Prediction of clinical drug efficacy by classification of drug-induced genomic expression profiles in vitro

摘要: Assays of drug action typically evaluate biochemical activity. However, accurately matching therapeutic efficacy with activity is a challenge. High-content cellular assays seek to bridge this gap by capturing broad information about the physiology action. Here, we present method predicting general classes into which various psychoactive drugs fall, based on high-content statistical categorization gene expression profiles induced these drugs. When used classification tree and random forest supervised algorithms analyze microarray data, derived “efficacy profiles” biomarker that correlate anti-depressant, antipsychotic opioid primary human neurons in vitro. These were as predictive models classify naive vitro treatments 83.3% (random forest) 88.9% (classification tree) accuracy. Thus, detailed contained genomic data sufficient match physiological effect novel at level its clinical relevance. This capacity identify basis signatures has potential utility discovery target validation.