{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T04:04:12Z","timestamp":1783483452015,"version":"3.55.0"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1009284","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2021,8,16]],"date-time":"2021-08-16T00:00:00Z","timestamp":1629072000000}}],"reference-count":75,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2021,8,4]],"date-time":"2021-08-04T00:00:00Z","timestamp":1628035200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004543","name":"china scholarship council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]},{"name":"institute guoqiang at tsinghua university"},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1652815"],"award-info":[{"award-number":["1652815"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"compgen fellowship"},{"name":"baidu fellowship"},{"name":"nsf career award"}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Modeling the impact of amino acid mutations on protein-protein interaction plays a crucial role in protein engineering and drug design. In this study, we develop GeoPPI, a novel structure-based deep-learning framework to predict the change of binding affinity upon mutations. Based on the three-dimensional structure of a protein, GeoPPI first learns a geometric representation that encodes topology features of the protein structure via a self-supervised learning scheme. These representations are then used as features for training gradient-boosting trees to predict the changes of protein-protein binding affinity upon mutations. We find that GeoPPI is able to learn meaningful features that characterize interactions between atoms in protein structures. In addition, through extensive experiments, we show that GeoPPI achieves new state-of-the-art performance in predicting the binding affinity changes upon both single- and multi-point mutations on six benchmark datasets. Moreover, we show that GeoPPI can accurately estimate the difference of binding affinities between a few recently identified SARS-CoV-2 antibodies and the receptor-binding domain (RBD) of the S protein. These results demonstrate the potential of GeoPPI as a powerful and useful computational tool in protein design and engineering. Our code and datasets are available at: <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/Liuxg16\/GeoPPI\" xlink:type=\"simple\">https:\/\/github.com\/Liuxg16\/GeoPPI<\/jats:ext-link>.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1009284","type":"journal-article","created":{"date-parts":[[2021,8,4]],"date-time":"2021-08-04T17:39:18Z","timestamp":1628098758000},"page":"e1009284","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":133,"title":["Deep geometric representations for modeling effects of mutations on protein-protein binding affinity"],"prefix":"10.1371","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6368-2043","authenticated-orcid":true,"given":"Xianggen","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7728-6412","authenticated-orcid":true,"given":"Yunan","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5971-046X","authenticated-orcid":true,"given":"Pengyong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sen","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1736-2978","authenticated-orcid":true,"given":"Jian","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2021,8,4]]},"reference":[{"issue":"1","key":"pcbi.1009284.ref001","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.molonc.2007.01.003","article-title":"Cancer therapeutic antibodies come of age: targeting minimal residual disease","volume":"1","author":"T Ben-Kasus","year":"2007","journal-title":"Molecular Oncology"},{"issue":"7475","key":"pcbi.1009284.ref002","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1038\/nature12744","article-title":"Therapeutic efficacy of potent neutralizing HIV-1-specific monoclonal antibodies in SHIV-infected rhesus monkeys","volume":"503","author":"DH Barouch","year":"2013","journal-title":"Nature"},{"issue":"5","key":"pcbi.1009284.ref003","doi-asserted-by":"crossref","first-page":"1549","DOI":"10.1093\/bib\/bbz095","article-title":"Computational approaches to therapeutic antibody design: established methods and emerging trends","volume":"21","author":"RA Norman","year":"2020","journal-title":"Briefings in