Academia.eduAcademia.edu

Outline

Title
Abstract
Introduction
Methods
Experimental Evaluation
Classification Results
Conclusions
References
All Topics
Computer Science
Machine Learning

Traveling on discrete embeddings of gene expression

Profile image of Vittorio MurinoVittorio Murino

2016, Artificial Intelligence in Medicine

https://doi.org/10.1016/J.ARTMED.2016.05.002
visibility

…

description

11 pages

link

1 file

Abstract

Objective: High-throughput technologies have generated an unprecedented amount of high-dimensional gene expression data. Algorithmic approaches could be extremely useful to distill information and derive compact interpretable representations of the statistical patterns present in the data. This paper proposes a mining approach to extract an informative representation of gene expression profiles based on a generative model called the Counting Grid (CG). Method: Using the CG model, gene expression values are arranged on a discrete grid, learned in a way that "similar" co-expression patterns are arranged in close proximity, thus resulting in an intuitive visualization of the dataset. More than this, the model permits to identify the genes that distinguish between classes (e.g. different types of cancer). Finally, each sample can be characterized with a discriminative signature-extracted from the model-that can be effectively employed for classification. Results: A thorough evaluation on several gene expression datasets demonstrate the suitability of the proposed approach from a twofold perspective: numerically, we reached state-of-the-art classification accuracies on 5 datasets out of 7, and similar results when the approach is tested in a gene selection setting (with a stability always above 0.87); clinically, by confirming that many of the genes highlighted by the model as significant play also a key role for cancer biology. Conclusion: The proposed framework can be successfully exploited to meaningfully visualize the samples; detect medically relevant genes; properly classify samples.

Related papers

Studies on Intelligent Approaches to Select Informative Genes from Gene Expression Data for Cancer Classification
mohd saberi saberi

2009

Abstract Gene expression technology namely microarrays, offers the ability to measure the expression levels of thousands of genes simultaneously in biological organisms. Gene expression data produced by the microarrays are expected to be of significant help in the developments of efficient cancer diagnoses and classification platforms. Many researchers have analyzed gene expression data to select a small subset of informative genes for cancer classification using various intelligent approaches.

View PDFchevron_right
Simple and Effective Visual Models for Gene Expression Cancer Diagnostics
Gregor Leban

Proceedings of the …, 2005

View PDFchevron_right
A Study on Computational Process in Gene Expression Data
vaira prakash

