{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T13:45:36Z","timestamp":1789047936543,"version":"build-2803163510"},"reference-count":57,"publisher":"Oxford University Press (OUP)","issue":"14","license":[{"start":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T00:00:00Z","timestamp":1781654400000},"content-version":"vor","delay-in-days":0,"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":["82341118"],"award-info":[{"award-number":["82341118"]}],"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":["323B2018"],"award-info":[{"award-number":["323B2018"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFC2607502"],"award-info":[{"award-number":["2024YFC2607502"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2025ZD01901102"],"award-info":[{"award-number":["2025ZD01901102"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2025ZD01900401"],"award-info":[{"award-number":["2025ZD01900401"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019069","name":"Chinese Academy of Engineering","doi-asserted-by":"publisher","award":["2023-JB-12"],"award-info":[{"award-number":["2023-JB-12"]}],"id":[{"id":"10.13039\/501100019069","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000925","name":"NHMRC","doi-asserted-by":"publisher","award":["GNT2017197"],"award-info":[{"award-number":["GNT2017197"]}],"id":[{"id":"10.13039\/501100000925","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003452","name":"Innovation and Technology Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003452","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7,9]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Predicting viral evolution and function remains a central challenge in biology, hindered by high sequence divergence and limited knowledge compared to cellular organisms. Here, we introduce LucaVirus, a multi-modal foundation model for viruses, trained on 25.4 billion nucleotide and amino acid tokens covering a vast majority of catalogued viral diversity. LucaVirus learns biologically meaningful representations that reflect relationships between sequences, protein\/gene homology, and evolutionary divergence. Using these embeddings, we developed downstream models that address key virology tasks: identifying hidden viruses in genomic \u2018dark matter\u2019, annotating enzymatic activities of uncharacterized proteins, predicting viral evolvability, and identifying antibody candidates for emerging viruses. LucaVirus demonstrates competitive performance in three tasks and matches leading models in the fourth with one-third the parameters. Together, these findings demonstrate the utility of a unified foundation model in analyzing viral sequence data and establish LucaVirus as an efficient and versatile platform for AI-driven virology, from virus discovery to functional and therapeutic predictions.<\/jats:p>","DOI":"10.1093\/nsr\/nwag376","type":"journal-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T12:22:02Z","timestamp":1781612522000},"source":"Crossref","is-referenced-by-count":2,"title":["Predicting the evolutionary and functional landscapes of viruses with a unified nucleotide-protein language model: LucaVirus"],"prefix":"10.1093","volume":"13","author":[{"given":"Yuan-Fei","family":"Pan","sequence":"first","affiliation":[{"name":"State Key Laboratory of Wetland Conservation and Restoration, National Observations and Research Station for Wetland Ecosystems of the Yangtze Estuary, Ministry of Education Key Laboratory for Biodiversity Science and Ecological Engineering, and Institute of Eco-Chongming, School of Life Sciences, Fudan University , Shanghai 200433 ,","place":["China"]},{"name":"National Key Laboratory of Intelligent Tracking and Forecasting for Infectious Diseases, School of Medicine, Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University , Shenzhen 518107 ,","place":["China"]},{"name":"State Key Laboratory for Biocontrol, School of Medicine, Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University , Shenzhen 518107 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1585-2009","authenticated-orcid":false,"given":"Yong","family":"He","sequence":"additional","affiliation":[{"name":"Apsara Lab, Alibaba Cloud Intelligence, Alibaba Group , Hangzhou 310030 