<?xml version="1.0" ?>
<BioSampleSet><BioSample access="public" publication_date="2022-04-01T00:00:00.000" last_update="2022-04-03T21:36:31.000" submission_date="2022-04-02T10:17:30.110" id="27230805" accession="SAMEA13509748">   <Ids>     <Id db="BioSample" is_primary="1">SAMEA13509748</Id>     <Id db="SRA">ERS11111755</Id>   </Ids>   <Description>     <Title>ERR7738592_bin.36</Title>     <Organism taxonomy_id="512314" taxonomy_name="uncultured Roseburia sp.">       <OrganismName>uncultured Roseburia sp.</OrganismName>     </Organism>     <Comment>       <Paragraph>This sample represents an uncultured Roseburia sp. MAG assembled and binned from ERR7738592.</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="16S rRNAs recovered">0</Attribute>     <Attribute attribute_name="16S recovered">FALSE</Attribute>     <Attribute attribute_name="16S recovery software">barrnap;0.9;--kingdom bac</Attribute>     <Attribute attribute_name="23S rRNAs recovered">0</Attribute>     <Attribute attribute_name="5S rRNAs recovered">0</Attribute>     <Attribute attribute_name="CheckM strain heterogeneity">50</Attribute>     <Attribute attribute_name="ENA first public">2022-04-01</Attribute>     <Attribute attribute_name="ENA last update">2022-04-01</Attribute>     <Attribute attribute_name="ENA-CHECKLIST">ERC000011</Attribute>     <Attribute attribute_name="External Id">SAMEA13509748</Attribute>     <Attribute attribute_name="GTDB r202 classification">d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Lachnospirales;f__Lachnospiraceae;g__Roseburia;s__Roseburia sp900552665</Attribute>     <Attribute attribute_name="INSDC center alias">Stanford University School of Medicine</Attribute>     <Attribute attribute_name="INSDC center name">stanford university school of medicine</Attribute>     <Attribute attribute_name="INSDC first public">2022-04-01T08:24:10Z</Attribute>     <Attribute attribute_name="INSDC last update">2022-04-01T08:24:10Z</Attribute>     <Attribute attribute_name="INSDC status">public</Attribute>     <Attribute attribute_name="MAG coverage depth">10.87</Attribute>     <Attribute attribute_name="MAG coverage software">Reads (ERR7738592) were merged using BBMerge (rem k=62 extend2=50 ecct vstrict) and then mapped to assembled contigs &gt;=1500bp (ERZ4567471) using Bowtie2 v2.3.4 (--very-sensitive -X 1000). Coverage was calculated using jgi_summarize_bam_contig_depths (default parameters) from MetaBAT2 v2.15.</Attribute>     <Attribute attribute_name="Submitter Id">REFINED_METABAT215_TOP10_CONTIGS_1500_ASSEMBLY_K77_MERGED__Nepal_MoBio_Fiber-Hadza-Nepal_B_21_THA1063YZ.36</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">metaSPAdes;3.13.1;-k 21,33,55,77 --merged BBMerge.fq.gz -1 R1.fq.gz -2 R2.fq.gz</Attribute>     <Attribute attribute_name="binning parameters">Reads from ERR7738592 were assembled into contigs (ERZ4567471). The following read sets from this study were the most similar to ERR7738592 as determined by MASH (-r -m 2 -s 100000 -k 32): ERR7738592,ERR7738572,ERR7738472,ERR7738558,ERR7738529,ERR7745779,ERR7745858,ERR7738619,ERR7738575,ERR7745769. Following processing using BBMerge (rem k=62 extend2=50 ecct vstrict), reads from each of these 10 samples were mapped using bowtie2 v2.3.4 (--very-sensitive -X 1000) onto contigs &gt;=1500bp from ERZ4567471. Depth information for all 10 mapped samples was utilized by MetaBAT2 2.15 for genome binning. Contigs flagged by any module in MAGpurify 2.1.0 (--weighted mode for gc_content, tetra_freq, and coverage modules; conspecific database augmented by high-quality MAGs from this study) were removed from the bin.