From 69c8e18c6e4f4adc39e1702f102913cf3e410b84 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Andreas=20Kusalananda=20K=C3=A4h=C3=A4ri?= <ak4@sanger.ac.uk> Date: Tue, 16 Nov 2010 14:04:54 +0000 Subject: [PATCH] Remove files no longer used. --- misc-scripts/external_db/README | 113 ------ .../external_db/convert_external_dbs.pl | 73 ---- misc-scripts/external_db/external_dbs.txt | 337 ------------------ .../load_additional_human_affy_xrefs.pl | 83 ----- .../load_additional_human_gkb_xrefs.pl | 88 ----- .../external_db/update_external_dbs.pl | 324 ----------------- 6 files changed, 1018 deletions(-) delete mode 100644 misc-scripts/external_db/README delete mode 100644 misc-scripts/external_db/convert_external_dbs.pl delete mode 100644 misc-scripts/external_db/external_dbs.txt delete mode 100644 misc-scripts/external_db/load_additional_human_affy_xrefs.pl delete mode 100644 misc-scripts/external_db/load_additional_human_gkb_xrefs.pl delete mode 100644 misc-scripts/external_db/update_external_dbs.pl diff --git a/misc-scripts/external_db/README b/misc-scripts/external_db/README deleted file mode 100644 index 37a5f0ff55..0000000000 --- a/misc-scripts/external_db/README +++ /dev/null @@ -1,113 +0,0 @@ -EXTERNAL_DB UPDATES -=================== - - -DESCRIPTION ------------ - -The external_db table contains a list of all external databases which are -referenced by ensembl. Specifically this table is used by the xref table -which contains lists of external database identifiers. - -Foremerly all EnsEMBL core databases had their own external_db tables -and used an enumeration of db_names. This was difficult to maintain and -required schema updates every release. The new system requires that -every ensembl database contains the exact same external_db table, which -ensures consistancy across all databases and makes it easier to test. - -MASTER EXTERNAL_DB LIST ------------------------ - -The master list of external databases is stored in the file: - -${ENSEMBL_HOME}/ensembl/misc-scripts/external_db/external_dbs.txt - -This file contains a tab-seperated list of values which are loaded into -the external_db tables. In order the columns are: - 'external_db_id', 'db_name', 'release', 'status', -'db_primary_acc_linkable', 'display_label_linkable', 'priority', -'db_display_name', 'type', 'secondary_db_name', 'secondary_db_table', -'description' - -- external_db_id -- internal identifier for this entry, primary key -- release -- is currently not used by the software and is always set to 1 -- status -- must be one of 'KNOWNXREF','KNOWN', 'XREF', 'PRED', 'ORTH', 'PSEUDO'. -This is used by the webcode to determine which genes/transcripts can be considered -to be known or unknown etc. -- dbprimary_acc_linkable -- used by the webcode to indicate if the linkable -element is the internal name in the database (e.g. HGNC_curated_gene) -- display_label_linkable -- used by the webcode to indicate if the linkable -element is the name of the database (e.g. WikiGene ) -- priority -- used for the website to indicate priority of display in page -( the higher the number, the closer to the top of the page) -- db_display_name -- name to be displayed in the website might be different -to name of database (e.g. HGNC Symbol rather than HGNC) -- type -- indicates kind of information the xref database offers (e.g. ALT_GENE -is used in OTTG to indicate that this external database produces alternative gene from Vega) -- secondary_db_name -- not used at the moment (requested by functional genomics team) -- secondary_db_table -- not used at the moment (requested by functiona genomics team) -- description -- free column to describe the external database - -... -12300 HGNC_curated_gene 1 KNOWNXREF 1 0 5 HGNC (curated) MISC \N \N -12305 HGNC_automatic_gene 1 KNOWNXREF 1 0 5 HGNC (automatic) MISC \N \N -12310 Clone_based_vega_gene 1 KNOWNXREF 1 0 5 Clone-based (Vega) MISC \N \N -12315 Clone_based_ensembl_gene 1 XREF 1 0 5 Clone-based (Ensembl) MISC \N \N -12400 HGNC_curated_transcript 1 KNOWNXREF 1 0 5 HGNC (curated) MISC \N \N -... - - -UPDATE PROCEDURE ----------------- - -The following describes the steps necessary to update the external_db table - - -(1) Add new external database(s) if the appropriate database(s) are not in the -master list: - (a) Add a row to the external_dbs.txt file. The columns must be tab - seperated and the external_db identifier must be unique. The - db_release should be set to 1 and the status should reflect the - how xrefs from this external database are used by web. - - For example a new external_db 'Celera_gene' could be added as the - following: - - 400 Celera_Gene 1 PRED 1 0 5 Celera gene MISC \N \N - - (b) Commit the external_dbs.txt file using cvs commit. This is to - ensure that nobody else who may also be updating the file will use - the same identifier that you chose (in the example ID 400). - - - - -(2) Propagate the contents of the file to all of the core style databases -(core|cdna|vega|otherfeatures). To update all of the core style databases -for release 56: - -perl update_external_dbs.pl -host ens-staging -file external_dbs.txt \ - -user ensadmin -pass secret -release 56 - -To update the human core database: - -perl update_external_dbs.pl -host ens-staging -file external_dbs.txt \ - -user ensadmin -pass secret -dbnames homo_sapiens_core_56_37a - -Upon executing the script it will display a list of dbs that the updates -will be applied and you will have to type 'yes' at a confirmation. - -If the databases to be updated contain rows that are not in the file, -a warning will be given and the database in question skipped. - -The flag -nonreleasemode it is used when we we want to load the master -database (use in combination with -master): e.g. we want to create a new -database with all the external_db from the file - -The flag -force is used to update the databases even there is a difference -between the master file and the databases. This should only be used when -we are sure the data in the database is wrong/not necessary and we want to -overwrite it with the information in the external_db.txt file. - -In Ensembl, the release coordinator is responsible for running this script -during the release process. diff --git a/misc-scripts/external_db/convert_external_dbs.pl