This context is commenced to examine the various methods and its challenges in Disease Identification of Gene Expression Data.The elementalresponsibility of these techniques is classification and categorization of gene expression, analysis of the expression, Pattern Recognition, and Identification. This provides an inclusive survey of Micro Array Data analysis techniques and intends a processing component for disease identification. For thehealthcare provider, it is essential to maintain the quality of data because this data is useful to provide cost effective healthcare treatments to the patients. Health Care Administration retains the Microarray data which is refined by expertise and is analyzed by the expertise to identify the disease. This process of analyzing this Microarray data as manual is complicated in identification and classification; due to this Microarray data some difficulties such as missing information, empty values, and incorrect entries. Exclusive of quality information there is no valuableconsequences. For successful data mining, animpediment in health data is individual the majordifficulty for examining medical data. So, it is essential to maintain the quality and accuracy data for data mining to making aneffective decision. The major goal of this survey is focused on various techniques of data mining for developing a prediction model for disease susceptibility using Gene Expression Data.The microarray data is pre-processed to analyze the gene expression to classify the over-expression and under-expression data. Then the classified gene data is then clustered and the best feature selection is applied to discover a pattern. Finally, the association mining handled under the organized set of the gene expression data to theidentification of the disease. This context provides efficient techniques to overcome the manual identification of diseases. 1. Introduction DNA microarrays propose the capability to appear at the expression of thousands of genes in a particularresearch one of the significantrelevance of microarray knowledge is disease identification and classification. Throughmicroarraytechnology, researchers will be proficient in organizing special diseases according todissimilar expression intensity incommon anddevelopment cells, to determine the affiliationamong genes, to recognize the critical genes in the development of disease [1]. The main task of microarray classification is to construct a classifier from chronological microarray gene expression data, and then it utilizes the classifier to categorizeprospectapproachingdata. Appropriate to the rapid improvementofDNA microarray knowledge, gene rangetechniques andorganizationtechniques are being figured for enhanceduse of classification algorithm in microarray gene expression data.The study of outsized gene expression data sets is fetching a dispute in disease classification [2]. Thusgene selection is one of the significantcharacteristics. Proficient gene selection can considerablysimplicity computational burden of the consequent classification assignment and can yield a much smaller and more condensed gene set,not including thedefeat of classification. In classifying microarray data, the key objective of gene selection is to explore for the genes, which remain the greatest amount of information about the set and decrease the categorization error. [3] Data mining techniques classically descend into either supervised or unsupervised classes.Microarray technologies afford a dominant tool by which the expression prototypes of thousands of genes can be examinedconcurrently whose relevancecollection from disease diagnosis to treatment response. Gene expression is the renovation of the DNA progression into mRNA progression by dictation then transformed into amino acid sequences called proteins. The key challenge in classifying gene expression data is the annoyance of dimensionality difficulty. There is ahugeamount of genes (features) evaluated to small sample sizes [3]. To conquer this, feature selection is worn to recognize differentially articulated genes and to eliminateinappropriate genes. Gene selection remains asa significant task to extend the exactness and speed ofclassification structures.In general, feature selection can be prepared into three kinds: Filter, Wrapper, and Embedded methods. They are classified based on how afeature selection methodmerges with the production of aclassification form. Anextensivequantity of literature has been available on gene selection techniques for constructionvaluable classification model. In this paper, we

View PDFchevron_right
Conquering the Curse of Dimensionality In Gene Expression Cancer Diagnosis: Tough Problem, Simple Models
Gregor Leban

Artificial Intelligence in …, 2005

View PDFchevron_right
A Classification Framework Applied to Cancer Gene Expression Profiles
Christina Chan

Journal of Healthcare Engineering, 2013

Classification of cancer based on gene expression has provided insight into possible treatment strategies. Thus, developing machine learning methods that can successfully distinguish among cancer subtypes or normal versus cancer samples is important. This work discusses supervised learning techniques that have been employed to classify cancers. Furthermore, a two-step feature selection method based on an attribute estimation method (e.g., ReliefF) and a genetic algorithm was employed to find a set of genes that can best differentiate between cancer subtypes or normal versus cancer samples. The application of different classification methods (e.g., decision tree, k-nearest neighbor, support vector machine (SVM), bagging, and random forest) on 5 cancer datasets shows that no classification method universally outperforms all the others. However, k-nearest neighbor and linear SVM generally improve the classification performance over other classifiers. Finally, incorporating diverse types of genomic data (e.g., protein-protein interaction data and gene expression) increase the prediction accuracy as compared to using gene expression alone.

View PDFchevron_right
Attribute Clustering for Grouping, Selection, and Classification of Gene Expression Data
Andrew Wong

IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2005

This paper presents an attribute clustering method which is able to group genes based on their interdependence so as to mine meaningful patterns from the gene expression data. It can be used for gene grouping, selection, and classification. The partitioning of a relational table into attribute subgroups allows a small number of attributes within or across the groups to be selected for analysis. By clustering attributes, the search dimension of a data mining algorithm is reduced. The reduction of search dimension is especially important to data mining in gene expression data because such data typically consist of a huge number of genes (attributes) and a small number of gene expression profiles (tuples). Most data mining algorithms are typically developed and optimized to scale to the number of tuples instead of the number of attributes. The situation becomes even worse when the number of attributes overwhelms the number of tuples, in which case, the likelihood of reporting patterns that are actually irrelevant due to chances becomes rather high. It is for the aforementioned reasons that gene grouping and selection are important preprocessing steps for many data mining algorithms to be effective when applied to gene expression data. This paper defines the problem of attribute clustering and introduces a methodology to solving it. Our proposed method groups interdependent attributes into clusters by optimizing a criterion function derived from an information measure that reflects the interdependence between attributes. By applying our algorithm to gene expression data, meaningful clusters of genes are discovered. The grouping of genes based on attribute interdependence within group helps to capture different aspects of gene association patterns in each group. Significant genes selected from each group then contain useful information for gene expression classification and identification. To evaluate the performance of the proposed approach, we applied it to two well-kn- - own gene expression data sets and compared our results with those obtained by other methods. Our experiments show that the proposed method is able to find the meaningful clusters of genes. By selecting a subset of genes which have high multiple-interdependence with others within clusters, significant classification information can be obtained. Thus, a small pool of selected genes can be used to build classifiers with very high classification rate. From the pool, gene expressions of different categories can be identified.