Bioinformatics"},{"issue":"5","key":"pcbi.1009284.ref004","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1038\/nri1837","article-title":"Potent antibody therapeutics by design","volume":"6","author":"PJ Carter","year":"2006","journal-title":"Nature Reviews Immunology"},{"issue":"8","key":"pcbi.1009284.ref005","doi-asserted-by":"crossref","first-page":"e1007207","DOI":"10.1371\/journal.pcbi.1007207","article-title":"Optimizing antibody affinity and stability by the automated design of the variable light-heavy chain interfaces","volume":"15","author":"S Warszawski","year":"2019","journal-title":"PLoS Computational Biology"},{"issue":"5","key":"pcbi.1009284.ref006","doi-asserted-by":"crossref","first-page":"e1006980","DOI":"10.1371\/journal.pcbi.1006980","article-title":"Experimentally guided computational antibody affinity maturation with de novo docking, modelling and rational design","volume":"15","author":"DA Cannon","year":"2019","journal-title":"PLoS Computational Biology"},{"issue":"3","key":"pcbi.1009284.ref007","doi-asserted-by":"crossref","first-page":"864","DOI":"10.1529\/biophysj.105.071589","article-title":"Calculation of absolute protein-ligand binding affinity using path and endpoint approaches","volume":"90","author":"MS Lee","year":"2006","journal-title":"Biophysical Journal"},{"issue":"2","key":"pcbi.1009284.ref008","doi-asserted-by":"crossref","first-page":"W382","DOI":"10.1093\/nar\/gki387","article-title":"The FoldX web server: an online force field","volume":"33","author":"J Schymkowitz","year":"2005","journal-title":"Nucleic Acids Research"},{"issue":"8","key":"pcbi.1009284.ref009","doi-asserted-by":"crossref","first-page":"3674","DOI":"10.1021\/jp0550816","article-title":"Coarse grained protein- lipid model with application to lipoprotein particles","volume":"110","author":"AY Shih","year":"2006","journal-title":"The Journal of Physical Chemistry B"},{"issue":"12","key":"pcbi.1009284.ref010","doi-asserted-by":"crossref","first-page":"1767","DOI":"10.1016\/j.str.2006.10.003","article-title":"Stability and dynamics of virus capsids described by coarse-grained modeling","volume":"14","author":"A Arkhipov","year":"2006","journal-title":"Structure"},{"issue":"5","key":"pcbi.1009284.ref011","doi-asserted-by":"crossref","first-page":"872","DOI":"10.1016\/j.bbagen.2014.10.019","article-title":"Enhanced sampling techniques in molecular dynamics simulations of biological systems","volume":"1850","author":"RC Bernardi","year":"2015","journal-title":"Biochimica et Biophysica Acta-General Subjects"},{"issue":"6","key":"pcbi.1009284.ref012","doi-asserted-by":"crossref","first-page":"e1003693","DOI":"10.1371\/journal.pcbi.1003693","article-title":"Genome-wide prediction and validation of peptides that bind human prosurvival Bcl-2 proteins","volume":"10","author":"J DeBartolo","year":"2014","journal-title":"PLoS Computational Biology"},{"key":"pcbi.1009284.ref013","unstructured":"Inc AS. Discovery Studio Modeling Environment, Release 4.0. 2013;."},{"issue":"2","key":"pcbi.1009284.ref014","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1002\/prot.25630","article-title":"iSEE: Interface structure, evolution, and energy-based machine learning predictor of binding affinity changes upon mutations","volume":"87","author":"C Geng","year":"2019","journal-title":"Proteins: Structure, Function, and Bioinformatics"},{"key":"pcbi.1009284.ref015","doi-asserted-by":"crossref","first-page":"100939","DOI":"10.1016\/j.isci.2020.100939","article-title":"MutaBind2: predicting the impacts of single and multiple mutations on protein-protein interactions","author":"N Zhang","year":"2020","journal-title":"Iscience"},{"issue":"3","key":"pcbi.1009284.ref016","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1093\/bioinformatics\/bty635","article-title":"SKEMPI 2.0: an updated benchmark of changes in protein\u2013protein binding energy, kinetics and thermodynamics upon mutation","volume":"35","author":"J Jankauskait\u0117","year":"2019","journal-title":"Bioinformatics"},{"key":"pcbi.1009284.ref017","doi-asserted-by":"crossref","first-page":"S477","DOI":"10.1098\/rsif.2008.0508.focus","article-title":"Challenges in the computational design of proteins","volume":"6","author":"M Su\u00e1rez","year":"2009","journal-title":"Journal of the Royal Society Interface"},{"issue":"30","key":"pcbi.1009284.ref018","doi-asserted-by":"crossref","first-page":"2494","DOI":"10.1002\/jcc.25522","article-title":"OSPREY 3.0: Open-source protein redesign for you, with powerful new features","volume":"39","author":"MA Hallen","year":"2018","journal-title":"Journal of Computational Chemistry"},{"key":"pcbi.1009284.ref019","unstructured":"Veli\u010dkovi\u0107 P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y. Graph attention networks. ICLR. 2018;."