b/misc-scripts/external_db/convert_external_dbs.pl deleted file mode 100644 index 89660e7997..0000000000 --- a/misc-scripts/external_db/convert_external_dbs.pl +++ /dev/null @@ -1,73 +0,0 @@ -use strict; -use warnings; -use DBI; - -my $user = 'ecs2dadmin'; -my $host = 'ecs2d'; -my $pass = 'TyhRv'; -my $dbname = shift; - -my $dbh = DBI->connect("DBI:mysql:host=$host;dbname=$dbname;", $user, $pass, - {RaiseError => 1}); - -# -# Store the old external_db table in a hash -# -my $sth = $dbh->prepare('SELECT external_db_id, db_name - FROM external_db'); - -print STDERR "READING OLD EXTERNAL DB\n"; -$sth->execute(); -my %old_ext_db = map {$_->[0], $_->[1]} @{$sth->fetchall_arrayref}; -$sth->finish(); - - -# -# drop the existing external_db table and replace it with the new table -# -print STDERR "REPLACING OLD EXTERNAL DB\n"; - -`cat external_db.sql | mysql -h $host -u $user -p$pass $dbname`; - -# -# Store the new external_db table in a hash -# -print STDERR "READING NEW EXTERNAL DB\n"; -$sth->execute(); -my %new_ext_db = map {$_->[1], $_->[0]} @{$sth->fetchall_arrayref}; -$sth->finish(); - -# -# update each row in the xref table -# -print STDERR "UPDATING XREF TABLE\n"; -$sth = $dbh->prepare('SELECT external_db_id, xref_id FROM xref'); -my($external_db_id, $xref_id); -$sth->execute(); -$sth->bind_columns(\$external_db_id, \$xref_id); - -my $update_sth = - $dbh->prepare('UPDATE xref SET external_db_id = ? WHERE xref_id = ?'); - -my $count = 0; - -while($sth->fetch()) { - my $dbname = $old_ext_db{$external_db_id}; - my $id = $new_ext_db{$dbname}; - if($id) { - $update_sth->execute($id, $xref_id); - $count++; - if($count % 1_000 == 0) { - print STDERR '.'; - } - } else { - warn("Could not convert ext_id=[$external_db_id] dbname=[$dbname]\n"); - } -} - -$sth->finish(); - -$dbh->disconnect(); - -print STDERR "COMPLETE. Converted $count xrefs.\n"; - diff --git a/misc-scripts/external_db/external_dbs.txt b/misc-scripts/external_db/external_dbs.txt deleted file mode 100644 index 85fa39b350..0000000000 --- a/misc-scripts/external_db/external_dbs.txt +++ /dev/null @@ -1,337 +0,0 @@ -210 Anopheles_symbol NULL KNOWN 1 0 50 Anopheles symbol MISC NULL NULL NULL -211 VB_Community_Symbol NULL KNOWN 1 0 50 VB Community Symbol MISC NULL NULL NULL -300 BRIGGSAE_HYBRID NULL KNOWNXREF 1 0 5 Briggsae Hybrid MISC NULL NULL NULL -400 Celera_Gene NULL PRED 1 0 5 Celera gene MISC NULL NULL NULL -410 Celera_Pep NULL PRED 1 0 5 Celera peptide MISC NULL NULL NULL -420 Celera_Trans NULL PRED 1 0 5 Celera transcript MISC NULL NULL NULL -600 DROS_ORTH NULL ORTH 1 0 5 DROS ORTH MISC NULL NULL NULL -700 EMBL NULL KNOWNXREF 1 0 5 European Nucleotide Archive (was EMBL) MISC NULL NULL NULL -701 EMBL_predicted NULL PRED 1 0 4 Predicted European Nucleotide Archive (was EMBL) MISC NULL NULL NULL -800 flybase_gene_id NULL KNOWNXREF 1 0 5 Flybase Gene MISC NULL NULL NULL -801 flybase_translation_id NULL KNOWNXREF 1 0 5 Flybase translation ID MISC NULL NULL NULL -802 flybase_gff NULL KNOWNXREF 1 0 5 Flybase GFF MISC NULL NULL NULL -803 flybase_polypeptide_id NULL KNOWNXREF 1 0 5 Flybase Polypeptide ID MISC NULL NULL NULL -804 flybase_annotation_id NULL KNOWNXREF 1 0 5 Flybase Annotation ID MISC NULL NULL NULL -805 flybase_symbol NULL KNOWNXREF 1 0 50 Flybase Symbol MISC NULL NULL NULL -806 flybase_synonym NULL KNOWNXREF 1 0 5 Flybase Synonym MISC NULL NULL NULL -807 flybase_name NULL KNOWNXREF 1 0 5 Flybase Name MISC NULL NULL NULL -808 flybase_transcript_id NULL KNOWNXREF 1 0 5 Flybase transcript ID MISC NULL NULL NULL -810 gadfly_gene_cgid NULL XREF 1 0 10 Gadfly gene CGID MISC NULL NULL NULL -811 gadfly_transcript_cgid NULL XREF 1 0 10 Gadfly transcript CGID MISC NULL NULL NULL -812 gadfly_translation_cgid NULL XREF 1 0 10 Gadfly translation CGID MISC NULL NULL NULL -821 FlyBaseName_gene NULL KNOWN 1 0 5 FlyBaseName gene MISC NULL NULL NULL -824 FlyBaseName_translation NULL KNOWN 1 0 5 FlyBaseName translation MISC NULL NULL NULL -825 FlyBaseName_transcript NULL XREF 1 0 50 FlyBaseName transcript MISC NULL NULL NULL -826 FlyBaseCGID_gene NULL XREF 1 0 5 FlyBaseCGID gene MISC NULL NULL NULL -827 FlyBaseCGID_transcript NULL XREF 1 0 50 FlyBaseCGID transcript MISC NULL NULL NULL -828 FlyBaseCGID_translation NULL XREF 1 0 50 FlyBaseCGID translation MISC NULL NULL NULL -880 BDGP_insitu_expr NULL KNOWNXREF 1 0 5 Berkeley Drosophila Genome Project in situ Gene Expression Database (embryogenesis) MISC NULL NULL NULL -882 FlyGrid NULL KNOWNXREF 1 0 5 FlyGRID Interaction Data, The General Repository for Interaction Datasets MISC NULL NULL NULL -883 FlyReactome NULL KNOWNXREF 1 0 5 FlyReactome, a Curated Knowledgebase of Drosophila Melanogaster Pathways MISC NULL NULL NULL -890 DEDb NULL KNOWNXREF 1 0 5 Drosophila melanogaster Exon Database MISC NULL NULL NULL -900 GKB NULL XREF 1 0 5 GKB MISC NULL NULL NULL -1000 GO NULL XREF 1 0 5 GO MISC NULL NULL NULL -250 ImmunoDB 1 KNOWN 1 0 50 ImmunoDB MISC NULL NULL NULL -1100 HGNC NULL KNOWNXREF 1 1 100 HGNC Symbol PRIMARY_DB_SYNONYM NULL NULL NULL -1200 Interpro NULL XREF 1 0 5 InterPro MISC NULL NULL NULL -1300 EntrezGene NULL KNOWNXREF 1 0 10 EntrezGene MISC NULL NULL NULL -1400 MGI NULL KNOWNXREF 1 1 50 MGI Symbol MISC NULL NULL NULL -1500 MIM NULL KNOWNXREF 1 0 5 MIM MISC NULL NULL NULL -1510 MIM_GENE NULL KNOWNXREF 1 0 5 MIM gene MISC NULL NULL NULL -1520 MIM_MORBID NULL KNOWNXREF 1 0 5 MIM disease MISC NULL NULL NULL -1600 PDB NULL KNOWNXREF 1 0 5 PDB MISC NULL NULL NULL -1700 protein_id NULL KNOWNXREF 1 0 5 Protein ID MISC NULL NULL NULL -1701 protein_id_predicted NULL PRED 1 0 4 Predicted Protein ID MISC NULL NULL NULL -1800 RefSeq_dna NULL KNOWN 1 0 25 RefSeq DNA MISC NULL NULL NULL -214 VB_Community_Annotation 1 KNOWN 1 0 50 VB Community Annotation MISC NULL NULL NULL -1805 RefSeq_dna_predicted NULL PRED 1 0 15 RefSeq DNA predicted MISC NULL NULL NULL -1810 RefSeq_peptide NULL KNOWN 1 0 26 RefSeq peptide MISC NULL NULL NULL -213 VB_RNA_Description 1 PRED 1 0 50 VB RNA Description MISC NULL NULL NULL -1815 RefSeq_peptide_predicted NULL PRED 1 0 16 RefSeq peptide predicted MISC NULL NULL NULL -1820 RefSeq_rna NULL KNOWN 1 0 24 RefSeq RNA MISC NULL NULL NULL -1825 RefSeq_rna_predicted NULL PRED 1 0 14 RefSeq RNA predicted MISC NULL NULL NULL -1830 RefSeq_genomic NULL KNOWN 1 0 23 RefSeq