View PDFchevron_right
A Review of Cancer Classification Software for Gene Expression Data
Zalmiyah Zakaria

International Journal of Bio-Science and Bio-Technology, 2015

Microarray technology provides a way for researchers to measure the expression level of thousands of genes simultaneously in a single experiment. Due to the increasing amount of microarray data, the field of microarray data analysis has become a major topic among researchers. One of the examples of microarray data analysis is classification. Classification is the process of determining the classes for samples. The goal of classification is to identify the differentially expressed genes so that these genes can be used to predict the classes for new samples. In order to perform the tasks of classification of microarray data, classification software is required for effective classification and analysis of large-scale data. This paper reviews numerous classification software applications for gene expression data. In this paper, the reviewed software can be categorized into six supervised classification methods: Support

View PDFchevron_right
Mining gene expression data using domain knowledge
Martine Collard, Laurent BRISSON

2008

Biology is now an information-intensive science and various research areas, like molecular biology, evolutionary biology or environmental biology, heavily depend on the availability and the efficient use of information. Data mining, that regroups several techniques for analyzing very large datasets, is used to solve problems in an increasing number of biological applications. This article focuses on the analysis of transcriptome, that reflects gene activity in a given cell population at a given time. We describe research ...

View PDFchevron_right
A signal-to-noise classification model for identification of differentially expressed genes from gene expression data
Barnali Sahu

2011

A major focus in cancer research is identifying genetic markers or biomarkers. To build a robust classifier we have to find out the differentially expressed genes (key genes) in binary classification. The differentially expressed genes or biomarker gene selection is the preprocessing task for cancer classification. In this paper, we have compared the results of two approaches for selecting biomarkers from Leukemia data set. The first approach for feature selection is by implementing k-means clustering and signal-to-noise ratio (SNR) method for gene ranking, the top scored genes from each cluster is selected and given to the classifiers. The second approach uses signal to noise ratio ranking only for feature selection. For validation of both the approaches, we have used k nearest neighbor (kNN), support vector machine (SVM), probabilistic Neural Network (PNN) and Feed Forward Neural Network (fNN). After comparing the final results of two approaches we have got 100%, 96%and 96% accuracy with SVM, kNN and PNN respectively in first approach with five numbers of genes. Whereas, performance of FNN is 2.17 with 10 numbers of genes. In second approach we have got 96%, 96% and 62% accuracies for SVM, kNN and PNN respectively for 5 numbers of genes and the performance of FNN is 2.52 for 10 genes.

View PDFchevron_right
Mapping microarray gene expression data into dissimilarity spaces for tumor classification
Vicente Garcia, José Salvador Sánchez Garreta

Microarray gene expression data sets usually contain a large number of genes, but a small number of samples. In this article, we present a two-stage classification model by combining feature selection with the dissimilarity-based representation paradigm. In the prepro-cessing stage, the ReliefF algorithm is used to generate a subset with a number of top-ranked genes; in the learning/classification stage, the samples represented by the previously selected genes are mapped into a dissimilarity space, which is then used to construct a classifier capable of separating the classes more easily than a feature-based model. The ultimate aim of this paper is not to find the best subset of genes, but to analyze the performance of the dissimilarity-based models by means of a comprehensive collection of experiments for the classification of microarray gene expression data. To this end, we compare the classification results of an artificial neural network, a support vector machine and the Fisher's linear discriminant classifier built on the feature (gene) space with those on the dissimilarity space when varying the number of genes selected by ReliefF, using eight different microarray databases. The results show that the dissimilarity-based classifiers systematically outperform the feature-based models. In addition, classification through the proposed representation appears to be more robust (i.e. less sensitive to the number of genes) than that with the conventional feature-based representation.

