Skip to content

Commit

Permalink
Clusterization of embeddings using GENA
Browse files Browse the repository at this point in the history
  • Loading branch information
@alexeyshmelev
alexeyshmelev authored Oct 11, 2024
1 parent d338b2e commit daae5ed
Show file tree
Hide file tree
Showing 2 changed files with 7,688 additions and 0 deletions.
28 changes: 28 additions & 0 deletions notebooks/2023-08-10 19_40_52.828317species_extended_metadata.csv
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,28 @@
,species,accession,current_accession,source_database,assembly_info.assembly_level,assembly_info.assembly_name,assembly_info.assembly_status,assembly_info.assembly_type,assembly_info.refseq_category,assembly_info.release_date,assembly_info.submitter,assembly_stats.contig_l50,assembly_stats.contig_n50,assembly_stats.gc_count,assembly_stats.gc_percent,assembly_stats.number_of_component_sequences,assembly_stats.number_of_contigs,assembly_stats.total_sequence_length,assembly_stats.total_ungapped_length,organism.organism_name,organism.tax_id,why_selected
0,homo_sapiens,GCF_000001405.40,GCF_000001405.40,SOURCE_DATABASE_REFSEQ,Chromosome,GRCh38.p14,current,haploid-with-alt-loci,reference genome,2022-02-03,Genome Reference Consortium,18,57879411,1374283647,40.5,35611,996,3099441038,2948318359,Homo sapiens,9606,model species
1,pan_troglodytes,GCF_028858775.1,GCF_028858775.1,SOURCE_DATABASE_REFSEQ,Chromosome,NHGRI_mPanTro3-v1.1-hic.freeze_pri,current,haploid,representative genome,2023-02-27,"National Human Genome Research Institute, National Institutes of Health",12,94528342,1319110838,40.5,1500,1500,3225356997,3222180001,Pan troglodytes,9598,model species
2,mus_musculus,GCF_000001635.27,GCF_000001635.27,SOURCE_DATABASE_REFSEQ,Chromosome,GRCm39,current,haploid,reference genome,2020-06-24,Genome Reference Consortium,15,59462871,1573609204,41.5,21254,305,2728206152,2654605538,Mus musculus,10090,model species
3,gallus_gallus,GCF_016699485.2,GCF_016699485.2,SOURCE_DATABASE_REFSEQ,Chromosome,bGalGal1.mat.broiler.GRCg7b,current,haploid,representative genome,2021-01-19,Vertebrate Genomes Project,18,18834961,443093403,42.0,676,676,1053315467,1049931549,Gallus gallus,9031,model species
4,danio_rerio,GCF_000002035.6,GCF_000002035.6,SOURCE_DATABASE_REFSEQ,Chromosome,GRCz11,current,haploid-with-alt-loci,reference genome,2017-05-09,Genome Reference Consortium,219,1422317,545845483,36.5,31634,19725,1373454788,1368765506,Danio rerio,7955,model species
5,drosophila_melanogaster,GCF_000001215.4,GCF_000001215.4,SOURCE_DATABASE_REFSEQ,Chromosome,Release 6 plus ISO1 MT,current,haploid,reference genome,2014-08-01,The FlyBase Consortium/Berkeley Drosophila Genome Project/Celera Genomics,3,21485538,59886014,42.0,1869,2441,143706478,142553500,Drosophila melanogaster,7227,model species
6,caenorhabditis_elegans,GCF_000002985.6,GCF_000002985.6,SOURCE_DATABASE_REFSEQ,Complete Genome,WBcel235,current,haploid,reference genome,2013-02-07,C. elegans Sequencing Consortium,3,17493829,36545374,35.0,3267,6,100272607,100272607,Caenorhabditis elegans,6239,model species
7,saccharomyces_cerevisiae,GCF_000146045.2,GCF_000146045.2,SOURCE_DATABASE_REFSEQ,Complete Genome,R64,current,haploid,reference genome,2014-12-17,Saccharomyces Genome Database,6,924431,4623000,38.0,16,16,12071326,12071326,Saccharomyces cerevisiae S288C,559292,model species
8,arabidopsis_thaliana,GCF_000001735.4,GCF_000001735.4,SOURCE_DATABASE_REFSEQ,Chromosome,TAIR10.1,current,haploid,reference genome,2018-03-15,The Arabidopsis Information Resource (TAIR),5,11194537,42859753,36.0,5,100,119146348,118960704,Arabidopsis thaliana,3702,model species
9,escherichia_coli,GCF_000008865.2,GCF_000008865.2,SOURCE_DATABASE_REFSEQ,Complete Genome,ASM886v2,current,haploid,reference genome,2018-06-08,GIRC,1,5498578,2824389,50.0,3,3,5594605,5594605,Escherichia coli O157:H7 str. Sakai,386585,model species
10,mandrillus_leucophaeus,GCF_000951045.1,GCF_000951045.1,SOURCE_DATABASE_REFSEQ,Scaffold,Mleu.le_1.0,current,haploid,representative genome,2015-03-12,Baylor College of Medicine,23470,31346,1108421426,40.5,246054,246054,3061992840,2721407539,Mandrillus leucophaeus,9568,for comparions with hs
11,ursus_americanus,GCF_020975775.1,GCF_020975775.1,SOURCE_DATABASE_REFSEQ,Contig,gsc_jax_bbear_1.0,current,haploid,representative genome,2021-11-24,Jackson Laboratory,43,13882922,990045675,42.0,2212,2212,2351947609,2351947609,Ursus americanus,9643,for comparions with hs
