EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DTAP: a unified graph transformer framework for joint prediction of drug–target affinity and docking pose

Junxi Liu, Yulian Ding, Yan Yan, Liangzhen Zheng, Yi Pan

Briefings in Bioinformatics · 2026

DOI: 10.1093/bib/bbag069 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Junxi Liu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Southern University of Science and Technology, Shenzhen 518055, China. Hauptthemen laut MEDLINE: Molecular Docking Simulation, Proteins, Drug Discovery. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Industry-University-Research Support Special Project of Jianye High-tech Zone Science and Technology Program, Shenzhen Science and Technology Program, Shenzhen Key Laboratory of Intelligent Bioinformatics.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Predicting drug–target interactions (DTIs) is crucial for modern drug discovery. However, existing machine learning models have significant limitations: they are typically designed for a single task—either predicting binding affinity or docking pose—leading to excellent performance on one metric but limited practical utility. These models also often struggle with generalizability to novel molecules and proteins due to their reliance on small, labeled datasets. Furthermore, they frequently ignore the essential information contained within the 3D structure of proteins and molecules. To overcome these challenges, we introduce DTAP, a unified framework that simultaneously predicts both the quality of docking poses and drug–target binding affinity. To boost its generalizability, DTAP leverages pretrained large models to learn rich, contextual representations of drugs and targets from extensive unlabeled data. The framework also directly incorporates 3D structural data from both molecules and proteins, using two graph transformers to learn their joint representations. A shared latent vector and task-specific decoders enable crucial cross-task knowledge transfer, allowing the model to learn from the interconnected nature of these two properties. DTAP significantly outperforms state-of-the-art methods on both tasks, demonstrating superior performance especially in cold start situations where data are scarce. Our interpretability analysis on the model’s attention mechanisms confirms its ability to effectively focus on key binding sites. All results indicate that DTAP is a valuable and practical tool for accurately predicting drug–target affinities and docking poses.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Molecular Docking SimulationProteinsDrug DiscoveryProtein BindingHumansAlgorithmsMachine Learning

Stichwörter der Autor:innen

docking posesdrug–target affinitygraph transformermulti-task learningpretrained large model

Substanzen

Proteins

Autor:innen und Institutionen

  • Southern University of Science and Technology, Shenzhen 518055, China.
  • Computer Science and Artificial Intelligence, Shenzhen University of Advanced Technology, Shenzhen 518107, China.
  • Nanjing Hanwei Public Health Research Institute Co., Ltd, Nanjing 210000, China.
  • Central for High Performance Computing, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China.
  • Shenzhen Zelixir Biotech Company Ltd., Shenzhen 518107, China.
  • Shenzhen Key Laboratory of Intelligent Bioinformatics, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China.

Förderung

  • Industry-University-Research Support Special Project of Jianye High-tech Zone Science and Technology Program
  • Shenzhen Science and Technology Program
  • Shenzhen Key Laboratory of Intelligent Bioinformatics
  • National Natural Science Foundation of China
  • Guangdong Basic and Applied Basic Research Foundation

Zitieren

APA

Liu, J., Ding, Y., Yan, Y., Zheng, L., & Pan, Y. (2026). DTAP: a unified graph transformer framework for joint prediction of drug–target affinity and docking pose. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag069

Vancouver

Liu J, Ding Y, Yan Y, Zheng L, Pan Y. DTAP: a unified graph transformer framework for joint prediction of drug–target affinity and docking pose. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag069

BibTeX
@article{Liu2026,
  author = {Liu, Junxi and Ding, Yulian and Yan, Yan and Zheng, Liangzhen and Pan, Yi},
  title = {DTAP: a unified graph transformer framework for joint prediction of drug–target affinity and docking pose},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  doi = {10.1093/bib/bbag069}
}
Kostenlos starten →