View PDFchevron_right

References (69)

  1. Lee JW, Lee JB, Park M, Song SH. An extensive comparison of recent classification tools applied to microarray data. Comput Stat Data Anal 2005;48(4):869-85.
  2. Statnikov A, Aliferis CF, Tsamardinos I, Hardin D, Levy S. A comprehensive evaluation of multicategory classification methods for microarray gene expression cancer diagnosis. Bioinformatics 2005;21(5):631-43.
  3. Wu M-Y, Dai D-Q, Shi Y, Yan H, Zhang X-F. Biomarker identification and cancer classification based on microarray data using Laplace naive Bayes model with mean shrinkage. IEEE/ACM Trans Comput Biol Bioinform 2012;9(6):1649-62.
  4. Tong M, Liu K-H, Xu C, Ju W. An ensemble of SVM classifiers based on gene pairs. Comput Biol Med 2013;43(6):729-37.
  5. Kerr G, Ruskin H, Crane M, Doolan P. Techniques for clustering gene expression data. Comput Biol Med 2008;38(3):283-93.
  6. de Souto M, Costa I, de Araujo D, Ludermir T, Schliep A. Clustering cancer gene expression data: a comparative study. BMC Bioinformatics 2008;9(1):497.
  7. Lazar C, Taminau J, Meganck S, Steenhoff D, Coletta A, Molter C, et al. A survey on filter techniques for feature selection in gene expression microarray analysis. IEEE/ACM Trans Comput Biol Bioinform 2012;9(4):1106-19.
  8. Hofmann T. Unsupervised learning by probabilistic latent semantic analysis. Mach Learning 2001;42(1-2):177-96.
  9. Fasoli M, Santo SD, Zenoni S, Tornielli GB, Farina L, Zamboni A, et al. The grapevine expression atlas reveals a deep transcriptome shift driving the entire plant into a maturation program. Plant Cell Online 2012;24(9):3489-505.
  10. Bicego M, Lovato P, Perina A, Fasoli M, Delledonne M, Pezzotti M, et al. Investigating topic models' capabilities in expression microarray data classification. IEEE/ACM Trans Comput Biol Bioinform 2012;9(6):1831-6.
  11. Rogers S, Girolami M, Campbell C, Breitling R. The latent process decomposition of cDNA microarray data sets. IEEE/ACM Trans Comput Biol Bioinform 2005;2(2):143-56.
  12. Perina A, Lovato P, Murino V, Bicego M. Biologically-aware latent Dirichlet allocation (BALDA) for the classification of expression microarray. In: Proceedings of the international conference on pattern recognition in bioinformatics, LNCS. Springer; 2010. p. 230-41.
  13. Bicego M, Lovato P, Ferrarini A, Delledonne M. Biclustering of expression microarray data with topic models. In: Proceedings of the international conference on pattern recognition. IEEE; 2010. p. 2728-31.
  14. Joachims T. Text categorization with support vector machines: learning with many relevant features. In: Proceedings of the European conference on machine learning. 1998. p. 137-42.
  15. Jojic N, Perina A. Multidimensional counting grids: Inferring word order from disordered bags of words. In: Uncertainty in artificial intelligence; 2011.
  16. Perina A, Jojic N. Image analysis by counting on a grid. In: International conference on computer vision and pattern recognition. 2011. p. 1985-92.
  17. Jordan I, Marino-Ramirez L, Koonin E. Evolutionary significance of gene expression divergence. Gene 2005;345(1):119-26.
