药物分子与靶标蛋白结合亲和力预测研究进展

doi:10.3778/j.issn.1002-8331.2405-0340

摘要/Abstract

摘要： 研究药物分子与靶标蛋白结合亲和力有助于了解生物系统和辅助药物开发。随着生物大数据驱动下的计算生物学技术发展，药物分子与靶标蛋白结合亲和力研究策略从传统单一生物医学实验迈向综合计算技术辅助预测，为药物开发提供新技术新方法。鉴于药物分子与靶标蛋白结合亲和力研究的重要性，从传统生物实验方法和计算生物学方法两个维度对其研究进展进行综述，重点介绍了预测药物分子与靶标蛋白结合亲和力的分子计算模拟、传统机器学习和深度学习方法，并阐述了每种计算生物学方法的应用场景、特点、优势和不足。最后，讨论了药物分子与靶标蛋白结合亲和力预测算法存在的问题以及未来方向，旨在为开发高性能药物分子与靶标蛋白结合亲和力预测模型提供参考。

关键词: 结合亲和力, 药物分子, 靶标蛋白, 传统机器学习, 深度学习

Abstract: Predicting the binding affinity between drug molecules and target proteins contributes to understanding biological systems and aiding drug discovery. With the development of computational biology technology driven by biological big data, the research strategy of the binding affinity between drug molecules and target proteins moves from traditional single biomedical experiments into integrated computational technology-aided prediction, which provides new technologies and methods for drug discovery. Since it is important to investigate the binding affinity between drug molecules and target proteins, this paper reviews the advances of it from two aspects, including traditional biological experimental methods and computational biology methods. For predicting the binding affinity between drug molecules and target proteins, it focuses on introducing three types of methods, i.e. molecular computational simulation, traditional machine learning and deep learning. Moreover, the paper also elaborates the application scenarios, characteristics, pros and cons of each computational biology method. Finally, it discusses the problems and future directions of each prediction method in predicting the binding affinity between drug molecules and target proteins. Taken together, this review aims to provide a reference for developing an efficient model to infer the binding affinity between drug molecules and target proteins.

Key words: binding affinity, drug molecule, target protein, traditional machine learning, deep learning

刘正美, 魏雪梅, 张俊鹏, 覃泊渊, 蒋玉, 张琦, 杨皓琳, 高健. 药物分子与靶标蛋白结合亲和力预测研究进展[J]. 计算机工程与应用, 2024, 60(23): 79-90.

LIU Zhengmei, WEI Xuemei, ZHANG Junpeng, QIN Boyuan, JIANG Yu, ZHANG Qi, YANG Haolin, GAO Jian. Research Progress in Predicting Binding Affinity between Drug Molecules and Target Proteins[J]. Computer Engineering and Applications, 2024, 60(23): 79-90.

