Scoring protein-ligand binding structures through learning atomic graphs with inter-molecular adjacency.

With a burgeoning number of artificial intelligence (AI) applications in various fields, biomolecular science has also given a big welcome to advanced AI techniques in recent years. In this broad field, scoring a protein-ligand binding structure to output the binding strength is a crucial problem th...

Full description

Saved in:
Bibliographic Details
Main Authors: Debby D Wang, Yuting Huang
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-05-01
Series:PLoS Computational Biology
Online Access:https://doi.org/10.1371/journal.pcbi.1013074
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850151563960516608
author Debby D Wang
Yuting Huang
author_facet Debby D Wang
Yuting Huang
author_sort Debby D Wang
collection DOAJ
description With a burgeoning number of artificial intelligence (AI) applications in various fields, biomolecular science has also given a big welcome to advanced AI techniques in recent years. In this broad field, scoring a protein-ligand binding structure to output the binding strength is a crucial problem that heavily relates to computational drug discovery. Aiming at this problem, we have proposed an efficient scoring framework using deep learning techniques. This framework describes a binding structure by a high-resolution atomic graph, places a focus on the inter-molecular interactions and learns the graph in a rational way. For a protein-ligand binding complex, the generated atomic graph reserves key information of the atoms (as graph nodes), and focuses on inter-molecular interactions (as graph edges) that can be identified by introducing multiple distance ranges to the atom pairs within the binding area. To provide more confidence in the predicted binding strengths, we have interpreted the deep learning model from the model level and in a post-hoc analysis. The proposed learning framework has been demonstrated to have competitive performance in scoring and screening tasks, which will prospectively promote the development of related fields further.
format Article
id doaj-art-0f2458a3f49a40a8a73bf5e2726a0b87
institution OA Journals
issn 1553-734X
1553-7358
language English
publishDate 2025-05-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS Computational Biology
spelling doaj-art-0f2458a3f49a40a8a73bf5e2726a0b872025-08-20T02:26:11ZengPublic Library of Science (PLoS)PLoS Computational Biology1553-734X1553-73582025-05-01215e101307410.1371/journal.pcbi.1013074Scoring protein-ligand binding structures through learning atomic graphs with inter-molecular adjacency.Debby D WangYuting HuangWith a burgeoning number of artificial intelligence (AI) applications in various fields, biomolecular science has also given a big welcome to advanced AI techniques in recent years. In this broad field, scoring a protein-ligand binding structure to output the binding strength is a crucial problem that heavily relates to computational drug discovery. Aiming at this problem, we have proposed an efficient scoring framework using deep learning techniques. This framework describes a binding structure by a high-resolution atomic graph, places a focus on the inter-molecular interactions and learns the graph in a rational way. For a protein-ligand binding complex, the generated atomic graph reserves key information of the atoms (as graph nodes), and focuses on inter-molecular interactions (as graph edges) that can be identified by introducing multiple distance ranges to the atom pairs within the binding area. To provide more confidence in the predicted binding strengths, we have interpreted the deep learning model from the model level and in a post-hoc analysis. The proposed learning framework has been demonstrated to have competitive performance in scoring and screening tasks, which will prospectively promote the development of related fields further.https://doi.org/10.1371/journal.pcbi.1013074
spellingShingle Debby D Wang
Yuting Huang
Scoring protein-ligand binding structures through learning atomic graphs with inter-molecular adjacency.
PLoS Computational Biology
title Scoring protein-ligand binding structures through learning atomic graphs with inter-molecular adjacency.
title_full Scoring protein-ligand binding structures through learning atomic graphs with inter-molecular adjacency.
title_fullStr Scoring protein-ligand binding structures through learning atomic graphs with inter-molecular adjacency.
title_full_unstemmed Scoring protein-ligand binding structures through learning atomic graphs with inter-molecular adjacency.
title_short Scoring protein-ligand binding structures through learning atomic graphs with inter-molecular adjacency.
title_sort scoring protein ligand binding structures through learning atomic graphs with inter molecular adjacency
url https://doi.org/10.1371/journal.pcbi.1013074
work_keys_str_mv AT debbydwang scoringproteinligandbindingstructuresthroughlearningatomicgraphswithintermolecularadjacency
AT yutinghuang scoringproteinligandbindingstructuresthroughlearningatomicgraphswithintermolecularadjacency