{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T01:08:35Z","timestamp":1773709715580,"version":"3.50.1"},"reference-count":41,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["NSF-IIS-2145314"],"award-info":[{"award-number":["NSF-IIS-2145314"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["NSF-IIS-2514834"],"award-info":[{"award-number":["NSF-IIS-2514834"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>As the SARS-CoV-2 virus rapidly evolves, predicting the trajectory of viral mutations has become a critical yet complex task. A deep understanding of future mutation patterns, in particular the mutations that will prevail in the near future, is vital in steering diagnostics, therapeutics, and vaccine strategies for disease control.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>In this study, we developed a model to forecast future SARS-CoV-2 mutation surges in real-time, using historical mutation frequency data from the USA. We transformed the temporal prediction problem into a supervised learning framework using a sliding window approach. This involved breaking the time series of mutation frequencies into very short segments. Considering the time-dependent nature of the data, we focused on modeling the first-order derivative of the mutation frequency. We predicted the final derivative in each segment based on the preceding derivatives, employing various machine learning methods, including random forest, XGBoost, support vector machine, and neural network models. Empowered by the novel transformation strategy and the high capacity of machine learning models, we observed low prediction error that is confined within 0.1% and 1% when making predictions of mutation rates for the future 30 and 80\u2009days, respectively. In addition, the method also led to a notable increase in prediction accuracy compared to traditional time-series models, as evidenced by much lower MAE (Mean Absolute Error) and MSE (Mean Squared Error) for predictions made within different time horizons. To further assess the method\u2019s effectiveness and robustness in predicting mutation patterns for unforeseen mutations, we first designed a synthetic case where we categorized all mutations into three major patterns. The model demonstrated its robustness by accurately predicting unseen mutation patterns when training on data from two pattern categories while testing on the third pattern category, showcasing its potential in forecasting a variety of mutation trajectories. We then applied our method to prediction for a recent time frame between 1 January 2025 and 10 June 2025, for both the USA and UK, where the model training was conducted using frequency sequence data collected between 12 December 2019 and 26 January 2023 in the USA. The model demonstrated superior performance for both datasets.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>To enhance accessibility and utility, we built our methodology into a GitHub package (https:\/\/github.com\/ZhouXY199502\/SWD). Our method has the potential applicability to study other infectious diseases or forecasting tasks, thus extending its relevance beyond the current COVID pandemic.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf508","type":"journal-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T23:18:26Z","timestamp":1758323906000},"source":"Crossref","is-referenced-by-count":1,"title":["Predicting the trend of SARS-CoV-2 mutation frequencies using historical data"],"prefix":"10.1093","volume":"41","author":[{"given":"Xinyu","family":"Zhou","sequence":"first","affiliation":[{"name":"Center for Computational Biology and Bioinformatics, Department of Medical and Molecular Genetics, School of Medicine, Indiana University , Indianapolis, IN, 46202,","place":["United States"]},{"name":"Department of Computer Science, Indiana University Bloomington , Bloomington, IN, 47408,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Yan","sequence":"additional","affiliation":[{"name":"Division of Microbiology Devices (DMD), Office of In Vitro Diagnostics and Radiological Health (OHT7), Center for Devices and Radiological Health (CDRH), U.S. Food and Drug Administration , Silver Spring, MD, 20993,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"Hu","sequence":"additional","affiliation":[{"name":"Center for Computational Biology and Bioinformatics, Department of Medical and Molecular