Genome Information By Organism

genomes including sequences, maps, chromosomes, assemblies and annotations

@kaggle.lsind18_genome_information_by_organism

Table List

6 tables(30.92 MB)

Genomes

Viruses

Prokaryotes

@kaggle.lsind18_genome_information_by_organism.prokaryotes

24.87 MB
249357 rows
17 columns

organism_name Organism Name	organism_groups Organism Groups	strain Strain	biosample BioSample	bioproject BioProject	assembly Assembly	level Level	size_mb Size(Mb)	gc GC%	replicons Replicons	wgs WGS	scaffolds Scaffolds	cds CDS	release_date Release Date	genbank_ftp GenBank FTP	refseq_ftp RefSeq FTP	genes Genes
Campylobacter jejuni subsp. jejuni NCTC 11168 = ATCC 700819	Bacteria;Proteobacteria;delta/epsilon subdivisions	NCTC 11168	SAMEA1705929	PRJNA8	GCA_000009085.1	Complete	1.64148	30.5	chromosome:NC_002163.1/AL111168.1	nan	1	1572	Thu Sep 27 2001 00:00:00 GMT+0000 (Coordinated Universal Time)	ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/000/009/085/GCA_000009085.1_ASM908v1	ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/009/085/GCF_000009085.1_ASM908v1	1668
Pseudomonas fluorescens	Bacteria;Proteobacteria;Gammaproteobacteria	NCTC10038	SAMEA3649026	PRJEB6403	GCA_900475215.1	Complete	6.51517	60	chromosome 1:NZ_LS483372.1/LS483372.1	nan	1	5702	Sun Jun 17 2018 00:00:00 GMT+0000 (Coordinated Universal Time)	ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/900/475/215/GCA_900475215.1_42727_B01	ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/900/475/215/GCF_900475215.1_42727_B01	6076
Xanthomonas campestris pv. campestris str. ATCC 33913	Bacteria;Proteobacteria;Gammaproteobacteria	ATCC 33913	SAMN02603845	PRJNA296	GCA_000007145.1	Complete	5.07619	65.1	chromosome:NC_003902.1/AE008922.1	nan	1	4179	Wed Nov 28 2001 00:00:00 GMT+0000 (Coordinated Universal Time)	ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/000/007/145/GCA_000007145.1_ASM714v1	ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/007/145/GCF_000007145.1_ASM714v1	4240
Salmonella enterica subsp. enterica serovar Typhimurium str. LT2	Bacteria;Proteobacteria;Gammaproteobacteria	LT2	SAMN02604315	PRJNA241	GCA_000006945.2	Complete	4.95138	52.2171	chromosome:NC_003197.2/AE006468.2; plasmid pSLT:NC_003277.2/AE006471.2	nan	2	4548	Fri Oct 26 2001 00:00:00 GMT+0000 (Coordinated Universal Time)	ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/000/006/945/GCA_000006945.2_ASM694v2	ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/006/945/GCF_000006945.2_ASM694v2	4714
Yersinia pestis	Bacteria;Proteobacteria;Gammaproteobacteria	FDAARGOS_601	SAMN10228581	PRJNA231221	GCA_003798225.1	Complete	4.93096	47.6924	chromosome:NZ_CP033699.1/CP033699.1; plasmid unnamed1:NZ_CP033697.1/CP033697.1; plasmid unnamed2:NZ_CP033698.1/CP033698.1; plasmid unnamed3:NZ_CP033700.1/CP033700.1	nan	4	4104	Tue Nov 20 2018 00:00:00 GMT+0000 (Coordinated Universal Time)	ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/003/798/225/GCA_003798225.1_ASM379822v1	ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/003/798/225/GCF_003798225.1_ASM379822v1	4446
Staphylococcus aureus subsp. aureus NCTC 8325	Bacteria;Terrabacteria group;Firmicutes	NCTC 8325	SAMN02604235	PRJNA237	GCA_000013425.1	Complete	2.82136	32.9	chromosome:NC_007795.1/CP000253.1	nan	1	2767	Mon Feb 13 2006 00:00:00 GMT+0000 (Coordinated Universal Time)	ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/000/013/425/GCA_000013425.1_ASM1342v1	ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/013/425/GCF_000013425.1_ASM1342v1	2872
Staphylococcus epidermidis	Bacteria;Terrabacteria group;Firmicutes	ATCC 14990	SAMN10738425	PRJNA515334	GCA_006094375.1	Complete	2.49106	32.1745	chromosome:NZ_CP035288.1/CP035288.1; plasmid unnamed1:NZ_CP035289.1/CP035289.1; plasmid unnamed2:NZ_CP035290.1/CP035290.1	nan	3	2310	Thu Jun 06 2019 00:00:00 GMT+0000 (Coordinated Universal Time)	ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/006/094/375/GCA_006094375.1_ASM609437v1	ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/006/094/375/GCF_006094375.1_ASM609437v1	2454
Lactococcus lactis subsp. lactis	Bacteria;Terrabacteria group;Firmicutes	A12	SAMEA4005236	PRJEB14157	GCA_900088425.1	Complete	2.73062	35.4946	chromosome 1:NZ_LT599049.1/LT599049.1; plasmid pA12-1:NZ_LT599050.1/LT599050.1; plasmid pA12-2:NZ_LT599051.1/LT599051.1; plasmid pA12-3:NZ_LT599052.1/LT599052.1; plasmid pA12-4:NZ_LT599053.1/LT599053.1	nan	5	2484	Sat Jul 23 2016 00:00:00 GMT+0000 (Coordinated Universal Time)	ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/900/088/425/GCA_900088425.1_A12	ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/900/088/425/GCF_900088425.1_A12	2700
Bacillus cereus ATCC 14579	Bacteria;Terrabacteria group;Firmicutes	ATCC 14579	SAMN10591533	PRJNA509739	GCA_006094295.1	Complete	5.43138	35.3078	chromosome:NZ_CP034551.1/CP034551.1; plasmid unnamed:NZ_CP034552.1/CP034552.1	nan	2	5318	Thu Jun 06 2019 00:00:00 GMT+0000 (Coordinated Universal Time)	ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/006/094/295/GCA_006094295.1_ASM609429v1	ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/006/094/295/GCF_006094295.1_ASM609429v1	5629
Clostridium perfringens ATCC 13124	Bacteria;Terrabacteria group;Firmicutes	ATCC 13124	SAMN02604008	PRJNA304	GCA_000013285.1	Complete	3.25668	28.4	chromosome:NC_008261.1/CP000246.1	nan	1	2796	Tue Jul 25 2006 00:00:00 GMT+0000 (Coordinated Universal Time)	ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/000/013/285/GCA_000013285.1_ASM1328v1	ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/013/285/GCF_000013285.1_ASM1328v1	2949


CREATE TABLE prokaryotes (
  "organism_name" VARCHAR,
  "organism_groups" VARCHAR,
  "strain" VARCHAR,
  "biosample" VARCHAR,
  "bioproject" VARCHAR,
  "assembly" VARCHAR,
  "level" VARCHAR,
  "size_mb" DOUBLE,
  "gc" DOUBLE,
  "replicons" VARCHAR,
  "wgs" VARCHAR,
  "scaffolds" BIGINT,
  "cds" BIGINT,
  "release_date" TIMESTAMP,
  "genbank_ftp" VARCHAR,
  "refseq_ftp" VARCHAR,
  "genes" BIGINT
);