</Attribute>     <Attribute attribute_name="binning software">MetaBAT2 v2.15; MAGpurify v2.1.0</Attribute>     <Attribute attribute_name="collection date" harmonized_name="collection_date" display_name="collection date">2016</Attribute>     <Attribute attribute_name="completeness approach">CheckM marker lineage: f__Lachnospiraceae (UID1286)</Attribute>     <Attribute attribute_name="completeness score">98.49</Attribute>     <Attribute attribute_name="completeness software">CheckM;1.1.2;lineage_wf</Attribute>     <Attribute attribute_name="contamination score">0.5</Attribute>     <Attribute attribute_name="contamination screening input">reads</Attribute>     <Attribute attribute_name="contamination screening parameters">All reads in ERR7738592 failed to map to hg19 (with custom masking) using BBMap v38.86 (minid=0.95 maxindel=3 bwr=0.16 bw=12 minhits=2).</Attribute>     <Attribute attribute_name="environment (biome)" harmonized_name="env_broad_scale" display_name="broad-scale environmental context">terrestrial biome</Attribute>     <Attribute attribute_name="environment (feature)" harmonized_name="env_local_scale" display_name="local-scale environmental context">human-associated habitat</Attribute>     <Attribute attribute_name="environment (material)" harmonized_name="env_medium" display_name="environmental medium">feces</Attribute>     <Attribute attribute_name="geographic location (country and/or sea)" harmonized_name="geo_loc_name" display_name="geographic location">Nepal</Attribute>     <Attribute attribute_name="geographic location (elevation)">1400</Attribute>     <Attribute attribute_name="geographic location (latitude)">28.17</Attribute>     <Attribute attribute_name="geographic location (longitude)">84.25</Attribute>     <Attribute attribute_name="inter-study species representative">GUT_GENOME098563</Attribute>     <Attribute attribute_name="intra-study species representative">ERR7738592_bin.36</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 feces</Attribute>     <Attribute attribute_name="metagenomic source">human gut metagenome</Attribute>     <Attribute attribute_name="nucleic acid extraction">https://doi.org/10.1371/journal.pbio.2005396</Attribute>     <Attribute attribute_name="number of standard tRNAs extracted">47</Attribute>     <Attribute attribute_name="project name" harmonized_name="project_name" display_name="project name">Metagenome sequencing of Nepali gut microbiome</Attribute>     <Attribute attribute_name="reassembly post binning">No</Attribute>     <Attribute attribute_name="reference for biomaterial" harmonized_name="ref_biomaterial" display_name="reference for biomaterial">https://doi.org/10.1371/journal.pbio.2005396</Attribute>     <Attribute attribute_name="sample collection device or method" harmonized_name="samp_collect_device" display_name="sample collection device or method">https://doi.org/10.1371/journal.pbio.2005396</Attribute>     <Attribute attribute_name="sample derived from">ERS2787404</Attribute>     <Attribute attribute_name="sample name" harmonized_name="sample_name" display_name="sample name">REFINED_METABAT215_TOP10_CONTIGS_1500_ASSEMBLY_K77_MERGED__Nepal_MoBio_Fiber-Hadza-Nepal_B_21_THA1063YZ.36</Attribute>     <Attribute attribute_name="sequencing method">Illumina NovaSeq 6000</Attribute>     <Attribute attribute_name="tRNA extraction software">tRNAscan-SE;2.0.9;-B</Attribute>     <Attribute attribute_name="taxonomic classification">GTDB-TK v1.7.0, r202 database, default parameters</Attribute>     <Attribute attribute_name="taxonomic identity marker">multi-marker approach</Attribute>     <Attribute attribute_name="unique standard tRNAs extracted">18</Attribute>   </Attributes>   <Status status="live" when="2022-04-04T15:31:17.970"/> </BioSample> </BioSampleSet>
