Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
E
ensembl
Manage
Activity
Members
Labels
Plan
Issues
0
Issue boards
Milestones
Iterations
Wiki
Requirements
Jira
Code
Merge requests
1
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Locked files
Build
Pipelines
Jobs
Pipeline schedules
Test cases
Artifacts
Deploy
Releases
Package Registry
Container Registry
Operate
Environments
Terraform modules
Monitor
Incidents
Service Desk
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Code review analytics
Issue analytics
Insights
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Terms and privacy
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
ensembl-gh-mirror
ensembl
Commits
c421e8cd
Commit
c421e8cd
authored
20 years ago
by
Ian Longden
Browse files
Options
Downloads
Patches
Plain Diff
set species_id to be the taxonomy, easier to in in the populate script
parent
6c8282cc
No related branches found
Branches containing commit
No related tags found
Tags containing commit
No related merge requests found
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
misc-scripts/xref_mapping/sql/populate_metadata.sql
+43
-30
43 additions, 30 deletions
misc-scripts/xref_mapping/sql/populate_metadata.sql
misc-scripts/xref_mapping/sql/table.sql
+1
-1
1 addition, 1 deletion
misc-scripts/xref_mapping/sql/table.sql
with
44 additions
and
31 deletions
misc-scripts/xref_mapping/sql/populate_metadata.sql
+
43
−
30
View file @
c421e8cd
...
...
@@ -4,20 +4,20 @@
################################################################################
#
SPECIES
INSERT
INTO
species
(
taxonomy_id
,
name
,
aliases
)
VALUES
(
9606
,
'homo_sapiens'
,
'human,hsapiens,homosapiens'
);
INSERT
INTO
species
(
taxonomy_id
,
name
,
aliases
)
VALUES
(
10090
,
'mus_musculus'
,
'mouse,mmusculus,musmusculus'
);
INSERT
INTO
species
(
taxonomy_id
,
name
,
aliases
)
VALUES
(
10116
,
'rattus_norvegicus'
,
'rat,rnovegicus,rattusnorvegicus'
);
INSERT
INTO
species
(
taxonomy_id
,
name
,
aliases
)
VALUES
(
31033
,
'fugu_rubripes'
,
'pufferfish,fugu,frubripes,fugurubripes'
);
INSERT
INTO
species
(
taxonomy_id
,
name
,
aliases
)
VALUES
(
7165
,
'anopheles_gambiae'
,
'mosquito,anopheles,agambiae,anophelesgambiae'
);
INSERT
INTO
species
(
taxonomy_id
,
name
,
aliases
)
VALUES
(
7227
,
'drosophila_melanogaster'
,
'drosophila,dmelongaster,drosophilamelanogaster'
);
INSERT
INTO
species
(
taxonomy_id
,
name
,
aliases
)
VALUES
(
6239
,
'caenorhabditis_elegans'
,
'elegans,celegans,caenorhabditiselegans'
);
INSERT
INTO
species
(
taxonomy_id
,
name
,
aliases
)
VALUES
(
6238
,
'caenorhabditis_briggsae'
,
'briggsae,cbriggsae,caenorhabditisbriggsae'
);
INSERT
INTO
species
(
taxonomy_id
,
name
,
aliases
)
VALUES
(
7955
,
'danio_rerio'
,
'zebrafish,danio,drerio,daniorerio'
);
INSERT
INTO
species
(
taxonomy_id
,
name
,
aliases
)
VALUES
(
9598
,
'pan_troglodytes'
