InForecaster: Forecasting Influenza Hemagglutinin Mutations Through the Lens of Anomaly Detection

TL;DR

This paper introduces InForecaster, an anomaly detection-based approach for predicting influenza hemagglutinin mutations, addressing data imbalance issues and improving mutation detection accuracy using normal unmutated samples.

Contribution

The paper proposes a novel anomaly detection framework for influenza mutation prediction, leveraging normal sample representations to better identify rare mutations.

Findings

Effective detection of hemagglutinin mutations demonstrated on four datasets.

Outperforms existing methods in mutation prediction accuracy.

Addresses class imbalance by modeling mutations as anomalies.

Abstract

The influenza virus hemagglutinin is an important part of the virus attachment to the host cells. The hemagglutinin proteins are one of the genetic regions of the virus with a high potential for mutations. Due to the importance of predicting mutations in producing effective and low-cost vaccines, solutions that attempt to approach this problem have recently gained a significant attention. A historical record of mutations have been used to train predictive models in such solutions. However, the imbalance between mutations and the preserved proteins is a big challenge for the development of such models that needs to be addressed. Here, we propose to tackle this challenge through anomaly detection (AD). AD is a well-established field in Machine Learning (ML) that tries to distinguish unseen anomalies from the normal patterns using only normal training samples. By considering mutations as the anomalous behavior, we could benefit existing rich solutions in this field that have emerged recently. Such methods also fit the problem setup of extreme imbalance between the number of unmutated vs. mutated training samples. Motivated by this formulation, our method tries to find a compact representation for unmutated samples while forcing anomalies to be separated from the normal ones. This helps the model to learn a shared unique representation between normal training samples as much as possible, which improves the discernibility and detectability of mutated samples from the unmutated ones at the test time. We conduct a large number of experiments on four publicly available datasets, consisting of 3 different hemagglutinin protein datasets, and one SARS-CoV-2 dataset, and show the effectiveness of our method through different standard criteria.