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", "u4atac", "u6atac"]" sorted by percent_minor_introns descending
This data as json, CSV (advanced)
Suggested facets: family, 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+ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 55661 | Cuculus canorus | Cuculidae | Cuculiformes | Chordata | GCF_000709325.1 | 526 | 144534 | 0.3626085757617537 | 94.1 | ["u11", "u4atac", "u6atac"] | ASM70932v1 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/709/325/GCF_000709325.1_ASM70932v1 | GCF_000709325.1;PRJNA263299;SAMN02298149;JNOX00000000.1;representative genome;55661;55661;Cuculus canorus;;BGI_N303;latest;Scaffold;Major;Full;2014/06/17;ASM70932v1;BGI;GCA_000709325.1;identical;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/709/325/GCF_000709325.1_ASM70932v1;;;na | 1 |
| 115618 | Columbina picui | Columbidae | Columbiformes | Chordata | GCA_013397635.1 | 251 | 93219 | 0.2685353589386969 | 72.9 | ["u11", "u4atac", "u6atac"] | ASM1339763v1 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/013/397/635/GCA_013397635.1_ASM1339763v1 | GCA_013397635.1;PRJNA545868;SAMN12253927;VYZG00000000.1;representative genome;115618;115618;Columbina picui;;B10K-DU-021-26;latest;Scaffold;Major;Full;2020/07/10;ASM1339763v1;B10K Consortium;na;na;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/013/397/635/GCA_013397635.1_ASM1339763v1;;;na | 1 |
| 78915 | Thamnocephalis sphaerospora | Sigmoideomycetaceae | Zoopagales | Zoopagomycota | GCA_003614735.1 | 67 | 25406 | 0.2630235936089192 | 78.0 | ["u11", "u4atac", "u6atac"] | Thasp1 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/003/614/735/GCA_003614735.1_Thasp1 | GCA_003614735.1;PRJNA421763;SAMN09741940;QUVU00000000.1;representative genome;78915;78915;Thamnocephalis sphaerospora;strain=RSA 1356;;latest;Scaffold;Major;Full;2018/10/04;Thasp1;DOE Joint Genome Institute;na;na;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/003/614/735/GCA_003614735.1_Thasp1;derived from single cell;;na | 1 |
| 80765 | Aphis gossypii | Aphididae | Hemiptera | Arthropoda | GCF_004010815.1 | 133 | 83534 | 0.1589635101055374 | 95.7 | ["u11", "u4atac", "u6atac"] | ASM401081v1 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/004/010/815/GCF_004010815.1_ASM401081v1 | GCF_004010815.1;PRJNA520932;SAMN08384359;PPXK00000000.1;representative genome;80765;80765;Aphis gossypii;breed=cotton aphid;AGOS-L3;latest;Scaffold;Major;Full;2019/01/10;ASM401081v1;Institute of Plant Physiology and Ecology,SIBS,CAS;GCA_004010815.1;different;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/004/010/815/GCF_004010815.1_ASM401081v1;;;na | 1 |
| 59628 | Paragonimus skrjabini miyazakii | Troglotrematidae | Plagiorchiida | Platyhelminthes | GCA_014338405.1 | 92 | 72182 | 0.1272933558402745 | 79.6 | ["u11", "u4atac", "u6atac"] | P_miyazaki_1.0.pg.lrna | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/014/338/405/GCA_014338405.1_P_miyazaki_1.0.pg.lrna | GCA_014338405.1;PRJNA245325;SAMN03154469;JTDE00000000.1;representative genome;59628;59628;Paragonimus skrjabini miyazakii;strain=Japan;;latest;Scaffold;Major;Full;2020/08/31;P_miyazaki_1.0.pg.lrna;The Genome Institute;na;na;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/014/338/405/GCA_014338405.1_P_miyazaki_1.0.pg.lrna;;;na | 1 |
| 13347 | Armadillidium vulgare | Armadillidiidae | Isopoda | Arthropoda | GCA_004104545.1 | 48 | 92537 | 0.0518442512286007 | 65.1 | ["u11", "u4atac", "u6atac"] | Arma_vul_BF2787 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/004/104/545/GCA_004104545.1_Arma_vul_BF2787 | GCA_004104545.1;PRJNA501402;SAMN10345417;SAUD00000000.1;representative genome;13347;13347;Armadillidium vulgare;;BF2787;latest;Scaffold;Major;Full;2019/01/24;Arma_vul_BF2787;Universite de Poitiers ecologie et Biologie des Interactions, UMR CNRS 7267;na;na;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/004/104/545/GCA_004104545.1_Arma_vul_BF2787;;;na | 1 |
