A; Mehta, Atul C; Rice, Thomas W; Blackstone, Eugene H

2017-04-01

Accurate and consistent regional lymph node classification is an important element in the staging and multidisciplinary management of lung cancer. Regional lymph node definition sets-lymph node maps-have been created to standardize regional lymph node classification. In 2009, the International Association for the Study of Lung Cancer (IASLC) introduced a lymph node map to supersede all preexisting lymph node maps. Our aim was to study if and how lung cancer specialists apply the IASLC lymph node map when classifying thoracic lymph nodes encountered on CT scans during lung cancer staging. From April 2013 through July 2013, invitations were distributed to all members of the Fleischner Society, Society of Thoracic Radiology, General Thoracic Surgical Club, and the American Association of Bronchology and Interventional Pulmonology to participate in an anonymous online image-based and text-based 20-question survey regarding lymph node classification for lung cancer staging on CT imaging. Three hundred thirty-seven people responded (approximately 25% participation). Respondents consisted of self-reported thoracic radiologists (n = 158), thoracic surgeons (n = 102), and pulmonologists who perform endobronchial ultrasonography (n = 77). Half of the respondents (50%; 95% CI, 44%-55%) reported using the IASLC lymph node map in daily practice, with no significant differences between subspecialties. A disparity was observed between the IASLC definition sets and their interpretation and application on CT scans, in particular for lymph nodes near the thoracic inlet, anterior to the trachea, anterior to the tracheal bifurcation, near the ligamentum arteriosum, between the bronchus intermedius and esophagus, in the internal mammary space, and adjacent to the heart. Use of older lymph node maps and inconsistencies in interpretation and application of definitions in the IASLC lymph node map may potentially lead to misclassification of stage and suboptimal management of lung cancer in some patients. Published by Elsevier Inc.

Gene profiling, biomarkers and pathways characterizing HCV-related hepatocellular carcinoma

PubMed Central

De Giorgi, Valeria; Monaco, Alessandro; Worchech, Andrea; Tornesello, MariaLina; Izzo, Francesco; Buonaguro, Luigi; Marincola, Francesco M; Wang, Ena; Buonaguro, Franco M

2009-01-01

Background Hepatitis C virus (HCV) infection is a major cause of hepatocellular carcinoma (HCC) worldwide. The molecular mechanisms of HCV-induced hepatocarcinogenesis are not yet fully elucidated. Besides indirect effects as tissue inflammation and regeneration, a more direct oncogenic activity of HCV can be postulated leading to an altered expression of cellular genes by early HCV viral proteins. In the present study, a comparison of gene expression patterns has been performed by microarray analysis on liver biopsies from HCV-positive HCC patients and HCV-negative controls. Methods Gene expression profiling of liver tissues has been performed using a high-density microarray containing 36'000 oligos, representing 90% of the human genes. Samples were obtained from 14 patients affected by HCV-related HCC and 7 HCV-negative non-liver-cancer patients, enrolled at INT in Naples. Transcriptional profiles identified in liver biopsies from HCC nodules and paired non-adjacent non-HCC liver tissue of the same HCV-positive patients were compared to those from HCV-negative controls by the Cluster program. The pathway analysis was performed using the BRB-Array- Tools based on the "Ingenuity System Database". Significance threshold of t-test was set at 0.001. Results Significant differences were found between the expression patterns of several genes falling into different metabolic and inflammation/immunity pathways in HCV-related HCC tissues as well as the non-HCC counterpart compared to normal liver tissues. Only few genes were found differentially expressed between HCV-related HCC tissues and paired non-HCC counterpart. Conclusion In this study, informative data on the global gene expression pattern of HCV-related HCC and non-HCC counterpart, as well as on their difference with the one observed in normal liver tissues have been obtained. These results may lead to the identification of specific biomarkers relevant to develop tools for detection, diagnosis, and classification of HCV-related HCC. PMID:19821982

Bayes multiple decision functions.

