PocketVina Enables Scalable and Highly Accurate Physically Valid Docking through Multi-Pocket Conditioning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sarigun, Ahmet, Uyar, Bora, Franke, Vedran, Akalin, Altuna
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911021293109248
author Sarigun, Ahmet
Uyar, Bora
Franke, Vedran
Akalin, Altuna
author_facet Sarigun, Ahmet
Uyar, Bora
Franke, Vedran
Akalin, Altuna
contents Sampling physically valid ligand-binding poses remains a major challenge in molecular docking, particularly for unseen or structurally diverse targets. We introduce PocketVina, a fast and memory-efficient, search-based docking framework that combines pocket prediction with systematic multi-pocket exploration. We evaluate PocketVina across four established benchmarks--PDBbind2020 (timesplit and unseen), DockGen, Astex, and PoseBusters--and observe consistently strong performance in sampling physically valid docking poses. PocketVina achieves state-of-the-art performance when jointly considering ligand RMSD and physical validity (PB-valid), while remaining competitive with deep learning-based approaches in terms of RMSD alone, particularly on structurally diverse and previously unseen targets. PocketVina also maintains state-of-the-art physically valid docking accuracy across ligands with varying degrees of flexibility. We further introduce TargetDock-AI, a benchmarking dataset we curated, consisting of over 500000 protein-ligand pairs, and a partition of the dataset labeled with PubChem activity annotations. On this large-scale dataset, PocketVina successfully discriminates active from inactive targets, outperforming a deep learning baseline while requiring significantly less GPU memory and runtime. PocketVina offers a robust and scalable docking strategy that requires no task-specific training and runs efficiently on standard GPUs, making it well-suited for high-throughput virtual screening and structure-based drug discovery.
format Preprint
id arxiv_https___arxiv_org_abs_2506_20043
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PocketVina Enables Scalable and Highly Accurate Physically Valid Docking through Multi-Pocket Conditioning
Sarigun, Ahmet
Uyar, Bora
Franke, Vedran
Akalin, Altuna
Quantitative Methods
Machine Learning
Biomolecules
Sampling physically valid ligand-binding poses remains a major challenge in molecular docking, particularly for unseen or structurally diverse targets. We introduce PocketVina, a fast and memory-efficient, search-based docking framework that combines pocket prediction with systematic multi-pocket exploration. We evaluate PocketVina across four established benchmarks--PDBbind2020 (timesplit and unseen), DockGen, Astex, and PoseBusters--and observe consistently strong performance in sampling physically valid docking poses. PocketVina achieves state-of-the-art performance when jointly considering ligand RMSD and physical validity (PB-valid), while remaining competitive with deep learning-based approaches in terms of RMSD alone, particularly on structurally diverse and previously unseen targets. PocketVina also maintains state-of-the-art physically valid docking accuracy across ligands with varying degrees of flexibility. We further introduce TargetDock-AI, a benchmarking dataset we curated, consisting of over 500000 protein-ligand pairs, and a partition of the dataset labeled with PubChem activity annotations. On this large-scale dataset, PocketVina successfully discriminates active from inactive targets, outperforming a deep learning baseline while requiring significantly less GPU memory and runtime. PocketVina offers a robust and scalable docking strategy that requires no task-specific training and runs efficiently on standard GPUs, making it well-suited for high-throughput virtual screening and structure-based drug discovery.
title PocketVina Enables Scalable and Highly Accurate Physically Valid Docking through Multi-Pocket Conditioning
topic Quantitative Methods
Machine Learning
Biomolecules
url https://arxiv.org/abs/2506.20043