Guidelines for evaluating structure-based methods for protein-ligand binding prediction
File(s)
Accepted version
Author(s)
Tran-Nguyen, Viet-Khoa
Ballester, Pedro
Type
Journal Article
Abstract
Scoring functions built with advanced deep learning algorithms have recently gained prominence in protein-ligand pose generation and binding affinity prediction for computational drug design. However, a number of shortcomings make it increasingly difficult to evaluate scoring functions for a specific task across studies. Transparent disclosure of training data, code and procedures is essential to permit reproducibility, reuse and independent scrutiny. Guarding against data leakage, sampling bias and flawed design is equally important. Furthermore, meaningful comparisons of scoring functions require common data splits, checks for run-to-run variability and performance baselines. Here we propose a set of guidelines to help the community identify the most promising methods for these important problems.
Date Acceptance
2026-09-28
Citation
Nature Machine Intelligence
ISSN
2522-5839
Publisher
Nature Research
Journal / Book Title
Nature Machine Intelligence
Copyright Statement
Subject to copyright. This paper is embargoed until publication. Once published the author’s accepted manuscript will be made available under a CC-BY License in accordance with Imperial’s Research Publications Open Access policy (www.imperial.ac.uk/oa-policy).
License URL
Publication Status
Accepted