<?xml version="1.0" ?>
<BioSampleSet><BioSample access="public" publication_date="2023-01-03T00:00:00.000" last_update="2023-04-12T11:48:47.000" submission_date="2023-01-04T08:31:11.843" id="32560546" accession="SAMEA14083917">   <Ids>     <Id db="BioSample" is_primary="1">SAMEA14083917</Id>     <Id db="SRA">ERS11687051</Id>   </Ids>   <Description>     <Title>Metagenome-assembled genome: ERR209721_bin.0_CONCOCT_v1.1_MAG</Title>     <Organism taxonomy_id="853" taxonomy_name="Faecalibacterium prausnitzii">       <OrganismName>Faecalibacterium prausnitzii</OrganismName>     </Organism>     <Comment>       <Paragraph>This sample represents a Third Party Annotation (TPA) Metagenome-Assembled Genome (MAG) assembled from the metagenomic run ERR209721 of study ERP002061.</Paragraph>     </Comment>   </Description>   <Owner>     <Name>EBI</Name>   </Owner>   <Models>     <Model>Generic</Model>   </Models>   <Package display_name="Generic">Generic.1.0</Package>   <Attributes>     <Attribute attribute_name="ENA-CHECKLIST">ERC000047</Attribute>     <Attribute attribute_name="ENA-FIRST-PUBLIC">2023-01-03</Attribute>     <Attribute attribute_name="ENA-LAST-UPDATE">2023-01-03</Attribute>     <Attribute attribute_name="External Id">SAMEA14083917</Attribute>     <Attribute attribute_name="INSDC center alias">EBI</Attribute>     <Attribute attribute_name="INSDC center name">European Bioinformatics Institute</Attribute>     <Attribute attribute_name="INSDC first public">2023-01-03T00:33:12Z</Attribute>     <Attribute attribute_name="INSDC last update">2023-01-03T00:33:12Z</Attribute>     <Attribute attribute_name="INSDC status">public</Attribute>     <Attribute attribute_name="Submitter Id">ERR209721_bin.0_CONCOCT_v1.1_MAG</Attribute>     <Attribute attribute_name="assembly quality">Many fragments with little to no review of assembly other than reporting of standard assembly statistics</Attribute>     <Attribute attribute_name="assembly software">metaspadesv3.11.1</Attribute>     <Attribute attribute_name="binning parameters">Default</Attribute>     <Attribute attribute_name="binning software">CONCOCT v1.1</Attribute>     <Attribute attribute_name="broker name">EMG broker account, EMBL-EBI</Attribute>     <Attribute attribute_name="collection date" harmonized_name="collection_date" display_name="collection date">2008-01-01</Attribute>     <Attribute attribute_name="completeness score">92.04</Attribute>     <Attribute attribute_name="completeness software">CheckM</Attribute>     <Attribute attribute_name="contamination score">1.54</Attribute>     <Attribute attribute_name="environment (biome)" harmonized_name="env_broad_scale" display_name="broad-scale environmental context">Host-associated</Attribute>     <Attribute attribute_name="environment (feature)" harmonized_name="env_local_scale" display_name="local-scale environmental context">Human</Attribute>     <Attribute attribute_name="environment (material)" harmonized_name="env_medium" display_name="environmental medium">Digestive system</Attribute>     <Attribute attribute_name="geographic location (country and/or sea)" harmonized_name="geo_loc_name" display_name="geographic location">Spain</Attribute>     <Attribute attribute_name="geographic location (latitude)">40.416634</Attribute>     <Attribute attribute_name="geographic location (longitude)">-3.7037659</Attribute>     <Attribute attribute_name="investigation type" harmonized_name="investigation_type" display_name="investigation type">metagenome-assembled genome</Attribute>     <Attribute attribute_name="isolation_source" harmonized_name="isolation_source" display_name="isolation source">human gut metagenome</Attribute>     <Attribute attribute_name="metagenomic source">human gut metagenome</Attribute>     <Attribute attribute_name="project name" harmonized_name="project_name" display_name="project name">The microbial diversity of environments like the human gut extends far beyond what is covered by reference genomes. Here we present a method for exhaustive and unsupervised co-abundance gene binning across a series of highly complex metagenomic samples. As the method does not rely on previously sequenced reference genomes it allows for discovery of new species, viruses and clonal heterogeneity. We demonstrate the method on human gut microbiome data and identify 7,381 co-abundance gene groups (CAGs) ranging in size from 3 to 6,319 genes. The CAGs represent a wide variety of biological entities including microbial genomes, phages and clonal differences. We name the 741 largest of these metagenomic species (MGS), because they correspond to microbial species. In addition, we establish microbial host affiliations by dependency-associations for many small CAGs. Longitudinal sampling in the same individuals indicates that some of these dependency-associations are important for the persistence of their microbial host</Attribute>     <Attribute attribute_name="sample derived from">SAMEA2042219</Attribute>     <Attribute attribute_name="sample name" harmonized_name="sample_name" display_name="sample name">ERR209721_bin.0_CONCOCT_v1.1_MAG</Attribute>     <Attribute attribute_name="scientific_name">Faecalibacterium prausnitzii</Attribute>     <Attribute attribute_name="sequencing method">Illumina Genome Analyzer IIx</Attribute>     <Attribute attribute_name="taxonomic identity marker">multi-marker approach</Attribute>   </Attributes>   <Status status="live" when="2023-01-05T08:29:15.043"/> </BioSample> </BioSampleSet>
