蛋白质复合物结构预测：方法与进展

doi:10.12211/2096-8280.2022-079

摘要/Abstract

摘要：

蛋白质复合物是不同蛋白质链通过相互作用形成的，自然界中很多蛋白质通过形成复合物而执行功能，因此准确地预测复合物的结构对于理解和掌握功能至关重要。近两年来，单条蛋白质链的结构预测有了突破性的进展，从氨基酸序列出发预测蛋白质结构的水平大幅提高。但相较于单体蛋白质，蛋白质复合物结构预测的准确性仍然较低。本文旨在总结蛋白质复合物结构预测的相关算法以及介绍最新进展。首先简要介绍蛋白质结构预测领域的相关人工智能算法，主要包括共进化分析与蛋白质接触预测、深度学习方法与蛋白质结构预测、预训练模型与蛋白质表征学习几个方面；其次系统总结了蛋白质复合物链间相互作用预测的基本方法，从复合物的多重序列比对构建到对于同源或异源复合物的链间残基接触预测；最后从相互作用位点指导复合物结构预测、蛋白质分子对接算法、端到端的复合物结构预测方法等方面阐述了蛋白质复合物结构预测的基本方法和思路。总体来说，目前蛋白质复合物结构预测精度不够高，有效地解决多重序列比对的配对和多聚体复合物模板搜索等问题，或者在大量的序列或结构数据上结合预训练模型的新范式，是一个合理而有效的方案。提升蛋白质复合物结构预测水平在合成生物学领域如抗体设计、药物发现等方面有很好的应用前景。

关键词: 蛋白质复合物, 蛋白质相互作用, 蛋白质链间接触预测, 蛋白质分子对接, 结构预测

Abstract:

Protein complexes carry out a variety of biological functions, and obtaining the three-dimensional structure of protein complexes is critical for understanding their functions. In many cases, not only can two proteins interact to form a protein dimer, but also multiple proteins interact to form a protein multimer. It is difficult and time-consuming to resolve the structure of protein complexes by experiments. Recently, there have been some attempts and methods to predict the structure of multimers based on the structure prediction for the monomers. Several groups in the CASP14 competition submitted the prediction of protein complex targets, which mainly included template -based methods or protein docking. Later, on the basis of AlphaFold2, researchers developed some end-to-end structure prediction methods for complexes, which accelerates the study of protein complex structure prediction. However, compared with the prediction of monomeric protein structure, the accuracy of prediction for protein complex structure is still lower. This review surveys updated methods and advances in protein complex prediction, including inter-chain residue contact prediction, protein docking, and end-to-end protein complex structure prediction. Firstly, AI algorithms for protein structure prediction are briefly introduced, including coevolutionary analysis and protein contact prediction, deep learning method and protein structure prediction, pretraining model, and protein representation learning. Secondly, basic methods for predicting interactions between protein complexes are systematically summarized, from the construction of multiple sequence alignments of the complexes to the prediction of the inter-residue contact between chains of homologous or heterologous complexes. Finally, basic methods and ideas for protein complex structure prediction are explored from the viewpoint of interaction sites guiding complex structure prediction, protein molecular docking algorithm, end-to-end complex structure prediction methods, etc. In order to better predict the structure of protein complexes, we need to devote our effort to following aspects: 1) constructing protein complexes datasets for training and evaluation of prediction methods for the structure of multimers, 2) developing efficient algorithms to improve the prediction accuracy such as MSA paring algorithm and building templates for multi-chain protein complex, and 3) enlarging databases for protein sequences and structures for better modeling protein complex with pretraining and self-supervised learning methods. In all, predicting protein complex structure still remains a challenge, and new methods to improve accuracy will be helpful for analyzing protein functions, designing proteins and drug discovery.

Key words: protein complex, protein-protein interaction, inter-chain contact prediction, protein docking, structure prediction

中图分类号:

Q816

黄鹤, 吴桐, 王闻达, 李佳珊, 孙黛雯, 叶启威, 龚新奇. 蛋白质复合物结构预测：方法与进展[J]. 合成生物学, 2023, 4(3): 507-523.

