EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Kinase–inhibitor binding affinity prediction with pretrained graph encoder and language model

Xudong Guo, Zixu Ran, Fuyi Li

Briefings in Bioinformatics · 2025

DOI: 10.1093/bib/bbaf338 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Xudong Guo und 2 weiteren Autor:innen. Beteiligte Einrichtung: College of Information Engineering, Northwest A&F University, Yangling, 712100, China. Hauptthemen laut MEDLINE: Protein Kinase Inhibitors. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China, Qin Chuangyuan Innovation and Entrepreneurship Talent Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurately predicting inhibitor–kinase binding affinity is crucial in drug discovery and medical applications, especially in the treatment of diseases such as cancer. Existing methods for predicting inhibitor–kinase affinity still face challenges, including insufficient data expression, limited feature extraction, and low performance. Despite the progress made through artificial intelligence methods, particularly deep learning technology, many current methods fail to capture the intricate interactions between kinases and inhibitors. Therefore, it is necessary to develop more advanced methods to solve the existing problems in inhibitor–kinase binding prediction. This study proposed Kinhibit, a novel framework for inhibitor–kinase binding affinity prediction. Kinhibit integrates self-supervised graph contrastive learning with multiview molecular graph representation and structure-informed protein language model (ESM-S) to extract features effectively. Kinhibit also employed a feature fusion approach to optimize the fusion of inhibitor and kinase features. Experimental results demonstrate the superiority of this method, achieving an accuracy of 92.6% in inhibitor prediction tasks of three mitogen-activated protein kinase (MAPK) signalling pathway kinases: Raf protein kinase (RAF), Mitogen-activated protein kinase kinase (MEK), and Extracellular Signal-Regulated Kinase (ERK). Furthermore, the framework achieves an impressive accuracy of 92.9% on the MAPK-All dataset. This study provides promising and effective tools for drug screening and biological sciences.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Protein Kinase InhibitorsHumansProtein BindingDeep LearningComputational BiologyDrug Discovery

Stichwörter der Autor:innen

binding affinitycontrastive learninggraph neural networkinhibitorkinase

Substanzen

Protein Kinase Inhibitors

Autor:innen und Institutionen

  • College of Information Engineering, Northwest A&F University, Yangling, 712100, China.
  • South Australian Immunogenomics Cancer Institute (SAiGENCI), The University of Adelaide, Adelaide 5005, South Australia, Australia.

Förderung

  • National Natural Science Foundation of China
  • National Key Research and Development Program of China
  • Qin Chuangyuan Innovation and Entrepreneurship Talent Project

Zitieren

APA

Guo, X., Ran, Z., & Li, F. (2025). Kinase–inhibitor binding affinity prediction with pretrained graph encoder and language model. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf338

Vancouver

Guo X, Ran Z, Li F. Kinase–inhibitor binding affinity prediction with pretrained graph encoder and language model. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf338

BibTeX
@article{Guo2025,
  author = {Guo, Xudong and Ran, Zixu and Li, Fuyi},
  title = {Kinase–inhibitor binding affinity prediction with pretrained graph encoder and language model},
  journal = {Briefings in Bioinformatics},
  year = {2025},
  doi = {10.1093/bib/bbaf338}
}
Kostenlos starten →