{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T07:53:11Z","timestamp":1776325991649,"version":"3.50.1"},"reference-count":38,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T00:00:00Z","timestamp":1669248000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100013407","name":"Netherlands eScience Center","doi-asserted-by":"publisher","award":["ASDI.2016.043"],"award-info":[{"award-number":["ASDI.2016.043"]}],"id":[{"id":"10.13039\/100013407","id-type":"DOI","asserted-by":"publisher"}]},{"name":"SURF Open Lab \u2018Machine","award":["AB\/AM\/10573"],"award-info":[{"award-number":["AB\/AM\/10573"]}]},{"name":"Computing Time on National Computer Facilities","award":["2018\/ENW\/00485366"],"award-info":[{"award-number":["2018\/ENW\/00485366"]}]},{"name":"Netherlands Organization for Scientific Research"},{"name":"European Union Horizon 2020 project BioExcel","award":["823830"],"award-info":[{"award-number":["823830"]}]},{"name":"Hypatia Fellowship from Radboudumc","award":["Rv819.52706"],"award-info":[{"award-number":["Rv819.52706"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,1,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Gaining structural insights into the protein\u2013protein interactome is essential to understand biological phenomena and extract knowledge for rational drug design or protein engineering. We have previously developed DeepRank, a deep-learning framework to facilitate pattern learning from protein\u2013protein interfaces using convolutional neural network (CNN) approaches. However, CNN is not rotation invariant and data augmentation is required to desensitize the network to the input data orientation which dramatically impairs the computation performance. Representing protein\u2013protein complexes as atomic- or residue-scale rotation invariant graphs instead enables using graph neural networks (GNN) approaches, bypassing those limitations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We have developed DeepRank-GNN, a framework that converts protein\u2013protein interfaces from PDB 3D coordinates files into graphs that are further provided to a pre-defined or user-defined GNN architecture to learn problem-specific interaction patterns. DeepRank-GNN is designed to be highly modularizable, easily customized and is wrapped into a user-friendly python3 package. Here, we showcase DeepRank-GNN\u2019s performance on two applications using a dedicated graph interaction neural network: (i) the scoring of docking poses and (ii) the discriminating of biological and crystal interfaces. In addition to the highly competitive performance obtained in those tasks as compared to state-of-the-art methods, we show a significant improvement in speed and storage requirement using DeepRank-GNN as compared to DeepRank.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>DeepRank-GNN is freely available from https:\/\/github.com\/DeepRank\/DeepRank-GNN.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Supplementary information<\/jats:title>\n                    <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btac759","type":"journal-article","created":{"date-parts":[[2022,11,23]],"date-time":"2022-11-23T09:41:41Z","timestamp":1669196501000},"source":"Crossref","is-referenced-by-count":155,"title":["DeepRank-GNN: a graph neural network framework to learn patterns in protein\u2013protein interfaces"],"prefix":"10.1093","volume":"39","author":[{"given":"Manon","family":"R\u00e9au","sequence":"first","affiliation":[{"name":"Computational Structural Biology Group, Department of Chemistry, Bijvoet Centre, Faculty of Science, Utrecht University , Utrecht 3584CH, The Netherlands"}]},{"given":"Nicolas","family":"Renaud","sequence":"additional","affiliation":[{"name":"Netherlands eScience Center , Amsterdam 1098 XG, The Netherlands"}]},{"given":"Li C","family":"Xue","sequence":"additional","affiliation":[{"name":"Center for Molecular and Biomolecular Informatics, Radboudumc , Nijmegen 6525 GA, The Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7369-1322","authenticated-orcid":false,"given":"Alexandre M J J","family":"Bonvin","sequence":"additional","affiliation":[{"name":"Computational Structural Biology Group, Department of Chemistry, Bijvoet Centre, Faculty of Science, Utrecht University , Utrecht 3584CH, The Netherlands"}]}],"member":"286","published-online":{"date-parts":[[2022,11,24]]},"reference":[{"key":"2023010107544976300_btac759-B1","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1093\/bioinformatics\/btaa714","article-title":"GraphQA: protein model quality assessment using graph convolutional networks","volume":"37","author":"Baldassarre","year":"2021","journal-title":"Bioinformatics"},{"key":"2023010107544976300_btac759-B2","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1186\/s12900-014-0022-0","article-title":"A