He HUANG, Tong WU, Wenda WANG, Jiashan LI, Daiwen SUN, Qiwei YE, Xinqi GONG. Prediction of protein complex structure: methods and progress[J]. Synthetic Biology Journal, 2023, 4(3): 507-523.

图/表 3

参考文献 112

1	LENSINK M F, BRYSBAERT G, MAURI T, et al. Prediction of protein assemblies, the next frontier: the CASP14-CAPRI experiment[J]. Proteins: Structure, Function and Bioinformatics, 2021, 89(12): 1800-1823.
2	JUMPER J, EVANS R, PRITZEL A, et al. Highly accurate protein structure prediction with AlphaFold[J]. Nature, 2021, 596(7873): 583-589.
3	BADAL V D, KUNDROTAS P J, VAKSER I A. Text mining for protein docking[J]. PLoS Computational Biology, 2015, 11(12): e1004630.
4	MARKOWETZ F, SPANG R. Inferring cellular networks-a review[J]. BMC Bioinformatics, 2007, 8(): S5.
5	MORCOS F, PAGNANI A, LUNT B, et al. Direct-coupling analysis of residue coevolution captures native contacts across many protein families[J]. Proceedings of the National Academy of Sciences of the United States of America, 2011, 108(49): E1293-E1301.
6	BALAKRISHNAN S, KAMISETTY H, CARBONELL J G, et al. Learning generative models for protein fold families[J]. Proteins: Structure, Function, and Bioinformatics, 2011, 79(4): 1061-1078.
7	HUANG H, GONG X Q. A review of protein inter-residue distance prediction[J]. Current Bioinformatics, 2020, 15(8): 821-830.
8	张海仓, 高玉娟, 邓明华, 等. 蛋白质中残基远程相互作用预测算法研究综述[J]. 计算机研究与发展, 2017, 54(1): 1-19.
	ZHANG H C, GAO Y J, DENG M H, et al. A survey on algorithms for protein contact prediction[J]. Journal of Computer Research and Development, 2017, 54(1): 1-19.
9	於东军, 李阳. 蛋白质残基接触图预测[J]. 南京理工大学学报, 2019, 43(1): 1-12.
	YU D J, LI Y. Protein residue-residue contact map prediction[J]. Journal of Nanjing University of Science and Technology, 2019, 43(1): 1-12.
10	WEIGT M, WHITE R A, SZURMANT H, et al. Identification of direct residue contacts in protein-protein interaction by message passing[J]. Proceedings of the National Academy of Sciences of the United States of America, 2009, 106(1): 67-72.
11	JONES D T, BUCHAN D W A, COZZETTO D, et al. PSICOV: precise structural contact prediction using sparse inverse covariance estimation on large multiple sequence alignments[J]. Bioinformatics, 2012, 28(2): 184-190.
12	EKEBERG M, LÖVKVIST C, LAN Y H, et al. Improved contact prediction in proteins: using pseudolikelihoods to infer Potts models[J]. Physical Review E-Statistical, Nonlinear, and Soft Matter Physics, 2013, 87(1): 012707.
13	ZHANG H C, ZHANG Q, JU F S, et al. Predicting protein inter-residue contacts using composite likelihood maximization and deep learning[J]. BMC Bioinformatics, 2019, 20(1): 537.
14	KAMISETTY H, OVCHINNIKOV S, BAKER D. Assessing the utility of coevolution-based residue-residue contact predictions in a sequence- and structure-rich era[J]. Proceedings of the National Academy of Sciences of the United States of America, 2013, 110(39): 15674-15679.
15	OVCHINNIKOV S, KAMISETTY H, BAKER D. Robust and accurate prediction of residue-residue interactions across protein interfaces using evolutionary information[J]. eLife, 2014, 3: e02030.
16	WANG S, SUN S Q, LI Z, et al. Accurate de novo prediction of protein contact map by ultra-deep learning model[J]. PLoS Computational Biology, 2017, 13(1): e1005324.
17	YANG J Y, ANISHCHENKO I, PARK H, et al. Improved protein structure prediction using predicted interresidue orientations[J]. Proceedings of the National Academy of Sciences, 2020, 117(3): 1496-1503.
18	SEEMAYER S, GRUBER M, SÖDING J. CCMpred—fast and precise prediction of protein residue-residue contacts from correlated mutations[J]. Bioinformatics, 2014, 30(21): 3128-3130.
19	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C/OL]// 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), VegasLas, NV, USA, 2016, 770-778 [2022-12-10]. .
20	SENIOR A W, EVANS R, JUMPER J, et al. Improved protein structure prediction using potentials from deep learning[J]. Nature, 2020, 577(7792): 706-710.
