Identification of toxicologically predictive gene sets using cDNA microarrays

We have developed an approach to classify toxicants based upon their influe nce on profiles of mRNA transcripts. Changes in liver gene expression were examined after exposure of mice to 24 model treatments that fall into five well-studied toxicological categories: peroxisome proliferators, aryl hydro carbon receptor agonists, noncoplanar polychlorinated biphenyls, inflammato ry agents, and hypoxia-inducing agents. Analysis of 1200 transcripts using both a correlation-based approach and a probabilistic approach resulted in a classification accuracy of between 50 and 70%. However, with the use of a forward parameter selection scheme, a diagnostic set of 12 transcripts was identified that provided an estimated 100% predictive accuracy based on le ave-one-out cross-validation. Expansion of this approach to additional chem icals of regulatory concern could serve as an important screening step in a new era of toxicological testing.