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Qi","family":"Liu","sequence":"additional","affiliation":[{"name":"Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences , Hangzhou 310024 ,","place":["China"]},{"name":"HIM-BGI Omics Center, Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences , Hangzhou 310000 ,","place":["China"]},{"name":"BGI Research , Hangzhou 310030 ,","place":["China"]},{"name":"Zhejiang Lab , Hangzhou 311121 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong-Tao","family":"Shan","sequence":"additional","affiliation":[{"name":"Zhejiang Lab , Hangzhou 311121 ,","place":["China"]},{"name":"State Key Laboratory of Biocontrol, School of Life Science, Sun Yat-sen University , Guangzhou 510275 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shu-Ning","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Public Health (Shenzhen), Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University , Shenzhen 518107 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia-Hao","family":"Ma","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Intelligent Tracking and Forecasting for Infectious Diseases, School of Medicine, Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University , Shenzhen 518107 ,","place":["China"]},{"name":"State Key Laboratory for Biocontrol, School of Medicine, Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University , Shenzhen 518107 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xue","family":"Liu","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Intelligent Tracking and Forecasting for Infectious Diseases, School of Medicine, Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University , Shenzhen 518107 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyun","family":"Pan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Wetland Conservation and Restoration, National Observations and Research Station for Wetland Ecosystems of the Yangtze Estuary, Ministry of Education Key Laboratory for Biodiversity Science and Ecological Engineering, and Institute of Eco-Chongming, School of Life Sciences, Fudan University , Shanghai 200433 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1017-5712","authenticated-orcid":false,"given":"Yinqi","family":"Bai","sequence":"additional","affiliation":[{"name":"BGI Research , Sanya 572025 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zan","family":"Xu","sequence":"additional","affiliation":[{"name":"Apsara Lab, Alibaba Cloud Intelligence, Alibaba Group , Hangzhou 310030 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7227-2580","authenticated-orcid":false,"given":"Tingjun","family":"Hou","sequence":"additional","affiliation":[{"name":"College of Pharmaceutical Sciences, Zhejiang University , Hangzhou 310058, Zhejiang ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Apsara Lab, Alibaba Cloud Intelligence, Alibaba Group , Hangzhou 310030 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jieping","family":"Ye","sequence":"additional","affiliation":[{"name":"Apsara Lab, Alibaba Cloud Intelligence, Alibaba Group , Hangzhou 310030 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianguo","family":"He","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Biocontrol, School of Life Science, Sun Yat-sen University , Guangzhou 510275 ,","place":["China"]},{"name":"School of Marine Sciences, Sun Yat-sen University State Key Laboratory of Biocontrol\/Southern Laboratory of Ocean Science and Engineering (Guangdong, Zhuhai ), ; Guangzhou 510275 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Edward C","family":"Holmes","sequence":"additional","affiliation":[{"name":"School of Medical Sciences, The University of Sydney , Sydney, NSW 2006 ,","place":["Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0439-5666","authenticated-orcid":false,"given":"Bo","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Wetland Conservation and Restoration, National Observations and Research Station for Wetland Ecosystems of the Yangtze Estuary, Ministry of Education Key Laboratory for Biodiversity Science and Ecological Engineering, and Institute of Eco-Chongming, School of Life Sciences, Fudan University , Shanghai 200433 ,","place":["China"]},{"name":"State Key Laboratory for Vegetation Structure, Functions and Construction (VegLab), Ministry of Education Key Laboratory for Transboundary Ecosecurity of Southwest China, Institute of Biodiversity, School