AUTHOR=Kim Hyojin , Shim Heesung , Ranganath Aditya , He Stewart , Stevenson Garrett , Allen Jonathan E. 

TITLE=Protein-ligand binding affinity prediction using multi-instance learning with docking structures

JOURNAL=Frontiers in Pharmacology

VOLUME=Volume 15 - 2024

YEAR=2025

URL=https://www.frontiersin.org/journals/pharmacology/articles/10.3389/fphar.2024.1518875

DOI=10.3389/fphar.2024.1518875

ISSN=1663-9812

ABSTRACT=Recent advances in 3D structure-based deep learning approaches demonstrate improved accuracy in predicting protein-ligand binding affinity in drug discovery. These methods complement physics-based computational modeling such as molecular docking for virtual high-throughput screening. Despite recent advances and improved predictive performance, most methods in this category primarily rely on utilizing co-complex crystal structures and experimentally measured binding affinities as both input and output data for model training. Nevertheless, co-complex crystal structures are not readily available and the inaccurate predicted structures from molecular docking can degrade the accuracy of the machine learning methods. We introduce a novel structure-based inference method utilizing multiple molecular docking poses for each co-complex entity. Our proposed method employs multi-instance learning with an attention network to predict binding affinity from a collection of docking poses. We validate our method using multiple datasets, including PDBbind and compounds targeting the main protease of SARS-CoV-2. The results demonstrate that our method leveraging docking poses is competitive with other state-of-the-art inference models that depend on co-complex crystal structures. This method offers binding affinity prediction without requiring co-complex crystal structures, thereby increasing its applicability to protein targets lacking such data.