Designing minimal E. coli genomes using variational autoencoders

Data associated with the manuscript: https://www.biorxiv.org/content/10.1101/2024.03.08.584160v2 Using a pangenome dataset for Escherichia coli, we explore how generation of minimal genomes can be achieved using variational autoencoders. Our results show that variational autoencoders can successfully create minimised genomes retaining the essential genes identified in the literature. data.tgz : Input data for the preprocessing, model fitting, and genome minimization F4_complete_presence_absence.csv Horesh et. al. 2021: https://www.microbiologyresearch.org/content/journal/mgen/10.1099/mgen.0.000499 accessionID_phylogroup_BD.csv Horesh et. al. 2021: https://www.microbiologyresearch.org/content/journal/mgen/10.1099/mgen.0.000499 essential_genes Goodall et. al. 2018: https://journals.asm.org/doi/10.1128/mbio.02096-17 GCF_000005845.2.gbff E. coli MG1655 wildtype sequence