},{"key":"pcbi.1009284.ref020","unstructured":"Gilmer J, Schoenholz SS, Riley PF, Vinyals O, Dahl GE. Neural Message Passing for Quantum Chemistry. In: Proceedings of the 34th International Conference on Machine Learning. JMLR.org; 2017. p. 1263\u20131272."},{"key":"pcbi.1009284.ref021","unstructured":"Devlin J, Chang MW, Lee K, Toutanova K. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In: Proceedings of the 2019 Conference of the Association for Computational Linguistics; 2019. p. 4171\u20134186. Available from: https:\/\/www.aclweb.org\/anthology\/N19-1423."},{"key":"pcbi.1009284.ref022","doi-asserted-by":"crossref","unstructured":"Grover A, Leskovec J. node2vec: Scalable feature learning for networks. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2016. p. 855\u2013864.","DOI":"10.1145\/2939672.2939754"},{"issue":"2","key":"pcbi.1009284.ref023","doi-asserted-by":"crossref","first-page":"895","DOI":"10.1021\/acs.jcim.8b00545","article-title":"Comparative assessment of scoring functions: the CASF-2016 update","volume":"59","author":"M Su","year":"2018","journal-title":"Journal of chemical information and modeling"},{"issue":"11","key":"pcbi.1009284.ref024","doi-asserted-by":"crossref","first-page":"e155","DOI":"10.1371\/journal.pcbi.0020155","article-title":"3D complex: a structural classification of protein complexes","volume":"2","author":"ED Levy","year":"2006","journal-title":"PLoS Computational Biology"},{"issue":"Nov","key":"pcbi.1009284.ref025","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Lvd Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"issue":"1","key":"pcbi.1009284.ref026","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1073\/pnas.0407280102","article-title":"The modular architecture of protein\u2013protein binding interfaces","volume":"102","author":"D Reichmann","year":"2005","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"2","key":"pcbi.1009284.ref027","doi-asserted-by":"crossref","first-page":"793","DOI":"10.1002\/prot.21968","article-title":"Specific interactions for ab initio folding of protein terminal regions with secondary structures","volume":"72","author":"Y Yang","year":"2008","journal-title":"Proteins: Structure, Function, and Bioinformatics"},{"issue":"11","key":"pcbi.1009284.ref028","doi-asserted-by":"crossref","first-page":"2714","DOI":"10.1110\/ps.0217002","article-title":"Distance-scaled, finite ideal-gas reference state improves structure-derived potentials of mean force for structure selection and stability prediction","volume":"11","author":"H Zhou","year":"2002","journal-title":"Protein Science"},{"issue":"1","key":"pcbi.1009284.ref029","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1002\/prot.20019","article-title":"A physical reference state unifies the structure-derived potential of mean force for protein folding and binding","volume":"56","author":"S Liu","year":"2004","journal-title":"Proteins: Structure, Function, and Bioinformatics"},{"issue":"3","key":"pcbi.1009284.ref030","doi-asserted-by":"crossref","first-page":"426","DOI":"10.1016\/j.jmb.2016.11.022","article-title":"BindProfX: assessing mutation-induced binding affinity change by protein interface profiles with pseudo-counts","volume":"429","author":"P Xiong","year":"2017","journal-title":"Journal of Molecular Biology"},{"issue":"2","key":"pcbi.1009284.ref031","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1038\/s42256-020-0149-6","article-title":"A topology-based network tree for the prediction of protein\u2013protein binding affinity changes following mutation","volume":"2","author":"M Wang","year":"2020","journal-title":"Nature Machine Intelligence"},{"issue":"12","key":"pcbi.1009284.ref032","doi-asserted-by":"crossref","first-page":"2082","DOI":"10.1002\/prot.24428","article-title":"Docking, scoring, and affinity prediction in CAPRI","volume":"81","author":"MF Lensink","year":"2013","journal-title":"Proteins: Structure, Function, and