EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Generative prediction of real-world prevalent SARS-CoV-2 mutation with in silico virus evolution

Xudong Liu, Zhiwei Nie, Haorui Si, Xurui Shen, Yutian Liu, Xiansong Huang, Tianyi Dong, Fan Xu, Zhixiang Ren, Peng Zhou, Jie Chen

Briefings in Bioinformatics · 2025

DOI: 10.1093/bib/bbaf276 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Xudong Liu und 10 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic and Computer Engineering, Peking University, Shenzhen, China. Hauptthemen laut MEDLINE: SARS-CoV-2, Mutation, COVID-19, Evolution, Molecular. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shenzhen Medical Research Funds in China, Natural Science Foundation of China, Self-Supporting Program of Guangzhou Laboratory.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SARS-CoV-2MutationCOVID-19Evolution, MolecularHumansComputer SimulationDeep LearningComputational Biology

Stichwörter der Autor:innen

generative deep learningin silico virus evolutionmutation predictionprotein language model

Autor:innen und Institutionen

  • School of Electronic and Computer Engineering, Peking University, Shenzhen, China.
  • Pengcheng Laboratory, Shenzhen, China.
  • Guangzhou Medical University, Guangzhou, China.
  • State Key Laboratory of Respiratory Disease, Guangzhou, China.
  • Guangzhou National Laboratory, Guangzhou, China.
  • School of Computer Science, Peking University, Beijing, China.

Förderung

  • Shenzhen Medical Research Funds in China
  • Natural Science Foundation of China
  • Self-Supporting Program of Guangzhou Laboratory
  • Young Scientists Program of Guangzhou Laboratory
  • Guangdong S&T Program
  • AI for Science (AI4S)-Preferred Program, Peking University Shenzhen Graduate School, China

Zitieren

APA

Liu, X., Nie, Z., Si, H., Shen, X., Liu, Y., Huang, X., Dong, T., Xu, F., Ren, Z., Zhou, P., & Chen, J. (2025). Generative prediction of real-world prevalent SARS-CoV-2 mutation with in silico virus evolution. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf276

Vancouver

Liu X, Nie Z, Si H, Shen X, Liu Y, Huang X, et al. Generative prediction of real-world prevalent SARS-CoV-2 mutation with in silico virus evolution. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf276

BibTeX
@article{Liu2025,
  author = {Liu, Xudong and Nie, Zhiwei and Si, Haorui and Shen, Xurui and Liu, Yutian and Huang, Xiansong and Dong, Tianyi and Xu, Fan and Ren, Zhixiang and Zhou, Peng and Chen, Jie},
  title = {Generative prediction of real-world prevalent SARS-CoV-2 mutation with in silico virus evolution},
  journal = {Briefings in Bioinformatics},
  year = {2025},
  doi = {10.1093/bib/bbaf276}
}
Kostenlos starten →