Login Register Cart 0
Generic placeholder image

Current Bioinformatics

Editor-in-Chief

ISSN (Print): 1574-8936
ISSN (Online): 2212-392X

Back
Journal Home About Journal Editorial Board Journal Insight Current Issue Volumes/Issues
Subscribe
Research Article

Drug-target Binding Affinity Prediction Based on Three-branched Multiscale Convolutional Neural Networks

Author(s): Yaoyao Lu, Junkai Liu, Tengsheng Jiang, Zhiming Cui and Hongjie Wu*

Volume 18, Issue 10, 2023

Published on: 19 September, 2023

Page: [853 - 862] Pages: 10

DOI: 10.2174/1574893618666230816090548

Price: $65

conference banner
Abstract

Background: New drugs are costly, time-consuming, and often accompanied by safety concerns. With the development of deep learning, computer-aided drug design has become more mainstream, and convolutional neural networks and graph neural networks have been widely used for drug– target affinity (DTA) prediction.

Objective: The paper proposes a method of predicting DTA using graph convolutional networks and multiscale convolutional neural networks.

Methods: We construct drug molecules into graph representation vectors and learn feature expressions through graph attention networks and graph convolutional networks. A three-branch convolutional neural network learns the local and global features of protein sequences, and the two feature representations are merged into a regression module to predict the DTA.

Results: We present a novel model to predict DTA, with a 2.5% improvement in the consistency index and a 21% accuracy improvement in terms of the mean squared error on the Davis dataset compared to DeepDTA. Morever, our method outperformed other mainstream DTA prediction models namely, GANsDTA, WideDTA, GraphDTA and DeepAffinity.

Conclusion: The results showed that the use of multiscale convolutional neural networks was better than a single-branched convolutional neural network at capturing protein signatures and the use of graphs to express drug molecules yielded better results.

