{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T18:01:50Z","timestamp":1780682510522,"version":"3.54.1"},"reference-count":51,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T00:00:00Z","timestamp":1780617600000},"content-version":"vor","delay-in-days":35,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2025-23323808"],"award-info":[{"award-number":["RS-2025-23323808"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute of Information & communications Technology Planning & Evaluation"},{"name":"Artificial Intelligence Convergence Innovation Human Resources Development","award":["IITP-2026-RS-2023-00254592"],"award-info":[{"award-number":["IITP-2026-RS-2023-00254592"]}]},{"name":"Korea government"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Protein function prediction is crucial for narrowing the gap between the rapid growth of protein sequences and the limited availability of experimental annotations. In recent years, protein language models (pLMs) that learn representations from large-scale sequence data have emerged as scalable frameworks for modeling protein function. However, most pLMs rely on self-supervised pretraining and struggle to capture correlations among functional labels, which constrains their applicability to annotation-specific tasks. To address this limitation, we present ProtDML, a protein function prediction framework based on distance metric learning that explicitly models label correlations. ProtDML learns a task-specific distance metric using a similarity-weighted pull\u2013push objective designed to encode co-annotation structure. This approach yields a label-aware feature space with improved intra-class compactness and inter-class separability, thereby enhancing the modeling of protein multifunctionality. Furthermore, we introduce a multi-view strategy that integrates complementary sequence-derived protein representations in sequence-only environments. On Pfam multi-label classification, ProtDML outperforms sequence-based baselines by effectively modeling domain co-occurrence patterns and transforming the embedding space into label-distinct clusters with clearer boundaries. Structural generalization on SCOP-based benchmarks demonstrates that ProtDML\u2019s function-informed metric learning can recover latent structural similarities, even without explicit structural supervision. On the CAFA3 benchmark, ProtDML achieves the lowest semantic distance across all ontologies, indicating robust performance in large-scale and imbalanced function prediction. A SARS-CoV-2 case study further illustrates its applicability to real-world viral data. Overall, ProtDML is model-agnostic and complements pretrained pLM embeddings, enabling accurate and scalable sequence-based protein function prediction.<\/jats:p>","DOI":"10.1093\/bib\/bbag293","type":"journal-article","created":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T11:44:09Z","timestamp":1778845449000},"source":"Crossref","is-referenced-by-count":0,"title":["ProtDML: label-aware representation learning for broad-spectrum protein function prediction"],"prefix":"10.1093","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1653-7764","authenticated-orcid":false,"given":"Yejin","family":"Kan","sequence":"first","affiliation":[{"name":"Department of Computer Science and Artificial Intelligence, Dongguk University , 30, Pildong-ro 1-gil, Jung-gu, Seoul 04620 ,","place":["South Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4664-5325","authenticated-orcid":false,"given":"Gangman","family":"Yi","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Artificial Intelligence , Dongguk University, 30, Pildong-ro 1-gil, Jung-gu, Seoul 04620,","place":["South Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,6,5]]},"reference":[{"key":"2026060513172430100_ref1","doi-asserted-by":"crossref","first-page":"D523","DOI":"10.1093\/nar\/gkac1052","article-title":"Uniprot: The universal protein knowledgebase in 2023","volume":"51","author":"The UniProt Consortium","year":"2022","journal-title":"Nucleic Acids Res"},{"key":"2026060513172430100_ref2","doi-asserted-by":"crossref","first-page":"D609","DOI":"10.1093\/nar\/gkae1010","article-title":"Uniprot: The universal protein knowledgebase in 2025","volume":"53","author":"The UniProt Consortium","year":"2024","journal-title":"Nucleic Acids Res"},{"key":"2026060513172430100_ref3","doi-asserted-by":"publisher","first-page":"106446","DOI":"10.1016\/j.compbiomed.2022.106446","article-title":"A systematic review of state-of-the-art strategies for machine learning-based protein function prediction","volume":"154","author":"Yan","year":"2023","journal-title":"Comput