genomes
Data license: ODbL · Data source: Larue & Roy, 2023
- taxonomy_id
- INTEGER (primary key), unique identifier for each species
- species
- TEXT, binomial name of the species
- family
- TEXT, taxonomic family of the species
- order
- TEXT, taxonomic order of the species
- phylum
- TEXT, taxonomic phylum of the species
- accession
- TEXT, accession number of the genome assembly
- n_minor_introns
- INTEGER, total number of minor introns in the genome
- n_major_introns
- INTEGER, total number of major introns in the genome
- percent_minor_introns
- REAL, percentage of minor introns in the genome
- busco_score
- REAL, BUSCO score assessing the genome assembly completeness (vs. eukaryota_odb10)
- minor_snRNAs
- TEXT, minor snRNAs found in the annotated transcriptome
- genome_version
- TEXT, version of the genome assembly
- source_url
- TEXT, URL for the source genome/annotation files
- source_metadata
- TEXT, additional metadata from the original data source
- minor_intron+
- INTEGER, indicates if the species is inferred to contain real minor introns (1) or not (0)
12 rows where minor_snRNAs = "["u11", "u6atac"]" sorted by percent_minor_introns descending
This data as json, CSV (advanced)
Suggested facets: order, phylum, n_minor_introns, minor_snRNAs (array)
| taxonomy_id | species | family | order | phylum | accession | n_minor_introns | n_major_introns | percent_minor_introns ▲ | busco_score | minor_snRNAs | genome_version | source_url | source_metadata | minor_intron+ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 36300 | Pelecanus crispus | Pelecanidae | Pelecaniformes | Chordata | GCF_000687375.1 | 436 | 114858 | 0.3781636511873991 | 59.2 | ["u11", "u6atac"] | ASM68737v1 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/687/375/GCF_000687375.1_ASM68737v1 | GCF_000687375.1;PRJNA253833;SAMN02339887;JJRG00000000.1;representative genome;36300;36300;Pelecanus crispus;;BGI_N334;latest;Scaffold;Major;Full;2014/05/09;ASM68737v1;BGI;GCA_000687375.1;identical;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/687/375/GCF_000687375.1_ASM68737v1;;;na | 1 |
| 8969 | Haliaeetus albicilla | Accipitridae | Accipitriformes | Chordata | GCF_000691405.1 | 427 | 120618 | 0.352761369738527 | 67.1 | ["u11", "u6atac"] | ASM69140v1 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/691/405/GCF_000691405.1_ASM69140v1 | GCF_000691405.1;PRJNA263514;SAMN02333670;JJRL00000000.1;representative genome;8969;8969;Haliaeetus albicilla;;BGI_N329;latest;Scaffold;Major;Full;2014/05/15;ASM69140v1;BGI;GCA_000691405.1;identical;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/691/405/GCF_000691405.1_ASM69140v1;;;na | 1 |
| 30419 | Opisthocomus hoazin | Opisthocomidae | Opisthocomiformes | Chordata | GCF_000692075.1 | 454 | 131938 | 0.342921022418273 | 77.6 | ["u11", "u6atac"] | ASM69207v1 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/692/075/GCF_000692075.1_ASM69207v1 | GCF_000692075.1;PRJNA263612;SAMN02302474;JMFL00000000.1;representative genome;30419;30419;Opisthocomus hoazin;;BGI_N306;latest;Scaffold;Major;Full;2014/05/19;ASM69207v1;BGI;GCA_000692075.1;identical;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/692/075/GCF_000692075.1_ASM69207v1;;;na | 1 |
| 156563 | Cyanistes caeruleus | Paridae | Passeriformes | Chordata | GCF_002901205.1 | 540 | 168060 | 0.3202846975088968 | 90.2 | ["u11", "u6atac"] | cyaCae2 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/002/901/205/GCF_002901205.1_cyaCae2 | GCF_002901205.1;PRJNA432745;SAMN03734925;PDCF00000000.1;representative genome;156563;156563;Cyanistes caeruleus;;BT333_1;latest;Scaffold;Major;Full;2018/01/26;cyaCae2;Dr. Bernd Tmmermann, NGS core facility, MPI Molecular Genetics;GCA_002901205.1;identical;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/002/901/205/GCF_002901205.1_cyaCae2;;;na | 1 |
| 4155 | Erythranthe guttata | Phrymaceae | Lamiales | Streptophyta | GCF_000504015.1 | 325 | 120866 | 0.2681717289237649 | 98.8 | ["u11", "u6atac"] | Mimgu1_0 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/504/015/GCF_000504015.1_Mimgu1_0 | GCF_000504015.1;PRJNA285087;SAMN02742818;APLE00000000.1;representative genome;4155;4155;Erythranthe guttata;cultivar=IM62;;latest;Scaffold;Major;Full;2014/04/02;Mimgu1_0;DOE Joint Genome Institute;GCA_000504015.1;different;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/504/015/GCF_000504015.1_Mimgu1_0;;;na | 1 |
