##gff-version 3
##sequence-region DS362223 1 28433
# conversion-by bp_genbank2gff3.pl
# organism Bacteroides uniformis ATCC 8492
# Note Bacteroides uniformis ATCC 8492 Scfld_3.0.1_6 genomic scaffold, whole genome shotgun sequence.
# date 30-JUL-2007
DS362223	GenBank	region	1	28433	.	+	1	ID=DS362223;Dbxref=BioProject:PRJNA18195,ATCC:8492,taxon:411479;Name=DS362223;Note=Bacteroides uniformis ATCC 8492 Scfld_3.0.1_6 genomic scaffold%2C whole genome shotgun sequence.,Bacteroides uniformis (GenBank Accession Number for 16S rDNA gene: L16486) is a member of the division Bacteroidetes. In one comprehensive 16S rDNA sequence-based enumeration of the colonic microbiota of three healthy adult humans,it represents,on average,0.718%25 of all 16S rDNA sequences and 1.506%25 of the sequences in its division (Eckburg et. al. (2005)). The sequenced strain was obtained from ATCC (ATCC 8492). We have collected 8.1X coverage in plasmid end reads and 454 reads. We will be performing one round of automated sequence improvement (pre-finishing),Sequencing/Assembly: The genomic DNA was purified from liquid culture derived from a single bacterial colony. A hybrid sequencing strategy that utilized reads from both 454 GS-20 and ABI 3730xl sequencers was devised and implemented to generate the draft genome sequences. 454 reads were assembled using Newbler (454 Life Sciences) into 454 de novo contigs. These de novo contigs were converted in silico to 800 base paired reads ('superreads') with 400 base overlaps with neighboring superreads. Finally,PCAP (Huang,et al,Genome Research,13:2164,(2003)) was used to assemble the super-reads and the conventional 3730xl capillary reads. This sequenced strain is part of a comprehensive,sequence-based survey of members of the normal human gut microbiota. A joint effort of the WU-GSC and the Center for Genome Sciences at Washington University School of Medicine,the purpose of this survey is to provide the general scientific community with a broad view of the gene content of 100 representatives of the major divisions represented in the intestine's microbial community. This information should provide a frame of reference for analyzing metagenomic studies of the human gut microbiome. Further details of this effort are described in a white paper entitled 'Extending Our View of Self: the Human Gut Microbiome Initiative (HGMI)' (http://www.genome.gov/Pages/Research/Sequencing/SeqProposals/HGMIS eq.pdf). These studies are supported by National Human Genome Research Institute. For answers to your questions regarding this assembly or project,or any other GSC genome project,please visit our Genome Groups web page (http://genome.wustl.edu/genome_group_index.cgi) and email the designated contact person. ;comment1=Bacteroides uniformis (GenBank Accession Number for 16S rDNA gene: L16486) is a member of the division Bacteroidetes. In one comprehensive 16S rDNA sequence-based enumeration of the colonic microbiota of three healthy adult humans%2C it represents%2C on average%2C 0.718%25 of all 16S rDNA sequences and 1.506%25 of the sequences in its division (Eckburg et. al. (2005)). The sequenced strain was obtained from ATCC (ATCC 8492). We have collected 8.1X coverage in plasmid end reads and 454 reads. We will be performing one round of automated sequence improvement (pre-finishing)%3B Sequencing/Assembly: The genomic DNA was purified from liquid culture derived from a single bacterial colony. A hybrid sequencing strategy that utilized reads from both 454 GS-20 and ABI 3730xl sequencers was devised and implemented to generate the draft genome sequences. 