{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T06:33:30Z","timestamp":1789194810992,"version":"build-2803163510"},"reference-count":50,"publisher":"National Academy of Sciences","issue":"24","license":[{"start":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T00:00:00Z","timestamp":1749427200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NIH","award":["GM139571"],"award-info":[{"award-number":["GM139571"]}]}],"content-domain":{"domain":["www.pnas.org"],"crossmark-restriction":true},"short-container-title":["Proc. Natl. Acad. Sci. U.S.A."],"published-print":{"date-parts":[[2025,6,17]]},"abstract":"<jats:p>The early detection of high-fitness viral variants is critical for pandemic response, yet limited experimental resources at the onset of variant emergence hinder effective identification. To address this, we introduce an active learning framework, VIRAL (Viral Identification via Rapid Active Learning), that integrates protein language model, Gaussian process with uncertainty estimation, and a biophysical model to predict the fitness of novel variants in a few-shot learning setting. By benchmarking on past SARS-CoV-2 data, we demonstrate that our method accelerates the identification of high-fitness variants by up to fivefold compared to random sampling while requiring experimental characterization of fewer than 1% of possible variants. We also demonstrate that our framework effectively identifies sites that are frequently mutated during natural viral evolution with a predictive advantage of up to two years compared to baseline strategies, particularly those enabling antibody escape while preserving ACE2 binding. Through systematic analysis of different acquisition strategies, we show that incorporating uncertainty in variant selection enables broader exploration of the sequence landscape, leading to the identification of evolutionarily distant but potentially dangerous variants. Our results suggest that VIRAL could serve as an effective early warning system for identifying concerning SARS-CoV-2 variants and potentially emerging viruses with pandemic potential before they achieve widespread circulation.<\/jats:p>","DOI":"10.1073\/pnas.2503742122","type":"journal-article","created":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T15:00:42Z","timestamp":1749481242000},"update-policy":"https:\/\/doi.org\/10.1073\/pnas.cm10313","source":"Crossref","is-referenced-by-count":11,"title":["Predicting high-fitness viral protein variants with Bayesian active learning and biophysics"],"prefix":"10.1073","volume":"122","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2359-5185","authenticated-orcid":false,"given":"Marian","family":"Huot","sequence":"first","affiliation":[{"name":"Department of Chemistry and Chemical Biology","place":["Cambridge"]},{"name":"Harvard University","place":["Cambridge"]},{"name":"Laboratory of Physics of the Ecole Normale Sup\u00e9rieure","place":["Paris, France"]},{"name":"Department of Physics, CNRS UMR 8023 and Paris Sciences and Lettres Research","place":["Paris, France"]},{"name":"Sorbonne Universit\u00e9","place":["Paris, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5503-1838","authenticated-orcid":false,"given":"Dianzhuo","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Chemistry and Chemical Biology","place":["Cambridge"]},{"name":"Harvard University","place":["Cambridge"]},{"name":"John A. Paulson School of Engineering and Applied Sciences","place":["Cambridge"]},{"name":"Harvard University","place":["Cambridge"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiacheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Paul G. Allen Center for Computer Science and Engineering","place":["Seattle"]},{"name":"University of Washington","place":["Seattle"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4769-2265","authenticated-orcid":false,"given":"Eugene I.","family":"Shakhnovich","sequence":"additional","affiliation":[{"name":"Department of Chemistry and Chemical Biology","place":["Cambridge"]},{"name":"Harvard University","place":["Cambridge"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"341","published-online":{"date-parts":[[2025,6,9]]},"reference":[{"key":"e_1_3_4_1_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-21118-2"},{"key":"e_1_3_4_2_2","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.70658"},{"key":"e_1_3_4_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2022.06.005"},{"key":"e_1_3_4_4_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.abl6251"},{"key":"e_1_3_4_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2022.12.018"},{"key":"e_1_3_4_6_2","first-page":"162","article-title":"SARS-CoV-2 variant biology: Immune escape, transmission and fitness","volume":"21","author":"Carabelli A. M.","year":"2023","unstructured":"A. M. Carabelli , SARS-CoV-2 variant biology: Immune escape, transmission and fitness. Nat. Rev. Microbiol. 21, 162\u2013177 (2023).","journal-title":"Nat. Rev. Microbiol."},{"key":"e_1_3_4_7_2","doi-asserted-by":"publisher","DOI":"10.1128\/mbio.00135-22"},{"key":"e_1_3_4_8_2","first-page":"521","article-title":"Imprinted SARS-CoV-2 humoral immunity induces convergent omicron RBD evolution","volume":"614","author":"Cao Y.","year":"2023","unstructured":"Y. Cao , Imprinted SARS-CoV-2 humoral immunity induces convergent omicron RBD evolution. Nature 614, 521\u2013529 (2023).","journal-title":"Nature"},{"key":"e_1_3_4_9_2","doi-asserted-by":"publisher","DOI":"10.1002\/gch2.1018"},{"key":"e_1_3_4_10_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.abm1208"},{"key":"e_1_3_4_11_2","doi-asserted-by":"crossref","unstructured":"J. Ito A protein language model for exploring viral fitness landscapes. Nat. Commun. 