PubMed

Wu, Wensong; Peña, Edsel A

2013-01-01

This paper deals with the problem of simultaneously making many ( M ) binary decisions based on one realization of a random data matrix X . M is typically large and X will usually have M rows associated with each of the M decisions to make, but for each row the data may be low dimensional. Such problems arise in many practical areas such as the biological and medical sciences, where the available dataset is from microarrays or other high-throughput technology and with the goal being to decide which among of many genes are relevant with respect to some phenotype of interest; in the engineering and reliability sciences; in astronomy; in education; and in business. A Bayesian decision-theoretic approach to this problem is implemented with the overall loss function being a cost-weighted linear combination of Type I and Type II loss functions. The class of loss functions considered allows for use of the false discovery rate (FDR), false nondiscovery rate (FNR), and missed discovery rate (MDR) in assessing the quality of decision. Through this Bayesian paradigm, the Bayes multiple decision function (BMDF) is derived and an efficient algorithm to obtain the optimal Bayes action is described. In contrast to many works in the literature where the rows of the matrix X are assumed to be stochastically independent, we allow a dependent data structure with the associations obtained through a class of frailty-induced Archimedean copulas. In particular, non-Gaussian dependent data structure, which is typical with failure-time data, can be entertained. The numerical implementation of the determination of the Bayes optimal action is facilitated through sequential Monte Carlo techniques. The theory developed could also be extended to the problem of multiple hypotheses testing, multiple classification and prediction, and high-dimensional variable selection. The proposed procedure is illustrated for the simple versus simple hypotheses setting and for the composite hypotheses setting through simulation studies. The procedure is also applied to a subset of a microarray data set from a colon cancer study.

Automated Extraction and Classification of Cancer Stage Mentions fromUnstructured Text Fields in a Central Cancer Registry

PubMed Central

AAlAbdulsalam, Abdulrahman K.; Garvin, Jennifer H.; Redd, Andrew; Carter, Marjorie E.; Sweeny, Carol; Meystre, Stephane M.

2018-01-01

Cancer stage is one of the most important prognostic parameters in most cancer subtypes. The American Joint Com-mittee on Cancer (AJCC) specifies criteria for staging each cancer type based on tumor characteristics (T), lymph node involvement (N), and tumor metastasis (M) known as TNM staging system. Information related to cancer stage is typically recorded in clinical narrative text notes and other informal means of communication in the Electronic Health Record (EHR). As a result, human chart-abstractors (known as certified tumor registrars) have to search through volu-minous amounts of text to extract accurate stage information and resolve discordance between different data sources. This study proposes novel applications of natural language processing and machine learning to automatically extract and classify TNM stage mentions from records at the Utah Cancer Registry. Our results indicate that TNM stages can be extracted and classified automatically with high accuracy (extraction sensitivity: 95.5%–98.4% and classification sensitivity: 83.5%–87%). PMID:29888032

Parenclitic Network Analysis of Methylation Data for Cancer Identification

PubMed Central

Karsakov, Alexander; Bartlett, Thomas; Ryblov, Artem; Meyerov, Iosif; Ivanchenko, Mikhail; Zaikin, Alexey

2017-01-01

We make use of ideas from the theory of complex networks to implement a machine learning classification of human DNA methylation data, that carry signatures of cancer development. The data were obtained from patients with various kinds of cancers and represented as parenclictic networks, wherein nodes correspond to genes, and edges are weighted according to pairwise variation from control group subjects. We demonstrate that for the 10 types of cancer under study, it is possible to obtain a high performance of binary classification between cancer-positive and negative samples based on network measures. Remarkably, an accuracy as high as 93−99% is achieved with only 12 network topology indices, in a dramatic reduction of complexity from the original 15295 gene methylation levels. Moreover, it was found that the parenclictic networks are scale-free in cancer-negative subjects, and deviate from the power-law node degree distribution in cancer. The node centrality ranking and arising modular structure could provide insights into the systems biology of cancer. PMID:28107365

Automated Extraction and Classification of Cancer Stage Mentions fromUnstructured Text Fields in a Central Cancer Registry.

PubMed

AAlAbdulsalam, Abdulrahman K; Garvin, Jennifer H; Redd, Andrew; Carter, Marjorie E; Sweeny, Carol; Meystre, Stephane M

2018-01-01

Cancer stage is one of the most important prognostic parameters in most cancer subtypes. The American Joint Com-mittee on Cancer (AJCC) specifies criteria for staging each cancer type based on tumor characteristics (T), lymph node involvement (N), and tumor metastasis (M) known as TNM staging system. Information related to cancer stage is typically recorded in clinical narrative text notes and other informal means of communication in the Electronic Health Record (EHR). As a result, human chart-abstractors (known as certified tumor registrars) have to search through volu-minous amounts of text to extract accurate stage information and resolve discordance between different data sources. This study proposes novel applications of natural language processing and machine learning to automatically extract and classify TNM stage mentions from records at the Utah Cancer Registry. Our results indicate that TNM stages can be extracted and classified automatically with high accuracy (extraction sensitivity: 95.5%-98.4% and classification sensitivity: 83.5%-87%).