Biol Med"},{"key":"2026060513172430100_ref4","doi-asserted-by":"publisher","first-page":"bbae289","DOI":"10.1093\/bib\/bbae289","article-title":"A comprehensive review and comparison of existing computational methods for protein function prediction","volume":"25","author":"Lin","year":"2024","journal-title":"Brief Bioinform"},{"key":"2026060513172430100_ref5","doi-asserted-by":"publisher","first-page":"D638","DOI":"10.1093\/nar\/gkac1000","article-title":"The string database in 2023: protein\u2013protein association networks and functional enrichment analyses for any sequenced genome of interest","volume":"51","author":"Szklarczyk","year":"2022","journal-title":"Nucleic Acids Res"},{"key":"2026060513172430100_ref6","doi-asserted-by":"crossref","first-page":"D520","DOI":"10.1093\/nar\/gky949","article-title":"Protein data bank: the single global archive for 3D macromolecular structure data","volume":"47","author":"wwPDB consortium","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2026060513172430100_ref7","doi-asserted-by":"publisher","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":"2026060513172430100_ref8","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"2026060513172430100_ref9","doi-asserted-by":"publisher","first-page":"7112","DOI":"10.1109\/TPAMI.2021.3095381","article-title":"ProtTrans: toward understanding the language of life through self-supervised learning","volume":"44","author":"Elnaggar","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2026060513172430100_ref10","doi-asserted-by":"publisher","first-page":"2102","DOI":"10.1093\/bioinformatics\/btac020","article-title":"ProteinBERT: a universal deep-learning model of protein sequence and function","volume":"38","author":"Brandes","year":"2022","journal-title":"Bioinformatics"},{"key":"2026060513172430100_ref11","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":"2026060513172430100_ref12","doi-asserted-by":"publisher","first-page":"D330","DOI":"10.1093\/nar\/gky1055","article-title":"The gene ontology resource: 20 years and still going strong","volume":"47","author":"The Gene Ontology Consortium","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2026060513172430100_ref13","article-title":"Distance metric learning for large margin nearest neighbor classification","volume-title":"Advances in Neural Information Processing Systems","author":"Weinberger","year":"2005"},{"key":"2026060513172430100_ref14","first-page":"207","article-title":"Distance metric learning for large margin nearest neighbor classification","volume":"10","author":"Weinberger","year":"2009","journal-title":"J Mach Learn Res"},{"key":"2026060513172430100_ref15","doi-asserted-by":"publisher","first-page":"045049","DOI":"10.1088\/2632-2153\/ad113b","article-title":"Parameter-free basis allocation for efficient multiple metric learning","volume":"4","author":"Kim","year":"2023","journal-title":"Machine Learning: Science and Technology"},{"key":"2026060513172430100_ref16","doi-asserted-by":"publisher","first-page":"D412","DOI":"10.1093\/nar\/gkaa913","article-title":"Pfam: the protein families database in 2021","volume":"49","author":"Mistry","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"2026060513172430100_ref17","doi-asserted-by":"publisher","first-page":"D310","DOI":"10.1093\/nar\/gkt1242","article-title":"SCOP2 prototype: a new approach to protein structure mining","volume":"42","author":"Andreeva","year":"2013","journal-title":"Nucleic Acids Res"},{"key":"2026060513172430100_ref18","doi-asserted-by":"publisher","first-page":"D376","DOI":"10.1093\/nar\/gkz1064","article-title":"The SCOP database in 2020: expanded classification of representative family and superfamily domains of known protein structures","volume":"48","author":"Andreeva","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2026060513172430100_ref19","doi-asserted-by":"publisher","first-page":"1295","DOI":"10.1093\/bioinformatics\/btx780","article-title":"DeepSF: deep convolutional neural network for mapping protein sequences to folds","volume":"34","author":"Hou","year":"2017","journal-title":"Bioinformatics"},{"key":"2026060513172430100_ref20","doi-asserted-by":"crossref","DOI":"10.1101\/676825","article-title":"Evaluating protein transfer learning with TAPE","volume-title":"Advances in Neural Information Processing Systems","author":"Rao","year":"2019"},{"key":"2026060513172430100_ref21","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1038\/nmeth.2340","article-title":"A large-scale evaluation of computational protein function prediction","volume":"10","author":"Radivojac","year":"2013","journal-title":"Nat