A Novel 4-D Dataset Paradigm for Studying Complete Ligand-Protein Dissociation Dynamics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Maodong, Zhang, Jiying, Wang, Zhe, Feng, Bin, Zeng, Wenqi, Chen, Dechin, Pan, Zhijun, Li, Yu, Liu, Zijing, Yang, Yi Isaac
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908833925824512
author Li, Maodong
Zhang, Jiying
Wang, Zhe
Feng, Bin
Zeng, Wenqi
Chen, Dechin
Pan, Zhijun
Li, Yu
Liu, Zijing
Yang, Yi Isaac
author_facet Li, Maodong
Zhang, Jiying
Wang, Zhe
Feng, Bin
Zeng, Wenqi
Chen, Dechin
Pan, Zhijun
Li, Yu
Liu, Zijing
Yang, Yi Isaac
contents The kinetics and dynamics of drug-protein binding and dissociation are crucial to understanding drug absorption and metabolism. Despite advances in artificial intelligence (AI) tools for drug-protein interaction studies, existing training datasets remain limited to static structures or quasi-static conformations. This paper proposes a novel computational approach for rapidly generating drug-protein dissociation trajectories and presents the inaugural dynamically time-resolved 4-D (t, x, y, z) trajectory database DD-13M. This dataset captures over 26,000 complete dissociation processes for 565 ligand-protein complexes, providing nearly 13 million frames of all-atom simulation trajectories. A deep equivariant generative model, UnbindingFlow, was trained using the DD-13M dataset. This model has the capacity to produce dissociation trajectories for novel targets whilst accurately predicting their rate constants (koff). DD-13M introduces a new type of training dataset for AI models, establishing a de novo paradigm for studying the dynamics of drug-protein interactions.
format Preprint
id arxiv_https___arxiv_org_abs_2504_18367
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Novel 4-D Dataset Paradigm for Studying Complete Ligand-Protein Dissociation Dynamics
Li, Maodong
Zhang, Jiying
Wang, Zhe
Feng, Bin
Zeng, Wenqi
Chen, Dechin
Pan, Zhijun
Li, Yu
Liu, Zijing
Yang, Yi Isaac
Computational Physics
Machine Learning
Chemical Physics
Biomolecules
The kinetics and dynamics of drug-protein binding and dissociation are crucial to understanding drug absorption and metabolism. Despite advances in artificial intelligence (AI) tools for drug-protein interaction studies, existing training datasets remain limited to static structures or quasi-static conformations. This paper proposes a novel computational approach for rapidly generating drug-protein dissociation trajectories and presents the inaugural dynamically time-resolved 4-D (t, x, y, z) trajectory database DD-13M. This dataset captures over 26,000 complete dissociation processes for 565 ligand-protein complexes, providing nearly 13 million frames of all-atom simulation trajectories. A deep equivariant generative model, UnbindingFlow, was trained using the DD-13M dataset. This model has the capacity to produce dissociation trajectories for novel targets whilst accurately predicting their rate constants (koff). DD-13M introduces a new type of training dataset for AI models, establishing a de novo paradigm for studying the dynamics of drug-protein interactions.
title A Novel 4-D Dataset Paradigm for Studying Complete Ligand-Protein Dissociation Dynamics
topic Computational Physics
Machine Learning
Chemical Physics
Biomolecules
url https://arxiv.org/abs/2504.18367