RECOVER identifies synergistic drug combinations in vitro through sequential model optimization
Paul A. Bertin, Jarrid Rector-Brooks, Deepak Sharma, Thomas Gaudelet, Andrew Anighoro, Torsten Groß, Francisco Martínez‐Peña, Eileen L. Tang, M S Suraj, Cristian Regep, Jeremy B. R. Hayter, Maksym Korablyov, Nicholas M. Valiante, Almer M. van der Sloot, Mike Tyers, Charles E.S. Roberts, Michael M. Bronstein, Luke L. Lairson, Jake P. Taylor‐King, Yoshua Bengio
Abstract
For large libraries of small molecules, exhaustive combinatorial chemical screens become infeasible to perform when considering a range of disease models, assay conditions, and dose ranges. Deep learning models have achieved state-of-the-art results in silico for the prediction of synergy scores. However, databases of drug combinations are biased toward synergistic agents and results do not generalize out of distribution. During 5 rounds of experimentation, we employ sequential model optimization with a deep learning model to select drug combinations increasingly enriched for synergism and active against a cancer cell line-evaluating only ∼5% of the total search space. Moreover, we find that learned drug embeddings (using structural information) begin to reflect biological mechanisms. In silico benchmarking suggests search queries are ∼5-10× enriched for highly synergistic drug combinations by using sequential rounds of evaluation when compared with random selection or ∼3× when using a pretrained model.