Deep-learning-enabled generative prevalent mutation prediction through host-to-herd in silico virus evolution
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 spanning from the host level to the herd level for prevalent mutation prediction as virus evolves within and b...
Saved in:
Published in | bioRxiv |
---|---|
Main Authors | , , , , , , , , , , |
Format | Paper |
Language | English |
Published |
Cold Spring Harbor
Cold Spring Harbor Laboratory Press
03.12.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | 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 spanning from the host level to the herd level for prevalent mutation prediction as virus evolves within and between hosts involving the impact of multiple selective pressures. Here, a deep-learning generative prediction framework for real-world prevalent mutations, GenPreMut, is developed with a novel host-to-herd selective pressure simulation strategy. Through the paradigm of host-to-herd in silico virus evolution, GenPreMut reproduces previous real-world prevalent mutations for multiple lineages with significant accuracy improvements over state-of-the-art methods. More importantly, GenPreMut correctly predicts future prevalent mutations that dominate the pandemic in the real world more than half a year in advance with in vitro experimental validation. Overall, GenPreMut demonstrates a proactive approach to the prevention of emerging viral infections, accelerating the process of discovering future prevalent mutations with the power of generative prediction.Competing Interest StatementThe authors have declared no competing interest. |
---|---|
DOI: | 10.1101/2024.11.28.625962 |