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)
23 rows where phylum = "Mollusca" sorted by percent_minor_introns descending
This data as json, CSV (advanced)
Suggested facets: family, order, busco_score, minor_snRNAs, 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+ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 37653 | Octopus bimaculoides | Octopodidae | Octopoda | Mollusca | GCF_001194135.1 | 505 | 118177 | 0.4255068165349421 | 92.2 | ["u11", "u12", "u4atac", "u6atac"] | Octopus_bimaculoides_v2_0 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/001/194/135/GCF_001194135.1_Octopus_bimaculoides_v2_0 | GCF_001194135.1;PRJNA305125;SAMN03271701;LGKD00000000.1;representative genome;37653;37653;Octopus bimaculoides;;UCB-OBI-ISO-001;latest;Scaffold;Major;Full;2015/08/18;Octopus_bimaculoides_v2_0;Vincent J. Coates Genomic Sequencing Laboratory at UC Berkeley;GCA_001194135.1;identical;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/001/194/135/GCF_001194135.1_Octopus_bimaculoides_v2_0;;;na | 1 |
| 2607531 | Octopus sinensis | Octopodidae | Octopoda | Mollusca | GCF_006345805.1 | 548 | 146482 | 0.3727130517581446 | 98.0 | ["u11", "u12", "u4atac", "u6atac"] | ASM634580v1 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/006/345/805/GCF_006345805.1_ASM634580v1 | GCF_006345805.1;PRJNA551489;SAMN11633729;VCDQ00000000.1;representative genome;2607531;2607531;Octopus sinensis;;Ov201803;latest;Chromosome;Major;Full;2019/06/17;ASM634580v1;Yellow Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences;GCA_006345805.1;different;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/006/345/805/GCF_006345805.1_ASM634580v1;;;na | 1 |
| 1735272 | Gigantopelta aegis | Peltospiridae | Mollusca | GCF_016097555.1 | 613 | 176410 | 0.3462826864305768 | 99.6 | ["u11", "u12", "u4atac", "u6atac"] | Gae_host_genome | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/016/097/555/GCF_016097555.1_Gae_host_genome | GCF_016097555.1;PRJNA727593;SAMN16968444;JAEHGF000000000.1;representative genome;1735272;1735272;Gigantopelta aegis;;Gae_Host;latest;Chromosome;Major;Full;2020/12/17;Gae_host_genome;Hong Kong University of Science and Technology;GCA_016097555.1;identical;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/016/097/555/GCF_016097555.1_Gae_host_genome;;;na | 1 | |
| 6500 | Aplysia californica | Aplysiidae | Aplysiida | Mollusca | GCF_000002075.1 | 476 | 141803 | 0.3345539397943477 | 91.4 | ["u11", "u12", "u4atac"] | AplCal3.0 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/002/075/GCF_000002075.1_AplCal3.0 | GCF_000002075.1;PRJNA209509;SAMN02953658;AASC00000000.3;representative genome;6500;6500;Aplysia californica;;F4 #8;latest;Scaffold;Major;Full;2013/05/15;AplCal3.0;Broad Institute;GCA_000002075.2;different;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/002/075/GCF_000002075.1_AplCal3.0;;;na | 1 |
| 6573 | Mizuhopecten yessoensis | Pectinidae | Pectinida | Mollusca | GCF_002113885.1 | 609 | 187321 | 0.324056829670622 | 98.4 | ["u11", "u12", "u4atac", "u6atac"] | ASM211388v2 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/002/113/885/GCF_002113885.1_ASM211388v2 | GCF_002113885.1;PRJNA390633;SAMN03013375;NEDP00000000.2;representative genome;6573;6573;Mizuhopecten yessoensis;strain=PY_sf001;;latest;Scaffold;Major;Full;2017/06/12;ASM211388v2;Novogene;GCA_002113885.2;different;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/002/113/885/GCF_002113885.1_ASM211388v2;;;na | 1 |
