UMAP-assisted $K$-means clustering of large-scale SARS-CoV-2 mutation datasets

TL;DR

This paper presents a UMAP-assisted $k$-means clustering method to efficiently analyze large-scale SARS-CoV-2 mutation datasets, improving clustering accuracy and visualization for understanding virus evolution.

Contribution

The study introduces a novel combination of UMAP with $k$-means clustering for large genomic datasets, demonstrating its superiority over PCA and t-SNE in accuracy and efficiency.

Findings

UMAP outperforms PCA and t-SNE in clustering large SARS-CoV-2 datasets.

UMAP-assisted clustering improves visualization and accuracy of mutation analysis.

The method enables effective analysis of increasingly large genomic datasets.

Abstract

Coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has a worldwide devastating effect. The understanding of evolution and transmission of SARS-CoV-2 is of paramount importance for the COVID-19 control, combating, and prevention. Due to the rapid growth of both the number of SARS-CoV-2 genome sequences and the number of unique mutations, the phylogenetic analysis of SARS-CoV-2 genome isolates faces an emergent large-data challenge. We introduce a dimension-reduced $k$-means clustering strategy to tackle this challenge. We examine the performance and effectiveness of three dimension-reduction algorithms: principal component analysis (PCA), t-distributed stochastic neighbor embedding (t-SNE), and uniform manifold approximation and projection (UMAP). By using four benchmark datasets, we found that UMAP is the best-suited technique due to its stable, reliable, and efficient performance, its ability to improve clustering accuracy, especially for large Jaccard distanced-based datasets, and its superior clustering visualization. The UMAP-assisted $k$-means clustering enables us to shed light on increasingly large datasets from SARS-CoV-2 genome isolates.