GS-DTI: a graph-structure-aware framework leveraging large language models for drug–target interaction prediction
Bioinformatics · 02.08.2025 · 41 (8)
DOI: 10.1093/bioinformatics/btaf445 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 09.08.2025. Verfasst von Qinze Yu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, CUHK, Hong Kong SAR 999077, China. Hauptthemen laut MEDLINE: Drug Discovery, Computational Biology. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Chinese University of Hong Kong.
Abstract (Originalsprache)
Motivation Accurate and generalizable prediction of drug–target interactions (DTIs) remains a critical challenge for drug discovery, particularly when addressing underexplored targets and compounds. Recent advances in graph neural networks and large-scale pre-trained models offer new opportunities to capture rich structural and functional features essential for DTI prediction while enhancing the generalization ability. Results We present GS-DTI, a graph structure-based DTI prediction framework that integrates molecular graph transformers, protein language models, and protein tertiary structure. Our method achieved robust and interpretable DTI predictions. GS-DTI extracts drug features from SMILES-derived molecular graphs using a knowledge-guided pre-trained transformer, while protein features are derived from both sequence and predicted 3D structure for comprehensive representation. A multi-task loss function equipped with contrastive learning is adopted to enhance generalization and functional interpretability. Extensive experiments on the benchmarks and challenging cross-domain settings demonstrate that GS-DTI achieves state-of-the-art performance. Notably, our model improves the MCC by over 10% compared to previous methods in the drug–target pair cold start test. The model can pinpoint the binding pockets of the targets, offering robust interpretability, and case studies show GS-DTI’s promising potential in virtual screening for new candidate drugs of BACE1. Availability and implementation The GS-DTI source code and processed datasets are available at https://github.com/purvavideha/GSDTI. All experimental data are derived from public sources.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Department of Computer Science and Engineering, CUHK, Hong Kong SAR 999077, China.
- Department of Computer Science and Technology, Beijing JiaoTong University, Beijing 100044, China.
- The CUHK Shenzhen Research Institute, Shenzhen 518057, China.
ORCID-Profile: Yu Li
Förderung
- Chinese University of Hong Kong
Zitieren
APA
Yu, Q., Zhou, C., Jiang, J., Shi, X., & Li, Y. (2025). GS-DTI: a graph-structure-aware framework leveraging large language models for drug–target interaction prediction. Bioinformatics, 41(8). https://doi.org/10.1093/bioinformatics/btaf445
Vancouver
Yu Q, Zhou C, Jiang J, Shi X, Li Y. GS-DTI: a graph-structure-aware framework leveraging large language models for drug–target interaction prediction. Bioinformatics. 2025;41(8). doi:10.1093/bioinformatics/btaf445
BibTeX
@article{Yu2025,
author = {Yu, Qinze and Zhou, Chang and Jiang, Jiyue and Shi, Xiangyu and Li, Yu},
title = {GS-DTI: a graph-structure-aware framework leveraging large language models for drug–target interaction prediction},
journal = {Bioinformatics},
year = {2025},
volume = {41},
number = {8},
doi = {10.1093/bioinformatics/btaf445}
}
EUVIMED