{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T10:01:07Z","timestamp":1792749667465,"version":"4.5.0"},"reference-count":34,"publisher":"Oxford University Press (OUP)","issue":"13","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62071278"],"award-info":[{"award-number":["62071278"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,6,27]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Summary<\/jats:title>\n                    <jats:p>Identifying the protein\u2013peptide binding residues is fundamentally important to understand the mechanisms of protein functions and explore drug discovery. Although several computational methods have been developed, most of them highly rely on third-party tools or complex data preprocessing for feature design, easily resulting in low computational efficacy and suffering from low predictive performance. To address the limitations, we propose PepBCL, a novel BERT (Bidirectional Encoder Representation from Transformers) -based contrastive learning framework to predict the protein\u2013peptide binding residues based on protein sequences only. PepBCL is an end-to-end predictive model that is independent of feature engineering. Specifically, we introduce a well pre-trained protein language model that can automatically extract and learn high-latent representations of protein sequences relevant for protein structures and functions. Further, we design a novel contrastive learning module to optimize the feature representations of binding residues underlying the imbalanced dataset. We demonstrate that our proposed method significantly outperforms the state-of-the-art methods under benchmarking comparison, and achieves more robust performance. Moreover, we found that we further improve the performance via the integration of traditional features and our learnt features. Interestingly, the interpretable analysis of our model highlights the flexibility and adaptability of deep learning-based protein language model to capture both conserved and non-conserved sequential characteristics of peptide-binding residues. Finally, to facilitate the use of our method, we establish an online predictive platform as the implementation of the proposed PepBCL, which is now available at http:\/\/server.wei-group.net\/PepBCL\/.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>https:\/\/github.com\/Ruheng-W\/PepBCL.<\/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\/btac352","type":"journal-article","created":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T08:38:08Z","timestamp":1653295088000},"page":"3351-3360","source":"Crossref","is-referenced-by-count":97,"title":["Predicting protein\u2013peptide binding residues via interpretable deep learning"],"prefix":"10.1093","volume":"38","author":[{"given":"Ruheng","family":"Wang","sequence":"first","affiliation":[{"name":"Shandong University School of Software, , Jinan 250101, China"},{"name":"Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR), Shandong University , Jinan 250101, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junru","family":"Jin","sequence":"additional","affiliation":[{"name":"Shandong University School of Software, , Jinan 250101, China"},{"name":"Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR), Shandong University , Jinan 250101, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6406-1142","authenticated-orcid":false,"given":"Quan","family":"Zou","sequence":"additional","affiliation":[{"name":"Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China , Chengdu 610054, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8721-8883","authenticated-orcid":false,"given":"Kenta","family":"Nakai","sequence":"additional","affiliation":[{"name":"Human Genome Center, Institute of Medical Science, The University of Tokyo , Tokyo 108-8639, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1444-190X","authenticated-orcid":false,"given":"Leyi","family":"Wei","sequence":"additional","affiliation":[{"name":"Shandong University School of Software, , Jinan 250101, China"},{"name":"Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR), Shandong University , Jinan 250101, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2022,5,23]]},"reference":[{"key":"2023041408095859500_","author":"Abdin","year":"2020"},{"key":"2023041408095859500_","doi-asserted-by":"crossref","first-page":"3389","DOI":"10.1093\/nar\/25.17.3389","article-title":"Gapped BLAST and PSI-BLAST: a new generation of protein database search programs","volume":"25","author":"Altschul","year":"1997","journal-title":"Nucleic Acids Res"},{"key":"2023041408095859500_","first-page":"1","article-title":"Predicting