From 921858ddc745decc7e0e9721365521ad4fbd5821 Mon Sep 17 00:00:00 2001 From: Colleen Xu Date: Mon, 24 Jul 2023 17:17:52 -0700 Subject: [PATCH 01/11] multiple service provider kps: change pubmed keyword to pmid --- CTD/smartapi.yaml | 18 +++++++++--------- EBIgene2phenotype/smartapi.yaml | 2 +- MGIgene2phenotype/smartapi.yaml | 2 +- bindingdb/smartapi.yaml | 4 ++-- dgidb/openapi.yml | 4 ++-- gtrx/gtrx.yaml | 4 ++-- mychem.info/openapi_full.yml | 4 ++-- mydisease.info/smartapi.yaml | 8 ++++---- mygene.info/openapi_full.yml | 6 +++--- myvariant.info/openapi_full.yml | 6 +++--- pharmgkb/smartapi.yaml | 10 +++++----- rhea/smartapi.yaml | 10 +++++----- semmeddb/smartapi.yaml | 4 ++-- semmeddb/version_without_operations.yaml | 4 ++-- 14 files changed, 43 insertions(+), 43 deletions(-) diff --git a/CTD/smartapi.yaml b/CTD/smartapi.yaml index 262e66b8..b6ff566f 100644 --- a/CTD/smartapi.yaml +++ b/CTD/smartapi.yaml @@ -139,7 +139,7 @@ paths: - "$ref": "#/components/x-bte-kgs-operations/pathway2gene_2" components: x-bte-kgs-operations: - ## - pubmed IDs are |-delimited strings but BTE seems to parse these correctly + ## - pubmed IDs are pipe-delimited (|) strings but BTE seems to parse these correctly ## - while the API supports multiple IDs as input (batch-query)...we aren't using it because ## response doesn't separate info from 1 input ID vs another. So BTE has trouble processing it ## (would need a custom api-response-transform) @@ -537,29 +537,29 @@ components: x-bte-response-mapping: chemical2gene: NCBIGene: data.GeneId ## no prefix - pubmed: data.PubMedIds ## no prefix + pmid: data.PubMedIds ## no prefix ## commenting out because data-processing / biolink-modeling issues # inTaxonName: data.Organism ## human-readable label # inTaxon: data.OrganismId ## no prefix gene2chemical: MESH: data.ChemicalId ## no prefix - pubmed: data.PubMedIds + pmid: data.PubMedIds ## commenting out because data-processing / biolink-modeling issues # inTaxonName: data.Organism ## human-readable label # inTaxon: data.OrganismId # chemical2disease_1: # MESH: data.DiseaseID ## HAS prefix # ctd_chemical_disease_interaction_types: data.DirectEvidence - # pubmed: data.PubMedIDs + # pmid: data.PubMedIDs disease2chemical: MESH: data.ChemicalID - pubmed: data.PubMedIDs + pmid: data.PubMedIDs ## commenting out because data-processing / biolink-modeling issues # ctd_chemical_disease_interaction_types: data.DirectEvidence ## |-delimited string is kept right now # chemical2disease_2: # OMIM: data.DiseaseID ## HAS PREFIX # ctd_chemical_disease_interaction_types: data.DirectEvidence - # pubmed: data.PubMedIDs + # pmid: data.PubMedIDs chemical2go: GO: data.GoTermID ## HAS PREFIX ## commenting out because data-processing / biolink-modeling issues @@ -567,17 +567,17 @@ components: # related_gene_ncbigene: data.GeneID ## no prefix disease2gene: NCBIGene: data.GeneID - pubmed: data.PubMedIDs + pmid: data.PubMedIDs ## commenting out because data-processing / biolink-modeling issues # ctd_gene_disease_interaction_types: data.DirectEvidence # gene2disease_1: # MESH: data.DiseaseID ## HAS PREFIX # ctd_gene_disease_interaction_types: data.DirectEvidence - # pubmed: data.PubMedIDs + # pmid: data.PubMedIDs # gene2disease_2: # OMIM: data.DiseaseID ## HAS PREFIX # ctd_gene_disease_interaction_types: data.DirectEvidence - # pubmed: data.PubMedIDs + # pmid: data.PubMedIDs # gene2pathway_1: # REACT: data.PathwayID ## HAS PREFIX # output_name: data.PathwayName diff --git a/EBIgene2phenotype/smartapi.yaml b/EBIgene2phenotype/smartapi.yaml index 6956b9be..88e2e05f 100644 --- a/EBIgene2phenotype/smartapi.yaml +++ b/EBIgene2phenotype/smartapi.yaml @@ -659,7 +659,7 @@ components: disease-object: OMIM: gene2phenotype.disease.disease_mim ## no prefix output_name: gene2phenotype.disease.disease_name - pubmed: gene2phenotype.pmids ## no prefix + pmid: gene2phenotype.pmids ## no prefix ## commenting out because data-processing / biolink-modeling issues # ## similar to "biolink:has_mode_of_inheritance" (predicate) but doesn't use the expected ontology terms and seems a bit different # g2p_allelic_requirement: gene2phenotype.allelic_requirement diff --git a/MGIgene2phenotype/smartapi.yaml b/MGIgene2phenotype/smartapi.yaml index d7351919..f7549bd3 100644 --- a/MGIgene2phenotype/smartapi.yaml +++ b/MGIgene2phenotype/smartapi.yaml @@ -677,7 +677,7 @@ components: DOID: mgi.associated_with_disease.doid ## has prefix gene_related_to_phenotype: MP: mgi.associated_with_phenotype.mp ## has prefix - pubmed: mgi.associated_with_phenotype.pubmed ## no prefix + pmid: mgi.associated_with_phenotype.pubmed ## no prefix ## commenting out because data-processing / biolink-modeling issues # mgi_allele_id: mgi.associated_with_phenotype.allele_id ## MGI curie # mgi_allele_symbol: mgi.associated_with_phenotype.allele_symbol ## free text? diff --git a/bindingdb/smartapi.yaml b/bindingdb/smartapi.yaml index a0e29310..fa07653c 100644 --- a/bindingdb/smartapi.yaml +++ b/bindingdb/smartapi.yaml @@ -642,7 +642,7 @@ components: pubchem-object: "PUBCHEM.COMPOUND": object.pubchem_cid ## no prefix "biolink:original_subject": subject.name ## was called "Target Name Assigned by Curator or DataSource" - pubmed: relation.pmid + pmid: relation.pmid ## no prefix ## commenting out because data-processing / biolink-modeling issues # in_taxon: subject.organism ## was called "Target Source Organism According to Curator or DataSource" # bindingdb_curation_datasource: relation.curation_datasource ## Curation/DataSource @@ -652,7 +652,7 @@ components: uniprot-subject: UniProtKB: subject.uniprot.accession ## no prefix "biolink:original_subject": subject.name - pubmed: relation.pmid + pmid: relation.pmid ## no prefix ## commenting out because data-processing / biolink-modeling issues # in_taxon: subject.organism # bindingdb_curation_datasource: relation.curation_datasource diff --git a/dgidb/openapi.yml b/dgidb/openapi.yml index ee1f8648..4a367d49 100644 --- a/dgidb/openapi.yml +++ b/dgidb/openapi.yml @@ -1979,14 +1979,14 @@ components: x-bte-response-mapping: forward: NCBIGene: object.NCBIGene - pubmed: association.pmids + pmid: association.pmids # no prefix ## commenting out because data-processing / biolink-modeling issues # dgidb_interaction_claim_source: association.interaction_claim_source # "biolink:original_predicate": association.interaction_types ## or dgidb interaction types # dgidb_interaction_group_score: association.interaction_group_score reverse: "CHEMBL.COMPOUND": subject.CHEMBL_COMPOUND - pubmed: association.pmids + pmid: association.pmids ## commenting out because data-processing / biolink-modeling issues # dgidb_interaction_claim_source: association.interaction_claim_source # "biolink:original_predicate": association.interaction_types ## or dgidb interaction types diff --git a/gtrx/gtrx.yaml