21	MAO W, DING W, GONG H. AmoebaContact and GDFold: a new pipeline for rapid prediction of protein structures[EB/OL]. arXiv, 2019: 1905.11640[2022-12-10]. .
22	JU F S, ZHU J W, SHAO B, et al. CopulaNet: learning residue co-evolution directly from multiple sequence alignment for protein structure prediction[J]. Nature Communications, 2021, 12: 2535.
23	ZHENG W, ZHANG C, LI Y, et al. Folding non-homologous proteins by coupling deep-learning contact maps with I-TASSER assembly simulations[J]. Cell Reports Methods, 2021, 1(3): 100014.
24	MORTUZA S M, ZHENG W, ZHANG C X, et al. Improving fragment-based ab initio protein structure assembly using low-accuracy contact-map predictions[J]. Nature Communications, 2021, 12: 5011.
25	DING W Z, GONG H P. Predicting the real-valued inter-residue distances for proteins[J]. Advanced Science, 2020, 7(19): 2001314.
26	WU T Q, GUO Z Y, HOU J, et al. DeepDist: real-value inter-residue distance prediction with deep residual convolutional network[J]. BMC Bioinformatics, 2021, 22(1): 30.
27	CHAUDHURY S, LYSKOV S, GRAY J J. PyRosetta: a script-based interface for implementing molecular modeling algorithms using Rosetta[J]. Bioinformatics, 2010, 26(5): 689-691.
28	BRUNGER A T. Version 1.2 of the crystallography and NMR system[J]. Nature Protocols, 2007, 2(11): 2728-2733.
29	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[EB/OL]. arXiv, 2017: 1706.03762[2022-12-10]. .
30	ALQURAISHI M. End-to-end differentiable learning of protein structure[J]. Cell Systems, 2019, 8(4): 292-301.e3.
31	VARADI M, ANYANGO S, DESHPANDE M, et al. AlphaFold Protein Structure Database: massively expanding the structural coverage of protein-sequence space with high-accuracy models[J]. Nucleic Acids Research, 2022, 50(D1): D439-D444.
32	LIN Z, AKIN H, RAO R, et al. Evolutionary-scale prediction of atomic-level protein structure with a language model[J]. Science, 2023, 379(6637): 1123-1130.
33	DEVLIN J, CHANG M, LEE K, et al. BERT: Pre-training of deep bidirectional transformers for language understanding[EB/OL]. arXiv, 2018: 1810.04805[2022-12-10]. .
34	RAO R, MEIER J, SERCU T, et al. Transformer protein language models are unsupervised structure learners[EB/OL].bioRxiv, 2020[2022-12-10]. .
35	RIVES A, MEIER J, SERCU T, et al. Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences[J]. Proceedings of the National Academy of Sciences of the United States of America, 2021, 118(15): e2016239118
36	RAO R, LIU J, VERKUIL R, et al. MSA Transformer[EB/OL]. 2021[2022-12-10]. .
37	FANG X, WANG F, LIU L, et al. HelixFold-single: MSA-free protein structure prediction by using protein language model as an alternative[EB/OL]. arXiv, 2022: 2207.13921[2022-12-10]. .
38	WU R D, DING F, WANG R, et al. High-resolution de novo structure prediction from primary sequence[EB/OL]. bioRxiv, 2022[2022-12-10] .
39	WANG W K, PENG Z L, YANG J Y. Single-sequence protein structure prediction using supervised transformer protein language models[J]. Nature Computational Science, 2022, 2(12): 804-814.
40	CHOWDHURY R, BOUATTA N, BISWAS S, et al. Single-sequence protein structure prediction using a language model and deep learning[J]. Nature Biotechnology, 2022, 40(11): 1617-1623.
41	HSU C, VERKUIL R, LIU J, et al. Learning inverse folding from millions of predicted structures[EB/OL]. bioRxiv, 2022[2022-12-10]. .
42	ELNAGGAR A, HEINZINGER M, DALLAGO C, et al. ProtTrans: towards cracking the language of life's code through self-supervised learning[EB/OL]//IEEE Trans Pattern Analysis & Machine Intelligence, 2021, 4[2022-12-10]. .
43	BRANDES N, GOLDMAN G, WANG C H, et al. Genome-wide prediction of disease variants with a deep protein language model[EB/OL]. bioRxiv, 2022[2022-12-10]. .
44	GUO Y Z, WU J X, MA H H, et al. Self-supervised pre-training for protein embeddings using tertiary structures[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2022, 36(6): 6801-6809.
45	ZHANG Z, XU M, JAMASB A, et al. Protein representation learning by geometric structure pretraining[EB/OL]. arXiv, 2022: 2203.06125[2023-02-01]. .
