Research progress of feature-based deep learning for predicting compound-protein interaction

RONG Danqi; WANG Qian; TANG Li; SI Wanyu; ZHAO Hongping

doi:10.11665/j.issn.1000-5048.2023040304

Journal of China Pharmaceutical University > 2023 > 54(3): 305-313. > DOI: 10.11665/j.issn.1000-5048.2023040304

RONG Danqi, WANG Qian, TANG Li, SI Wanyu, ZHAO Hongping. Research progress of feature-based deep learning for predicting compound-protein interaction[J]. Journal of China Pharmaceutical University, 2023, 54(3): 305-313. DOI: 10.11665/j.issn.1000-5048.2023040304

Citation:

PDF (974 KB)

Research progress of feature-based deep learning for predicting compound-protein interaction

Institute of Medical Big Data and Artificial Intelligence, School of Science, China Pharmaceutical University, Nanjing 211198, China

Funds: This study was supported by the National Natural Science Foundation of China (No.81973512); and the Key Project of Philosophy and Social Science Research in Colleges and Universities in Jiangsu Province (No.2023SJZD130)

More Information

Received Date: April 02, 2023
Revised Date: June 18, 2023

Graphical Abstract

Abstract

Abstract

The prediction of compound-protein interaction (CPI) is a critical technological tool for discovering lead compounds and drug repurposing during the process of drug development.In recent years, deep learning has been widely used in CPI research, which has accelerated the development of CPI prediction in drug discovery.This review focuses on feature-based CPI prediction models.First, we described the datasets, as well as typical feature representation methods commonly used for compounds and proteins in CPI prediction.Based on the critical problems in modeling, we discussed models for CPI prediction from two perspectives: multimodal features and attention mechanisms.Then, the performance of 12 selected models was evaluated on 3 benchmark datasets for both classification and regression tasks.Finally, the review summarizes the existing challenges in this field and prospects for future directions.We believe that this investigation will provide some reference and insight for further research on CPI prediction.
- deep learning,
- compound-protein interaction,
- drug repurposing,
- lead compound screening

FullText(HTML)

References (47)

