{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T02:56:03Z","timestamp":1787021763932,"version":"build-2736575974"},"reference-count":41,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T00:00:00Z","timestamp":1752624000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the National Social Science Fund of China","award":["Grant No. 23CTJ010"],"award-info":[{"award-number":["Grant No. 23CTJ010"]}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["11991024, 12271071"],"award-info":[{"award-number":["11991024, 12271071"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"the Doctoral Research Project of Chongqing Normal University","award":["Grant No. 21XLB020"],"award-info":[{"award-number":["Grant No. 21XLB020"]}]},{"name":"the China Scholarship Council","award":["No. 202304500006"],"award-info":[{"award-number":["No. 202304500006"]}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>\n                    Ubiquitination is critical in biomedical research. Predicting ubiquitination sites based on deep learning model have advanced the study of ubiquitination. However, traditional supervised model limits in the scenarios where labels are scarcity across species. To address this issue, we introduce EUP, an online webserver for ubiquitination prediction and model interpretation for multi-species. EUP is constructed by extracting lysine site-dependent features from pretrained language model ESM2. Then, utilizing conditional variational inference to reduce the ESM2 features to a lower-dimensional latent representation. By constructing downstream models built on this latent feature representation, EUP exhibited superior performance in predicting ubiquitination sites across species, while maintaining low inference latency. Furthermore, key features for predicting ubiquitination sites were identified across animals, plants, and microbes. The identification of shared key features that capture evolutionarily conserved traits enhances the interpretability of the EUP model for ubiquitination prediction. EUP is free and available at (\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/eup.aibtit.com\/\" xlink:type=\"simple\">https:\/\/eup.aibtit.com\/<\/jats:ext-link>\n                    ).\n                  <\/jats:p>","DOI":"10.1371\/journal.pcbi.1013268","type":"journal-article","created":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T17:31:56Z","timestamp":1752687116000},"page":"e1013268","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":2,"title":["EUP: Enhanced cross-species prediction of ubiquitination sites via a conditional variational autoencoder network based on ESM2"],"prefix":"10.1371","volume":"21","author":[{"given":"Junhao","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeyu","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yawen","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zongqing","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6361-0840","authenticated-orcid":true,"given":"Yu-Juan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,7,16]]},"reference":[{"key":"pcbi.1013268.ref001","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gkx1041","article-title":"iUUCD 2.0: an update with rich annotations for ubiquitin and ubiquitin-like conjugations","volume":"46","author":"J Zhou","year":"2018","journal-title":"Nucleic Acids Res"},{"issue":"7856","key":"pcbi.1013268.ref002","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1038\/s41586-021-03445-y","article-title":"CRL4AMBRA1 is a master regulator of D-type cyclins","volume":"592","author":"D Simoneschi","year":"2021","journal-title":"Nature"},{"issue":"11","key":"pcbi.1013268.ref003","doi-asserted-by":"crossref","first-page":"1008","DOI":"10.1038\/s41557-020-0528-y","article-title":"Lysine acylation using conjugating enzymes for site-specific modification and ubiquitination of recombinant proteins","volume":"12","author":"R Hofmann","year":"2020","journal-title":"Nat Chem"},{"issue":"11","key":"pcbi.1013268.ref004","doi-asserted-by":"crossref","first-page":"2342","DOI":"10.1038\/nprot.2017.105","article-title":"Identification of cross talk between SUMOylation and ubiquitylation using a sequential peptide immunopurification approach","volume":"12","author":"FP McManus","year":"2017","journal-title":"Nat Protoc"},{"issue":"1","key":"pcbi.1013268.ref005","doi-asserted-by":"crossref","first-page":"1181","DOI":"10.1038\/s41467-022-28782-y","article-title":"Ubiquitin and a charged loop regulate the ubiquitin E3 ligase activity of Ark2C","volume":"13","author":"A Paluda","year":"2022","journal-title":"Nat Commun"},{"key":"pcbi.1013268.ref006","doi-asserted-by":"crossref","first-page":"884903","DOI":"10.3389\/fpls.2022.884903","article-title":"A Caps-Ubi Model for Protein