tetano
Editor, Senior Moderator
Brief Bioinform
. 2025 May 1;26(3):bbaf276.
doi: 10.1093/bib/bbaf276. Generative prediction of real-world prevalent SARS-CoV-2 mutation with in silico virus evolution
Xudong Liu[SUP] 1 [/SUP], Zhiwei Nie[SUP] 1 2 [/SUP], Haorui Si[SUP] 3 4 5 [/SUP], Xurui Shen[SUP] 5 [/SUP], Yutian Liu[SUP] 2 6 [/SUP], Xiansong Huang[SUP] 2 [/SUP], Tianyi Dong[SUP] 5 7 8 [/SUP], Fan Xu[SUP] 2 [/SUP], Zhixiang Ren[SUP] 2 [/SUP], Peng Zhou[SUP] 3 5 [/SUP], Jie Chen[SUP] 1 2 [/SUP]
Affiliations
Predicting the mutation prevalence trends of emerging viruses in the real world is an efficient means to update vaccines or drugs in advance. It is crucial to develop a computational method for the prediction of real-world prevalent SARS-CoV-2 mutations considering the impact of multiple selective pressures within and between hosts. Here, a deep-learning generative framework for real-world prevalent SARS-CoV-2 mutation prediction, named ViralForesight, is developed on top of protein language models and in silico virus evolution. Through the paradigm of host-to-herd in silico virus evolution, ViralForesight reproduced previous real-world prevalent SARS-CoV-2 mutations for multiple lineages with superior performance. More importantly, ViralForesight correctly predicted the future prevalent mutations that dominated the COVID-19 pandemic in the real world more than half a year in advance with in vitro experimental validation. Overall, ViralForesight demonstrates a proactive approach to the prevention of emerging viral infections, accelerating the process of discovering future prevalent mutations with the power of generative deep learning.
Keywords: generative deep learning; in silico virus evolution; mutation prediction; protein language model.
. 2025 May 1;26(3):bbaf276.
doi: 10.1093/bib/bbaf276. Generative prediction of real-world prevalent SARS-CoV-2 mutation with in silico virus evolution
Xudong Liu[SUP] 1 [/SUP], Zhiwei Nie[SUP] 1 2 [/SUP], Haorui Si[SUP] 3 4 5 [/SUP], Xurui Shen[SUP] 5 [/SUP], Yutian Liu[SUP] 2 6 [/SUP], Xiansong Huang[SUP] 2 [/SUP], Tianyi Dong[SUP] 5 7 8 [/SUP], Fan Xu[SUP] 2 [/SUP], Zhixiang Ren[SUP] 2 [/SUP], Peng Zhou[SUP] 3 5 [/SUP], Jie Chen[SUP] 1 2 [/SUP]
Affiliations
- PMID: 40532108
- DOI: 10.1093/bib/bbaf276
Predicting the mutation prevalence trends of emerging viruses in the real world is an efficient means to update vaccines or drugs in advance. It is crucial to develop a computational method for the prediction of real-world prevalent SARS-CoV-2 mutations considering the impact of multiple selective pressures within and between hosts. Here, a deep-learning generative framework for real-world prevalent SARS-CoV-2 mutation prediction, named ViralForesight, is developed on top of protein language models and in silico virus evolution. Through the paradigm of host-to-herd in silico virus evolution, ViralForesight reproduced previous real-world prevalent SARS-CoV-2 mutations for multiple lineages with superior performance. More importantly, ViralForesight correctly predicted the future prevalent mutations that dominated the COVID-19 pandemic in the real world more than half a year in advance with in vitro experimental validation. Overall, ViralForesight demonstrates a proactive approach to the prevention of emerging viral infections, accelerating the process of discovering future prevalent mutations with the power of generative deep learning.
Keywords: generative deep learning; in silico virus evolution; mutation prediction; protein language model.