Developing new bioinformatic methods to supercharge genome-centric metagenomics using machine learning

Microbes are everywhere and play important roles in most aspects of life and an importantpart of complex microbial community investigation is the extraction of single organismgenomes. The maturation of metagenomic binning techniques has greatly increased thequality of metagenomic assembled genomes, by utilizing features such as sequencecoverage and K-mer frequencies. However, challenges still remain with these approaches.K-mer frequencies depend on long contigs for stabilisation and sequence coverageinformation can be biased by high copy number sequences. The nanopore sequencingplatform, which is already an often integrated step in the metagenomic analysis, producesinformation rich data containing information on the possible methylation of DNA bases.Methylation represents a powerful feature, as the DNA modification depends on the state ofthe methylome of the organism. Here we explore incorporation of methylation modificationas a feature into metagenomic binning using machine learning to complement challengesinherent in sequence centric binning features.