Genomic MISC NULL NULL NULL -1900 Sanger_Hver1_2_1 NULL XREF 1 0 5 Sanger Hver 121 MISC NULL NULL NULL -1901 Sanger_Hver1_3_1 NULL XREF 1 0 5 Sanger Hver 131 MISC NULL NULL NULL -1902 SNGR_Hver NULL XREF 1 0 5 Sanger Hver MISC NULL NULL NULL -1910 Sanger_Mver1_1_1 NULL XREF 1 0 5 Sanger Hver 111 MISC NULL NULL NULL -2000 Uniprot/SPTREMBL NULL KNOWN 1 0 20 UniProtKB/TrEMBL MISC NULL NULL NULL -2001 Uniprot/SPTREMBL_predicted NULL PRED 1 0 15 Predicted UniProtKB/TrEMBL MISC NULL NULL NULL -2010 prediction_SPTREMBL NULL XREF 1 1 10 Prediction UniProtKB/TrEMBL MISC NULL NULL NULL -2100 Superfamily NULL KNOWNXREF 1 0 5 Superfamily MISC NULL NULL NULL -2200 Uniprot/SWISSPROT NULL KNOWN 1 1 30 UniProtKB/Swiss-Prot MISC NULL NULL NULL -2201 Uniprot/SWISSPROT_predicted NULL PRED 1 1 15 Predicted UniProtKB/Swiss-Prot MISC NULL NULL NULL -2202 Uniprot/Varsplic NULL KNOWN 1 1 15 UniprotKB/SpliceVariant MISC NULL NULL NULL -2250 UniProtKB_all NULL XREF 1 0 40 UniProtKB generic accession number (TrEMBL or SwissProt not differentiated) MISC NULL NULL NULL -2300 Vega_gene NULL KNOWNXREF 1 0 5 Vega gene MISC NULL NULL NULL -2305 Vega_gene_like NULL XREF 1 0 5 Vega gene like MISC NULL NULL NULL -2310 Vega_transcript NULL KNOWNXREF 1 0 5 Vega transcript MISC NULL NULL NULL -2315 Vega_transcript_like NULL XREF 1 0 5 Vega transcript like MISC NULL NULL NULL -2320 Vega_translation NULL KNOWNXREF 1 0 5 Vega translation MISC NULL NULL NULL -2400 wormbase_gene NULL KNOWN 1 0 5 Wormbase Gene MISC NULL NULL NULL -2410 wormbase_transcript NULL KNOWN 1 0 5 Wormbase Transcript MISC NULL NULL NULL -2420 wormpep_id NULL KNOWN 1 0 5 Wormpep ID MISC NULL NULL NULL -2430 wormbase_pseudogene NULL PSEUDO 1 0 5 Wormbase Pseudogene MISC NULL NULL NULL -2440 wormbase_locus NULL KNOWN 1 0 5 Wormbase Locus MISC NULL NULL NULL -2510 ZFIN_ID NULL KNOWNXREF 1 1 5 ZFIN PRIMARY_DB_SYNONYM NULL NULL NULL -2530 ZFIN_xpat NULL KNOWNXREF 1 0 4 ZFIN expression patterns MISC NULL NULL NULL -2600 GeneDB NULL KNOWN 1 0 5 GeneDB MISC NULL NULL NULL -2601 cint_jgi_v1 NULL KNOWN 1 0 10 JGI Gene ID (JGI 1.0) MISC NULL NULL NULL -2602 cint_jgi_v2 NULL KNOWN 1 0 5 JGI Gene ID (JGI 2.0) MISC NULL NULL NULL -2610 cint_aniseed_v1 NULL KNOWN 1 0 5 ANISEED (JGI 1.0) MISC NULL NULL NULL -2611 cint_aniseed_v2 NULL KNOWN 1 0 5 ANISEED (JGI 2.0) MISC NULL NULL NULL -2700 Ens_Hs_gene NULL XREF 1 0 5 Ensembl Human Gene MISC NULL NULL NULL -2710 Ens_Hs_transcript NULL XREF 1 0 5 Ensembl Human Transcript MISC NULL NULL NULL -2720 Ens_Hs_translation NULL XREF 1 0 5 Ensembl Human Translation MISC NULL NULL NULL -2800 RGD NULL KNOWNXREF 1 1 50 RGD Symbol MISC NULL NULL NULL -2900 Genoscope_pred_gene NULL XREF 1 0 38 Genoscope pred gene MISC NULL NULL NULL -2910 Genoscope_pred_transcript NULL XREF 1 0 39 Genoscope pred transcript MISC NULL NULL NULL -2920 Genoscope_annotated_gene NULL KNOWN 1 0 40 Genoscope annotated gene MISC NULL NULL NULL -2930 Genoscope_pred_translation NULL XREF 1 0 40 Genoscope pred translation MISC NULL NULL NULL -2940 Genoscope_ann_transcript NULL KNOWN 1 0 40 Genoscope annotated transcript MISC NULL NULL NULL -2950 Genoscope_ann_translation NULL KNOWN 1 0 40 Genoscope annotated translation MISC NULL NULL NULL -3300 miRBase NULL KNOWNXREF 1 0 1 miRBase MISC NULL NULL NULL -3310 miRBase_predicted NULL XREF 1 0 1 miRBase predicted MISC NULL NULL NULL -3400 SGD NULL KNOWN 1 1 50 SGD MISC NULL NULL NULL -3500 IPI NULL KNOWN 1 0 5 IPI MISC NULL NULL NULL -3800 CCDS NULL KNOWN 1 0 50 CCDS MISC NULL NULL NULL -3900 PUBMED NULL KNOWN 1 0 5 Sequence Publications LIT NULL NULL NULL -4000 MEDLINE NULL KNOWN 1 0 5 MEDLINE LIT NULL NULL NULL -4100 UniGene NULL KNOWN 1 0 5 UniGene MISC NULL NULL NULL -212 VB_External_Description 1 PRED 1 0 50 VB External Description MISC NULL NULL NULL -4200 RFAM NULL XREF 1 0 5 RFAM MISC NULL NULL NULL -4400 Xenopus_Jamboree NULL KNOWN 1 0 1 Jamboree MISC NULL NULL NULL -4500 Tiffin NULL XREF 1 0 1 Tiffin DNA motifs MISC NULL NULL NULL -4600 OTTG NULL XREF 1 0 1 Havana gene ALT_GENE NULL NULL NULL -4610 OTTT NULL XREF 1 0 1 Havana transcript ALT_TRANS NULL NULL NULL -4620 OTTP NULL XREF 1 0 1 Havana translation MISC NULL NULL NULL -4650 shares_CDS_with NULL XREF 1 0 1 transcript having same CDS ALT_TRANS NULL NULL NULL -4660 shares_CDS_with_ENST NULL XREF 1 0 1 Imported HAVANA transcripts (Shares CDS with ENST) ALT_TRANS NULL NULL NULL -4670 shares_CDS_with_OTTT NULL XREF 1 0 1 Havana transcript having same CDS ALT_TRANS NULL NULL NULL -4680 shares_CDS_and_UTR_with_OTTT NULL XREF 1 0 1 Transcript having exact match between ENSEMBL and HAVANA ALT_TRANS NULL NULL NULL -4690 ENSG NULL XREF 1 0 1 Ensembl gene ALT_GENE NULL NULL NULL -4700 Medaka NULL XREF 1 0 1 Medaka Genome Project MISC NULL NULL NULL -4800 ENST NULL XREF 1 0 1 Ensembl transcript having exact match with Havana ALT_TRANS NULL NULL NULL -4810 ENST_ident NULL XREF 1 0 1 Ensembl transcript having exact match with Havana ALT_TRANS NULL NULL NULL -4820 ENST_CDS NULL XREF 1 0 1 Ensembl transcript sharing CDS with Havana ALT_TRANS NULL NULL NULL -4900 TCAG NULL KNOWN 1 0 75 TCAG Chr 7 Annotation MISC NULL NULL NULL -5000 Ens_Mm_gene NULL XREF 1 0 40 Ensembl Mouse Gene MISC NULL NULL NULL -5010 Ens_Mm_transcript NULL XREF 1 0 40 Ensembl Mouse Transcript MISC NULL NULL NULL -5020 Ens_Mm_translation NULL XREF 1 0 40 Ensembl Mouse Translation MISC NULL NULL NULL -5100 IMGT_HLA NULL KNOWN 1 0 7 IMGT/HLA MISC NULL NULL NULL -5200 Oxford_FGU_Md_gene NULL PRED 1 0 1 Oxford Ponting Group Monodelphis predictions gene id ALT_TRANS NULL NULL NULL -5300 Oxford_FGU_Md_tscript NULL PRED 1 0 1 Oxford Ponting Group Monodelphis predictions transcript id ALT_TRANS NULL NULL NULL -5400 Oxford_FGU_Oa_gene NULL PRED 1 0 1 Oxford Ponting Group Platypus predictions gene id ALT_TRANS NULL NULL NULL -5500 Oxford_FGU_Oa_tscript NULL PRED 1 0 1 Oxford Ponting Group Platypus predictions transcript id ALT_TRANS NULL NULL NULL -5700 Ens_Cf_gene NULL XREF 1 0 5 Ensembl Dog Gene MISC NULL NULL NULL -5710 Ens_Cf_transcript NULL XREF 1 0 5 Ensembl Dog Transcript MISC NULL NULL NULL -5720 Ens_Cf_translation NULL XREF 1 0 5 Ensembl Dog Translation MISC NULL NULL NULL -5800 Ens_Dr_gene NULL XREF 1 0 5 Ensembl Zebrafish Gene MISC NULL NULL NULL -5810 Ens_Dr_transcript NULL XREF 1 0 5 