Machine learning algorithm to characterize antimicrobial resistance associated with the International Space Station surface microbiome

Background: Antimicrobial Resistance (AMR) has a detrimental impact on humanhealth on Earth and it is equally concerning in other environments such as space dueto microgravity, radiation and confinement, especially for long-distance space travel.The International Space Station (ISS) is ideal for investigating microbial diversity andvirulence. The shotgun metagenomics data of the ISS generated during the MicrobialTracking – 1 (MT-1) project and resulting metagenome-assembled genomes (MAGs)across three flights in eight different locations during 12 months were used in thisstudy. The objective of this study was to identify the AMR genes associated with wholegenomes of 227 cultivable strains, 21 shotgun metagenome sequences, and 24 MAGsretrieved from the ISS environmental samples that were treated with propidiummonoazide (PMA; viable microbes).Results: We have analyzed the data using a deep learning model, allowing us to gobeyond traditional cut-offs based only on high DNA sequence similarity and extendingthe catalog of AMR genes. Our results in PMA treated samples revealed AMRdominance in the last flight for Kalamiella piersonii , a bacteria related to urinary tractinfection in humans. The analysis of 227 pure strains isolated from the MT-1 projectrevealed hundreds of antibiotic resistance genes from many isolates, including two topranking species that corresponded to strains of Enterobacter bugandensis and Bacillus cereus . Computational predictions were experimentally validated by antibioticresistance profiles in these two species, showing a high degree of concordance.Specifically, disc assay data confirmed the high resistance of these two pathogens tovarious beta-lactam antibiotics.Conclusion: Overall, our computational predictions and validation analysesdemonstrate the advantages of machine learning to uncover concealed AMRdeterminants in metagenomics datasets, expanding the understanding of the ISSenvironmental microbiomes and their pathogenic potential in humans.