PDB-wide, evolution-based assessment of protein-protein interfaces","volume":"14","author":"Baskaran","year":"2014","journal-title":"BMC Struct. Biol"},{"key":"2023010107544976300_btac759-B4","doi-asserted-by":"crossref","first-page":"1091","DOI":"10.1002\/prot.25888","article-title":"Energy-based graph convolutional networks for scoring protein docking models","volume":"88","author":"Cao","year":"2020","journal-title":"Proteins: Struct., Funct. Bioinformatics"},{"key":"2023010107544976300_btac759-B5","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1186\/1471-2105-13-334","article-title":"Protein interface classification by evolutionary analysis","volume":"13","author":"Duarte","year":"2012","journal-title":"BMC Bioinformatics"},{"key":"2023010107544976300_btac759-B8","author":"Fout","year":"2017"},{"key":"2023010107544976300_btac759-B9","doi-asserted-by":"crossref","first-page":"4200","DOI":"10.1021\/acs.jcim.0c00411","article-title":"Three-dimensional convolutional neural networks and a cross-docked data set for structure-based drug design","volume":"60","author":"Francoeur","year":"2020","journal-title":"J. Chem. Inf. Model"},{"key":"2023010107544976300_btac759-B10","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1038\/s41592-019-0666-6","article-title":"Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning","volume":"17","author":"Gainza","year":"2020","journal-title":"Nat. Methods"},{"key":"2023010107544976300_btac759-B11","doi-asserted-by":"crossref","first-page":"e1410","DOI":"10.1002\/wcms.1410","article-title":"Finding the \u0394\u0394G spot: are predictors of binding affinity changes upon mutations in protein\u2013protein interactions ready for it?","volume":"9","author":"Geng","year":"2019","journal-title":"WIREs Comput. Mol. Sci"},{"key":"2023010107544976300_btac759-B12","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1093\/bioinformatics\/btz496","article-title":"iScore: a novel graph kernel-based function for scoring protein-protein docking models","volume":"36","author":"Geng","year":"2020","journal-title":"Bioinformatics"},{"key":"2023010107544976300_btac759-B1200","author":"Hagberg","year":"2008"},{"key":"2023010107544976300_btac759-B13","doi-asserted-by":"crossref","first-page":"2332","DOI":"10.1093\/bioinformatics\/btab118","article-title":"VoroCNN: deep convolutional neural network built on 3D voronoi tessellation of protein structures","volume":"37","author":"Igashov","year":"2021","journal-title":"Bioinformatics"},{"key":"2023010107544976300_btac759-B14","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1021\/acs.jcim.7b00650","article-title":"KDEEP: protein\u2013ligand absolute binding affinity prediction via 3D-Convolutional neural networks","volume":"58","author":"Jim\u00e9nez","year":"2018","journal-title":"J. Chem. Inf. Model"},{"key":"2023010107544976300_btac759-B15","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction with AlphaFold","volume":"596","author":"Jumper","year":"2021","journal-title":"Nature"},{"key":"2023010107544976300_btac759-B16","doi-asserted-by":"crossref","first-page":"5150","DOI":"10.1021\/acsomega.9b04162","article-title":"graphDelta: MPNN scoring function for the affinity prediction of protein\u2013ligand complexes","volume":"5","author":"Karlov","year":"2020","journal-title":"ACS Omega"},{"key":"2023010107544976300_btac759-B17","author":"Kingma","year":"2017"},{"key":"2023010107544976300_btac759-B18","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"ImageNet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"2023010107544976300_btac759-B19","doi-asserted-by":"crossref","first-page":"704","DOI":"10.1002\/prot.21804","article-title":"Docking and scoring protein complexes: CAPRI 3rd edition","volume":"69","author":"Lensink","year":"2007","journal-title":"Proteins"},{"key":"2023010107544976300_btac759-B20","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1002\/prot.25007","article-title":"Prediction of homoprotein and heteroprotein complexes by protein docking and template-based modeling: a CASP-CAPRI experiment","volume":"84","author":"Lensink","year":"2016","journal-title":"Proteins: Struct., Funct., Bioinformatics"},{"key":"2023010107544976300_btac759-B21","doi-asserted-by":"crossref","first-page":"1800","DOI":"10.1002\/prot.26222","article-title":"Prediction of protein assemblies, the next frontier: the CASP14-CAPRI experiment","volume":"89","author":"Lensink","year":"2021","journal-title":"Proteins"},{"key":"2023010107544976300_btac759-B22","doi-asserted-by":"crossref","first-page":"3163","DOI":"10.1002\/prot.24678","article-title":"Score_set: a CAPRI benchmark for scoring protein complexes","volume":"82","author":"Lensink","year":"2014","journal-title":"Proteins: