Classifying the Stoichiometry of Virus-like Particles with Interpretable Machine Learning

TL;DR

This paper presents an interpretable machine learning pipeline for classifying virus-like particle stoichiometry, enabling efficient analysis and feature identification to aid vaccine development.

Contribution

It introduces a new dataset and a linear model-based approach for classifying VLP stoichiometry with interpretability and feature analysis.

Findings

The pipeline accurately classifies VLP stoichiometry.

Feature encoding impacts model performance and interpretability.

Key protein sequence features influencing assembly are identified.

Abstract

Virus-like particles (VLPs) are valuable for vaccine development due to their immune-triggering properties. Understanding their stoichiometry, the number of protein subunits to form a VLP, is critical for vaccine optimisation. However, current experimental methods to determine stoichiometry are time-consuming and require highly purified proteins. To efficiently classify stoichiometry classes in proteins, we curate a new dataset and propose an interpretable, data-driven pipeline leveraging linear machine learning models. We also explore the impact of feature encoding on model performance and interpretability, as well as methods to identify key protein sequence features influencing classification. The evaluation of our pipeline demonstrates that it can classify stoichiometry while revealing protein features that possibly influence VLP assembly. The data and code used in this work are publicly available at https://github.com/Shef-AIRE/StoicIML.