of Ecology and Environmental Science, and Southwest United Graduate School, Yunnan University , Kunming 650500 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao-Qing","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Public Health (Shenzhen), Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University , Shenzhen 518107 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhao-Rong","family":"Li","sequence":"additional","affiliation":[{"name":"Apsara Lab, Alibaba Cloud Intelligence, Alibaba Group , Hangzhou 310030 ,","place":["China"]},{"name":"Zhejiang Lab , Hangzhou 311121 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6154-4437","authenticated-orcid":false,"given":"Mang","family":"Shi","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Intelligent Tracking and Forecasting for Infectious Diseases, School of Medicine, Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University , Shenzhen 518107 ,","place":["China"]},{"name":"State Key Laboratory for Biocontrol, School of Medicine, Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University , Shenzhen 518107 ,","place":["China"]},{"name":"Guangdong Provincial Center for Disease Control and Prevention , Guangzhou 511430 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,6,17]]},"reference":[{"key":"2026072409284717200_bib1","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1038\/s41579-021-00665-x","article-title":"Diversity and evolution of the animal virome","volume":"20","author":"Harvey","year":"2022","journal-title":"Nat Rev Micro"},{"key":"2026072409284717200_bib2","doi-asserted-by":"publisher","first-page":"1559","DOI":"10.1038\/s41467-025-56769-y","article-title":"In-depth analysis of 17,115 rice transcriptomes reveals extensive viral diversity in rice plants","volume":"16","author":"Zhu","year":"2025","journal-title":"Nat Commun"},{"key":"2026072409284717200_bib3","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1038\/s41579-022-00811-z","article-title":"Soil viral diversity, ecology and climate change","volume":"21","author":"Jansson","year":"2022","journal-title":"Nat Rev Micro"},{"key":"2026072409284717200_bib4","doi-asserted-by":"publisher","first-page":"1261498","DOI":"10.1126\/science.1261498","article-title":"Patterns and ecological drivers of ocean viral communities","volume":"348","author":"Brum","year":"2015","journal-title":"Science"},{"key":"2026072409284717200_bib5","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1126\/science.aap9072","article-title":"Predicting reservoir hosts and arthropod vectors from evolutionary signatures in RNA virus genomes","volume":"362","author":"Babayan","year":"2018","journal-title":"Science"},{"key":"2026072409284717200_bib6","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1038\/s41586-023-06617-0","article-title":"Learning from prepandemic data to forecast viral escape","volume":"622","author":"Thadani","year":"2023","journal-title":"Nature"},{"key":"2026072409284717200_bib7","doi-asserted-by":"publisher","first-page":"960","DOI":"10.1038\/s41559-024-02353-4","article-title":"The evolutionary drivers and correlates of viral host jumps","volume":"8","author":"Tan","year":"2024","journal-title":"Nat Ecol Evol"},{"key":"2026072409284717200_bib8","doi-asserted-by":"publisher","first-page":"710","DOI":"10.1038\/s41586-024-07809-y","article-title":"Birth of protein folds and functions in the virome","volume":"633","author":"Nomburg","year":"2024","journal-title":"Nature"},{"key":"2026072409284717200_bib9","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1038\/nrg2323","article-title":"Rates of evolutionary change in viruses: patterns and determinants","volume":"9","author":"Duffy","year":"2008","journal-title":"Nat Rev Genet"},{"key":"2026072409284717200_bib10","doi-asserted-by":"publisher","first-page":"6929","DOI":"10.1016\/j.cell.2024.09.027","article-title":"Using artificial intelligence to document the hidden RNA virosphere","volume":"187","author":"Hou","year":"2024","journal-title":"Cell"},{"key":"2026072409284717200_bib11","doi-asserted-by":"publisher","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":"2026072409284717200_bib12","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1126\/science.ads0018","article-title":"Simulating 500 million years of evolution with a language