{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T09:20:07Z","timestamp":1769851207364,"version":"3.49.0"},"reference-count":31,"publisher":"Oxford University Press (OUP)","issue":"W1","license":[{"start":{"date-parts":[[2022,5,25]],"date-time":"2022-05-25T00:00:00Z","timestamp":1653436800000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000925","name":"National Health and Medical Research Council","doi-asserted-by":"publisher","award":["GNT1174405"],"award-info":[{"award-number":["GNT1174405"]}],"id":[{"id":"10.13039\/501100000925","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000265","name":"Medical Research Council","doi-asserted-by":"publisher","award":["MR\/M026302\/1"],"award-info":[{"award-number":["MR\/M026302\/1"]}],"id":[{"id":"10.13039\/501100000265","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Victorian Government's Operational Infrastructure Support Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,5]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Recent advances in protein structural modelling have enabled the accurate prediction of the holo 3D structures of almost any protein, however protein function is intrinsically linked to the interactions it makes. While a number of computational approaches have been proposed to explore potential biological interactions, they have been limited to specific interactions, and have not been readily accessible for non-experts or use in bioinformatics pipelines. Here we present CSM-Potential, a geometric deep learning approach to identify regions of a protein surface that are likely to mediate protein-protein and protein\u2013ligand interactions in order to provide a link between 3D structure and biological function. Our method has shown robust performance, outperforming existing methods for both predictive tasks. By assessing the performance of CSM-Potential on independent blind tests, we show that our method was able to achieve ROC AUC values of up to 0.81 for the identification of potential protein-protein binding sites, and up to 0.96 accuracy on biological ligand classification. Our method is freely available as a user-friendly and easy-to-use web server and API at http:\/\/biosig.unimelb.edu.au\/csm_potential.<\/jats:p>","DOI":"10.1093\/nar\/gkac381","type":"journal-article","created":{"date-parts":[[2022,5,5]],"date-time":"2022-05-05T11:17:16Z","timestamp":1651749436000},"page":"W204-W209","source":"Crossref","is-referenced-by-count":11,"title":["CSM-Potential: mapping protein interactions and biological ligands in 3D space using geometric deep learning"],"prefix":"10.1093","volume":"50","author":[{"given":"Carlos H M","family":"Rodrigues","sequence":"first","affiliation":[{"name":"Computational Biology and Clinical Informatics, Baker Heart and Diabetes Institute , Melbourne , Victoria , Australia"},{"name":"School of Chemistry and Molecular Biosciences, University of Queensland , Brisbane , Queensland , Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2948-2413","authenticated-orcid":false,"given":"David B","family":"Ascher","sequence":"additional","affiliation":[{"name":"Computational Biology and Clinical Informatics, Baker Heart and Diabetes Institute , Melbourne , Victoria , Australia"},{"name":"School of Chemistry and Molecular Biosciences, University of Queensland , Brisbane , Queensland , Australia"}]}],"member":"286","published-online":{"date-parts":[[2022,5,24]]},"reference":[{"key":"2022070423571724400_B1","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":"2022070423571724400_B2","doi-asserted-by":"crossref","DOI":"10.1101\/2021.10.04.463034","article-title":"Protein complex prediction with AlphaFold-Multimer","author":"Evans","year":"2021"},{"key":"2022070423571724400_B3","doi-asserted-by":"crossref","first-page":"871","DOI":"10.1126\/science.abj8754","article-title":"Accurate prediction of protein structures and interactions using a three-track neural network","volume":"373","author":"Baek","year":"2021","journal-title":"Science"},{"key":"2022070423571724400_B4","doi-asserted-by":"crossref","first-page":"590","DOI":"10.1038\/s41586-021-03828-1","article-title":"Highly accurate protein