{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T00:09:42Z","timestamp":1778458182469,"version":"3.51.4"},"publisher-location":"New York, NY","reference-count":38,"publisher":"Springer US","isbn-type":[{"value":"9781071652633","type":"print"},{"value":"9781071652640","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-1-0716-5264-0_17","type":"book-chapter","created":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T23:53:39Z","timestamp":1778457219000},"page":"321-329","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["RNA Large Language Models in Virology"],"prefix":"10.1007","author":[{"given":"Weiwei","family":"Shen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liucun","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixue","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,5,1]]},"reference":[{"issue":"3","key":"17_CR1","doi-asserted-by":"publisher","first-page":"220","DOI":"10.3390\/v11030220","volume":"11","author":"C Retel","year":"2019","unstructured":"Retel C, M\u00e4rkle H, Becks L, Feulner PGD (2019) Ecological and evolutionary processes shaping viral genetic diversity. Viruses 11(3):220","journal-title":"Viruses"},{"issue":"4","key":"17_CR2","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1016\/j.tree.2007.11.010","volume":"23","author":"R Belshaw","year":"2008","unstructured":"Belshaw R, Gardner A, Rambaut A, Pybus OG (2008) Pacing a small cage: mutation and RNA viruses. Trends Ecol Evol 23(4):188\u2013193. https:\/\/doi.org\/10.1016\/j.tree.2007.11.010","journal-title":"Trends Ecol Evol"},{"key":"17_CR3","doi-asserted-by":"publisher","unstructured":"Zwart MP, Kupczok A, Iranzo J (2023) Editorial: predicting virus evolution: from genome evolution to epidemiological trends. Front Virol 3. https:\/\/doi.org\/10.3389\/fviro.2023.1215709","DOI":"10.3389\/fviro.2023.1215709"},{"key":"17_CR4","doi-asserted-by":"publisher","unstructured":"Lewitter F, Notredame C (2007) Recent evolutions of multiple sequence alignment algorithms. PLoS Comput Biol 3(8). https:\/\/doi.org\/10.1371\/journal.pcbi.0030123","DOI":"10.1371\/journal.pcbi.0030123"},{"issue":"10","key":"17_CR5","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1000505","volume":"5","author":"EC Holmes","year":"2009","unstructured":"Holmes EC, Grenfell BT (2009) Discovering the Phylodynamics of RNA viruses. PLoS Comput Biol 5(10):e1000505. https:\/\/doi.org\/10.1371\/journal.pcbi.1000505","journal-title":"PLoS Comput Biol"},{"issue":"5","key":"17_CR6","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1016\/j.bsheal.2025.09.006","volume":"7","author":"W Shen","year":"2025","unstructured":"Shen W, Li Y, Zhu L, Huang T (2025) Predict SARS-CoV-2 genome interactions based on RNA language models. Biosafety Health 7(5):333\u2013343. https:\/\/doi.org\/10.1016\/j.bsheal.2025.09.006","journal-title":"Biosafety Health"},{"key":"17_CR7","doi-asserted-by":"publisher","first-page":"3498","DOI":"10.1016\/j.csbj.2024.09.031","volume":"23","author":"OA Sarumi","year":"2024","unstructured":"Sarumi OA, Heider D (2024) Large language models and their applications in bioinformatics. Comput Struct Biotechnol J 23:3498\u20133505. https:\/\/doi.org\/10.1016\/j.csbj.2024.09.031","journal-title":"Comput Struct Biotechnol J"},{"issue":"15","key":"17_CR8","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2016239118","volume":"118","author":"A Rives","year":"2021","unstructured":"Rives A, Meier J, Sercu T, Goyal S, Lin Z, Liu J, Guo D, Ott M, Zitnick CL, Ma J, Fergus R (2021) Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. Proc Natl Acad Sci U S A 118(15):e2016239118. https:\/\/doi.org\/10.1073\/pnas.2016239118","journal-title":"Proc Natl Acad Sci U S A"},{"key":"17_CR9","doi-asserted-by":"publisher","unstructured":"Gong T, Bu D (2024) Language models enable zero-shot prediction of RNA secondary structure including