,
'chimp,chimpanzee,ptroglodytes,pantroglodytes'
);
INSERT
INTO
species
(
taxonomy_id
,
name
,
aliases
)
VALUES
(
9031
,
'gallus_gallus'
,
'chicken,chick,ggallus,gallusgallus'
);
INSERT
INTO
species
(
taxonomy_id
,
name
,
aliases
)
VALUES
(
99883
,
'tetraodon_nigroviridis'
,
'tetraodon,tnigroviridis,tetraodonnigroviridis'
);
INSERT
INTO
species
(
taxonomy_id
,
name
,
aliases
)
VALUES
(
9913
,
'bos_taurus'
,
'cow,btaurus,bostaurus'
);
INSERT
INTO
species
(
taxonomy_id
,
name
,
aliases
)
VALUES
(
9615
,
'canis_familaris'
,
'dog,doggy,cfamiliaris,canisfamiliaris'
);
INSERT
INTO
species
(
species_id
,
taxonomy_id
,
name
,
aliases
)
VALUES
(
9606
,
9606
,
'homo_sapiens'
,
'human,hsapiens,homosapiens'
);
INSERT
INTO
species
(
species_id
,
taxonomy_id
,
name
,
aliases
)
VALUES
(
10090
,
10090
,
'mus_musculus'
,
'mouse,mmusculus,musmusculus'
);
INSERT
INTO
species
(
species_id
,
taxonomy_id
,
name
,
aliases
)
VALUES
(
10116
,
10116
,
'rattus_norvegicus'
,
'rat,rnovegicus,rattusnorvegicus'
);
INSERT
INTO
species
(
species_id
,
taxonomy_id
,
name
,
aliases
)
VALUES
(
31033
,
31033
,
'fugu_rubripes'
,
'pufferfish,fugu,frubripes,fugurubripes'
);
INSERT
INTO
species
(
species_id
,
taxonomy_id
,
name
,
aliases
)
VALUES
(
7165
,
7165
,
'anopheles_gambiae'
,
'mosquito,anopheles,agambiae,anophelesgambiae'
);
INSERT
INTO
species
(
species_id
,
taxonomy_id
,
name
,
aliases
)
VALUES
(
7227
,
7227
,
'drosophila_melanogaster'
,
'drosophila,dmelongaster,drosophilamelanogaster'
);
INSERT
INTO
species
(
species_id
,
taxonomy_id
,
name
,
aliases
)
VALUES
(
6239
,
6239
,
'caenorhabditis_elegans'
,
'elegans,celegans,caenorhabditiselegans'
);
INSERT
INTO
species
(
species_id
,
taxonomy_id
,
name
,
aliases
)
VALUES
(
6238
,
6238
,
'caenorhabditis_briggsae'
,
'briggsae,cbriggsae,caenorhabditisbriggsae'
);
INSERT
INTO
species
(
species_id
,
taxonomy_id
,
name
,
aliases
)
VALUES
(
7955
,
7955
,
'danio_rerio'
,
'zebrafish,danio,drerio,daniorerio'
);
INSERT
INTO
species
(
species_id
,
taxonomy_id
,
name
,
aliases
)
VALUES
(
9598
,
9598
,
'pan_troglodytes'
,
'chimp,chimpanzee,ptroglodytes,pantroglodytes'
);
INSERT
INTO
species
(
species_id
,
taxonomy_id
,
name
,
aliases
)
VALUES
(
9031
,
9031
'gallus_gallus'
,
'chicken,chick,ggallus,gallusgallus'
);
INSERT
INTO
species
(
species_id
,
taxonomy_id
,
name
,
aliases
)
VALUES
(
99883
,
99883
,
'tetraodon_nigroviridis'
,
'tetraodon,tnigroviridis,tetraodonnigroviridis'
);
INSERT
INTO
species
(
species_id
,
taxonomy_id
,
name
,
aliases
)
VALUES
(
9913
,
9913
,
'bos_taurus'
,
'cow,btaurus,bostaurus'
);
INSERT
INTO
species
(
species_id
,
taxonomy_id
,
name
,
aliases
)
VALUES
(
9615
,
9615
,
'canis_familaris'
,
'dog,doggy,cfamiliaris,canisfamiliaris'
);
################################################################################
#
SOURCES
-
types
of
data
we
can
read
...
...
