Application of Machine Learning and Mechanistic Modeling to Predict Intravenous Pharmacokinetic Profiles in Humans.

Journal: Journal of medicinal chemistry
PMID:

Abstract

Accurate prediction of new compounds' pharmacokinetic (PK) profile in humans is crucial for drug discovery. Traditional methods, including allometric scaling and mechanistic modeling, rely on parameters from or testing, which are labor-intensive and involve ethical concerns. This study leverages machine learning (ML) to overcome these limitations by developing data-driven models. We compiled a large data set of small molecules' physicochemical and PK properties from public sources and digitized human plasma concentration-time profiles for approximately 800 compounds from the literature. We introduced a hybrid modeling framework that combines ML with physiologically based pharmacokinetic modeling and a hierarchical ML framework that employs two steps of learning to directly estimate PK profiles. Tested on 106 drugs, these frameworks demonstrated prediction accuracies within a 2-fold and 5-fold error for 40-60% and 80%-90% of compounds, respectively, in both AUC and . Proposed approaches could enhance early molecular screening and design, advancing drug discovery capabilities.

Authors

  • Xuelian Jia
    Department of Chemistry and Biochemistry, Rowan University, Glassboro, New Jersey 08028, United States.
  • Donato Teutonico
    Translational Medicine & Early Development, Sanofi, Vitry-sur-Seine, France.
  • Saroj Dhakal
    Global DMPK Modeling & Simulation, Sanofi, 350 Water St, Cambridge, MA, 02141, USA.
  • Yorgos M Psarellis
    Department of Chemical and Biomolecular Engineering, Johns Hopkins University, Baltimore, USA.
  • Alexandra Abós
    Medical Psychology Unit, Department of Medicine, Institute of Neuroscience, University of Barcelona, Barcelona, Catalonia, Spain.
  • Hao Zhu
    State Key Laboratory of Advanced Technology for Materials Synthesis and Processing, Wuhan University of Technology Wuhan 430070 PR China chang@whut.edu.cn suntl@whut.edu.cn.
  • Panteleimon D Mavroudis
    Quantitative Pharmacology, DMPK, Sanofi US, Waltham, MA, USA.
  • Nikhil Pillai
    Quantitative Pharmacology, DMPK, Sanofi US, Waltham, MA, USA. Electronic address: nikhil.pillai@sanofi.com.