Ensembl Zebrafish Transcript MISC NULL NULL NULL -5820 Ens_Dr_translation NULL XREF 1 0 5 Ensembl Zebrafish Translation MISC NULL NULL NULL -5900 Ens_Md_gene NULL XREF 1 0 5 Ensembl Monodelphis Gene MISC NULL NULL NULL -6100 Havana_gene NULL XREF 1 0 100 Havana gene ID MISC NULL NULL NULL -6200 Ens_Rn_gene NULL XREF 1 0 5 Ensembl Rat Gene MISC NULL NULL NULL -6300 Ens_Ol_gene NULL XREF 1 0 5 Ensembl Medaka Gene MISC NULL NULL NULL -6400 Ens_Gg_gene NULL XREF 1 0 40 Ensembl Chicken Gene MISC NULL NULL NULL -6410 Ens_Gg_transcript NULL XREF 1 0 40 Ensembl Chicken Transcript MISC NULL NULL NULL -6420 Ens_Gg_translation NULL XREF 1 0 40 Ensembl Chicken Translation MISC NULL NULL NULL -6500 IMCB_Tr_gene NULL XREF 1 0 40 IMCB Fugu Gene MISC NULL NULL NULL -6600 Ens_Ag_gene NULL XREF 1 0 5 Ensembl Mosquito Gene MISC NULL NULL NULL -6630 Ens_Am_gene NULL XREF 1 0 5 Ensembl Bee Gene MISC NULL NULL NULL -6660 Ens_Ce_gene NULL XREF 1 0 5 Ensembl Worm Gene MISC NULL NULL NULL -6690 Ens_Dm_gene NULL XREF 1 0 5 Ensembl FruitFly Gene MISC NULL NULL NULL -6720 Ens_Fr_gene NULL XREF 1 0 5 Ensembl Fugu Gene MISC NULL NULL NULL -6750 Ens_Pt_gene NULL XREF 1 0 5 Ensembl Chimpanzee Gene MISC NULL NULL NULL -6780 Ens_Rn_gene NULL XREF 1 0 5 Ensembl Rat Gene MISC NULL NULL NULL -6810 Ens_Tn_gene NULL XREF 1 0 5 Ensembl PufferFish Gene MISC NULL NULL NULL -6820 Ens_Tr_transcript NULL XREF 1 0 40 Ensembl Fugu Transcript MISC NULL NULL NULL -7120 Ens_Aa_translation NULL XREF 1 0 40 Ensembl Aedes Translation MISC NULL NULL NULL -7159 AedesGenBank NULL PRED 1 0 30 Aedes GenBank MISC NULL NULL NULL -7160 Aedes_ManualAnnotation NULL PRED 1 0 30 Aedes ManualAnnotation MISC NULL NULL NULL -7170 Ixodes_ManualAnnotation NULL PRED 1 0 30 Ixodes ManualAnnotation MISC NULL NULL NULL -7200 IMGT/LIGM_DB NULL XREF 1 1 10 IMGT/LIGM-DB MISC NULL NULL NULL -7201 IMGT/GENE_DB NULL KNOWN 1 0 40 IMGT/GENE-DB MISC NULL NULL NULL -8000 Vega_mouse_transcript NULL XREF 1 0 5 Vega mouse transcript MISC NULL NULL NULL -8100 Platypus_olfactory_receptor NULL XREF 1 0 40 Platypus olfactory receptor gene MISC NULL NULL NULL -8200 PRF NULL XREF 1 0 5 PRF MISC NULL NULL NULL -8300 PIR NULL XREF 1 0 5 PIR MISC NULL NULL NULL -8400 TetNig_cdna NULL XREF 1 0 40 Genoscope tetraodon cDNA MISC NULL NULL NULL -8500 GasAcu_cdna NULL XREF 1 0 40 Stickleback cDNA MISC NULL NULL NULL -8600 OrnAna_454_cdna NULL XREF 1 0 40 Platypus 454 cDNA MISC NULL NULL NULL -8700 TakRub_cdna NULL XREF 1 0 40 Takifugu cDNA MISC NULL NULL NULL -8800 CioInt_est NULL XREF 1 0 40 Ciona intestinalis EST MISC NULL NULL NULL -8900 CioInt_cdna NULL XREF 1 0 40 Ciona intestinalis cDNA MISC NULL NULL NULL -9000 CaeEle_est NULL XREF 1 0 40 C Elegans EST MISC NULL NULL NULL -9100 XenTro_Gurdon_EST NULL XREF 1 0 40 Xenopus Gurdon EST Clusters MISC NULL NULL NULL -9110 XenTro_cdna NULL XREF 1 0 40 Xenopus Tropicalis cDNA MISC NULL NULL NULL -9120 XenLae_cdna NULL XREF 1 0 40 Xenopus Laevis cDNA MISC NULL NULL NULL -9200 TakRub_est NULL XREF 1 0 40 Takifugu EST MISC NULL NULL NULL -9210 TakRub_annotation NULL XREF 1 0 40 Takifugu gene annotation MISC NULL NULL NULL -9220 TakRub_seleno_annotation NULL XREF 1 0 40 Takifugu selenoprotein annotation MISC NULL NULL NULL -9400 TetNig_mouse_econtig NULL XREF 1 0 40 Genoscope mouse exofish econtig MISC NULL NULL NULL -9410 TetNig_fugu_econtig NULL XREF 1 0 40 Genoscope fugu exofish econtig MISC NULL NULL NULL -9420 TetNig_human_econtig NULL XREF 1 0 40 Genoscope human exofish econtig MISC NULL NULL NULL -9430 TetNig_human_IPI_econtig NULL XREF 1 0 40 Genoscope human IPI exofish econtig MISC NULL NULL NULL -9440 TetNig_mouse_IPI_econtig NULL XREF 1 0 40 Genoscope mouse IPI exofish econtig MISC NULL NULL NULL -9450 TetNig_rat_econtig NULL XREF 1 0 40 Genoscope rat exofish econtig MISC NULL NULL NULL -9460 TetNig_chick_econtig NULL XREF 1 0 40 Genoscope chicken exofish econtig MISC NULL NULL NULL -9500 OryLat_est NULL XREF 1 0 40 Medaka EST MISC NULL NULL NULL -9600 Trace_archive NULL XREF 1 0 40 Trace Archive id MISC NULL NULL NULL -9700 CioSav_est NULL XREF 1 0 40 Ciona savignyi EST MISC NULL NULL NULL -9800 kyotograil_2004 NULL PRED 1 0 30 Ciona intestinalis Kyotograil 2004 predictions MISC NULL NULL NULL -9900 kyotograil_2005 NULL PRED 1 0 30 Ciona intestinalis Kyotograil 2005 predictions MISC NULL NULL NULL -10000 wormbase_id NULL XREF 1 0 30 Generic exdb for worbase id of any type for feature table MISC NULL NULL NULL -10100 EPD NULL KNOWNXREF 1 0 5 Eukaryotic Promoter Database (Bucher) MISC NULL NULL NULL -10200 GPCR NULL KNOWNXREF 1 0 5 The G protein-coupled receptor database MISC NULL NULL NULL -10300 MEROPS NULL KNOWNXREF 1 0 5 MEROPS - the Peptidase Database MISC NULL NULL NULL -10500 TransFac NULL KNOWNXREF 1 0 5 TransFac, database of transcription factors and their binding sites MISC NULL NULL NULL -10600 modCB_gene NULL KNOWNXREF 1 0 5 Caenorhabditis briggsae, InParanoid model organism database MISC NULL NULL NULL -10700 modCE_gene NULL KNOWNXREF 1 0 5 Caenorhabditis elegans, InParanoid model organism database MISC NULL NULL NULL -10800 modDD_gene NULL KNOWNXREF 1 0 5 Dictyostelium discoideum, InParanoid model organism database MISC NULL NULL NULL -10900 GI NULL XREF 1 0 5 GenInfo Identifier, a sequence identification number for a nucleotide sequence MISC NULL NULL NULL -11000 UCSC NULL KNOWNXREF 1 0 100 UCSC Stable ID MISC NULL NULL NULL -11100 Culex_ncRNA NULL XREF 1 0 70 Culex ncRNAs MISC NULL NULL NULL -12300 HGNC_curated_gene NULL KNOWNXREF 1 0 5 HGNC (curated) MISC NULL NULL NULL -12305 HGNC_automatic_gene NULL KNOWNXREF 1 0 5 HGNC (automatic) MISC NULL NULL NULL -12310 Clone_based_vega_gene NULL KNOWNXREF 1 0 5 Clone-based (Vega) MISC NULL NULL NULL -12315 Clone_based_ensembl_gene NULL XREF 1 0 5 Clone-based (Ensembl) MISC NULL NULL NULL -12400 HGNC_curated_transcript NULL KNOWNXREF 1 0 5 HGNC (curated) MISC NULL NULL NULL -12405 HGNC_automatic_transcript NULL KNOWNXREF 1 0 5 HGNC (automatic) MISC NULL NULL NULL -12410 Clone_based_vega_transcript NULL KNOWNXREF 1 0 5 Clone-based (Vega) MISC NULL NULL NULL -12415 Clone_based_ensembl_transcript NULL XREF 1 0 5 Clone-based (Ensembl) MISC NULL NULL NULL -12500 DBASS3 NULL XREF 1 0 50 DataBase of Aberrant 3' Splice Sites MISC NULL NULL NULL -12505 DBASS5 NULL XREF 