@@ -57,57 +57,70 @@ INSERT INTO source VALUES (1300, 'Interpro', 1, 'Y', 2);
###
HUMAN
##
uniprot
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
1
,
1
,
'ftp://ftp.ebi.ac.uk/pub/databases/SPproteomes/swissprot_files/proteomes/9606.SPC'
,
''
,
now
(),
now
(),
"UniProtParser"
);
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
1
,
9606
,
'ftp://ftp.ebi.ac.uk/pub/databases/SPproteomes/swissprot_files/proteomes/9606.SPC'
,
''
,
now
(),
now
(),
"UniProtParser"
);
##
refseq
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
3
,
1
,
'ftp://ftp.ncbi.nih.gov/refseq/H_sapiens/mRNA_Prot/human.protein.gpff.gz'
,
''
,
now
(),
now
(),
"RefSeqGPFFParser"
);
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
3
,
9606
,
'ftp://ftp.ncbi.nih.gov/refseq/H_sapiens/mRNA_Prot/human.protein.gpff.gz'
,
''
,
now
(),
now
(),
"RefSeqGPFFParser"
);
##
refseq
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
3
,
1
,
'ftp://ftp.ncbi.nih.gov/refseq/H_sapiens/mRNA_Prot/human.rna.fna.gz'
,
''
,
now
(),
now
(),
"RefSeqParser"
);
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
3
,
9606
,
'ftp://ftp.ncbi.nih.gov/refseq/H_sapiens/mRNA_Prot/human.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
,
1
,
'ftp://ftp.ebi.ac.uk/pub/databases/GO/goa/HUMAN/gene_association.goa_human.gz'
,
''
,
now
(),
now
(),
"GOParser"
);
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
1070
,
9606
,
'ftp://ftp.ebi.ac.uk/pub/databases/GO/goa/HUMAN/gene_association.goa_human.gz'
,
''
,
now
(),
now
(),
"GOParser"
);
##
HUGO
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
1090
,
1
,
'http://www.gene.ucl.ac.uk/public-files/nomen/ens4.txt http://www.gene.ucl.ac.uk/public-files/nomen/ens1.txt'
,
''
,
now
(),
now
(),
"HUGOParser"
);
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
1090
,
9606
,
'http://www.gene.ucl.ac.uk/public-files/nomen/ens4.txt http://www.gene.ucl.ac.uk/public-files/nomen/ens1.txt'
,
''
,
now
(),
now
(),
"HUGOParser"
);
##
Interpro
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
1300
,
1
,
' ftp://ftp.ebi.ac.uk/pub/databases/interpro/short_name.dat ftp://ftp.ebi.ac.uk/pub/databases/interpro/protein2interpro.dat.gz'
,
''
,
now
(),
now
(),
"InterproParser"
);
#
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
1300
,
9606
,
' ftp://ftp.ebi.ac.uk/pub/databases/interpro/short_name.dat ftp://ftp.ebi.ac.uk/pub/databases/interpro/protein2interpro.dat.gz'
,
''
,
now
(),
now
(),
"InterproParser"
);
###
MOUSE
##
uniprot
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
1
,
2
,
'ftp://ftp.ebi.ac.uk/pub/databases/SPproteomes/swissprot_files/proteomes/10090.SPC'
,
''
,
now
(),
now
(),
"UniProtParser"
);
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
1
,
10090
,
'ftp://ftp.ebi.ac.uk/pub/databases/SPproteomes/swissprot_files/proteomes/10090.SPC'
,
''
,
now
(),
now
(),
"UniProtParser"
);
##
refseq
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
3
,
2
,
'ftp://ftp.ncbi.nih.gov/refseq/M_musculus/mRNA_Prot/mouse.protein.gpff.gz'
,
''
,
now
(),
now
(),
"RefSeqGPFFParser"
);
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
3
,
10090
,
'ftp://ftp.ncbi.nih.gov/refseq/M_musculus/mRNA_Prot/mouse.protein.gpff.gz'
,
''
,
now
(),
now
(),
"RefSeqGPFFParser"
);
##
refseq
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
3
,
2
,
'ftp://ftp.ncbi.nih.gov/refseq/M_musculus/mRNA_Prot/mouse.rna.fna.gz'
,
''
,
now
(),
now
(),
"RefSeqParser"
);
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
3
,
10090
,
'ftp://ftp.ncbi.nih.gov/refseq/M_musculus/mRNA_Prot/mouse.rna.fna.gz'
,
''
,
now
(),
now
(),
"RefSeqParser"
);
##
mgd
(
MGI
-- MarkerSymbol)
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
1080
,
2
,
'ftp://ftp.informatics.jax.org/pub/reports/MRK_SwissProt_TrEMBL.rpt'
,