References

[1]	Fu MY, Zhu YY, Wu CY, et al. Prediction of plasma protein binding rate based on machine learning[J]. J China Pharm Univ (中国药科大学学报), 2021, 52(6): 699-706.
[2]	Zhong FS. Studies on drug-target interactions based on graph neural network(基于图神经网络的药物—靶标作用研究)[D]. Shanghai: Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 2022.
[3]	Kim S, Chen J, Cheng TJ, et al. PubChem in 2021: new data content and improved web interfaces[J]. Nucleic Acids Res, 2021, 49(D1): D1388-D1395.
[4]	Bento AP, Gaulton A, Hersey A, et al. The ChEMBL bioactivity database: an update[J]. Nucleic Acids Res, 2014, 42(Database issue): D1083-D1090.
[5]	Szklarczyk D, Santos A, von Mering C, et al. STITCH 5: augmenting protein-chemical interaction networks with tissue and affinity data[J]. Nucleic Acids Res, 2016, 44(D1): D380-D384.
[6]	Liu TQ, Lin Y, Wen X, et al. BindingDB: a web-accessible database of experimentally determined protein-ligand binding affinities[J]. Nucleic Acids Res, 2007, 35(Database issue): D198-D201.
[7]	Su MY, Yang QF, Du Y, et al. Comparative assessment of scoring functions: the CASF-2016 update[J]. J Chem Inf Model, 2019, 59(2): 895-913.
[8]	Mysinger MM, Carchia M, Irwin JJ, et al. Directory of useful decoys, enhanced (DUD-E): better ligands and decoys for better benchmarking[J]. J Med Chem, 2012, 55(14): 6582-6594.
[9]	Wishart DS, Feunang YD, Guo AC, et al. DrugBank 5.0: a major update to the DrugBank database for 2018[J]. Nucleic Acids Res, 2018, 46(D1): D1074-D1082.
[10]	Davis MI, Hunt JP, Herrgard S, et al. Comprehensive analysis of kinase inhibitor selectivity[J]. Nat Biotechnol, 2011, 29(11): 1046-1051.
[11]	Tang J, Szwajda A, Shakyawar S, et al. Making sense of large-scale kinase inhibitor bioactivity data sets: a comparative and integrative analysis[J]. J Chem Inf Model, 2014, 54(3): 735-743.
[12]	Du PF, Wang X, Xu C, et al. PseAAC-Builder: a cross-platform stand-alone program for generating various special Chou''s pseudo-amino acid compositions[J]. Anal Biochem, 2012, 425(2): 117-119.
[13]	Chen Z, Zhou Y, Song JN, et al. hCKSAAP_UbSite: improved prediction of human ubiquitination sites by exploiting amino acid pattern and properties[J]. Biochim Biophys Acta, 2013, 1834(8): 1461-1467.
[14]	Wan XZ, Wu XL, Wang DY, et al. An inductive graph neural network model for compound-protein interaction prediction based on a homogeneous graph[J]. Brief Bioinform, 2022, 23(3): bbac073.
[15]	Chen Y, Wu H, Ge WH, et al. Research on entity relation extraction of Chinese adverse drug reaction reports based on deep learning method[J]. J China Pharm Univ (中国药科大学学报), 2019, 50(6): 753-759.
[16]	?ztürk H, ?zgür A, OzkirimLi E. DeepDTA: deep drug-target binding affinity prediction[J]. Bioinformatics, 2018, 34(17): i821-i829.
[17]	?ztürk H, OzkirimLi E, ?zgür A. WideDTA: prediction of drug-target binding affinity[J].arXiv,2019:1902.04166v1.
[18]	Yang JB, Cai YY, Zhao KR, et al. Concepts and applications of chemical fingerprint for hit and lead screening[J]. Drug Discov Today, 2022, 27(11): 103356.
[19]	Lee I, Keum J, Nam H. DeepConv-DTI: prediction of drug-target interactions via deep learning with convolution on protein sequences[J]. PLoS Comput Biol, 2019, 15(6): e1007129.
[20]	Rifaioglu AS, Cetin Atalay R, Cansen Kahraman D, et al. MDeePred: novel multi-channel protein featurization for deep learning-based binding affinity prediction in drug discovery[J]. Bioinformatics, 2021, 37(5): 693-704.
[21]	Wang SD, Du ZZ, Ding M, et al. LDCNN-DTI: a novel light deep convolutional neural network for drug-target interaction predictions[C]//2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). Seoul:IEEE, 2021: 1132-1136.
[22]	Wang KL, Zhou RY, Li YH, et al. DeepDTAF: a deep learning method to predict protein-ligand binding affinity[J]. Brief Bioinform, 2021, 22(5): bbab072.
[23]	Wang S, Jiang MJ, Zhang SG, et al. MCN-CPI: multiscale convolutional network for compound-protein interaction prediction[J]. Biomolecules, 2021, 11(8): 1119.
[24]	Lin X. DeepGS: Deep Representation Learning of graphs and sequences for drug-target binding affinity prediction[J]. arXiv,2020: 2003.13902v2.
[25]	Wei LS, Long WT, Wei LY. MDL-CPI: multi-view deep learning model for compound-protein interaction prediction[J]. Methods, 2022, 204: 418-427.
[26]	Nguyen T, Le H, Quinn TP, et al. GraphDTA: predicting drug-target binding affinity with graph neural networks[J]. Bioinformatics, 2021, 37(8): 1140-1147.
[27]	Chen S, Sun Z, Lin LH, et al. To improve protein sequence profile prediction through image captioning on pairwise residue distance map[J]. J Chem Inf Model, 2020, 60(1): 391-399.
[28]	Wang S, Sun SQ, Li Z, et al. Accurate de novo prediction of protein contact map by ultra-deep learning model[J]. PLoS Comput Biol, 2017, 13(1): e1005324.
[29]	Jiang MJ, Li Z, Zhang SG, et al. Drug-target affinity prediction using graph neural network and contact maps[J]. RSC Adv, 2020, 10(35): 20701-20712.
[30]	Michel M, Menéndez Hurtado D, Elofsson A. PconsC4: fast, accurate and hassle-free contact predictions[J]. Bioinformatics, 2019, 35(15): 2677-2679.
[31]	Guo BJ, Zheng HY, Jiang HH, et al. Enhanced compound-protein binding affinity prediction by representing protein multimodal information via a coevolutionary strategy[J]. Brief Bioinform, 2023, 24(2): bbac628.
[32]	Li SY, Wan FP, Shu HT, et al. MONN: a multi-objective neural network for predicting compound-protein interactions and affinities[J]. Cell Syst, 2020, 10(4): 308-322.e11.
[33]	Yang ZD, Zhong WH, Zhao L, et al. MGraphDTA: deep multiscale graph neural network for explainable drug-target binding affinity prediction[J]. Chem Sci, 2022, 13(3): 816-833.
[34]	Gao KY, Fokoue A, Luo H, et al. Interpretable drug target prediction using deep neural representation[C]//Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. California: International Joint Conferences on Artificial Intelligence Organization, 2018: 3371-3377.
[35]	Zhao Q, Xiao F, Yang M, et al. AttentionDTA: prediction of drug-target binding affinity using attention model[C]// IEEE International Conference on Bioinformatics and Biomedicine (BIBM). San Diego: IEEE, 2019: 64-69.
[36]	Chen LF, Tan XQ, Wang DY, et al. TransformerCPI: improving compound-protein interaction prediction by sequence-based deep learning with self-attention mechanism and label reversal experiments[J]. Bioinformatics, 2020, 36(16): 4406-4414.
[37]	Nguyen NQ, Jang G, Kim H, et al. Perceiver CPI: a nested cross-attention network for compound-protein interaction prediction[J]. Bioinformatics, 2023, 39(1): btac731.
[38]	Huang KX, Xiao C, Glass LM, et al. MolTrans: molecular Interaction Transformer for drug-target interaction prediction[J]. Bioinformatics, 2021, 37(6): 830-836.
[39]	Wang J, Dokholyan NV. Yuel: improving the generalizability of structure-free compound-protein interaction prediction[J]. J Chem Inf Model, 2022, 62(3): 463-471.
[40]	Bai PZ, Miljkovi? F, John B, et al. Interpretable bilinear attention network with domain adaptation improves drug-target prediction[J]. Nat Mach Intell, 2023, 5(2): 126-136.
[41]	Zhao QC, Yang MY, Cheng ZJ, et al. Biomedical data and deep learning computational models for predicting compound-protein relations[J]. IEEE/ACM Trans Comput Biol Bioinform, 2022, 19(4): 2092-2110.
[42]	Wang SD, Du ZZ, Ding M, et al. KG-DTI: a knowledge graph based deep learning method for drug-target interaction predictions and Alzheimer''s disease drug repositions[J]. Appl Intell, 2022, 52(1): 846-857.
[43]	Li YF, Sun C, Wei JM, et al. Drug-Protein interaction prediction by correcting the effect of incomplete information in heterogeneous information[J]. Bioinformatics, 2022, 38(22): 5073-5080.
[44]	Ma WJ, Zhang SG, Li Z, et al. Predicting drug-target affinity by learning protein knowledge from biological networks[J]. IEEE J Biomed Health Inform, 2023, 27(4): 2128-2137.
[45]	Wu F, Jin ST, Jiang YH, et al. Pre-training of equivariant graph matching networks with conformation flexibility for drug binding[J]. Adv Sci, 2022, 9(33): e2203796.
[46]	Wan FP, Zhu Y, Hu HL, et al. DeepCPI: a deep learning-based framework for large-scale in silico drug screening[J]. Genomics Proteomics Bioinformatics, 2019, 17(5): 478-495.
[47]	Nguyen TM, Nguyen T, Tran T. Mitigating cold-start problems in drug-target affinity prediction with interaction knowledge transferring[J]. Brief Bioinform, 2022, 23(4): bbac269.

