RECOVER: sequential model optimization platform for combination drug repurposing identifies novel synergistic compounds in vitro

TL;DR

RECOVER employs a sequential deep learning-guided optimization platform to efficiently identify novel synergistic drug combinations in vitro, significantly reducing experimental screening efforts and rediscovering clinically relevant pairs.

Contribution

This work introduces a sequential model optimization approach that outperforms random and static methods in discovering synergistic drug combinations, with fewer experiments and improved generalization.

Findings

Achieved enrichment of synergistic drug pairs by 5-10x over random search.

Rediscovered drug combinations under clinical trial investigation.

Structural drug embeddings reflect mechanisms of action.

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 towards synergistic agents and these results do not necessarily generalise out of distribution. We employ a sequential model optimization search utilising a deep learning model to quickly discover synergistic drug combinations active against a cancer cell line, requiring substantially less screening than an exhaustive evaluation. Our small scale wet lab experiments only account for evaluation of ~5% of the total search space. After only 3 rounds of ML-guided in vitro experimentation (including a calibration round), we find that the set of drug pairs queried is enriched for highly synergistic combinations; two additional rounds of ML-guided experiments were performed to ensure reproducibility of trends. Remarkably, we rediscover drug combinations later confirmed to be under study within clinical trials. Moreover, we find that drug embeddings generated using only structural information begin to reflect mechanisms of action. Prior in silico benchmarking suggests we can enrich search queries by a factor of ~5-10x for highly synergistic drug combinations by using sequential rounds of evaluation when compared to random selection, or by a factor of >3x when using a pretrained model selecting all drug combinations at a single time point.