Dive into Machine Learning Algorithms for Influenza Virus Host Prediction with Hemagglutinin Sequences
Yanhua Xu, Dominik Wojtczak
TL;DR
This study addresses host prediction for Influenza A by analyzing hemagglutinin sequences with a broad ML toolkit. It compares PSSM-based representations (EG-PSSM, GDPC-PSSM, ER-PSSM) and alignment-free word embeddings, evaluated across diverse models including Transformer and XGBoost, using nested cross-validation on two GISAID-based datasets. Key findings show that Transformer-based architectures (notably 5-gram Transformer) and ER-PSSM-XGBoost achieve top performance, while 3-gram word embeddings offer strong robustness; incomplete sequences have limited impact. The work demonstrates viable, scalable pathways for rapid host prediction from HA data and highlights tradeoffs between engineered features and end-to-end learning, with implications for surveillance and outbreak response.
Abstract
Influenza viruses mutate rapidly and can pose a threat to public health, especially to those in vulnerable groups. Throughout history, influenza A viruses have caused pandemics between different species. It is important to identify the origin of a virus in order to prevent the spread of an outbreak. Recently, there has been increasing interest in using machine learning algorithms to provide fast and accurate predictions for viral sequences. In this study, real testing data sets and a variety of evaluation metrics were used to evaluate machine learning algorithms at different taxonomic levels. As hemagglutinin is the major protein in the immune response, only hemagglutinin sequences were used and represented by position-specific scoring matrix and word embedding. The results suggest that the 5-grams-transformer neural network is the most effective algorithm for predicting viral sequence origins, with approximately 99.54% AUCPR, 98.01% F1 score and 96.60% MCC at a higher classification level, and approximately 94.74% AUCPR, 87.41% F1 score and 80.79% MCC at a lower classification level.