¹CuraGen Corporation, Branford, CT, USA

Correspondence: Dr EC Gunther, Yale University School of Medicine, Department of Neurology, YPI CP314, 100 John Murphy Dr., New Haven, CT 06513, USA. Tel: +1 203 705 5030; Fax: 1 203 785 5098; E-mail: erik.gunther@yale.edu

²Current address: Rosetta Inpharmatics, Seattle, WA, USA

Received 6 August 2004; Revised 12 October 2004; Accepted 3 December 2004; Published online 22 February 2005.

Abstract

Genomic expression signatures provide high-content biomarkers of cellular physiology, including the diverse responses to therapeutic drugs. To recognize these signatures, we devised a method of biomarker evaluation called 'sampling over gene space' (SOGS) that imparts superior predictive performance to existing supervised classification algorithms. Applied to microarray data from drug-treated human cortical neuron 1A cell cultures, this method predicts whether individual compounds possess anticonvulsant, antihypertensive, cyclooxygenase inhibitor, or opioid action. Thus, stable cell lines can be suitable for expression signature-based screening of a diverse range of activities. A SOGS-based system also discriminates physiologically active from inactive compounds, identifies drugs with off-target side effects, and incorporates a quantitative method for assigning confidence to individual predictions that, at its most stringent, approaches 100% accuracy. The capacity to resolve multiple distinct drug activities while simultaneously discriminating inactive and potential false-positive compounds in a cell line presents a unified framework for streamlined chemical genomic drug discovery.