  18. Lovato P, Bicego M, Cristani M, Jojic N, Perina A. Feature selection using counting grids: application to microarray data. In: Structural, syntactic, and statistical pattern recognition, vol. 7626 of LNCS. 2012. p. 629-37.
  19. Perina A, Kesa M, Bicego M. Expression microarray data classification using counting grids and fisher kernel. In: Proceedings of the international conference on pattern recognition. 2014. p. 1770-5.
  20. Frey BJ, Jojic N. A comparison of algorithms for inference and learning in probabilistic graphical models. IEEE Trans Pattern Anal Mach Intell 2005;27:2005.
  21. DeRisi JL, Iyer VR, Brown PO. Exploring the metabolic and genetic control of gene expression on a genomic scale. Science 1997;278(5338):680-6.
  22. Rossignol T, Dulau L, Julien A, Blondin B. Genome-wide monitoring of wine yeast gene expression during alcoholic fermentation. Yeast 2003;20(16):1369-85.
  23. Rodriguez-Colman MJ, Reverter-Branchat G, Sorolla MA, Tamarit J, Ros J, Cabiscol E. The forkhead transcription factor Hcm1 promotes mitochondrial biogenesis and stress resistance in yeast. J Biol Chem 2010;285(47):37092-101.
  24. Ashburner M, Ball CA, Blake JA, Botstein D, Butler H, Cherry JM, et al. Gene ontology: tool for the unification of biology. Nat Genet 2000;25(1):25-9.
  25. Beißbarth T, Speed TP. GOstat: find statistically overrepresented Gene Ontologies within a group of genes. Bioinformatics 2004;20(9):1464-5.
  26. Dhanasekaran SM, Barrette TR, Ghosh D, Shah R, Varambally S, Kurachi K, et al. Delineation of prognostic biomarkers in prostate cancer. Nature 2001;412(6849):822-6.
  27. Bhattacharjee A, Richards WG, Staunton J, Li C, Monti S, Vasa P, et al. Classification of human lung carcinomas by mRNA expression profiling reveals distinct adenocarcinoma subclasses. Proc Natl Acad Sci USA 2001;98(24):13790-5.
  28. Pomeroy SL, Tamayo P, Gaasenbeek M, Sturla LM, Angelo M, McLaughlin ME, et al. Prediction of central nervous system embryonal tumour outcome based on gene expression. Nature 2002;415(6870):436-42.
  29. Manning CD, Raghavan P, Schütze H. Introduction to information retrieval, vol. 1. Cambridge: Cambridge University Press; 2008.
  30. Kuncheva LI. A stability index for feature selection. In: Proceedings of the 25th IASTED artificial intelligence and applications, AIAP'07. 2007. p. 390-5.
  31. Jun J-I, Lau LF. Taking aim at the extracellular matrix: CCN proteins as emerging therapeutic targets. Nat Rev Drug Discov 2011;10(12):945-63.
  32. Chen C-C, Lau L. Functions and mechanisms of action of CCN matricellular proteins. Int J Biochem Cell Biol 2009;41(4):771-83.
  33. Bennewith KL, Huang X, Ham CM, Graves EE, Erler JT, Kambham N, et al. The role of tumor cell-derived connective tissue growth factor (CTGF/CCN2) in pancreatic tumor growth. Cancer Res 2009;69(3):775-84.
  34. Xie D, Yin D, Wang H-J, Liu G-T, Elashoff R, Black K, et al. Levels of expression of CYR61 and CTGF are prognostic for tumor progression and survival of individuals with gliomas. Clin Cancer Res 2004;10(6):2072-81.
  35. Chen P-P, Li W-J, Wang Y, Zhao S, Li D-Y, Feng L-Y, et al. Expression of cyr61, CTGF, and WISP-1 correlates with clinical features of lung cancer. PLoS ONE 2007;2(6):e534.
