Current BioinformaticsCurrent BioinformaticsCurrent Bioinformatics1574-89362212-392XBentham Science64386110.2174/0115748936264731230928112936Life SciencesResearch ArticleQLDTI: A Novel Reinforcement Learning-based Prediction Model for Drug-Target InteractionGaoJieinfo@benthamscience.netFuQiminginfo@benthamscience.netSunJiachenginfo@benthamscience.netWangYunzheinfo@benthamscience.netXiaYoubinginfo@benthamscience.netLuYouinfo@benthamscience.netWuHongjieinfo@benthamscience.netChenJianpinginfo@benthamscience.netSchool of Electronic and Information Engineering, Suzhou University of Science and TechnologySchool of Medical Informatics, Xuzhou Medical UniversityJiangsu Province Key Laboratory of Intelligent Building Energy Efficiency, Suzhou University of Science and Technology0104202419435237407012025Copyright ©; 2024, Bentham Science Publishers2024Bentham Science Publishershttps://journals.eco-vector.com/1574-8936/article/view/643861

Background:Predicting drug-target interaction (DTI) plays a crucial role in drug research and development. More and more researchers pay attention to the problem of developing more powerful prediction methods. Traditional DTI prediction methods are basically realized by biochemical experiments, which are time-consuming, risky, and costly. Nowadays, DTI prediction is often solved by using a single information source and a single model, or by combining some models, but the prediction results are still not accurate enough.

Objective:The study aimed to utilize existing data and machine learning models to integrate heterogeneous data sources and different models, further improving the accuracy of DTI prediction.

Methods:This paper has proposed a novel prediction method based on reinforcement learning, called QLDTI (predicting drug-target interaction based on Q-learning), which can be mainly divided into two parts: data fusion and model fusion. Firstly, it fuses the drug and target similarity matrices calculated by different calculation methods through Q-learning. Secondly, the new similarity matrices are inputted into five models, NRLMF, CMF, BLM-NII, NetLapRLS, and WNN-GIP, for further training. Then, all sub-model weights are continuously optimized again by Q-learning, which can be used to linearly weight all sub-model prediction results to output the final prediction result.

Results:QLDTI achieved AUC accuracy of 99.04%, 99.12%, 98.28%, and 98.35% on E, NR, IC, and GPCR datasets, respectively. Compared to the existing five models NRLMF, CMF, BLM-NII, NetLapRLS, and WNN-GIP, the QLDTI method has achieved better results on four benchmark datasets of E, NR, IC, and GPCR.

Conclusion:Data fusion and model fusion have been proven effective for DTI prediction, further improving the prediction accuracy of DTI.