Struct., Funct. Bioinformatics"},{"key":"2023010107544976300_btac759-B23","doi-asserted-by":"crossref","first-page":"D265","DOI":"10.1093\/nar\/gkz991","article-title":"CDD\/SPARCLE: the conserved domain database in 2020","volume":"48","author":"Lu","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"2023010107544976300_btac759-B24","author":"Mahbub","year":"2022"},{"key":"2023010107544976300_btac759-B25","doi-asserted-by":"crossref","DOI":"10.3389\/fenvs.2015.00080","article-title":"DeepTox: toxicity prediction using deep learning","volume":"3","author":"Mayr","year":"2016","journal-title":"Front. Environ. Sci"},{"key":"2023010107544976300_btac759-B26","doi-asserted-by":"crossref","first-page":"4170","DOI":"10.1021\/acs.jcim.9b00927","article-title":"Combining docking pose rank and structure with deep learning improves protein-ligand binding mode prediction","volume":"60","author":"Morrone","year":"2020","journal-title":"J. Chem. Inf. Model"},{"key":"2023010107544976300_btac759-B7","author":"Paszke","year":"2017"},{"key":"2023010107544976300_btac759-B27","doi-asserted-by":"crossref","first-page":"3313","DOI":"10.1093\/bioinformatics\/btz122","article-title":"Protein model quality assessment using 3D oriented convolutional neural networks","volume":"35","author":"Pag\u00e8s","year":"2019","journal-title":"Bioinformatics"},{"key":"2023010107544976300_btac759-B28","doi-asserted-by":"crossref","first-page":"942","DOI":"10.1021\/acs.jcim.6b00740","article-title":"Protein\u2013ligand scoring with convolutional neural networks","volume":"57","author":"Ragoza","year":"2017","journal-title":"J. Chem. Inf. Model"},{"key":"2023010107544976300_btac759-B29","author":"R\u00e9au","year":"2021"},{"key":"2023010107544976300_btac759-B30","author":"Renaud","year":"2020"},{"key":"2023010107544976300_btac759-B31","doi-asserted-by":"publisher","author":"Renaud","year":"2021","DOI":"10.1101\/2021.01.29.425727"},{"key":"2023010107544976300_btac759-B32","author":"Renaud","year":"2021"},{"key":"2023010107544976300_btac759-B33","author":"Renaud","year":"2021"},{"key":"2023010107544976300_btac759-B35","doi-asserted-by":"crossref","first-page":"e0249404","DOI":"10.1371\/journal.pone.0249404","article-title":"Development of a graph convolutional neural network model for efficient prediction of protein-ligand binding affinities","volume":"16","author":"Son","year":"2021","journal-title":"PLoS One"},{"key":"2023010107544976300_btac759-B36","doi-asserted-by":"crossref","first-page":"4131","DOI":"10.1021\/acs.jcim.9b00628","article-title":"Graph convolutional neural networks for predicting drug-target interactions","volume":"59","author":"Torng","year":"2019","journal-title":"J. Chem. Inf. Model"},{"key":"2023010107544976300_btac759-B37","doi-asserted-by":"crossref","first-page":"3031","DOI":"10.1016\/j.jmb.2015.07.016","article-title":"Updates to the integrated protein-protein interaction benchmarks: docking benchmark version 5 and affinity benchmark version 2","volume":"427","author":"Vreven","year":"2015","journal-title":"J. Mol. Biol"},{"key":"2023010107544976300_btac759-B38","doi-asserted-by":"crossref","first-page":"2113","DOI":"10.1093\/bioinformatics\/btz870","article-title":"Protein docking model evaluation by 3D deep convolutional neural networks","volume":"36","author":"Wang","year":"2020","journal-title":"Bioinformatics"},{"key":"2023010107544976300_btac759-B39","doi-asserted-by":"crossref","first-page":"647915","DOI":"10.3389\/fmolb.2021.647915","article-title":"Protein docking model evaluation by graph neural networks","volume":"8","author":"Wang","year":"2021","journal-title":"Front. Mol. Biosci"},{"key":"2023010107544976300_btac759-B40","doi-asserted-by":"crossref","first-page":"720","DOI":"10.1016\/j.jmb.2015.09.014","article-title":"The HADDOCK2.2 web server: user-friendly integrative modeling of biomolecular complexes","volume":"428","author":"van Zundert","year":"2016","journal-title":"J. Mol. Biol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btac759\/47774027\/btac759.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/1\/btac759\/48448994\/btac759.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/1\/btac759\/48448994\/btac759.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T05:13:25Z","timestamp":1672550005000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btac759\/6845451"}},"subtitle":[],"editor":[{"given":"Lenore","family":"Cowen","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2022,11,24]]},"references-count":38,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,11,24]]},"published-print":{"date-parts":[[2023,1,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btac759","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2021.12.08.471762","asserted-by":"object"}]},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,1,1]]},"published":{"date-parts":[[2022,11,24]]},"article-number":"btac759"}}