Genetics, School of Medicine, Indiana University , Indianapolis, IN, 46202,","place":["United States"]},{"name":"Carmel High School , Carmel, IN, 46032,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haixu","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Indiana University Bloomington , Bloomington, IN, 47408,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1656-8939","authenticated-orcid":false,"given":"Yijie","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Indiana University Bloomington , Bloomington, IN, 47408,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Information Systems and Operations Management, Ball State University , Muncie, IN, 47306,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Center for Computational Biology and Bioinformatics, Department of Medical and Molecular Genetics, School of Medicine, Indiana University , Indianapolis, IN, 46202,","place":["United States"]},{"name":"Department of Biomedical Engineering, Oregon Health and Science University , Portland, OR, 97201,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8645-848X","authenticated-orcid":false,"given":"Sha","family":"Cao","sequence":"additional","affiliation":[{"name":"Center for Computational Biology and Bioinformatics, Department of Medical and Molecular Genetics, School of Medicine, Indiana University , Indianapolis, IN, 46202,","place":["United States"]},{"name":"Department of Biomedical Engineering, Oregon Health and Science University , Portland, OR, 97201,","place":["United States"]},{"name":"Department of Biostatistics and Health Data Science, School of Medicine, Indiana University , Indianapolis, IN, 46202,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2025,9,17]]},"reference":[{"key":"2025101607430232200_btaf508-B1","first-page":"1267","article-title":"From alpha to omicron: how different variants of concern of the sars-coronavirus-2 impacted the world","volume":"12","author":"Andre","year":"2023","journal-title":"Biology (Basel)"},{"key":"2025101607430232200_btaf508-B2","doi-asserted-by":"crossref","first-page":"17646","DOI":"10.1021\/jacs.1c07965","article-title":"Predicting mutational effects on receptor binding of the spike protein of SARS-CoV-2 variants","volume":"143","author":"Bai","year":"2021","journal-title":"J Am Chem Soc"},{"key":"2025101607430232200_btaf508-B3","first-page":"1255","article-title":"Evolution and epidemic spread of SARS-CoV-2 in Brazil","volume":"369","author":"Candido","year":"2020","journal-title":"Science (1979)"},{"key":"2025101607430232200_btaf508-B4","first-page":"162","article-title":"SARS-CoV-2 variant biology: immune escape, transmission and fitness","volume":"21","author":"Carabelli","year":"2023","journal-title":"Nat Rev Microbiol"},{"key":"2025101607430232200_btaf508-B5","doi-asserted-by":"crossref","first-page":"e63409","DOI":"10.7554\/eLife.63409","article-title":"COVID-19 cg enables SARS-CoV-2 mutation and lineage tracking by locations and dates of interest","volume":"10","author":"Chen","year":"2021","journal-title":"Elife"},{"key":"2025101607430232200_btaf508-B6","doi-asserted-by":"crossref","first-page":"113193","DOI":"10.1016\/j.chaos.2023.113193","article-title":"Competition of SARS-CoV-2 variants on the pandemic transmission dynamics","volume":"169","author":"Chen","year":"2023","journal-title":"Chaos Solitons Fractals"},{"key":"2025101607430232200_btaf508-B7","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1038\/s41588-022-01033-y","article-title":"Global landscape of SARS-CoV-2 genomic surveillance and data sharing","volume":"54","author":"Chen","year":"2022","journal-title":"Nat Genet"},{"key":"2025101607430232200_btaf508-B8","doi-asserted-by":"crossref","first-page":"145","DOI":"10.3934\/publichealth.2023012","article-title":"Sources, diffusion and prediction in COVID-19 pandemic: lessons learned to face next health emergency","volume":"10","author":"Coccia","year":"2023","journal-title":"AIMS Public Health"},{"key":"2025101607430232200_btaf508-B9","first-page":"708","article-title":"Establishment and lineage dynamics of the SARS-CoV-2 epidemic in the uk","volume":"371","author":"Du Plessis","year":"2021","journal-title":"Science (1979)"},{"key":"2025101607430232200_btaf508-B10","doi-asserted-by":"crossref","first-page":"512","DOI":"10.1038\/s41592-023-01769-3","article-title":"Outbreak. info genomic reports: scalable and dynamic surveillance of