protein\u2013ligand and protein\u2013peptide interfaces","volume":"129","author":"Bertolazzi","year":"2014","journal-title":"Eur. Phys. J"},{"key":"2023041408095859500_","first-page":"1597","author":"Chen","year":"2020"},{"key":"2023041408095859500_","doi-asserted-by":"crossref","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach","volume":"44","author":"DeLong","year":"1988","journal-title":"Biometrics"},{"key":"2023041408095859500_","author":"Devlin","year":"2018"},{"key":"2023041408095859500_","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1038\/nrm1589","article-title":"Intrinsically unstructured proteins and their functions","volume":"6","author":"Dyson","year":"2005","journal-title":"Nat. Rev. Mol. Cell Biol"},{"key":"2023041408095859500_","first-page":"1","article-title":"ProtTrans: towards cracking the language of life\u2019s code through self-supervised deep learning and high performance computing","author":"Elnaggar","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"2023041408095859500_","first-page":"61","author":"Gao","year":"2020"},{"key":"2023041408095859500_","doi-asserted-by":"crossref","first-page":"107857","DOI":"10.1016\/j.carres.2019.107857","article-title":"StackCBPred: a stacking based prediction of protein\u2013carbohydrate binding sites from sequence","volume":"486","author":"Gattani","year":"2019","journal-title":"Carbohydrate Res"},{"key":"2023041408095859500_","first-page":"9729","author":"He","year":"2020"},{"key":"2023041408095859500_","first-page":"2577","article-title":"Dictionary of protein secondary structure: pattern recognition of hydrogen-bonded and geometrical features","volume":"22","author":"Kabsch","year":"1983","journal-title":"Biopolym. Original Res. Biomol"},{"key":"2023041408095859500_","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1007\/s13312-011-0055-4","article-title":"Receiver operating characteristic (ROC) curve for medical researchers","volume":"48","author":"Kumar","year":"2011","journal-title":"Indian Pediatrics"},{"key":"2023041408095859500_","doi-asserted-by":"crossref","first-page":"2096","DOI":"10.1002\/prot.24422","article-title":"Detection of peptide-binding sites on protein surfaces: the first step toward the modeling and targeting of peptide-mediated interactions","volume":"81","author":"Lavi","year":"2013","journal-title":"Proteins Struct. Funct. Bioinf"},{"key":"2023041408095859500_","doi-asserted-by":"crossref","first-page":"W431","DOI":"10.1093\/nar\/gkv495","article-title":"GalaxyPepDock: a protein\u2013peptide docking tool based on interaction similarity and energy optimization","volume":"43","author":"Lee","year":"2015","journal-title":"Nucleic Acids Res"},{"key":"2023041408095859500_","doi-asserted-by":"crossref","first-page":"2757","DOI":"10.1093\/bioinformatics\/bty1047","article-title":"mAHTPred: a sequence-based Meta-predictor for improving the prediction of anti-hypertensive peptides using effective feature representation","volume":"35","author":"Manavalan","year":"2019","journal-title":"Bioinformatics"},{"key":"2023041408095859500_","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1016\/j.omtn.2019.04.019","article-title":"Meta-4mCpred: a sequence-based meta-predictor for accurate DNA 4mC site prediction using effective feature representation","volume":"16","author":"Manavalan","year":"2019","journal-title":"Mol. Therapy Nucleic Acids"},{"key":"2023041408095859500_","doi-asserted-by":"crossref","first-page":"e1004639","DOI":"10.1371\/journal.pcbi.1004639","article-title":"A large-scale assessment of nucleic acids binding site prediction programs","volume":"11","author":"Miao","year":"2015","journal-title":"PLoS Comput. Biol"},{"key":"2023041408095859500_","doi-asserted-by":"crossref","first-page":"e405","DOI":"10.1371\/journal.pbio.0030405","article-title":"Systematic discovery of new recognition peptides mediating protein interaction networks","volume":"3","author":"Neduva","year":"2005","journal-title":"PLoS Biol"},{"key":"2023041408095859500_","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1126\/science.1083653","article-title":"Assembly of cell regulatory systems through protein interaction domains","volume":"300","author":"Pawson","year":"2003","journal-title":"Science"},{"key":"2023041408095859500_","doi-asserted-by":"crossref","first-page":"e1000335","DOI":"10.1371\/journal.pcbi.1000335","article-title":"Accurate prediction of peptide binding sites on protein surfaces","volume":"5","author":"Petsalaki","year":"2009","journal-title":"PLoS Comput. Biol"},{"key":"2023041408095859500_","first-page":"505","article-title":"Peptidic modulators