CheckM2: a rapid, scalable and accurate tool for assessing microbial genome quality using machine learning

This work presents CheckM2, which is a machine learning-based tool to predict genome quality of isolate, single-cell and metagenome-assembled genomes. Advances in sequencing technologies and bioinformatics tools have dramatically increased the recovery rate of microbial genomes from metagenomic data. Assessing the quality of metagenome-assembled genomes (MAGs) is a critical step before downstream analysis. Here, we present CheckM2, an improved method of predicting genome quality of MAGs using machine learning. Using synthetic and experimental data, we demonstrate that CheckM2 outperforms existing tools in both accuracy and computational speed. In addition, CheckM2's database can be rapidly updated with new high-quality reference genomes, including taxa represented only by a single genome. We also show that CheckM2 accurately predicts genome quality for MAGs from novel lineages, even for those with reduced genome size (for example, Patescibacteria and the DPANN superphylum). CheckM2 provides accurate genome quality predictions across bacterial and archaeal lineages, giving increased confidence when inferring biological conclusions from MAGs.

Automated summary

This work presents CheckM2, a machine learning-based tool for predicting the genome quality of isolated, single-cell, and metagenome-assembled genomes. CheckM2 outperforms existing tools in accuracy and computational speed, as demonstrated by synthetic and experimental data. CheckM2's database can be rapidly updated with new high-quality reference genomes, even for taxa represented by only a single genome. It accurately predicts the genome quality of MAGs from novel lineages, including those with reduced genome size.