{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T01:32:44Z","timestamp":1790904764195,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"New Generation Artificial Intelligence, National Science and Technology Major Project of China","award":["2025ZD0121801"],"award-info":[{"award-number":["2025ZD0121801"]}]},{"name":"Prevention and Control of Emerging and Major Infectious Diseases, National Science and Technology Major Project of China","award":["2025ZD01901102"],"award-info":[{"award-number":["2025ZD01901102"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3819057","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:47Z","timestamp":1786036547000},"page":"12679-12690","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4277-9558","authenticated-orcid":false,"given":"Dongxin","family":"Ye","sequence":"first","affiliation":[{"name":"Shanghai Innovation Institute, Shanghai, China and University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0476-4727","authenticated-orcid":false,"given":"Fang","family":"Hu","sequence":"additional","affiliation":[{"name":"Shanghai Innovation Institute, Shanghai, China and Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0152-5402","authenticated-orcid":false,"given":"Han","family":"Hu","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, China and Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3481-3256","authenticated-orcid":false,"given":"Shu","family":"Hu","sequence":"additional","affiliation":[{"name":"Fudan University, Institute of Infection and Health, Shanghai, China and Shanghai Sci-Tech Inno Center for Infection & Immunity, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7261-1705","authenticated-orcid":false,"given":"Yang","family":"Tan","sequence":"additional","affiliation":[{"name":"Shanghai Innovation Institute, Shanghai, China and Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9163-2761","authenticated-orcid":false,"given":"Wanli","family":"Ouyang","sequence":"additional","affiliation":[{"name":"Shenzhen Loop Area Institute, Shenzhen, China and Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2961-8096","authenticated-orcid":false,"given":"Stan Z.","family":"Li","sequence":"additional","affiliation":[{"name":"Westlake University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8176-9951","authenticated-orcid":false,"given":"Jie","family":"Cui","sequence":"additional","affiliation":[{"name":"Institute of Infection and Health, Fudan University, Shanghai, China and Shanghai Sci-Tech Inno Center for Infection & Immunity, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5014-1993","authenticated-orcid":false,"given":"Nanqing","family":"Dong","sequence":"additional","affiliation":[{"name":"Shanghai Innovation Institute, Shanghai, China and Shanghai Artificial Intelligence Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07487-w"},{"key":"e_1_3_2_1_2_1","volume-title":"Informative RNA base embedding for RNA structural alignment and clustering by deep representation learning. NAR genomics and bioinformatics","author":"Akiyama Manato","year":"2022","unstructured":"Manato Akiyama and Yasubumi Sakakibara. 2022. Informative RNA base embedding for RNA structural alignment and clustering by deep representation learning. NAR genomics and bioinformatics, Vol. 4, 1 (2022), lqac012."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.3389\/fgene.2025.1634882"},{"key":"e_1_3_2_1_4_1","volume-title":"Nucleic acids research","author":"Benson Dennis A","year":"2012","unstructured":"Dennis A Benson, Mark Cavanaugh, Karen Clark, Ilene Karsch-Mizrachi, David J Lipman, James Ostell, and Eric W Sayers. 2012. GenBank. Nucleic acids research, Vol. 41, D1 (2012), D36-D42."