##gff-version 3
##sequence-region NZ_KE386494 1 16538
# conversion-by bp_genbank2gff3.pl
# organism Caldanaerobius polysaccharolyticus DSM 13641
# Note Caldanaerobius polysaccharolyticus DSM 13641 CalpoDRAFT_CPK.2, whole genome shotgun sequence.
# date 15-DEC-2019
NZ_KE386494	GenBank	region	1	16538	.	+	1	ID=NZ_KE386494;Dbxref=BioProject:PRJNA224116,taxon:935948;Name=NZ_KE386494;Note=Caldanaerobius polysaccharolyticus DSM 13641 CalpoDRAFT_CPK.2%2C whole genome shotgun sequence.,REFSEQ INFORMATION: The reference sequence was derived from KE386494. URL -- http://www.jgi.doe.gov JGI Project ID: 97983 Source DNA and organism available from Hans-Peter Klenk at the German Collection of Microorganisms and Cell Cultures (DSMZ) (hans-peter.klenk@dsmz.de) Contacts: Jonathan Eisen (jaeisen@ucdavis.edu) Tanja Woyke (microbe@cuba.jgi-psf.org) Whole genome sequencing and draft assembly at JGI Annotation by JGI The JGI and collaborators endorse the principles for the distribution and use of large scale sequencing data adopted by the larger genome sequencing community and urge users of this data to follow them. It is our intention to publish the work of this project in a timely fashion and we welcome collaborative interaction on the project and analysis. (http://www.genome.gov/page.cfm?pageID%3D10506376) Full annotations are available from IMG. The annotation was added by the NCBI Prokaryotic Genome Annotation Pipeline (PGAP). Information about PGAP can be found here: https://www.ncbi.nlm.nih.gov/genome/annotation_prok/ ##MIGS-Data-START## assembly :: ALLPATHS v. R37654 country :: USA investigation_type :: bacteria_archaea project_name :: Caldanaerobius polysaccharolyticum KMTHCJ,DSM 13641 sequencing_meth :: WGS ref_biomaterial :: DSM 13641,ATCC BAA-17 biotic_relationship :: Free living rel_to_oxygen :: Anaerobe finishing_strategy :: Level 3: Improved-High-Quality Draft GOLD Stamp ID :: Gi02942 Current Finishing Status :: Level 3: Improved-High-Quality Draft Type Strain :: Yes Greengenes ID :: 13759 Funding Program :: DOE-GEBA 2007 Gene Calling Method :: Prodigal 1.4,GenePRIMP Isolation Site :: Organic waste leachate,from a canning factory in Hoopeston,East Central Illinois Cell Shape :: Rod-shaped Motility :: Motile Sporulation :: Nonsporulating Temperature Range :: Thermophile Temperature Optimum :: 65 pH :: 6.8 Gram Staining :: Gram+ Diseases :: None ##MIGS-Data-END## ##Genome-Assembly-Data-START## Finishing Goal :: Improved High-Quality Draft Current Finishing Status :: Improved High-Quality Draft Assembly Method :: ALLPATHS v. R37654 Genome Coverage :: Unknown Sequencing Technology :: 454-GS-FLX,Illumina GAII ##Genome-Assembly-Data-END## ##Genome-Annotation-Data-START## Annotation Provider :: NCBI RefSeq Annotation Date :: 12/15/2019 15:43:43 Annotation Pipeline :: NCBI Prokaryotic Genome Annotation Pipeline (PGAP) Annotation Method :: Best-placed reference protein