##gff-version 3
##sequence-region NZ_KE386494 1 7261
# 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	7261	.	+	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	555	.	-	1	ID=CALPO_RS0106040;Name=CALPO_RS0106040
NZ_KE386494	GenBank	mRNA	1	555	.	-	1	ID=CALPO_RS0106040.t01;Parent=CALPO_RS0106040
NZ_KE386494	GenBank	CDS	1	555	.	-	1	ID=CALPO_RS0106040.p01;Parent=CALPO_RS0106040.t01;eC_number=3.1.4.-;Name=CALPO_RS0106040;Note=Derived by automated computational analysis using gene prediction method: Protein Homology.;codon_start=1;inference=COORDINATES: similar to AA sequence:RefSeq:WP_014062550.1;product=phosphodiesterase;protein_id=WP_026486529.1;transl_table=11;translation=length.184
NZ_KE386494	GenBank	exon	1	555	.	-	1	Parent=CALPO_RS0106040.t01
NZ_KE386494	GenBank	gene	674	1657	.	-	1	ID=CALPO_RS0106045;Name=CALPO_RS0106045
NZ_KE386494	GenBank	mRNA	674	1657	.	-	1	ID=CALPO_RS0106045.t01;Parent=CALPO_RS0106045
NZ_KE386494	GenBank	CDS	674	1657	.	-	1	ID=CALPO_RS0106045.p01;Parent=CALPO_RS0106045.t01;Name=CALPO_RS0106045;Note=Derived by automated computational analysis using gene prediction method: Protein Homology.;codon_start=1;inference=COORDINATES: similar to AA sequence:RefSeq:WP_007655989.1;product=glycosidase;protein_id=WP_026486530.1;transl_table=11;translation=length.327
NZ_KE386494	GenBank	exon	674	1657	.	-	1	Parent=CALPO_RS0106045.t01
NZ_KE386494	GenBank	gene	1691	2515	.	-	1	ID=CALPO_RS0106050;Name=CALPO_RS0106050
NZ_KE386494	GenBank	mRNA	1691	2515	.	-	1	ID=CALPO_RS0106050.t01;Parent=CALPO_RS0106050
NZ_KE386494	GenBank	CDS	1691	2515	.	-	1	ID=CALPO_RS0106050.p01;Parent=CALPO_RS0106050.t01;Name=CALPO_RS0106050;Note=Derived by automated computational analysis using gene prediction method: Protein Homology.;codon_start=1;inference=COORDINATES: similar to AA sequence:RefSeq:WP_005545278.1;product=carbohydrate ABC transporter permease;protein_id=WP_026486531.1;transl_table=11;translation=length.274
NZ_KE386494	GenBank	exon	1691	2515	.	-	1	Parent=CALPO_RS0106050.t01
NZ_KE386494	GenBank	gene	2545	3423	.	-	1	ID=CALPO_RS0106055;Name=CALPO_RS0106055
NZ_KE386494	GenBank	mRNA	2545	3423	.	-	1	ID=CALPO_RS0106055.t01;Parent=CALPO_RS0106055
NZ_KE386494	GenBank	CDS	2545	3423	.	-	1	ID=CALPO_RS0106055.p01;Parent=CALPO_RS0106055.t01;Name=CALPO_RS0106055;Note=Derived by automated computational analysis using gene prediction method: Protein Homology.;codon_start=1;inference=COORDINATES: similar to AA sequence:RefSeq:WP_019006603.1;product=sugar ABC transporter permease;protein_id=WP_084295216.1;transl_table=11;translation=length.292
NZ_KE386494	GenBank	exon	2545	3423	.	-	1	Parent=CALPO_RS0106055.t01
NZ_KE386494	GenBank	gene	3511	4854	.	-	1	ID=CALPO_RS0106060;Name=CALPO_RS0106060
NZ_KE386494	GenBank	mRNA	3511	4854	.	-	1	ID=CALPO_RS0106060.t01;Parent=CALPO_RS0106060
NZ_KE386494	GenBank	CDS	3511	4854	.	-	1	ID=CALPO_RS0106060.p01;Parent=CALPO_RS0106060.t01;Name=CALPO_RS0106060;Note=Derived by automated computational analysis using gene prediction method: Protein Homology.;codon_start=1;inference=COORDINATES: protein motif:HMM:NF024808.0;product=ABC transporter substrate-binding protein;protein_id=WP_026486533.1;transl_table=11;translation=length.447
NZ_KE386494	GenBank	exon	3511	4854	.	-	1	Parent=CALPO_RS0106060.t01
NZ_KE386494	GenBank	gene	5009	6025	.	-	1	ID=CALPO_RS0106065;Name=CALPO_RS0106065
NZ_KE386494	GenBank	mRNA	5009	6025	.	-	1	ID=CALPO_RS0106065.t01;Parent=CALPO_RS0106065
NZ_KE386494	GenBank	CDS	5009	6025	.	-	1	ID=CALPO_RS0106065.p01;Parent=CALPO_RS0106065.t01;Name=CALPO_RS0106065;Note=Derived by automated computational analysis using gene prediction method: Protein Homology.;codon_start=1;inference=COORDINATES: similar to AA sequence:RefSeq:WP_013298389.1;product=LacI family transcriptional regulator;protein_id=WP_026486534.1;transl_table=11;translation=length.338
NZ_KE386494	GenBank	exon	5009	6025	.	-	1	Parent=CALPO_RS0106065.t01
NZ_KE386494	GenBank	gene	6269	7261	.	-	1	ID=CALPO_RS0106070;Name=CALPO_RS0106070
NZ_KE386494	GenBank	mRNA	6269	7261	.	-	1	ID=CALPO_RS0106070.t01;Parent=CALPO_RS0106070
NZ_KE386494	GenBank	CDS	6269	7261	.	-	1	ID=CALPO_RS0106070.p01;Parent=CALPO_RS0106070.t01;Name=CALPO_RS0106070;Note=Derived by automated computational analysis using gene prediction method: Protein Homology.;codon_start=1;inference=COORDINATES: similar to AA sequence:RefSeq:WP_013298386.1;product=cellulase family glycosylhydrolase;protein_id=WP_026486535.1;transl_table=11;translation=length.330
NZ_KE386494	GenBank	exon	6269	7261	.	-	1	Parent=CALPO_RS0106070.t01