Genome-wide identification of novel expression signatures reveal distinct patterns and prevalence of binding motifs for p53, nuclear factor-κB and other signal transcription factors in head and neck squamous cell carcinoma

PubMed Central

Yan, Bin; Yang, Xinping; Lee, Tin-Lap; Friedman, Jay; Tang, Jun; Van Waes, Carter; Chen, Zhong

2007-01-01

Background Differentially expressed gene profiles have previously been observed among pathologically defined cancers by microarray technologies, including head and neck squamous cell carcinomas (HNSCCs). However, the molecular expression signatures and transcriptional regulatory controls that underlie the heterogeneity in HNSCCs are not well defined. Results Genome-wide cDNA microarray profiling of ten HNSCC cell lines revealed novel gene expression signatures that distinguished cancer cell subsets associated with p53 status. Three major clusters of over-expressed genes (A to C) were defined through hierarchical clustering, Gene Ontology, and statistical modeling. The promoters of genes in these clusters exhibited different patterns and prevalence of transcription factor binding sites for p53, nuclear factor-κB (NF-κB), activator protein (AP)-1, signal transducer and activator of transcription (STAT)3 and early growth response (EGR)1, as compared with the frequency in vertebrate promoters. Cluster A genes involved in chromatin structure and function exhibited enrichment for p53 and decreased AP-1 binding sites, whereas clusters B and C, containing cytokine and antiapoptotic genes, exhibited a significant increase in prevalence of NF-κB binding sites. An increase in STAT3 and EGR1 binding sites was distributed among the over-expressed clusters. Novel regulatory modules containing p53 or NF-κB concomitant with other transcription factor binding motifs were identified, and experimental data supported the predicted transcriptional regulation and binding activity. Conclusion The transcription factors p53, NF-κB, and AP-1 may be important determinants of the heterogeneous pattern of gene expression, whereas STAT3 and EGR1 may broadly enhance gene expression in HNSCCs. Defining these novel gene signatures and regulatory mechanisms will be important for establishing new molecular classifications and subtyping, which in turn will promote development of targeted therapeutics for HNSCC. PMID:17498291

Fluorescence-based bioassays for the detection and evaluation of food materials.

PubMed

Nishi, Kentaro; Isobe, Shin-Ichiro; Zhu, Yun; Kiyama, Ryoiti

2015-10-13

We summarize here the recent progress in fluorescence-based bioassays for the detection and evaluation of food materials by focusing on fluorescent dyes used in bioassays and applications of these assays for food safety, quality and efficacy. Fluorescent dyes have been used in various bioassays, such as biosensing, cell assay, energy transfer-based assay, probing, protein/immunological assay and microarray/biochip assay. Among the arrays used in microarray/biochip assay, fluorescence-based microarrays/biochips, such as antibody/protein microarrays, bead/suspension arrays, capillary/sensor arrays, DNA microarrays/polymerase chain reaction (PCR)-based arrays, glycan/lectin arrays, immunoassay/enzyme-linked immunosorbent assay (ELISA)-based arrays, microfluidic chips and tissue arrays, have been developed and used for the assessment of allergy/poisoning/toxicity, contamination and efficacy/mechanism, and quality control/safety. DNA microarray assays have been used widely for food safety and quality as well as searches for active components. DNA microarray-based gene expression profiling may be useful for such purposes due to its advantages in the evaluation of pathway-based intracellular signaling in response to food materials.

Fluorescence-Based Bioassays for the Detection and Evaluation of Food Materials

PubMed Central

Nishi, Kentaro; Isobe, Shin-Ichiro; Zhu, Yun; Kiyama, Ryoiti

2015-01-01

We summarize here the recent progress in fluorescence-based bioassays for the detection and evaluation of food materials by focusing on fluorescent dyes used in bioassays and applications of these assays for food safety, quality and efficacy. Fluorescent dyes have been used in various bioassays, such as biosensing, cell assay, energy transfer-based assay, probing, protein/immunological assay and microarray/biochip assay. Among the arrays used in microarray/biochip assay, fluorescence-based microarrays/biochips, such as antibody/protein microarrays, bead/suspension arrays, capillary/sensor arrays, DNA microarrays/polymerase chain reaction (PCR)-based arrays, glycan/lectin arrays, immunoassay/enzyme-linked immunosorbent assay (ELISA)-based arrays, microfluidic chips and tissue arrays, have been developed and used for the assessment of allergy/poisoning/toxicity, contamination and efficacy/mechanism, and quality control/safety. DNA microarray assays have been used widely for food safety and quality as well as searches for active components. DNA microarray-based gene expression profiling may be useful for such purposes due to its advantages in the evaluation of pathway-based intracellular signaling in response to food materials. PMID:26473869

An NRG Oncology/GOG study of molecular classification for risk prediction in endometrioid endometrial cancer