1 0 50 DataBase of Aberrant 5' Splice Sites MISC NULL NULL NULL -12510 HPA NULL XREF 1 0 50 Human Protein Atlas MISC NULL NULL NULL -12550 MGI_curated_gene NULL KNOWNXREF 1 0 5 MGI (curated) MISC NULL NULL NULL -12555 MGI_automatic_gene NULL KNOWNXREF 1 0 5 MGI (automatic) MISC NULL NULL NULL -12560 MGI_curated_transcript NULL KNOWNXREF 1 0 5 MGI (curated) MISC NULL NULL NULL -12565 MGI_automatic_transcript NULL KNOWNXREF 1 0 5 MGI (automatic) MISC NULL NULL NULL -12600 WikiGene NULL XREF 0 1 50 WikiGene MISC NULL NULL NULL -12601 Tgut_symbol NULL KNOWNXREF 0 0 100 Tgut symbol - Prof. David Burt, Roslin Institute and Royal (Dick) School of Veterinary Studies, Edinburgh University, UK PRIMARY_DB_SYNONYM NULL NULL NULL -12610 Fantom NULL XREF 0 1 50 Fantom MISC NULL NULL NULL -12620 Duck_consortium NULL XREF 0 0 0 Duck consortium MISC NULL NULL NULL -12630 BGI_duck_transcriptome NULL XREF 0 0 0 Beijing Genomics Institute (BGI) duck transcriptome MISC NULL NULL NULL -12700 goslim_goa NULL XREF 1 0 5 GOSlim GOA MISC NULL NULL NULL -12710 WTSI_gorilla_transcriptome NULL XREF 0 0 0 Wellcome Trust Sanger Institute (WTSI) gorilla transcriptome MISC NULL NULL NULL -12720 WTSI_zebrafish_transcriptome NULL XREF 0 0 0 Wellcome Trust Sanger Institute (WTSI) zebrafish transcriptome MISC NULL NULL NULL -20005 UniParc NULL KNOWNXREF 1 0 0 UniParc PRIMARY_DB_SYNONYM NULL NULL NULL -20008 BRENDA NULL KNOWNXREF 1 0 0 BRENDA PRIMARY_DB_SYNONYM NULL NULL NULL -20009 BioCyc NULL KNOWNXREF 1 0 0 BioCyc PRIMARY_DB_SYNONYM NULL NULL NULL -20010 BuruList NULL KNOWNXREF 1 0 0 BuruList PRIMARY_DB_SYNONYM NULL NULL NULL -20013 EchoBASE NULL KNOWNXREF 1 0 0 EchoBASE PRIMARY_DB_SYNONYM NULL NULL NULL -20014 EcoGene NULL KNOWNXREF 1 0 0 EcoGene PRIMARY_DB_SYNONYM NULL NULL NULL -20017 GeneDB_Spombe NULL KNOWNXREF 1 0 0 GeneDB_Spombe PRIMARY_DB_SYNONYM NULL NULL NULL -20025 Leproma NULL KNOWNXREF 1 0 0 Leproma PRIMARY_DB_SYNONYM NULL NULL NULL -20031 2DBase_Ecoli NULL KNOWNXREF 1 0 0 2DBase-Ecoli PRIMARY_DB_SYNONYM NULL NULL NULL -20038 SagaList NULL KNOWNXREF 1 0 0 SagaList PRIMARY_DB_SYNONYM NULL NULL NULL -20040 SubtiList NULL KNOWNXREF 1 0 0 SubtiList PRIMARY_DB_SYNONYM NULL NULL NULL -20042 TIGR NULL KNOWNXREF 1 0 0 TIGR PRIMARY_DB_SYNONYM NULL NULL NULL -20043 TubercuList NULL KNOWNXREF 1 0 0 TubercuList PRIMARY_DB_SYNONYM NULL NULL NULL -20046 ArrayExpress NULL KNOWNXREF 1 0 0 ArrayExpress PRIMARY_DB_SYNONYM NULL NULL NULL -20050 GermOnline NULL KNOWNXREF 1 0 0 GermOnline PRIMARY_DB_SYNONYM NULL NULL NULL -20059 DIP NULL KNOWNXREF 1 0 0 DIP PRIMARY_DB_SYNONYM NULL NULL NULL -20061 DisProt NULL KNOWNXREF 1 0 0 DisProt PRIMARY_DB_SYNONYM NULL NULL NULL -20062 DrugBank NULL KNOWNXREF 1 0 0 DrugBank PRIMARY_DB_SYNONYM NULL NULL NULL -20065 GlycoSuiteDB NULL KNOWNXREF 1 0 0 GlycoSuiteDB PRIMARY_DB_SYNONYM NULL NULL NULL -20066 HAMAP NULL KNOWNXREF 1 0 0 HAMAP PRIMARY_DB_SYNONYM NULL NULL NULL -20067 HOGENOM NULL KNOWNXREF 1 0 0 HOGENOM PRIMARY_DB_SYNONYM NULL NULL NULL -20071 HSSP NULL KNOWNXREF 1 0 0 HSSP PRIMARY_DB_SYNONYM NULL NULL NULL -20072 IntAct NULL KNOWNXREF 1 0 0 IntAct PRIMARY_DB_SYNONYM NULL NULL NULL -20074 KEGG NULL KNOWNXREF 1 0 0 KEGG PRIMARY_DB_SYNONYM NULL NULL NULL -20078 PDBsum NULL KNOWNXREF 1 0 0 PDBsum PRIMARY_DB_SYNONYM NULL NULL NULL -20082 PeroxiBase NULL KNOWNXREF 1 0 0 PeroxiBase PRIMARY_DB_SYNONYM NULL NULL NULL -20083 PhosSite NULL KNOWNXREF 1 0 0 PhosSite PRIMARY_DB_SYNONYM NULL NULL NULL -20084 PptaseDB NULL KNOWNXREF 1 0 0 PptaseDB PRIMARY_DB_SYNONYM NULL NULL NULL -20085 REBASE NULL KNOWNXREF 1 0 0 REBASE PRIMARY_DB_SYNONYM NULL NULL NULL -20088 Reactome NULL KNOWNXREF 1 0 0 Reactome PRIMARY_DB_SYNONYM NULL NULL NULL -20090 SWISS_2DPAGE NULL KNOWNXREF 1 0 0 SWISS-2DPAGE PRIMARY_DB_SYNONYM NULL NULL NULL -20097 RegulonDb_Transcript NULL KNOWNXREF 1 0 0 RegulonDb PRIMARY_DB_SYNONYM NULL NULL NULL -20099 RegulonDb_Gene NULL KNOWNXREF 1 0 0 RegulonDb PRIMARY_DB_SYNONYM NULL NULL NULL -20101 IntEnz NULL KNOWNXREF 1 0 0 EnzymeCommission PRIMARY_DB_SYNONYM NULL NULL NULL -20102 ArrayExpressExperiment NULL KNOWNXREF 1 0 0 ArrayExpressExperiment PRIMARY_DB_SYNONYM NULL NULL NULL -20200 EMBLBANK_GENE NULL KNOWNXREF 0 0 0 European Nucleotide Archive PRIMARY_DB_SYNONYM NULL NULL NULL -20201 GeneDB_SPombe_transcript NULL KNOWNXREF 0 0 0 GeneDB_SPombe PRIMARY_DB_SYNONYM NULL NULL NULL -20202 EBACTERIA_GENE NULL KNOWNXREF 0 0 0 e!Bacteria PRIMARY_DB_SYNONYM NULL NULL NULL -20203 EBACTERIA_TRANSCRIPT NULL KNOWNXREF 0 0 0 e!Bacteria PRIMARY_DB_SYNONYM NULL NULL NULL -20204 EPROTIST_GENE NULL KNOWNXREF 0 0 0 e!Protists PRIMARY_DB_SYNONYM NULL NULL NULL -20205 EPROTIST_TRANSCRIPT NULL KNOWNXREF 0 0 0 e!Protists PRIMARY_DB_SYNONYM NULL NULL NULL -20207 EFUNGI_GENE NULL KNOWNXREF 0 0 0 e!Fungi PRIMARY_DB_SYNONYM NULL NULL NULL -20208 EFUNGI_TRANSCRIPT NULL KNOWNXREF 0 0 0 e!Fungi PRIMARY_DB_SYNONYM NULL NULL NULL -20209 EMBLBANK_TRANSCRIPT NULL KNOWNXREF 0 0 0 European Nucleotide Archive PRIMARY_DB_SYNONYM NULL NULL NULL -20210 GeneDB_SPombe_gene NULL KNOWNXREF 0 0 0 GeneDB_SPombe PRIMARY_DB_SYNONYM NULL NULL NULL -20301 RNAMMER NULL KNOWNXREF 1 0 0 RNAmmer MISC NULL NULL NULL -20302 TRNASCAN_SE NULL KNOWNXREF 1 0 0 tRNAScan-SE MISC NULL NULL NULL -20303 dictyBase NULL KNOWNXREF 1 0 0 DictyBase PRIMARY_DB_SYNONYM NULL NULL NULL -20304 dictyBase_gene NULL KNOWNXREF 1 0 0 DictyBase PRIMARY_DB_SYNONYM NULL NULL NULL -20305 dictyBase_transcript NULL KNOWNXREF 1 0 0 DictyBase PRIMARY_DB_SYNONYM NULL NULL NULL -20306 ASPGD NULL KNOWNXREF 1 0 0 AspGD PRIMARY_DB_SYNONYM NULL NULL NULL -20307 ASPGD_GENE NULL KNOWNXREF 1 0 0 AspGD PRIMARY_DB_SYNONYM NULL NULL NULL -20308 ASPGD_TRANSCRIPT NULL KNOWNXREF 1 0 0 AspGD PRIMARY_DB_SYNONYM NULL NULL NULL -20309 CADRE NULL KNOWNXREF 1 0 0 CADRE PRIMARY_DB_SYNONYM NULL NULL NULL -20310 CADRE_GENE NULL KNOWNXREF 1 0 0 CADRE PRIMARY_DB_SYNONYM NULL NULL NULL -20311 CADRE_TRANSCRIPT NULL KNOWNXREF 1 0 0 CADRE PRIMARY_DB_SYNONYM NULL NULL NULL -20312 SGD_GENE NULL KNOWNXREF 1 0 0 SGD PRIMARY_DB_SYNONYM NULL NULL NULL -20313 SGD_TRANSCRIPT NULL KNOWNXREF 1 0 0 SGD PRIMARY_DB_SYNONYM NULL NULL NULL -20214 phatr_jgi_v2_bd NULL KNOWNXREF 1 0 0 JGI ID (JGI 2.0 unmapped sequence) PRIMARY_DB_SYNONYM NULL NULL NULL -20215 phatr_jgi_v2 NULL KNOWNXREF 1 0 0 JGI ID (JGI 