12,otolemur_garnettii,GCF_000181295.1,GCF_000181295.1,SOURCE_DATABASE_REFSEQ,Scaffold,OtoGar3,current,haploid,representative genome,2011-03-16,"Broad Institute of MIT and Harvard, USA, Cambridge",21634,27100,970092506,41.0,200240,200240,2519724550,2359530453,Otolemur garnettii,30611,for comparions with hs
13,ictidomys_tridecemlineatus,GCF_016881025.1,GCF_016881025.1,SOURCE_DATABASE_REFSEQ,Chromosome,HiC_Itri_2,current,haploid,representative genome,2021-02-17,Stanford University School of Medicine,14011,44127,922323740,39.5,7131,153543,2478949113,2311056943,Ictidomys tridecemlineatus,43179,for comparions with hs
14,tursiops_truncatus,GCF_011762595.1,GCF_011762595.1,SOURCE_DATABASE_REFSEQ,Chromosome,mTurTru1.mat.Y,current,haploid,representative genome,2020-03-27,Vertebrate Genomes Project,72,9729386,983049046,41.0,361,1035,2378505825,2372283309,Tursiops truncatus,9739,for comparions with hs
15,jaculus_jaculus,GCF_020740685.1,GCF_020740685.1,SOURCE_DATABASE_REFSEQ,Chromosome,mJacJac1.mat.Y.cur,current,haploid,representative genome,2021-11-04,Vertebrate Genomes Project,39,22104564,1197020115,41.5,159,715,2863848715,2850145970,Jaculus jaculus,51337,for comparions with hs
16,loxodonta_africana,GCF_000001905.1,GCF_000001905.1,SOURCE_DATABASE_REFSEQ,Scaffold,Loxafr3.0,current,haploid,representative genome,2009-07-15,Broad Institute,13607,69023,1271170210,40.5,95865,95865,3196721236,3118525743,Loxodonta africana,9785,for comparions with hs
17,cricetulus_griseus_chok1gshd,GCF_000223135.1,GCF_000223135.1,SOURCE_DATABASE_REFSEQ,Scaffold,CriGri_1.0,current,haploid,representative genome,2011-08-23,Beijing Genomics Institute,16413,39362,958940600,41.0,265786,265786,2399770464,2318115958,Cricetulus griseus,10029,for comparions with hs
18,latimeria_chalumnae,GCF_000225785.1,GCF_000225785.1,SOURCE_DATABASE_REFSEQ,Scaffold,LatCha1,current,haploid,representative genome,2011-09-12,Broad Institute,50768,12671,898562212,41.0,291828,291828,2860575514,2183576361,Latimeria chalumnae,7897,for comparions with hs
19,taeniopygia_guttata,GCF_003957565.2,GCF_003957565.2,SOURCE_DATABASE_REFSEQ,Chromosome,bTaeGut1.4.pri,current,haploid,representative genome,2021-05-04,Vertebrate Genomes Project,32,8964551,440667168,41.5,198,550,1056254409,1052619621,Taeniopygia guttata,59729,for comparions with hs
20,salmo_salar,GCF_905237065.1,GCF_905237065.1,SOURCE_DATABASE_REFSEQ,Chromosome,Ssal_v3.1,current,haploid,representative genome,2021-04-21,NORWEGIAN UNIVERSITY OF LIFE SCIENCES,33,28058890,1196906875,43.0,4222,4222,2756584103,2756563003,Salmo salar,8030,for comparions with hs
21,hucho_hucho,GCA_003317085.1,GCA_003317085.1,SOURCE_DATABASE_GENBANK,Scaffold,ASM331708v1,current,haploid,representative genome,2018-07-13,University Of Aberdeen,12736,37639,818035905,42.5,71639,221746,2487549814,1917049985,Hucho hucho,62062,for comparions with hs
22,amphiprion_percula,GCA_003047355.2,GCA_003047355.2,SOURCE_DATABASE_GENBANK,Chromosome,Nemo_v1.1,current,haploid,representative genome,2018-11-28,King Abdullah University of Science and Technology,84,3123421,359308998,39.5,365,1047,908939294,908906862,Amphiprion percula,161767,for comparions with hs
23,haplochromis_burtoni,GCF_018398535.1,GCF_018398535.1,SOURCE_DATABASE_REFSEQ,Scaffold,NCSU_Asbu1,current,haploid,representative genome,2021-05-19,"Reade Roberts Lab, North Carolina State University",4400,47717,309492643,40.5,7420,39826,854572272,760845823,Haplochromis burtoni,8153,for comparions with hs
24,ciona_savignyi,GCA_000149265.1,GCA_000149265.1,SOURCE_DATABASE_GENBANK,Scaffold,ASM14926v1,current,haploid,representative genome,2004-02-25,Broad Institute,6415,22563,226293806,36.5,66800,74923,587352817,557749356,Ciona savignyi,51511,for comparions with hs
25,carassius_auratus,GCF_003368295.1,GCF_003368295.1,SOURCE_DATABASE_REFSEQ,Chromosome,ASM336829v1,current,haploid,representative genome,2018-08-09,National Institutes of Health,513,821153,682311513,37.0,8462,8462,1820618472,1820393772,Carassius auratus,7957,for comparions with dr
26,sinocyclocheilus_grahami,GCF_001515645.1,GCF_001515645.1,SOURCE_DATABASE_REFSEQ,Scaffold,SAMN03320097.WGS_v1.1,current,haploid,representative genome,2015-12-16,"BGI, Shenzhen",15555,29354,588385207,37.5,168073,168073,1750271176,1567422664,Sinocyclocheilus grahami,75366,for comparions with dr
Loading

0 comments on commit daae5ed

Please sign in to comment.