@article {O{\~n}ate173203, author = {Florian Plaza O{\~n}ate and Emmanuelle Le Chatelier and Mathieu Almeida and Ales-sandra C. L. Cervino and Franck Gauthier and Fr{\'e}d{\'e}ric Magoul{\`e}s and S. Dusko Ehrlich and Matthieu Pichaud}, title = {MSPminer: abundance-based reconstitution of microbial pan-genomes from shotgun meta-genomic data}, elocation-id = {173203}, year = {2018}, doi = {10.1101/173203}, publisher = {Cold Spring Harbor Laboratory}, abstract = {Motivation Analysis toolkits for shotgun metagenomic data achieve strain-level characterization of complex microbial communities by capturing intra-species gene content variation. Yet, these tools are hampered by the extent of reference genomes that are far from covering all microbial variability, as many species are still not sequenced or have only few strains available. Binning co-abundant genes obtained from de novo assembly is a powerful reference-free technique to discover and reconstitute gene repertoire of microbial species. While current methods accurately identify species core parts, they miss many accessory genes or split them into small gene groups that remain unassociated to core clusters.Results We introduce MSPminer, a computationally efficient software tool that reconstitutes Metagenomic Species Pan-genomes (MSPs) by binning co-abundant genes across metagenomic samples. MSPminer relies on a new robust measure of proportionality coupled with an empirical classifier to group and distinguish not only species core genes but accessory genes also. Applied to a large scale metagenomic dataset, MSPminer successfully delineates in a few hours the gene repertoires of 1 661 microbial species with similar specificity and higher sensitivity than existing tools. The taxonomic annotation of MSPs reveals microorganisms hitherto unknown and brings coherence in the nomenclature of the species of the human gut microbiota. The provided MSPs can be readily used for taxonomic profiling and biomarkers discovery in human gut metagenomic samples. In addition, MSPminer can be applied on gene count tables from other ecosystems to perform similar analyses.Availability The binary is freely available for non-commercial users at enterome.fr/site/downloads/ Contact: florian.plaza-onate{at}inra.frSupplementary information Available in the file named Supplementary Information.pdf}, URL = {https://www.biorxiv.org/content/early/2018/07/16/173203}, eprint = {https://www.biorxiv.org/content/early/2018/07/16/173203.full.pdf}, journal = {bioRxiv} }