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Sam Boshar Benjamin Evans Ziqi Tang Armand Picard Yanis Adel Franziska K Lorbeer Chandana Rajesh Tristan Karch Shawn Sidbon David Emms et al. 2025. A foundational model for joint sequence-function multi-species modeling at scale for long-range genomic prediction. bioRxiv (2025) 2025-12.","DOI":"10.64898\/2025.12.22.695963"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1099\/jgv.0.002067"},{"key":"e_1_3_2_1_7_1","first-page":"1349","volume-title":"Nature","volume":"652","author":"Brixi Garyk","year":"2026","unstructured":"Garyk Brixi, Matthew G Durrant, Jerome Ku, Mohsen Naghipourfar, Michael Poli, Gwanggyu Sun, Greg Brockman, Daniel Chang, Alison Fanton, Gabriel A Gonzalez, et al., 2026. Genome modelling and design across all domains of life with Evo 2. Nature, Vol. 652, 8112 (2026), 1349-1361."},{"key":"e_1_3_2_1_8_1","volume-title":"BLAST: architecture and applications. BMC bioinformatics","author":"Camacho Christiam","year":"2009","unstructured":"Christiam Camacho, George Coulouris, Vahram Avagyan, Ning Ma, Jason Papadopoulos, Kevin Bealer, and Thomas L Madden. 2009. BLAST: architecture and applications. BMC bioinformatics, Vol. 10, 1 (2009), 421."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1101\/2022.08.06.503062"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-024-02523-z"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1101\/2021.11.09.467890"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1101\/2024.12.01.625444"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1093\/nargab\/lqae106"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkae1310"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2983"},{"key":"e_1_3_2_1_16_1","volume-title":"Simulation study and comparative evaluation of viral contiguous sequence identification tools. BMC bioinformatics","author":"Glickman Cody","year":"2021","unstructured":"Cody Glickman, Jo Hendrix, and Michael Strong. 2021. Simulation study and comparative evaluation of viral contiguous sequence identification tools. BMC bioinformatics, Vol. 22, 1 (2021), 329."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12863-023-01123-8"},{"key":"e_1_3_2_1_18_1","unstructured":"Yong He Pan Fang Yongtao Shan Yuanfei Pan Yanhong Wei Yichang Chen Yihao Chen Yi Liu Zhenyu Zeng Zhan Zhou et al. 2025. Generalized biological foundation model with unified nucleic acid and protein language. Nature Machine Intelligence (2025) 1-12."},{"key":"e_1_3_2_1_19_1","volume-title":"What can we predict about viral evolution and emergence? Current opinion in virology","author":"Holmes Edward C","year":"2013","unstructured":"Edward C Holmes. 2013. What can we predict about viral evolution and emergence? Current opinion in virology, Vol. 3, 2 (2013), 180-184."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btab083"},{"key":"e_1_3_2_1_21_1","volume-title":"NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction. arXiv preprint arXiv:2511.02888","author":"Li Zhongmin","year":"2025","unstructured":"Zhongmin Li, Runze Ma, Jiahao Tan, Chengzi Tan, and Shuangjia Zheng. 2025. NABench: Large-Scale Benchmarks of Nucleotide Foundation Models for Fitness Prediction. arXiv preprint arXiv:2511.02888 (2025)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1093\/gigascience\/giaf132"},{"key":"e_1_3_2_1_23_1","volume-title":"Bioinformatics","volume":"41","author":"Lindsey LeAnn M","year":"2025","unstructured":"LeAnn M Lindsey, Nicole L Pershing, Anisa Habib, Keith Dufault-Thompson, W Zac Stephens, Anne J Blaschke, Xiaofang Jiang, and Hari Sundar. 2025. The impact of tokenizer selection in genomic language models. Bioinformatics, Vol. 41, 9 (2025), btaf456."},{"key":"e_1_3_2_1_24_1","volume-title":"Genbench: A benchmarking suite for systematic evaluation of genomic foundation models. arXiv preprint arXiv:2406.01627","author":"Liu Zicheng","year":"2024","unstructured":"Zicheng Liu, Jiahui Li, Siyuan Li, Zelin Zang, Cheng Tan, Yufei Huang, Yajing Bai, and Stan Z Li. 2024. Genbench: A benchmarking suite for systematic evaluation of genomic foundation models. arXiv preprint arXiv:2406.01627 (2024)."},{"key":"e_1_3_2_1_25_1","volume-title":"BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=uKB4cFNQFg","author":"Marin Frederikke Isa","year":"2024","unstructured":"Frederikke Isa Marin, Felix Teufel, Marc Horlacher, Dennis Madsen, Dennis Pultz, Ole Winther, and Wouter Boomsma. 