Forecasting viral evolution from phylogenetic trees
- 1Stanford University
Abstract
Viral mutation forecasting plays a key role in pandemic preparedness by enabling researchers to anticipate novel variants and design proactive interventions. Evolutionary histories, represented as phylogenetic trees, offer key insights into the emergence of past and present strains, yet their role in predicting future sequence changes remains largely unexplored. We introduce antiGen, a machine learning model that forecasts the evolutionary future of viruses by learning from their evolutionary past. antiGen achieves state-of-the-art performance for predicting mutations to the SARS-CoV-2 spike protein, anticipating never-before-seen mutations and mutations that emerge years after the model's training window. antiGen-forecasted spike mutations also retain pseudoviral infectivity in vitro. Moreover, antiGen demonstrates leading predictive performance on surface proteins of influenza virus, respiratory syncytial virus, and dengue virus despite far less available sequencing data. Viral evolution models that explicitly learn from phylogenetic structure offer a valuable resource for applications ranging from epidemiological modeling to therapeutic development.
Related
- Phylogenetic parallelograms: visual comparison of discordant phylogenetic trees
- Phylogenetic characterization of circulating bovine viral diarrhea virus subgenotypes 1b and 1l in cattle from the Mediterranean region of Türkiye
- An extension of the classic Buneman theorem from phylogenetic trees to networks
- Rclade: automated taxonomic collapsing and geological-timescale annotation of time-calibrated phylogenetic trees in R
- BME-like Quartet Weights for Phylogenetic Trees
BibTeX
@misc{specht2026forecasting,
title = {{Forecasting viral evolution from phylogenetic trees}},
author = {I. Specht and S. Park and S. Chithrananda and C. L. Driscoll and G. Brixi and J. A. Palacios and B. L. Hie},
howpublished = {bioRxiv},
year = {2026},
month = aug,
doi = {10.64898/2026.08.27.741102},
url = {https://www.biorxiv.org/content/10.64898/2026.08.27.741102v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Forecasting viral evolution from phylogenetic trees
AU - I. Specht
AU - S. Park
AU - S. Chithrananda
AU - C. L. Driscoll
AU - G. Brixi
AU - J. A. Palacios
AU - B. L. Hie
PY - 2026
DA - 2026/08/27
PB - bioRxiv
DO - 10.64898/2026.08.27.741102
UR - https://www.biorxiv.org/content/10.64898/2026.08.27.741102v1
AB - Viral mutation forecasting plays a key role in pandemic preparedness by enabling researchers to anticipate novel variants and design proactive interventions. Evolutionary histories, represented as phylogenetic trees, offer key insights into the emergence of past and present strains, yet their role in predicting future sequence changes remains largely unexplored. We introduce antiGen, a machine learning model that forecasts the evolutionary future of viruses by learning from their evolutionary past. antiGen achieves state-of-the-art performance for predicting mutations to the SARS-CoV-2 spike protein, anticipating never-before-seen mutations and mutations that emerge years after the model's training window. antiGen-forecasted spike mutations also retain pseudoviral infectivity in vitro. Moreover, antiGen demonstrates leading predictive performance on surface proteins of influenza virus, respiratory syncytial virus, and dengue virus despite far less available sequencing data. Viral evolution models that explicitly learn from phylogenetic structure offer a valuable resource for applications ranging from epidemiological modeling to therapeutic development.
ER -