Machine Learning Prediction of On/Off Target-driven Clinical Adverse Events.

Journal: Pharmaceutical research
PMID:

Abstract

OBJECTIVE: Currently, 90% of clinical drug development fails, where 30% of these failures are due to clinical toxicity. The current extensive animal toxicity studies are not predictive of clinical adverse events (AEs) at clinical doses, while current computation models only consider very few factors with limited success in clinical toxicity prediction. We aimed to address these issues by developing a machine learning (ML) model to directly predict clinical AEs.

Authors

  • Albert Cao
    Department of Pharmaceutical Sciences, College of Pharmacy, University of Michigan, Ann Arbor, MI, 48109, United States.
  • Luchen Zhang
    Department of Pharmaceutical Sciences, College of Pharmacy, University of Michigan, Ann Arbor, MI, 48109, United States.
  • Yingzi Bu
    Department of Pharmaceutical Sciences, College of Pharmacy, University of Michigan, Ann Arbor, MI, 48109, United States.
  • Duxin Sun
    Department of Pharmaceutical Sciences, College of Pharmacy, University of Michigan, Ann Arbor, MI, 48109, United States. duxins@umich.edu.