{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T21:48:58Z","timestamp":1791841738680,"version":"4.3.4"},"reference-count":27,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T00:00:00Z","timestamp":1790726400000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100021520","name":"National Supercomputing Center","doi-asserted-by":"publisher","award":["KSC-2023-CRE-0532"],"award-info":[{"award-number":["KSC-2023-CRE-0532"]}],"id":[{"id":"10.13039\/501100021520","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korean government Ministry of Science and ICT","award":["RS-2025-02214037"],"award-info":[{"award-number":["RS-2025-02214037"]}],"id":[{"id":"https:\/\/ror.org\/01wpjm123","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Korean government Ministry of Science and ICT","award":["RS-2021-NR057690"],"award-info":[{"award-number":["RS-2021-NR057690"]}],"id":[{"id":"https:\/\/ror.org\/01wpjm123","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,10,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Anti-CRISPR (Acr) proteins inhibit CRISPR-Cas immunity and are key targets for precise control of CRISPR-based genome editing and phage\u2013host coevolution research. Their experimental identification is costly and low-throughput, so computational predictors are used to prioritise candidates for testing. In this setting validated positives number in the hundreds while phage-derived putative negatives reach tens of thousands, producing extreme class imbalance. Yet existing classification-based predictors train and evaluate on 1:1 balanced datasets and allow high-similarity sequences between training and test, overestimating real-world performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We present AcrSeek, a metric-learning framework that trains a projection head over a frozen protein language model (PLM) encoder with hybrid negative mining (offline global plus online semi-hard) under a joint triplet\u2013focal objective. Under nested 5-fold cross-validation with leakage controlled by 40% identity clustering, AcrSeek improved AUPRC on the imbalanced (1:383) test set from 0.017 to 0.355 over AcrNET (matched PLM backbone), reaching 0.508 with ESM-2 3B. AcrSeek therefore remains structurally robust under extreme class imbalance and may also serve other protein-function detection problems with scarce positives.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>Source code at https:\/\/github.com\/jeongchans\/acrseek, archived at Zenodo (DOI: 10.5281\/zenodo.21946803); data and model checkpoints at Zenodo (DOI: 10.5281\/zenodo.20115442).<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btag729","type":"journal-article","created":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T11:21:09Z","timestamp":1790594469000},"source":"Crossref","is-referenced-by-count":0,"title":["AcrSeek: metric learning with hybrid negative mining for anti-CRISPR protein detection under extreme class imbalance"],"prefix":"10.1093","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1910-8970","authenticated-orcid":false,"given":"Chan-Seok","family":"Jeong","sequence":"first","affiliation":[{"name":"Division of National Supercomputing, Korea Institute of Science and Technology Information , Daejeon,","place":["Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,9,29]]},"reference":[{"key":"2026101217270743700_btag729-B1","author":"Abnar","year":"2020"},{"key":"2026101217270743700_btag729-B2","author":"Abraham","year":"2019"},{"key":"2026101217270743700_btag729-B3","author":"Achtibat","year":"2024"},{"key":"2026101217270743700_btag729-B4","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1016\/S0022-2836(05)80360-2","article-title":"Basic local alignment search tool","volume":"215","author":"Altschul","year":"1990","journal-title":"J Mol Biol"},{"key":"2026101217270743700_btag729-B5","doi-asserted-by":"publisher","first-page":"W16","DOI":"10.1093\/nar\/gkw387","article-title":"PHASTER: a better, faster version of the PHAST phage search tool","volume":"44","author":"Arndt","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2026101217270743700_btag729-B6","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1038\/nature11723","article-title":"Bacteriophage genes that inactivate the CRISPR\/Cas bacterial immune system","volume":"493","author":"Bondy-Denomy","year":"2013","journal-title":"Nature"},{"key":"2026101217270743700_btag729-B7","author":"Davis","year":"2006"},{"key":"2026101217270743700_btag729-B8","doi-asserted-by":"publisher","first-page":"D393","DOI":"10.1093\/nar\/gkx835","article-title":"Anti-crisprdb: A comprehensive online resource for anti-CRISPR proteins","volume":"46","author":"Dong","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2026101217270743700_btag729-B9","doi-asserted-by":"publisher","first-page":"4698","DOI":"10.1093\/nar\/gkaa219","article-title":"Machine learning predicts new anti-CRISPR