EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SP-DTI: subpocket-informed transformer for drug–target interaction prediction

Sizhe Liu iD, Yuchen Liu, Haofeng Xu, Jun Xia iD, Stan Z Li

Bioinformatics · 2025

DOI: 10.1093/bioinformatics/btaf011 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2025. Verfasst von Sizhe Liu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Thomas Lord Department of Computer Science, University of Southern California, Los Angeles, CA 90089, United States. Hauptthemen laut MEDLINE: Drug Discovery, Proteins, Computational Biology. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Drug–target interaction (DTI) prediction is crucial for drug discovery, significantly reducing costs and time in experimental searches across vast drug compound spaces. While deep learning has advanced DTI prediction accuracy, challenges remain: (i) existing methods often lack generalizability, with performance dropping significantly on unseen proteins and cross-domain settings; and (ii) current molecular relational learning often overlooks subpocket-level interactions, which are vital for a detailed understanding of binding sites. Results We introduce SP-DTI, a subpocket-informed transformer model designed to address these challenges through: (i) detailed subpocket analysis using the Cavity Identification and Analysis Routine for interaction modeling at both global and local levels, and (ii) integration of pre-trained language models into graph neural networks to encode drugs and proteins, enhancing generalizability to unlabeled data. Benchmark evaluations show that SP-DTI consistently outperforms state-of-the-art models, achieving an area under the receiver operating characteristic curve of 0.873 in unseen protein settings, an 11% improvement over the best baseline. Availability and implementation The model scripts are available at https://github.com/Steven51516/SP-DTI.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Drug DiscoveryProteinsComputational BiologyBinding SitesNeural Networks, ComputerDeep LearningProtein BindingSoftware

Substanzen

Proteins

Autor:innen und Institutionen

  • Thomas Lord Department of Computer Science, University of Southern California, Los Angeles, CA 90089, United States.
  • Department of Quantitative and Computational Biology, University of Southern California, Los Angeles, CA 90089, United States.
  • School of Engineering, Westlake University, Hangzhou 310024, China.

ORCID-Profile: Sizhe Liu, Jun Xia

Förderung

  • National Natural Science Foundation of China Project

Zitieren

APA

Liu, S., Liu, Y., Xu, H., Xia, J., & Li, S. Z. (2025). SP-DTI: subpocket-informed transformer for drug–target interaction prediction. Bioinformatics. https://doi.org/10.1093/bioinformatics/btaf011

Vancouver

Liu S, Liu Y, Xu H, Xia J, Li SZ. SP-DTI: subpocket-informed transformer for drug–target interaction prediction. Bioinformatics. 2025. doi:10.1093/bioinformatics/btaf011

BibTeX
@article{Liu2025,
  author = {Liu, Sizhe and Liu, Yuchen and Xu, Haofeng and Xia, Jun and Li, Stan Z},
  title = {SP-DTI: subpocket-informed transformer for drug–target interaction prediction},
  journal = {Bioinformatics},
  year = {2025},
  doi = {10.1093/bioinformatics/btaf011}
}
Kostenlos starten →