##gff-version 3
##sequence-region NC_023151 1 9871
# conversion-by bp_genbank2gff3.pl
# organism Thermotoga maritima MSB8
# Note Thermotoga maritima MSB8, complete genome.
# date 09-DEC-2019
NC_023151	GenBank	region	1	9871	.	+	1	ID=NC_023151;Dbxref=BioProject:PRJNA224116,taxon:243274;Name=NC_023151;Note=Thermotoga maritima MSB8%2C complete genome.,REFSEQ INFORMATION: The reference sequence was derived from CP007013. URL -- http://www.jgi.doe.gov JGI Project ID: 403117 Source DNA and Organism available from Kenneth M. Noll (noll@uconn.edu) Source DNA available from Kenneth M. Noll (noll@uconn.edu) Organism available from Kenneth M. Noll (noll@uconn.edu) Contacts: Kenneth M. Noll (noll@uconn.edu) Tanja Woyke (microbe@cuba.jgi-psf.org) Whole genome sequencing and draft assembly at JGI-PGF Annotation by JGI-ORNL 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). 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## investigation_type :: bacteria_archaea project_name :: Thermotoga maritima MSB8,DSM 3109 collection_date :: 1982 lat_lon :: 38.3912 14.9676 country :: Italy num_replicons :: 1 ref_biomaterial :: DSM 3109,ATCC 43589 biotic_relationship :: Free living rel_to_oxygen :: Anaerobe isol_growth_condt :: 10360571 assembly :: Newbler v. 2.3 finishing_strategy :: Level 6: Finished environment :: Mud sequencing_meth :: WGS GOLD Stamp ID :: Gi08995 Current Finishing Status :: Level 6: Finished Type Strain :: Yes Funding Program :: DOE-CSP 2010 Gene Calling Method :: Prodigal 1.4,GenePRIMP Isolation Site :: anaerobic marine mud Isolation Comments :: isolated by Stetter Temperature Range :: Hyperthermophile Temperature Optimum :: 80 Gram Staining :: Gram- Sequencing Depth :: 30x Diseases :: None ##MIGS-Data-END## ##Genome-Assembly-Data-START## Finishing Goal :: Finished Current Finishing Status :: Finished Assembly Method :: Newbler v. 2.3 Genome Coverage :: 30x Sequencing Technology :: 454,Illumina GAii ##Genome-Assembly-Data-END## ##Genome-Annotation-Data-START## Annotation Provider :: NCBI RefSeq Annotation Date :: 12/09/2019 02:10:01 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) :: 1,945 CDSs (total) :: 1,893 Genes (coding) :: 1,877 CDSs (with protein) :: 1,877 Genes (RNA) :: 52 rRNAs :: 1,1,1 (5S,16S,23S) complete rRNAs :: 1,1,1 (5S,16S,23S) tRNAs :: 46 ncRNAs :: 3 Pseudo Genes (total) :: 16 CDSs (without protein) :: 16 Pseudo Genes (ambiguous residues) :: 0 of 16 Pseudo Genes (frameshifted) :: 10 of 16 Pseudo Genes (incomplete) :: 9 of 16 Pseudo Genes (internal stop) :: 2 of 16 Pseudo Genes (multiple problems) :: 4 of 16 CRISPR Arrays :: 7 ##Genome-Annotation-Data-END## COMPLETENESS: full length. ;comment1=REFSEQ INFORMATION: The reference sequence was derived from CP007013. URL -- http://www.jgi.doe.gov JGI Project ID: 403117 Source DNA and Organism available from Kenneth M. Noll (noll@uconn.edu) Source DNA available from Kenneth M. Noll (noll@uconn.edu) Organism available from Kenneth M. Noll (noll@uconn.edu) Contacts: Kenneth M. Noll (noll@uconn.edu) Tanja Woyke (microbe@cuba.jgi-psf.org) Whole genome sequencing and draft assembly at JGI-PGF Annotation by JGI-ORNL 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). 