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

Journal Article · 03 January 2025 · Frontiers in Pharmacology

DOI: https://doi.org/10.3389/fphar.2024.1518875 · OSTI ID:2516789

Kim, Hyojin ^[1]; Shim, Heesung ^[1]; Ranganath, Aditya ^[1]; He, Stewart ^[1]; Stevenson, Garrett ^[1]; Allen, Jonathan E. ^[1]

---

1. Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)

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-crystal complex structures and experimentally measured binding affinities as both input and output data for model training. Nevertheless, co-crystal complex 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 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-crystal structures. This method offers binding affinity prediction without requiring co-crystal structures, thereby increasing its applicability to protein targets lacking such data.

• Research Organization: Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
• Sponsoring Organization: Defense Threat Reduction Agency (DTRA); USDOE National Nuclear Security Administration (NNSA)
• Grant/Contract Number: AC52-07NA27344
• OSTI ID: 2516789
• Report Number(s): LLNL--JRNL-2000673
• Journal Information: Frontiers in Pharmacology, Journal Name: Frontiers in Pharmacology Vol. 15; ISSN 1663-9812
• Publisher: Frontiers Research FoundationCopyright Statement
• Country of Publication: United States
• Language: English