SARS-CoV-2 variants and mutations","volume":"20","author":"Gangavarapu","year":"2023","journal-title":"Nat Methods"},{"key":"2025101607430232200_btaf508-B11","doi-asserted-by":"crossref","first-page":"2212","DOI":"10.1056\/NEJMoa2105000","article-title":"Vaccine breakthrough infections with SARS-CoV-2 variants","volume":"384","author":"Hacisuleyman","year":"2021","journal-title":"N Engl J Med"},{"key":"2025101607430232200_btaf508-B12","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1038\/s41579-021-00573-0","article-title":"SARS-CoV-2 variants, spike mutations and immune escape","volume":"19","author":"Harvey","year":"2021","journal-title":"Nat Rev Microbiol"},{"key":"2025101607430232200_btaf508-B13","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1146\/annurev-med-042921-020956","article-title":"COVID-19: challenges of viral variants","volume":"74","author":"Jacobs","year":"2023","journal-title":"Annu Rev Med"},{"key":"2025101607430232200_btaf508-B14","doi-asserted-by":"crossref","first-page":"147020","DOI":"10.1016\/j.gene.2022.147020","article-title":"Geographical distribution of host\u2019s specific SARS-CoV-2 mutations in the early phase of the covid-19 pandemic","volume":"851","author":"Khalid","year":"2023","journal-title":"Gene"},{"key":"2025101607430232200_btaf508-B15","doi-asserted-by":"crossref","first-page":"2664","DOI":"10.1016\/j.asoc.2010.10.015","article-title":"A novel hybridization of artificial neural networks and arima models for time series forecasting","volume":"11","author":"Khashei","year":"2011","journal-title":"Appl Soft Comput"},{"key":"2025101607430232200_btaf508-B16","doi-asserted-by":"crossref","first-page":"594","DOI":"10.1002\/jcc.27025","article-title":"Binding of human ACE2 and RBD of omicron enhanced by unique interaction patterns among SARS-CoV-2 variants of concern","volume":"44","author":"Kim","year":"2023","journal-title":"J Comput Chem"},{"key":"2025101607430232200_btaf508-B18","doi-asserted-by":"crossref","first-page":"997","DOI":"10.1016\/j.cell.2020.04.023","article-title":"Genomic epidemiology of SARS-CoV-2 in Guangdong province, China","volume":"181","author":"Lu","year":"2020","journal-title":"Cell"},{"key":"2025101607430232200_btaf508-B19","doi-asserted-by":"crossref","first-page":"eabk3445","DOI":"10.1126\/scitranslmed.abk3445","article-title":"Predicting the mutational drivers of future SARS-CoV-2 variants of concern","volume":"14","author":"Maher","year":"2022","journal-title":"Sci Transl Med"},{"key":"2025101607430232200_btaf508-B20","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1111\/joes.12429","article-title":"Machine learning advances for time series forecasting","volume":"37","author":"Masini","year":"2023","journal-title":"J Econ Surv"},{"key":"2025101607430232200_btaf508-B21","doi-asserted-by":"crossref","first-page":"1800","DOI":"10.3389\/fmicb.2020.01800","article-title":"Geographic and genomic distribution of SARS-CoV-2 mutations","volume":"11","author":"Mercatelli","year":"2020","journal-title":"Front Microbiol"},{"key":"2025101607430232200_btaf508-B22","doi-asserted-by":"crossref","first-page":"e82980","DOI":"10.7554\/eLife.82980","article-title":"Future COVID19 surges prediction based on SARS-CoV-2 mutations surveillance","volume":"12","author":"Najar","year":"2023","journal-title":"Elife"},{"key":"2025101607430232200_btaf508-B23","author":"Oreshkin","year":"2019"},{"key":"2025101607430232200_btaf508-B24","doi-asserted-by":"crossref","first-page":"1518","DOI":"10.1038\/s41591-021-01472-w","article-title":"The next phase of SARS-CoV-2 surveillance: real-time molecular epidemiology","volume":"27","author":"Oude Munnink","year":"2021","journal-title":"Nat Med"},{"key":"2025101607430232200_btaf508-B25","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1186\/s12967-020-02344-6","article-title":"Emerging SARS-CoV-2 mutation hot spots include a novel rna-dependent-rna polymerase variant","volume":"18","author":"Pachetti","year":"2020","journal-title":"J Transl Med"},{"key":"2025101607430232200_btaf508-B26","first-page":"100232","article-title":"Beyond COVID-19: do biothermodynamic properties allow predicting the future evolution of SARS-CoV-2 variants?","volume":"22","author":"Popovic","year":"2022","journal-title":"Microb Risk Anal"},{"key":"2025101607430232200_btaf508-B27","author":"Ruder","year":"2017"},{"key":"2025101607430232200_btaf508-B28","doi-asserted-by":"crossref","first-page":"1181","DOI":"10.1016\/j.ijforecast.2019.07.001","article-title":"Deepar: probabilistic forecasting with autoregressive recurrent networks","volume":"36","author":"Salinas","year":"2020","journal-title":"Int J Forecast"},{"key":"2025101607430232200_btaf508-B29","first-page":"214","author":"Sateesh Babu","year":"2016"},{"key":"2025101607430232200_btaf508-B30","doi-asserted-by":"crossref","first-page":"778","DOI":"10.3390\/clinpract11040093","article-title":"Analysis of the Delta variant b. 1.617. 