Health AI Central
Share:
Peer-Reviewed Publication
J Chem Inf Model2025;65(18):9398-9411.September 22, 2025Comparative Study

Practically Significant Method Comparison Protocols for Machine Learning in Small Molecule Drug Discovery.

Jeremy R Ash1, Cas Wognum2,3, Raquel Rodríguez-Pérez4, Matteo Aldeghi5, Alan C Cheng6, Djork-Arné Clevert7, Ola Engkvist8,9, Cheng Fang10, Daniel J Price11, Jacqueline M Hughes-Oliver12, W Patrick Walters13
1Johnson & Johnson Innovative Medicine, Spring House, Pennsylvania 19477, United States.
2Valence Laboratories, Montréal, Québec H2S 3G6, Canada.
3Recursion Pharmaceuticals, Salt Lake City, Utah 84101, United States.
4Novartis Pharma AG, Basel CH-4056, Switzerland.
5Bayer Research and Innovation Center, Cambridge, Massachusetts 02142, United States.
6Merck & Co., Inc., South San Francisco, California 94080, United States.
7Pfizer Research and Development, Berlin 10117, Germany.
8Department of Computer Science and Engineering, Chalmers University of Technology & University of Gothenburg, Gothenburg, Mölndal 412 58, Sweden.
9Molecular AI, Discovery Sciences AstraZeneca R&D, Gothenburg, Mölndal 431 83, Sweden.
10Blueprint Medicines Corporation, Cambridge, Massachusetts 02139, United States.
11Nimbus Therapeutics, Boston, Massachusetts 02210, United States.
12Department of Statistics, North Carolina State University, Raleigh, North Carolina 27607, United States.
13Relay Therapeutics, Cambridge, Massachusetts 02139, United States.
PubMed DOI

Abstract

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…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free AccountSign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.