Machine learning prediction of side effects for drugs in clinical trials

Cell Rep Methods. 2022 Dec 7;2(12):100358. doi: 10.1016/j.crmeth.2022.100358. eCollection 2022 Dec 19.

Abstract

Early and accurate detection of side effects is critical for the clinical success of drugs under development. Here, we aim to predict unknown side effects for drugs with a small number of side effects identified in randomized controlled clinical trials. Our machine learning framework, the geometric self-expressive model (GSEM), learns globally optimal self-representations for drugs and side effects from pharmacological graph networks. We show the usefulness of the GSEM on 505 therapeutically diverse drugs and 904 side effects from multiple human physiological systems. Here, we also show a data integration strategy that could be adopted to improve the ability of side effect prediction models to identify unknown side effects that might only appear after the drug enters the market.

Keywords: adverse drug effect; adverse drug events; clinical trials; computational modeling; computational pharmacology; drug side effect prediction; interpretable model; machine learning; matrix completion; networks.

Publication types

  • Research Support, U.S. Gov't, Non-P.H.S.
  • Research Support, Non-U.S. Gov't

MeSH terms

  • Computational Biology*
  • Drug-Related Side Effects and Adverse Reactions* / diagnosis
  • Humans
  • Machine Learning
  • Randomized Controlled Trials as Topic