Drug-target interactionsdata fusionmodel fusionQ-learningweight distributionmachine learning.Sachdev K, Gupta MK. A comprehensive review of feature based methods for drug target interaction prediction. J Biomed Inform 2019; 93: 103159. doi: 10.1016/j.jbi.2019.103159 PMID: 30926470Chen R, Liu X, Jin S, Lin J, Liu J. Machine learning for drug-target interaction prediction. Molecules 2018; 23(9): 2208. doi: 10.3390/molecules23092208 PMID: 30200333Keiser MJ, Roth BL, Armbruster BN, Ernsberger P, Irwin JJ, Shoichet BK. Relating protein pharmacology by ligand chemistry. Nat Biotechnol 2007; 25(2): 197-206. doi: 10.1038/nbt1284 PMID: 17287757Pujadas G, Vaque M, Ardevol A, et al. Protein-ligand docking: A review of recent advances and future perspectives. Curr Pharm Anal 2008; 4(1): 1-19. doi: 10.2174/157341208783497597Jumper J, Evans R, Pritzel A, et al. Highly accurate protein structure prediction with AlphaFold. Nature 2021; 596(7873): 583-9. doi: 10.1038/s41586-021-03819-2 PMID: 34265844Yamanishi Y. Chemogenomic approaches to infer drug–target interaction networksData Mining for Systems Biology: Methods and Protocols. Totowa, NJ, USA: Humana Press 2013; Vol. 939: pp. 97-113. doi: 10.1007/978-1-62703-107-3_9Mousavian Z, Masoudi-Nejad A. Drug–target interaction prediction via chemogenomic space: Learning-based methods. Expert Opin Drug Metab Toxicol 2014; 10(9): 1273-87. doi: 10.1517/17425255.2014.950222 PMID: 25112457Tabei Y, Pauwels E, Stoven V, Takemoto K, Yamanishi Y. Identification of chemogenomic features from drug–target interaction networks using interpretable classifiers. Bioinformatics 2012; 28(18): i487-94. doi: 10.1093/bioinformatics/bts412 PMID: 22962471Smith TF, Waterman MS. Identification of common molecular subsequences. J Mol Biol 1981; 147(1): 195-7. doi: 10.1016/0022-2836(81)90087-5 PMID: 7265238Yang M, Wu G, Zhao Q, Li Y, Wang J. Computational drug repositioning based on multi-similarities bilinear matrix factorization. Brief Bioinform 2021; 22(4): bbaa267. doi: 10.1093/bib/bbaa267 PMID: 33147616Ding Y, Tang J, Guo F. Identification of drug–target interactions via fuzzy bipartite local model. Neural Comput Appl 2020; 32(14): 10303-19. doi: 10.1007/s00521-019-04569-zJamali AA, Kusalik A, Wu F. NMTF-DTI: A nonnegative matrix tri-factorization approach with multiple kernel fusion for drug-target interaction prediction. IEEE/ACM Trans Comput Biol Bioinformatics 2021; 1. doi: 10.1109/TCBB.2021.3135978Jia C, Akhonda MABS, Levin-Schwartz Y, Long Q, Calhoun VD, Adali T. Consecutive independence and correlation transform for multimodal data fusion: discovery of one-to-many associations in structural and functional imaging data. Appl Sci (Basel) 2021; 11(18): 8382. doi: 10.3390/app11188382Jung YS, Kim Y, Cho YR. Comparative analysis of network-based approaches and machine learning algorithms for predicting drug-target interactions. Methods 2022; 198: 19-31. doi: 10.1016/j.ymeth.2021.10.007 PMID: 34737033Olayan RS, Ashoor H, Bajic VB. DDR: efficient computational method to predict drug–target interactions using graph mining and machine learning approaches. Bioinformatics 2018; 34(7): 1164-73. doi: 10.1093/bioinformatics/btx731 PMID: 29186331Yu D, Liu G, Zhao N, Liu X, Guo M. FPSC-DTI: Drug–target interaction prediction based on feature projection fuzzy classification and super cluster fusion. Mol Omics 2020; 16(6): 583-91. doi: 10.1039/D0MO00062K PMID: 33084702Liu Y, Wu M, Miao C, Zhao P, Li XL. Neighborhood regularized logistic matrix factorization for drug-target interaction prediction. PLOS Comput Biol 2016; 12(2): e1004760. doi: 10.1371/journal.pcbi.1004760 PMID: 26872142Zheng X, Ding H, Mamitsuka H, et al. Collaborative matrix factorization with multiple similarities for predicting drug-target interactions. Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining. 1025-33.Mei JP, Kwoh CK, Yang P, Li XL, Zheng J. Drug–target interaction prediction by learning from local information and neighbors. Bioinformatics 2013; 29(2): 238-45. doi: 10.1093/bioinformatics/bts670 PMID: 23162055Xia Z, Wu LY, Zhou X, et al. Semi-supervised drug-protein interaction prediction from heterogeneous biological spacesC//BMC systems biology. BioMed Central 2010; 4(2): 1-16.van Laarhoven T, Marchiori E. Predicting drug-target interactions for new drug compounds using a weighted nearest neighbor profile. PLoS One 2013; 8(6): e66952. doi: 10.1371/journal.pone.0066952 PMID: 23840562Law V, Knox C, Djoumbou Y, et al. DrugBank 4.0: Shedding new light on drug metabolism. Nucleic Acids Res 2014; 42(D1): D1091-7. doi: 10.1093/nar/gkt1068 PMID: 24203711Kanehisa M, Goto S, Hattori M, et al. From genomics to chemical genomics: New developments in KEGG. Nucleic Acids Res 2006; 34(90001)(1): D354-7. doi: 10.1093/nar/gkj102 PMID: 16381885Schomburg I, Chang A, Placzek S, et al. BRENDA in 2013: Integrated reactions, kinetic data, enzyme function data, improved disease classification: New options and contents in BRENDA. Nucleic Acids Res 2013; 41(Database issue): D764-72. PMID: 23203881Hecker N, Ahmed J, von Eichborn J, et al. SuperTarget goes quantitative: Update on drug-target interactions. Nucleic Acids Res 2012; 40(D1): D1113-7. doi: 10.1093/nar/gkr912 PMID: 22067455Peng L, Liao B, Zhu W, Li Z, Li K. Predicting drug–target interactions with multi-information fusion. IEEE J Biomed Health Inform 2017; 21(2): 561-72. doi: 10.1109/JBHI.2015.2513200 PMID: 26731781Gaulton A, Bellis LJ, Bento AP, et al. ChEMBL: A large-scale bioactivity database for drug discovery. Nucleic Acids Res 2012; 40(D1): D1100-7. doi: 10.1093/nar/gkr777 PMID: 21948594