CGRclust: Chaos Game Representation for Twin Contrastive Clustering of Unlabelled DNA Sequences

TL;DR

CGRclust introduces an unsupervised deep learning approach using Chaos Game Representations and twin contrastive clustering to accurately classify diverse unlabelled DNA sequences without alignment or labels.

Contribution

It is the first method to apply unsupervised twin contrastive learning to CGR images for DNA sequence clustering, outperforming existing methods.

Findings

Achieved over 81.70% accuracy on mitochondrial DNA datasets.

Consistently outperformed recent clustering methods across diverse datasets.

Demonstrated robustness and scalability across various sequence lengths and taxonomic levels.

Abstract

This study proposes CGRclust, a novel combination of unsupervised twin contrastive clustering of Chaos Game Representations (CGR) of DNA sequences, with convolutional neural networks (CNNs). To the best of our knowledge, CGRclust is the first method to use unsupervised learning for image classification (herein applied to two-dimensional CGR images) for clustering datasets of DNA sequences. CGRclust overcomes the limitations of traditional sequence classification methods by leveraging unsupervised twin contrastive learning to detect distinctive sequence patterns, without requiring DNA sequence alignment or biological/taxonomic labels. CGRclust accurately clustered twenty-five diverse datasets, with sequence lengths ranging from 664 bp to 100 kbp, including mitochondrial genomes of fish, fungi, and protists, as well as viral whole genome assemblies and synthetic DNA sequences. Compared with three recent clustering methods for DNA sequences (DeLUCS, iDeLUCS, and MeShClust v3.0.), CGRclust is the only method that surpasses 81.70% accuracy across all four taxonomic levels tested for mitochondrial DNA genomes of fish. Moreover, CGRclust also consistently demonstrates superior performance across all the viral genomic datasets. The high clustering accuracy of CGRclust on these twenty-five datasets, which vary significantly in terms of sequence length, number of genomes, number of clusters, and level of taxonomy, demonstrates its robustness, scalability, and versatility.