{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T04:10:28Z","timestamp":1779336628156,"version":"3.51.4"},"reference-count":33,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T00:00:00Z","timestamp":1775260800000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2024YFA0919600"],"award-info":[{"award-number":["2024YFA0919600"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["32470704"],"award-info":[{"award-number":["32470704"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies","award":["2022B1212010005"],"award-info":[{"award-number":["2022B1212010005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Although deep learning has significantly advanced the field of protein function prediction, current approaches are limited by their reliance on a narrow set of modalities. Specifically, they primarily rely on sequence patterns and treat protein domain data and functional labels merely as categorical tags. Consequently, they fail to capitalize on the semantic richness embedded within their textual definitions. These constraints hinder their ability to generalize to novel labels. To tackle this issue, we present MZSGO, a multimodal zero-shot framework that fuses evolutionary signals from protein language models with semantic features derived from large language models (LLMs). By employing an adaptive gated fusion mechanism, MZSGO effectively aligns sequence-based and text-based modalities to enable robust predictions for unseen labels.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>By unifying protein representations and functional annotations, we bridge the semantic gap that limits current approaches. Results indicate that while our model remains competitive on supervised benchmarks, it demonstrates a marked advantage over existing methods in zero-shot tasks. It specifically excels at recognizing previously unseen long-tail and novel Gene Ontology (GO) terms.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>The source code and datasets are available at https:\/\/github.com\/toxic-byte\/MZSGO.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btag168","type":"journal-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T11:45:13Z","timestamp":1775130313000},"source":"Crossref","is-referenced-by-count":0,"title":["MZSGO: multimodal zero-shot protein function annotation via evolutionary signals and textual semantics"],"prefix":"10.1093","volume":"42","author":[{"given":"Boyue","family":"Cui","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen) , Shenzhen, Guangdong 518055,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujuan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen) , Shenzhen, Guangdong 518055,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiqu","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen) , Shenzhen, Guangdong 518055,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaming","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen) , Shenzhen, Guangdong 518055,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen) , Shenzhen, Guangdong 518055,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6500-6217","authenticated-orcid":false,"given":"Yadong","family":"Wang","sequence":"additional","affiliation":[{"name":"Center for Bioinformatics, Faculty of Computing, Harbin Institute of Technology , Harbin, Heilongjiang 150001,","place":["China"]},{"name":"Key Laboratory of Biological Bigdata, Ministry of Education, Harbin Institute of Technology , Harbin, Heilongjiang 150001,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8045-5264","authenticated-orcid":false,"given":"Junyi","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen) , Shenzhen, Guangdong 518055,","place":["China"]},{"name":"Key Laboratory of Biological Bigdata, Ministry of Education, Harbin Institute of Technology , Harbin, Heilongjiang 150001,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2026,4,3]]},"reference":[{"key":"2026052023564954900_btag168-B1","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1038\/75556","article-title":"Gene ontology: tool for the unification of biology","volume":"25","author":"Ashburner","year":"2000","journal-title":"Nat Genet"},{"key":"2026052023564954900_btag168-B2"},{"key":"2026052023564954900_btag168-B3","doi-asserted-by":"crossref","first-page":"D444","DOI":"10.1093\/nar\/gkae1082","article-title":"InterPro: the protein sequence classification resource in 2025","volume":"53","author":"Blum","year":"2025","journal-title":"Nucleic Acids Res"},{"key":"2026052023564954900_btag168-B4","first-page":"89","volume-title":"Plant Bioinformatics: Methods and Protocols"},{"key":"2026052023564954900_btag168-B5","doi-asserted-by":"crossref","first-page":"366","DOI":"10.1038\/s41592-021-01101-x","article-title":"Sensitive protein alignments at tree-of-life scale using DIAMOND","volume":"18","author":"Buchfink","year":"2021","journal-title":"Nat Methods"},{"key":"2026052023564954900_btag168-B6","first-page":"669","author":"Chakraborty S, Bisong E, Bhatt S"},{"key":"2026052023564954900_btag168-B7","doi-asserted-by":"crossref","first-page":"btaf170","DOI":"10.1093\/bioinformatics\/btaf170","article-title":"ProtNote: a multimodal method for protein\u2013function annotation","volume":"41","author":"Char","year":"2025","journal-title":"Bioinformatics"},{"key":"2026052023564954900_btag168-B8","doi-asserted-by":"crossref","first-page":"823","DOI":"10.1038\/35015694","article-title":"Protein function in the post-genomic era","volume":"405","author":"Eisenberg","year":"2000","journal-title":"Nature"},{"key":"2026052023564954900_btag168-B9","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1093\/bib\/bbl004","article-title":"Automated