model","volume":"387","author":"Hayes","year":"2025","journal-title":"Science"},{"key":"2026072409284717200_bib13","doi-asserted-by":"crossref","first-page":"1349","DOI":"10.1038\/s41586-026-10176-5","article-title":"Genome modeling and design across all domains of life with Evo 2","volume":"652","author":"Brixi","year":"2026","journal-title":"Nature"},{"key":"2026072409284717200_bib14","doi-asserted-by":"publisher","first-page":"eado9336","DOI":"10.1126\/science.ado9336","article-title":"Sequence modeling and design from molecular to genome scale with Evo","volume":"386","author":"Nguyen","year":"2024","journal-title":"Science"},{"key":"2026072409284717200_bib15","doi-asserted-by":"publisher","first-page":"1412","DOI":"10.1038\/s42003-024-07098-1","article-title":"Evolution shapes and conserves genomic signatures in viruses","volume":"7","author":"Holmudden","year":"2024","journal-title":"Commun Biol"},{"key":"2026072409284717200_bib16","doi-asserted-by":"publisher","DOI":"10.3389\/fgene.2012.00242","article-title":"On programmed ribosomal frameshifting: the alternative proteomes","volume":"3","author":"Ketteler","year":"2012","journal-title":"Front Genet"},{"key":"2026072409284717200_bib17","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/j.coviro.2013.03.009","article-title":"Viral precursor polyproteins: keys of regulation from replication to maturation","volume":"3","author":"Yost","year":"2013","journal-title":"Curr Opin Virol"},{"key":"2026072409284717200_bib18","doi-asserted-by":"publisher","first-page":"101346","DOI":"10.1016\/j.coviro.2023.101346","article-title":"Predicting zoonotic potential of viruses: where are we?","volume":"61","author":"Mollentze","year":"2023","journal-title":"Curr Opin Virol"},{"key":"2026072409284717200_bib19","doi-asserted-by":"publisher","first-page":"e3001390","DOI":"10.1371\/journal.pbio.3001390","article-title":"Identifying and prioritizing potential human-infecting viruses from their genome sequences","volume":"19","author":"Mollentze","year":"2021","journal-title":"PLoS Biol"},{"key":"2026072409284717200_bib20","doi-asserted-by":"publisher","first-page":"942","DOI":"10.1038\/s42256-025-01044-4","article-title":"Generalized biological foundation model with unified nucleic acid and protein language","volume":"7","author":"He","year":"2025","journal-title":"Nat Mach Intell"},{"key":"2026072409284717200_bib21","doi-asserted-by":"publisher","first-page":"D609","DOI":"10.1093\/nar\/gkae1010","article-title":"UniProt: the Universal protein knowledgebase in 2025","volume":"53","author":"The UniProt C","year":"2025","journal-title":"Nucleic Acids Res"},{"key":"2026072409284717200_bib22","doi-asserted-by":"publisher","first-page":"4023","DOI":"10.1016\/j.cell.2022.08.023","article-title":"Expansion of the global RNA virome reveals diverse clades of bacteriophages","volume":"185","author":"Neri","year":"2022","journal-title":"Cell"},{"key":"2026072409284717200_bib23","doi-asserted-by":"publisher","first-page":"1098","DOI":"10.1016\/j.cell.2021.01.029","article-title":"Massive expansion of human gut bacteriophage diversity","volume":"184","author":"Camarillo-Guerrero","year":"2021","journal-title":"Cell"},{"key":"2026072409284717200_bib24","doi-asserted-by":"publisher","first-page":"1262","DOI":"10.1038\/s41564-020-0755-4","article-title":"Doubling of the known set of RNA viruses by metagenomic analysis of an aquatic virome","volume":"5","author":"Wolf","year":"2020","journal-title":"Nat Microbiol"},{"key":"2026072409284717200_bib25","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1126\/science.abm5847","article-title":"Cryptic and abundant marine viruses at the evolutionary origins of Earth\u2019s RNA virome","volume":"376","author":"Zayed","year":"2022","journal-title":"Science"},{"key":"2026072409284717200_bib26","doi-asserted-by":"publisher","first-page":"1109","DOI":"10.1016\/j.cell.2019.03.040","article-title":"Marine DNA viral macro- and microdiversity from pole to pole","volume":"177","author":"Gregory","year":"2019","journal-title":"Cell"},{"key":"2026072409284717200_bib27","article-title":"BSM: small but powerful biological sequence model for genes and proteins","author":"Xiang"},{"key":"2026072409284717200_bib28","article-title":"COMET: benchmark for comprehensive biological multi-omics evaluation tasks and language