Bioinformatics"},{"issue":"4","key":"pcbi.1009284.ref033","doi-asserted-by":"crossref","first-page":"547","DOI":"10.3390\/ijms17040547","article-title":"SAAMBE: webserver to predict the charge of binding free energy caused by amino acids mutations","volume":"17","author":"M Petukh","year":"2016","journal-title":"International Journal of Molecular Sciences"},{"issue":"2","key":"pcbi.1009284.ref034","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1002\/pro.2829","article-title":"AB-Bind: antibody binding mutational database for computational affinity predictions","volume":"25","author":"S Sirin","year":"2016","journal-title":"Protein Science"},{"issue":"12","key":"pcbi.1009284.ref035","doi-asserted-by":"crossref","first-page":"1777","DOI":"10.1016\/j.str.2008.09.012","article-title":"Prediction of protein-protein interface sequence diversity using flexible backbone computational protein design","volume":"16","author":"EL Humphris","year":"2008","journal-title":"Structure"},{"issue":"5","key":"pcbi.1009284.ref036","doi-asserted-by":"crossref","first-page":"e0232528","DOI":"10.1371\/journal.pone.0232528","article-title":"Multifaceted analysis of training and testing convolutional neural networks for protein secondary structure prediction","volume":"15","author":"M Shapovalov","year":"2020","journal-title":"PloS One"},{"issue":"12","key":"pcbi.1009284.ref037","doi-asserted-by":"crossref","first-page":"e1003926","DOI":"10.1371\/journal.pcbi.1003926","article-title":"ECOD: an evolutionary classification of protein domains","volume":"10","author":"H Cheng","year":"2014","journal-title":"PLoS Computational Biology"},{"issue":"W1","key":"pcbi.1009284.ref038","doi-asserted-by":"crossref","first-page":"W333","DOI":"10.1093\/nar\/gkt450","article-title":"BeAtMuSiC: prediction of changes in protein\u2013protein binding affinity on mutations","volume":"41","author":"Y Dehouck","year":"2013","journal-title":"Nucleic Acids Research"},{"key":"pcbi.1009284.ref039","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1016\/B978-1-4832-2734-4.50017-6","volume-title":"Evolving genes and proteins","author":"E Zuckerkandl","year":"1965"},{"issue":"12","key":"pcbi.1009284.ref040","doi-asserted-by":"crossref","first-page":"e1009089","DOI":"10.1371\/journal.ppat.1009089","article-title":"A natural mutation between SARS-CoV-2 and SARS-CoV determines neutralization by a cross-reactive antibody","volume":"16","author":"NC Wu","year":"2020","journal-title":"PLoS Pathogens"},{"issue":"7839","key":"pcbi.1009284.ref041","doi-asserted-by":"crossref","first-page":"682","DOI":"10.1038\/s41586-020-2852-1","article-title":"SARS-CoV-2 neutralizing antibody structures inform therapeutic strategies","volume":"588","author":"CO Barnes","year":"2020","journal-title":"Nature"},{"issue":"1","key":"pcbi.1009284.ref042","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1016\/j.cell.2020.05.025","article-title":"Potent neutralizing antibodies against SARS-CoV-2 identified by high-throughput single-cell sequencing of convalescent patients\u2019 B cells","volume":"182","author":"Y Cao","year":"2020","journal-title":"Cell"},{"issue":"6506","key":"pcbi.1009284.ref043","doi-asserted-by":"crossref","first-page":"956","DOI":"10.1126\/science.abc7520","article-title":"Isolation of potent SARS-CoV-2 neutralizing antibodies and protection from disease in a small animal model","volume":"369","author":"TF Rogers","year":"2020","journal-title":"Science"},{"key":"pcbi.1009284.ref044","first-page":"545","volume-title":"Methods in enzymology","author":"A Leaver-Fay","year":"2011"},{"issue":"12","key":"pcbi.1009284.ref045","doi-asserted-by":"crossref","first-page":"1771","DOI":"10.1093\/bioinformatics\/btu097","article-title":"ZDOCK server: interactive docking prediction of protein\u2013protein complexes and symmetric multimers","volume":"30","author":"BG Pierce","year":"2014","journal-title":"Bioinformatics"},{"key":"pcbi.1009284.ref046","doi-asserted-by":"crossref","first-page":"437","DOI":"10.1038\/s41586-020-2456-9","article-title":"Convergent antibody responses to SARS-CoV-2 in convalescent individuals","volume":"584","author":"D Robbiani","year":"2020","journal-title":"Nature"},{"issue":"6506","key":"pcbi.1009284.ref047","doi-asserted-by":"crossref","first-page":"1014","DOI":"10.1126\/science.abd0831","article-title":"Antibody cocktail to SARS-CoV-2 spike protein