参考文献

[1] JONES D S, SILVERMAN A P, COCHRAN J R. Developing therapeutic proteins by engineering ligand-receptor interactions[J]. Trends in Biotechnology, 2008, 26(9): 498-505.
[2] ARMINGOL E, OFFICER A, HARISMENDY O, et al. Deciphering cell-cell interactions and communication from gene expression[J]. Nature Reviews Genetics, 2020, 22(2): 71-88.
[3] HUGHES J P, REES S, KALINDJIAN S B, et al. Principles of early drug discovery[J]. British Journal of Pharmacology, 2011, 162(6): 1239-1249.
[4] CLARK L J, BU G, NANNENGA B L, et al. MicroED for the study of protein-ligand interactions and the potential for drug discovery[J].Nature Reviews Chemistry, 2021, 5(12): 853-858.
[5] BAGHERIAN M, SABETI E, WANG K, et al. Machine learning approaches and databases for prediction of drug-target interaction:a survey paper[J].Briefings in Bioinformatics, 2021, 22(1): 247-269.
[6] THAFAR M A, OLAYAN R S, ASHOOR H, et al. DTiGEMS+:drug-target interaction prediction using graph embedding, graph mining, and similarity-based techniques[J]. Journal of Cheminformatics, 2020, 12(1): 1-17.
[7] STOKES J M, YANG K, SWANSON K, et al. A deep learning approach to antibiotic discovery[J]. Cell, 2020, 180(4): 688-702.
[8] PANTSAR T, POSO A. Binding affinity via docking: fact and fiction[J]. Molecules, 2018, 23(8): 1899.
[9] 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[J]. Nucleic Acids Research, 2009, 37: 441-445.
[10] GROMIHA M M, YUGANDHAR K, JEMIMAH S. Protein-protein interactions: scoring schemes and binding affinity[J]. Current Opinion in Structural Biology, 2017, 44: 31-38.
[11] GAPSYS V, PéREZ-BENITO L, ALDEGHI M, et al. Large scale relative protein ligand binding affinities using non-equilibrium alchemy[J]. Chemical Science, 2020, 11(4): 1140-1152.
[12] SVERGUN D I, PETOUKHOV M V, KOCH M H J. Determination of domain structure of proteins from X-ray solution scattering[J]. Biophysical Journal, 2001, 80(6): 2946-2953.
[13] PE?A A, SWEENEY A, COOK A D, et al. Structure of microtubule-trapped human kinesin-5 and its mechanism of inhibition revealed using cryoelectron microscopy[J]. Structure, 2020, 28(4): 450-457.
[14] MARKOWETZ F. All biology is computational biology[J]. PLoS Biology, 2017, 15(3): 2002050.
[15] SEYFINEJAD B, OZKAN S A, JOUYBAN A. Recent advances in the determination of unbound concentration and plasma protein binding of drugs: analytical methods[J]. Talanta, 2021, 225: 122052.
[16] SRIVASTAVA N, MISHRA B N, SRIVASTAVA P. In-silico identification of drug lead molecule against pesticide exposed-neurodevelopmental disorders through network-based computational model approach[J]. Current Bioinformatics, 2019, 14(5): 460-467.
[17] HINGORANI A D, KUAN V, FINAN C, et al. Improving the odds of drug development success through human genomics: modelling study[J]. Scientific Reports, 2019, 9(1): 18911.
[18] CALDWELL G W, YAN Z Y.Isothermal titration calorimetry characterization of drug-binding energetics to blood proteins[J]. Optimization in Drug Discovery: in Vitro Methods, 2004: 123-149.
[19] ERIKSSON M A L, GABRIELSSON J, NILSSON L B. Studies of drug binding to plasma proteins using a variant of equilibrium dialysis[J]. Journal of Pharmaceutical and Biomedical Analysis, 2005, 38(3): 381-389.
[20] FABINI E, DANIELSON U H. Monitoring drug-serum protein interactions for early ADME prediction through surface plasmon resonance technology[J]. Journal of Pharmaceutical and Biomedical Analysis, 2017, 144: 188-194.
[21] SHARMEEN S, KYEI I, HATCH A, et al. Analysis of drug interactions with serum proteins and related binding agents by affinity capillary electrophoresis: a review[J]. Electrophoresis, 2022, 43(23/24): 2302-2323.
[22] DUNCAN T M, SHAH N B. Bio-layer interferometry for measuring kinetics of protein-protein interactions and allosteric ligand effects[J]. Journal of Visualized Experiments, 2014, 84: 51383.
[23] COBANOGLU M C, LIU C, HU F, et al. Predicting drug-target interactions using probabilistic matrix factorization[J]. Journal of Chemical Information and Modeling, 2013, 53(12): 3399-3409.
[24] YAMANISHI Y, ARAKI M, GUTTERIDGE A, et al. Prediction of drug-target interaction networks from the integration of chemical and genomic spaces[J]. Bioinformatics, 2008, 24(13): 232-240.
[25] SLUSKY J, LIU X, FENG H, et al. Dowker complex based machine learning (DCML) models for protein-ligand binding affinity prediction[J]. PLoS Computational Biology, 2022, 18(4): 1009943.
