From 088d2689d27ba3dc9b219837341e4cce7c2fa300 Mon Sep 17 00:00:00 2001 From: Chris Mungall Date: Mon, 3 Feb 2025 19:34:03 -0800 Subject: [PATCH] Adding new entries for kbase Attempting to best resolve PURL muddle; see https://github.com/biopragmatics/obo-db-ingest/issues/15 --- ontologies.Makefile | 60 ++++++++++++++++--- src/semsql/builder/prefixes/prefixes.csv | 20 ++++--- .../builder/prefixes/prefixes_local.csv | 20 ++++--- src/semsql/builder/registry/ontologies.yaml | 48 +++++++++++---- 4 files changed, 113 insertions(+), 35 deletions(-) diff --git a/ontologies.Makefile b/ontologies.Makefile index 87ec914..54260f3 100644 --- a/ontologies.Makefile +++ b/ontologies.Makefile @@ -548,6 +548,17 @@ db/orcid.owl: download/orcid.owl cp $< $@ +download/ror.owl: STAMP + curl -L -s https://w3id.org/biopragmatics/resources/ror/ror.owl.gz | gzip -dc > $@.tmp + sha256sum -b $@.tmp > $@.sha256 + mv $@.tmp $@ + +.PRECIOUS: download/ror.owl + +db/ror.owl: download/ror.owl + cp $< $@ + + download/cpont.owl: STAMP curl -L -s https://w3id.org/cpont/cpont.owl > $@.tmp sha256sum -b $@.tmp > $@.sha256 @@ -966,6 +977,17 @@ db/interpro.owl: download/interpro.owl perl -npe 's@ go:@ GO:@g;s@ ro:@ RO:@g;s@ interpro:@ InterPro:@g' $< > $@.tmp && robot convert -i $@.tmp -o $@ +download/pfam.owl: STAMP + curl -L -s https://w3id.org/biopragmatics/resources/pfam/pfam.owl > $@.tmp + sha256sum -b $@.tmp > $@.sha256 + mv $@.tmp $@ + +.PRECIOUS: download/pfam.owl + +db/pfam.owl: download/pfam.owl + cp $< $@ + + download/hgnc.genegroup.owl: STAMP curl -L -s https://github.com/biopragmatics/obo-db-ingest/raw/main/export/hgnc.genegroup/hgnc.genegroup.owl.gz | gzip -dc > $@.tmp sha256sum -b $@.tmp > $@.sha256 @@ -999,14 +1021,14 @@ db/sgd.owl: download/sgd.owl robot merge -i $< -o $@ -download/dictybase.owl: STAMP - curl -L -s https://github.com/biopragmatics/obo-db-ingest/raw/main/export/dictybase/dictybase.owl.gz | gzip -dc > $@.tmp +download/gtdb.owl: STAMP + curl -L -s https://w3id.org/biopragmatics/resources/gtdb/gtdb.owl > $@.tmp sha256sum -b $@.tmp > $@.sha256 mv $@.tmp $@ -.PRECIOUS: download/dictybase.owl +.PRECIOUS: download/gtdb.owl -db/dictybase.owl: download/dictybase.owl +db/gtdb.owl: download/gtdb.owl cp $< $@ @@ -1022,7 +1044,7 @@ db/eccode.owl: download/eccode.owl download/uniprot.owl: STAMP - curl -L -s https://w3id.org/biopragmatics/resources/uniprot/2022_02/uniprot.owl.gz | gzip -dc > $@.tmp + curl -L -s https://w3id.org/biopragmatics/resources/uniprot/uniprot.owl.gz | gzip -dc > $@.tmp sha256sum -b $@.tmp > $@.sha256 mv $@.tmp $@ @@ -1032,15 +1054,37 @@ db/uniprot.owl: download/uniprot.owl cp $< $@ +download/uniprot.ptm.owl: STAMP + curl -L -s https://w3id.org/biopragmatics/resources/uniprot.ptm/uniprot.ptm.owl > $@.tmp + sha256sum -b $@.tmp > $@.sha256 + mv $@.tmp $@ + +.PRECIOUS: download/uniprot.ptm.owl + +db/uniprot.ptm.owl: download/uniprot.ptm.owl + cp $< $@ + + +download/credit.owl: STAMP + curl -L -s https://raw.githubusercontent.com/biopragmatics/obo-db-ingest/main/export/credit/credit.owl > $@.tmp + sha256sum -b $@.tmp > $@.sha256 + mv $@.tmp $@ + +.PRECIOUS: download/credit.owl + +db/credit.owl: download/credit.owl + cp $< $@ + + download/rhea.owl: STAMP - curl -L -s https://w3id.org/biopragmatics/resources/rhea/rhea.obo > $@.tmp + curl -L -s https://w3id.org/biopragmatics/resources/rhea/rhea.owl.gz | gzip -dc > $@.tmp sha256sum -b $@.tmp > $@.sha256 mv $@.tmp $@ .PRECIOUS: download/rhea.owl db/rhea.owl: download/rhea.owl - robot merge -i $< -o $@ + perl -npe 's@https://www.ebi.ac.uk/.*ec=@https://bioregistry.io/eccode:@g' $< > $@.tmp && robot convert -i $@.tmp -o $@ download/swisslipid.owl: STAMP @@ -1317,4 +1361,4 @@ download/%.owl: STAMP db/%.owl: download/%.owl robot merge -i $< -o $@ -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 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 +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 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 diff --git a/src/semsql/builder/prefixes/prefixes.csv b/src/semsql/builder/prefixes/prefixes.csv index 16ac6f3..cf734a8 100644 --- a/src/semsql/builder/prefixes/prefixes.csv +++ b/src/semsql/builder/prefixes/prefixes.csv @@ -117,6 +117,7 @@ OccO,http://purl.obolibrary.org/obo/OccO_ IOFcore,https://spec.industrialontologies.org/ontology/ UPa,http://purl.obolibrary.org/obo/UPa_ orcid,https://orcid.org/ +ror,https://ror.org/ evs.ncit,http://ncicb.nci.nih.gov/xml/owl/EVS/Thesaurus.owl# old.fix,http://purl.org/obo/owl/FIX# mlo,http://www.a2rd.net.br/mlo# @@ -150,15 +151,20 @@ OMIMPS,https://www.omim.org/phenotypicSeries/PS co_324,https://cropontology.org/rdf/CO_324: PPEO,http://purl.org/ppeo/PPEO.owl# InterPro,http://purl.obolibrary.org/obo/InterPro_ +PFAM,https://www.ebi.ac.uk/interpro/entry/pfam/ +PFAM.CLAN,https://www.ebi.ac.uk/interpro/set/pfam/ hgnc.genegroup,http://purl.obolibrary.org/obo/hgnc.genegroup_ hgnc,http://purl.obolibrary.org/obo/hgnc_ -SGD,http://purl.obolibrary.org/obo/sgd_ -hgnc.genegroup,http://purl.obolibrary.org/obo/dictybase_ -EC,http://purl.obolibrary.org/obo/eccode_ -uniprot.obo,http://purl.obolibrary.org/obo/uniprot_ -uniprot.obo,http://purl.obolibrary.org/obo/uniprot_ -RHEA,http://purl.obolibrary.org/obo/rhea_ -uniprot.obo,http://purl.obolibrary.org/obo/uniprot_ +SGD,https://www.yeastgenome.org/locus/ +gtdb,https://gtdb.ecogenomic.org/tree?r= +EC,https://bioregistry.io/eccode: +UniProtKB,https://bioregistry.io/uniprot: +UniProtKB,https://bioregistry.io/uniprot: +RESID,https://proteininformationresource.org/cgi-bin/resid?id= +UNIMOD,http://www.unimod.org/modifications_view.php?editid1= +uniprot.ptm,https://biopragmatics.github.io/providers/uniprot.ptm/ +credit,https://credit.niso.org/contributor-roles/ +RHEA,https://www.rhea-db.org/rhea/ swisslipid,http://purl.obolibrary.org/obo/swisslipid_ drugbank,http://purl.obolibrary.org/obo/drugbank_ drugbank,http://purl.obolibrary.org/obo/drugcentral_ diff --git a/src/semsql/builder/prefixes/prefixes_local.csv b/src/semsql/builder/prefixes/prefixes_local.csv index 7c0060d..57880c5 100644 --- a/src/semsql/builder/prefixes/prefixes_local.csv +++ b/src/semsql/builder/prefixes/prefixes_local.csv @@ -54,6 +54,7 @@ OccO,http://purl.obolibrary.org/obo/OccO_ IOFcore,https://spec.industrialontologies.org/ontology/ UPa,http://purl.obolibrary.org/obo/UPa_ orcid,https://orcid.org/ +ror,https://ror.org/ evs.ncit,http://ncicb.nci.nih.gov/xml/owl/EVS/Thesaurus.owl# old.fix,http://purl.org/obo/owl/FIX# mlo,http://www.a2rd.net.br/mlo# @@ -87,15 +88,20 @@ OMIMPS,https://www.omim.org/phenotypicSeries/PS co_324,https://cropontology.org/rdf/CO_324: PPEO,http://purl.org/ppeo/PPEO.owl# InterPro,http://purl.obolibrary.org/obo/InterPro_ +PFAM,https://www.ebi.ac.uk/interpro/entry/pfam/ +PFAM.CLAN,https://www.ebi.ac.uk/interpro/set/pfam/ hgnc.genegroup,http://purl.obolibrary.org/obo/hgnc.genegroup_ hgnc,http://purl.obolibrary.org/obo/hgnc_ -SGD,http://purl.obolibrary.org/obo/sgd_ -hgnc.genegroup,http://purl.obolibrary.org/obo/dictybase_ -EC,http://purl.obolibrary.org/obo/eccode_ -uniprot.obo,http://purl.obolibrary.org/obo/uniprot_ -uniprot.obo,http://purl.obolibrary.org/obo/uniprot_ -RHEA,http://purl.obolibrary.org/obo/rhea_ -uniprot.obo,http://purl.obolibrary.org/obo/uniprot_ +SGD,https://www.yeastgenome.org/locus/ +gtdb,https://gtdb.ecogenomic.org/tree?r= +EC,https://bioregistry.io/eccode: +UniProtKB,https://bioregistry.io/uniprot: +UniProtKB,https://bioregistry.io/uniprot: +RESID,https://proteininformationresource.org/cgi-bin/resid?id= +UNIMOD,http://www.unimod.org/modifications_view.php?editid1= +uniprot.ptm,https://biopragmatics.github.io/providers/uniprot.ptm/ +credit,https://credit.niso.org/contributor-roles/ +RHEA,https://www.rhea-db.org/rhea/ swisslipid,http://purl.obolibrary.org/obo/swisslipid_ drugbank,http://purl.obolibrary.org/obo/drugbank_ drugbank,http://purl.obolibrary.org/obo/drugcentral_ diff --git a/src/semsql/builder/registry/ontologies.yaml b/src/semsql/builder/registry/ontologies.yaml index a46086a..4f9d26f 100644 --- a/src/semsql/builder/registry/ontologies.yaml +++ b/src/semsql/builder/registry/ontologies.yaml @@ -238,6 +238,11 @@ ontologies: url: https://w3id.org/orcidio/orcidio.owl prefixmap: orcid: https://orcid.org/ + ror: + url: https://w3id.org/biopragmatics/resources/ror/ror.owl.gz + compression: gzip + prefixmap: + ror: https://ror.org/ cpont: url: https://w3id.org/cpont/cpont.owl biolink: @@ -302,6 +307,7 @@ ontologies: zip_extract_file: Mus_musculus.owl post_processing_steps: - "sqlite3 {db} < views/reactome.sql" + efo: url: http://www.ebi.ac.uk/efo/efo.owl has_imports: true @@ -421,6 +427,11 @@ ontologies: format: obo prefixmap: InterPro: http://purl.obolibrary.org/obo/InterPro_ + pfam: + url: https://w3id.org/biopragmatics/resources/pfam/pfam.owl + prefixmap: + PFAM: https://www.ebi.ac.uk/interpro/entry/pfam/ + PFAM.CLAN: https://www.ebi.ac.uk/interpro/set/pfam/ hgnc.genegroup: url: https://github.com/biopragmatics/obo-db-ingest/raw/main/export/hgnc.genegroup/hgnc.genegroup.owl.gz compression: gzip @@ -436,29 +447,40 @@ ontologies: url: https://w3id.org/biopragmatics/resources/sgd/sgd.obo format: obo prefixmap: - SGD: http://purl.obolibrary.org/obo/sgd_ - dictybase: - url: https://github.com/biopragmatics/obo-db-ingest/raw/main/export/dictybase/dictybase.owl.gz - compression: gzip + SGD: https://www.yeastgenome.org/locus/ + gtdb: + url: https://w3id.org/biopragmatics/resources/gtdb/gtdb.owl prefixmap: - hgnc.genegroup: http://purl.obolibrary.org/obo/dictybase_ + gtdb: https://gtdb.ecogenomic.org/tree?r= eccode: url: https://w3id.org/biopragmatics/resources/eccode/eccode.owl.gz compression: gzip prefixmap: - EC: http://purl.obolibrary.org/obo/eccode_ - uniprot.obo: http://purl.obolibrary.org/obo/uniprot_ + EC: "https://bioregistry.io/eccode:" + UniProtKB: "https://bioregistry.io/uniprot:" uniprot: - url: https://w3id.org/biopragmatics/resources/uniprot/2022_02/uniprot.owl.gz + url: https://w3id.org/biopragmatics/resources/uniprot/uniprot.owl.gz compression: gzip prefixmap: - uniprot.obo: http://purl.obolibrary.org/obo/uniprot_ + UniProtKB: "https://bioregistry.io/uniprot:" + uniprot.ptm: + url: https://w3id.org/biopragmatics/resources/uniprot.ptm/uniprot.ptm.owl + prefixmap: + RESID: https://proteininformationresource.org/cgi-bin/resid?id= + UNIMOD: http://www.unimod.org/modifications_view.php?editid1= + uniprot.ptm: https://biopragmatics.github.io/providers/uniprot.ptm/ + credit: + url: https://raw.githubusercontent.com/biopragmatics/obo-db-ingest/main/export/credit/credit.owl + prefixmap: + credit: https://credit.niso.org/contributor-roles/ rhea: - url: https://w3id.org/biopragmatics/resources/rhea/rhea.obo - build_command: "robot merge -i $< -o $@" + url: https://w3id.org/biopragmatics/resources/rhea/rhea.owl.gz + # https://github.com/biopragmatics/obo-db-ingest/issues/15 + build_command: "perl -npe 's@https://www.ebi.ac.uk/.*ec=@https://bioregistry.io/eccode:@g' $< > $@.tmp && robot convert -i $@.tmp -o $@" + compression: gzip + # build_command: "robot merge -i $< -o $@" prefixmap: - RHEA: http://purl.obolibrary.org/obo/rhea_ - uniprot.obo: http://purl.obolibrary.org/obo/uniprot_ + RHEA: https://www.rhea-db.org/rhea/ swisslipid: url: https://github.com/biopragmatics/obo-db-ingest/raw/main/export/swisslipid/2023-02-03/swisslipid.obo.gz format: obo