454 reads were assembled using Newbler (454 Life Sciences) into 454 de novo contigs. These de novo contigs were converted in silico to 800 base paired reads ('superreads') with 400 base overlaps with neighboring superreads. Finally%2C PCAP (Huang%2C et al%2C Genome Research%2C 13:2164%2C (2003)) was used to assemble the super-reads and the conventional 3730xl capillary reads. This sequenced strain is part of a comprehensive%2C sequence-based survey of members of the normal human gut microbiota. A joint effort of the WU-GSC and the Center for Genome Sciences at Washington University School of Medicine%2C the purpose of this survey is to provide the general scientific community with a broad view of the gene content of 100 representatives of the major divisions represented in the intestine's microbial community. This information should provide a frame of reference for analyzing metagenomic studies of the human gut microbiome. Further details of this effort are described in a white paper entitled 'Extending Our View of Self: the Human Gut Microbiome Initiative (HGMI)' (http://www.genome.gov/Pages/Research/Sequencing/SeqProposals/HGMIS eq.pdf). These studies are supported by National Human Genome Research Institute. For answers to your questions regarding this assembly or project%2C or any other GSC genome project%2C please visit our Genome Groups web page (http://genome.wustl.edu/genome_group_index.cgi) and email the designated contact person. ;date=30-JUL-2007;mol_type=genomic DNA;organism=Bacteroides uniformis ATCC 8492;strain=ATCC 8492;type_material=type strain of Bacteroides uniformis
DS362223	GenBank	gene	1	3195	.	+	1	ID=BACUNI_00315;Name=BACUNI_00315
DS362223	GenBank	mRNA	1	3195	.	+	1	ID=BACUNI_00315.t01;Parent=BACUNI_00315
DS362223	GenBank	CDS	1	3195	.	+	1	ID=BACUNI_00315.p01;Parent=BACUNI_00315.t01;Dbxref=InterPro:IPR000531,InterPro:IPR008969,InterPro:IPR012910;Name=BACUNI_00315;Note=COG: NOG26156 non supervised orthologous group;codon_start=1;inference=protein motif:HMMPfam:IPR000531,protein motif:HMMPfam:IPR012910,protein motif:superfamily:IPR008969,similar to AA sequence:INSD:ABR41882.1;product=TonB-linked outer membrane protein%2C SusC/RagA family;protein_id=EDO56028.1;transl_table=11;translation=length.1064
DS362223	GenBank	exon	1	3195	.	+	1	Parent=BACUNI_00315.t01
DS362223	GenBank	gene	3209	4888	.	+	1	ID=BACUNI_00316;Name=BACUNI_00316
DS362223	GenBank	mRNA	3209	4888	.	+	1	ID=BACUNI_00316.t01;Parent=BACUNI_00316
DS362223	GenBank	CDS	3209	4888	.	+	1	ID=BACUNI_00316.p01;Parent=BACUNI_00316.t01;Dbxref=InterPro:IPR012944;Name=BACUNI_00316;Note=COG: NOG26302 non supervised orthologous group;codon_start=1;inference=protein motif:HMMPfam:IPR012944,similar to AA sequence:INSD:ABQ03815.1;product=SusD family protein;protein_id=EDO56029.1;transl_table=11;translation=length.559
DS362223	GenBank	exon	3209	4888	.	+	1	Parent=BACUNI_00316.t01
DS362223	GenBank	gene	4930	6900	.	+	1	ID=BACUNI_00317;Name=BACUNI_00317
DS362223	GenBank	mRNA	4930	6900	.	+	1	ID=BACUNI_00317.t01;Parent=BACUNI_00317
DS362223	GenBank	CDS	4930	6900	.	+	1	ID=BACUNI_00317.p01;Parent=BACUNI_00317.t01;Name=BACUNI_00317;codon_start=1;inference=similar to AA sequence:REFSEQ:YP_001193133.1;product=hypothetical protein;protein_id=EDO56030.1;transl_table=11;translation=length.656
DS362223	GenBank	exon	4930	6900	.	+	1	Parent=BACUNI_00317.t01
DS362223	GenBank	gene	6909	9530	.	+	1	ID=BACUNI_00318;Name=BACUNI_00318
DS362223	GenBank	mRNA	6909	9530	.	+	1	ID=BACUNI_00318.t01;Parent=BACUNI_00318
DS362223	GenBank	CDS	6909	9530	.	+	1	ID=BACUNI_00318.p01;Parent=BACUNI_00318.t01;Name=BACUNI_00318;Note=COG: NOG38840 non supervised orthologous group%3B Psort location: OuterMembrane%2C score:9.52;codon_start=1;product=hypothetical protein;protein_id=EDO56031.1;transl_table=11;translation=length.873
