Practically Significant Method Comparison Protocols for Machine Learning in Small Molecule Drug Discovery
Review article, 2025
Machine Learning (ML) methods that relate molecular structure to properties are frequently proposed as in silico surrogates for expensive or time-consuming experiments. In small molecule drug discovery, such methods inform high-stakes decisions like compound synthesis and in vivo studies. This application lies at the intersection of multiple scientific disciplines. When comparing new ML methods to baseline or state-of-the-art approaches, statistically rigorous method comparison protocols and domain-appropriate performance metrics are essential to ensure replicability and ultimately the adoption of ML in small molecule drug discovery. This paper proposes a set of guidelines to incentivize rigorous and domain-appropriate techniques for method comparison tailored to small molecule property modeling. These guidelines, accompanied by annotated examples using open-source software tools, lay a foundation for robust ML benchmarking and thus the development of more impactful methods.
Author
Jeremy R. Ash
Johnson & Johnson Innovative Medicine
Cas Wognum
Recursion Pharmaceuticals
Valence Discovery
Raquel Rodríguez-Pérez
Novartis International AG
Matteo Aldeghi
Bayer AG
Alan C. Cheng
Merck & Co., Inc.
Djork Arné Clevert
Pfizer
Ola Engkvist
Chalmers, Computer Science and Engineering (Chalmers), Data Science and AI
AstraZeneca AB
Cheng Fang
Blueprint Medicines Corporation
Daniel J. Price
Nimbus Therapeutics
Jacqueline M. Hughes-Oliver
North Carolina State University
W. Patrick Walters
Relay Therapeutics
Journal of Chemical Information and Modeling
1549-9596 (ISSN) 1549960x (eISSN)
Vol. 65 18 9398-9411Subject Categories (SSIF 2025)
Bioinformatics (Computational Biology)
Computer Sciences
Signal Processing
DOI
10.1021/acs.jcim.5c01609
PubMed
40932128