« Previous Next »
Graphical Abstract

[1]
Cao L, Coventry B, Goreshnik I, et al. Design of protein-binding proteins from the target structure alone. Nature 2022; 605(7910): 551-60.
[http://dx.doi.org/10.1038/s41586-022-04654-9] [PMID: 35332283]
[2]
Gonzalez MW, Kann MG. Chapter 4: Protein interactions and disease. PLOS Comput Biol 2012; 8(12): e1002819.
[http://dx.doi.org/10.1371/journal.pcbi.1002819] [PMID: 23300410]
[3]
Yu JL, Dai QQ, Li GB. Deep learning in target prediction and drug repositioning: Recent advances and challenges. Drug Discov Today 2021; 1359-6446.
[PMID: 34718208]
[4]
Deng L, Zeng Y, Liu H, Liu Z, Liu X. DeepMHADTA: Prediction of drug-target binding affinity using multi-head self-attention and convolutional neural network. Curr Issues Mol Biol 2022; 44(5): 2287-99.
[http://dx.doi.org/10.3390/cimb44050155] [PMID: 35678684]
[5]
Aminpour M, Montemagno C, Tuszynski JA. An overview of molecular modeling for drug discovery with specific illustrative examples of applications. Molecules 2019; 24(9): 1693.
[http://dx.doi.org/10.3390/molecules24091693] [PMID: 31052253]
[6]
Scior T, Bender A, Tresadern G, et al. Recognizing pitfalls in virtual screening: A critical review. J Chem Inf Model 2012; 52(4): 867-81.
[http://dx.doi.org/10.1021/ci200528d] [PMID: 22435959]
[7]
Damale MG, Patil RB, Ansari SA, et al. Molecular docking, pharmacophore based virtual screening and molecular dynamics studies towards the identification of potential leads for the management of H. pylori. RSC Adv 2019; 9(45): 26176-208.
[http://dx.doi.org/10.1039/C9RA03281A] [PMID: 35531003]
[8]
Loo JSE, Emtage AL, Murali L, Lee SS, Kueh ALW, Alexander SPH. Ligand discrimination during virtual screening of the CB1 cannabinoid receptor crystal structures following cross-docking and microsecond molecular dynamics simulations. RSC Adv 2019; 9(28): 15949-56.
[http://dx.doi.org/10.1039/C9RA01095E] [PMID: 35521393]
[9]
Jana S, Ganeshpurkar A, Singh SK. Multiple 3D-QSAR modeling, e-pharmacophore, molecular docking, and in vitro study to explore novel AChE inhibitors. RSC Adv 2018; 8(69): 39477-95.
[http://dx.doi.org/10.1039/C8RA08198K] [PMID: 35558010]
[10]
Stanzione F, Giangreco I, Cole JC. Use of molecular docking computational tools in drug discovery. Prog Med Chem 2021; 60: 273-343.
[http://dx.doi.org/10.1016/bs.pmch.2021.01.004] [PMID: 34147204]
[11]
Rajasekhar S, Karuppasamy R, Chanda K. Exploration of potential inhibitors for tuberculosis via structure-based drug design, molecular docking, and molecular dynamics simulation studies. J Comput Chem 2021; 42(24): 1736-49.
[http://dx.doi.org/10.1002/jcc.26712] [PMID: 34216033]
[12]
Salo-Ahen OMH, Alanko I, Bhadane R, et al. Molecular dynamics simulations in drug discovery and pharmaceutical development. Processes 2020; 9(1): 71.
[http://dx.doi.org/10.3390/pr9010071]
[13]
Singh P, Mishra M, Agarwal S, Sau S, Iyer AK, Kashaw SK. Exploring the role of water molecules in the ligand binding domain of PDE4B and PDE4D: Virtual screening based molecular docking of some active scaffolds. Curr Computeraided Drug Des 2019; 15(4): 334-66.
[http://dx.doi.org/10.2174/1573409914666181105153543] [PMID: 30394213]
[14]
Lim J, Ryu S, Park K, Choe YJ, Ham J, Kim WY. Predicting drug–target interaction using a novel graph neural network with 3D structure-embedded graph representation. J Chem Inf Model 2019; 59(9): 3981-8.
[http://dx.doi.org/10.1021/acs.jcim.9b00387] [PMID: 31443612]
[15]
Peng J, Wang Y, Guan J, et al. An end-to-end heterogeneous graph representation learning-based framework for drug–target interaction prediction. Brief Bioinform 2021; 22(5): bbaa430.
[http://dx.doi.org/10.1093/bib/bbaa430] [PMID: 33517357]
[16]
Shin B, Park S, Kang K, et al. Self-attention based molecule representation for predicting drug-target interaction. arXiv:190806760 2019.
[17]
Huang K, Xiao C, Glass LM, Sun J. MolTrans: Molecular interaction transformer for drug–target interaction prediction. Bioinformatics 2021; 37(6): 830-6.
[http://dx.doi.org/10.1093/bioinformatics/btaa880] [PMID: 33070179]
[18]
Zhao T, Hu Y, Valsdottir LR, Zang T, Peng J. Identifying drug–target interactions based on graph convolutional network and deep neural network. Brief Bioinform 2021; 22(2): 2141-50.
[http://dx.doi.org/10.1093/bib/bbaa044] [PMID: 32367110]
[19]
Zhang Q, He Y, Wang S, et al. Base-resolution prediction of transcription factor binding signals by a deep learning framework. PLoS Comput Biol 2022; 18(3): e1009941.
[http://dx.doi.org/10.1101/2021.11.01.466840]
[20]
Shen Z, Zhang Q, Han K, Huang DS. A deep learning model for RNA-protein binding preference prediction based on hierarchical LSTM and attention network. IEEE/ACM Trans Comput Biol Bioinformatics 2022; 19(2): 753-62.
[PMID: 32750884]
[21]
Yuan L, Huang DS. A network-guided association mapping approach from DNA methylation to disease. Sci Rep 2019; 9(1): 5601.
[http://dx.doi.org/10.1038/s41598-019-42010-6] [PMID: 30944378]
[22]
He Y, Shen Z, Zhang Q, Wang S, Huang DS. A survey on deep learning in DNA/RNA motif mining. Brief Bioinform 2021; 22(4): bbaa229.
[http://dx.doi.org/10.1093/bib/bbaa229] [PMID: 33005921]
[23]
Wang L, You ZH, Huang YA, Huang DS, Chan KCC. An efficient approach based on multi-sources information to predict circRNA – disease associations using deep convolutional neural network. Bioinformatics 2020; 36(13): 4038-46.
[http://dx.doi.org/10.1093/bioinformatics/btz825] [PMID: 31793982]
