Paper
RECOVER identifies synergistic drug combinations in vitro through sequential model optimization
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.
Authors: Paul 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 Valiante · Almer van der Sloot · Mike Tyers · Charles E.S. Roberts · Michael M. Bronstein · Luke L. Lairson · Jake P. Taylor-King · Yoshua Bengio