| 6579 | Pecten maximus | Pectinidae | Pectinida | Mollusca | GCF_902652985.1 | 617 | 190510 | 0.3228219979385435 | 98.4 | ["u11", "u12", "u4atac", "u6atac"] | xPecMax1.1 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/902/652/985/GCF_902652985.1_xPecMax1.1 | GCF_902652985.1;PRJNA625562;SAMEA994736;CACRWE000000000.1;representative genome;6579;6579;Pecten maximus;;;latest;Chromosome;Major;Full;2019/11/26;xPecMax1.1;SC;GCA_902652985.1;identical;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/902/652/985/GCF_902652985.1_xPecMax1.1;;;na | 1 |
| 100452 | Candidula unifasciata | Geomitridae | Stylommatophora | Mollusca | GCA_905116865.2 | 401 | 124877 | 0.3200881240121969 | 83.1 | ["u11", "u12", "u4atac", "u6atac"] | CUNI_anot_genome.v2 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/905/116/865/GCA_905116865.2_CUNI_anot_genome.v2 | GCA_905116865.2;PRJEB41346;SAMEA7574008;CAJHNH000000000.2;representative genome;100452;100452;Candidula unifasciata;;;latest;Scaffold;Major;Full;2021/05/16;CUNI_anot_genome.v2;Senckenber Biodiversity and Climate Research Centre Frankfurt;na;na;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/905/116/865/GCA_905116865.2_CUNI_anot_genome.v2;;;na | 1 |
| 188477 | Elysia chlorotica | Plakobranchidae | Mollusca | GCA_003991915.1 | 404 | 130418 | 0.3088165599058262 | 92.9 | ["u11", "u12", "u4atac", "u6atac"] | ElyChl2.0 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/003/991/915/GCA_003991915.1_ElyChl2.0 | GCA_003991915.1;PRJNA484060;SAMN09762595;RQTK00000000.1;representative genome;188477;188477;Elysia chlorotica;;EC2010;latest;Scaffold;Major;Full;2019/01/04;ElyChl2.0;BGI;na;na;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/003/991/915/GCA_003991915.1_ElyChl2.0;;;na | 1 | |
| 400727 | Pomacea canaliculata | Ampullariidae | Architaenioglossa | Mollusca | GCF_003073045.1 | 570 | 188773 | 0.3010409679787476 | 100.0 | ["u11", "u12", "u4atac", "u6atac"] | ASM307304v1 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/003/073/045/GCF_003073045.1_ASM307304v1 | GCF_003073045.1;PRJNA472795;SAMN08443704;PZQS00000000.1;representative genome;400727;400727;Pomacea canaliculata;;SZHN2017;latest;Chromosome;Major;Full;2018/05/11;ASM307304v1;Agricultural Genomics Institute at Shenzhen, Chinese Academy of Agricultural Sciences;GCA_003073045.1;different;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/003/073/045/GCF_003073045.1_ASM307304v1;;;na | 1 |
| 225164 | Lottia gigantea | Lottiidae | Mollusca | GCF_000327385.1 | 352 | 119088 | 0.2947086403215003 | 95.7 | ["u11", "u12", "u4atac", "u6atac"] | Helro1 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/327/385/GCF_000327385.1_Helro1 | GCF_000327385.1;PRJNA259762;SAMN02769626;AMQO00000000.1;representative genome;225164;225164;Lottia gigantea;;;latest;Scaffold;Major;Full;2012/12/20;Helro1;DOE Joint Genome Institute;GCA_000327385.1;identical;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/327/385/GCF_000327385.1_Helro1;;;na | 1 | |
| 6526 | Biomphalaria glabrata | Planorbidae | Mollusca | GCF_000457365.1 | 464 | 168163 | 0.2751635266001292 | 85.9 | ["u11", "u12", "u4atac", "u6atac"] | ASM45736v1 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/457/365/GCF_000457365.1_ASM45736v1 | GCF_000457365.1;PRJNA290623;SAMN02953846;APKA00000000.1;representative genome;6526;6526;Biomphalaria glabrata;;BB02;latest;Scaffold;Major;Full;2013/09/06;ASM45736v1;Washington University (WashU);GCA_000457365.1;different;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/457/365/GCF_000457365.1_ASM45736v1;;;na | 1 | |
