biostudies-literatureLi LChinese Academy of SciencesMinistry of Science and Technology of the People's Republic of ChinaMinistry of Science and Technology of the People's Republic of ChinaNational Natural Science Foundation of ChinaAlliance of National and International·Science Organizations for the Belt·and·Road RegionsNational Key Research & Development Program of ChinaBeijing Municipal Science & Technology Commission, Administrative Commission of Zhongguancun Science Parke2405058https://www.ebi.ac.uk/biostudies/studies/S-EPMC11615786biostudies-literatureUnknown11(45)The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has evolved many high-risk variants, resulting in repeated COVID-19 waves over the past years. Therefore, accurate early warning of high-risk variants is vital for epidemic prevention and control. However, detecting high-risk variants through experimental and epidemiological research is time-consuming and often lags behind the emergence and spread of these variants. In this study, HiRisk-Detector a machine learning algorithm based on haplotype network, is developed for computationally early detecting high-risk SARS-CoV-2 variants. Leveraging over 7.6 million high-quality and complete SARS-CoV-2 genomes and metadata, the effectiveness, robustness, and generalizability of HiRisk-Detector are validated. First, HiRisk-Detector isAdvanced science (Weinheim, Baden-Wurttemberg, Germany)Machine Learning Early Detection of SARS-CoV-2 High-Risk Variants.PMC116157863227071832170678Z211100002121006ANSO-CR-KP-2022-092023YFC30415002023YFC2604400XDB380302002021YFF0703703Y2021038Li CZhang ZBao YZhao WSong SLuo HZou DLi LLi NXue YfalseMachine Learning Early Detection of SARS-CoV-2 High-Risk Variants.The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has evolved many high-risk variants, resulting in repeated COVID-19 waves over the past years. Therefore, accurate early warning of high-risk variants is vital for epidemic prevention and control. However, detecting high-risk variants through experimental and epidemiological research is time-consuming and often lags behind the emergence and spread of these variants. In this study, HiRisk-Detector a machine learning algorithm based on haplotype network, is developed for computationally early detecting high-risk SARS-CoV-2 variants. Leveraging over 7.6 million high-quality and complete SARS-CoV-2 genomes and metadata, the effectiveness, robustness, and generalizability of HiRisk-Detector are validated. First, HiRisk-Detector is2024-01-01T00:00:00Z2024 Dec2026-06-03T00:35:50.672Z2025-04-19T14:40:24.147ZS-EPMC116157863940140010.1002/advs.202405058