16 4236 (2025).","DOI":"10.1101\/2024.03.15.584819"},{"key":"e_1_3_4_12_2","doi-asserted-by":"publisher","DOI":"10.1126\/scitranslmed.abk3445"},{"key":"e_1_3_4_13_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2314518121"},{"key":"e_1_3_4_14_2","doi-asserted-by":"publisher","DOI":"10.1002\/pro.2915"},{"key":"e_1_3_4_15_2","doi-asserted-by":"publisher","DOI":"10.1093\/molbev\/msy131"},{"key":"e_1_3_4_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.molcel.2024.06.028"},{"key":"e_1_3_4_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.bpj.2023.10.026"},{"key":"e_1_3_4_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2020.08.012"},{"key":"e_1_3_4_19_2","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.83442"},{"key":"e_1_3_4_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cels.2020.09.007"},{"key":"e_1_3_4_21_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.2c00752"},{"key":"e_1_3_4_22_2","doi-asserted-by":"publisher","DOI":"10.1039\/D0SC06805E"},{"key":"e_1_3_4_23_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1215251110"},{"key":"e_1_3_4_24_2","unstructured":"A. Gessner S. W. Ober O. Vickery D. Ogli\u0107 T. U\u00e7ar Active learning for affinity prediction of antibodies. arXiv [Preprint] (2024). https:\/\/arxiv.org\/pdf\/2406.07263 (Accessed 21 September 2024)."},{"key":"e_1_3_4_25_2","doi-asserted-by":"crossref","unstructured":"T. Hayes Simulating 500 million years of evolution with a language model. Science 387 850\u2013858 (2025).","DOI":"10.1126\/science.ads0018"},{"key":"e_1_3_4_26_2","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065704001899"},{"key":"e_1_3_4_27_2","first-page":"108322","article-title":"Structure-based design with tag-based purification and in-process biotinylation enable streamlined development of SARS-CoV-2 spike molecular probes","volume":"33","author":"Zhou T.","year":"2020","unstructured":"T. Zhou , Structure-based design with tag-based purification and in-process biotinylation enable streamlined development of SARS-CoV-2 spike molecular probes. SSRN Electron. J. 33, 108322 (2020).","journal-title":"SSRN Electron. J."},{"key":"e_1_3_4_28_2","doi-asserted-by":"crossref","unstructured":"T. Loux D. Wang E. I. Shakhnovich More structure less accuracy: ESM3\u2019s binding prediction paradox. bioRxiv [Preprint] (2024). https:\/\/doi.org\/10.1101\/2024.12.09.627585 (Accessed 15 December 2024).","DOI":"10.1101\/2024.12.09.627585"},{"key":"e_1_3_4_29_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06487-6"},{"key":"e_1_3_4_30_2","doi-asserted-by":"crossref","unstructured":"J. Meier R. Rao R. Verkuil J. Liu T. Sercu A. Rives Language models enable zero-shot prediction of the effects of mutations on protein function. Adv. Neural Inf. Process. Syst. 34 29287\u201329303 (2021).","DOI":"10.1101\/2021.07.09.450648"},{"key":"e_1_3_4_31_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-020-0521-4"},{"key":"e_1_3_4_32_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature13087"},{"key":"e_1_3_4_33_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2023.09.022"},{"key":"e_1_3_4_34_2","doi-asserted-by":"publisher","DOI":"10.1098\/rsif.2024.0598"},{"key":"e_1_3_4_35_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2104241118"},{"key":"e_1_3_4_36_2","doi-asserted-by":"crossref","unstructured":"P. M. Groth M. H. Kerrn L. Olsen J. Salomon W. Boomsma Kermut: Composite kernel regression for protein variant effects. bioRxiv [Preprint] (2024). https:\/\/doi.org\/10.48550\/arXiv.2407.00002 (Accessed 20 December 2024).","DOI":"10.1101\/2024.05.28.596219"},{"key":"e_1_3_4_37_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2020.06.025"},{"key":"e_1_3_4_38_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2852-1"},{"key":"e_1_3_4_39_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41594-020-0469-6"},{"key":"e_1_3_4_40_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03817-4"},{"key":"e_1_3_4_41_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2313681121"},{"key":"e_1_3_4_42_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.abq0839"},{"key":"e_1_3_4_43_2","doi-asserted-by":"crossref","unstructured":"V. Mohanty E. I. Shakhnovich Biophysical fitness landscape design traps viral evolution. bioRxiv [Preprint] (2025). https:\/\/doi.org\/10.1101\/2025.03.30.646233 (Accessed 1 April 2025).","DOI":"10.1101\/2025.03.30.646233"},{"key":"e_1_3_4_44_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-34506-z"},{"key":"e_1_3_4_45_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03807-6"},{"key":"e_1_3_4_46_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.ade2574"},{"key":"e_1_3_4_47_2","doi-asserted-by":"publisher","DOI":"10.1002\/gch2.1018"},{"key":"e_1_3_4_48_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.abf9302"},{"key":"e_1_3_4_49_2","doi-asserted-by":"publisher","DOI":"10.1093\/molbev\/mst010"},{"key":"e_1_3_4_50_2","unstructured":"M. Huot VIRAL. GitHub. https:\/\/github.com\/m-huot\/VIRAL. Deposited 21 May 2025."}],"container-title":["Proceedings of the National Academy of Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pnas.org\/doi\/pdf\/10.1073\/pnas.2503742122","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T15:01:01Z","timestamp":1749481261000},"score":1,"resource":{"primary":{"URL":"https:\/\/pnas.org\/doi\/10.1073\/pnas.2503742122"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,9]]},"references-count":50,"journal-issue":{"issue":"24","published-print":{"date-parts":[[2025,6,17]]}},"alternative-id":["10.1073\/pnas.2503742122"],"URL":"https:\/\/doi.org\/10.1073\/pnas.2503742122","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2025.03.12.642881","asserted-by":"object"}]},"ISSN":["0027-8424","1091-6490"],"issn-type":[{"value":"0027-8424","type":"print"},{"value":"1091-6490","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,9]]},"assertion":[{"value":"2025-03-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-06","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e2503742122"}}