Enhancing kinase-inhibitor activity and selectivity prediction through contrastive learning

Yanan Tian, Ruiqiang Lu, Xiaoqing Gong, Wei Zhao, Yuquan Li, Xiaorui Wang, Xinming Jia, Qin Li, Yuwei Yang, Henry H. Y. Tong, Joel P. Arrais, Xiaojun Yao () and Huanxiang Liu ()
Additional contact information
Yanan Tian: Macao Polytechnic University, Faculty of Applied Sciences
Ruiqiang Lu: Macao Polytechnic University, Faculty of Applied Sciences
Xiaoqing Gong: Macao Polytechnic University, Faculty of Applied Sciences
Wei Zhao: Macao Polytechnic University, Faculty of Applied Sciences
Yuquan Li: Guizhou University, State Key Laboratory of Public Big Data, College of Computer Science and Technology
Xiaorui Wang: Zhejiang University, College of Pharmaceutical Sciences
Xinming Jia: Macao Polytechnic University, Faculty of Applied Sciences
Qin Li: Macao Polytechnic University, Faculty of Applied Sciences
Yuwei Yang: Macao Polytechnic University, Faculty of Applied Sciences
Henry H. Y. Tong: Macao Polytechnic University, Faculty of Applied Sciences
Joel P. Arrais: University of Coimbra, CISUC/LASI—Centre for Informatics and Systems of the University of Coimbra, Department of Informatics Engineering
Xiaojun Yao: Macao Polytechnic University, Faculty of Applied Sciences
Huanxiang Liu: Macao Polytechnic University, Faculty of Applied Sciences

Nature Communications, 2025, vol. 16, issue 1, 1-22

Abstract: Abstract Developing selective kinase inhibitors is challenging due to the conserved kinase structures and costly kinome profiling experiments, highlighting the need for accurate prediction of kinase-inhibitor affinity and specificity. Here we present MMCLKin, an attention consistency-guided contrastive learning framework that integrates geometric graph and sequence networks with multi-head attention and multimodal, multiscale contrastive learning to accurately and interpretably predict kinase-inhibitor activity and selectivity. MMCLKin outperforms existing methods across two 3D kinase-drug datasets and demonstrates strong generalizability on ten diverse protein-drug and one mutation-aware datasets, and effectively screens on both known and unknown kinase structures. In-depth analysis of attention coefficients reveals that MMCLKin can identify key residues and molecular functional groups critical for kinase-inhibitor binding. Additionally, ADP-Glo assays confirm that five out of 20 MMCLKin-identified compounds inhibit the pathogenic LRRK2 G2019S mutant, with four exhibiting nanomolar-level potency. Collectively, MMCLKin represents a useful tool for discovering potent and selective kinase inhibitors.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-025-65869-8 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-025-65869-8

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-025-65869-8

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().