| 36100 | Haliotis rubra | Haliotidae | Lepetellida | Mollusca | GCF_003918875.1 | 596 | 226514 | 0.2624278983752366 | 96.9 | ["u11", "u12", "u4atac", "u6atac"] | ASM391887v1 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/003/918/875/GCF_003918875.1_ASM391887v1 | GCF_003918875.1;PRJNA801670;SAMN09981888;QXJH00000000.1;representative genome;36100;36100;Haliotis rubra;;DU_JTF1;latest;Scaffold;Major;Full;2018/12/07;ASM391887v1;Deakin University;GCA_003918875.1;different;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/003/918/875/GCF_003918875.1_ASM391887v1;;;na | 1 |
| 6454 | Haliotis rufescens | Haliotidae | Lepetellida | Mollusca | GCF_003343065.1 | 644 | 256099 | 0.2508344920796282 | 98.0 | ["u11", "u12", "u4atac", "u6atac"] | H.ruf_v1.0 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/003/343/065/GCF_003343065.1_H.ruf_v1.0 | GCF_003343065.1;PRJNA801671;SAMN08558906;QGMO00000000.1;representative genome;6454;6454;Haliotis rufescens;;Redab-CP-2226-F;latest;Scaffold;Major;Full;2018/07/26;H.ruf_v1.0;Iowa State University;GCA_003343065.1;different;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/003/343/065/GCF_003343065.1_H.ruf_v1.0;;;na | 1 |
| 6565 | Crassostrea virginica | Ostreidae | Ostreida | Mollusca | GCF_002022765.2 | 695 | 278262 | 0.2491423409342658 | 97.6 | ["u11", "u12", "u4atac", "u6atac"] | C_virginica-3.0 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/002/022/765/GCF_002022765.2_C_virginica-3.0 | GCF_002022765.2;PRJNA379157;SAMN06349363;MWPT00000000.3;representative genome;6565;6565;Crassostrea virginica;;RU13XGHG1-28;latest;Chromosome;Major;Full;2017/09/01;C_virginica-3.0;McDonnell Genome Institute - Washington University School of Medicine;GCA_002022765.4;different;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/002/022/765/GCF_002022765.2_C_virginica-3.0;;;na | 1 |
| 6596 | Mercenaria mercenaria | Veneridae | Venerida | Mollusca | GCF_014805675.1 | 585 | 246956 | 0.2363244876606299 | 96.5 | ["u11", "u12", "u4atac", "u6atac"] | ASM1480567v1.1 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/014/805/675/GCF_014805675.1_ASM1480567v1.1 | GCF_014805675.1;PRJNA783326;SAMN13611631;WTXZ00000000.1;representative genome;6596;6596;Mercenaria mercenaria;;YKG-2019;latest;Chromosome;Major;Full;2020/10/02;ASM1480567v1.1;Institute of Oceanology, Chinese Academy of Sciences;GCA_014805675.2;different;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/014/805/675/GCF_014805675.1_ASM1480567v1.1;;;na | 1 |
| 29159 | Crassostrea gigas | Ostreidae | Ostreida | Mollusca | GCF_902806645.1 | 574 | 243087 | 0.2355731939046462 | 100.0 | ["u11", "u12", "u4atac", "u6atac"] | cgigas_uk_roslin_v1 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/902/806/645/GCF_902806645.1_cgigas_uk_roslin_v1 | GCF_902806645.1;PRJNA629593;SAMEA6259236;CADCXH000000000.1;representative genome;29159;29159;Crassostrea gigas;;;latest;Chromosome;Major;Full;2020/02/19;cgigas_uk_roslin_v1;THE ROSLIN INSTITUTE;GCA_902806645.1;identical;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/902/806/645/GCF_902806645.1_cgigas_uk_roslin_v1;;;na | 1 |
| 158019 | Sepia pharaonis | Sepiidae | Sepiida | Mollusca | GCA_903632075.3 | 495 | 214778 | 0.229940587068513 | 77.3 | ["u11", "u12", "u4atac", "u6atac"] | SPHA2.0 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/903/632/075/GCA_903632075.3_SPHA2.0 | GCA_903632075.3;PRJEB33343;SAMEA6654644;CAHIKZ000000000.3;representative genome;158019;158019;Sepia pharaonis;strain=farmed;;latest;Contig;Major;Full;2021/02/02;SPHA2.0;NINGBO UNIVERSITY;na;na;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/903/632/075/GCA_903632075.3_SPHA2.0;;;na | 1 |
