Skip to content

Commit 75988a3

Browse files
authored
Merge pull request #94 from INCATools/new-entries-and-uri-resolution
Adding new entries for kbase
2 parents af8e476 + 9db2f71 commit 75988a3

File tree

4 files changed

+113
-35
lines changed

4 files changed

+113
-35
lines changed

ontologies.Makefile

Lines changed: 52 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -559,6 +559,17 @@ db/orcid.owl: download/orcid.owl
559559
cp $< $@
560560

561561

562+
download/ror.owl: STAMP
563+
curl -L -s https://w3id.org/biopragmatics/resources/ror/ror.owl.gz | gzip -dc > $@.tmp
564+
sha256sum -b $@.tmp > $@.sha256
565+
mv $@.tmp $@
566+
567+
.PRECIOUS: download/ror.owl
568+
569+
db/ror.owl: download/ror.owl
570+
cp $< $@
571+
572+
562573
download/cpont.owl: STAMP
563574
curl -L -s https://w3id.org/cpont/cpont.owl > $@.tmp
564575
sha256sum -b $@.tmp > $@.sha256
@@ -977,6 +988,17 @@ db/interpro.owl: download/interpro.owl
977988
perl -npe 's@ go:@ GO:@g;s@ ro:@ RO:@g;s@ interpro:@ InterPro:@g' $< > $@.tmp && robot convert -i $@.tmp -o $@
978989

979990

991+
download/pfam.owl: STAMP
992+
curl -L -s https://w3id.org/biopragmatics/resources/pfam/pfam.owl > $@.tmp
993+
sha256sum -b $@.tmp > $@.sha256
994+
mv $@.tmp $@
995+
996+
.PRECIOUS: download/pfam.owl
997+
998+
db/pfam.owl: download/pfam.owl
999+
cp $< $@
1000+
1001+
9801002
download/hgnc.genegroup.owl: STAMP
9811003
curl -L -s https://github.com/biopragmatics/obo-db-ingest/raw/main/export/hgnc.genegroup/hgnc.genegroup.owl.gz | gzip -dc > $@.tmp
9821004
sha256sum -b $@.tmp > $@.sha256
@@ -1010,14 +1032,14 @@ db/sgd.owl: download/sgd.owl
10101032
robot merge -i $< -o $@
10111033

10121034

1013-
download/dictybase.owl: STAMP
1014-
curl -L -s https://github.com/biopragmatics/obo-db-ingest/raw/main/export/dictybase/dictybase.owl.gz | gzip -dc > $@.tmp
1035+
download/gtdb.owl: STAMP
1036+
curl -L -s https://w3id.org/biopragmatics/resources/gtdb/gtdb.owl > $@.tmp
10151037
sha256sum -b $@.tmp > $@.sha256
10161038
mv $@.tmp $@
10171039

1018-
.PRECIOUS: download/dictybase.owl
1040+
.PRECIOUS: download/gtdb.owl
10191041

1020-
db/dictybase.owl: download/dictybase.owl
1042+
db/gtdb.owl: download/gtdb.owl
10211043
cp $< $@
10221044

10231045

@@ -1033,7 +1055,7 @@ db/eccode.owl: download/eccode.owl
10331055

10341056

10351057
download/uniprot.owl: STAMP
1036-
curl -L -s https://w3id.org/biopragmatics/resources/uniprot/2022_02/uniprot.owl.gz | gzip -dc > $@.tmp
1058+
curl -L -s https://w3id.org/biopragmatics/resources/uniprot/uniprot.owl.gz | gzip -dc > $@.tmp
10371059
sha256sum -b $@.tmp > $@.sha256
10381060
mv $@.tmp $@
10391061

@@ -1043,15 +1065,37 @@ db/uniprot.owl: download/uniprot.owl
10431065
cp $< $@
10441066

10451067

1068+
download/uniprot.ptm.owl: STAMP
1069+
curl -L -s https://w3id.org/biopragmatics/resources/uniprot.ptm/uniprot.ptm.owl > $@.tmp
1070+
sha256sum -b $@.tmp > $@.sha256
1071+
mv $@.tmp $@
1072+
1073+
.PRECIOUS: download/uniprot.ptm.owl
1074+
1075+
db/uniprot.ptm.owl: download/uniprot.ptm.owl
1076+
cp $< $@
1077+
1078+
1079+
download/credit.owl: STAMP
1080+
curl -L -s https://raw.githubusercontent.com/biopragmatics/obo-db-ingest/main/export/credit/credit.owl > $@.tmp
1081+
sha256sum -b $@.tmp > $@.sha256
1082+
mv $@.tmp $@
1083+
1084+
.PRECIOUS: download/credit.owl
1085+
1086+
db/credit.owl: download/credit.owl
1087+
cp $< $@
1088+
1089+
10461090
download/rhea.owl: STAMP
1047-
curl -L -s https://w3id.org/biopragmatics/resources/rhea/rhea.obo > $@.tmp
1091+
curl -L -s https://w3id.org/biopragmatics/resources/rhea/rhea.owl.gz | gzip -dc > $@.tmp
10481092
sha256sum -b $@.tmp > $@.sha256
10491093
mv $@.tmp $@
10501094