models","author":"Ren"},{"key":"2026072409284717200_bib29","doi-asserted-by":"publisher","first-page":"3776","DOI":"10.1109\/TASLPRO.2025.3606231","article-title":"An empirical study of catastrophic forgetting in large language models during continual fine-tuning","volume":"33","author":"Luo","year":"2025","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"2026072409284717200_bib30","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1038\/s41592-024-02523-z","article-title":"Nucleotide transformer: building and evaluating robust foundation models for human genomics","volume":"22","author":"Dalla-Torre","year":"2025","journal-title":"Nat Methods"},{"key":"2026072409284717200_bib31","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1016\/j.compbiolchem.2007.05.004","article-title":"FSDB: a frameshift signal database","volume":"31","author":"Moon","year":"2007","journal-title":"Comput Biol Chem"},{"key":"2026072409284717200_bib32","doi-asserted-by":"publisher","first-page":"10915","DOI":"10.1073\/pnas.89.22.10915","article-title":"Amino acid substitution matrices from protein blocks","volume":"89","author":"Henikoff","year":"1992","journal-title":"Proc Natl Acad Sci"},{"key":"2026072409284717200_bib33","doi-asserted-by":"publisher","first-page":"D304","DOI":"10.1093\/nar\/gkt1240","article-title":"SCOPe: structural classification of proteins\u2014extended, integrating SCOP and ASTRAL data and classification of new structures","volume":"42","author":"Fox","year":"2013","journal-title":"Nucleic Acids Res"},{"key":"2026072409284717200_bib34","doi-asserted-by":"publisher","first-page":"e02329","DOI":"10.1128\/mBio.02329-18","article-title":"Origins and evolution of the global RNA virome","volume":"9","author":"Wolf","year":"2018","journal-title":"mBio"},{"key":"2026072409284717200_bib35","doi-asserted-by":"publisher","first-page":"e00061","DOI":"10.1128\/MMBR.00061-19","article-title":"Global organization and proposed megataxonomy of the virus world","volume":"84","author":"Koonin Eugene","year":"2020","journal-title":"Microbiol Mol Biol Rev"},{"key":"2026072409284717200_bib36","doi-asserted-by":"publisher","first-page":"E2401","DOI":"10.1073\/pnas.1621061114","article-title":"Multiple origins of viral capsid proteins from cellular ancestors","volume":"114","author":"Krupovic","year":"2017","journal-title":"Proc Natl Acad Sci"},{"key":"2026072409284717200_bib37","doi-asserted-by":"publisher","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":"Nat Biotechnol"},{"key":"2026072409284717200_bib38","doi-asserted-by":"publisher","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":"2026072409284717200_bib39","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1186\/s12859-019-3019-7","article-title":"HH-suite3 for fast remote homology detection and deep protein annotation","volume":"20","author":"Steinegger","year":"2019","journal-title":"BMC Bioinf"},{"key":"2026072409284717200_bib40","doi-asserted-by":"publisher","first-page":"1026","DOI":"10.1038\/nbt.3988","article-title":"MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets","volume":"35","author":"Steinegger","year":"2017","journal-title":"Nat Biotechnol"},{"key":"2026072409284717200_bib41","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1038\/s41592-022-01488-1","article-title":"ColabFold: making protein folding accessible to all","volume":"19","author":"Mirdita","year":"2022","journal-title":"Nat Methods"},{"key":"2026072409284717200_bib42","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1038\/nmeth.3027","article-title":"Deep mutational scanning: a new style of protein science","volume":"11","author":"Fowler","year":"2014","journal-title":"Nat Methods"},{"key":"2026072409284717200_bib43","article-title":"Dnabert-2: efficient foundation model and benchmark for multi-species genome","author":"Zhou"},{"key":"2026072409284717200_bib44","doi-asserted-by":"crossref","first-page":"64331","DOI":"10.52202\/075280-2810","article-title":"Proteingym: large-scale benchmarks for protein fitness prediction and design","volume":"36","author":"Notin","year":"2023","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026072409284717200_bib45","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1038\/s41586-021-04043-8","article-title":"Disease variant prediction with deep generative models of evolutionary