46	ZHOU G, GAO Z, DING Q, et al. Uni-Mol: a universal 3D molecular representation learning framework[EB/OL][2022-12-10]. .
47	HOPF T A, SCHÄRFE C P I, RODRIGUES J P G L M, et al. Sequence co-evolution gives 3D contacts and structures of protein complexes[J]. eLife, 2014, 3: e03430.
48	ZENG H, WANG S, ZHOU T M, et al. ComplexContact: a web server for inter-protein contact prediction using deep learning[J]. Nucleic Acids Research, 2018, 46(W1): W432-W437.
49	CHEN B, XIE Z W, XU J B, et al. Improve the protein complex prediction with protein language models[EB/OL]. bioRxiv, 2022[2022-12-10]. .
50	ZHENG W, LI Y, ZHANG C X, et al. Protein structure prediction using deep learning distance and hydrogen-bonding restraints in CASP14[J]. Proteins: Structure, Function, and Bioinformatics, 2021, 89(12): 1734-1751.
51	EVANS R, O'NEILL M, PRITZEL A, et al. Protein complex prediction with AlphaFold-Multimer[EB/OL]. bioRxiv, 2022[2022-12-10]. .
52	SUN D W, LIU S J, GONG X Q. Review of multimer protein-protein interaction complex topology and structure prediction[J]. Chinese Physics B, 2020, 29(10): 57-66.
53	YANG Y X, GONG X Q. A new probability method to understand protein-protein interface formation mechanism at amino acid level[J]. Journal of Theoretical Biology, 2018, 436: 18-25.
54	YANG Y X, WANG W, LOU Y, et al. Geometric and amino acid type determinants for protein-protein interaction interfaces[J]. Quantitative Biology, 2018, 6(2): 163-174.
55	WANG W, YANG Y X, YIN J X, et al. Different protein-protein interface patterns predicted by different machine learning methods[J]. Scientific Reports, 2017, 7: 16023.
56	ZHAO Z N, GONG X Q. Trimer protein-protein complex interface interacting residue pairs prediction using deep learning approach[C]//Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics. September 7-10, 2019, Niagara Falls, NY, USA. New York: ACM, 2019: 580-585.
57	SUN D W, GONG X Q. Tetramer protein complex interface residue pairs prediction with LSTM combined with graph representations[J]. Biochimica et Biophysica Acta (BBA)-Proteins and Proteomics, 2020, 1868(11): 140504.
58	LIU J L, GONG X Q. Attention mechanism enhanced LSTM with residual architecture and its application for protein-protein interaction residue pairs prediction[J]. BMC Bioinformatics, 2019, 20(1): 609.
59	ZHAO Z N, GONG X Q. Protein-protein interaction interface residue pair prediction based on deep learning architecture[J]. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2019, 16(5): 1753-1759.
60	LYU Y F, HE R N, HU J J, et al. Prediction of the tetramer protein complex interaction based on CNN and SVM[J]. Frontiers in Genetics, 2023, 14: 1076904.
61	XIE Z W, XU J B. Deep graph learning of inter-protein contacts[J]. Bioinformatics, 2022, 38(4): 947-953.
62	MOREHEAD A, CHEN C, CHENG J. Geometric transformers for protein interface contact prediction[EB/OL]. arXiv, 2021: 2110.02423[2022-12-10]. .
63	GUO Z, LIU J, SKOLNICK J, et al. Prediction of inter-chain distance maps of protein complexes with 2D attention-based deep neural networks[J]. Nature Communications, 2022, 13: 6963.
64	YAN Y M, HUANG S Y. Accurate prediction of inter-protein residue-residue contacts for homo-oligomeric protein complexes[J]. Briefings in Bioinformatics, 2021, 22(5): bbab038.
65	LIN P C, YAN Y M, HUANG S Y. DeepHomo2.0: improved protein-protein contact prediction of homodimers by transformer-enhanced deep learning[J]. Briefings in Bioinformatics, 2022, 24(1), bbac499.
66	ROY R S, QUADIR F, SOLTANIKAZEMI E, et al. A deep dilated convolutional residual network for predicting interchain contacts of protein homodimers[J]. Bioinformatics, 2022, 38(7): 1904-1910.
67	WU T, HUANG H, LI J S, et al. Inter-chain contact map prediction for protein complex based on graph attention network and triangular multiplication update[C]//2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). December 6-8, 2022, Las Vegas, NV, USA. IEEE, 2023: 2143-2148.
