{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T14:00:52Z","timestamp":1768572052585,"version":"3.49.0"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Singapore Economic Development Board and NVIDIA Singapore via the Industrial Postgraduate Program Ph.D. Scholarship"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3646961","type":"journal-article","created":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T18:42:48Z","timestamp":1766428968000},"page":"217737-217749","source":"Crossref","is-referenced-by-count":0,"title":["PRO-GO: Reference-Guided Protein Sequence Generation Using Gene Ontology Terms"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0773-6105","authenticated-orcid":false,"given":"Darren","family":"Tan","sequence":"first","affiliation":[{"name":"NVIDIA Singapore, Golden Mile Tower, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7111-2008","authenticated-orcid":false,"given":"Ian","family":"McLoughlin","sequence":"additional","affiliation":[{"name":"Singapore Institute of Technology, Punggol Coast Road, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1291-1753","authenticated-orcid":false,"given":"Aik","family":"Beng Ng","sequence":"additional","affiliation":[{"name":"NVIDIA Singapore, Golden Mile Tower, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4554-0791","authenticated-orcid":false,"given":"Zhengkui","family":"Wang","sequence":"additional","affiliation":[{"name":"Singapore Institute of Technology, Punggol Coast Road, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abraham C.","family":"Stern","sequence":"additional","affiliation":[{"name":"NVIDIA Singapore, Golden Mile Tower, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4958-9237","authenticated-orcid":false,"given":"Simon","family":"See","sequence":"additional","affiliation":[{"name":"NVIDIA Singapore, Golden Mile Tower, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbc.2021.100558"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.7554\/elife.96154.2.sa0"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41392-023-01440-5"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/biology12020166"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbad358"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.actbio.2014.01.019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-28313-9"},{"key":"ref8","first-page":"1","article-title":"Flexible and controllable protein design by prefix-tuning large-scale protein language models","author":"Luo","year":"2023","journal-title":"BioRxiv"},{"issue":"1","key":"ref9","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":"Nature Genet."},{"issue":"1","key":"ref10","article-title":"The gene ontology knowledgebase in 2023","volume":"224","author":"Aleksander","year":"2023","journal-title":"Genetics"},{"issue":"1","key":"ref11","doi-asserted-by":"crossref","first-page":"4348","DOI":"10.1038\/s41467-022-32007-7","article-title":"ProtGPT2 is a deep unsupervised language model for protein design","volume":"13","author":"Ferruz","year":"2022","journal-title":"Nature Commun."},{"issue":"11","key":"ref12","doi-asserted-by":"crossref","first-page":"968","DOI":"10.1016\/j.cels.2023.10.002","article-title":"ProGen2: Exploring the boundaries of protein language models","volume":"14","author":"Nijkamp","year":"2023","journal-title":"Cell Syst."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1126\/science.ade2574"},{"key":"ref14","article-title":"ProLLaMA: A protein language model for multi-task protein language processing","author":"Lv","year":"2024","journal-title":"arXiv:2402.16445"},{"issue":"S3","key":"ref15","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1186\/1471-2105-14-S3-S5","article-title":"Protein function prediction using domain families","volume":"14","author":"Rentzsch","year":"2013","journal-title":"BMC Bioinf."},{"key":"ref16","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1007\/978-1-4939-3743-1_9","article-title":"Evaluating functional annotations of enzymes using the gene ontology","volume":"1446","author":"Holliday","year":"2016","journal-title":"Methods Mol. Biol."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1093\/gbe\/evae176"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-80786-0"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btv398"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.64"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btu739"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/28.1.235"},{"issue":"2","key":"ref23","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1038\/s41587-023-01773-0","article-title":"Fast and accurate protein structure search with foldseek","volume":"42","author":"van Kempen","year":"2024","journal-title":"Nature Biotechnol."},{"key":"ref24","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv:2407.21783"},{"key":"ref25","first-page":"1","article-title":"A novel score for highly accurate and efficient prediction of native protein structures","author":"Wu","year":"2020","journal-title":"BioRxiv"},{"issue":"7","key":"ref26","doi-asserted-by":"crossref","first-page":"889","DOI":"10.1093\/bioinformatics\/btq066","article-title":"How significant is a protein structure similarity with TM-score = 0.5?","volume":"26","author":"Xu","year":"2010","journal-title":"Bioinformatics"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1002\/prot.20264"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4121"},{"key":"ref29","article-title":"Lost in the middle: How language models use long contexts","author":"Liu","year":"2023","journal-title":"arXiv:2307.03172"},{"key":"ref30","first-page":"100","article-title":"What makes good in-context examples for GPT-3?","volume-title":"Proc. 3rd Workshop Knowl. Extraction Integr. Deep Learn. Archit.","author":"Liu"},{"key":"ref31","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv:2005.14165"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-9-s5-s4"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11309730.pdf?arnumber=11309730","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:51:01Z","timestamp":1768510261000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11309730\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3646961","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}