structure prediction for the human proteome","volume":"596","author":"Tunyasuvunakool","year":"2021","journal-title":"Nature"},{"key":"2022070423571724400_B5","doi-asserted-by":"crossref","first-page":"1841","DOI":"10.1093\/bioinformatics\/btq302","article-title":"Applying the Naive Bayes classifier with kernel density estimation to the prediction of protein-protein interaction sites","volume":"26","author":"Murakami","year":"2010","journal-title":"Bioinformatics"},{"key":"2022070423571724400_B6","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1186\/1471-2105-12-244","article-title":"HomPPI: a class of sequence homology based protein-protein interface prediction methods","volume":"12","author":"Xue","year":"2011","journal-title":"BMC Bioinformatics"},{"key":"2022070423571724400_B7","doi-asserted-by":"crossref","first-page":"630","DOI":"10.1002\/prot.21248","article-title":"Prediction-based fingerprints of protein-protein interactions","volume":"66","author":"Porollo","year":"2007","journal-title":"Proteins"},{"key":"2022070423571724400_B8","doi-asserted-by":"crossref","first-page":"O26","DOI":"10.1186\/1758-2946-6-S1-O26","article-title":"KRIPO - a structure-based pharmacophores approach explains polypharmacological effects","volume":"6","author":"Ritschel","year":"2014","journal-title":"J. Cheminform"},{"key":"2022070423571724400_B9","doi-asserted-by":"crossref","first-page":"2308","DOI":"10.1021\/acs.jcim.5b00534","article-title":"ProBiS-CHARMMing: web interface for prediction and optimization of ligands in protein binding sites","volume":"55","author":"Konc","year":"2015","journal-title":"J. Chem. Inf. Model."},{"key":"2022070423571724400_B10","doi-asserted-by":"crossref","first-page":"607","DOI":"10.1016\/j.jmb.2004.04.012","article-title":"Recognition of functional sites in protein structures","volume":"339","author":"Shulman-Peleg","year":"2004","journal-title":"J. Mol. Biol."},{"key":"2022070423571724400_B11","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":"2022070423571724400_B12","doi-asserted-by":"crossref","first-page":"W285","DOI":"10.1093\/nar\/gku397","article-title":"PRISM: a web server and repository for prediction of protein-protein interactions and modeling their 3D complexes","volume":"42","author":"Baspinar","year":"2014","journal-title":"Nucleic Acids Res."},{"key":"2022070423571724400_B13","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1093\/bioinformatics\/btu626","article-title":"PDB-wide collection of binding data: current status of the PDBbind database","volume":"31","author":"Liu","year":"2015","journal-title":"Bioinformatics"},{"key":"2022070423571724400_B14","doi-asserted-by":"crossref","first-page":"D1140","DOI":"10.1093\/nar\/gkt1043","article-title":"SAbDab: the structural antibody database","volume":"42","author":"Dunbar","year":"2014","journal-title":"Nucleic Acids Res."},{"key":"2022070423571724400_B15","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":"2022070423571724400_B16","doi-asserted-by":"crossref","first-page":"3150","DOI":"10.1093\/bioinformatics\/bts565","article-title":"CD-HIT: accelerated for clustering the next-generation sequencing data","volume":"28","author":"Fu","year":"2012","journal-title":"Bioinformatics"},{"key":"2022070423571724400_B17","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1093\/nar\/28.1.235","article-title":"The protein data bank","volume":"28","author":"Berman","year":"2000","journal-title":"Nucleic Acids Res."},{"key":"2022070423571724400_B18","first-page":"5115","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recogn","author":"Monti","year":"2017"},{"key":"2022070423571724400_B19","doi-asserted-by":"crossref","first-page":"855","DOI":"10.1093\/bioinformatics\/btt058","article-title":"aCSM: noise-free graph-based signatures to large-scale receptor-based ligand prediction","volume":"29","author":"Pires","year":"2013","journal-title":"Bioinformatics"},{"key":"2022070423571724400_B20","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1093\/bioinformatics\/btt691","article-title":"mCSM: predicting the effects of mutations in proteins using graph-based signatures","volume":"30","author":"Pires","year":"2014","journal-title":"Bioinformatics"},{"key":"2022070423571724400_B21","doi-asserted-by":"crossref","first-page":"W417","DOI":"10.1093\/nar\/gkab273","article-title":"mmCSM-PPI: predicting the effects of multiple point mutations on protein-protein interactions","volume":"49","author":"Rodrigues","year":"2021","journal-title":"Nucleic Acids Res."