Prediction of virus-host association using protein language models and multiple instance learning

Predicting virus-host associations is essential to determine the specific host species that viruses interact with, and discover if new viruses infect humans and animals. Currently, the host of the majority of viruses is unknown, particularly in microbiomes. To address this challenge, we introduce EvoMIL, a deep learning method that predicts the host species for viruses from viral sequences only. It also identifies important viral proteins that significantly contribute to host prediction. The method combines a pre-trained large protein language model (ESM) and attention-based multiple instance learning to allow protein-orientated predictions. Our results show that protein embeddings capture stronger predictive signals than sequence composition features, including amino acids, physiochemical properties, and DNA k-mers. In multi-host prediction tasks, EvoMIL achieves median F1 score improvements of 8.6%, 12.3%, and 4.1% in prokaryotic hosts, and 0.5%, 1.8% and 3% in eukaryotic hosts. EvoMIL binary classifiers achieve impressive AUC over 0.95 for all prokaryotic and range from roughly 0.8 to 0.9 for eukaryotic hosts. Furthermore, EvoMIL estimates the importance of single proteins in the prediction task and maps them to an embedding landscape of all viral proteins, where proteins with similar functions are distinctly clustered together, highlighting the ability of EvoMIL to capture key proteins in virus-host specificity. Author summaryBeing able to predict which viruses can infect which host species, and identifying the specific proteins that are involved in these interactions, are fundamental tasks in virology. Traditional methods for predicting these interactions rely on common manual features among proteins, overlooking the structure of the protein "language" encoded in individual proteins. We have developed a novel method that combines a protein language model and multiple instance learning to allow host prediction directly from protein sequences, without the need to extract manual features. This method significantly improved prediction accuracy and revealed key proteins involved in virus-host interactions.