pseudoknots. bioRxiv:2024.2001.2027.577533. https:\/\/doi.org\/10.1101\/2024.01.27.577533","DOI":"10.1101\/2024.01.27.577533"},{"issue":"1","key":"17_CR10","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1038\/s41580-021-00407-0","volume":"23","author":"JG Greener","year":"2022","unstructured":"Greener JG, Kandathil SM, Moffat L, Jones DT (2022) A guide to machine learning for biologists. Nat Rev Mol Cell Biol 23(1):40\u201355. https:\/\/doi.org\/10.1038\/s41580-021-00407-0","journal-title":"Nat Rev Mol Cell Biol"},{"issue":"Database issue","key":"17_CR11","doi-asserted-by":"publisher","first-page":"D54","DOI":"10.1093\/nar\/gkr854","volume":"40","author":"Y Kodama","year":"2012","unstructured":"Kodama Y, Shumway M, Leinonen R (2012) The sequence read archive: explosive growth of sequencing data. Nucleic Acids Res 40(Database issue):D54\u2013D56. https:\/\/doi.org\/10.1093\/nar\/gkr854","journal-title":"Nucleic Acids Res"},{"issue":"Database issue","key":"17_CR12","doi-asserted-by":"publisher","first-page":"D136","DOI":"10.1093\/nar\/gkr1178","volume":"40","author":"S Federhen","year":"2012","unstructured":"Federhen S (2012) The NCBI taxonomy database. Nucleic Acids Res 40(Database issue):D136\u2013D143. https:\/\/doi.org\/10.1093\/nar\/gkr1178","journal-title":"Nucleic Acids Res"},{"issue":"7","key":"17_CR13","doi-asserted-by":"publisher","first-page":"120","DOI":"10.46234\/ccdcw2022.019","volume":"4","author":"M Zhao","year":"2022","unstructured":"Zhao M, Chen J, Wang Q, Lu Z, Jia Z (2022) A landscape analysis on virus: based on NCBI database. China CDC Wkly 4(7):120\u2013125. https:\/\/doi.org\/10.46234\/ccdcw2022.019","journal-title":"China CDC Wkly"},{"key":"17_CR14","doi-asserted-by":"publisher","unstructured":"Sheehan N, Leonelli S, Botta F (2023) From collection to analysis: a comparison of GISAID and the Covid-19 data portal. https:\/\/doi.org\/10.1101\/2023.05.13.540634","DOI":"10.1101\/2023.05.13.540634"},{"key":"17_CR15","doi-asserted-by":"publisher","unstructured":"Shu Y, McCauley J (2017) GISAID: global initiative on sharing all influenza data\u2014from vision to reality. Euro Surveill 22(13). https:\/\/doi.org\/10.2807\/1560-7917.Es.2017.22.13.30494","DOI":"10.2807\/1560-7917.Es.2017.22.13.30494"},{"key":"17_CR16","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/978-981-97-6703-8_2","volume-title":"Machine learning in single-cell RNA-seq data analysis","author":"K Raza","year":"2024","unstructured":"Raza K (2024) Preprocessing and quality control. In: Raza K (ed) Machine learning in single-cell RNA-seq data analysis. Springer Nature Singapore, Singapore, pp 17\u201330. https:\/\/doi.org\/10.1007\/978-981-97-6703-8_2"},{"issue":"17","key":"17_CR17","doi-asserted-by":"publisher","first-page":"i884","DOI":"10.1093\/bioinformatics\/bty560","volume":"34","author":"S Chen","year":"2018","unstructured":"Chen S, Zhou Y, Chen Y, Gu J (2018) Fastp: an ultra-fast all-in-one FASTQ preprocessor. Bioinformatics 34(17):i884\u2013i890. https:\/\/doi.org\/10.1093\/bioinformatics\/bty560","journal-title":"Bioinformatics"},{"issue":"23","key":"17_CR18","doi-asserted-by":"publisher","first-page":"3150","DOI":"10.1093\/bioinformatics\/bts565","volume":"28","author":"L Fu","year":"2012","unstructured":"Fu L, Niu B, Zhu Z, Wu S, Li W (2012) CD-HIT: accelerated for clustering the next-generation sequencing data. Bioinformatics 28(23):3150\u20133152. https:\/\/doi.org\/10.1093\/bioinformatics\/bts565","journal-title":"Bioinformatics"},{"issue":"11","key":"17_CR19","doi-asserted-by":"publisher","first-page":"1026","DOI":"10.1038\/nbt.3988","volume":"35","author":"M Steinegger","year":"2017","unstructured":"Steinegger M, S\u00f6ding J (2017) MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets. Nat Biotechnol 35(11):1026\u20131028. https:\/\/doi.org\/10.1038\/nbt.3988","journal-title":"Nat Biotechnol"},{"key":"17_CR20","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Paper presented at the Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, California, USA"},{"issue":"8","key":"17_CR21","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1038\/nbt.3300","volume":"33","author":"B