PubMed Central

Cosgrove, Casey M; Tritchler, David L; Cohn, David E; Mutch, David G; Rush, Craig M; Lankes, Heather A; Creasman, William T.; Miller, David S; Ramirez, Nilsa C; Geller, Melissa A; Powell, Matthew A; Backes, Floor J; Landrum, Lisa M; Timmers, Cynthia; Suarez, Adrian A; Zaino, Richard J; Pearl, Michael L; DiSilvestro, Paul A; Lele, Shashikant B; Goodfellow, Paul J

2017-01-01

Objectives The purpose of this study was to assess the prognostic significance of a simplified, clinically accessible classification system for endometrioid endometrial cancers combining Lynch syndrome screening and molecular risk stratification. Methods Tumors from NRG/GOG GOG210 were evaluated for mismatch repair defects (MSI, MMR IHC, and MLH1 methylation), POLE mutations, and loss of heterozygosity. TP53 was evaluated in a subset of cases. Tumors were assigned to four molecular classes. Relationships between molecular classes and clinicopathologic variables were assessed using contingency tests and Cox proportional methods. Results Molecular classification was successful for 982 tumors. Based on the NCI consensus MSI panel assessing MSI and loss of heterozygosity combined with POLE testing, 49% of tumors were classified copy number stable (CNS), 39% MMR deficient, 8% copy number altered (CNA) and 4% POLE mutant. Cancer-specific mortality occurred in 5% of patients with CNS tumors; 2.6% with POLE tumors; 7.6% with MMR deficient tumors and 19% with CNA tumors. The CNA group had worse progression-free (HR 2.31, 95%CI 1.53–3.49) and cancer-specific survival (HR 3.95; 95%CI 2.10–7.44). The POLE group had improved outcomes, but the differences were not statistically significant. CNA class remained significant for cancer-specific survival (HR 2.11; 95%CI 1.04–4.26) in multivariable analysis. The CNA molecular class was associated with TP53 mutation and expression status. Conclusions A simple molecular classification for endometrioid endometrial cancers that can be easily combined with Lynch syndrome screening provides important prognostic information. These findings support prospective clinical validation and further studies on the predictive value of a simplified molecular classification system. PMID:29132872

Advanced Cancer Genomics Institute: Genetic Signatures and Therapeutic Targets in Cancer Progression

DTIC Science & Technology

2014-02-01

Roswell Park Cancer Institute Division, Buffalo, NY 14263 REPORT DATE: February 2014 TYPE OF REPORT: Annual PREPARED FOR: U.S. Army...PERFORMING ORGANIZATION REPORT NUMBER Roswell Park Cancer Institute Elm and Carlton Streets Buffalo, NY 14263 9. SPONSORING...prostatectomy material to isolate RNA and DNA from AD- and CR-CaP cases. Roswell Park already has produced a 5- slide tumor microarray containing 722 CaP

Large-scale integrative network-based analysis identifies common pathways disrupted by copy number alterations across cancers

PubMed Central

2013-01-01

Background Many large-scale studies analyzed high-throughput genomic data to identify altered pathways essential to the development and progression of specific types of cancer. However, no previous study has been extended to provide a comprehensive analysis of pathways disrupted by copy number alterations across different human cancers. Towards this goal, we propose a network-based method to integrate copy number alteration data with human protein-protein interaction networks and pathway databases to identify pathways that are commonly disrupted in many different types of cancer. Results We applied our approach to a data set of 2,172 cancer patients across 16 different types of cancers, and discovered a set of commonly disrupted pathways, which are likely essential for tumor formation in majority of the cancers. We also identified pathways that are only disrupted in specific cancer types, providing molecular markers for different human cancers. Analysis with independent microarray gene expression datasets confirms that the commonly disrupted pathways can be used to identify patient subgroups with significantly different survival outcomes. We also provide a network view of disrupted pathways to explain how copy number alterations affect pathways that regulate cell growth, cycle, and differentiation for tumorigenesis. Conclusions In this work, we demonstrated that the network-based integrative analysis can help to identify pathways disrupted by copy number alterations across 16 types of human cancers, which are not readily identifiable by conventional overrepresentation-based and other pathway-based methods. All the results and source code are available at http://compbio.cs.umn.edu/NetPathID/. PMID:23822816

Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks | Center for Cancer Research

Cancer.gov

The purpose of this study was to develop a method of classifying cancers to specific diagnostic categories based on their gene expression signatures using artificial neural networks (ANNs). We trained the ANNs using the small, round blue-cell tumors (SRBCTs) as a model. These cancers belong to four distinct diagnostic categories and often present diagnostic dilemmas in

3D texture analysis for classification of second harmonic generation images of human ovarian cancer

NASA Astrophysics Data System (ADS)

Wen, Bruce; Campbell, Kirby R.; Tilbury, Karissa; Nadiarnykh, Oleg; Brewer, Molly A.; Patankar, Manish; Singh, Vikas; Eliceiri, Kevin. W.; Campagnola, Paul J.