set,GeneMarkS-2+ Annotation Software revision :: 4.10 Features Annotated :: Gene,CDS,rRNA,tRNA,ncRNA,repeat_region Genes (total) :: 2,494 CDSs (total) :: 2,434 Genes (coding) :: 2,359 CDSs (with protein) :: 2,359 Genes (RNA) :: 60 rRNAs :: 1,1,1 (5S,16S,23S) complete rRNAs :: 1,1,1 (5S,16S,23S) tRNAs :: 53 ncRNAs :: 4 Pseudo Genes (total) :: 75 CDSs (without protein) :: 75 Pseudo Genes (ambiguous residues) :: 0 of 75 Pseudo Genes (frameshifted) :: 44 of 75 Pseudo Genes (incomplete) :: 31 of 75 Pseudo Genes (internal stop) :: 13 of 75 Pseudo Genes (multiple problems) :: 11 of 75 CRISPR Arrays :: 5 ##Genome-Annotation-Data-END## ;comment1=REFSEQ INFORMATION: The reference sequence was derived from KE386494. URL -- http://www.jgi.doe.gov JGI Project ID: 97983 Source DNA and organism available from Hans-Peter Klenk at the German Collection of Microorganisms and Cell Cultures (DSMZ) (hans-peter.klenk@dsmz.de) Contacts: Jonathan Eisen (jaeisen@ucdavis.edu) Tanja Woyke (microbe@cuba.jgi-psf.org) Whole genome sequencing and draft assembly at JGI Annotation by JGI The JGI and collaborators endorse the principles for the distribution and use of large scale sequencing data adopted by the larger genome sequencing community and urge users of this data to follow them. It is our intention to publish the work of this project in a timely fashion and we welcome collaborative interaction on the project and analysis. (http://www.genome.gov/page.cfm?pageID%3D10506376) Full annotations are available from IMG. The annotation was added by the NCBI Prokaryotic Genome Annotation Pipeline (PGAP). Information about PGAP can be found here: https://www.ncbi.nlm.nih.gov/genome/annotation_prok/ ##MIGS-Data-START## assembly :: ALLPATHS v. R37654 country :: USA investigation_type :: bacteria_archaea project_name :: Caldanaerobius polysaccharolyticum KMTHCJ%2C DSM 13641 sequencing_meth :: WGS ref_biomaterial :: DSM 13641%2C ATCC BAA-17 biotic_relationship :: Free living rel_to_oxygen :: Anaerobe finishing_strategy :: Level 3: Improved-High-Quality Draft GOLD Stamp ID :: Gi02942 Current Finishing Status :: Level 3: Improved-High-Quality Draft Type Strain :: Yes Greengenes ID :: 13759 Funding Program :: DOE-GEBA 2007 Gene Calling Method :: Prodigal 1.4%2C GenePRIMP Isolation Site :: Organic waste leachate%2C from a canning factory in Hoopeston%2C East Central Illinois Cell Shape :: Rod-shaped Motility :: Motile Sporulation :: Nonsporulating Temperature Range :: Thermophile Temperature Optimum :: 65 pH :: 6.8 Gram Staining :: Gram+ Diseases :: None ##MIGS-Data-END## ##Genome-Assembly-Data-START## Finishing Goal :: Improved High-Quality Draft Current Finishing Status :: Improved High-Quality Draft Assembly Method :: ALLPATHS v. R37654 Genome Coverage :: Unknown Sequencing Technology :: 454-GS-FLX%3B Illumina GAII ##Genome-Assembly-Data-END## ##Genome-Annotation-Data-START## Annotation Provider :: NCBI RefSeq Annotation Date :: 12/15/2019 15:43:43 Annotation Pipeline :: NCBI Prokaryotic Genome Annotation Pipeline (PGAP) Annotation Method :: Best-placed reference protein set%3B GeneMarkS-2+ Annotation Software revision :: 4.10 Features Annotated :: Gene%3B CDS%3B rRNA%3B tRNA%3B ncRNA%3B repeat_region Genes (total) :: 2%2C494 CDSs (total) :: 2%2C434 Genes (coding) :: 2%2C359 CDSs (with protein) :: 2%2C359 Genes (RNA) :: 60 rRNAs :: 1%2C 1%2C 1 (5S%2C 16S%2C 23S) complete rRNAs :: 1%2C 1%2C 1 (5S%2C 16S%2C 23S) tRNAs :: 53 ncRNAs :: 4 Pseudo Genes (total) :: 75 CDSs (without protein) :: 75 Pseudo Genes (ambiguous residues) :: 0 of 75 Pseudo Genes (frameshifted) :: 44 of 75 Pseudo Genes (incomplete) :: 31 of 75 Pseudo Genes (internal stop) :: 13 of 75 Pseudo Genes (multiple problems) :: 11 of 75 CRISPR Arrays :: 5 ##Genome-Annotation-Data-END## ;culture_collection=DSM:13641;date=15-DEC-2019;mol_type=genomic DNA;organism=Caldanaerobius polysaccharolyticus DSM 13641;strain=DSM 13641;submitter_seqid=CalpoDRAFT_CPK.2;type_material=type strain of Caldanaerobius polysaccharolyticus
NZ_KE386494	GenBank	gene	1	1041	.	+	1	ID=CALPO_RS0104485;Name=CALPO_RS0104485
NZ_KE386494	GenBank	mRNA	1	1041	.	+	1	ID=CALPO_RS0104485.t01;Parent=CALPO_RS0104485
NZ_KE386494	GenBank	CDS	1	1041	.	+	1	ID=CALPO_RS0104485.p01;Parent=CALPO_RS0104485.t01;Name=CALPO_RS0104485;Note=Derived by automated computational analysis using gene prediction method: Protein Homology.;codon_start=1;inference=COORDINATES: similar to AA sequence:RefSeq:WP_014518807.1;product=aliphatic sulfonate ABC transporter substrate-binding protein;protein_id=WP_026486265.1;transl_table=11;translation=length.346
NZ_KE386494	GenBank	exon	1	1041	.	+	1	Parent=CALPO_RS0104485.t01
NZ_KE386494	GenBank	gene	1065	1904	.	+	1	ID=CALPO_RS0104490;Name=CALPO_RS0104490
NZ_KE386494	GenBank	mRNA	1065	1904	.	+	1	ID=CALPO_RS0104490.t01;Parent=CALPO_RS0104490
NZ_KE386494	GenBank	CDS	1065	1904	.	+	1	ID=CALPO_RS0104490.p01;Parent=CALPO_RS0104490.t01;Name=CALPO_RS0104490;Note=Derived by automated computational analysis using gene prediction method: Protein Homology.;codon_start=1;inference=COORDINATES: similar to AA sequence:RefSeq:WP_007059403.1;product=ABC transporter ATP-binding protein;protein_id=WP_026486266.1;transl_table=11;translation=length.279
NZ_KE386494	GenBank	exon	1065	1904	.	+	1	Parent=CALPO_RS0104490.t01
NZ_KE386494	GenBank	gene	1837	2610	.	+	1	ID=CALPO_RS0104495;Name=CALPO_RS0104495
NZ_KE386494	GenBank	mRNA	1837	2610	.	+	1	ID=CALPO_RS0104495.t01;Parent=CALPO_RS0104495
NZ_KE386494	GenBank	CDS	1837	2610	.	+	1	ID=CALPO_RS0104495.p01;Parent=CALPO_RS0104495.t01;Name=CALPO_RS0104495;Note=Derived by automated computational analysis using gene prediction method: Protein Homology.;codon_start=1;inference=COORDINATES: similar to AA sequence:RefSeq:WP_015311744.1;product=ABC transporter permease;protein_id=WP_035172165.1;transl_table=11;translation=length.257