Methods"},{"key":"2026060513172430100_ref22","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1186\/s13059-016-1037-6","article-title":"An expanded evaluation of protein function prediction methods shows an improvement in accuracy","volume":"17","author":"Jiang","year":"2016","journal-title":"Genome Biol"},{"key":"2026060513172430100_ref23","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1186\/s13059-019-1835-8","article-title":"The CAFA challenge reports improved protein function prediction and new functional annotations for hundreds of genes through experimental screens","volume":"20","author":"Zhou","year":"2019","journal-title":"Genome Biol"},{"key":"2026060513172430100_ref24","doi-asserted-by":"publisher","first-page":"1049","DOI":"10.46234\/ccdcw2021.255","article-title":"Gisaid\u2019s role in pandemic response","volume":"3","author":"Khare","year":"2021","journal-title":"China CDC Wkly"},{"key":"2026060513172430100_ref25","doi-asserted-by":"publisher","first-page":"812","DOI":"10.1016\/j.cell.2020.06.043","article-title":"Tracking changes in SARS-CoV-2 spike: evidence that D614G increases infectivity of the COVID-19 virus","volume":"182","author":"Korber","year":"2020","journal-title":"Cell"},{"key":"2026060513172430100_ref26","doi-asserted-by":"publisher","first-page":"914","DOI":"10.1016\/j.cell.2020.04.011","article-title":"The architecture of SARS-CoV-2 transcriptome","volume":"181","author":"Kim","year":"2025","journal-title":"Cell"},{"key":"2026060513172430100_ref27","doi-asserted-by":"publisher","first-page":"730","DOI":"10.1016\/j.cell.2020.09.018","article-title":"Molecular architecture of the SARS-CoV-2 virus","volume":"183","author":"Yao","year":"2025","journal-title":"Cell"},{"key":"2026060513172430100_ref28","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1002\/prot.1035","article-title":"Prediction of protein cellular attributes using pseudo-amino acid composition","volume":"43","author":"Chou","year":"2001","journal-title":"Proteins"},{"key":"2026060513172430100_ref29","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1016\/j.ab.2012.03.015","article-title":"PseAAC-Builder: a cross-platform stand-alone program for generating various special Chou\u2019s pseudo-amino acid compositions","volume":"425","author":"Pufeng","year":"2012","journal-title":"Anal Biochem"},{"key":"2026060513172430100_ref30","doi-asserted-by":"crossref","first-page":"3495","DOI":"10.3390\/ijms15033495","article-title":"PseAAC-General: fast building various modes of general form of Chou\u2019s pseudo-amino acid composition for large-scale protein datasets","volume":"15","author":"Pufeng","year":"2014","journal-title":"Int J Mol Sci"},{"key":"2026060513172430100_ref31","doi-asserted-by":"publisher","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":"2026060513172430100_ref32","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1016\/S0968-0004(98)01298-5","article-title":"Iterated profile searches with PSI-BLAST\u2014A tool for discovery in protein databases","volume":"23","author":"Altschul","year":"1998","journal-title":"Trends Biochem Sci"},{"key":"2026060513172430100_ref33","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1016\/j.jtbi.2017.01.003","article-title":"Advancing the prediction accuracy of protein-protein interactions by utilizing evolutionary information from position-specific scoring matrix and ensemble classifier","volume":"418","author":"Wang","year":"2017","journal-title":"J Theor Biol"},{"key":"2026060513172430100_ref34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0185587","article-title":"Improved detection of DNA-binding proteins via compression technology on PSSM information","volume":"12","author":"Wang","year":"2017","journal-title":"PLoS One"},{"key":"2026060513172430100_ref35","doi-asserted-by":"publisher","first-page":"03","DOI":"10.1093\/biomethods\/bpac008","article-title":"PSSMCOOL: a comprehensive R package for generating evolutionary-based descriptors of protein sequences from PSSM profiles","volume":"7","author":"Mohammadi","year":"2022","journal-title":"Biol Methods Protoc"},{"key":"2026060513172430100_ref36","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1186\/s12859-021-04223-3","article-title":"FEGS: a novel feature extraction model for protein sequences and its applications","volume":"22","author":"Zengchao","year":"2021","journal-title":"BMC Bioinformatics"},{"key":"2026060513172430100_ref37","doi-asserted-by":"publisher","first-page":"17850","DOI":"10.1609\/aaai.v39i17.33963","article-title":"T-MDML: triplet-based multiple distance metric learning for multi-instance multi-label classification with label