Ubiquitination Site Prediction","volume":"13","author":"Y Luo","year":"2022","journal-title":"Front Plant Sci"},{"issue":"22","key":"pcbi.1013268.ref007","doi-asserted-by":"crossref","first-page":"12735","DOI":"10.1073\/pnas.2135500100","article-title":"A subset of membrane-associated proteins is ubiquitinated in response to mutations in the endoplasmic reticulum degradation machinery","volume":"100","author":"AL Hitchcock","year":"2003","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"2","key":"pcbi.1013268.ref008","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbab574","article-title":"GPS-Uber: a hybrid-learning framework for prediction of general and E3-specific lysine ubiquitination sites","volume":"23","author":"C Wang","year":"2022","journal-title":"Brief Bioinform"},{"key":"pcbi.1013268.ref009","article-title":"CPLM 4.0: an updated database with rich annotations for protein lysine modifications","volume":"50","author":"W Zhang","year":"2022","journal-title":"Nucleic Acids Res"},{"issue":"6","key":"pcbi.1013268.ref010","doi-asserted-by":"crossref","first-page":"1115","DOI":"10.24272\/j.issn.2095-8137.2023.263","article-title":"From beasts to bytes: Revolutionizing zoological research with artificial intelligence","volume":"44","author":"Y-J Zhang","year":"2023","journal-title":"Zool Res"},{"key":"pcbi.1013268.ref011","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1007\/s11103-022-01288-3","article-title":"PseAraUbi: predicting arabidopsis ubiquitination sites by incorporating the physico-chemical and structural features","volume":"110","author":"W Wang","year":"2022","journal-title":"Plant Mol Biol"},{"issue":"5","key":"pcbi.1013268.ref012","doi-asserted-by":"crossref","first-page":"661","DOI":"10.1093\/bioinformatics\/btw701","article-title":"ESA-UbiSite: accurate prediction of human ubiquitination sites by identifying a set of effective negatives","volume":"33","author":"J-R Wang","year":"2017","journal-title":"Bioinformatics"},{"issue":"8","key":"pcbi.1013268.ref013","doi-asserted-by":"crossref","first-page":"1461","DOI":"10.1016\/j.bbapap.2013.04.006","article-title":"hCKSAAP_UbSite: improved prediction of human ubiquitination sites by exploiting amino acid pattern and properties","volume":"1834","author":"Z Chen","year":"2013","journal-title":"Biochim Biophys Acta"},{"issue":"7","key":"pcbi.1013268.ref014","doi-asserted-by":"crossref","first-page":"614","DOI":"10.2174\/1574893614666190311141647","article-title":"Prediction of Protein Ubiquitination Sites in Arabidopsis thaliana","volume":"14","author":"J Chen","year":"2019","journal-title":"CBIO"},{"issue":"7","key":"pcbi.1013268.ref015","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0022930","article-title":"Prediction of ubiquitination sites by using the composition of k-spaced amino acid pairs","volume":"6","author":"Z Chen","year":"2011","journal-title":"PLoS One"},{"issue":"6637","key":"pcbi.1013268.ref016","doi-asserted-by":"crossref","first-page":"1123","DOI":"10.1126\/science.ade2574","article-title":"Evolutionary-scale prediction of atomic-level protein structure with a language model","volume":"379","author":"Z Lin","year":"2023","journal-title":"Science"},{"issue":"8","key":"pcbi.1013268.ref017","doi-asserted-by":"crossref","first-page":"2102","DOI":"10.1093\/bioinformatics\/btac020","article-title":"ProteinBERT: a universal deep-learning model of protein sequence and function","volume":"38","author":"N Brandes","year":"2022","journal-title":"Bioinformatics"},{"key":"pcbi.1013268.ref018","volume-title":"Advances in Neural Information Processing Systems","author":"A Vaswani","year":"2017"},{"issue":"1","key":"pcbi.1013268.ref019","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1038\/s41594-022-00866-9","article-title":"Genetic code expansion reveals aminoacylated lysine ubiquitination mediated by UBE2W","volume":"30","author":"J Zang","year":"2023","journal-title":"Nat Struct Mol Biol"},{"key":"pcbi.1013268.ref020","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"K He","year":"2016"},{"key":"pcbi.1013268.ref021","article-title":"Auto-encoding variational bayes.","author":"DP Kingma","year":"2013"},{"issue":"2","key":"pcbi.1013268.ref022","article-title":"Interpretable feature extraction and dimensionality reduction in ESM2 for protein localization prediction","volume":"25","author":"Z Luo","year":"2024","journal-title":"Brief Bioinform"},{"issue":"4","key":"pcbi.1013268.ref023","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbae314","article-title":"Comprehensive single-cell RNA-seq analysis using deep interpretable generative modeling guided by biological hierarchy knowledge","volume":"25","author":"H Chen","year":"2024","journal-title":"Brief