2.0) PRIMARY_DB_SYNONYM NULL NULL NULL -20216 phatr_jgi_v2_bd_gene NULL KNOWNXREF 1 0 0 JGI Gene ID (JGI 2.0 unmapped sequence) PRIMARY_DB_SYNONYM NULL NULL NULL -20217 phatr_jgi_v2_gene NULL KNOWNXREF 1 0 0 JGI Gene ID (JGI 2.0) PRIMARY_DB_SYNONYM NULL NULL NULL -20218 phatr_jgi_v2_bd_transcript NULL KNOWNXREF 1 0 0 JGI transcript ID (JGI 2.0 unmapped sequence) PRIMARY_DB_SYNONYM NULL NULL NULL -20219 phatr_jgi_v2_transcript NULL KNOWNXREF 1 0 0 JGI transcript ID (JGI 2.0) PRIMARY_DB_SYNONYM NULL NULL NULL -20220 thaps_jgi_v2_bd NULL KNOWNXREF 1 0 0 JGI ID (JGI 2.0 unmapped sequence) PRIMARY_DB_SYNONYM NULL NULL NULL -20221 thaps_jgi_v2 NULL KNOWNXREF 1 0 0 JGI ID (JGI 2.0) PRIMARY_DB_SYNONYM NULL NULL NULL -20222 thaps_jgi_v2_gene NULL KNOWNXREF 1 0 0 JGI Gene ID (JGI 2.0) PRIMARY_DB_SYNONYM NULL NULL NULL -20223 thaps_jgi_v2_bd_gene NULL KNOWNXREF 1 0 0 JGI Gene ID (JGI 2.0 unmapped sequence) PRIMARY_DB_SYNONYM NULL NULL NULL -20224 thaps_jgi_v2_gene NULL KNOWNXREF 1 0 0 JGI Gene ID (JGI 2.0) PRIMARY_DB_SYNONYM NULL NULL NULL -20225 thaps_jgi_v2_bd_transcript NULL KNOWNXREF 1 0 0 JGI transcript ID (JGI 2.0 unmapped sequence) PRIMARY_DB_SYNONYM NULL NULL NULL -20226 thaps_jgi_v2_transcript NULL KNOWNXREF 1 0 0 JGI transcript ID (JGI 2.0) PRIMARY_DB_SYNONYM NULL NULL NULL -20227 Diatom_EST_Cluster NULL XREF 1 0 0 ENS EST Cluster (Diatom ESTDB) MISC NULL NULL NULL -50000 BGI_EST_Cluster NULL XREF 1 0 0 EST Cluster (BGI Indica) MISC NULL NULL NULL -50005 EC_NUMBER NULL XREF 1 0 0 Enzyme EC Number MISC NULL NULL NULL -50010 FSTs NULL XREF 1 0 0 Flanking Sequence Tag (FST) MISC NULL NULL NULL -50015 gene_name NULL KNOWNXREF 1 0 0 Gene Name MISC NULL NULL NULL -50020 Gramene_Pathway NULL XREF 1 0 0 Gramene Pathway MISC NULL NULL NULL -50030 Gramene_GenesDB NULL KNOWNXREF 1 0 100 Gramene Curated Gene MISC NULL NULL NULL -50035 Gramene_MarkersDB NULL XREF 1 0 0 Gramene MISC NULL NULL NULL -50040 Gramene_MarkersDB_mRNA NULL XREF 1 0 0 GenBank mRNA (Gramene) MISC NULL NULL NULL -50050 Gramene_MarkersDB_EST NULL XREF 1 0 0 GenBank EST (Gramene) MISC NULL NULL NULL -50060 IRGSP_Gene NULL XREF 1 0 0 IRGSP/RAP Gene MISC NULL NULL NULL -50065 KOME NULL KNOWNXREF 1 0 0 Full Length cDNA (KOME) MISC NULL NULL NULL -50070 miRNA_Accession NULL XREF 1 0 0 miRNA miRBase accession MISC NULL NULL NULL -50080 miRNA_Registry NULL XREF 1 0 1 miRNA Registry MISC NULL NULL NULL -50090 NASC_GENE_ID NULL XREF 1 0 1 NASC Gene ID MISC NULL NULL NULL -50100 NASC_TRANSCRIPT_ID NULL XREF 1 0 1 NASC Transcript ID MISC NULL NULL NULL -50110 PlantGDB_PUT NULL XREF 1 0 1 PlantGDB Transcript MISC NULL NULL NULL -50120 RAP_Gene NULL XREF 1 0 0 IRGSP/RAP Gene MISC NULL NULL NULL -50130 siRNA_Sunkar NULL XREF 1 0 0 siRNA ID from Sunkar et. al. 2005 NAR 33(14):4443-54 MISC NULL NULL NULL -50140 TIGR_LOCUS NULL XREF 0 1 1 MSU/TIGR Locus MISC NULL NULL NULL -50150 TIGR_LOCUS_MODEL NULL XREF 0 1 0 MSU/TIGR Locus (Model) MISC NULL NULL NULL -50160 TAIR_LOCUS NULL XREF 1 0 8 TAIR Locus MISC NULL NULL NULL -50170 TAIR_LOCUS_MODEL NULL XREF 1 0 8 TAIR Locus (Model) MISC NULL NULL NULL -50180 TIGR_GeneIndex NULL XREF 1 0 0 Gene Index MISC NULL NULL NULL -50185 TO NULL XREF 1 0 0 Plant Trait Ontology MISC NULL NULL NULL -50190 PO NULL XREF 1 0 0 Plant Structure Ontology MISC NULL NULL NULL -50195 PO_to_gene NULL XREF 1 0 0 Plant Structure Ontology MISC NULL NULL NULL -50196 GO_to_gene NULL XREF 1 0 0 Gene Ontology MISC NULL NULL NULL -50200 GRO NULL XREF 1 0 0 Plant Growth Stage MISC NULL NULL NULL -50510 AFFY_RICE NULL XREF 1 0 1 Affymx GeneChip Rice ARRAY NULL NULL NULL -50520 AFFY_ATH1 NULL XREF 1 0 1 Affymx GeneChip ATH1 ARRAY NULL NULL NULL -50530 AFFY_Vitis_Vinifera NULL XREF 1 0 1 Affymx GeneChip Vitis vinifera ARRAY NULL NULL NULL -50540 AFFY_Poplar NULL XREF 1 0 1 Affymx GeneChip Poplar ARRAY NULL NULL NULL -50541 LRG NULL KNOWN 1 0 10 Locus Reference Genomic MISC NULL NULL NULL -50542 ENS_LRG_gene NULL KNOWN 1 0 10 LRG display in Ensembl MISC NULL NULL NULL -50543 ENS_LRG_transcript NULL KNOWN 1 0 10 LRG display in Ensembl MISC NULL NULL NULL -20228 CADRE_Afum_A1163 NULL KNOWNXREF 1 0 0 CADRE PRIMARY_DB_SYNONYM NULL NULL NULL -50600 IKMCs_KOs NULL XREF 1 0 10 International Knockout Mouse Consortium Knockouts MISC NULL NULL Mouse lines produced as part of a high throughput strategy by the International Knockout Mouse Consortium to knock out every protein coding gene in mouse -50601 IKMCs_ES_cells_available NULL XREF 1 0 10 International Knockout Mouse Consortium Knockouts (ES cells available) MISC NULL NULL Mouse lines produced as part of a high throughput strategy by the International Knockout Mouse Consortium to knock out every protein coding gene in mouse (ES cells available) -50602 IKMCs_Mice_available NULL XREF 1 0 10 International Knockout Mouse Consortium Knockouts (Mice available) MISC NULL NULL Mouse lines produced as part of a high throughput strategy by the International Knockout Mouse Consortium to knock out every protein coding gene in mouse (Mice available) -50603 IKMCs_No_products_available_yet NULL XREF 1 0 10 International Knockout Mouse Consortium Knockouts (No products available yet) MISC NULL NULL Mouse lines produced as part of a high throughput strategy by the International Knockout Mouse Consortium to knock out every protein coding gene in mouse (No products available yet) -50604 IKMCs_Vector_available NULL XREF 1 0 10 International Knockout Mouse Consortium Knockouts (Vector available) MISC NULL NULL Mouse lines produced as part of a high throughput strategy by the International Knockout Mouse Consortium to knock out every protein coding gene in mouse (Vector available) -5901 Ens_Md_transcript NULL XREF 1 0 5 Ensembl Monodelphis Transcript MISC NULL NULL NULL -832 InteractiveFly NULL KNOWNXREF 0 1 5 The Interactive Fly gene MISC NULL NULL NULL -829 BioGRID NULL KNOWNXREF 1 0 5 BioGRID Interaction data, The General Repository for Interaction Datasets gene MISC NULL NULL NULL -7180 VB_Community_Annotation NULL KNOWN 1 0 30 VB Community Annotation MISC NULL NULL NULL -831 GenomeRNAi NULL KNOWNXREF 1 0 5 GenomeRNAi, a database for cell-based RNAi phenotypes gene MISC NULL NULL NULL -830 FlyExpress NULL KNOWNXREF 1 0 5 FlyExpress, expression patterns of developmentally relevant genes in Drosophila