  36. Fahmy RG, Dass CR, Sun L-Q, Chesterman CN, Khachigian LM. Transcription factor Egr-1 supports FGF-dependent angiogenesis during neovascularization and tumor growth. Nat Med 2003;9(8):1026-32.
  37. Lu D, Wolfgang CD, Hai T. Activating transcription factor 3, a stress-inducible gene, suppresses ras-stimulated tumorigenesis. J Biol Chem 2006;281(15):10473-81.
  38. Troup S, Njue C, Kliewer EV, Parisien M, Roskelley C, Chakravarti S, et al. Reduced expression of the small leucine-rich proteoglycans, lumican, and decorin is associated with poor outcome in node-negative invasive breast cancer. Clin Cancer Res 2003;9(1):207-14.
  39. Shahzad MMK, Arevalo JM, Armaiz-Pena GN, Lu C, Stone RL, Moreno-Smith M, et al. Stress effects on FosB-and interleukin-8 (IL8)-driven ovarian cancer growth and metastasis. J Biol Chem 2010;285(46):35462-70.
  40. Kataoka F, Tsuda H, Arao T, Nishimura S, Tanaka H, Nomura H, et al. EGRI and FOSB gene expressions in cancer stroma are independent prognostic indicators for epithelial ovarian cancer receiving standard therapy. Genes Chromosomes Cancer 2012;51(3):300-12.
  41. Wielockx B, Libert C, Wilson C. Matrilysin (matrix metalloproteinase-7): a new promising drug target in cancer and inflammation? Cytokine Growth Factor Rev 2004;15(2-3):111-5.
  42. Tokunaga K, Nakamura Y, Sakata K, Fujimori K, Ohkubo M, Sawada K, et al. Enhanced expression of a glyceraldehyde-3-phosphate dehydrogenase gene in human lung cancers. Cancer Res 1987;47(21):5616-9.
  43. Revillion F, Pawlowski V, Hornez L, Peyrat J. Glyceraldehyde-3-phosphate dehydrogenase gene expression in human breast cancer. Eur J Cancer 2000;36(8):1038-42.
  44. Minn A, Gupta G, Siegel P, Bos P, Shu W, Giri D, et al. Genes that mediate breast cancer metastasis to lung. Nature 2005;436(7050):518-24.
  45. D'Amico G, Korhonen EA, Anisimov A, Zarkada G, Holopainen T, Hagerling R, et al. Tie1 deletion inhibits tumor growth and improves angiopoietin antagonist therapy. J Clin Investig 2014;124(2):824-34.
  46. Shankar J, Messenberg A, Chan J, Underhill TM, Foster LJ, Nabi IR. Pseudopodial actin dynamics control epithelial-mesenchymal transition in metastatic cancer cells. Cancer Res 2010;70(9):3780-90.
  47. Kim J, Lee S, Chae Y, Kang B, Lee Y, Oh S, et al. Association between phosphorylated amp-activated protein kinase and mapk3/1 expression and prognosis for patients with gastric cancer. Oncology 2013;85(2):78-85.
  48. Balkwill F. Cancer and the chemokine network. Nat Rev Cancer 2004;4(7):540-50.
  49. Lin W-C, Li AF-Y, Chi C-W, Chung W-W, Huang CL, Lui W-Y, et al. Tie-1 protein tyrosine kinase: a novel independent prognostic marker for gastric cancer. Clin Cancer Res 1999;5(7):1745-51.
  50. Moncho-Amor V, Ibanez de Caceres I, Bandres E, Martinez-Poveda B, Orgaz J, Sanchez-Perez I, et al. Dusp1/mkp1 promotes angiogenesis, invasion and metastasis in non-small-cell lung cancer. Oncogene 2011;30(6):668-78.
  51. Bieche I, Lerebours F, Tozlu S, Espie M, Marty M, Lidereau R. Molecular profiling of inflammatory breast cancer: identification of a poor-prognosis gene expression signature. Clin Cancer Res 2004;10(20):6789-95.