Bioinform"},{"issue":"6736","key":"pcbi.1013268.ref024","doi-asserted-by":"crossref","first-page":"850","DOI":"10.1126\/science.ads0018","article-title":"Simulating 500 million years of evolution with a language model","volume":"387","author":"T Hayes","year":"2025","journal-title":"Science"},{"issue":"13","key":"pcbi.1013268.ref025","doi-asserted-by":"crossref","first-page":"1658","DOI":"10.1093\/bioinformatics\/btl158","article-title":"Cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences","volume":"22","author":"W Li","year":"2006","journal-title":"Bioinformatics"},{"key":"pcbi.1013268.ref026","volume-title":"Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining","author":"T Akiba","year":"2019"},{"key":"pcbi.1013268.ref027","author":"K Agustianto","year":"2019"},{"issue":"1","key":"pcbi.1013268.ref028","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1186\/s13040-023-00322-4","volume":"16","author":"D Chicco","year":"2023","journal-title":"BioData Min"},{"issue":"1","key":"pcbi.1013268.ref029","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbac606","article-title":"AFP-MFL: accurate identification of antifungal peptides using multi-view feature learning","volume":"24","author":"Y Fang","year":"2023","journal-title":"Brief Bioinform"},{"key":"pcbi.1013268.ref030","first-page":"3319","volume-title":"Proceedings of the 34th International Conference on Machine Learning","author":"M Sundararajan","year":"2017"},{"issue":"2","key":"pcbi.1013268.ref031","article-title":"Interpretable feature extraction and dimensionality reduction in ESM2 for protein localization prediction","volume":"25","author":"Z Luo","year":"2024","journal-title":"Brief Bioinform"},{"issue":"11","key":"pcbi.1013268.ref032","doi-asserted-by":"crossref","first-page":"1389","DOI":"10.1109\/LSP.2014.2337313","article-title":"Fast Implementation of DeLong\u2019s Algorithm for Comparing the Areas Under Correlated Receiver Operating Characteristic Curves","volume":"21","author":"X Sun","year":"2014","journal-title":"IEEE Signal Process Lett"},{"issue":"5","key":"pcbi.1013268.ref033","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3236009","article-title":"A Survey of Methods for Explaining Black Box Models","volume":"51","author":"R Guidotti","year":"2018","journal-title":"ACM Comput Surv"},{"key":"pcbi.1013268.ref034","volume-title":"Local interpretable model-agnostic explanations for music content analysis","author":"S Mishra","year":"2017"},{"issue":"8","key":"pcbi.1013268.ref035","doi-asserted-by":"crossref","first-page":"880","DOI":"10.1016\/j.tplants.2023.03.008","article-title":"Role of ubiquitination in arsenic tolerance in plants","volume":"28","author":"J Zhang","year":"2023","journal-title":"Trends Plant Sci"},{"key":"pcbi.1013268.ref036","unstructured":"Lindsey J, Gurnee W, Ameisen E, Chen B, Pearce A, Turner NL. On the biology of a large language model. Transformer Circuits Thread. 2025."},{"issue":"1","key":"pcbi.1013268.ref037","doi-asserted-by":"crossref","first-page":"1914","DOI":"10.1038\/s41467-022-29443-w","article-title":"Learning meaningful representations of protein sequences","volume":"13","author":"NS Detlefsen","year":"2022","journal-title":"Nat Commun"},{"key":"pcbi.1013268.ref038","article-title":"Simulating 500 million years of evolution with a language model","author":"T Hayes","year":"2024","journal-title":"bioRxiv"},{"issue":"1","key":"pcbi.1013268.ref039","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1186\/s12859-023-05549-w","article-title":"Protein language models can capture protein quaternary state","volume":"24","author":"O Avraham","year":"2023","journal-title":"BMC Bioinformatics"},{"issue":"9","key":"pcbi.1013268.ref040","doi-asserted-by":"crossref","DOI":"10.1093\/gigascience\/giab058","article-title":"Scalable analysis of multi-modal biomedical data","volume":"10","author":"J Smith","year":"2021","journal-title":"Gigascience"},{"issue":"12","key":"pcbi.1013268.ref041","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btad718","article-title":"DeepProSite: structure-aware protein binding site prediction using ESMFold and pretrained language model","volume":"39","author":"Y Fang","year":"2023","journal-title":"Bioinformatics"}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1013268","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T17:32:04Z","timestamp":1752687124000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1013268"}},"subtitle":[],"editor":[{"given":"Yu","family":"Xue","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,7,16]]},"references-count":41,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2025,7,16]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1013268","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,16]]}}}