Alipanahi","year":"2015","unstructured":"Alipanahi B, Delong A, Weirauch MT, Frey BJ (2015) Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning. Nat Biotechnol 33(8):831\u2013838. https:\/\/doi.org\/10.1038\/nbt.3300","journal-title":"Nat Biotechnol"},{"issue":"11","key":"17_CR22","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0141287","volume":"10","author":"E Asgari","year":"2015","unstructured":"Asgari E, Mofrad MR (2015) Continuous distributed representation of biological sequences for deep proteomics and genomics. PLoS One 10(11):e0141287. https:\/\/doi.org\/10.1371\/journal.pone.0141287","journal-title":"PLoS One"},{"issue":"1","key":"17_CR23","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s41095-021-0247-3","volume":"8","author":"Y Xu","year":"2022","unstructured":"Xu Y, Wei H, Lin M, Deng Y, Sheng K, Zhang M, Tang F, Dong W, Huang F, Xu C (2022) Transformers in computational visual media: a survey. Comput Vis Media 8(1):33\u201362. https:\/\/doi.org\/10.1007\/s41095-021-0247-3","journal-title":"Comput Vis Media"},{"issue":"10","key":"17_CR24","doi-asserted-by":"publisher","first-page":"4316","DOI":"10.3390\/app14104316","volume":"14","author":"AR Sajun","year":"2024","unstructured":"Sajun AR, Zualkernan I, Sankalpa D (2024) A historical survey of advances in transformer architectures. Appl Sci 14(10):4316","journal-title":"Appl Sci"},{"key":"17_CR25","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1016\/j.aiopen.2021.08.002","volume":"2","author":"X Han","year":"2021","unstructured":"Han X, Zhang Z, Ding N, Gu Y, Liu X, Huo Y, Qiu J, Yao Y, Zhang A, Zhang L, Han W, Huang M, Jin Q, Lan Y, Liu Y, Liu Z, Lu Z, Qiu X, Song R, Tang J, Wen J-R, Yuan J, Zhao WX, Zhu J (2021) Pre-trained models: past, present and future. AI Open 2:225\u2013250. https:\/\/doi.org\/10.1016\/j.aiopen.2021.08.002","journal-title":"AI Open"},{"key":"17_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cbpa.2021.04.005","volume":"65","author":"M AlQuraishi","year":"2021","unstructured":"AlQuraishi M (2021) Machine learning in protein structure prediction. Curr Opin Chem Biol 65:1\u20138. https:\/\/doi.org\/10.1016\/j.cbpa.2021.04.005","journal-title":"Curr Opin Chem Biol"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Chen J, Hu Z, Sun S, Tan Q, Wang Y, Yu Q, Zong L, Hong L, Xiao J, King I, Li Y (2022) Interpretable RNA foundation model from unannotated data for highly accurate RNA structure and function predictions. bioRxiv","DOI":"10.1101\/2022.08.06.503062"},{"issue":"1","key":"17_CR28","doi-asserted-by":"publisher","first-page":"e3","DOI":"10.1093\/nar\/gkad1031","volume":"52","author":"Y Zhang","year":"2023","unstructured":"Zhang Y, Lang M, Jiang J, Gao Z, Xu F, Litfin T, Chen K, Singh J, Huang X, Song G, Tian Y, Zhan J, Chen J, Zhou Y (2023) Multiple sequence alignment-based RNA language model and its application to structural inference. Nucleic Acids Res 52(1):e3\u2013e3. https:\/\/doi.org\/10.1093\/nar\/gkad1031","journal-title":"Nucleic Acids Res"},{"key":"17_CR29","doi-asserted-by":"publisher","unstructured":"Akiyama M, Sakakibara Y (2022) Informative RNA base embedding for RNA structural alignment and clustering by deep representation learning. NAR Genomics and Bioinformatics 4(1). https:\/\/doi.org\/10.1093\/nargab\/lqac012","DOI":"10.1093\/nargab\/lqac012"},{"issue":"1","key":"17_CR30","doi-asserted-by":"publisher","DOI":"10.1093\/bioadv\/vbac023","volume":"2","author":"K Yamada","year":"2022","unstructured":"Yamada K, Hamada M (2022) Prediction of RNA-protein interactions using a nucleotide language model. Bioinform Adv 2(1):vbac023. https:\/\/doi.org\/10.1093\/bioadv\/vbac023","journal-title":"Bioinform Adv"},{"key":"17_CR31","doi-asserted-by":"publisher","unstructured":"Li S, Moayedpour S, Li R, Bailey M, Riahi S, Miladi M, Miner J, Zheng D, Wang J, Balsubramani A, Tran K, Zacharia M, Wu