TEAM: A time‐enhanced attention‐based model for virus mutation prediction

Abstract

The evolution of severe acute respiratory syndrome coronavirus 2 (SARS‐CoV‐2) during the coronavirus disease 2019 (COVID‐19) pandemic highlights the critical need for predicting virus mutations in order to stay ahead of infectious diseases. Here, we present the time‐enhanced attention‐based model (TEAM), which combines phylogenetic sampling with deep learning to improve virus mutation prediction accuracy. TEAM introduces a novel time‐enhanced phylogenetic sampling strategy that preserves both evolutionary and temporal sequence relationships, enhancing its ability to predict site‐specific mutations as a multi‐class classification task. The framework leverages evolutionary scale modeling embeddings and a dual‐attention mechanism to capture sequence‐level patterns and temporal dynamics. Experiments on the SARS‐CoV‐2 spike protein dataset show that TEAM substantially outperforms existing methods. Further evaluations on membrane protein and H1N1 datasets confirm its robustness and generalizability. In practice, TEAM provides a scalable and interpretable solution for mutation prediction, offering valuable insights for evolutionary research and public health planning.