Resolving data bias improves generalization in binding affinity prediction.
Europe PMC REST API · Indexed academic record · Source published: Tue Oct 21 2025 00:00:00 GMT+0000 (Coordinated Universal Time) · Indexed here: Thu Oct 08 2026 09:08:05 GMT+0000 (Coordinated Universal Time)
Saved source excerpt
The field of computational drug design requires accurate scoring functions to predict binding affinities for protein-ligand interactions. However, train-test data leakage between the PDBbind database and the Comparative Assessment of Scoring Function benchmark datasets has severely inflated the performance metrics of currently available deep-learning-based binding affinity prediction models, leadi
This is a cited excerpt from the source. Read the original link for the complete text. Automated indexing and topic classification do not constitute fact verification.