[26] SAVOJARDO C, BRUCIAFERRI N, TARTARI G, et al. DeepMito: accurate prediction of protein sub-mitochondrial localization using convolutional neural networks[J]. Bioinformatics, 2020, 36(1): 56-64.
[27] TANG J, SZWAJDA A, SHAKYAWAR S, et al. Making sense of large-scale kinase inhibitor bioactivity data sets: a comparative and integrative analysis[J]. Journal of Chemical Information and Modeling, 2014, 54(3): 735-743.
[28] DAVIS M I, HUNT J P, HERRGARD S, et al. Comprehensive analysis of kinase inhibitor selectivity[J]. Nature Biotechnology, 2011, 29(11): 1046-1051.
[29] LIU Z, SU M, HAN L, et al. Forging the basis for developing protein-ligand interaction scoring functions[J]. Accounts of Chemical Research, 2017, 50(2): 302-309.
[30] XU L, RU X, SONG R. Application of machine learning for drug-target interaction prediction[J]. Frontiers in Genetics, 2021, 12: 680117.
[31] MAHMUD S M H, CHEN W, MENG H, et al. Prediction of drug-target interaction based on protein features using undersampling and feature selection techniques with boosting[J]. Analytical Biochemistry, 2020, 589: 113507.
[32] LAARHOVEN V T, NABUURS S B, MARCHIORI E. Gaussian interaction profile kernels for predicting drug-target interaction[J]. Bioinformatics, 2011, 27(21): 3036-3043.
[33] WANG D D, OU-YANG L, XIE H, et al. Predicting the impacts of mutations on protein-ligand binding affinity based on molecular dynamics simulations and machine learning methods[J]. Computational and Structural Biotechnology Journal, 2020, 18: 439-454.
[34] WANG L, DENG Y, WU Y, et al. Accurate modeling of scaffold hopping transformations in drug discovery[J]. Journal of Chemical Theory and Computation, 2016, 13(1): 42-54.
[35] WANG D D, ZHU M, YAN H. Computationally predicting binding affinity in protein-ligand complexes: free energy-based simulations and machine learning-based scoring functions[J]. Briefings in Bioinformatics, 2021, 22(3): 107.
[36] BEIERLEIN F R, MICHEL J, ESSEX J W. A simple QM/MM approach for capturing polarization effects in protein-ligand binding free energy calculations[J]. The Journal of Physical Chemistry B, 2011, 115(17): 4911-4926.
[37] HUANG K, LUO S, CONG Y, et al. An accurate free energy estimator: based on MM/PBSA combined with interaction entropy for protein-ligand binding affinity[J]. Nanoscale, 2020, 12(19): 10737-10750.
[38] PERRYMAN A L, LIN J H, MCCAMMON J A. HIV-1 protease molecular dynamics of a wild‐type and of the V82F/I84V mutant: possible contributions to drug resistance and a potential new target site for drugs[J]. Protein Science, 2004, 13(4): 1108-1123.
[39] SHAN Y, KIM E T, EASTWOOD M P, et al. How does a drug molecule find its target binding site?[J]. Journal of the American Chemical Society, 2011, 133(24): 9181-9183.
[40] GUTERRES H, IM W. Improving protein-ligand docking results with high-throughput molecular dynamics simulations[J]. Journal of Chemical Information and Modeling, 2020, 60(4): 2189-2198.
[41] SONG S, CHEN X, ZHANG Y, et al. Protein-ligand docking using differential evolution with an adaptive mechanism[J]. Knowledge-Based Systems, 2021, 231: 107433.
[42] HUANG N, KALYANARAMAN C, BERNACKI K, et al. Molecular mechanics methods for predicting protein-ligand binding[J]. Physical Chemistry Chemical Physics, 2006, 8(44): 5166- 5177.
[43] HUANG S Y, ZOU X Q. An iterative knowledge-based scoring function to predict protein-ligand interactions: I. derivation of interaction potentials[J].Journal of Computational Chemistry, 2006, 27(15): 1866-1875.
[44] FRIESNER R A, BANKS J L, MURPHY R B, et al. Glide: a new approach for rapid, accurate docking and scoring. 1. method and assessment of docking accuracy[J]. Journal of Medicinal Chemistry, 2004, 47(7): 1739-1749.
[45] TAO P, LAI L H. Protein ligand docking based on empirical method for binding affinity estimation[J]. Journal of Computer-Aided Molecular Design, 2001, 15: 429-446.
[46] WU Q, PENG Z, ZHANG Y, et al. COACH-D: improved protein-ligand binding sites prediction with refined ligand-binding poses through molecular docking[J]. Nucleic Acids Research, 2018, 46(1): 438-442.
[47] VENKATACHALAM C M. LigandFit: a novel method for the shape-directed rapid docking of ligands to protein active sites[J]. Journal of Molecular Graphics and Modelling, 2003, 21: 289-307.
[48] ZHAO H, CAFLISCH A. Discovery of ZAP70 inhibitors by high-throughput docking into a conformation of its kinase domain generated by molecular dynamics[J]. Bioorganic & Medicinal Chemistry Letters, 2013, 23(20): 5721-5726.
