Paper Info
Title
Discovery of Biomarker Genes from Earthworm Microarray Data by Discriminant Analysis and Clustering
Abstract
Monitoring, assessment and prediction of environmental risks that chemicals pose demand rapid and accurate diagnostic assays. One important goal of microarray experiments is to discover novel biomarkers for toxicity evaluation. A variety of toxicological effects have been associated with explosive compounds 2,4,6-trinitrotoluene (TNT) and 1,3,5-trinitro-1,3,5-triazacyclohexane (RDX). Here we developed a discriminant analysis and cluster (DAC) pipeline to analyze a 248-array dataset with 15,208 non-redundant earthworm (Eisenia fetida) gene probes on each array. Our objective was to identify biomarker genes that can separate earthworm samples into three groups: control (untreated), TNT-treated, and RDX-treated. First, the class comparison statistical algorithm implemented in BRB-ArrayTools was used to infer a total of 869 genes that significantly changed relative to controls as a result of exposure to TNT or RDX at various concentrations for 4 or 14 days. Then, nine tree-based supervised machine learning algorithms were applied to generate classification rules and a set of 286 classifier genes. These classifier genes were ranked by their overall weight of significance in the nine classification methods, and were used to build support vector machines (SVM). A SVM containing all 286 classifier genes had the highest classification accuracy (91.5%). Results of unsupervised clustering show that the use of the top 100 classifier genes can assign the largest number of the 248 worm samples into the three reference clusters obtained by using all the 14,188 filtered genes, suggesting that these top-ranked genes may be potential candidates for biomarkers. This study demonstrates that the DAC pipeline can be used to identify a small set of biomarker genes from high dimensional datasets and generate a reliable SVM classification model for multiple classes.
Year
DOI
Venue
2009
10.1109/IJCBS.2009.134
IJCBS
Keywords
Field
DocType
dac pipeline,non-redundant earthworm,earthworm microarray data,classification rules,classification,pattern clustering,discriminant analysis,learning (artificial intelligence),classification method,pattern classification,high dimensional dataset,unsupervised clustering,decision tree,support vector machine,biology computing,svm classification model,biomarker gene,tree-based supervised machine learning algorithm,classifier gene,classification rule,novel biomarkers,clustering,classifier genes,reliable svm classification model,biomarker genes,eisenia fetida,biomarker,earthworm sample,support vector machines,earthworm microarray,highest classification accuracy,learning artificial intelligence,microarray data
Decision tree,Eisenia fetida,Pattern recognition,Computer science,Support vector machine,Biomarker (medicine),Microarray analysis techniques,Artificial intelligence,Linear discriminant analysis,Cluster analysis,Classifier (linguistics)
Conference
ISBN
Citations 
PageRank 
978-0-7695-3739-9
0
0.34
References 
Authors
6
4
Name
Order
Citations
PageRank
Ying Li19318.75
Nan Wang22813.11
Edward J. Perkins322520.46
Ping Gong401.01