embryogenesis gene MISC NULL NULL NULL -833 MitoDrome NULL KNOWNXREF 1 0 5 Nuclear genes encoding proteins targeted to the mitochondrion gene MISC NULL NULL NULL diff --git a/misc-scripts/external_db/load_additional_human_affy_xrefs.pl b/misc-scripts/external_db/load_additional_human_affy_xrefs.pl deleted file mode 100644 index af8ef92eb6..0000000000 --- a/misc-scripts/external_db/load_additional_human_affy_xrefs.pl +++ /dev/null @@ -1,83 +0,0 @@ -#Contact: Emmanuel Mongin (mongin@ebi.ac.uk) - -use strict; -use DBI; -use Getopt::Long; -use Bio::EnsEMBL::DBSQL::DBAdaptor; -use Bio::EnsEMBL::DBSQL::DBEntryAdaptor; -use Bio::EnsEMBL::DBEntry; -use Bio::SeqIO; - - - -my ( $host, $dbuser, $dbname, $dbpass, $port, $filename ); - -my %map; - -GetOptions( "host=s", \$host, - "user=s", \$dbuser, - "pass=s", \$dbpass, - "port=i", \$port, - "dbname=s", \$dbname, - "file=s", \$filename - ); - -if( ! $filename ) { - usage() -} - -print STDERR "Connecting to $host, $dbname\n"; - - -my $db = new Bio::EnsEMBL::DBSQL::DBAdaptor( - '-host' => $host, - '-user' => $dbuser, - '-dbname' => $dbname, - '-pass' => $dbpass, - '-port' => $port - ); - -my $adaptor = $db->get_DBEntryAdaptor(); - -print STDERR "Loading expression data\n"; - -open (AFFY, $filename ) || die "Can't open AFFY file"; - -while (<AFFY>) { - chomp; - my ($transl_id,$db1,$id) = split; - - if ($id ne "NULL") { - my $dbentry = Bio::EnsEMBL::DBEntry->new - ( -adaptor => $adaptor, - -primary_id => $id, - -display_id => $id, - -version => 1, - -release => 1, - -dbname => $db1); - $dbentry->status("XREF"); - print "$transl_id\t$db1\t$id\n"; - $adaptor->store($dbentry,$transl_id,"Translation"); - } -} - -close(AFFY); - - -sub usage { - print STDERR <<HELP - -Usage: perl load_additional_human_affy_xrefs.pl - -host db connection detail - -user - -pass - -port - -dbname - -file filename - File with xrefs to upload - -HELP -; - - exit(); -} diff --git a/misc-scripts/external_db/load_additional_human_gkb_xrefs.pl b/misc-scripts/external_db/load_additional_human_gkb_xrefs.pl deleted file mode 100644 index 63e99527c9..0000000000 --- a/misc-scripts/external_db/load_additional_human_gkb_xrefs.pl +++ /dev/null @@ -1,88 +0,0 @@ -#Contact: Emmanuel Mongin (mongin@ebi.ac.uk) - -use strict; -use DBI; -use Getopt::Long; -use Bio::EnsEMBL::DBSQL::DBAdaptor; -use Bio::EnsEMBL::DBSQL::DBEntryAdaptor; -use Bio::EnsEMBL::DBEntry; -use Bio::SeqIO; - - - -my ( $host, $dbuser, $dbname, $dbpass, $port, $filename ); - -my %map; - -GetOptions( "host=s", \$host, - "user=s", \$dbuser, - "pass=s", \$dbpass, - "port=i", \$port, - "dbname=s", \$dbname, - "file=s", \$filename - ); - -if( ! $filename ) { - usage() -} - -print STDERR "Connecting to $host, $dbname\n"; - - -my $db = new Bio::EnsEMBL::DBSQL::DBAdaptor( - '-host' => $host, - '-user' => $dbuser, - '-dbname' => $dbname, - '-pass' => $dbpass, - '-port' => $port - ); - -my $adaptor = $db->get_DBEntryAdaptor(); - -print STDERR "Loading GKB mapping\n"; -open (GKB, $filename ) || die "Can't open GKB file"; - -my $sth = - $db->prepare("SELECT o.ensembl_id - FROM object_xref o, xref x - WHERE x.dbprimary_acc = ? AND x.xref_id = o.xref_id"); -my $db1 = "GKB"; - - -while (<GKB>) { - chomp; - my ($sp,$id) = split; - - $sth->execute($sp); - while (my $transl_id = $sth->fetchrow) { - my $dbentry = Bio::EnsEMBL::DBEntry->new - ( -adaptor => $adaptor, - -primary_id => $id, - -display_id => $id, - -version => 1, - -release => 1, - -dbname => $db1); - $dbentry->status("XREF"); - print STDERR "$transl_id\t$db1\t$id\n"; - - $adaptor->store($dbentry,$transl_id,"Translation"); - } -} - -sub usage { - print STDERR <<HELP - -Usage: perl load_additional_human_gkb_xrefs.pl - -host db connection detail - -user - -pass - -port - -dbname - -file filename - File with xrefs to upload - -HELP -; - - exit(); -} diff --git a/misc-scripts/external_db/update_external_dbs.pl b/misc-scripts/external_db/update_external_dbs.pl deleted file mode 100644 index 2e9ea3a6bb..0000000000 --- a/misc-scripts/external_db/update_external_dbs.pl +++ /dev/null @@ -1,324 +0,0 @@ -#!/usr/local/ensembl/bin/perl -w - -# -# updates the external db tables on all of the core databases on a given host -# - -use strict; - -use Getopt::Long; -use DBI; -use IO::File; - -my ( $host, $user, $pass, $port, @dbnames, - $file, $release_num, $master, $nonreleasemode, $force ); - -GetOptions( "dbhost|host=s", \$host, - "dbuser|user=s", \$user, - "dbpass|pass=s", \$pass, - "dbport|port=i", \$port, - "file=s", \$file, - "dbnames=s@", \@dbnames, - "release_num=i", \$release_num, - "master=s", \$master, - "nonreleasemode", \$nonreleasemode, - "force", \$force ); - -$port ||= 3306; - -$file ||= "external_dbs.txt"; - -usage("[DIE] Need a host") if(!$host); - -#release num XOR dbname are required. -usage( "[DIE] Need either both a release number and " - . "database names or neither" ) - if ( ( $release_num && @dbnames ) || ( !$release_num && !@dbnames ) ); - -if(!$nonreleasemode){ - # master database is required - usage("[DIE] Master database required") if (!$master); -} - -my $dsn = "DBI:mysql:host=$host;port=$port"; - -my $db = DBI->connect( $dsn, $user, $pass, {RaiseError => 1} ); - -if($release_num) { - @dbnames = map {$_->[0] } @{ $db->selectall_arrayref( "show databases" ) }; - - # - # filter out all non-core databases - # - @dbnames = grep {/^[a-zA-Z]+\_[a-zA-Z]+\_(core|est|estgene|vega|otherfeatures|cdna)\_${release_num}\_\d+[A-Za-z]?$/} @dbnames; -} - -my @field_names = qw(external_db_id db_name release status dbprimary_acc_linkable display_label_linkable priority db_display_name type); - -my @types = qw(ARRAY ALT_TRANS MISC LIT PRIMARY_DB_SYNONYM ALT_GENE); - -# -# make sure the user wishes to continue -# -print STDERR "Please make sure you've updated $file from CVS!