protein function prediction\u2014the genomic challenge","volume":"7","author":"Friedberg","year":"2006","journal-title":"Brief Bioinform"},{"key":"2026052023564954900_btag168-B10","doi-asserted-by":"crossref","first-page":"537","DOI":"10.1093\/bioinformatics\/btm628","article-title":"Multiple testing on the directed acyclic graph of gene ontology","volume":"24","author":"Goeman","year":"2008","journal-title":"Bioinformatics"},{"key":"2026052023564954900_btag168-B11"},{"key":"2026052023564954900_btag168-B12","doi-asserted-by":"crossref","first-page":"i217","DOI":"10.1093\/bioinformatics\/btaf178","article-title":"Locality-aware pooling enhances protein language model performance across varied applications","volume":"41","author":"Hoang","year":"2025","journal-title":"Bioinformatics"},{"key":"2026052023564954900_btag168-B13","volume":"39","year":"2023","journal-title":"Bioinformatics"},{"key":"2026052023564954900_btag168-B14","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":"2026052023564954900_btag168-B15"},{"key":"2026052023564954900_btag168-B16","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1038\/s42256-024-00795-w","article-title":"Protein function prediction as approximate semantic entailment","volume":"6","author":"Kulmanov","year":"2024","journal-title":"Nat Mach Intell"},{"key":"2026052023564954900_btag168-B17","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1093\/bioinformatics\/btz595","article-title":"DeepGOPlus: improved protein function prediction from sequence","volume":"36","author":"Kulmanov","year":"2020","journal-title":"Bioinformatics"},{"key":"2026052023564954900_btag168-B18","doi-asserted-by":"crossref","first-page":"i238","DOI":"10.1093\/bioinformatics\/btac256","article-title":"DeepGOZero: improving protein function prediction from sequence and zero-shot learning based on ontology axioms","volume":"38","author":"Kulmanov","year":"2022","journal-title":"Bioinformatics"},{"key":"2026052023564954900_btag168-B19","doi-asserted-by":"crossref","first-page":"bbae077","DOI":"10.1093\/bib\/bbae077","article-title":"Partial order relation-based gene ontology embedding improves protein function prediction","volume":"25","author":"Li","year":"2024","journal-title":"Brief Bioinform"},{"key":"2026052023564954900_btag168-B20","doi-asserted-by":"crossref","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":"2026052023564954900_btag168-B21","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":"Lin","year":"2023","journal-title":"Science"},{"key":"2026052023564954900_btag168-B22","doi-asserted-by":"crossref","first-page":"bbac409","DOI":"10.1093\/bib\/bbac409","article-title":"BioGPT: generative pre-trained transformer for bio-medical text generation and mining","volume":"23","author":"Luo","year":"2022","journal-title":"Brief Bioinform"},{"key":"2026052023564954900_btag168-B23","doi-asserted-by":"crossref","first-page":"4526","DOI":"10.1093\/bioinformatics\/btab485","article-title":"HEMDAG: a family of modular and scalable hierarchical ensemble methods to improve gene ontology term prediction","volume":"37","author":"Notaro","year":"2021","journal-title":"Bioinformatics"},{"key":"2026052023564954900_btag168-B25","author":"Paszke A, Gross S, Massa F"},{"key":"2026052023564954900_btag168-B26","first-page":"1929","volume":"15","author":"Srivastava N, Hinton GE, Krizhevsky A","year":"2014","journal-title":"J Mach Learn Res"},{"key":"2026052023564954900_btag168-B27","first-page":"451"},{"key":"2026052023564954900_btag168-B28","doi-asserted-by":"crossref","first-page":"D609","DOI":"10.1093\/nar\/gkae1010","article-title":"UniProt: the universal protein knowledgebase in 2025","volume":"53","author":"Bateman","year":"2025","journal-title":"Nucleic Acids Res"},{"key":"2026052023564954900_btag168-B29"},{"key":"2026052023564954900_btag168-B30","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1038\/s41467-024-54816-8","article-title":"DPFunc: accurately predicting protein function via deep learning with domain-guided structure information","volume":"16","author":"Wang","year":"2025","journal-title":"Nat Commun"},{"key":"2026052023564954900_btag168-B31","doi-asserted-by":"crossref","first-page":"btaf390","DOI":"10.1093\/bioinformatics\/btaf390","article-title":"ProtGO: universal protein function prediction utilizing multi-modal gene ontology knowledge","volume":"41","author":"Wang","year":"2025","journal-title":"Bioinformatics"},{"key":"2026052023564954900_btag168-B32","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","article-title":"A comprehensive survey on graph neural networks","volume":"32","author":"Wu","year":"2021","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"2026052023564954900_btag168-B33"},{"key":"2026052023564954900_btag168-B34","doi-asserted-by":"crossref","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"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btag168\/67786304\/btag168.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/5\/btag168\/67786304\/btag168.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/5\/btag168\/67786304\/btag168.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T03:57:02Z","timestamp":1779335822000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btag168\/8586736"}},"subtitle":[],"editor":[{"given":"Can","family":"Alkan","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,4,3]]},"references-count":33,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5,3]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag168","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,5]]},"published":{"date-parts":[[2026,4,3]]},"article-number":"btag168"}}