Dive into Machine Learning Algorithms for Influenza Virus Host Prediction with Hemagglutinin Sequences

TL;DR

This study evaluates machine learning algorithms, especially a 5-grams-transformer neural network, for predicting the host origin of influenza viruses based on hemagglutinin sequences, achieving high accuracy and performance metrics.

Contribution

It introduces the use of hemagglutinin sequence representations and compares multiple ML algorithms, identifying the transformer neural network as the most effective for viral host prediction.

Findings

Transformer neural network achieved ~99.54% AUCPR at higher classification levels.

High accuracy metrics for the 5-grams-transformer neural network.

Effective prediction of viral sequence origins using hemagglutinin sequences.

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.