\n"; -print STDERR - "The following databases will have their external_db tables " - . "updated if necessary:\n "; -print join( "\n ", @dbnames ); -print "\nContinue with update (yes/no)> "; - -my $input = lc(<STDIN>); -chomp($input); -if ($input ne 'yes') { - print "external_db conversion aborted\n"; - exit(); -} - -# -# read all of the new external_db entries from the file -# -my $fh = IO::File->new(); -$fh->open($file) or die("Could not open input file $file"); -my @rows; -my %bad_lines; - -while (my $row = <$fh>) { - chomp($row); - next if ($row =~ /^#/); # skip comments - next if ($row =~ /^$/); # and blank lines - next if ($row =~ /^\s+$/); # and whitespace-only lines - my @a = split(/\t/, $row); - push @rows, { - 'external_db_id' => $a[0], - 'db_name' => $a[1], - 'release' => $a[2], - 'status' => $a[3], - 'dbprimary_acc_linkable' => $a[4], - 'display_label_linkable' => $a[5], - 'priority' => $a[6], - 'db_display_name' => $a[7], - 'type' => $a[8] }; - - if ( $a[1] =~ /-/ ) { - print STDERR "Database name " - . $a[1] - . " contains '-' characters " - . "which will break Mart, " - . "please replace them with '_' until Mart is fixed\n"; - exit(1); - } - - # do some formatting checks - my $blank; - for (my $i=0; $i < scalar(@a); $i++) { - if ($a[$i] eq '') { - $bad_lines{$row} = $field_names[$i] . " - field blank - check all tabs/spaces in line"; - } - } - - if ($a[1] =~ /\s/) { - $bad_lines{$row} = "db_name field appears to contain spaces"; - } - if ($a[1] =~ /^$/) { - $bad_lines{$row} = "db_name field appears to be missing"; - } - if ($a[1] =~ /^\s+$/) { - $bad_lines{$row} = "db_name field appears to be blank"; - } - if ($a[1] =~ /^\d+$/) { - $bad_lines{$row} = "db_name field appears to be numeric - check formatting"; - } - - my $type_ok; - foreach my $type (@types) { - $type_ok = 1 if ($a[8] eq $type); - } - $bad_lines{$row} = "type field is " . $a[8] . ", not one of the recognised types" if (!$type_ok); - -} -$fh->close(); - -if (%bad_lines) { - print STDERR "Cannot parse the following line(s) from $file; check that all fields are present and are separated by one tab (not spaces). \n"; - print STDERR "Name of problem field, and the error is printed in brackets first\n\n"; - foreach my $row (keys %bad_lines) { - print STDERR "[". $bad_lines{$row} . "]" . " $row\n"; - } - exit(1); -} - -# Load into master database - if(!$nonreleasemode){ - load_database($db, $master, @rows); - } - # Check each other database in turn - # Load if no extra rows in db that aren't in master - # Warn and skip if there are - - foreach my $dbname (@dbnames) { - - print STDERR "Looking at $dbname ... \n"; - if ($force || $nonreleasemode) { - - print STDERR "Forcing overwrite of external_db table in " - . "$dbname from $file\n"; - load_database( $db, $dbname, @rows ); - - } elsif (compare_external_db($db, $master, $dbname)) { - - print STDERR "$dbname has no additional rows. " - . "Overwriting external_db table from $file\n"; - load_database( $db, $dbname, @rows ); - - } else { - - print STDERR "$dbname has extra rows " - . "that are not in $file, skipping\n"; - - } - - } - -print STDERR "Updates complete\n"; - - - -sub load_database { - my ($db, $dbname, @rows) = @_; - - $db->do("USE $dbname"); - - # Save all existing release information from the table. - my $sth = $db->prepare( - qq( SELECT external_db_id, db_release - FROM external_db) ); - $sth->execute(); - - my %saved_release; - while ( my ( $id, $release ) = $sth->fetchrow_array() ) { - if ( defined($release) && $release ne '1' ) { - $saved_release{$id} = $release; - } - } - $sth->finish(); - - # Delete the existing table - $sth = $db->prepare('DELETE FROM external_db'); - $sth->execute(); - $sth->finish(); - - # Populate the table with data from the file (using the saved release - # information) - $sth = $db->prepare( - qq( INSERT INTO external_db ( - external_db_id, - db_name, - db_release, - status, - dbprimary_acc_linkable, - display_label_linkable, - priority, - db_display_name, - type) VALUES (?,?,?,?,?,?,?,?,?)) ); - - foreach my $row (@rows) { - my $id = $row->{'external_db_id'}; - - $sth->execute( $id, - $row->{'db_name'}, ( - exists( $saved_release{$id} ) - ? $saved_release{$id} - : $row->{'release'} - ), - $row->{'status'}, - $row->{'dbprimary_acc_linkable'}, - $row->{'display_label_linkable'}, - $row->{'priority'}, - $row->{'db_display_name'}, - $row->{'type'} ); - } - - $sth->finish(); -} - - -# return true if the tables are the same, undef if not -sub compare_external_db { - - my ($db, $master, $dbname) = @_; - - my $same = 1; - - # check each row in $dbname against each row in $master - # only compare ID and name since we're only aiming to catch extra rows in $dbname - $db->do("use $dbname"); - - my $sth = $db->prepare(qq {SELECT d.external_db_id, d.db_name - FROM $dbname.external_db d - LEFT JOIN $master.external_db m - ON (d.external_db_id=m.external_db_id AND d.db_name=m.db_name) - WHERE m.external_db_id IS NULL OR m.db_name IS NULL }); - $sth->execute(); - - while (my ($id, $external_db_name) = $sth->fetchrow_array) { - print "$dbname has external_db entry for $external_db_name (ID $id) which is not present in $master\n"; - $same = undef; - - } - - $sth->finish(); - - return $same; - -} - -sub usage { - my $error = shift; - - print STDERR <<EOF; - $error - - Usage: $0 options - - -host hostname - -user username - -pass password - -port port_of_server optional - -master the name of the master database to load the file into - -force force update, even if there are rows in the database - that are not in the file - -release the release of the database to update used to match - database names, e.g. 13 - -file the path of the file containing the insert statements - of the entries of the external_db table. Default is - 'external_dbs.txt' - -dbnames the names of the database to update. If not provided - all of the core databases matching the release arg - will be updated. Either -dbnames or -release must - be specified, but not both. Multiple dbnames can be - provided. - -nonreleasemode Does not require master schema and forces the update. - - - Examples: - - # Update two databases - - ./update_external_dbs.pl -host ecs1c -file external_dbs.txt \\ - -user ensadmin -pass secret -master master_schema_14 \\ - -dbnames homo_sapiens_core_14_33 -dbnames mus_musculus_core_14_30 - - # Update all Core databases for release 14 - - ./update_external_dbs.pl -host ens-staging -file external_dbs.txt \\ - -user ensadmin -pass secret -release 42 -master master_schema_42 - - If the databases to be updated contain rows that are not in the file, - a warning will be given and the database in question skipped, unless - -force is used. - - This program will not overwrite the db_release column of any table. - -EOF - exit; -} ## end sub usage -- GitLab