68	GAO M, AN D N, PARKS J M, et al. AF2Complex predicts direct physical interactions in multimeric proteins with deep learning[J]. Nature Communications, 2022, 13: 1744.
69	HUANG H, ZENG C S, GONG X Q. Inter-protein contact map generated only from intra-monomer by image inpainting[C]//2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). December 9-12, 2021. Houston, TX, USA. IEEE, 2021: 131-136.
70	CHEN Y, WANG W, LIU J L, et al. Protein interface complementarity and gene duplication improve link prediction of protein-protein interaction network[J]. Frontiers in Genetics, 2020, 11: 291.
71	WEN J, CHAN R H F, YAU S C, et al. K-mer natural vector and its application to the phylogenetic analysis of genetic sequences[J]. Gene, 2014, 546(1): 25-34.
72	ZHAO N, ZHUO M J, TIAN K, et al. Protein-protein interaction and non-interaction predictions using gene sequence natural vector[J]. Communications Biology, 2022, 5: 652.
73	GE F Q, PENG C X, CUI X Y, et al. Inter-domain distance prediction based on deep learning for domain assembly[J]. Briefings in Bioinformatics, 2023: bbad100.
74	SEN N, MADHUSUDHAN M S. A structural database of chain-chain and domain-domain interfaces of proteins[J]. Protein Science, 2022, 31(9): e4406.
75	谢腾宇, 周晓根, 胡俊, 等. 基于接触图残基对距离约束的蛋白质结构预测算法[J]. 计算机科学, 2020, 47(1): 59-65.
	XIE T Y, ZHOU X G, HU J, et al. Contact map-based residue-pair distances restrained protein structure prediction algorithm[J]. Computer Science, 2020, 47(1): 59-65.
76	QUADIR F, ROY R S, SOLTANIKAZEMI E, et al. Deep Complex: a web server of predicting protein complex structures by deep learning inter-chain contact prediction and distance-based modelling[J]. Frontiers in Molecular Biosciences, 2021, 8: 716973.
77	SOLTANIKAZEMI E, ROY R S, QUADIR F, et al. DRL Complex: reconstruction of protein quaternary structures using deep reinforcement learning[EB/OL]. arXiv, 2022: 2205.13594[2022-12-10]. .
78	BAEK M, ANISHCHENKO I, PARK H, et al. Protein oligomer modeling guided by predicted interchain contacts in CASP14[J]. Proteins: Structure, Function, and Bioinformatics, 2021, 89(12): 1824-1833.
79	DE VRIES S J, VAN DIJK M, BONVIN A M J J. The HADDOCK web server for data-driven biomolecular docking[J]. Nature Protocols, 2010, 5(5): 883-897.
80	ESQUIVEL-RODRÍGUEZ J, YANG Y D, KIHARA D. Multi-LZerD: multiple protein docking for asymmetric complexes[J]. Proteins: Structure, Function, and Bioinformatics, 2012, 80(7): 1818-1833.
81	RITCHIE D W, GRUDININ S. Spherical polar Fourier assembly of protein complexes with arbitrary point group symmetry[J]. Journal of Applied Crystallography, 2016, 49(1): 158-167.
82	YAN Y M, TAO H Y, HUANG S Y. HSYMDOCK: a docking web server for predicting the structure of protein homo-oligomers with C _n or D _n symmetry[J]. Nucleic Acids Research, 2018, 46(W1): W423-W431.
83	PARK T, WOO H, YANG J, et al. Protein oligomer structure prediction using GALAXY in CASP14[J]. Proteins: Structure, Function, and Bioinformatics, 2021, 89(12): 1844-1851.
84	ROY BURMAN S S, YOVANNO R A, GRAY J J. Flexible backbone assembly and refinement of symmetrical homomeric complexes[J]. Structure, 2019, 27(6): 1041-1051.e8.
85	PIERCE B, TONG W W, WENG Z P. M-ZDOCK: a grid-based approach for C _n symmetric multimer docking[J]. Bioinformatics, 2005, 21(8): 1472-1478.
86	PIERCE B G, WIEHE K, HWANG H, et al. ZDOCK server: interactive docking prediction of protein-protein complexes and symmetric multimers[J]. Bioinformatics, 2014, 30(12): 1771-1773.
87	JIMÉNEZ-GARCÍA B, PONS C, FERNÁNDEZ-RECIO J. pyDockWEB: a web server for rigid-body protein-protein docking using electrostatics and desolvation scoring[J]. Bioinformatics, 2013, 29(13): 1698-1699.
88	KOZAKOV D, HALL D R, XIA B, et al. The ClusPro web server for protein-protein docking[J]. Nature Protocols, 2017, 12(2): 255-278.
89	XU X J, QIU L M, YAN C F, et al. Performance of MDockPP in CAPRI rounds 28-29 and 31-35 including the prediction of water-mediated interactions[J]. Proteins: Structure, Function, and Bioinformatics, 2017, 85(3): 424-434.