| 101127 | Hesseltinella vesiculosa | Cunninghamellaceae | Mucorales | Mucoromycota | GCA_002104935.1 | 17 | 39511 | 0.0430074883626796 | 94.9 | ["u11", "u4atac", "u6atac"] | Hesve2 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/002/104/935/GCA_002104935.1_Hesve2 | GCA_002104935.1;PRJNA243954;SAMN02745228;MCGT00000000.1;representative genome;101127;101127;Hesseltinella vesiculosa;strain=NRRL 3301;;latest;Contig;Major;Full;2017/04/20;Hesve2;DOE Joint Genome Institute;na;na;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/002/104/935/GCA_002104935.1_Hesve2;;;na | 1 |
| 6956 | Dermatophagoides pteronyssinus | Pyroglyphidae | Sarcoptiformes | Arthropoda | GCF_001901225.1 | 10 | 30330 | 0.03295978905735 | 92.5 | ["u11", "u4atac", "u6atac"] | ASM190122v2 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/001/901/225/GCF_001901225.1_ASM190122v2 | GCF_001901225.1;PRJNA509265;SAMN06062376;MQNO00000000.2;representative genome;6956;6956;Dermatophagoides pteronyssinus;strain=airmid;;latest;Scaffold;Major;Full;2017/06/21;ASM190122v2;Maynooth University;GCA_001901225.2;different;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/001/901/225/GCF_001901225.1_ASM190122v2;;;na | 1 |
| 6954 | Dermatophagoides farinae | Pyroglyphidae | Sarcoptiformes | Arthropoda | GCF_020809275.1 | 10 | 30775 | 0.0324833522819554 | 94.5 | ["u11", "u4atac", "u6atac"] | ASM2080927v1 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/020/809/275/GCF_020809275.1_ASM2080927v1 | GCF_020809275.1;PRJNA811591;SAMN10743607;SDOV00000000.1;representative genome;6954;6954;Dermatophagoides farinae;;JKM2019;latest;Contig;Major;Full;2021/11/09;ASM2080927v1;EasyATGC;GCA_020809275.1;different;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/020/809/275/GCF_020809275.1_ASM2080927v1;;;na | 1 |
| 13706 | Syncephalastrum racemosum | Syncephalastraceae | Mucorales | Mucoromycota | GCA_002105135.1 | 11 | 38912 | 0.0282609254168486 | 97.3 | ["u11", "u4atac", "u6atac"] | Synrac1 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/002/105/135/GCA_002105135.1_Synrac1 | GCA_002105135.1;PRJNA330704;SAMN05421883;MCGN00000000.1;representative genome;13706;13706;Syncephalastrum racemosum;strain=NRRL 2496;;latest;Contig;Major;Full;2017/04/20;Synrac1;DOE Joint Genome Institute;na;na;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/002/105/135/GCA_002105135.1_Synrac1;;;na | 1 |
| 2086695 | Heterostelium album | Acytosteliaceae | Acytosteliales | Evosea | GCF_000004825.1 | 7 | 32736 | 0.0213786152765476 | 86.7 | ["u11", "u4atac", "u6atac"] | PolPal_Dec2009 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/004/825/GCF_000004825.1_PolPal_Dec2009 | GCF_000004825.1;PRJNA46447;SAMN02953767;ADBJ00000000.1;representative genome;670386;2086695;Heterostelium album PN500;strain=PN500;;latest;Scaffold;Major;Full;2010/01/29;PolPal_Dec2009;Leibniz Institute for Age Research - Fritz Lipmann Institute;GCA_000004825.1;identical;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/004/825/GCF_000004825.1_PolPal_Dec2009;;;na | 1 |
| 278681 | Olpidium bornovanus | Olpidiaceae | Olpidiales | Olpidiomycota | GCA_017911155.1 | 3 | 14394 | 0.020837674515524 | 20.4 | ["u11", "u4atac", "u6atac"] | Olpbor1 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/017/911/155/GCA_017911155.1_Olpbor1 | GCA_017911155.1;PRJNA346684;SAMN05920846;JAEFCI000000000.1;representative genome;278681;278681;Olpidium bornovanus;;S191;latest;Contig;Major;Full;2021/04/08;Olpbor1;DOE Joint Genome Institute;na;na;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/017/911/155/GCA_017911155.1_Olpbor1;derived from metagenome;;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]);