DS362223	GenBank	exon	6909	9530	.	+	1	Parent=BACUNI_00318.t01
DS362223	GenBank	gene	9925	11496	.	-	1	ID=BACUNI_00319;Name=BACUNI_00319
DS362223	GenBank	mRNA	9925	11496	.	-	1	ID=BACUNI_00319.t01;Parent=BACUNI_00319
DS362223	GenBank	CDS	9925	11496	.	-	1	ID=BACUNI_00319.p01;Parent=BACUNI_00319.t01;Dbxref=InterPro:IPR006710;Name=BACUNI_00319;Note=KEGG: bcl:ABC1148 3.6e-111 xylosidase/arabinosidase K01198:K01209%3B COG: COG3507 Beta-xylosidase;codon_start=1;inference=protein motif:HMMPanther:IPR006710,protein motif:HMMPfam:IPR006710,similar to AA sequence:INSD:ABC75004.1;product=glycosyl hydrolase%2C family 43;protein_id=EDO56032.1;transl_table=11;translation=length.523
DS362223	GenBank	exon	9925	11496	.	-	1	Parent=BACUNI_00319.t01
DS362223	GenBank	gene	11543	11722	.	+	1	ID=BACUNI_00320;Name=BACUNI_00320
DS362223	GenBank	mRNA	11543	11722	.	+	1	ID=BACUNI_00320.t01;Parent=BACUNI_00320
DS362223	GenBank	CDS	11543	11722	.	+	1	ID=BACUNI_00320.p01;Parent=BACUNI_00320.t01;Name=BACUNI_00320;codon_start=1;product=hypothetical protein;protein_id=EDO56033.1;transl_table=11;translation=length.59
DS362223	GenBank	exon	11543	11722	.	+	1	Parent=BACUNI_00320.t01
DS362223	GenBank	gene	11747	13528	.	+	1	ID=BACUNI_00321;Name=BACUNI_00321
DS362223	GenBank	mRNA	11747	13528	.	+	1	ID=BACUNI_00321.t01;Parent=BACUNI_00321
DS362223	GenBank	CDS	11747	13528	.	+	1	ID=BACUNI_00321.p01;Parent=BACUNI_00321.t01;Dbxref=InterPro:IPR001547,InterPro:IPR013781;Name=BACUNI_00321;Note=KEGG: sde:Sde_2636 3.1e-66 DNA mismatch repair protein K01179%3B COG: COG2730 Endoglucanase;codon_start=1;inference=protein motif:Gene3D:IPR013781,protein motif:HMMPfam:IPR001547,similar to AA sequence:REFSEQ:YP_001193127.1;product=cellulase (glycosyl hydrolase family 5);protein_id=EDO56034.1;transl_table=11;translation=length.593
DS362223	GenBank	exon	11747	13528	.	+	1	Parent=BACUNI_00321.t01
DS362223	GenBank	gene	13749	17831	.	+	1	ID=BACUNI_00322;Name=BACUNI_00322
DS362223	GenBank	mRNA	13749	17831	.	+	1	ID=BACUNI_00322.t01;Parent=BACUNI_00322
DS362223	GenBank	CDS	13749	17831	.	+	1	ID=BACUNI_00322.p01;Parent=BACUNI_00322.t01;Dbxref=InterPro:IPR000005,InterPro:IPR001789,InterPro:IPR003594,InterPro:IPR003661,InterPro:IPR004358,InterPro:IPR005829,InterPro:IPR008957,InterPro:IPR009057,InterPro:IPR009082,InterPro:IPR011006,InterPro:IPR011047,InterPro:IPR011110,InterPro:IPR011123,InterPro:IPR012287;Name=BACUNI_00322;Note=KEGG: ana:all4963 2.4e-58 cyaC%3B adenylate cyclase carring two-component hybrid sensor and regulator domains%3B COG: COG0642 Signal transduction histidine kinase%3B Psort location: CytoplasmicMembrane%2C score:10.00;codon_start=1;inference=protein motif:BlastProDom:IPR001789,protein motif:FPrintScan:IPR000005,protein motif:FPrintScan:IPR004358,protein motif:Gene3D:IPR003594,protein motif:Gene3D:IPR012287,protein motif:HMMPfam:IPR000005,protein motif:HMMPfam:IPR001789,protein motif:HMMPfam:IPR003594,protein motif:HMMPfam:IPR003661,protein motif:HMMPfam:IPR011110,protein motif:HMMPfam:IPR011123,protein motif:HMMSmart:IPR000005,protein motif:HMMSmart:IPR001789,protein motif:HMMSmart:IPR003594,protein motif:HMMSmart:IPR003661,protein motif:ScanRegExp:IPR000005,protein motif:ScanRegExp:IPR005829,protein motif:superfamily:IPR003594,protein motif:superfamily:IPR008957,protein motif:superfamily:IPR009057,protein motif:superfamily:IPR009082,protein motif:superfamily:IPR011006,protein motif:superfamily:IPR011047;product=ATPase/histidine kinase/DNA gyrase B/HSP90 domain protein;protein_id=EDO56035.1;transl_table=11;translation=length.1360
DS362223	GenBank	exon	13749	17831	.	+	1	Parent=BACUNI_00322.t01