| 55810 | Bulinus truncatus | Planorbidae | Mollusca | GCA_021962125.1 | 460 | 210043 | 0.2185242015553222 | 92.5 | ["u11", "u12", "u4atac", "u6atac"] | Btru.v1 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/021/962/125/GCA_021962125.1_Btru.v1 | GCA_021962125.1;PRJNA680620;SAMN17050146;JAGDYQ000000000.1;representative genome;55810;55810;Bulinus truncatus;;NR-21971;latest;Scaffold;Major;Full;2022/02/04;Btru.v1;The University of Melbourne;na;na;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/021/962/125/GCA_021962125.1_Btru.v1;;;na | 1 | |
| 259542 | Plakobranchus ocellatus | Plakobranchidae | Mollusca | GCA_019648995.1 | 347 | 190990 | 0.1813554095653219 | 87.1 | ["u11", "u12", "u4atac", "u6atac"] | PoB_v1 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/019/648/995/GCA_019648995.1_PoB_v1 | GCA_019648995.1;PRJDB3267;SAMD00025085;BLXT00000000.1;representative genome;259542;259542;Plakobranchus ocellatus;;;latest;Scaffold;Major;Full;2021/05/09;PoB_v1;National Institute for Basic Biology;na;na;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/019/648/995/GCA_019648995.1_PoB_v1;;;na | 1 | |
| 1093978 | Elysia marginata | Plakobranchidae | Mollusca | GCA_019649035.1 | 309 | 171432 | 0.179922091987353 | 85.5 | ["u11", "u12", "u4atac", "u6atac"] | Ema_v1 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/019/649/035/GCA_019649035.1_Ema_v1 | GCA_019649035.1;PRJDB3267;SAMD00025083;BMAT00000000.1;representative genome;1093978;1093978;Elysia marginata;;;latest;Scaffold;Major;Full;2021/05/09;Ema_v1;National Institute for Basic Biology;na;na;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/019/649/035/GCA_019649035.1_Ema_v1;;;na | 1 | |
| 29158 | Mytilus galloprovincialis | Mytilidae | Mytilida | Mollusca | GCA_900618805.1 | 449 | 283796 | 0.157962321236961 | 72.2 | ["u11", "u12", "u4atac", "u6atac"] | MGAL_10 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/900/618/805/GCA_900618805.1_MGAL_10 | GCA_900618805.1;PRJEB24883;SAMEA104605961;UYJE00000000.1;representative genome;29158;29158;Mytilus galloprovincialis;;;latest;Scaffold;Major;Full;2020/10/12;MGAL_10;CNAG;na;na;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/900/618/805/GCA_900618805.1_MGAL_10;;;na | 1 |
| 370345 | Batillaria attramentaria | Batillariidae | Mollusca | GCA_018292915.1 | 205 | 139093 | 0.147166506338928 | 36.5 | ["u11", "u12", "u4atac", "u6atac"] | EWHU_Batt_1.0 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/018/292/915/GCA_018292915.1_EWHU_Batt_1.0 | GCA_018292915.1;PRJNA640962;SAMN15338893;JACVVK000000000.1;representative genome;370345;370345;Batillaria attramentaria;;Wonlab-2016;latest;Contig;Major;Full;2021/05/06;EWHU_Batt_1.0;Ewha Womans University;na;na;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/018/292/915/GCA_018292915.1_EWHU_Batt_1.0;;;na | 1 | |
| 45954 | Dreissena polymorpha | Dreissenidae | Myida | Mollusca | GCA_020536995.1 | 408 | 332362 | 0.1226072061784415 | 80.4 | ["u11", "u12", "u4atac", "u6atac"] | UMN_Dpol_1.0 | https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/020/536/995/GCA_020536995.1_UMN_Dpol_1.0 | GCA_020536995.1;PRJNA533175;SAMN11444935;JAIWYP000000000.1;representative genome;45954;45954;Dreissena polymorpha;;Duluth1;latest;Chromosome;Major;Full;2021/10/26;UMN_Dpol_1.0;University of Minnesota;na;na;https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/020/536/995/GCA_020536995.1_UMN_Dpol_1.0;;;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]);