CovTransformer: A transformer model for SARS-CoV-2 lineage frequency forecasting
Virus Evolution · 06.12.2024 · 10 (1)
DOI: 10.1093/ve/veae086 ↗Kurz gefasst
Fachartikel in der Zeitschrift Virus Evolution, online erschienen am 14.11.2024. Verfasst von Yinan Feng und 5 weiteren Autor:innen. Beteiligte Einrichtung: Earth and Environmental Sciences Division, Los Alamos National Laboratory, Los Alamos, NM, United States. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Laboratory Directed Research and Development, National Institute of Allergy and Infectious Diseases.
Abstract (Originalsprache)
With hundreds of SARS-CoV-2 lineages circulating in the global population, there is an ongoing need for predicting and forecasting lineage frequencies and thus identifying rapidly expanding lineages. Accurate prediction would allow for more focused experimental efforts to understand pathogenicity of future dominating lineages and characterize the extent of their immune escape. Here, we first show that the inherent noise and biases in lineage frequency data make a commonly-used regression-based approach unreliable. To address this weakness, we constructed a machine learning model for SARS-CoV-2 lineage frequency forecasting, called CovTransformer, based on the transformer architecture. We designed our model to navigate challenges such as a limited amount of data with high levels of noise and bias. We first trained and tested the model using data from the UK and the USA, and then tested the generalization ability of the model to many other countries and US states. Remarkably, the trained model makes accurate predictions two months into the future with high levels of accuracy both globally (in 31 countries with high levels of sequencing effort) and at the US-state level. Our model performed substantially better than a widely used forecasting tool, the multinomial regression model implemented in Nextstrain, demonstrating its utility in SARS-CoV-2 monitoring. Assuming a newly emerged lineage is identified and assigned, our test using retrospective data shows that our model is able to identify the dominating lineages 7 weeks in advance on average before they became dominant. Overall, our work demonstrates that transformer models represent a promising approach for SARS-CoV-2 forecasting and pandemic monitoring.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Earth and Environmental Sciences Division, Los Alamos National Laboratory, Los Alamos, NM, United States.
- Theoretical Biology and Biophysics, Theoretical Division, Los Alamos National Laboratory, Los Alamos, NM, United States.
- Department of Applied Mathematics, University of Washington, Seattle, WA, United States.
- Department of Computational Mathematics, Science and Engineering, Michigan State University, East Lansing, MI, United States.
- School of Data Science and Society, University of North Carolina at Chapel Hill, Chapel Hill, NC, United States.
ORCID-Profile: Michael Kupperman, Ruian Ke
Förderung
- Laboratory Directed Research and Development
- National Institute of Allergy and Infectious Diseases
Zitieren
APA
Feng, Y., Goldberg, E. E., Kupperman, M., Zhang, X., Lin, Y., & Ke, R. (2024). CovTransformer: A transformer model for SARS-CoV-2 lineage frequency forecasting. Virus Evolution, 10(1). https://doi.org/10.1093/ve/veae086
Vancouver
Feng Y, Goldberg EE, Kupperman M, Zhang X, Lin Y, Ke R. CovTransformer: A transformer model for SARS-CoV-2 lineage frequency forecasting. Virus Evolution. 2024;10(1). doi:10.1093/ve/veae086
BibTeX
@article{Feng2024,
author = {Feng, Yinan and Goldberg, Emma E and Kupperman, Michael and Zhang, Xitong and Lin, Youzuo and Ke, Ruian},
title = {CovTransformer: A transformer model for SARS-CoV-2 lineage frequency forecasting},
journal = {Virus Evolution},
year = {2024},
volume = {10},
number = {1},
doi = {10.1093/ve/veae086}
}
EUVIMED