2 covid-19","volume":"11","author":"Shiehzadegan","year":"2021","journal-title":"Clin Pract"},{"key":"2025101607430232200_btaf508-B31","author":"Singer","year":"2020"},{"key":"2025101607430232200_btaf508-B32","doi-asserted-by":"crossref","first-page":"757","DOI":"10.1038\/s41576-021-00408-x","article-title":"The biological and clinical significance of emerging SARS-CoV-2 variants","volume":"22","author":"Tao","year":"2021","journal-title":"Nat Rev Genet"},{"key":"2025101607430232200_btaf508-B33","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1080\/00031305.2017.1380080","article-title":"Forecasting at scale","volume":"72","author":"Taylor","year":"2018","journal-title":"Am Stat"},{"key":"2025101607430232200_btaf508-B34","doi-asserted-by":"crossref","first-page":"a041390","DOI":"10.1101\/cshperspect.a041390","article-title":"The evolution and biology of SARS-CoV-2 variants","volume":"12","author":"Telenti","year":"2022","journal-title":"Cold Spring Harb Perspect Med"},{"key":"2025101607430232200_btaf508-B11473364","doi-asserted-by":"publisher","first-page":"815389","DOI":"10.3389\/fmed.2022.815389","article-title":"SARS-cov-2 mutations and their impact on diagnostics, therapeutics and vaccines","volume":"9","author":"Thakur","year":"2022","journal-title":"Front Med (Lausanne)"},{"key":"2025101607430232200_btaf508-B35","doi-asserted-by":"crossref","first-page":"4267","DOI":"10.3390\/math10224267","article-title":"Covid-19 genome sequence analysis for new variant prediction and generation","volume":"10","author":"Ullah","year":"2022","journal-title":"Mathematics"},{"key":"2025101607430232200_btaf508-B36","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.cell.2020.11.020","article-title":"Evaluating the effects of SARS-CoV-2 spike mutation d614g on transmissibility and pathogenicity","volume":"184","author":"Volz","year":"2021","journal-title":"Cell"},{"key":"2025101607430232200_btaf508-B37","doi-asserted-by":"crossref","first-page":"1037","DOI":"10.1001\/jama.2021.2294","article-title":"SARS-CoV-2 variants of concern in the United States\u2014challenges and opportunities","volume":"325","author":"Walensky","year":"2021","journal-title":"JAMA"},{"key":"2025101607430232200_btaf508-B38"},{"key":"2025101607430232200_btaf508-B39","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/S0893-6080(05)80023-1","article-title":"Stacked generalization","volume":"5","author":"Wolpert","year":"1992","journal-title":"Neural Networks"},{"key":"2025101607430232200_btaf508-B40","doi-asserted-by":"crossref","first-page":"1188","DOI":"10.1038\/s41564-021-00954-4","article-title":"SARS-CoV-2 variant prediction and antiviral drug design are enabled by rbd in vitro evolution","volume":"6","author":"Zahradn\u00edk","year":"2021","journal-title":"Nat Microbiol"},{"key":"2025101607430232200_btaf508-B41","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/S0925-2312(01)00702-0","article-title":"Time series forecasting using a hybrid arima and neural network model","volume":"50","author":"Zhang","year":"2003","journal-title":"Neurocomputing (Amst)"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaf508\/64302284\/btaf508.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/10\/btaf508\/64302284\/btaf508.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/10\/btaf508\/64302284\/btaf508.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T11:43:23Z","timestamp":1760615003000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btaf508\/8256687"}},"subtitle":[],"editor":[{"given":"Zhiyong","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,9,17]]},"references-count":41,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,10,2]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf508","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,10]]},"published":{"date-parts":[[2025,9,17]]},"article-number":"btaf508"}}