diff --git a/misc-scripts/xref_mapping/sql/populate_metadata.sql b/misc-scripts/xref_mapping/sql/populate_metadata.sql index 997a6dbce91e9e49082257e6b8880f1e5ed91a92..abf197d11c22bd5f88fb7145749d731a5aea0f2b 100644 --- a/misc-scripts/xref_mapping/sql/populate_metadata.sql +++ b/misc-scripts/xref_mapping/sql/populate_metadata.sql @@ -22,6 +22,11 @@ INSERT INTO species (species_id, taxonomy_id, name, aliases) VALUES (8364, 8364, INSERT INTO species (species_id, taxonomy_id, name, aliases) VALUES (13616, 13616, 'monodelphis_domestica', 'opossum,monodelphis,mdomestica,monodelphisdomestica'); INSERT INTO species (species_id, taxonomy_id, name, aliases) VALUES (4932, 4932, 'saccharomyces_cerevisiae', 'yeast,saccharomyces,scerevisiae,saccharomycescerevisiae'); +INSERT INTO species (species_id, taxonomy_id, name, aliases) VALUES (7460, 7460, 'apis_mellifera', 'apismellifera,honeybee,amellifera'); + +INSERT INTO species (species_id, taxonomy_id, name, aliases) VALUES (7719, 7719, 'ciona_intestinalis', 'cionaintestinalis,cintestinalis,seasquirt'); + + ################################################################################ # SOURCES - types of data we can read @@ -309,6 +314,60 @@ INSERT INTO source_url (source_id, species_id, url, checksum, file_modified_date # -------------------------------------------------------------------------------- +#### HoneyBee + +## Uniprot +INSERT INTO source_url (source_id, species_id, url, checksum, file_modified_date, upload_date, parser) VALUES (1, 7460, 'ftp://ftp.ebi.ac.uk/pub/databases/uniprot/knowledgebase/uniprot_sprot.dat.gz', '', now(), now(), "UniProtParser"); + +INSERT INTO source_url (source_id, species_id, url, checksum, file_modified_date, upload_date, parser) VALUES (2, 7460, 'ftp://ftp.ebi.ac.uk/pub/databases/uniprot/knowledgebase/uniprot_trembl.dat.gz', '', now(), now(), "UniProtParser"); + +## refseq +INSERT INTO source_url (source_id, species_id, url, checksum, file_modified_date, upload_date, parser) VALUES (3, 7460,'ftp://ftp.ncbi.nih.gov/genomes/Apis_mellifera/protein/protein.gbk.gz', '', now(), now(), "RefSeqGPFFParser"); + +## refseq +INSERT INTO source_url (source_id, species_id, url, checksum, file_modified_date, upload_date, parser) VALUES (4, 7460,'ftp://ftp.ncbi.nih.gov/genomes/Apis_mellifera/RNA/rna.gbk.gz', '', now(), now(), "RefSeqGPFFParser"); + +## GO +INSERT INTO source_url (source_id, species_id, url, checksum, file_modified_date, upload_date, parser) VALUES (1070, 7460,'ftp://ftp.ebi.ac.uk/pub/databases/GO/goa/UNIPROT/gene_association.goa_uniprot.gz', '', now(), now(), "GOParser"); + +## Interpro +INSERT INTO source_url (source_id, species_id, url, checksum, file_modified_date, upload_date, parser) VALUES (1300, 7460,'ftp://ftp.ebi.ac.uk/pub/databases/interpro/interpro.xml.gz', '', now(), now(), "InterproParser"); + +## UniGene +INSERT INTO source_url (source_id, species_id, url, checksum, file_modified_date, upload_date, parser) VALUES (6, 7460,'ftp://ftp.ncbi.nih.gov/repository/UniGene/Ame.seq.uniq.gz ftp://ftp.ncbi.nih.gov/repository/UniGene/Ame.data.gz', '', now(), now(), "UniGeneParser"); + + + + +#### SeqSquirt + +## Uniprot +INSERT INTO source_url (source_id, species_id, url, checksum, file_modified_date, upload_date, parser) VALUES (1, 7719, 'ftp://ftp.ebi.ac.uk/pub/databases/uniprot/knowledgebase/uniprot_sprot.dat.gz', '', now(), now(), "UniProtParser"); + +INSERT INTO source_url (source_id, species_id, url, checksum, file_modified_date, upload_date, parser) VALUES (2, 7719, 'ftp://ftp.ebi.ac.uk/pub/databases/uniprot/knowledgebase/uniprot_trembl.dat.gz', '', now(), now(), "UniProtParser"); + +## refseq +INSERT INTO source_url (source_id, species_id, url, checksum, file_modified_date, upload_date, parser) VALUES (3, 7719,'ftp://ftp.ncbi.nih.gov/refseq/release/vertebrate_other/vertebrate_other1.protein.gpff.gz', '', now(), now(), "RefSeqGPFFParser"); + +INSERT INTO source_url (source_id, species_id, url, checksum, file_modified_date, upload_date, parser) VALUES (3, 7719,'ftp://ftp.ncbi.nih.gov/refseq/release/vertebrate_other/vertebrate_other2.protein.gpff.gz', '', now(), now(), "RefSeqGPFFParser"); + +INSERT INTO source_url (source_id, species_id, url, checksum, file_modified_date, upload_date, parser) VALUES (3, 7719,'ftp://ftp.ncbi.nih.gov/refseq/release/vertebrate_other/vertebrate_other3.protein.gpff.gz', '', now(), now(), "RefSeqGPFFParser"); + +INSERT INTO source_url (source_id, species_id, url, checksum, file_modified_date, upload_date, parser) VALUES (4, 7719,'ftp://ftp.ncbi.nih.gov/refseq/release/vertebrate_other/vertebrate_other1.rna.fna.gz', '', now(), now(), "RefSeqParser"); + +INSERT INTO source_url (source_id, species_id, url, checksum, file_modified_date, upload_date, parser) VALUES (4, 7719,'ftp://ftp.ncbi.nih.gov/refseq/release/vertebrate_other/vertebrate_other2.rna.fna.gz', '', now(), now(), "RefSeqParser"); + +INSERT INTO source_url (source_id, species_id, url, checksum, file_modified_date, upload_date, parser) VALUES (4, 7719,'ftp://ftp.ncbi.nih.gov/refseq/release/vertebrate_other/vertebrate_other3.rna.fna.gz', '', now(), now(), "RefSeqParser"); + +## GO +INSERT INTO source_url (source_id, species_id, url, checksum, file_modified_date, upload_date, parser) VALUES (1070, 7719,'ftp://ftp.ebi.ac.uk/pub/databases/GO/goa/UNIPROT/gene_association.goa_uniprot.gz', '', now(), now(), "GOParser"); + +## Interpro +INSERT INTO source_url (source_id, species_id, url, checksum, file_modified_date, upload_date, parser) VALUES (1300, 7719,'ftp://ftp.ebi.ac.uk/pub/databases/interpro/interpro.xml.gz', '', now(), now(), "InterproParser"); + +## UniGene +INSERT INTO source_url (source_id, species_id, url, checksum, file_modified_date, upload_date, parser) VALUES (6, 7719,'ftp://ftp.ncbi.nih.gov/repository/UniGene/Cin.seq.uniq.gz ftp://ftp.ncbi.nih.gov/repository/UniGene/Cin.data.gz', '', now(), now(), "UniGeneParser"); + ################################################################################