Identification and Optimization of Classifier Genes from Multi-Class Earthworm Microarray Dataset

Abstract

Monitoring, assessment and prediction of environmental risks that chemicals pose demand rapid and accurate diagnostic assays. A variety of toxicological effects have been associated with explosive compounds TNT and RDX. One important goal of microarray experiments is to discover novel biomarkers for toxicity evaluation. We have developed an earthworm microarray containing 15,208 unique oligo probes and have used it to profile gene expression in 248 earthworms exposed to TNT, RDX or neither. We assembled a new machine learning pipeline consisting of several well-established feature filtering/selection and classification techniques to analyze the 248-array dataset in order to construct classifier models that can separate earthworm samples into three groups: control, TNT-treated, and RDX-treated. First, a total of 869 genes differentially expressed in response to TNT or RDX exposure were identified using a univariate statistical algorithm of class comparison. Then, decision tree-based algorithms were applied to select a subset of 354 classifier genes, which were ranked by their overall weight of significance. A multiclass support vector machine (MC-SVM) method and an unsupervised K-mean clustering method were applied to independently refine the classifier, producing a smaller subset of 39 and 30 classifier genes, separately, with 11 common genes being potential biomarkers. The combined 58 genes were considered the refined subset and used to build MC-SVM and clustering models with classification accuracy of 83.5% and 56.9%, respectively. This study demonstrates that the machine learning approach can be used to identify and optimize a small subset of classifier/biomarker genes from high dimensional datasets and generate classification models of acceptable precision for multiple classes.

Conserved toxic responses across divergent phylogenetic lineages: a meta-analysis of the neurotoxic effects of RDX among multiple species using toxicogenomics

“…Earthworm (Eisinia fetida) exposures to RDX and gene expression analysis have been described in detail by Li et al (2010) and Gong et al (2010). Briefly, earthworm exposures were conducted in a field collected silty loam soil in accordance with the American Society for Testing And Materials guideline (ASTM 1997).…”

Wildlife Toxicity Assessment for 1,3,5-Trinitrohexahydro-1,3,5-Triazine (RDX)

“…A range of bioinformatic approaches have been used to investigate the impact of RDX toxicity in a range of species including rats [55], quail [31], fish [56], and earthworms [57][58][59][60][61] with a view to elucidating mechanisms of toxicity and developing predictive models for enhanced monitoring. While these exploratory studies reveal a consistent range of responses to RDX across species, the range of differentially expressed genes or enriched pathways still represents a somewhat complex descriptive toxicology, with the results highly dependent on the choice of statistical methods.…”

Freshwater Conservation and Biomonitoring of Structure and Function

“…The introduction of more complex modeling techniques that can assess the predictive power of combinations of biomarkers (Li et al, 2010) has been a significant step forward, particularly when applied to linking phenotypic responses (e.g., physiology) to molecular responses, especially in a network context. Although effective, this approach has limitations: in particular, it cannot identify synergistic effects between variables, it has a relatively low statistical power, and biological interpretation is challenging.…”