2024. BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=uKB4cFNQFg"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09749-7"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Hayden C Metsky Nicole L Welch Priya P Pillai Nicholas J Haradhvala Laurie Rumker Sreekar Mantena Yibin B Zhang David K Yang Cheri M Ackerman Juliane Weller et al. 2022. Designing sensitive viral diagnostics with machine learning. Nature biotechnology Vol. 40 7 (2022) 1123-1131.","DOI":"10.1038\/s41587-022-01213-5"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaa705"},{"key":"e_1_3_2_1_29_1","volume-title":"Science","volume":"386","author":"Nguyen Eric","year":"2024","unstructured":"Eric Nguyen, Michael Poli, Matthew G Durrant, Brian Kang, Dhruva Katrekar, David B Li, Liam J Bartie, Armin W Thomas, Samuel H King, Garyk Brixi, et al., 2024. Sequence modeling and design from molecular to genome scale with Evo. Science, Vol. 386, 6723 (2024), eado9336."},{"key":"e_1_3_2_1_30_1","volume-title":"Hyenadna: Long-range genomic sequence modeling at single nucleotide resolution. Advances in neural information processing systems","author":"Nguyen Eric","year":"2023","unstructured":"Eric Nguyen, Michael Poli, Marjan Faizi, Armin Thomas, Michael Wornow, Callum Birch-Sykes, Stefano Massaroli, Aman Patel, Clayton Rabideau, Yoshua Bengio, et al., 2023. Hyenadna: Long-range genomic sequence modeling at single nucleotide resolution. Advances in neural information processing systems, Vol. 36 (2023), 43177-43201."},{"key":"e_1_3_2_1_31_1","volume-title":"Steffanie Paul, Han Spinner, Nathan Rollins, Ada Shaw, Rose Orenbuch, Ruben Weitzman, et al.","author":"Notin Pascal","year":"2023","unstructured":"Pascal Notin, Aaron Kollasch, Daniel Ritter, Lood Van Niekerk, Steffanie Paul, Han Spinner, Nathan Rollins, Ada Shaw, Rose Orenbuch, Ruben Weitzman, et al., 2023. Proteingym: Large-scale benchmarks for protein fitness prediction and design. Advances in neural information processing systems, Vol. 36 (2023), 64331-64379."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Nuala A O'Leary Mathew W Wright J Rodney Brister Stacy Ciufo Diana Haddad Rich McVeigh Bhanu Rajput Barbara Robbertse Brian Smith-White Danso Ako-Adjei et al. 2016. Reference sequence (RefSeq) database at NCBI: current status taxonomic expansion and functional annotation. Nucleic acids research Vol. 44 D1 (2016) D733-D745.","DOI":"10.1093\/nar\/gkv1189"},{"key":"e_1_3_2_1_33_1","unstructured":"Yuan-Fei Pan Yong He Yu-Qi Liu Yong-Tao Shan Shu-Ning Liu Jia-Hao Ma Xue Liu Xiaoyun Pan Yinqi Bai Zan Xu et al. 2025. Predicting the evolutionary and functional landscapes of viruses with a unified nucleotide-protein language model: Lucavirus. bioRxiv (2025) 2025-06."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-60872-5"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-17123-w"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.59247\/jahir.v2i3.298"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ygeno.2022.110414"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40168-017-0283-5"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40484-019-0187-4"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00872-0"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1128\/JVI.00694-10"},{"key":"e_1_3_2_1_42_1","volume-title":"Quasispecies theory and emerging viruses: challenges and applications. npj Viruses","author":"Sardany\u00e9s Josep","year":"2024","unstructured":"Josep Sardany\u00e9s, Celia Perales, Esteban Domingo, and Santiago F Elena. 2024. Quasispecies theory and emerging viruses: challenges and applications. npj Viruses, Vol. 2, 1 (2024), 54."},{"key":"e_1_3_2_1_43_1","volume-title":"Proceedings of the 41st International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"43648","author":"Schiff Yair","year":"2024","unstructured":"Yair Schiff, Chia Hsiang Kao, Aaron Gokaslan, Tri Dao, Albert Gu, and Volodymyr Kuleshov. 2024. Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling. In Proceedings of the 41st International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 235), Ruslan Salakhutdinov, Zico Kolter, Katherine Heller, Adrian Weller, Nuria Oliver, Jonathan Scarlett, and Felix Berkenkamp (Eds.). PMLR, 43632-43648."