10511095
.PRECIOUS: download/rhea.owl
10521096

10531097
db/rhea.owl: download/rhea.owl
1054-
robot merge -i $< -o $@
1098+
perl -npe 's@https://www.ebi.ac.uk/.*ec=@https://bioregistry.io/eccode:@g' $< > $@.tmp && robot convert -i $@.tmp -o $@
10551099

10561100

10571101
download/swisslipid.owl: STAMP
@@ -1328,4 +1372,4 @@ download/%.owl: STAMP
13281372
db/%.owl: download/%.owl
13291373
robot merge -i $< -o $@
13301374

1331-
EXTRA_ONTOLOGIES = swo chiro pcl chemessence ogco ncit fma maxo foodon chebiplus msio pride modl phenio phenio_test comploinc hba mba dmba dhba pba bero aio reacto xsmo bcio sio icd10who ordo gard mondo-ingest oeo envthes wifire taxslim goldterms sdgio kin biovoices omop comet cco occo iof upa go go-lego go-amigo neo bao orcid cpont biolink biopax enanomapper mlo ito chemont molgenie cso obiws biopragmatics-reactome reactome-hs reactome-mm efo hcao hpinternational edam chr sweetAll oboe-core oboe-standards lov schema-dot-org prov dtype vaem qudtunit quantitykind cellosaurus cosmo fhkb dbpendiaont uberoncm icd10cm omim co_324 ppeo interpro hgnc.genegroup hgnc sgd dictybase eccode uniprot rhea swisslipid drugbank drugcentral complexportal wikipathways pathbank kegg.genome drugmechdb rxnorm vccf ontobiotope nando ecso enigma_context ontie ecosim nmdc_schema mixs kgcl fibo bfo2020 bfo2020_core bfo2020_notime bfo2020_time
1375+
EXTRA_ONTOLOGIES = swo chiro pcl chemessence ogco ncit fma maxo foodon chebiplus msio pride modl phenio phenio_test comploinc hba mba dmba dhba pba bero aio reacto xsmo bcio sio icd10who ordo gard mondo-ingest oeo envthes wifire taxslim goldterms sdgio kin biovoices omop comet cco occo iof upa go go-lego go-amigo neo bao orcid ror cpont biolink biopax enanomapper mlo ito chemont molgenie cso obiws biopragmatics-reactome reactome-hs reactome-mm efo hcao hpinternational edam chr sweetAll oboe-core oboe-standards lov schema-dot-org prov dtype vaem qudtunit quantitykind cellosaurus cosmo fhkb dbpendiaont uberoncm icd10cm omim co_324 ppeo interpro pfam hgnc.genegroup hgnc sgd gtdb eccode uniprot uniprot.ptm credit rhea swisslipid drugbank drugcentral complexportal wikipathways pathbank kegg.genome drugmechdb rxnorm vccf ontobiotope nando ecso enigma_context ontie ecosim nmdc_schema mixs kgcl fibo bfo2020 bfo2020_core bfo2020_notime bfo2020_time