prevents rapid mutational escape seen with individual antibodies","volume":"369","author":"A Baum","year":"2020","journal-title":"Science"},{"issue":"6","key":"pcbi.1009284.ref048","doi-asserted-by":"crossref","first-page":"946","DOI":"10.1086\/651022","article-title":"Escape from Human Monoclonal Antibody Neutralization Affects In Vitro and In Vivo Fitness of Severe Acute Respiratory Syndrome Coronavirus","volume":"201","author":"B Rockx","year":"2010","journal-title":"The Journal of Infectious Diseases"},{"issue":"W1","key":"pcbi.1009284.ref049","doi-asserted-by":"crossref","first-page":"W469","DOI":"10.1093\/nar\/gkw458","article-title":"mCSM-AB: a web server for predicting antibody\u2013antigen affinity changes upon mutation with graph-based signatures","volume":"44","author":"DE Pires","year":"2016","journal-title":"Nucleic Acids Research"},{"key":"pcbi.1009284.ref050","doi-asserted-by":"crossref","unstructured":"Pathak D, Krahenbuhl P, Donahue J, Darrell T, Efros AA. Context encoders: Feature learning by inpainting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2016. p. 2536\u20132544.","DOI":"10.1109\/CVPR.2016.278"},{"key":"pcbi.1009284.ref051","doi-asserted-by":"crossref","unstructured":"Qiu J, Chen Q, Dong Y, Zhang J, Yang H, Ding M, et al. GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining; 2020. p. 1150\u20131160.","DOI":"10.1145\/3394486.3403168"},{"issue":"1","key":"pcbi.1009284.ref052","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1109\/72.554195","article-title":"Face recognition: A convolutional neural-network approach","volume":"8","author":"S Lawrence","year":"1997","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"4","key":"pcbi.1009284.ref053","doi-asserted-by":"crossref","first-page":"778","DOI":"10.1002\/prot.22488","article-title":"Improved prediction of protein side-chain conformations with SCWRL4","volume":"77","author":"GG Krivov","year":"2009","journal-title":"Proteins: Structure, Function, and Bioinformatics"},{"issue":"7","key":"pcbi.1009284.ref054","doi-asserted-by":"crossref","first-page":"1731","DOI":"10.1021\/ja026939x","article-title":"HADDOCK: a protein-protein docking approach based on biochemical or biophysical information","volume":"125","author":"C Dominguez","year":"2003","journal-title":"Journal of the American Chemical Society"},{"issue":"7620","key":"pcbi.1009284.ref055","doi-asserted-by":"crossref","first-page":"320","DOI":"10.1038\/nature19946","article-title":"The coming of age of de novo protein design","volume":"537","author":"PS Huang","year":"2016","journal-title":"Nature"},{"issue":"17","key":"pcbi.1009284.ref056","doi-asserted-by":"crossref","first-page":"e118","DOI":"10.1093\/nar\/gkr407","article-title":"Predicting the functional impact of protein mutations: application to cancer genomics","volume":"39","author":"B Reva","year":"2011","journal-title":"Nucleic Acids Research"},{"issue":"8","key":"pcbi.1009284.ref057","doi-asserted-by":"crossref","first-page":"1439","DOI":"10.1002\/pro.674","article-title":"Quantitation of protein\u2013protein interactions by thermal stability shift analysis","volume":"20","author":"CJ Layton","year":"2011","journal-title":"Protein Science"},{"issue":"7","key":"pcbi.1009284.ref058","doi-asserted-by":"crossref","first-page":"2302","DOI":"10.1093\/nar\/gki524","article-title":"TM-align: a protein structure alignment algorithm based on the TM-score","volume":"33","author":"Y Zhang","year":"2005","journal-title":"Nucleic Acids Research"},{"issue":"20","key":"pcbi.1009284.ref059","doi-asserted-by":"crossref","first-page":"2600","DOI":"10.1093\/bioinformatics\/bts489","article-title":"SKEMPI: a structural kinetic and energetic database of mutant protein interactions and its use in empirical models","volume":"28","author":"IH Moal","year":"2012","journal-title":"Bioinformatics"},{"issue":"W1","key":"pcbi.1009284.ref060","doi-asserted-by":"crossref","first-page":"W338","DOI":"10.1093\/nar\/gkz383","article-title":"mCSM-PPI2: predicting the effects of mutations on protein\u2013protein interactions","volume":"47","author":"CH Rodrigues","year":"2019","journal-title":"Nucleic Acids Research"},{"issue":"8","key":"pcbi.1009284.ref061","doi-asserted-by":"crossref","first-page":"e1002623","DOI":"10.1371\/journal.pcbi.1002623","article-title":"Alternative protein-protein interfaces are frequent exceptions","volume":"8","author":"T Hamp","year":"2012","journal-title":"PLoS Computational Biology"},{"key":"pcbi.1009284.ref062","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE International Conference on Computer Vision; 2015. p. 1026\u20131034.","DOI":"10.1109\/ICCV.2015.123"},{"key":"pcbi.1009284.ref063","unstructured":"Hu W, Liu B, Gomes J, Zitnik M, Liang P, Pande V, et al. Strategies for Pre-training Graph Neural Networks. In: International Conference on Learning Representations; 2020. Available from: https:\/\/openreview.net\/forum?id=HJlWWJSFDH."