correlation","volume":"39","author":"Kim","year":"2025","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2026060513172430100_ref38","doi-asserted-by":"publisher","first-page":"1079","DOI":"10.1109\/TKDE.2010.164","article-title":"Random k-labelsets for multilabel classification","volume":"23","author":"Tsoumakas","year":"2011","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"2026060513172430100_ref39","doi-asserted-by":"publisher","first-page":"2038","DOI":"10.1016\/j.patcog.2006.12.019","article-title":"ML-KNN: a lazy learning approach to multi-label learning","volume":"40","author":"Zhang","year":"2007","journal-title":"Pattern Recogn"},{"key":"2026060513172430100_ref40","first-page":"1","article-title":"Scikit-multilearn: a python library for multi-label classification","volume":"20","author":"Szyma\u0144ski","year":"2019","journal-title":"J Mach Learn Res"},{"key":"2026060513172430100_ref41","doi-asserted-by":"publisher","first-page":"2230","DOI":"10.1093\/nar\/gkn038","article-title":"Phylogenetic classification of short environmental DNA fragments","volume":"36","author":"Krause","year":"2008","journal-title":"Nucleic Acids Res"},{"key":"2026060513172430100_ref42","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbad201","article-title":"MMSMAPlus: a multi-view multi-scale multi-attention embedding model for protein function prediction","volume":"24","author":"Wang","year":"2023","journal-title":"Brief Bioinform"},{"key":"2026060513172430100_ref43","doi-asserted-by":"publisher","first-page":"4319","DOI":"10.1093\/nar\/29.21.4319","article-title":"The Arabidopsis thaliana genome contains at least 29 active genes encoding set domain proteins that can be assigned to four evolutionarily conserved classes","volume":"29","author":"Baumbusch","year":"2001","journal-title":"Nucleic Acids Res"},{"key":"2026060513172430100_ref44","doi-asserted-by":"publisher","first-page":"2692","DOI":"10.1093\/molbev\/msab042","article-title":"Evolution of conserved noncoding sequences in Arabidopsis thaliana","volume":"38","author":"Yocca","year":"2021","journal-title":"Mol Biol Evol"},{"key":"2026060513172430100_ref45","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1038\/s41580-019-0163-x","article-title":"Advances in protein structure prediction and design","volume":"20","author":"Kuhlman","year":"2019","journal-title":"Nat Rev Mol Cell Biol"},{"key":"2026060513172430100_ref46","doi-asserted-by":"publisher","first-page":"1315","DOI":"10.1038\/s41592-019-0598-1","article-title":"Unified rational protein engineering with sequence-based deep representation learning","volume":"16","author":"Alley","year":"2019","journal-title":"Nat Methods"},{"key":"2026060513172430100_ref47","article-title":"Learning protein sequence embeddings using information from structure","volume-title":"International Conference on Learning Representations","author":"Bepler","year":"2019"},{"key":"2026060513172430100_ref48","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1093\/bioinformatics\/btz595","article-title":"DeepGOPlus: improved protein function prediction from sequence","volume":"36","author":"Kulmanov","year":"2019","journal-title":"Bioinformatics"},{"key":"2026060513172430100_ref49","doi-asserted-by":"publisher","first-page":"i53","DOI":"10.1093\/bioinformatics\/btt228","article-title":"Information-theoretic evaluation of predicted ontological annotations","volume":"29","author":"Clark","year":"2013","journal-title":"Bioinformatics"},{"key":"2026060513172430100_ref50","first-page":"233","article-title":"The relationship between precision-recall and ROC curves","volume-title":"Proceedings of the 23rd International Conference on Machine Learning, ICML \u201906","author":"Davis","year":"2006"},{"key":"2026060513172430100_ref51","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1093\/bioinformatics\/btx624","article-title":"DeepGO: predicting protein functions from sequence and interactions using a deep ontology-aware classifier","volume":"34","author":"Kulmanov","year":"2017","journal-title":"Bioinformatics"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/3\/bbag293\/68481867\/bbag293.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/3\/bbag293\/68481867\/bbag293.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T17:17:35Z","timestamp":1780679855000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbag293\/8703112"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":51,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,5,4]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbag293","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,5]]},"published":{"date-parts":[[2026,5]]},"article-number":"bbag293"}}