90	KONG R, LIU R R, XU X M, et al. Template-based modeling and ab-initio docking using CoDock in CAPRI[J]. Proteins: Structure, Function, and Bioinformatics, 2020, 88(8): 1100-1109.
91	MARZE N A, ROY BURMAN S S, SHEFFLER W, et al. Efficient flexible backbone protein-protein docking for challenging targets[J]. Bioinformatics, 2018, 34(20): 3461-3469.
92	TORCHALA M, MOAL I H, CHALEIL R A G, et al. SwarmDock: a server for flexible protein-protein docking[J]. Bioinformatics, 2013, 29(6): 807-809.
93	QUIGNOT C, REY J, YU J C, et al. InterEvDock2: an expanded server for protein docking using evolutionary and biological information from homology models and multimeric inputs[J]. Nucleic Acids Research, 2018, 46(W1): W408-W416.
94	BAEK M, PARK T, HEO L, et al. GalaxyHomomer: a web server for protein homo-oligomer structure prediction from a monomer sequence or structure[J]. Nucleic Acids Research, 2017, 45(W1): W320-W324.
95	GANEA O E, HUANG X, ZURICH E, et al. Independent SE(3)- equivariant models for end-to-end rigid protein docking[EB/OL]. arXiv, 2022: 2111.07786[2022-12-10]. .
96	VREVEN T, MOAL I H, VANGONE A, et al. Updates to the integrated protein-protein interaction benchmarks: Docking benchmark version 5 and affinity benchmark version 2[J]. Journal of Molecular Biology, 2015, 427(19): 3031-3041.
97	YU J C, GUEROIS R. PPI4DOCK: large scale assessment of the use of homology models in free docking over more than 1000 realistic targets[J]. Bioinformatics, 2016, 32(24): 3760-3767.
98	YAN Y M, HUANG S Y. A non-redundant benchmark for symmetric protein docking[J]. Big Data Mining and Analytics, 2019, 2(2): 92-99.
99	MIRDITA M, SCHÜTZE K, MORIWAKI Y, et al. ColabFold: making protein folding accessible to all[J]. Nature Methods, 2022, 19(6): 679-682.
100	BRYANT P, POZZATI G, ELOFSSON A. Improved prediction of protein-protein interactions using AlphaFold2[J]. Nature Communications, 2022, 13: 1265.
101	ZHU W, SHENOY A, KUNDROTAS P, et al. Evaluation of AlphaFold-Multimer prediction on multi-chain protein complexes[EB/OL]. 2022[2022-12-29]. .
102	TSUCHIYA Y, YAMAMORI Y, TOMII K. Protein-protein interaction prediction methods: from docking-based to AI-based approaches[J].Biophysical Reviews, 2022, 14(6): 1341-1348.
103	LI Z Y, LIU X Y, CHEN W J, et al. Uni-fold: an open-source platform for developing protein folding models beyond AlphaFold[EB/OL]. bioRxiv, 2022[2022-12-10]. .
104	LI Z Y, YANG S W, LIU X Y, et al. Uni-fold symmetry: harnessing symmetry in folding large protein complexes[EB/OL]. bioRxiv, 2022[2022-12-10]. .
105	BRYANT P, POZZATI G, ZHU W S, et al. Predicting the structure of large protein complexes using AlphaFold and Monte Carlo tree search[J]. Nature Communications, 2022, 13: 6028.
106	GHANI U, DESTA I, JINDAL A, et al. Improved docking of protein models by a combination of AlphaFold2 and ClusPro[EB/OL]. bioRxiv, 2022[2022-12-10]. .
107	HUMPHREYS I R, PEI J M, BAEK M, et al. Computed structures of core eukaryotic protein complexes[J]. Science, 2021, 374(6573): eabm4805.
108	JOHANSSON-ÅKHE I, WALLNER B. Improving peptide-protein docking with AlphaFold-Multimer using forced sampling[J]. Frontiers in Bioinformatics, 2022, 2: 959160.
109	LEE C E, SU B H, TSENG Y J. Comparative studies of AlphaFold, RoseTTAFold and Modeller: a case study involving the use of G-protein-coupled receptors[J]. Briefings in Bioinformatics, 2022, 23(5): bbac308.
110	YIN R, FENG B Y, VARSHNEY A, et al. Benchmarking AlphaFold for protein complex modeling reveals accuracy determinants[J]. Protein Science, 2022, 31(8): e4379.
111	BRYANT P. Deep learning for protein complex structure prediction[J]. Current Opinion in Structural Biology, 2023, 79: 102529.
112	HAN B Q, REN C J, WANG W D, et al. Computational prediction of protein intrinsically disordered region related interactions and functions[J]. Genes, 2023, 14(2): 432.