[49] LI J, FU A, ZHANG L. An overview of scoring functions used for protein-ligand interactions in molecular docking[J]. Interdisciplinary Sciences: Computational Life Sciences, 2019, 11(2): 320-328.
[50] TROTT O, OLSON A J. AutoDock Vina: improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading[J]. Journal of Computational Chemistry, 2009, 31(2): 455-461.
[51] JAIN A N. Surflex: fully automatic flexible molecular docking using a molecular similarity-based search engine[J]. Journal of Medicinal Chemistry, 2003, 46(4): 499-511.
[52] BALLESTER P J, MITCHELL J B O. A machine learning approach to predicting protein-ligand binding affinity with applications to molecular docking[J]. Bioinformatics, 2010, 26(9): 1169-1175.
[53] YUAN Q, GAO J, WU D, et al. DrugE-Rank: improving drug-target interaction prediction of new candidate drugs or targets by ensemble learning to rank[J]. Bioinformatics, 2016, 32(12): 18-27.
[54] SHAR P A, TAO W, GAO S, et al.Pred-binding: large-scale protein-ligand binding affinity prediction[J]. Journal of Enzyme Inhibition and Medicinal Chemistry, 2016, 31(6): 1443-1450.
[55] WANG Y, GUO Y, KUANG Q, et al. A comparative study of family-specific protein-ligand complex affinity prediction based on random forest approach[J]. Journal of Computer-aided Molecular Design, 2015, 29: 349-360.
[56] KUNDU I, PAUL G, BANERJEE R. A machine learning approach towards the prediction of protein-ligand binding affinity based on fundamental molecular properties[J].RSC Advances, 2018, 8(22): 12127-12137.
[57] CHAUHAN N K, SINGH K. A review on conventional machine learning vs deep learning[C]//Proceedings of the 2018 International Conference on Computing, Power and Communication Technologies, 2018: 347-352.
[58] COLWELL L J.Statistical and machine learning approaches to predicting protein-ligand interactions[J]. Current Opinion in Structural Biology, 2018, 49: 123-128.
[59] PRZYTYCKA T M, LIU Y, WU M, et al. Neighborhood regularized logistic matrix factorization for drug-target interaction prediction[J]. PLoS Computational Biology, 2016, 12(2):1004760.
[60] OLAYAN R S, ASHOOR H, BAJIC V B. DDR: efficient computational method to predict drug-target interactions using graph mining and machine learning approaches[J]. Bioinformatics, 2018, 34(7): 1164-1173.
[61] ZANNI R, GALVEZ-LLOMPART M, GALVEZ J, et al. QSAR multi-target in drug discovery: a review[J]. Current Computer-Aided Drug Design, 2014, 10(2): 129-136.
[62] DING H, TAKIGAWA I, MAMITSUKA H, et al. Similarity-based machine learning methods for predicting drug-target interactions: a brief review[J]. Briefings in Bioinformatics, 2014, 15(5): 734-747.
[63] HE T, HEIDEMEYER M, BAN F, et al. SimBoost: a read-across approach for predicting drug-target binding affinities using gradient boosting machines[J]. Journal of Cheminformatics, 2017, 9(1): 1-14.
[64] PAHIKKALA T, AIROLA A, PIETILA S, et al. Toward more realistic drug-target interaction predictions[J]. Briefings in Bioinformatics, 2014, 16(2): 325-337.
[65] ELTON D C, BOUKOUVALAS Z, FUGE M D, et al. Deep learning for molecular design-a review of the state of the art[J]. Molecular Systems Design & Engineering, 2019, 4(4): 828-849.
[66] ASHTAWY H M, MAHAPATRA N R. BgN-Score and BsN-Score: bagging and boosting based ensemble neural networks scoring functions for accurate binding affinity prediction of protein-ligand complexes[J]. BMC Bioinformatics, 2015, 16: 1-12.
[67] JIMéNEZ J, ?KALI? M, MARTíNEZ-ROSELL G, et al. KDEEP: protein-ligand absolute binding affinity prediction via 3D-convolutional neural networks[J]. Journal of Chemical Information and Modeling, 2018, 58(2): 287-296.
[68] STEPNIEWSKA-DZIUBINSKA M M, ZIELENKIEWICZ P, SIEDLECKI P, et al. Development and evaluation of a deep learning model for protein-ligand binding affinity prediction[J]. Bioinformatics, 2018, 34(21): 3666-3674.
[69] WANG K, ZHOU R, LI Y, et al. DeepDTAF: a deep learning method to predict protein-ligand binding affinity[J]. Briefings in Bioinformatics, 2021, 22(5): 72.
[70] GU Y, ZHANG X, XU A, et al. Protein-ligand binding affinity prediction with edge awareness and supervised attention[J]. iScience, 2023, 26(1): 105892.
[71] JIN Z, WU T, CHEN T, et al. CAPLA: improved prediction of protein-ligand binding affinity by a deep learning approach based on a cross-attention mechanism[J]. Bioinformatics, 2023, 39(2): 49.