data","volume":"599","author":"Frazer","year":"2021","journal-title":"Nature"},{"key":"2026072409284717200_bib46","first-page":"16990","article-title":"Tranception: protein fitness prediction with autoregressive transformers and inference-time retrieval","author":"Notin","year":"2022","journal-title":"PMLR"},{"key":"2026072409284717200_bib47","doi-asserted-by":"publisher","first-page":"734","DOI":"10.1093\/bioinformatics\/btaa739","article-title":"CoV-AbDab: the coronavirus antibody database","volume":"37","author":"Raybould","year":"2021","journal-title":"Bioinformatics"},{"key":"2026072409284717200_bib48","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s41586-024-07487-w","article-title":"Accurate structure prediction of biomolecular interactions with AlphaFold 3","volume":"630","author":"Abramson","year":"2024","journal-title":"Nature"},{"key":"2026072409284717200_bib49","doi-asserted-by":"publisher","first-page":"1141","DOI":"10.1093\/bioinformatics\/btab762","article-title":"CSM-AB: graph-based antibody\u2013antigen binding affinity prediction and docking scoring function","volume":"38","author":"Myung","year":"2022","journal-title":"Bioinformatics"},{"key":"2026072409284717200_bib50","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1186\/s12859-023-05562-z","article-title":"DG-affinity: predicting antigen\u2013antibody affinity with language models from sequences","volume":"24","author":"Yuan","year":"2023","journal-title":"BMC Bioinf"},{"key":"2026072409284717200_bib51","doi-asserted-by":"publisher","first-page":"2453","DOI":"10.1016\/j.immuni.2024.07.022","article-title":"An explainable language model for antibody specificity prediction using curated influenza hemagglutinin antibodies","volume":"57","author":"Wang","year":"2024","journal-title":"Immunity"},{"key":"2026072409284717200_bib52","doi-asserted-by":"publisher","first-page":"e2410529121","DOI":"10.1073\/pnas.2410529121","article-title":"Improved deep learning prediction of antigen\u2013antibody interactions","volume":"121","author":"Gao","year":"2024","journal-title":"Proc Natl Acad Sci USA"},{"key":"2026072409284717200_bib53","doi-asserted-by":"publisher","first-page":"7206","DOI":"10.1016\/j.cell.2025.10.006","article-title":"Generation of antigen-specific paired-chain antibodies using large language models","volume":"188","author":"Wasdin","year":"2025","journal-title":"Cell"},{"key":"2026072409284717200_bib54","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3458754","article-title":"Domain-specific language model pretraining for biomedical natural language processing","volume":"3","author":"Gu","year":"2021","journal-title":"ACM Trans Comput Healthcare"},{"key":"2026072409284717200_bib55","doi-asserted-by":"publisher","first-page":"e2322420121","DOI":"10.1073\/pnas.2322420121","article-title":"Embers of autoregression show how large language models are shaped by the problem they are trained to solve","volume":"121","author":"McCoy","year":"2024","journal-title":"Proc Natl Acad Sci USA"},{"key":"2026072409284717200_bib56","doi-asserted-by":"publisher","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":"2026072409284717200_bib57","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1126\/science.adq1977","article-title":"AI and biosecurity: the need for governance","volume":"385","author":"Bloomfield","year":"2024","journal-title":"Science"}],"container-title":["National Science Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/nsr\/advance-article-pdf\/doi\/10.1093\/nsr\/nwag376\/68541551\/nwag376.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/nsr\/article-pdf\/13\/14\/nwag376\/68541551\/nwag376.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/nsr\/article-pdf\/13\/14\/nwag376\/68541551\/nwag376.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T13:28:59Z","timestamp":1784899739000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/nsr\/article\/doi\/10.1093\/nsr\/nwag376\/8709798"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,17]]},"references-count":57,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2026,7,9]]}},"URL":"https:\/\/doi.org\/10.1093\/nsr\/nwag376","relation":{},"ISSN":["2095-5138","2053-714X"],"issn-type":[{"value":"2095-5138","type":"print"},{"value":"2053-714X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,7]]},"published":{"date-parts":[[2026,6,17]]},"article-number":"nwag376"}}