''
,
now
(),
now
(),
"MGDParser"
);
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
1080
,
10090
,
'ftp://ftp.informatics.jax.org/pub/reports/MRK_SwissProt_TrEMBL.rpt'
,
''
,
now
(),
now
(),
"MGDParser"
);
##
GO
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
1070
,
2
,
'ftp://ftp.ebi.ac.uk/pub/databases/GO/goa/MOUSE/gene_association.goa_mouse.gz'
,
''
,
now
(),
now
(),
"GOParser"
);
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
1070
,
10090
,
'ftp://ftp.ebi.ac.uk/pub/databases/GO/goa/MOUSE/gene_association.goa_mouse.gz'
,
''
,
now
(),
now
(),
"GOParser"
);
###
RAT
##
uniprot
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
1
,
3
,
'ftp://ftp.ebi.ac.uk/pub/databases/SPproteomes/swissprot_files/proteomes/10116.SPC'
,
''
,
now
(),
now
(),
"UniProtParser"
);
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
1
,
10116
,
'ftp://ftp.ebi.ac.uk/pub/databases/SPproteomes/swissprot_files/proteomes/10116.SPC'
,
''
,
now
(),
now
(),
"UniProtParser"
);
##
refseq
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
3
,
3
,
'ftp://ftp.ncbi.nih.gov/refseq/R_norvegicus/mRNA_Prot/rat.protein.gpff.gz'
,
''
,
now
(),
now
(),
"RefSeqGPFFParser"
);
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
3
,
10116
,
'ftp://ftp.ncbi.nih.gov/refseq/R_norvegicus/mRNA_Prot/rat.protein.gpff.gz'
,
''
,
now
(),
now
(),
"RefSeqGPFFParser"
);
##
refseq
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
3
,
3
,
'ftp://ftp.ncbi.nih.gov/refseq/R_norvegicus/mRNA_Prot/rat.rna.fna.gz'
,
''
,
now
(),
now
(),
"RefSeqParser"
);
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
3
,
10116
,
'ftp://ftp.ncbi.nih.gov/refseq/R_norvegicus/mRNA_Prot/rat.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
,
3
,
'ftp://ftp.ebi.ac.uk/pub/databases/GO/goa/RAT/gene_association.goa_rat.gz'
,
''
,
now
(),
now
(),
"GOParser"
);
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
1070
,
10116
,
'ftp://ftp.ebi.ac.uk/pub/databases/GO/goa/RAT/gene_association.goa_rat.gz'
,
''
,
now
(),
now
(),
"GOParser"
);
##
RGD
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
1200
,
3
,
'ftp://rgd.mcw.edu/pub/data_release/genbank_to_gene_ids.txt'
,
''
,
now
(),
now
(),
"RGDParser"
);
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
1200
,
10116
,
'ftp://rgd.mcw.edu/pub/data_release/genbank_to_gene_ids.txt'
,
''
,
now
(),
now
(),
"RGDParser"
);
###
Zebrafish
##
uniprot
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
1
,
7955
,
'ftp://ftp.ebi.ac.uk/pub/databases/SPproteomes/swissprot_files/proteomes/7955.SPC'
,
''
,
now
(),
now
(),
"UniProtParser"
);
##
refseq
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
3
,
7955
,
'ftp://ftp.ncbi.nih.gov/refseq/D_rerio/mRNA_Prot/zebrafish.protein.gpff.gz'
,
''
,
now
(),
now
(),
"RefSeqGPFFParser"
);
##
refseq
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
3
,
7955
,
'ftp://ftp.ncbi.nih.gov/refseq/D_rerio/mRNA_Prot/zebrafish.rna.fna.gz'
,
''
,
now
(),
now
(),
"RGDParser"
);
##
GO
#
MONSTER
file
of
all
GO
!!!!!!
INSERT
INTO
source_url
(
source_id
,
species_id
,
url
,
checksum
,
file_modified_date
,
upload_date
,
parser
)
VALUES
(
1070
,
7955
,
'ftp://ftp.ebi.ac.uk/pub/databases/GO/goa/SPTR/gene_association.goa_sptr.gz'
,
''
,
now
(),
now
(),
"GOParser"
);
################################################################################
This diff is collapsed.
Click to expand it.
misc-scripts/xref_mapping/sql/table.sql
+
1
−
1
View file @
c421e8cd
...
...
@@ -111,7 +111,7 @@ CREATE TABLE direct_xref (
CREATE
TABLE
species
(
species_id
int
unsigned
not
null
auto_increment
,
species_id
int
unsigned
not
null
,
taxonomy_id
int
unsigned
not
null
,
name
varchar
(
255
)
not
null
,
aliases
varchar
(
255
),
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment