DTIAM: a Unified Framework for Predicting Drug-target Interactions, Binding Affinities and Drug Mechanisms

Overview

Journal Nat Commun

Specialty Biology

Date 2025 Mar 16

PMID 40089473

Authors

Zhangli Lu

Guoqiang Song

Huimin Zhu

Chuqi Lei

Xinliang Sun

Kaili Wang

Libo Qin

Yafei Chen

Jing Tang

Min Li

Affiliations

Soon will be listed here.

Abstract

Accurate and robust prediction of drug-target interactions (DTIs) plays a vital role in drug discovery but remains challenging due to limited labeled data, cold start problems, and insufficient understanding of mechanisms of action (MoA). Distinguishing activation and inhibition mechanisms is particularly critical in clinical applications. Here, we propose DTIAM, a unified framework for predicting interactions, binding affinities, and activation/inhibition mechanisms between drugs and targets. DTIAM learns drug and target representations from large amounts of label-free data through self-supervised pre-training, which accurately extracts their substructure and contextual information, and thus benefits the downstream prediction based on these representations. DTIAM achieves substantial performance improvement over other state-of-the-art methods in all tasks, particularly in the cold start scenario. Moreover, independent validation demonstrates the strong generalization ability of DTIAM. All these results suggest that DTIAM can provide a practically useful tool for predicting novel DTIs and further distinguishing the MoA of candidate drugs.

References

Wen M, Zhang Z, Niu S, Sha H, Yang R, Yun Y . Deep-Learning-Based Drug-Target Interaction Prediction. J Proteome Res. 2017; 16(4):1401-1409. DOI: 10.1021/acs.jproteome.6b00618. View

DiMasi J, Hansen R, Grabowski H . The price of innovation: new estimates of drug development costs. J Health Econ. 2003; 22(2):151-85. DOI: 10.1016/S0167-6296(02)00126-1. View

Paul S, Mytelka D, Dunwiddie C, Persinger C, Munos B, Lindborg S . How to improve R&D productivity: the pharmaceutical industry's grand challenge. Nat Rev Drug Discov. 2010; 9(3):203-14. DOI: 10.1038/nrd3078. View

Pushpakom S, Iorio F, Eyers P, Jane Escott K, Hopper S, Wells A . Drug repurposing: progress, challenges and recommendations. Nat Rev Drug Discov. 2018; 18(1):41-58. DOI: 10.1038/nrd.2018.168. View

Zhang P, Wei Z, Che C, Jin B . DeepMGT-DTI: Transformer network incorporating multilayer graph information for Drug-Target interaction prediction. Comput Biol Med. 2022; 142:105214. DOI: 10.1016/j.compbiomed.2022.105214. View

Zhu H, Zhou R, Cao D, Tang J, Li M . A pharmacophore-guided deep learning approach for bioactive molecular generation. Nat Commun. 2023; 14(1):6234. PMC: 10558534. DOI: 10.1038/s41467-023-41454-9. View

Batool M, Ahmad B, Choi S . A Structure-Based Drug Discovery Paradigm. Int J Mol Sci. 2019; 20(11). PMC: 6601033. DOI: 10.3390/ijms20112783. View

Yang D, Zhou Q, Labroska V, Qin S, Darbalaei S, Wu Y . G protein-coupled receptors: structure- and function-based drug discovery. Signal Transduct Target Ther. 2021; 6(1):7. PMC: 7790836. DOI: 10.1038/s41392-020-00435-w. View

Saikia S, Bordoloi M . Molecular Docking: Challenges, Advances and its Use in Drug Discovery Perspective. Curr Drug Targets. 2018; 20(5):501-521. DOI: 10.2174/1389450119666181022153016. View

10.

Pagadala N, Syed K, Tuszynski J . Software for molecular docking: a review. Biophys Rev. 2017; 9(2):91-102. PMC: 5425816. DOI: 10.1007/s12551-016-0247-1. View

11.

Mei J, Kwoh C, Yang P, Li X, Zheng J . Drug-target interaction prediction by learning from local information and neighbors. Bioinformatics. 2012; 29(2):238-45. DOI: 10.1093/bioinformatics/bts670. View

12.

Olayan R, Ashoor H, Bajic V . DDR: efficient computational method to predict drug-target interactions using graph mining and machine learning approaches. Bioinformatics. 2017; 34(7):1164-1173. PMC: 5998943. DOI: 10.1093/bioinformatics/btx731. View

13.

Wu Y, Gao M, Zeng M, Zhang J, Li M . BridgeDPI: a novel Graph Neural Network for predicting drug-protein interactions. Bioinformatics. 2022; 38(9):2571-2578. DOI: 10.1093/bioinformatics/btac155. View

14.

Wu Z, Li W, Liu G, Tang Y . Network-Based Methods for Prediction of Drug-Target Interactions. Front Pharmacol. 2018; 9:1134. PMC: 6189482. DOI: 10.3389/fphar.2018.01134. View

15.

Chen R, Liu X, Jin S, Lin J, Liu J . Machine Learning for Drug-Target Interaction Prediction. Molecules. 2018; 23(9). PMC: 6225477. DOI: 10.3390/molecules23092208. View

16.

DSouza S, Prema K, Balaji S . Machine learning models for drug-target interactions: current knowledge and future directions. Drug Discov Today. 2020; 25(4):748-756. DOI: 10.1016/j.drudis.2020.03.003. View

17.

Shi H, Liu S, Chen J, Li X, Ma Q, Yu B . Predicting drug-target interactions using Lasso with random forest based on evolutionary information and chemical structure. Genomics. 2018; 111(6):1839-1852. DOI: 10.1016/j.ygeno.2018.12.007. View

18.

Nguyen T, Le H, Quinn T, Nguyen T, Le T, Venkatesh S . GraphDTA: predicting drug-target binding affinity with graph neural networks. Bioinformatics. 2020; 37(8):1140-1147. DOI: 10.1093/bioinformatics/btaa921. View

19.

Jiang M, Li Z, Zhang S, Wang S, Wang X, Yuan Q . Drug-target affinity prediction using graph neural network and contact maps. RSC Adv. 2022; 10(35):20701-20712. PMC: 9054320. DOI: 10.1039/d0ra02297g. View

20.

Karimi M, Wu D, Wang Z, Shen Y . DeepAffinity: interpretable deep learning of compound-protein affinity through unified recurrent and convolutional neural networks. Bioinformatics. 2019; 35(18):3329-3338. PMC: 6748780. DOI: 10.1093/bioinformatics/btz111. View