{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T04:05:57Z","timestamp":1783483557014,"version":"3.55.0"},"reference-count":31,"publisher":"Oxford University Press (OUP)","issue":"Supplement_1","license":[{"start":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T00:00:00Z","timestamp":1752537600000},"content-version":"vor","delay-in-days":14,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272105"],"award-info":[{"award-number":["62272105"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24A20257"],"award-info":[{"award-number":["U24A20257"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ZJ Lab and Shanghai Center for Brain Science and Brain-Inspired Intelligence Technology","award":["B18015"],"award-info":[{"award-number":["B18015"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,7,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Summary<\/jats:title>\n                  <jats:p>Automated protein function prediction\/annotation (AFP) is vital for understanding biological processes and advancing biomedical research. Existing text-based AFP methods including the state-of-the-art method, GORetriever, rely on expert-curated relevant literature, which is costly and time-consuming, and cover only a small portion of the proteins in UniProt. To overcome this limitation, we propose GOAnnotator, a novel framework for automated protein function annotation. It consists of two key modules: PubRetriever, a hybrid system for retrieving and re-ranking relevant literature, and GORetriever+, an enhanced module for identifying Gene Ontology (GO) terms from the retrieved texts. Extensive experiments over three benchmark datasets demonstrate that GOAnnotator delivers high-quality functional annotations, surpassing GORetriever in realistic situations by uncovering unique literature and predicting additional functions. These results highlight its great potential to streamline and enhance annotation of protein functions without relying on manual curation.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The code and data are available at https:\/\/github.com\/ZhuLab-Fudan\/GOAnnotator.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf199","type":"journal-article","created":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T13:02:54Z","timestamp":1752584574000},"page":"i410-i419","source":"Crossref","is-referenced-by-count":2,"title":["GOAnnotator: accurate protein function annotation using automatically retrieved literature"],"prefix":"10.1093","volume":"41","author":[{"given":"Huiying","family":"Yan","sequence":"first","affiliation":[{"name":"Institute of Science and Technology for Brain-Inspired Intelligence and MOE Frontiers Center for Brain Science, Fudan University , Shanghai 200433,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hancheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Science and Technology for Brain-Inspired Intelligence and MOE Frontiers Center for Brain Science, Fudan University , Shanghai 200433,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaojun","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Science and Technology for Brain-Inspired Intelligence and MOE Frontiers Center for Brain Science, Fudan University , Shanghai 200433,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6067-5312","authenticated-orcid":false,"given":"Shanfeng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Institute of Science and Technology for Brain-Inspired Intelligence and MOE Frontiers Center for Brain Science, Fudan University , Shanghai 200433,","place":["China"]},{"name":"Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence (Fudan University), Ministry of Education , Shanghai, 200433,","place":["China"]},{"name":"Shanghai Key Lab of Intelligent Information Processing and Shanghai Institute of Artificial Intelligence Algorithm, Fudan University , Shanghai, 200433,","place":["China"]},{"name":"Zhangjiang Fudan International Innovation Center , Shanghai 201210,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,7,15]]},"reference":[{"key":"2025071509024599700_btaf199-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":"2025071509024599700_btaf199-B2","doi-asserted-by":"crossref","first-page":"D609","DOI":"10.1093\/nar\/gkae1010","article-title":"UniProt: the universal protein knowledgebase in 2025","volume":"53","year":"2025","journal-title":"Nucleic Acids Res"},{"key":"2025071509024599700_btaf199-B3","doi-asserted-by":"crossref","first-page":"i318","DOI":"10.1093\/bioinformatics\/btad208","article-title":"Combining protein sequences and structures with transformers and equivariant graph neural networks to predict protein function","volume":"39","author":"Boadu","year":"2023","journal-title":"Bioinformatics"},{"key":"2025071509024599700_btaf199-B4","doi-asserted-by":"crossref","first-page":"2825","DOI":"10.1093\/bioinformatics\/btab198","article-title":"TALE: transformer-based protein function annotation with joint sequence\u2013label embedding","volume":"37","author":"Cao","year":"2021","journal-title":"Bioinformatics"},{"key":"2025071509024599700_btaf199-B5","year":"2024"},{"key":"2025071509024599700_btaf199-B6","year":"2025"},{"key":"2025071509024599700_btaf199-B7","doi-asserted-by":"crossref","first-page":"bax081","DOI":"10.1093\/database\/bax081","article-title":"eGenPub, a text mining system for extending computationally mapped bibliography for uniprot knowledgebase by capturing centrality","volume":"2017","author":"Ding","year":"2017","journal-title":"Database"},{"key":"2025071509024599700_btaf199-B8","first-page":"39","author":"Faggioli","year":"2023"},{"key":"2025071509024599700_btaf199-B9","author":"Friedberg","year":"2023"},{"key":"2025071509024599700_btaf199-B10","first-page":"47","article-title":"SWISS-PROT: connecting biomolecular knowledge via a protein database","volume":"3","author":"Gasteiger","year":"2001","journal-title":"Curr Issues Mol Biol"},{"key":"2025071509024599700_btaf199-B11","doi-asserted-by":"crossref","first-page":"3168","DOI":"10.1038\/s41467-021-23303-9","article-title":"Structure-based protein function prediction using graph convolutional networks","volume":"12","author":"Gligorijevi\u0107","year":"2021","journal-title":"Nat Commun"},{"key":"2025071509024599700_btaf199-B12","doi-asserted-by":"crossref","first-page":"D1057","DOI":"10.1093\/nar\/gku1113","article-title":"The GOA database: gene ontology annotation updates for 2015","volume":"43","author":"Huntley","year":"2015","journal-title":"Nucleic Acids Res"},{"key":"2025071509024599700_btaf199-B13","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":"2025071509024599700_btaf199-B14","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":"2025071509024599700_btaf199-B15","doi-asserted-by":"crossref","first-page":"bbab502","DOI":"10.1093\/bib\/bbab502","article-title":"Accurate protein function prediction via graph attention networks with predicted structure information","volume":"23","author":"Lai","year":"2022","journal-title":"Brief Bioinform"},{"key":"2025071509024599700_btaf199-B16","first-page":"708","author":"Nogueira","year":"2020"},{"key":"2025071509024599700_btaf199-B17","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1093\/bib\/3.3.275","article-title":"High-quality protein knowledge resource: SWISS-PROT and TrEMBL","volume":"3","author":"O\u2019Donovan","year":"2002","journal-title":"Brief Bioinformatics"},{"key":"2025071509024599700_btaf199-B18","author":"OpenAI, Achiam J, Adler S","year":"2024"},{"key":"2025071509024599700_btaf199-B19","author":"Qwen, Yang A, Yang B","year":"2025"},{"key":"2025071509024599700_btaf199-B20","doi-asserted-by":"crossref","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":"PNAS"},{"key":"2025071509024599700_btaf199-B21","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1561\/1500000019","article-title":"The probabilistic relevance framework: BM25 and beyond","volume":"3","author":"Robertson","year":"2009","journal-title":"FNT Inf Retriev"},{"key":"2025071509024599700_btaf199-B22","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1002\/asi.4630270302","article-title":"Relevance weighting of search terms","volume":"27","author":"Robertson","year":"1976","journal-title":"J Am Soc Inf Sci"},{"key":"2025071509024599700_btaf199-B23","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1016\/j.gpb.2023.04.001","article-title":"NetGO 3.0: a protein language model improves large-scale functional annotations","volume":"21","author":"Wang","year":"2023","journal-title":"Genomics Proteomics Bioinformatics"},{"key":"2025071509024599700_btaf199-B24","doi-asserted-by":"crossref","first-page":"e3001464","DOI":"10.1371\/journal.pbio.3001464","article-title":"A crowdsourcing open platform for literature curation in UniProt","volume":"19","author":"Wang","year":"2021","journal-title":"PLoS Biol"},{"key":"2025071509024599700_btaf199-B25","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1093\/bioinformatics\/btx541","article-title":"tmVar 2.0: integrating genomic variant information from literature with dbsnp and clinvar for precision medicine","volume":"34","author":"Wei","year":"2018","journal-title":"Bioinformatics"},{"key":"2025071509024599700_btaf199-B26","doi-asserted-by":"crossref","first-page":"W540","DOI":"10.1093\/nar\/gkae235","article-title":"PubTator 3.0: an AI-powered literature resource for unlocking biomedical knowledge","volume":"52","author":"Wei","year":"2024","journal-title":"Nucleic Acids Res"},{"key":"2025071509024599700_btaf199-B27","doi-asserted-by":"crossref","first-page":"ii53","DOI":"10.1093\/bioinformatics\/btae401","article-title":"GORetriever: reranking protein-description-based go candidates by literature-driven deep information retrieval for protein function annotation","volume":"40","author":"Yan","year":"2024","journal-title":"Bioinformatics"},{"key":"2025071509024599700_btaf199-B28","first-page":"8003","author":"Yasunaga","year":"2022"},{"key":"2025071509024599700_btaf199-B29","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.ymeth.2018.05.026","article-title":"DeepText2GO: improving large-scale protein function prediction with deep semantic text representation","volume":"145","author":"You","year":"2018","journal-title":"Methods"},{"key":"2025071509024599700_btaf199-B30","doi-asserted-by":"crossref","first-page":"i262","DOI":"10.1093\/bioinformatics\/btab270","article-title":"DeepGraphGO: graph neural network for large-scale, multispecies protein function prediction","volume":"37","author":"You","year":"2021","journal-title":"Bioinformatics"},{"key":"2025071509024599700_btaf199-B31","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\/article-pdf\/41\/Supplement_1\/i410\/63745489\/btaf199.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/Supplement_1\/i410\/63745489\/btaf199.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T13:02:58Z","timestamp":1752584578000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/41\/Supplement_1\/i410\/8199377"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,1]]},"references-count":31,"journal-issue":{"issue":"Supplement_1","published-print":{"date-parts":[[2025,7,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf199","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,7]]},"published":{"date-parts":[[2025,7,1]]}}}