Revisiting K-mer Profile for Effective and Scalable Genome Representation Learning
This work addresses the need for efficient genome analysis in metagenomics, offering a scalable solution for real-world datasets, though it is incremental as it builds on existing k-mer methods.
The paper tackles the problem of genome representation learning for metagenomic binning by revisiting k-mer-based representations, proposing a lightweight and scalable model that achieves comparable performance to recent genome foundation models while being significantly more scalable.
Obtaining effective representations of DNA sequences is crucial for genome analysis. Metagenomic binning, for instance, relies on genome representations to cluster complex mixtures of DNA fragments from biological samples with the aim of determining their microbial compositions. In this paper, we revisit k-mer-based representations of genomes and provide a theoretical analysis of their use in representation learning. Based on the analysis, we propose a lightweight and scalable model for performing metagenomic binning at the genome read level, relying only on the k-mer compositions of the DNA fragments. We compare the model to recent genome foundation models and demonstrate that while the models are comparable in performance, the proposed model is significantly more effective in terms of scalability, a crucial aspect for performing metagenomic binning of real-world datasets.