},{"key":"2022070423571724400_B22","doi-asserted-by":"crossref","first-page":"1453","DOI":"10.1093\/bioinformatics\/btz779","article-title":"mCSM-AB2: guiding rational antibody design using graph-based signatures","volume":"36","author":"Myung","year":"2020","journal-title":"Bioinformatics"},{"key":"2022070423571724400_B23","doi-asserted-by":"crossref","first-page":"4066","DOI":"10.1021\/acs.jmedchem.5b00104","article-title":"pkCSM: predicting small-molecule pharmacokinetic and toxicity properties using graph-based signatures","volume":"58","author":"Pires","year":"2015","journal-title":"J. Med. Chem."},{"key":"2022070423571724400_B24","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1016\/0022-2836(71)90324-X","article-title":"The interpretation of protein structures: estimation of static accessibility","volume":"55","author":"Lee","year":"1971","journal-title":"J. Mol. Biol."},{"key":"2022070423571724400_B25","doi-asserted-by":"crossref","first-page":"1195","DOI":"10.1002\/prot.22639","article-title":"Detection of multiscale pockets on protein surfaces using mathematical morphology","volume":"78","author":"Kawabata","year":"2010","journal-title":"Proteins"},{"key":"2022070423571724400_B26","doi-asserted-by":"crossref","first-page":"47","DOI":"10.12688\/f1000research.3-47.v2","article-title":"FeatureViewer, a BioJS component for visualization of position-based annotations in protein sequences","volume":"3","author":"Garcia","year":"2014","journal-title":"F1000Res"},{"key":"2022070423571724400_B27","doi-asserted-by":"crossref","first-page":"3755","DOI":"10.1093\/bioinformatics\/bty419","article-title":"NGL viewer: web-based molecular graphics for large complexes","volume":"34","author":"Rose","year":"2018","journal-title":"Bioinformatics"},{"key":"2022070423571724400_B28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1021\/acs.jcim.7b00425","article-title":"SmilesDrawer: parsing and drawing SMILES-Encoded molecular structures using client-side javascript","volume":"58","author":"Probst","year":"2018","journal-title":"J.\u00a0Chem. Inf. Model"},{"key":"2022070423571724400_B29","doi-asserted-by":"crossref","first-page":"3516","DOI":"10.1016\/j.febslet.2015.10.003","article-title":"Computational prediction of protein interfaces: a review of data driven methods","volume":"589","author":"Xue","year":"2015","journal-title":"FEBS Lett"},{"key":"2022070423571724400_B30","doi-asserted-by":"crossref","first-page":"e1006483","DOI":"10.1371\/journal.pcbi.1006483","article-title":"A benchmark driven guide to binding site comparison: an exhaustive evaluation using tailor-made data sets (ProSPECCTs)","volume":"14","author":"Ehrt","year":"2018","journal-title":"PLoS Comput. Biol."},{"key":"2022070423571724400_B31","first-page":"15272","article-title":"Fast End-to-End Learning on Protein Surfaces","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Sverrisson","year":"2021"}],"container-title":["Nucleic Acids Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/nar\/article-pdf\/50\/W1\/W204\/44376396\/gkac381.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/nar\/article-pdf\/50\/W1\/W204\/44376396\/gkac381.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T02:41:51Z","timestamp":1700534511000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/nar\/article\/50\/W1\/W204\/6591535"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,24]]},"references-count":31,"journal-issue":{"issue":"W1","published-online":{"date-parts":[[2022,5,24]]},"published-print":{"date-parts":[[2022,7,5]]}},"URL":"https:\/\/doi.org\/10.1093\/nar\/gkac381","relation":{},"ISSN":["0305-1048","1362-4962"],"issn-type":[{"value":"0305-1048","type":"print"},{"value":"1362-4962","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,7,5]]},"published":{"date-parts":[[2022,5,24]]}}}