DS362223	GenBank	gene	17970	20852	.	+	1	ID=BACUNI_00323;Name=BACUNI_00323
DS362223	GenBank	mRNA	17970	20852	.	+	1	ID=BACUNI_00323.t01;Parent=BACUNI_00323
DS362223	GenBank	CDS	17970	20852	.	+	1	ID=BACUNI_00323.p01;Parent=BACUNI_00323.t01;Dbxref=InterPro:IPR000322,InterPro:IPR013145;eC_number=3.2.1.-;Name=BACUNI_00323;Note=KEGG: aba:Acid345_0898 2.4e-163 alpha-glucosidase K01187%3B COG: COG1501 Alpha-glucosidases%2C family 31 of glycosyl hydrolases;codon_start=1;inference=protein motif:HMMPfam:IPR000322,protein motif:HMMSmart:IPR013145;product=glycosyl hydrolase%2C family 31;protein_id=EDO56036.1;transl_table=11;translation=length.960
DS362223	GenBank	exon	17970	20852	.	+	1	Parent=BACUNI_00323.t01
DS362223	GenBank	gene	20994	23513	.	+	1	ID=BACUNI_00324;Name=BACUNI_00324
DS362223	GenBank	mRNA	20994	23513	.	+	1	ID=BACUNI_00324.t01;Parent=BACUNI_00324
DS362223	GenBank	CDS	20994	23513	.	+	1	ID=BACUNI_00324.p01;Parent=BACUNI_00324.t01;Dbxref=InterPro:IPR006101,InterPro:IPR006102,InterPro:IPR006103,InterPro:IPR006104,InterPro:IPR008964,InterPro:IPR008979,InterPro:IPR013781,InterPro:IPR013812;Name=BACUNI_00324;Note=KEGG: xcb:XC_4208 9.5e-160 beta-galactosidase K01190%3B COG: COG3250 Beta-galactosidase/beta-glucuronidase;codon_start=1;inference=protein motif:FPrintScan:IPR006101,protein motif:Gene3D:IPR013781,protein motif:Gene3D:IPR013812,protein motif:HMMPfam:IPR006102,protein motif:HMMPfam:IPR006103,protein motif:HMMPfam:IPR006104,protein motif:ScanRegExp:IPR006101,protein motif:superfamily:IPR006102,protein motif:superfamily:IPR008964,protein motif:superfamily:IPR008979,similar to AA sequence:REFSEQ:YP_001304431.1;product=glycosyl hydrolase family 2%2C sugar binding domain protein;protein_id=EDO56037.1;transl_table=11;translation=length.839
DS362223	GenBank	exon	20994	23513	.	+	1	Parent=BACUNI_00324.t01
DS362223	GenBank	gene	23561	25774	.	+	1	ID=BACUNI_00325;Name=BACUNI_00325
DS362223	GenBank	mRNA	23561	25774	.	+	1	ID=BACUNI_00325.t01;Parent=BACUNI_00325
DS362223	GenBank	CDS	23561	25774	.	+	1	ID=BACUNI_00325.p01;Parent=BACUNI_00325.t01;Dbxref=InterPro:IPR001764,InterPro:IPR002772;Name=BACUNI_00325;Note=KEGG: bth:BT3314 4.1e-238 thermostable beta-glucosidase B K05349%3B COG: COG1472 Beta-glucosidase-related glycosidases%3B Psort location: Periplasmic%2C score:9.76;codon_start=1;inference=protein motif:FPrintScan:IPR001764,protein motif:HMMPfam:IPR001764,protein motif:HMMPfam:IPR002772,protein motif:ScanRegExp:IPR001764,similar to AA sequence:INSD:EAM62862.1;product=glycosyl hydrolase family 3 N-terminal domain protein;protein_id=EDO56038.1;transl_table=11;translation=length.737
DS362223	GenBank	exon	23561	25774	.	+	1	Parent=BACUNI_00325.t01
DS362223	GenBank	gene	25849	25980	.	-	1	ID=BACUNI_00327;Name=BACUNI_00327
DS362223	GenBank	mRNA	25849	25980	.	-	1	ID=BACUNI_00327.t01;Parent=BACUNI_00327
DS362223	GenBank	CDS	25849	25980	.	-	1	ID=BACUNI_00327.p01;Parent=BACUNI_00327.t01;Name=BACUNI_00327;codon_start=1;product=hypothetical protein;protein_id=EDO56040.1;transl_table=11;translation=length.43
DS362223	GenBank	exon	25849	25980	.	-	1	Parent=BACUNI_00327.t01
DS362223	GenBank	gene	25971	28433	.	+	1	ID=BACUNI_00326;Name=BACUNI_00326
DS362223	GenBank	mRNA	25971	28433	.	+	1	ID=BACUNI_00326.t01;Parent=BACUNI_00326
DS362223	GenBank	CDS	25971	28433	.	+	1	ID=BACUNI_00326.p01;Parent=BACUNI_00326.t01;Dbxref=InterPro:IPR008928;Name=BACUNI_00326;Note=COG: NOG04001 non supervised orthologous group;codon_start=1;inference=protein motif:superfamily:IPR008928,similar to AA sequence:REFSEQ:YP_001303770.1;product=hypothetical protein;protein_id=EDO56039.1;transl_table=11;translation=length.820
DS362223	GenBank	exon	25971	28433	.	+	1	Parent=BACUNI_00326.t01