{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:38:45Z","timestamp":1772933925532,"version":"3.50.1"},"reference-count":92,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11402046","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"8096-8105","source":"Crossref","is-referenced-by-count":0,"title":["Large Language Models for Bioinformatics: Applications and Challenges"],"prefix":"10.1109","author":[{"given":"Wenxi","family":"Zhu","sequence":"first","affiliation":[{"name":"Jinan University,Guangzhou,China,510632"}]},{"given":"Wensheng","family":"Gan","sequence":"additional","affiliation":[{"name":"Jinan University,Guangzhou,China,510632"}]},{"given":"Zhenlian","family":"Qi","sequence":"additional","affiliation":[{"name":"Guangdong Eco-Engineering Polytechnic,Guangzhou,China,510520"}]},{"given":"Philip S.","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Illinois Chicago,Chicago,USA,60607"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386351"},{"issue":"2","key":"ref2","article-title":"A survey of large language models","volume":"1","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS60453.2023.00126"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref7","article-title":"Long range arena: A benchmark for efficient transformers","volume-title":"9th International Conference on Learning Representations","author":"Tay","year":"2021"},{"key":"ref8","first-page":"4171","article-title":"BERT: Pretraining of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2024.09.002"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-024-02318-w"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386291"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiolchem.2025.108535"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-024-02123-4"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00872-0"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.tig.2024.11.013"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btab083"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1002\/pmic.202300011"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1126\/science.ade2574"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1093\/abt\/tbae012"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-32007-7"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jare.2025.02.011"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18632\/aging.205055"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-024-00863-8"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-53081-z"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-021-01252-x"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2016239118"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1872"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3095381"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5681"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btac020"},{"key":"ref31","article-title":"Closer look at efficient inference methods: A survey of speculative decoding","author":"Ryu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3715318"},{"key":"ref33","article-title":"Benchmarking large language models on multiple tasks in bioinformatics NLP with prompting","author":"Jiang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref34","first-page":"1","article-title":"ProGen: Language modeling for protein generation","author":"Madani","year":"2020","journal-title":"Machine Learning for Structural Biology Workshop in NeurIPS"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"issue":"140","key":"ref36","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.184"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2026.3662462"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2025.3609415"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-53759-4"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-024-02487-0"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-60872-5"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00836-4"},{"key":"ref44","article-title":"DNABERT-2: Efficient foundation model and benchmark for multi-species genome","volume-title":"International Conference on Learning Representations","author":"Zhou","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-024-02511-w"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-024-02523-z"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-43651-y"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbaf203"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1126\/science.ads0018"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03819-2"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07487-w"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-49647-6"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-025-02636-z"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.cels.2023.10.001"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-50903-y"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.34133\/research.0721"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1002\/mlf2.12151"},{"key":"ref58","article-title":"ZymCTRL: a conditional language model for the controllable generation of artificial enzymes","author":"Munsamy","year":"2022","journal-title":"Machine Learning in Structural Biology Workshop"},{"key":"ref59","article-title":"Y-Mol: A multiscale biomedical knowledgeguided large language model for drug development","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2021.659622"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108339"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae533"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btad519"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-59628-y"},{"key":"ref65","article-title":"DrugLLM: Open large language model for few-shot molecule generation","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref66","article-title":"Small molecule optimization with large language models","author":"Guevorguian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref67","article-title":"SMILES-Mamba: Chemical mamba foundation models for drug ADMET prediction","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1039\/D2CP05332B"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386743"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1039\/c0ib00070a"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkaa1043"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0028766"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1021\/acscatal.3c02743"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.crimmu.2021.03.002"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-56855-z"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbaa054"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajhg.2024.08.010"},{"key":"ref78","article-title":"Protein language models are biased by unequal sequence sampling across the tree of life","author":"Ding","year":"2024","journal-title":"BioRxiv"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557327"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3712001"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1016\/j.nlp.2025.100174"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-56989-2"},{"key":"ref83","article-title":"Carbon emissions and large neural network training","author":"Patterson","year":"2021","journal-title":"arXiv preprint"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(23)00225-X"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbad493"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103664"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbab506"},{"key":"ref88","article-title":"Jamba: A hybrid transformer-mamba language model","volume-title":"International Conference on Learning Representations","author":"Lieber","year":"2025"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00499-z"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-36559-0"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-025-01042-6"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.4"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11402046.pdf?arnumber=11402046","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T06:55:24Z","timestamp":1772866524000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11402046\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":92,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11402046","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}