  52. Zhang Y-J, Li H, Wu H-C, Shen J, Wang L, Yu M-W, et al. Silencing of hint1, a novel tumor suppressor gene, by promoter hypermethylation in hepatocellular carcinoma. Cancer Lett 2009;275(2):277-84.
  53. Singh D, Febbo PG, Ross K, Jackson DG, Manola J, Ladd C, et al. Gene expression correlates of clinical prostate cancer behavior. Cancer Cell 2002;1(2):203-9.
  54. Alon U, Barkai N, Notterman DA, Gish K, Ybarra S, Mack D, et al. Broad patterns of gene expression revealed by clustering analysis of tumor and normal colon tissues probed by oligonucleotide arrays. Proc Natl Acad Sci USA 1999;96(12):6745-50.
  55. Shipp MA, Ross KN, Tamayo P, Weng AP, Kutok JL, Aguiar RC, et al. Diffuse large b-cell lymphoma outcome prediction by gene-expression profiling and supervised machine learning. Nat Med 2002;8(1):68-74.
  56. Golub TR, Slonim DK, Tamayo P, Huard C, Gaasenbeek M, Mesirov JP, et al. Molecular classification of cancer: class discovery and class prediction by gene expression monitoring. Science 1999;286(5439):531-7.
  57. Van't Veer LJ, Dai H, Van De Vijver MJ, He YD, Hart AA, Mao M, et al. Gene expression profiling predicts clinical outcome of breast cancer. Nature 2002;415(6871):530-6.
  58. Yu L, Han Y, Berens M. Stable gene selection from microarray data via sample weighting. IEEE/ACM Trans Comput Biol Bioinform 2012;9:262-72.
  59. Peng H, Long F, Ding C. Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell 2005;27(8):1226-38.
  60. Weston J, Elisseeff A, Schölkopf B, Tipping M. Use of the zero norm with linear models and kernel methods. J Mach Learning Res 2003;3:1439-61.
  61. Perina A, Cristani M, Castellani U, Murino V, Jojic N. Free energy score spaces: using generative information in discriminative classifiers. IEEE Trans Pattern Anal Mach Intell 2012;34(7):1249-62.
  62. Perina A, Bicego M, Castellani U, Murino V. Exploiting geometry in counting grids. SIMBAD; 2013. p. 250-64.
  63. Jaakkola T, Haussler D. Exploiting generative models in discriminative classifiers. In: Advances in neural information processing systems. 1999. p. 487-93.
  64. Wang X, Gotoh O. A robust gene selection method for microarray-based cancer classification. Cancer Inform 2010;9:15-30.
  65. Chen P-C, Huang S-Y, Chen W, Hsiao C. A new regularized least squares support vector regression for gene selection. BMC Bioinformatics 2009;10(1):44.
  66. Osareh A, Shadgar B. Classification and diagnostic prediction of cancers using gene microarray data analysis. J Appl Sci 2009;9(3):459-68.
  67. Liu H, Liu L, Zhang H. Ensemble gene selection by grouping for microarray data classification. J Biomed Inform 2010;43(1):81-7.
  68. Bolón-Canedo V, Sánchez-Maro no N, Alonso-Betanzos A. An ensemble of filters and classifiers for microarray data classification. Pattern Recogn 2012;45(1):531-9.
  69. Statnikov A, Aliferis CF, Tsamardinos I, Hardin D, Levy S. A comprehensive evaluation of multicategory classification methods for microarray gene expression cancer diagnosis. Bioinformatics 2005;21(5):631-43.