[1]	TANG Linfang, ZHANG Ziqiang, SU Rina, HE Shuwang, YAO Jing. Advances in taste-masking technology of oral paediatric medicine[J]. Journal of China Pharmaceutical University, 2017, 48(2): 135-141. DOI: 10.11665/j.issn.1000-5048.20170202
[2]	DENG Yan-ping, XIAO Yan-yu, PING Qi-neng, GU Xiao-zhen, BAO Quan-ying. Combined system of sinomenine hydrochloride sustained-release pellets[J]. Journal of China Pharmaceutical University, 2009, 40(3): 222-226.
[3]	Preparation of Turbutaline Sulphate Pulsatile Controlled-release Pellets[J]. Journal of China Pharmaceutical University, 2004, (4): 17-20.
[4]	Studies on Famotidine Pulsatile Controlled-Release Capsules[J]. Journal of China Pharmaceutical University, 1997, (3): 25-29.
[6]	Study on the Controlled-Release System of Propranolol Hydrochloride[J]. Journal of China Pharmaceutical University, 1994, (2): 83-87.
[7]	Studies on Isosorbide- 5- Mononitrate Controlled Release Tablets[J]. Journal of China Pharmaceutical University, 1993, (6): 327-330.
[8]	Studies on Controlled Release Tablet of Piroxicam[J]. Journal of China Pharmaceutical University, 1990, (4): 201-204.
[9]	DEVELOPMENT OF CONTROLLED-RELEASE CHLORPHENIRAMINE PELLETS[J]. Journal of China Pharmaceutical University, 1985, (1): 28-37.
[10]	Li Hanyun, Li Fengwen, Liu Guojie, Chen Shuguang, Cheng Yun. PREDICTION OF SHELF-LIFE OF CONTROLLED- RELEASE OPHTHALMIC FILM OF PILOCARPINE[J]. Journal of China Pharmaceutical University, 1984, (3): 1-5.

Cited By

Cited by

Periodical cited type(2)

1.	杨婧雯，陈芊，单云龙，刘嘉莉，尉宁，王婧，王广基，周芳. 间充质干细胞产品及其外泌体在炎症性肠病治疗中的研究进展. 中国药科大学学报. 2024(01): 103-114 . 本站查看
2.	张强，罗曦，韩丽颖，王帅，包永睿，李天娇，孟宪生. 基于代谢组学研究hUC-MSCs-Exos联合复方木鸡颗粒抑制人肝癌细胞SMMC-7721增殖机制. 中华中医药杂志. 2024(10): 5481-5487 .

Other cited types(1)

Get Citation

PDF

XML

Article views (335) PDF downloads (357) Cited by(3)

Turn off MathJax

Article Contents

Abstract

References

Research progress of feature-based deep learning for predicting compound-protein interaction

Abstract

References

Related Articles

Cited by

Periodical cited type(2)

Other cited types(1)

Catalog

Research progress of feature-based deep learning for predicting compound-protein interaction

Abstract

References

Related Articles

Cited by

Periodical cited type(2)

Other cited types(1)

Catalog

Export File

Citation

Format

Content