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

Abstract

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database has been produced that characterizes the gene expression and physiological effects of hundreds of approved and withdrawn drugs, toxicants, and biochemical standards in various organs of live rats.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

NSAID-Induced Acute Phase Response is Due to Increased Intestinal Permeability and Characterized by Early and Consistent Alterations in Hepatic Gene Expression

“…This connection of traditional and novel data provides context and meaning to the alterations in gene expression caused by a candidate drug or chemical (Amin et al, 2002;Bushel et al, 2002;Hamadeh et al, 2002aHamadeh et al, , 2002bSteiner et al, 2004;Fielden et al, 2005;Ruepp et al, 2005). Further, this database has been mined using rigorous, statistical approaches based on sophisticated classification algorithms and logistic regression producing a library of linear, robust binary classifiers (Ganter et al, 2005;Natsoulis et al, 2005). These classifiers can be used to characterize, diagnose, and predict pharmacologic and toxicologic properties using gene expression data (Steiner et al, 2004;Ganter et al, 2005.…”

Alternating Direction Methods for Latent Variable Gaussian Graphical Model Selection

“…[29] profiles which contains 301 samples with 6316 variables (genes). The other data set is the Iconix microarray data set (denoted as Iconix) from drug treated rat livers [41] which contains 255 samples with 10455 variables.…”

Interval Data Classification under Partial Information: A Chance-Constraint Approach

“…In the recent past there has been a growing interest in analysis of interval-valued data in the learning community [1,2]. In many real world problems it is not possible to describe the data by a precise value but intervals may be a more proper description.…”

“…Also in the case of gene-expression data like micro-array, since the experiments are usually noisy and data is prone to be erroneous, data for a number of replicates of the same experiment are provided. Past research has shown that handling uncertainty in such applications by the representation as interval data leads to accurate learning algorithms [3,1]. Classification formulations which are capable of handling interval data have immense importance from a pragmatic perspective.…”