src/semsql/builder/prefixes/prefixes.csv

Lines changed: 13 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -118,6 +118,7 @@ OccO,http://purl.obolibrary.org/obo/OccO_
118118
IOFcore,https://spec.industrialontologies.org/ontology/
119119
UPa,http://purl.obolibrary.org/obo/UPa_
120120
orcid,https://orcid.org/
121+
ror,https://ror.org/
121122
evs.ncit,http://ncicb.nci.nih.gov/xml/owl/EVS/Thesaurus.owl#
122123
old.fix,http://purl.org/obo/owl/FIX#
123124
mlo,http://www.a2rd.net.br/mlo#
@@ -151,15 +152,20 @@ OMIMPS,https://www.omim.org/phenotypicSeries/PS
151152
co_324,https://cropontology.org/rdf/CO_324:
152153
PPEO,http://purl.org/ppeo/PPEO.owl#
153154
InterPro,http://purl.obolibrary.org/obo/InterPro_
155+
PFAM,https://www.ebi.ac.uk/interpro/entry/pfam/
156+
PFAM.CLAN,https://www.ebi.ac.uk/interpro/set/pfam/
154157
hgnc.genegroup,http://purl.obolibrary.org/obo/hgnc.genegroup_
155158
hgnc,http://purl.obolibrary.org/obo/hgnc_
156-
SGD,http://purl.obolibrary.org/obo/sgd_
157-
hgnc.genegroup,http://purl.obolibrary.org/obo/dictybase_
158-
EC,http://purl.obolibrary.org/obo/eccode_
159-
uniprot.obo,http://purl.obolibrary.org/obo/uniprot_
160-
uniprot.obo,http://purl.obolibrary.org/obo/uniprot_
161-
RHEA,http://purl.obolibrary.org/obo/rhea_
162-
uniprot.obo,http://purl.obolibrary.org/obo/uniprot_
159+
SGD,https://www.yeastgenome.org/locus/
160+
gtdb,https://gtdb.ecogenomic.org/tree?r=
161+
EC,https://bioregistry.io/eccode:
162+
UniProtKB,https://bioregistry.io/uniprot:
163+
UniProtKB,https://bioregistry.io/uniprot:
164+
RESID,https://proteininformationresource.org/cgi-bin/resid?id=
165+
UNIMOD,http://www.unimod.org/modifications_view.php?editid1=
166+
uniprot.ptm,https://biopragmatics.github.io/providers/uniprot.ptm/
167+
credit,https://credit.niso.org/contributor-roles/
168+
RHEA,https://www.rhea-db.org/rhea/
163169
swisslipid,http://purl.obolibrary.org/obo/swisslipid_
164170
drugbank,http://purl.obolibrary.org/obo/drugbank_
165171
drugbank,http://purl.obolibrary.org/obo/drugcentral_

src/semsql/builder/prefixes/prefixes_local.csv

Lines changed: 13 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -55,6 +55,7 @@ OccO,http://purl.obolibrary.org/obo/OccO_
5555
IOFcore,https://spec.industrialontologies.org/ontology/
5656
UPa,http://purl.obolibrary.org/obo/UPa_
5757
orcid,https://orcid.org/
58+
ror,https://ror.org/
5859
evs.ncit,http://ncicb.nci.nih.gov/xml/owl/EVS/Thesaurus.owl#
5960
old.fix,http://purl.org/obo/owl/FIX#
6061
mlo,http://www.a2rd.net.br/mlo#
@@ -88,15 +89,20 @@ OMIMPS,https://www.omim.org/phenotypicSeries/PS
8889
co_324,https://cropontology.org/rdf/CO_324:
8990
PPEO,http://purl.org/ppeo/PPEO.owl#
9091
InterPro,http://purl.obolibrary.org/obo/InterPro_
92+
PFAM,https://www.ebi.ac.uk/interpro/entry/pfam/
93+
PFAM.CLAN,https://www.ebi.ac.uk/interpro/set/pfam/
9194
hgnc.genegroup,http://purl.obolibrary.org/obo/hgnc.genegroup_
9295
hgnc,http://purl.obolibrary.org/obo/hgnc_
93-
SGD,http://purl.obolibrary.org/obo/sgd_
94-
hgnc.genegroup,http://purl.obolibrary.org/obo/dictybase_
95-
EC,http://purl.obolibrary.org/obo/eccode_
96-
uniprot.obo,http://purl.obolibrary.org/obo/uniprot_
97-
uniprot.obo,http://purl.obolibrary.org/obo/uniprot_
98-
RHEA,http://purl.obolibrary.org/obo/rhea_
99-
uniprot.obo,http://purl.obolibrary.org/obo/uniprot_
96+
SGD,https://www.yeastgenome.org/locus/
97+
gtdb,https://gtdb.ecogenomic.org/tree?r=
98+
EC,https://bioregistry.io/eccode:
99+
UniProtKB,https://bioregistry.io/uniprot:
100+
UniProtKB,https://bioregistry.io/uniprot:
101+
RESID,https://proteininformationresource.org/cgi-bin/resid?id=
102+
UNIMOD,http://www.unimod.org/modifications_view.php?editid1=
103+
uniprot.ptm,https://biopragmatics.github.io/providers/uniprot.ptm/
104+
credit,https://credit.niso.org/contributor-roles/
105+
RHEA,https://www.rhea-db.org/rhea/
100106
swisslipid,http://purl.obolibrary.org/obo/swisslipid_
101107
drugbank,http://purl.obolibrary.org/obo/drugbank_
102108
drugbank,http://purl.obolibrary.org/obo/drugcentral_

