Topological Learning Prediction of Virus-like Particle Stoichiometry and Stability

TL;DR

This paper presents a novel topological machine learning model using persistent Laplacian spectra to predict virus-like particle stoichiometry and stability, outperforming existing methods and demonstrating robustness across datasets.

Contribution

Introduces a persistent Laplacian-based machine learning model that captures topological features for predicting VLP properties, with improved accuracy and robustness.

Findings

The PLML model outperforms existing methods on VLP datasets.

VLP706 dataset confirms model's robustness and generalizability.

60-mers and 180-mers are more stable than 240-mers and 420-mers.

Abstract

Understanding the stoichiometry and associated stability of virus-like particles (VLPs) is crucial for optimizing their assembly efficiency and immunogenic properties, which are essential for advancing biotechnology, vaccine design, and drug delivery. However, current experimental methods for determining VLP stoichiometry are labor-intensive, and time consuming. Machine learning approaches have hardly been applied to the study of VLPs. To address this challenge, we introduce a novel persistent Laplacian-based machine learning (PLML) mode that leverages both harmonic and non-harmonic spectra to capture intricate topological and geometric features of VLP structures. This approach achieves superior performance on the VLP200 dataset compared to existing methods. To further assess robustness and generalizability, we collected a new dataset, VLP706, containing 706 VLP samples with expanded stoichiometry diversity. Our PLML model maintains strong predictive accuracy on VLP706. Additionally, through random sequence perturbative mutation analysis, we found that 60-mers and 180-mers exhibit greater stability than 240-mers and 420-mers.