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymeth.2020.05.018"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42003-025-08982-0"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-65066-7"},{"key":"e_1_3_2_1_48_1","first-page":"737","volume-title":"Nature","volume":"171","author":"Watson James D","year":"1953","unstructured":"James D Watson and Francis HC Crick. 1953. Molecular structure of nucleic acids: a structure for deoxyribose nucleic acid. Nature, Vol. 171, 4356 (1953), 737-738."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.3389\/fbioe.2025.1537471"},{"key":"e_1_3_2_1_50_1","volume-title":"Improved metagenomic analysis with Kraken 2. Genome biology","author":"Wood Derrick E","year":"2019","unstructured":"Derrick E Wood, Jennifer Lu, and Ben Langmead. 2019. Improved metagenomic analysis with Kraken 2. Genome biology, Vol. 20, 1 (2019), 257."},{"key":"e_1_3_2_1_51_1","unstructured":"Wei Wu Qiuyi Li Yuanyuan Zhang Zhihao Zhan Ruipu Chen Mingyang Li Kun Fu Junyan Qi Yongzhou Bao Chao Wang et al. 2025. GENERator: a long-context generative genomic foundation model. arXiv preprint arXiv:2502.07272 (2025)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2548"},{"key":"e_1_3_2_1_53_1","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv et al. 2025. Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.304"},{"key":"e_1_3_2_1_55_1","volume-title":"R Curtis Hendrickson, et al.","author":"Zerbini Francisco Murilo","year":"2023","unstructured":"Francisco Murilo Zerbini, Stuart G Siddell, Elliot J Lefkowitz, Arcady R Mushegian, Evelien M Adriaenssens, Poliane Alfenas-Zerbini, Donald M Dempsey, Bas E Dutilh, Maria Laura Garcia, R Curtis Hendrickson, et al., 2023. Changes to virus taxonomy and the ICTV Statutes ratified by the International Committee on Taxonomy of Viruses (2023). Archives of virology, Vol. 168, 7 (2023), 175."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"crossref","unstructured":"Liang Zhang Hua Pang Chenghao Zhang Song Li Yang Tan Fan Jiang Mingchen Li Yuanxi Yu Ziyi Zhou Banghao Wu et al. 2025. VenusMutHub: a systematic evaluation of protein mutation effect predictors on small-scale experimental data. Acta Pharmaceutica Sinica B (2025).","DOI":"10.1016\/j.apsb.2025.03.028"},{"key":"e_1_3_2_1_57_1","first-page":"41642","volume-title":"International Conference on Learning Representations","volume":"2024","author":"Zhou Zhihan","year":"2024","unstructured":"Zhihan Zhou, Yanrong Ji, Weijian Li, Pratik Dutta, Ramana Davuluri, and Han Liu. 2024. DNABERT-2: Efficient foundation model and benchmark for multi-species genomes. In International Conference on Learning Representations, Vol. 2024. 41642-41665."},{"key":"e_1_3_2_1_58_1","unstructured":"Zhihan Zhou Robert Riley Satria Kautsar Weimin Wu Rob Egan Steven Hofmeyr Shira Goldhaber-Gordon Mutian Yu Harrison Ho Fengchen Liu et al. 2025a. GenomeOcean: An Efficient Genome Foundation Model Trained on Large-Scale Metagenomic Assemblies. bioRxiv (2025) 2025-01."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaf188"},{"key":"e_1_3_2_1_60_1","volume-title":"NeurIPS 2024 Workshop on AI for New Drug Modalities. https:\/\/openreview.net\/forum?id=Gzo3JMPY8w","author":"Zou Shuxian","unstructured":"Shuxian Zou, Tianhua Tao, Sazan Mahbub, Caleb Ellington, Robin Jonathan Algayres, Dian Li, Yonghao Zhuang, Hongyi Wang, Le Song, and Eric P. Xing. 2024. A Large-Scale Foundation Model for RNA Function and Structure Prediction. In NeurIPS 2024 Workshop on AI for New Drug Modalities. https:\/\/openreview.net\/forum?id=Gzo3JMPY8w"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:20:27Z","timestamp":1786065627000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3819057"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":60,"alternative-id":["10.1145\/3770855.3819057","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3819057","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}