| 4146 | Olea europaea | Oleaceae | Lamiales | Streptophyta | GCF_002742605.1 | 383 | 181335 | 0.2107661321388085 | 95.7 | ["u11", "u6atac"] | O_europaea_v1 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/002/742/605/GCF_002742605.1_O_europaea_v1 | GCF_002742605.1;PRJNA417827;SAMN05943011;MSRW00000000.1;representative genome;158386;4146;Olea europaea var. sylvestris;;;latest;Chromosome;Major;Full;2017/11/03;O_europaea_v1;International Olive Genome Consortium;GCA_002742605.1;different;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/002/742/605/GCF_002742605.1_O_europaea_v1;;;na | 1 |
| 34283 | Gossypium armourianum | Malvaceae | Malvales | Streptophyta | GCA_013677265.1 | 65 | 63538 | 0.1021964372749713 | 41.6 | ["u11", "u6atac"] | ASM1367726v1 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/013/677/265/GCA_013677265.1_ASM1367726v1 | GCA_013677265.1;PRJNA488266;SAMN10346752;JABFAE000000000.1;representative genome;34283;34283;Gossypium armourianum;;6;latest;Chromosome;Major;Full;2020/09/03;ASM1367726v1;Mississippi State University;na;na;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/013/677/265/GCA_013677265.1_ASM1367726v1;;;na | 1 |
| 34504 | Paragonimus westermani | Troglotrematidae | Plagiorchiida | Platyhelminthes | GCA_008508345.1 | 36 | 53189 | 0.0676373884452794 | 71.8 | ["u11", "u6atac"] | ASM850834v1 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/008/508/345/GCA_008508345.1_ASM850834v1 | GCA_008508345.1;PRJNA454344;SAMN09005564;QNGE00000000.1;representative genome;34504;34504;Paragonimus westermani;strain=IND2009;;latest;Scaffold;Major;Full;2019/09/18;ASM850834v1;University of Queensland;na;na;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/008/508/345/GCA_008508345.1_ASM850834v1;;;na | 1 |
| 60492 | Racocetra fulgida | Gigasporaceae | Diversisporales | Mucoromycota | GCA_910592135.1 | 15 | 32613 | 0.0459727841118058 | 17.3 | ["u11", "u6atac"] | Racocetra_fulgida_IN212 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/910/592/135/GCA_910592135.1_Racocetra_fulgida_IN212 | GCA_910592135.1;PRJEB45340;SAMEA8911301;CAJVPZ000000000.1;representative genome;60492;60492;Racocetra fulgida;strain=IN212;IU-57-3 Pot A Chicken Ranch;latest;Contig;Major;Full;2021/11/12;Racocetra_fulgida_IN212;UPPSALA UNIVERISTY;na;na;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/910/592/135/GCA_910592135.1_Racocetra_fulgida_IN212;;;na | 1 |
| 109871 | Batrachochytrium dendrobatidis | Rhizophydiales | Chytridiomycota | GCF_000203795.1 | 3 | 28469 | 0.0105366676032593 | 92.5 | ["u11", "u6atac"] | v1.0 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/203/795/GCF_000203795.1_v1.0 | GCF_000203795.1;PRJNA225502;SAMN02746048;ADAR00000000.1;representative genome;684364;109871;Batrachochytrium dendrobatidis JAM81;strain=JAM81;;latest;Scaffold;Major;Full;2011/04/12;v1.0;US DOE Joint Genome Institute (JGI-PGF);GCA_000203795.1;identical;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/203/795/GCF_000203795.1_v1.0;;;na | 1 | |
| 1896186 | Mortierella sp. am989 | Mortierellaceae | Mortierellales | Mucoromycota | GCA_015502455.1 | 3 | 33147 | 0.0090497737556561 | 91.4 | ["u11", "u6atac"] | UCR_MspAM989 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/015/502/455/GCA_015502455.1_UCR_MspAM989 | GCA_015502455.1;PRJNA340567;SAMN05720439;JAAAUM000000000.1;representative genome;1896186;1896186;Mortierella sp. AM989;strain=AM989;;latest;Scaffold;Major;Full;2020/11/16;UCR_MspAM989;DOE Joint Genome Institute;na;na;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/015/502/455/GCA_015502455.1_UCR_MspAM989;;;na | 1 |
| 86630 | Rhizopus azygosporus | Rhizopodaceae | Mucorales | Mucoromycota | GCA_003325435.1 | 3 | 48803 | 0.006146785231324 | 94.1 | ["u11", "u6atac"] | Razy_CA | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/003/325/435/GCA_003325435.1_Razy_CA | GCA_003325435.1;PRJNA418064;SAMN08014123;PJQL00000000.1;representative genome;86630;86630;Rhizopus azygosporus;strain=CBS 357.93;;latest;Scaffold;Major;Full;2018/07/17;Razy_CA;University of California, Riverside;na;na;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/003/325/435/GCA_003325435.1_Razy_CA;;assembly from type material;na | 1 |
Advanced export
JSON shape: default, array, newline-delimited, object
CREATE TABLE "genomes" (
"taxonomy_id" INTEGER,
"species" TEXT,
"family" TEXT,
"order" TEXT,
"phylum" TEXT,
"accession" TEXT,
"n_minor_introns" INTEGER,
"n_major_introns" INTEGER,
"percent_minor_introns" REAL,
"busco_score" REAL,
"minor_snRNAs" TEXT,
"genome_version" TEXT,
"source_url" TEXT,
"source_metadata" TEXT,
"minor_intron+" INTEGER
,PRIMARY KEY ([taxonomy_id])
);
CREATE INDEX [idx_genomes_phylum]
ON [genomes] ([phylum]);
CREATE INDEX [idx_genomes_order]
ON [genomes] ([order]);
CREATE INDEX [idx_genomes_family]
ON [genomes] ([family]);