[72] NGUYEN T, LE H, QUINN T P, et al. GraphDTA: predicting drug-target binding affinity with graph neural networks[J]. Bioinformatics, 2021, 37(8): 1140-1147.
[73] NGUYEN T M, NGUYEN T, LE T M, et al. GEFA: early fusion approach in drug-target affinity prediction[J]. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2022, 19(2): 718-728.
[74] LI Q, ZHANG X, WU L, et al.PLA-MoRe: a protein-ligand binding affinity prediction model via comprehensive molecular representations[J]. Journal of Chemical Information and Modeling, 2022, 62(18): 4380-4390.
[75] LI M, LU Z, WU Y, et al. BACPI: a bi-directional attention Neural Network for compound-protein interaction and binding affinity prediction[J]. Bioinformatics, 2022, 38(7): 1995-2002.
[76] LI S, WAN F, SHU H, et al. MONN: a multi-objective neural network for predicting compound-protein interactions and affinities[J]. Cell Systems, 2020, 10(4): 308-322.
[77] YUAN W, CHEN G, CHEN C Y C. FusionDTA: attention-based feature polymerizer and knowledge distillation for drug-target binding affinity prediction[J]. Briefings in Bioinformatics, 2022, 23(1):506.
[78] ?ZTüRK H, ?ZGüR A, OZKIRIMLI E. DeepDTA: deep drug-target binding affinity prediction[J]. Bioinformatics, 2018, 34(17): 821-829.
[79] WANG J, WEN N, WANG C, et al. ELECTRA-DTA: a new compound-protein binding affinity prediction model based on the contextualized sequence encoding[J]. Journal of Cheminformatics, 2022, 14(1): 1-14.
[80] SHIM J, HONG Z Y, SOHN I, et al. Prediction of drug-target binding affinity using similarity-based convolutional neural network[J]. Scientific Reports, 2021, 11(1): 4416.
[81] ZENG Y, CHEN X, LUO Y, et al. Deep drug-target binding affinity prediction with multiple attention blocks[J]. Briefings in Bioinformatics, 2021, 22(5): 117.
[82] GHIMIRE A, TAYARA H, XUAN Z, et al. CSatDTA: prediction of drug-target binding affinity using convolution model with self-attention[J]. International Journal of Molecular Sciences, 2022, 23(15): 8453.
[83] KARIMI M, WU D, WANG Z, et al. DeepAffinity: interpretable deep learning of compound-protein affinity through unified recurrent and convolutional neural networks[J]. Bioinformatics, 2019, 35(18): 3329-3338.
[84] JONES D, KIM H, ZHANG X, et al. Improved protein-ligand binding affinity prediction with structure-based deep fusion inference[J]. Journal of Chemical Information and Modeling, 2021, 61(4): 1583-1592.
[85] SIMONOVSKY M, MEYERS J. DeeplyTough: learning structural comparison of protein binding sites[J]. Journal of Chemical Information and Modeling, 2020, 60(4): 2356-2366.
[86] TORNG W, ALTMAN R B. Graph convolutional neural networks for predicting drug-target interactions[J]. Journal of Chemical Information and Modeling, 2019, 59(10): 4131-4149.
[87] AHMED A, MAM B, SOWDHAMINI R. DEELIG: a deep learning approach to predict protein-ligand binding affinity[J]. Bioinformatics and Biology Insights, 2021, 15: 1-9.
[88] LIM J, RYU S, PARK K, et al. Predicting drug-target interaction using a novel graph neural network with 3D structure-embedded graph representation[J]. Journal of Chemical Information and Modeling, 2019, 59(9): 3981-3988.
[89] LIM S, LU Y, CHO C Y, et al.A review on compound-protein interaction prediction methods: data, format, representation and model[J]. Computational and Structural Biotechnology Journal, 2021, 19: 1541-1556.
[90] TSUBAKI M, TOMII K, SESE J J B. Compound-protein interaction prediction with end-to-end learning of Neural Networks for graphs and sequences[J]. Bioinformatics, 2019, 35(2): 309-318.
[91] SHEN H, ZHANG Y, ZHENG C, et al. A cascade graph convolutional network for predicting protein-ligand binding affinity[J]. International Journal of Molecular Sciences, 2021, 22(8): 4023.
[92] YANG Z, ZHONG W, ZHAO L, et al. MGraphDTA: deep multiscale graph neural network for explainable drugtarget binding affinity prediction[J]. Chemical Science, 2022, 13(3): 816-833.
[93] DU J, GUO J, KANG D, et al. New techniques and strategies in drug discovery[J]. Chinese Chemical Letters, 2020, 31(7): 1695-1708.
[94] KOH P W, LIANG P. Understanding black-box predictions via influence functions[C]//Proceedings of the International Conference on Machine Learning, 2017: 1885-1894.
[95] HE H H, CHEN G X, CHEN C Y C. NHGNN-DTA: a node-adaptive hybrid graph neural network for interpretable drug-target binding affinity prediction[J]. Bioinformatics, 2023, 39(6): 355.