2016-10-01

Remodeling of the collagen architecture in the extracellular matrix (ECM) has been implicated in ovarian cancer. To quantify these alterations we implemented a form of 3D texture analysis to delineate the fibrillar morphology observed in 3D Second Harmonic Generation (SHG) microscopy image data of normal (1) and high risk (2) ovarian stroma, benign ovarian tumors (3), low grade (4) and high grade (5) serous tumors, and endometrioid tumors (6). We developed a tailored set of 3D filters which extract textural features in the 3D image sets to build (or learn) statistical models of each tissue class. By applying k-nearest neighbor classification using these learned models, we achieved 83-91% accuracies for the six classes. The 3D method outperformed the analogous 2D classification on the same tissues, where we suggest this is due the increased information content. This classification based on ECM structural changes will complement conventional classification based on genetic profiles and can serve as an additional biomarker. Moreover, the texture analysis algorithm is quite general, as it does not rely on single morphological metrics such as fiber alignment, length, and width but their combined convolution with a customizable basis set.

The Consensus Molecular Subtypes of Colorectal Cancer

PubMed Central

Guinney, Justin; Dienstmann, Rodrigo; Wang, Xin; de Reyniès, Aurélien; Schlicker, Andreas; Soneson, Charlotte; Marisa, Laetitia; Roepman, Paul; Nyamundanda, Gift; Angelino, Paolo; Bot, Brian M.; Morris, Jeffrey S.; Simon, Iris M.; Gerster, Sarah; Fessler, Evelyn; de Sousa e Melo, Felipe; Missiaglia, Edoardo; Ramay, Hena; Barras, David; Homicsko, Krisztian; Maru, Dipen; Manyam, Ganiraju C.; Broom, Bradley; Boige, Valerie; Perez-Villamil, Beatriz; Laderas, Ted; Salazar, Ramon; Gray, Joe W.; Hanahan, Douglas; Tabernero, Josep; Bernards, Rene; Friend, Stephen H.; Laurent-Puig, Pierre; Medema, Jan Paul; Sadanandam, Anguraj; Wessels, Lodewyk; Delorenzi, Mauro; Kopetz, Scott; Vermeulen, Louis; Tejpar, Sabine

2015-01-01

Colorectal cancer (CRC) is a frequently lethal disease with heterogeneous outcomes and drug responses. To resolve inconsistencies among the reported gene expression–based CRC classifications and facilitate clinical translation, we formed an international consortium dedicated to large-scale data sharing and analytics across expert groups. We show marked interconnectivity between six independent classification systems coalescing into four consensus molecular subtypes (CMS) with distinguishing features: CMS1 (MSI Immune, 14%), hypermutated, microsatellite unstable, strong immune activation; CMS2 (Canonical, 37%), epithelial, chromosomally unstable, marked WNT and MYC signaling activation; CMS3 (Metabolic, 13%), epithelial, evident metabolic dysregulation; and CMS4 (Mesenchymal, 23%), prominent transforming growth factor β activation, stromal invasion, and angiogenesis. Samples with mixed features (13%) possibly represent a transition phenotype or intra-tumoral heterogeneity. We consider the CMS groups the most robust classification system currently available for CRC – with clear biological interpretability – and the basis for future clinical stratification and subtype–based targeted interventions. PMID:26457759

A measure of association for ordered categorical data in population-based studies

PubMed Central

Nelson, Kerrie P; Edwards, Don

2016-01-01

Ordinal classification scales are commonly used to define a patient’s disease status in screening and diagnostic tests such as mammography. Challenges arise in agreement studies when evaluating the association between many raters’ classifications of patients’ disease or health status when an ordered categorical scale is used. In this paper, we describe a population-based approach and chance-corrected measure of association to evaluate the strength of relationship between multiple raters’ ordinal classifications where any number of raters can be accommodated. In contrast to Shrout and Fleiss’ intraclass correlation coefficient, the proposed measure of association is invariant with respect to changes in disease prevalence. We demonstrate how unique characteristics of individual raters can be explored using random effects. Simulation studies are conducted to demonstrate the properties of the proposed method under varying assumptions. The methods are applied to two large-scale agreement studies of breast cancer screening and prostate cancer severity. PMID:27184590