FMCA-DTI: a Fragment-oriented Method Based on a Multihead Cross Attention Mechanism to Improve Drug-target Interaction Prediction

Overview

Journal Bioinformatics

Publisher Oxford University Press

Specialty Biology

Date 2024 May 29

PMID 38810106

Authors

Qi Zhang

Le Zuo

Ying Ren

Siyuan Wang

Wenfa Wang

Lerong Ma

Jing Zhang

Bisheng Xia

Affiliations

Soon will be listed here.

Abstract

Motivation: Identifying drug-target interactions (DTI) is crucial in drug discovery. Fragments are less complex and can accurately characterize local features, which is important in DTI prediction. Recently, deep learning (DL)-based methods predict DTI more efficiently. However, two challenges remain in existing DL-based methods: (i) some methods directly encode drugs and proteins into integers, ignoring the substructure representation; (ii) some methods learn the features of the drugs and proteins separately instead of considering their interactions.

Results: In this article, we propose a fragment-oriented method based on a multihead cross attention mechanism for predicting DTI, named FMCA-DTI. FMCA-DTI obtains multiple types of fragments of drugs and proteins by branch chain mining and category fragment mining. Importantly, FMCA-DTI utilizes the shared-weight-based multihead cross attention mechanism to learn the complex interaction features between different fragments. Experiments on three benchmark datasets show that FMCA-DTI achieves significantly improved performance by comparing it with four state-of-the-art baselines.

Availability And Implementation: The code for this workflow is available at: https://github.com/jacky102022/FMCA-DTI.

References

Ozturk H, Ozgur A, Ozkirimli E . DeepDTA: deep drug-target binding affinity prediction. Bioinformatics. 2018; 34(17):i821-i829. PMC: 6129291. DOI: 10.1093/bioinformatics/bty593. View

Faulon J, Misra M, Martin S, Sale K, Sapra R . Genome scale enzyme-metabolite and drug-target interaction predictions using the signature molecular descriptor. Bioinformatics. 2007; 24(2):225-33. DOI: 10.1093/bioinformatics/btm580. View

Keiser M, Roth B, Armbruster B, Ernsberger P, Irwin J, Shoichet B . Relating protein pharmacology by ligand chemistry. Nat Biotechnol. 2007; 25(2):197-206. DOI: 10.1038/nbt1284. View

Liu H, Sun J, Guan J, Zheng J, Zhou S . Improving compound-protein interaction prediction by building up highly credible negative samples. Bioinformatics. 2015; 31(12):i221-9. PMC: 4765858. DOI: 10.1093/bioinformatics/btv256. View

Morris G, Huey R, Lindstrom W, Sanner M, Belew R, Goodsell D . AutoDock4 and AutoDockTools4: Automated docking with selective receptor flexibility. J Comput Chem. 2009; 30(16):2785-91. PMC: 2760638. DOI: 10.1002/jcc.21256. View

Arus-Pous J, Patronov A, Bjerrum E, Tyrchan C, Reymond J, Chen H . SMILES-based deep generative scaffold decorator for de-novo drug design. J Cheminform. 2021; 12(1):38. PMC: 7260788. DOI: 10.1186/s13321-020-00441-8. View

Hopkins A . Drug discovery: Predicting promiscuity. Nature. 2009; 462(7270):167-8. DOI: 10.1038/462167a. View

Yao L, Evans J, Rzhetsky A . Novel opportunities for computational biology and sociology in drug discovery. Trends Biotechnol. 2010; 28(4):161-70. PMC: 3654551. DOI: 10.1016/j.tibtech.2010.01.004. View

Laufkotter O, Sturm N, Bajorath J, Chen H, Engkvist O . Combining structural and bioactivity-based fingerprints improves prediction performance and scaffold hopping capability. J Cheminform. 2019; 11(1):54. PMC: 6686534. DOI: 10.1186/s13321-019-0376-1. View

10.

Cheng F, Liu C, Jiang J, Lu W, Li W, Liu G . Prediction of drug-target interactions and drug repositioning via network-based inference. PLoS Comput Biol. 2012; 8(5):e1002503. PMC: 3349722. DOI: 10.1371/journal.pcbi.1002503. View

11.

Probst D, Reymond J . A probabilistic molecular fingerprint for big data settings. J Cheminform. 2018; 10(1):66. PMC: 6755601. DOI: 10.1186/s13321-018-0321-8. View

12.

Dou L, Zhang Z, Liu D, Qian Y, Zhang Q . BCM-DTI: A fragment-oriented method for drug-target interaction prediction using deep learning. Comput Biol Chem. 2023; 104:107844. DOI: 10.1016/j.compbiolchem.2023.107844. View

13.

Chen X, Yan C, Zhang X, Zhang X, Dai F, Yin J . Drug-target interaction prediction: databases, web servers and computational models. Brief Bioinform. 2015; 17(4):696-712. DOI: 10.1093/bib/bbv066. View

14.

Mahmud S, Chen W, Liu Y, Awal M, Ahmed K, Rahman M . PreDTIs: prediction of drug-target interactions based on multiple feature information using gradient boosting framework with data balancing and feature selection techniques. Brief Bioinform. 2021; 22(5). PMC: 7989622. DOI: 10.1093/bib/bbab046. View

15.

Ezzat A, Wu M, Li X, Kwoh C . Drug-target interaction prediction via class imbalance-aware ensemble learning. BMC Bioinformatics. 2017; 17(Suppl 19):509. PMC: 5259867. DOI: 10.1186/s12859-016-1377-y. View

16.

He Z, Zhang J, Shi X, Hu L, Kong X, Cai Y . Predicting drug-target interaction networks based on functional groups and biological features. PLoS One. 2010; 5(3):e9603. PMC: 2836373. DOI: 10.1371/journal.pone.0009603. View

17.

Chen W, Chen G, Zhao L, Chen C . Predicting Drug-Target Interactions with Deep-Embedding Learning of Graphs and Sequences. J Phys Chem A. 2021; 125(25):5633-5642. DOI: 10.1021/acs.jpca.1c02419. View

18.

Zhang W, Lin W, Zhang D, Wang S, Shi J, Niu Y . Recent Advances in the Machine Learning-Based Drug-Target Interaction Prediction. Curr Drug Metab. 2018; 20(3):194-202. DOI: 10.2174/1389200219666180821094047. View

19.

Lee I, Keum J, Nam H . DeepConv-DTI: Prediction of drug-target interactions via deep learning with convolution on protein sequences. PLoS Comput Biol. 2019; 15(6):e1007129. PMC: 6594651. DOI: 10.1371/journal.pcbi.1007129. View

20.

A Thafar M, Olayan R, Ashoor H, Albaradei S, Bajic V, Gao X . DTiGEMS+: drug-target interaction prediction using graph embedding, graph mining, and similarity-based techniques. J Cheminform. 2021; 12(1):44. PMC: 7325230. DOI: 10.1186/s13321-020-00447-2. View