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## investigation_type :: bacteria_archaea project_name :: Thermotoga maritima MSB8%2C DSM 3109 collection_date :: 1982 lat_lon :: 38.3912 14.9676 country :: Italy num_replicons :: 1 ref_biomaterial :: DSM 3109%2C ATCC 43589 biotic_relationship :: Free living rel_to_oxygen :: Anaerobe isol_growth_condt :: 10360571 assembly :: Newbler v. 2.3 finishing_strategy :: Level 6: Finished environment :: Mud sequencing_meth :: WGS GOLD Stamp ID :: Gi08995 Current Finishing Status :: Level 6: Finished Type Strain :: Yes Funding Program :: DOE-CSP 2010 Gene Calling Method :: Prodigal 1.4%2C GenePRIMP Isolation Site :: anaerobic marine mud Isolation Comments :: isolated by Stetter Temperature Range :: Hyperthermophile Temperature Optimum :: 80 Gram Staining :: Gram- Sequencing Depth :: 30x Diseases :: None ##MIGS-Data-END## ##Genome-Assembly-Data-START## Finishing Goal :: Finished Current Finishing Status :: Finished Assembly Method :: Newbler v. 2.3 Genome Coverage :: 30x Sequencing Technology :: 454%3B Illumina GAii ##Genome-Assembly-Data-END## ##Genome-Annotation-Data-START## Annotation Provider :: NCBI RefSeq Annotation Date :: 12/09/2019 02:10:01 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) :: 1%2C945 CDSs (total) :: 1%2C893 Genes (coding) :: 1%2C877 CDSs (with protein) :: 1%2C877 Genes (RNA) :: 52 rRNAs :: 1%2C 1%2C 1 (5S%2C 16S%2C 23S) complete rRNAs :: 1%2C 1%2C 1 (5S%2C 16S%2C 23S) tRNAs :: 46 ncRNAs :: 3 Pseudo Genes (total) :: 16 CDSs (without protein) :: 16 Pseudo Genes (ambiguous residues) :: 0 of 16 Pseudo Genes (frameshifted) :: 10 of 16 Pseudo Genes (incomplete) :: 9 of 16 Pseudo Genes (internal stop) :: 2 of 16 Pseudo Genes (multiple problems) :: 4 of 16 CRISPR Arrays :: 7 ##Genome-Annotation-Data-END## COMPLETENESS: full length. ;culture_collection=DSM:3109;date=09-DEC-2019;isolation_source=anaerobic marine mud;mol_type=genomic DNA;organism=Thermotoga maritima MSB8;strain=MSB8;type_material=type strain of Thermotoga maritima
NC_023151	GenBank	gene	1	1950	.	+	1	ID=THEMA_RS08275;Name=THEMA_RS08275;old_locus_tag=THEMA_08355
NC_023151	GenBank	mRNA	1	1950	.	+	1	ID=THEMA_RS08275.t01;Parent=THEMA_RS08275
NC_023151	GenBank	CDS	1	1950	.	+	1	ID=THEMA_RS08275.p01;Parent=THEMA_RS08275.t01;Name=THEMA_RS08275;Note=Derived by automated computational analysis using gene prediction method: Protein Homology.;codon_start=1;inference=COORDINATES: similar to AA sequence:RefSeq:NP_229000.1;old_locus_tag=THEMA_08355;product=beta-galactosidase;protein_id=WP_004080133.1;transl_table=11;translation=length.649
NC_023151	GenBank	exon	1	1950	.	+	1	Parent=THEMA_RS08275.t01
NC_023151	GenBank	gene	1965	2945	.	+	1	ID=THEMA_RS08280;Name=THEMA_RS08280;old_locus_tag=THEMA_08360
NC_023151	GenBank	mRNA	1965	2945	.	+	1	ID=THEMA_RS08280.t01;Parent=THEMA_RS08280