NZ_KE386494	GenBank	exon	1837	2610	.	+	1	Parent=CALPO_RS0104495.t01
NZ_KE386494	GenBank	gene	2615	4024	.	-	1	ID=CALPO_RS0104500;Name=CALPO_RS0104500
NZ_KE386494	GenBank	mRNA	2615	4024	.	-	1	ID=CALPO_RS0104500.t01;Parent=CALPO_RS0104500
NZ_KE386494	GenBank	CDS	2615	4024	.	-	1	ID=CALPO_RS0104500.p01;Parent=CALPO_RS0104500.t01;Name=CALPO_RS0104500;Note=Derived by automated computational analysis using gene prediction method: Protein Homology.;codon_start=1;inference=COORDINATES: similar to AA sequence:RefSeq:WP_013297199.1;product=arabinan endo-1%2C5-alpha-L-arabinosidase;protein_id=WP_026486268.1;transl_table=11;translation=length.469
NZ_KE386494	GenBank	exon	2615	4024	.	-	1	Parent=CALPO_RS0104500.t01
NZ_KE386494	GenBank	gene	4050	6005	.	-	1	ID=CALPO_RS0104505;Name=CALPO_RS0104505
NZ_KE386494	GenBank	mRNA	4050	6005	.	-	1	ID=CALPO_RS0104505.t01;Parent=CALPO_RS0104505
NZ_KE386494	GenBank	CDS	4050	6005	.	-	1	ID=CALPO_RS0104505.p01;Parent=CALPO_RS0104505.t01;Name=CALPO_RS0104505;Note=Derived by automated computational analysis using gene prediction method: Protein Homology.;codon_start=1;inference=COORDINATES: similar to AA sequence:RefSeq:WP_013150626.1;product=glycoside hydrolase family 127 protein;protein_id=WP_026486269.1;transl_table=11;translation=length.651
NZ_KE386494	GenBank	exon	4050	6005	.	-	1	Parent=CALPO_RS0104505.t01
NZ_KE386494	GenBank	gene	6092	7603	.	-	1	ID=CALPO_RS0104510;Name=CALPO_RS0104510
NZ_KE386494	GenBank	mRNA	6092	7603	.	-	1	ID=CALPO_RS0104510.t01;Parent=CALPO_RS0104510
NZ_KE386494	GenBank	CDS	6092	7603	.	-	1	ID=CALPO_RS0104510.p01;Parent=CALPO_RS0104510.t01;Name=CALPO_RS0104510;Note=Derived by automated computational analysis using gene prediction method: Protein Homology.;codon_start=1;inference=COORDINATES: similar to AA sequence:RefSeq:WP_013150627.1;product=alpha-N-arabinofuranosidase;protein_id=WP_026486270.1;transl_table=11;translation=length.503
NZ_KE386494	GenBank	exon	6092	7603	.	-	1	Parent=CALPO_RS0104510.t01
NZ_KE386494	GenBank	gene	7606	8877	.	-	1	ID=CALPO_RS0104515;Name=CALPO_RS0104515
NZ_KE386494	GenBank	mRNA	7606	8877	.	-	1	ID=CALPO_RS0104515.t01;Parent=CALPO_RS0104515
NZ_KE386494	GenBank	CDS	7606	8877	.	-	1	ID=CALPO_RS0104515.p01;Parent=CALPO_RS0104515.t01;Name=CALPO_RS0104515;Note=Derived by automated computational analysis using gene prediction method: Protein Homology.;codon_start=1;inference=COORDINATES: similar to AA sequence:RefSeq:WP_020616984.1;product=glycoside hydrolase family 27 protein;protein_id=WP_035172167.1;transl_table=11;translation=length.423
NZ_KE386494	GenBank	exon	7606	8877	.	-	1	Parent=CALPO_RS0104515.t01
NZ_KE386494	GenBank	gene	8927	10405	.	-	1	ID=CALPO_RS0104520;Name=CALPO_RS0104520
NZ_KE386494	GenBank	mRNA	8927	10405	.	-	1	ID=CALPO_RS0104520.t01;Parent=CALPO_RS0104520
NZ_KE386494	GenBank	CDS	8927	10405	.	-	1	ID=CALPO_RS0104520.p01;Parent=CALPO_RS0104520.t01;Name=CALPO_RS0104520;Note=Derived by automated computational analysis using gene prediction method: Protein Homology.;codon_start=1;inference=COORDINATES: similar to AA sequence:RefSeq:WP_017209453.1;product=alpha-N-arabinofuranosidase;protein_id=WP_026486272.1;transl_table=11;translation=length.492
NZ_KE386494	GenBank	exon	8927	10405	.	-	1	Parent=CALPO_RS0104520.t01
NZ_KE386494	GenBank	gene	10842	11744	.	-	1	ID=CALPO_RS0104525;Name=CALPO_RS0104525
NZ_KE386494	GenBank	mRNA	10842	11744	.	-	1	ID=CALPO_RS0104525.t01;Parent=CALPO_RS0104525
NZ_KE386494	GenBank	CDS	10842	11744	.	-	1	ID=CALPO_RS0104525.p01;Parent=CALPO_RS0104525.t01;Name=CALPO_RS0104525;Note=Derived by automated computational analysis using gene prediction method: Protein Homology.;codon_start=1;inference=COORDINATES: similar to AA sequence:RefSeq:WP_018884579.1;product=carbohydrate ABC transporter permease;protein_id=WP_026486273.1;transl_table=11;translation=length.300
NZ_KE386494	GenBank	exon	10842	11744	.	-	1	Parent=CALPO_RS0104525.t01
NZ_KE386494	GenBank	gene	11797	12741	.	-	1	ID=CALPO_RS0104530;Name=CALPO_RS0104530
NZ_KE386494	GenBank	mRNA	11797	12741	.	-	1	ID=CALPO_RS0104530.t01;Parent=CALPO_RS0104530
NZ_KE386494	GenBank	CDS	11797	12741	.	-	1	ID=CALPO_RS0104530.p01;Parent=CALPO_RS0104530.t01;Name=CALPO_RS0104530;Note=Derived by automated computational analysis using gene prediction method: Protein Homology.;codon_start=1;inference=COORDINATES: similar to AA sequence:RefSeq:WP_015736779.1;product=ABC transporter permease subunit;protein_id=WP_156940146.1;transl_table=11;translation=length.314
NZ_KE386494	GenBank	exon	11797	12741	.	-	1	Parent=CALPO_RS0104530.t01
NZ_KE386494	GenBank	gene	12832	14430	.	-	1	ID=CALPO_RS0104535;Name=CALPO_RS0104535
NZ_KE386494	GenBank	mRNA	12832	14430	.	-	1	ID=CALPO_RS0104535.t01;Parent=CALPO_RS0104535
NZ_KE386494	GenBank	CDS	12832	14430	.	-	1	ID=CALPO_RS0104535.p01;Parent=CALPO_RS0104535.t01;Name=CALPO_RS0104535;Note=Derived by automated computational analysis using gene prediction method: Protein Homology.;codon_start=1;inference=COORDINATES: similar to AA sequence:RefSeq:WP_018933442.1;product=extracellular solute-binding protein;protein_id=WP_026486275.1;transl_table=11;translation=length.532
NZ_KE386494	GenBank	exon	12832	14430	.	-	1	Parent=CALPO_RS0104535.t01
NZ_KE386494	GenBank	gene	14691	16538	.	-	1	ID=CALPO_RS0104540;Name=CALPO_RS0104540
NZ_KE386494	GenBank	mRNA	14691	16538	.	-	1	ID=CALPO_RS0104540.t01;Parent=CALPO_RS0104540
NZ_KE386494	GenBank	CDS	14691	16538	.	-	1	ID=CALPO_RS0104540.p01;Parent=CALPO_RS0104540.t01;Name=CALPO_RS0104540;Note=Derived by automated computational analysis using gene prediction method: Protein Homology.;codon_start=1;inference=COORDINATES: protein motif:HMM:NF019556.0;product=hypothetical protein;protein_id=WP_026486276.1;transl_table=11;translation=length.615
NZ_KE386494	GenBank	exon	14691	16538	.	-	1	Parent=CALPO_RS0104540.t01