方法	输入特征				网络架构	任务
方法	共进化	单体距离图	单体结构	蛋白语言模型	残差网络	同源	异源
ComplexContact^[48]	√				√		√
Glinter^[61]		√	√	√	√ + 图学习	√	√
DeepHomo^[64]	√	√			√	√
DeepHomo2^[65]	√	√		√	√	√
DRcon^[66]	√	√			√ + 空洞卷积	√
DeepInteract^[62]			√		几何深度学习		√
CDPred^[63]	√	√		√	√ + 注意力机制	√	√
PDII^[69]		√			图像修复	√	√
PGT^[67]		√		√	√ + 图注意力+三角更新	√

方法	输入特征				网络架构	任务
方法	共进化	单体距离图	单体结构	蛋白语言模型	残差网络	同源	异源
ComplexContact^[48]	√				√		√
Glinter^[61]		√	√	√	√ + 图学习	√	√
DeepHomo^[64]	√	√			√	√
DeepHomo2^[65]	√	√		√	√	√
DRcon^[66]	√	√			√ + 空洞卷积	√
DeepInteract^[62]			√		几何深度学习		√
CDPred^[63]	√	√		√	√ + 注意力机制	√	√
PDII^[69]		√			图像修复	√	√
PGT^[67]		√		√	√ + 图注意力+三角更新	√

[1]	孟巧珍, 郭菲. “可折叠性”在酶智能设计改造中的应用研究——以AlphaFold2为例[J]. 合成生物学, 2023, 4(3): 571-589.
[2]	唐一鸣, 姚逸飞, 杨中元, 周运, 王子超, 韦广红. 神经退行性疾病相关蛋白病理性聚集和液液相分离研究进展[J]. 合成生物学, 2023, 4(3): 590-610.