[24]
Wang L, You ZH, Huang DS, Zhou F. Combining high speed ELM learning with a deep convolutional neural network feature encoding for predicting protein-RNA interactions. IEEE/ACM Trans Comput Biol Bioinformatics 2020; 17(3): 972-80.
[http://dx.doi.org/10.1109/TCBB.2018.2874267] [PMID: 30296240]
[25]
Abbasi K, Razzaghi P, Poso A, Ghanbari-Ara S, Masoudi-Nejad A. Deep learning in drug target interaction prediction: current and future perspectives. Curr Med Chem 2021; 28(11): 2100-13.
[http://dx.doi.org/10.2174/1875533XMTA5qNzU62] [PMID: 32895036]
[26]
Cherkasov A, Muratov EN, Fourches D, et al. QSAR modeling: Where have you been? Where are you going to? J Med Chem 2014; 57(12): 4977-5010.
[http://dx.doi.org/10.1021/jm4004285] [PMID: 24351051]
[27]
Zhang S, Golbraikh A, Tropsha A. Development of quantitative structure-binding affinity relationship models based on novel geometrical chemical descriptors of the protein-ligand interfaces. J Med Chem 2006; 49(9): 2713-24.
[http://dx.doi.org/10.1021/jm050260x] [PMID: 16640331]
[28]
Politi R, Rusyn I, Tropsha A. Prediction of binding affinity and efficacy of thyroid hormone receptor ligands using QSAR and structure-based modeling methods. Toxicol Appl Pharmacol 2014; 280(1): 177-89.
[http://dx.doi.org/10.1016/j.taap.2014.07.009] [PMID: 25058446]
[29]
Wang S, Jiang M, Zhang S, et al. Mcn-cpi: Multiscale convolutional network for compound–protein interaction prediction. Biomolecules 2021; 11(8): 1119.
[http://dx.doi.org/10.3390/biom11081119] [PMID: 34439785]
[30]
Öztürk H, Özgür A, Ozkirimli E. DeepDTA: Deep drug–target binding affinity prediction. Bioinformatics 2018; 34(17): i821-9.
[http://dx.doi.org/10.1093/bioinformatics/bty593] [PMID: 30423097]
[31]
Zhao L, Wang J, Pang L, Liu Y, Zhang J. GANsDTA: Predicting drug-target binding affinity using GANs. Front Genet 2020; 10: 1243.
[http://dx.doi.org/10.3389/fgene.2019.01243] [PMID: 31993067]
[32]
Öztürk H, Ozkirimli E, Özgür A. WideDTA: prediction of drug-target binding affinity. arXiv:190204166 2019.
[33]
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): 3329-38.
[http://dx.doi.org/10.1093/bioinformatics/btz111] [PMID: 30768156]
[34]
Mayr A, Klambauer G, Unterthiner T, et al. Large-scale comparison of machine learning methods for drug target prediction on ChEMBL. Chem Sci 2018; 9(24): 5441-51.
[http://dx.doi.org/10.1039/C8SC00148K] [PMID: 30155234]
[35]
Yi HC, You ZH, Huang DS, Li X, Jiang TH, Li LP. A deep learning framework for robust and accurate prediction of ncRNA-protein interactions using evolutionary information. Mol Ther Nucleic Acids 2018; 11: 337-44.
[http://dx.doi.org/10.1016/j.omtn.2018.03.001] [PMID: 29858068]
[36]
Chuai G, Ma H, Yan J, et al. DeepCRISPR: optimized CRISPR guide RNA design by deep learning. Genome Biol 2018; 19(1): 80.
[http://dx.doi.org/10.1186/s13059-018-1459-4] [PMID: 29945655]
[37]
Shen Z, Zhang YH, Han K, et al. miRNA-disease association prediction with collaborative matrix factorization. Biomolecular Networks for Complex Diseases 2017; 2017.
[38]
Feng Q, Dueva E, Cherkasov A, et al. Padme: A deep learning-based framework for drug-target interaction prediction. ar-Xiv:180709741 2018.
[39]
Nguyen T, Le H, Quinn TP, Nguyen T, Le TD, Venkatesh S. GraphDTA: Predicting drug–target binding affinity with graph neural networks. Bioinformatics 2021; 37(8): 1140-7.
[http://dx.doi.org/10.1093/bioinformatics/btaa921] [PMID: 33119053]
[40]
Yang Z, Zhong W, Zhao L, Yu-Chian CC. MGraphDTA: deep multiscale graph neural network for explainable drug–target binding affinity prediction. Chem Sci 2022; 13(3): 816-33.
[http://dx.doi.org/10.1039/D1SC05180F] [PMID: 35173947]
[41]
Bento AP, Hersey A, Félix E, et al. An open source chemical structure curation pipeline using RDKit. J Cheminform 2020; 12(1): 51.
[http://dx.doi.org/10.1186/s13321-020-00456-1] [PMID: 33431044]
[42]
Davis MI, Hunt JP, Herrgard S, et al. Comprehensive analysis of kinase inhibitor selectivity. Nat Biotechnol 2011; 29(11): 1046-51.
[http://dx.doi.org/10.1038/nbt.1990] [PMID: 22037378]
[43]
Tang J, Szwajda A, Shakyawar S, et al. Making sense of large-scale kinase inhibitor bioactivity data sets: a comparative and integrative analysis. J Chem Inf Model 2014; 54(3): 735-43.
[http://dx.doi.org/10.1021/ci400709d] [PMID: 24521231]
[44]
Barbet J, Huclier-Markai S. Equilibrium, affinity, dissociation constants, IC5O: Facts and fantasies. Pharm Stat 2019; 18(5): 513-25.
[http://dx.doi.org/10.1002/pst.1943] [PMID: 30977282]
[45]
Ma F, Liu W, Liang L, Tang B, Zhang CY. Sensitive detection of alkaline phosphatase by dephosphorylation-initiated transcription reaction-mediated dual signal amplification. Chem Commun 2018; 54(19): 2413-6.
[http://dx.doi.org/10.1039/C8CC00540K] [PMID: 29457170]
[46]
Cer R Z, Mudunuri U, Stephens R, et al. IC50-to-Ki: A web-based tool for converting IC50 to Ki values for inhibitors of enzyme activity and ligand binding. Nucleic Acids Res 2009; 37(Web Server issue): W441-5.
[47]
Gönen M, Heller G. Concordance probability and discriminatory power in proportional hazards regression. Biometrika 2005; 92(4): 965-70.
[http://dx.doi.org/10.1093/biomet/92.4.965]
[48]
Varma R. Picking Loss Functions - A comparison between MSE, Cross Entropy, and Hinge Loss 2018. Available from:https://rohanvarma.me/Loss-Functions/

Rights & Permissions Print Cite
© 2024 Bentham Science Publishers | Privacy Policy