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 important
part of complex microbial community investigation is the extraction of single organism
genomes. The maturation of metagenomic binning techniques has greatly increased the
quality of metagenomic assembled genomes, by utilizing features such as sequence
coverage and K-mer frequencies. However, challenges still remain with these approaches.
K-mer frequencies depend on long contigs for stabilisation and sequence coverage
information can be biased by high copy number sequences. The nanopore sequencing
platform, which is already an often integrated step in the metagenomic analysis, produces
information rich data containing information on the possible methylation of DNA bases.
Methylation represents a powerful feature, as the DNA modification depends on the state of
the methylome of the organism. Here we explore incorporation of methylation modification
as a feature into metagenomic binning using machine learning to complement challenges
inherent in sequence centric binning features.