},{"issue":"6","key":"pcbi.1009284.ref064","doi-asserted-by":"crossref","first-page":"844","DOI":"10.1016\/j.str.2011.03.019","article-title":"A smoothed backbone-dependent rotamer library for proteins derived from adaptive kernel density estimates and regressions","volume":"19","author":"MV Shapovalov","year":"2011","journal-title":"Structure"},{"key":"pcbi.1009284.ref065","first-page":"1189","article-title":"Greedy function approximation: a gradient boosting machine","author":"JH Friedman","year":"2001","journal-title":"Annals of Statistics"},{"issue":"6088","key":"pcbi.1009284.ref066","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"DE Rumelhart","year":"1986","journal-title":"Nature"},{"key":"pcbi.1009284.ref067","volume-title":"Deep Learning","author":"I Goodfellow","year":"2016"},{"key":"pcbi.1009284.ref068","article-title":"Adam: A Method for Stochastic Optimization","author":"DP Kingma","year":"2014","journal-title":"CoRR"},{"key":"pcbi.1009284.ref069","article-title":"Automatic differentiation in PyTorch","author":"A Paszke","year":"2017","journal-title":"Neural Information Processing Systems"},{"key":"pcbi.1009284.ref070","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"F Pedregosa","year":"2011","journal-title":"Journal of Machine Learning Research"},{"issue":"4","key":"pcbi.1009284.ref071","doi-asserted-by":"crossref","first-page":"1013","DOI":"10.1016\/j.cell.2020.09.035","article-title":"Structurally resolved SARS-CoV-2 antibody shows high efficacy in severely infected hamsters and provides a potent cocktail pairing strategy","volume":"183","author":"S Du","year":"2020","journal-title":"Cell"},{"issue":"1","key":"pcbi.1009284.ref072","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-020-18159-4","article-title":"A panel of human neutralizing mAbs targeting SARS-CoV-2 spike at multiple epitopes","volume":"11","author":"T Noy-Porat","year":"2020","journal-title":"Nature Communications"},{"issue":"5","key":"pcbi.1009284.ref073","doi-asserted-by":"crossref","first-page":"1295","DOI":"10.1016\/j.cell.2020.08.012","article-title":"Deep mutational scanning of SARS-CoV-2 receptor binding domain reveals constraints on folding and ACE2 binding","volume":"182","author":"TN Starr","year":"2020","journal-title":"Cell"},{"key":"pcbi.1009284.ref074","doi-asserted-by":"crossref","first-page":"W299","DOI":"10.1093\/nar\/gki370","article-title":"ConSurf 2005: the projection of evolutionary conservation scores of residues on protein structures","volume":"33","author":"M Landau","year":"2005","journal-title":"Nucleic Acids Research"},{"issue":"2","key":"pcbi.1009284.ref075","doi-asserted-by":"crossref","first-page":"991","DOI":"10.1021\/acs.jctc.7b00660","article-title":"Fast calculation of protein\u2013protein binding free energies using umbrella sampling with a coarse-grained model","volume":"14","author":"JS Patel","year":"2018","journal-title":"Journal of chemical theory and computation"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1009284","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2021,8,16]],"date-time":"2021-08-16T00:00:00Z","timestamp":1629072000000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1009284","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,16]],"date-time":"2021-08-16T19:08:42Z","timestamp":1629140922000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1009284"}},"subtitle":[],"editor":[{"given":"Roland L.","family":"Dunbrack","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2021,8,4]]},"references-count":75,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2021,8,4]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1009284","relation":{"new_version":[{"id-type":"doi","id":"10.1371\/journal.pcbi.1009284","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,4]]}}}