of protein-protein interactions: progress and challenges in computational design","volume":"91","author":"Rubinstein","year":"2009","journal-title":"Biopolym. Original Res. Biomol"},{"key":"2023041408095859500_","doi-asserted-by":"crossref","first-page":"11399","DOI":"10.1038\/s41598-019-47765-6","article-title":"DeepInsight: a methodology to transform a non-image data to an image for convolution neural network architecture","volume":"9","author":"Sharma","year":"2019","journal-title":"Sci. Rep"},{"key":"2023041408095859500_","doi-asserted-by":"crossref","first-page":"bbab297","DOI":"10.1093\/bib\/bbab297","article-title":"DeepFeature: feature selection in nonimage data using convolutional neural network","volume":"22","author":"Sharma","year":"2021","journal-title":"Brief. Bioinformatics"},{"key":"2023041408095859500_","doi-asserted-by":"crossref","first-page":"3464","DOI":"10.1093\/bioinformatics\/btab316","article-title":"SPOT-1D-Single: improving the single-sequence-based prediction of protein secondary structure, backbone angles, solvent accessibility and half-sphere exposures using a large training set and ensembled deep learning","volume":"37","author":"Singh","year":"2021","journal-title":"Bioinformatics"},{"key":"2023041408095859500_","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1038\/s41592-019-0437-4","article-title":"Protein-level assembly increases protein sequence recovery from metagenomic samples manyfold","volume":"16","author":"Steinegger","year":"2019","journal-title":"Nat. Methods"},{"key":"2023041408095859500_","doi-asserted-by":"crossref","first-page":"1223","DOI":"10.1002\/jcc.24314","article-title":"Sequence-based prediction of protein\u2013peptide binding sites using support vector machine","volume":"37","author":"Taherzadeh","year":"2016","journal-title":"J. Comput. Chem"},{"key":"2023041408095859500_","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1093\/bioinformatics\/btx614","article-title":"Structure-based prediction of protein\u2013peptide binding regions using Random Forest","volume":"34","author":"Taherzadeh","year":"2018","journal-title":"Bioinformatics"},{"key":"2023041408095859500_","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.drudis.2009.10.009","article-title":"Synthetic therapeutic peptides: science and market","volume":"15","author":"Vlieghe","year":"2010","journal-title":"Drug Discov. Today"},{"key":"2023041408095859500_","doi-asserted-by":"crossref","first-page":"110278","DOI":"10.1016\/j.jtbi.2020.110278","article-title":"Predicting protein\u2013peptide binding sites with a deep convolutional neural network","volume":"496","author":"Wardah","year":"2020","journal-title":"J. Theor. Biol"},{"key":"2023041408095859500_","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1016\/j.tibs.2012.05.001","article-title":"Linear motifs: lost in (pre) translation","volume":"37","author":"Weatheritt","year":"2012","journal-title":"Trends Biochem. Sci"},{"key":"2023041408095859500_","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1093\/bib\/bbv023","article-title":"A comprehensive comparative review of sequence-based predictors of DNA-and RNA-binding residues","volume":"17","author":"Yan","year":"2016","journal-title":"Brief. Bioinf"},{"key":"2023041408095859500_","doi-asserted-by":"crossref","first-page":"821","DOI":"10.1093\/bib\/bbx022","article-title":"Review and comparative assessment of sequence-based predictors of protein-binding residues","volume":"19","author":"Zhang","year":"2018","journal-title":"Brief. Bioinf"},{"key":"2023041408095859500_","doi-asserted-by":"crossref","first-page":"1459","DOI":"10.1021\/acs.jcim.8b00019","article-title":"Improving sequence-based prediction of protein\u2013peptide binding residues by introducing intrinsic disorder and a consensus method","volume":"58","author":"Zhao","year":"2018","journal-title":"J. Chem. Inf. Model"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btac352\/43882794\/btac352.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/13\/3351\/49884361\/btac352.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/13\/3351\/49884361\/btac352.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T21:07:32Z","timestamp":1700600852000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/38\/13\/3351\/6590647"}},"subtitle":[],"editor":[{"given":"Lenore","family":"Cowen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":34,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2022,6,27]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btac352","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,7,1]]},"published":{"date-parts":[[2022,5,23]]}}}