M, Gu X, Clinton R, Asquith C, Skalesk J, Boeglin L, Chivukula S, Dias A, Montoya FU, Agarwal V, Bar-Joseph Z, Jager S (2023) CodonBERT: Large Language Models for mRNA design and optimization. bioRxiv:2023.2009.2009.556981. https:\/\/doi.org\/10.1101\/2023.09.09.556981","DOI":"10.1101\/2023.09.09.556981"},{"issue":"2","key":"17_CR32","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1038\/s41592-024-02523-z","volume":"22","author":"H Dalla-Torre","year":"2025","unstructured":"Dalla-Torre H, Gonzalez L, Mendoza-Revilla J, Lopez Carranza N, Grzywaczewski AH, Oteri F, Dallago C, Trop E, de Almeida BP, Sirelkhatim H, Richard G, Skwark M, Beguir K, Lopez M, Pierrot T (2025) Nucleotide transformer: building and evaluating robust foundation models for human genomics. Nat Methods 22(2):287\u2013297. https:\/\/doi.org\/10.1038\/s41592-024-02523-z","journal-title":"Nat Methods"},{"issue":"6","key":"17_CR33","doi-asserted-by":"publisher","first-page":"932","DOI":"10.1038\/s41587-021-01179-w","volume":"40","author":"ML Bileschi","year":"2022","unstructured":"Bileschi ML, Belanger D, Bryant DH, Sanderson T, Carter B, Sculley D, Bateman A, DePristo MA, Colwell LJ (2022) Using deep learning to annotate the protein universe. Nat Biotechnol 40(6):932\u2013937. https:\/\/doi.org\/10.1038\/s41587-021-01179-w","journal-title":"Nat Biotechnol"},{"issue":"21","key":"17_CR34","doi-asserted-by":"publisher","first-page":"15858","DOI":"10.3390\/ijms242115858","volume":"24","author":"T Yue","year":"2023","unstructured":"Yue T, Wang Y, Zhang L, Gu C, Xue H, Wang W, Lyu Q, Dun Y (2023) Deep learning for genomics: from early neural nets to modern large language models. Int J Mol Sci 24(21):15858","journal-title":"Int J Mol Sci"},{"key":"17_CR35","doi-asserted-by":"publisher","unstructured":"Rao R, Meier J, Sercu T, Ovchinnikov S, Rives A (2020) Transformer protein language models are unsupervised structure learners. bioRxiv:2020.2012.2015.422761. https:\/\/doi.org\/10.1101\/2020.12.15.422761","DOI":"10.1101\/2020.12.15.422761"},{"key":"17_CR36","doi-asserted-by":"publisher","unstructured":"Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. In: 2017 IEEE International Conference on Computer Vision (ICCV), 22\u201329 Oct. 2017. pp 618\u2013626. https:\/\/doi.org\/10.1109\/ICCV.2017.74","DOI":"10.1109\/ICCV.2017.74"},{"issue":"6526","key":"17_CR37","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1126\/science.abd7331","volume":"371","author":"B Hie","year":"2021","unstructured":"Hie B, Zhong ED, Berger B, Bryson B (2021) Learning the language of viral evolution and escape. Science 371(6526):284\u2013288. https:\/\/doi.org\/10.1126\/science.abd7331","journal-title":"Science"},{"key":"17_CR38","doi-asserted-by":"publisher","unstructured":"Zvyagin M, Brace A, Hippe K, Deng Y, Zhang B, Bohorquez CO, Clyde A, Kale B, Perez-Rivera D, Ma H, Mann CM, Irvin M, Pauloski JG, Ward L, Hayot-Sasson V, Emani M, Foreman S, Xie Z, Lin D, Shukla M, Nie W, Romero J, Dallago C, Vahdat A, Xiao C, Gibbs T, Foster I, Davis JJ, Papka ME, Brettin T, Stevens R, Anandkumar A, Vishwanath V, Ramanathan A (2022) GenSLMs: genome-scale language models reveal SARS-CoV-2 evolutionary dynamics. bioRxiv. https:\/\/doi.org\/10.1101\/2022.10.10.511571","DOI":"10.1101\/2022.10.10.511571"}],"container-title":["Methods in Molecular Biology","Microbial \u2018Omics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-1-0716-5264-0_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T23:53:40Z","timestamp":1778457220000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-1-0716-5264-0_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9781071652633","9781071652640"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-1-0716-5264-0_17","relation":{},"ISSN":["1064-3745","1940-6029"],"issn-type":[{"value":"1064-3745","type":"print"},{"value":"1940-6029","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 May 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}