Virtual screening for small molecule pathway regulators by image profile matching

Abstract

AbstractIdentifying chemical regulators of biological pathways is a time-consuming bottleneck in developing therapeutics and research compounds. Typically, thousands to millions of candidate small molecules are tested in target-based biochemical screens or phenotypic cell-based screens, both expensive experiments customized to each disease. Here, our broad, virtual profile-based screening approach instead matches compounds to pathways based on phenotypic information in public cell image data, created using the Cell Painting assay. Our computational strategy efficiently uncovered the expected small molecule regulators for 19% of positive control genes. In discovery mode, we identified compounds related to three of seven tested genes, validated in subsequent gene-relevant assays. This image profile-based approach could replace many customized labor- and resource-intensive screens and accelerate the discovery of biologically and therapeutically useful compounds.One-Sentence SummaryIf a genetic perturbation impacts cell morphology, a computational query can reveal compounds whose morphology “matches”.