Related papers

Expression Microarray data classification using Counting Grids and Fisher Kernel
Maria Kesa

Hybrid generative-discriminative models are useful in biomedical applications-generative modeling extracts interpretable features from raw data, highlighting its properties and increasing classification accuracy when used as input for a discriminative classifier. This raises the question: which generative model should be used for a particular application? In this paper we apply a recently proposed generative model called the Counting Grid to expression microarray data and derive the corresponding Fisher kernel. We justify why this model is particularly well-suited for this application and evaluate classification accuracy on four gene expression data sets, including three tumor data sets and a blood sample data set from schizophrenic patients and healthy controls. We report state of the art results on three of the analyzed data sets and closely match the accuracy from previous work on the other.

View PDFchevron_right
Computational intelligence approach for gene expression data mining and classification
Javed M Khan

The exploration of high dimensional gene expression microarray data demands powerful analytical tools. Our data mining software, VISual Data Analyzer (VISDA) for cluster discovery, reveals many distinguishing patterns among gene expression profiles. The model-supported hierarchical data exploration tool has two complementary schemes: discriminatory dimensionality reduction for structure-focused data visualization, and cluster decomposition by probabilistic clustering. Reducing dimensionality generates the visualization of the complete data set at the top level. This data set is then partitioned into subclusters that can consequently be visualized at lower levels and if necessary partitioned again. These approaches produce different visualizations that are compared against known phenotypes from the microarray experiments. For class prediction on cancers using miroarray data, Multilayer Perceptrons (MLPs) are trained and optimized, whose architecture and parameters are regularized and initialized by weighted Fisher Criterion (wFC)-based Discriminatory Component Analysis (DCA). The prediction performance is compared and evaluated via multifold cross-validation.

View PDFchevron_right
Feature Selection Using Counting Grids: Application to Microarray Data
P. Lovato

Lecture Notes in Computer Science, 2012

In this paper a novel feature selection scheme is proposed, which exploits the potentialities of a recent probabilistic generative model, the Counting Grid. This model is able to cluster together similar observations, highlighting the compactness of a class and its underlying structure. The proposed feature selection scheme is applied to the expression microarray scenario, a peculiar context with very few patterns and a huge number of features. Experiments on benchmark datasets show that the proposed approach is effective and stable, assessing state-of-the-art classification accuracies.

View PDFchevron_right
Using Classification and Visualization on Pattern Databases for Gene Expression Data Analysis
Ruggero G. Pensa

Intl. Workshop on Pattern Representation and Management, 2004

We are designing new data mining techniques on gene ex- pression data, more precisely inductive querying techniques that extract a priori interesting bi-sets, i.e., sets of objects (or biological situations) and associated sets of attributes (or genes). The so-called (formal) con- cepts are important special cases of a priori interesting bi-sets in derived boolean expression matrices, e.g., matrices that encode

View PDFchevron_right
A Classification-Based Machine Learning Approach for the Analysis of Genome-Wide Expression Data
Soumyaroop Bhattacharya, James Lyons-Weiler

Genome Research, 2003

Three important areas of data analysis for global gene expression analysis are class discovery, class prediction, and finding dysregulated genes (biomarkers). The clinical application of microarray data will require marker genes whose expression patterns are sufficiently well understood to allow accurate predictions on disease subclass membership. Commonly used methods of analysis include hierarchical clustering algorithms, t-, F-, and Z-tests, and machine learning approaches. We describe an approach called the maximum difference subset (MDSS) algorithm that combines classification algorithms, classical statistics, and elements of machine learning and provides a coherent framework. By integrating prediction accuracy, the MDSS algorithm learns the critical threshold of statistical significance (the ␣ or P-value), eliminating the arbitrariness of setting a threshold of statistical significance and minimizing the effect of the normality assumptions. To reduce the false positive rate and to increase external validity of the predictive gene set, a jackknife step is used. This step identifies and removes genes in the initial MDSS with low combined predictive utility. The overall MDSS provides a prediction that is less dependent on an arbitrary study design (sample inclusion or exclusion) and should thus have high external validity. We demonstrate that this approach, unlike other published methods, identifies biomarkers capable of predicting the outcome of anthracycline-cytarabine chemotherapy in cases of acute myeloid leukemia. By incorporating two criteria-statistical significance and predictive utility-the approach learns the significance level relevant for a given data set. The MDSS approach can be used with any test and classifier operator pair.

View PDFchevron_right

Related topics

  • Engineering
  • Computer Science
  • Algorithms
  • Machine Learning
  • Classification (Machine Learning)
  • Medicine
  • Artificial Intelligence in Medicine
  • Gene Selection
  • Representation Politics
    • 580 California St., Suite 400
    San Francisco, CA, 94104
    © 2025 Academia. All rights reserved