proteins","volume":"48","author":"Eitzinger","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"2026101217270743700_btag729-B10","doi-asserted-by":"publisher","first-page":"3784","DOI":"10.1038\/s41467-020-17652-0","article-title":"Machine-learning approach expands the repertoire of anti-CRISPR protein families","volume":"11","author":"Gussow","year":"2020","journal-title":"Nat Commun"},{"key":"2026101217270743700_btag729-B11","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btad259","article-title":"AcrNET: predicting anti-CRISPR WITH deep learning","volume":"39","author":"Li","year":"2023","journal-title":"Bioinformatics"},{"key":"2026101217270743700_btag729-B12","author":"Lin","year":"2017"},{"key":"2026101217270743700_btag729-B13","doi-asserted-by":"publisher","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":"Lin","year":"2023","journal-title":"Science"},{"key":"2026101217270743700_btag729-B14","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1038\/s41579-019-0299-x","article-title":"Evolutionary classification of CRISPR-Cas systems: a burst of class 2 and derived variants","volume":"18","author":"Makarova","year":"2020","journal-title":"Nat Rev Microbiol"},{"key":"2026101217270743700_btag729-B15","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1038\/s41592-020-0771-6","article-title":"Anti-CRISPR protein applications: natural brakes for CRISPR-Cas technologies","volume":"17","author":"Marino","year":"2020","journal-title":"Nat Methods"},{"key":"2026101217270743700_btag729-B16","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1016\/j.molcel.2020.09.015","article-title":"A type I-F anti-CRISPR protein inhibits the CRISPR-Cas surveillance complex by ADP-ribosylation","volume":"80","author":"Niu","year":"2020","journal-title":"Mol Cell"},{"key":"2026101217270743700_btag729-B17","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1038\/nrmicro.2017.120","article-title":"Anti-CRISPR: discovery, mechanism and function","volume":"16","author":"Pawluk","year":"2018","journal-title":"Nat Rev Microbiol"},{"key":"2026101217270743700_btag729-B18","doi-asserted-by":"publisher","first-page":"e2016239118","DOI":"10.1073\/pnas.2016239118","article-title":"Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences","volume":"118","author":"Rives","year":"2021","journal-title":"Proc Natl Acad Sci U S A"},{"key":"2026101217270743700_btag729-B19","doi-asserted-by":"publisher","first-page":"e0118432","DOI":"10.1371\/journal.pone.0118432","article-title":"The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets","volume":"10","author":"Saito","year":"2015","journal-title":"PLoS One"},{"key":"2026101217270743700_btag729-B20","author":"Schroff","year":"2015"},{"key":"2026101217270743700_btag729-B21","doi-asserted-by":"publisher","first-page":"1026","DOI":"10.1038\/nbt.3988","article-title":"MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets","volume":"35","author":"Steinegger","year":"2017","journal-title":"Nat Biotechnol"},{"key":"2026101217270743700_btag729-B22","author":"Vig","year":"2021"},{"key":"2026101217270743700_btag729-B23","doi-asserted-by":"publisher","first-page":"2714","DOI":"10.1016\/j.molcel.2022.05.003","article-title":"Anti-CRISPR prediction using deep learning reveals an inhibitor of Cas13b nucleases","volume":"82","author":"Wandera","year":"2022","journal-title":"Mol Cell"},{"key":"2026101217270743700_btag729-B24","doi-asserted-by":"publisher","first-page":"W348","DOI":"10.1093\/nar\/gkaa432","article-title":"PaCRISPR: A server for predicting and visualizing anti-CRISPR proteins","volume":"48","author":"Wang","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"2026101217270743700_btag729-B25","author":"Wu","year":"2017"},{"key":"2026101217270743700_btag729-B26","doi-asserted-by":"publisher","first-page":"4544","DOI":"10.1109\/JBHI.2024.3350666","article-title":"GraphCL-DTA: a graph contrastive learning with molecular semantics for drug-target binding affinity prediction","volume":"28","author":"Yang","year":"2024","journal-title":"IEEE J Biomed Health Inform"},{"key":"2026101217270743700_btag729-B27","doi-asserted-by":"publisher","first-page":"1358","DOI":"10.1126\/science.adf2465","article-title":"Enzyme function prediction using contrastive learning","volume":"379","author":"Yu","year":"2023","journal-title":"Science"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btag729\/71476225\/btag729.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/10\/btag729\/71476225\/btag729.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/10\/btag729\/71476225\/btag729.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T21:27:14Z","timestamp":1791840434000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btag729\/8847223"}},"subtitle":[],"editor":[{"given":"Pier Luigi","family":"Martelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,29]]},"references-count":27,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2026,10,2]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag729","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,10]]},"published":{"date-parts":[[2026,9,29]]},"article-number":"btag729"}}