src/semsql/builder/registry/ontologies.yaml

Lines changed: 35 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -243,6 +243,11 @@ ontologies:
243243
url: https://w3id.org/orcidio/orcidio.owl
244244
prefixmap:
245245
orcid: https://orcid.org/
246+
ror:
247+
url: https://w3id.org/biopragmatics/resources/ror/ror.owl.gz
248+
compression: gzip
249+
prefixmap:
250+
ror: https://ror.org/
246251
cpont:
247252
url: https://w3id.org/cpont/cpont.owl
248253
biolink:
@@ -307,6 +312,7 @@ ontologies:
307312
zip_extract_file: Mus_musculus.owl
308313
post_processing_steps:
309314
- "sqlite3 {db} < views/reactome.sql"
315+
310316
efo:
311317
url: http://www.ebi.ac.uk/efo/efo.owl
312318
has_imports: true
@@ -426,6 +432,11 @@ ontologies:
426432
format: obo
427433
prefixmap:
428434
InterPro: http://purl.obolibrary.org/obo/InterPro_
435+
pfam:
436+
url: https://w3id.org/biopragmatics/resources/pfam/pfam.owl
437+
prefixmap:
438+
PFAM: https://www.ebi.ac.uk/interpro/entry/pfam/
439+
PFAM.CLAN: https://www.ebi.ac.uk/interpro/set/pfam/
429440
hgnc.genegroup:
430441
url: https://github.com/biopragmatics/obo-db-ingest/raw/main/export/hgnc.genegroup/hgnc.genegroup.owl.gz
431442
compression: gzip
@@ -441,29 +452,40 @@ ontologies:
441452
url: https://w3id.org/biopragmatics/resources/sgd/sgd.obo
442453
format: obo
443454
prefixmap:
444-
SGD: http://purl.obolibrary.org/obo/sgd_
445-
dictybase:
446-
url: https://github.com/biopragmatics/obo-db-ingest/raw/main/export/dictybase/dictybase.owl.gz
447-
compression: gzip
455+
SGD: https://www.yeastgenome.org/locus/
456+
gtdb:
457+
url: https://w3id.org/biopragmatics/resources/gtdb/gtdb.owl
448458
prefixmap:
449-
hgnc.genegroup: http://purl.obolibrary.org/obo/dictybase_
459+
gtdb: https://gtdb.ecogenomic.org/tree?r=
450460
eccode:
451461
url: https://w3id.org/biopragmatics/resources/eccode/eccode.owl.gz
452462
compression: gzip
453463
prefixmap:
454-
EC: http://purl.obolibrary.org/obo/eccode_
455-
uniprot.obo: http://purl.obolibrary.org/obo/uniprot_
464+
EC: "https://bioregistry.io/eccode:"
465+
UniProtKB: "https://bioregistry.io/uniprot:"
456466
uniprot:
457-
url: https://w3id.org/biopragmatics/resources/uniprot/2022_02/uniprot.owl.gz
467+
url: https://w3id.org/biopragmatics/resources/uniprot/uniprot.owl.gz
458468
compression: gzip
459469
prefixmap:
460-
uniprot.obo: http://purl.obolibrary.org/obo/uniprot_
470+
UniProtKB: "https://bioregistry.io/uniprot:"
471+
uniprot.ptm:
472+
url: https://w3id.org/biopragmatics/resources/uniprot.ptm/uniprot.ptm.owl
473+
prefixmap:
474+
RESID: https://proteininformationresource.org/cgi-bin/resid?id=
475+
UNIMOD: http://www.unimod.org/modifications_view.php?editid1=
476+
uniprot.ptm: https://biopragmatics.github.io/providers/uniprot.ptm/
477+
credit:
478+
url: https://raw.githubusercontent.com/biopragmatics/obo-db-ingest/main/export/credit/credit.owl
479+
prefixmap:
480+
credit: https://credit.niso.org/contributor-roles/
461481
rhea:
462-
url: https://w3id.org/biopragmatics/resources/rhea/rhea.obo
463-
build_command: "robot merge -i $< -o $@"
482+
url: https://w3id.org/biopragmatics/resources/rhea/rhea.owl.gz
483+
# https://github.com/biopragmatics/obo-db-ingest/issues/15
484+
build_command: "perl -npe 's@https://www.ebi.ac.uk/.*ec=@https://bioregistry.io/eccode:@g' $< > $@.tmp && robot convert -i $@.tmp -o $@"
485+
compression: gzip
486+
# build_command: "robot merge -i $< -o $@"
464487
prefixmap:
465-
RHEA: http://purl.obolibrary.org/obo/rhea_
466-
uniprot.obo: http://purl.obolibrary.org/obo/uniprot_
488+
RHEA: https://www.rhea-db.org/rhea/
467489
swisslipid:
468490
url: https://github.com/biopragmatics/obo-db-ingest/raw/main/export/swisslipid/2023-02-03/swisslipid.obo.gz
469491
format: obo

0 commit comments

Comments
 (0)