NC_023151	GenBank	CDS	1965	2945	.	+	1	ID=THEMA_RS08280.p01;Parent=THEMA_RS08280.t01;Name=THEMA_RS08280;Note=Derived by automated computational analysis using gene prediction method: Protein Homology.;codon_start=1;inference=COORDINATES: similar to AA sequence:RefSeq:NP_228999.1;old_locus_tag=THEMA_08360;product=ABC transporter ATP-binding protein;protein_id=WP_004080134.1;transl_table=11;translation=length.326
NC_023151	GenBank	exon	1965	2945	.	+	1	Parent=THEMA_RS08280.t01
NC_023151	GenBank	gene	2942	6205	.	+	1	ID=THEMA_RS08285;Name=THEMA_RS08285;old_locus_tag=THEMA_08365
NC_023151	GenBank	mRNA	2942	6205	.	+	1	ID=THEMA_RS08285.t01;Parent=THEMA_RS08285
NC_023151	GenBank	CDS	2942	6205	.	+	1	ID=THEMA_RS08285.p01;Parent=THEMA_RS08285.t01;Name=THEMA_RS08285;Note=Derived by automated computational analysis using gene prediction method: Protein Homology.;codon_start=1;inference=COORDINATES: similar to AA sequence:RefSeq:NP_228998.1;old_locus_tag=THEMA_08365;product=DUF4981 domain-containing protein;protein_id=WP_010865279.1;transl_table=11;translation=length.1087
NC_023151	GenBank	exon	2942	6205	.	+	1	Parent=THEMA_RS08285.t01
NC_023151	GenBank	gene	6211	7869	.	+	1	ID=THEMA_RS08290;Name=THEMA_RS08290;old_locus_tag=THEMA_08370
NC_023151	GenBank	mRNA	6211	7869	.	+	1	ID=THEMA_RS08290.t01;Parent=THEMA_RS08290
NC_023151	GenBank	CDS	6211	7869	.	+	1	ID=THEMA_RS08290.p01;Parent=THEMA_RS08290.t01;Name=THEMA_RS08290;Note=Derived by automated computational analysis using gene prediction method: Protein Homology.;codon_start=1;inference=COORDINATES: similar to AA sequence:RefSeq:NP_228997.1;old_locus_tag=THEMA_08370;product=alpha-galactosidase;protein_id=WP_004080136.1;transl_table=11;translation=length.552
NC_023151	GenBank	exon	6211	7869	.	+	1	Parent=THEMA_RS08290.t01
NC_023151	GenBank	gene	7866	8822	.	+	1	ID=THEMA_RS08295;Name=galT;locus_tag=THEMA_RS08295;old_locus_tag=THEMA_08375
NC_023151	GenBank	mRNA	7866	8822	.	+	1	ID=THEMA_RS08295.t01;Parent=THEMA_RS08295
NC_023151	GenBank	CDS	7866	8822	.	+	1	ID=THEMA_RS08295.p01;Parent=THEMA_RS08295.t01;Name=galT;Note=Derived by automated computational analysis using gene prediction method: Protein Homology.;codon_start=1;inference=COORDINATES: similar to AA sequence:RefSeq:NP_228996.1;locus_tag=THEMA_RS08295;old_locus_tag=THEMA_08375;product=galactose-1-phosphate uridylyltransferase;protein_id=WP_004080138.1;transl_table=11;translation=length.318
NC_023151	GenBank	exon	7866	8822	.	+	1	Parent=THEMA_RS08295.t01
NC_023151	GenBank	gene	8819	9871	.	+	1	ID=THEMA_RS08300;Name=THEMA_RS08300;old_locus_tag=THEMA_08380
NC_023151	GenBank	mRNA	8819	9871	.	+	1	ID=THEMA_RS08300.t01;Parent=THEMA_RS08300
NC_023151	GenBank	CDS	8819	9871	.	+	1	ID=THEMA_RS08300.p01;Parent=THEMA_RS08300.t01;eC_number=2.7.1.6;Name=THEMA_RS08300;Note=Derived by automated computational analysis using gene prediction method: Protein Homology.;codon_start=1;inference=COORDINATES: similar to AA sequence:RefSeq:NP_228995.1;old_locus_tag=THEMA_08380;product=galactokinase;protein_id=WP_004080140.1;transl_table=11;translation=length.350
NC_023151	GenBank	exon	8819	9871	.	+	1	Parent=THEMA_RS08300.t01