b/gtrx/gtrx.yaml index 87694bdb..812afc34 100644 --- a/gtrx/gtrx.yaml +++ b/gtrx/gtrx.yaml @@ -666,7 +666,7 @@ components: drug: ## using order and language from gtrx website for these fields UNII: object.intervention.inxight ## no prefix - pubmed: references.pmid ## no prefix + pmid: references.pmid ## no prefix ## commenting out because data-processing / biolink-modeling issues # type_of_intervention: object.intervention.int_class # intervention_MUST_be_started_within: object.timeframe @@ -679,7 +679,7 @@ components: # clinical_summary: subject.clinical_summary disease: OMIM: subject.omim ## no prefix - pubmed: references.pmid ## no prefix + pmid: references.pmid ## no prefix ## commenting out because data-processing / biolink-modeling issues # type_of_intervention: object.intervention.int_class # intervention_MUST_be_started_within: object.timeframe diff --git a/mychem.info/openapi_full.yml b/mychem.info/openapi_full.yml index d5484433..b3f75de3 100644 --- a/mychem.info/openapi_full.yml +++ b/mychem.info/openapi_full.yml @@ -631,7 +631,7 @@ components: RHEA: chebi.xrefs.rhea drugMechChembl_EnsemblOutput: ENSEMBL: chembl.drug_mechanisms.target_components.ensembl_gene ## no prefix - pubmed: chembl.drug_mechanisms.mechanism_refs.PubMed ## no prefix + pmid: chembl.drug_mechanisms.mechanism_refs.PubMed ## no prefix output_name: chembl.drug_mechanisms.target_name ## commenting out because data-processing / biolink-modeling issues # chembl_drug_action_type: chembl.drug_mechanisms.action_type @@ -645,7 +645,7 @@ components: input_name: chembl.drug_mechanisms.target_name drugMechChembl_UniprotOutput: UniProtKB: chembl.drug_mechanisms.target_components.uniprot ## no prefix - pubmed: chembl.drug_mechanisms.mechanism_refs.PubMed ## no prefix + pmid: chembl.drug_mechanisms.mechanism_refs.PubMed ## no prefix output_name: chembl.drug_mechanisms.target_name ## commenting out because data-processing / biolink-modeling issues # chembl_drug_action_type: chembl.drug_mechanisms.action_type diff --git a/mydisease.info/smartapi.yaml b/mydisease.info/smartapi.yaml index 03f7c1aa..4f1ac011 100644 --- a/mydisease.info/smartapi.yaml +++ b/mydisease.info/smartapi.yaml @@ -605,7 +605,7 @@ components: ## not including "name" field since BTE isn't ingesting / using it to annotate nodes... disease-gene: NCBIGene: disgenet.genes_related_to_disease.gene_id ## no prefix - pubmed: disgenet.genes_related_to_disease.pubmed ## no prefix + pmid: disgenet.genes_related_to_disease.pubmed ## no prefix ## commenting out because data-processing / biolink-modeling issues # disgenet_source: disgenet.genes_related_to_disease.source # ## could remove "disgenet-" prefix from the key @@ -616,7 +616,7 @@ components: # disgenet-score: disgenet.genes_related_to_disease.score disease-variant: DBSNP: disgenet.variants_related_to_disease.rsid ## no prefix - pubmed: disgenet.variants_related_to_disease.pubmed ## no prefix + pmid: disgenet.variants_related_to_disease.pubmed ## no prefix ## commenting out because data-processing / biolink-modeling issues # disgenet_source: disgenet.variants_related_to_disease.source # ## could remove "disgenet-" prefix from the key @@ -628,7 +628,7 @@ components: disease-phenotype: HP: hpo.phenotype_related_to_disease.hpo_id ## HAS PREFIX (HP) ## note: there are 6 reference-related fields (parser created based on ID namespace) - pubmed: hpo.phenotype_related_to_disease.pmid_refs ## HAS PREFIX (PMID) + pmid: hpo.phenotype_related_to_disease.pmid_refs ## HAS PREFIX (PMID) ## note: there are 4 frequency-related fields (parser created based on different data types) "biolink:has_quotient": hpo.phenotype_related_to_disease.numeric_freq ## decimal freq "biolink:frequency_qualifier": hpo.phenotype_related_to_disease.hp_freq ## HP ontology freq term @@ -652,7 +652,7 @@ components: # hp_sex: hpo.phenotype_related_to_disease.sex disease-chemical: MESH: ctd.chemical_related_to_disease.mesh_chemical_id ## no prefix - pubmed: ctd.chemical_related_to_disease.pubmed ## no prefix + pmid: ctd.chemical_related_to_disease.pubmed ## no prefix ## commenting out because data-processing / biolink-modeling issues # # name: ctd.chemical_related_to_disease.chemical_name # ## direct_evidence has two values, 'marker/mechanism' or 'therapeutic' diff --git a/mygene.info/openapi_full.yml b/mygene.info/openapi_full.yml index 5041db2e..1ed6773c 100644 --- a/mygene.info/openapi_full.yml +++ b/mygene.info/openapi_full.yml @@ -1235,19 +1235,19 @@ components: output_name: pathway.biocarta.name biologicalProcess: GO: go.BP.id ## HAS PREFIX (GO) - pubmed: go.BP.pubmed + pmid: go.BP.pubmed ## commenting out because data-processing / biolink-modeling issues # evidence: go.BP.evidence ## categorical variable? # go_qualifier: go.BP.qualifier ## seems to be like a relation molecularFunction: GO: go.MF.id ## HAS PREFIX (GO) - pubmed: go.MF.pubmed + pmid: go.MF.pubmed ## commenting out because data-processing / biolink-modeling issues # evidence: go.MF.evidence ## categorical variable? # go_qualifier: go.MF.qualifier ## seems to be like a relation cellularComponent: GO: go.CC.id ## HAS PREFIX (GO) - pubmed: go.CC.pubmed + pmid: go.CC.pubmed ## commenting out because data-processing / biolink-modeling issues # evidence: go.CC.evidence ## categorical variable? # go_qualifier: go.CC.qualifier ## seems to be like a relation diff --git a/myvariant.info/openapi_full.yml b/myvariant.info/openapi_full.yml index 041228e0..9d80b4cd 100644 --- a/myvariant.info/openapi_full.yml +++ b/myvariant.info/openapi_full.yml @@ -615,7 +615,7 @@ components: x-bte-response-mapping: civic-geneDisease: DOID: civic.evidence_items.disease.doid - pubmed: civic.evidence_items.source.pubmed + pmid: civic.evidence_items.source.pubmed ## no prefix ## commenting out because data-processing / biolink-modeling issues # ## categorical var / relation # civic_clinical_significance: civic.evidence_items.clinical_significance @@ -641,7 +641,7 @@ components: DOID: civic.evidence_items.disease.doid ## variant name input_name: _id - pubmed: civic.evidence_items.source.pubmed + pmid: civic.evidence_items.source.pubmed ## no prefix ## commenting out because data-processing / biolink-modeling issues # ## categorical var / relation # civic_clinical_significance: civic.evidence_items.clinical_significance @@ -704,7 +704,7 @@ components: input_name: _id ## variant name ## commenting out because data-processing / biolink-modeling issues ## not taking notes on a bunch of fields about the gene and variant - # pubmed: docm.pubmed_id ## issue: lists are ", "-delimited strings + # pmid: docm.pubmed_id ## no prefix. issue: lists are ", "-delimited strings # docm_source: docm.source ## issue: sometimes it's just the value "-" or `null` # source_url: docm.url ##: sometimes it's just `null` # variant_consequence_type: docm.trv_type diff --git a/pharmgkb/smartapi.yaml b/pharmgkb/smartapi.yaml index 89fae4d8..2f911001 100644 --- a/pharmgkb/smartapi.yaml +++ b/pharmgkb/smartapi.yaml @@ -1936,34 +1936,34 @@ components: "PHARMGKB.CHEMICAL": data.obj2Id output_name: data.obj2Name input_name: data.obj1Name - pubmed: data.pmid + pmid: data.pmid ## no prefix ## commenting out because data-processing / biolink-modeling issues # pharmgkb_source_of_connection: data.relType connection-obj-pathway: "PHARMGKB.PATHWAYS": data.obj2Id output_name: data.obj2Name input_name: data.obj1Name - pubmed: data.pmid + pmid: data.pmid ## commenting out because data-processing / biolink-modeling issues # pharmgkb_source_of_connection: data.relType connection-obj-disease: "PHARMGKB.DISEASE": data.obj2Id output_name: data.obj2Name input_name: data.obj1Name - pubmed: data.pmid + pmid: data.pmid ## commenting out because data-processing / biolink-modeling issues # pharmgkb_source_of_connection: data.relType connection-obj-gene: "PHARMGKB.GENE": data.obj2Id output_name: data.obj2Name input_name: data.obj1Name - pubmed: data.pmid + pmid: data.pmid ## commenting out because data-processing / biolink-modeling issues # pharmgkb_source_of_connection: data.relType connection-obj-dbsnp: DBSNP: data.obj2Name ## DBSNP rs ID is put there input_name: data.obj1Name - pubmed: data.pmid + pmid: data.pmid ## commenting out because data-processing / biolink-modeling issues # pharmgkb_source_of_connection: data.relType pathEnd-chem: diff --git a/rhea/smartapi.yaml b/rhea/smartapi.yaml index 388b97fa..5acde2c9 100644 --- a/rhea/smartapi.yaml +++ b/rhea/smartapi.yaml @@ -766,35 +766,35 @@ components: x-bte-response-mapping: side_l-object: CHEBI: side_l.chebi_id ## has CHEBI prefix - pubmed: citations ## has PMID prefix + pmid: citations ## has PMID prefix ## commenting out because data-processing / biolink-modeling issues # equation: equation # is_transport: is_transport # reaction_status: status side_r-object: CHEBI: side_r.chebi_id ## has CHEBI prefix - pubmed: citations ## has PMID prefix + pmid: citations ## has PMID prefix ## commenting out because data-processing / biolink-modeling issues # equation: equation # is_transport: is_transport # reaction_status: status side_l_reactive-object: CHEBI: side_l.reactive_parts.chebi_id ## has CHEBI prefix - pubmed: citations ## has PMID prefix + pmid: citations ## has PMID prefix ## commenting out because data-processing / biolink-modeling issues # equation: equation # is_transport: is_transport # reaction_status: status side_r_reactive-object: CHEBI: side_r.reactive_parts.chebi_id ## has CHEBI prefix - pubmed: citations ## has PMID prefix + pmid: citations ## has PMID prefix ## commenting out because data-processing / biolink-modeling issues # equation: equation # is_transport: is_transport # reaction_status: status reaction-object: RHEA: _id ## has RHEA prefix - pubmed: citations ## has PMID prefix + pmid: citations ## has PMID prefix ## commenting out because data-processing / biolink-modeling issues # equation: equation # is_transport: is_transport diff --git a/semmeddb/smartapi.yaml b/semmeddb/smartapi.yaml index 703c7698..0b20faf2 100644 --- a/semmeddb/smartapi.yaml +++ b/semmeddb/smartapi.yaml @@ -3125,7 +3125,7 @@ components: x-bte-response-mapping: umls-obj: UMLS: object.umls ## no prefix - pubmed: predication.pmid ## no prefix + pmid: predication.pmid ## no prefix "biolink:supporting_text": predication.sentence "biolink:original_subject": subject.umls "biolink:original_object": object.umls @@ -3137,7 +3137,7 @@ components: # "biolink:original_predicate": predicate umls-subj: UMLS: subject.umls ## no prefix - pubmed: predication.pmid ## no prefix + pmid: predication.pmid ## no prefix "biolink:supporting_text": predication.sentence "biolink:original_subject": subject.umls "biolink:original_object": object.umls diff --git a/semmeddb/version_without_operations.yaml b/semmeddb/version_without_operations.yaml index cb5be128..613bd342 100644 --- a/semmeddb/version_without_operations.yaml +++ b/semmeddb/version_without_operations.yaml @@ -627,7 +627,7 @@ components: x-bte-response-mapping: umls-obj: UMLS: object.umls ## no prefix - pubmed: predication.pmid ## no prefix + pmid: predication.pmid ## no prefix "biolink:supporting_text": predication.sentence "biolink:original_subject": subject.umls "biolink:original_object": object.umls @@ -639,7 +639,7 @@ components: # "biolink:original_predicate": predicate umls-subj: UMLS: subject.umls ## no prefix - pubmed: predication.pmid ## no prefix + pmid: predication.pmid ## no prefix "biolink:supporting_text": predication.sentence "biolink:original_subject": subject.umls "biolink:original_object": object.umls From 8b8a0052d30c8491116a7d927e7a310c25d01ec7 Mon Sep 17 00:00:00 2001 From: Colleen Xu Date: Mon, 24 Jul 2023 19:35:47 -0700 Subject: [PATCH 02/11] multiple service provider kps: change pmid keyword to ref_pmid --- CTD/smartapi.yaml | 16 ++++++++-------- EBIgene2phenotype/smartapi.yaml | 2 +- MGIgene2phenotype/smartapi.yaml | 2 +- bindingdb/smartapi.yaml | 4 ++-- dgidb/openapi.yml | 4 ++-- gtrx/gtrx.yaml | 4 ++-- mychem.info/openapi_full.yml | 4 ++-- mydisease.info/smartapi.yaml | 8 ++++---- mygene.info/openapi_full.yml | 6 +++--- myvariant.info/openapi_full.yml | 6 +++--- pharmgkb/smartapi.yaml | 10 +++++----- rhea/smartapi.yaml | 10 +++++----- semmeddb/smartapi.yaml | 4 ++-- semmeddb/version_without_operations.yaml | 4 ++-- 14 files changed, 42 insertions(+), 42 deletions(-) diff --git a/CTD/smartapi.yaml b/CTD/smartapi.yaml index b6ff566f..9ad6c153 100644 --- a/CTD/smartapi.yaml +++ b/CTD/smartapi.yaml @@ -537,29 +537,29 @@ components: x-bte-response-mapping: chemical2gene: NCBIGene: data.GeneId ## no prefix - pmid: data.PubMedIds ## no prefix + ref_pmid: data.PubMedIds ## no prefix ## commenting out because data-processing / biolink-modeling issues # inTaxonName: data.Organism ## human-readable label # inTaxon: data.OrganismId ## no prefix gene2chemical: MESH: data.ChemicalId ## no prefix - pmid: data.PubMedIds + ref_pmid: data.PubMedIds ## commenting out because data-processing / biolink-modeling issues # inTaxonName: data.Organism ## human-readable label # inTaxon: data.OrganismId # chemical2disease_1: # MESH: data.DiseaseID ## HAS prefix # ctd_chemical_disease_interaction_types: data.DirectEvidence - # pmid: data.PubMedIDs + # ref_pmid: data.PubMedIDs disease2chemical: MESH: data.ChemicalID - pmid: data.PubMedIDs + ref_pmid: data.PubMedIDs ## commenting out because data-processing / biolink-modeling issues # ctd_chemical_disease_interaction_types: data.DirectEvidence ## |-delimited string is kept right now # chemical2disease_2: # OMIM: data.DiseaseID ## HAS PREFIX # ctd_chemical_disease_interaction_types: data.DirectEvidence - # pmid: data.PubMedIDs + # ref_pmid: data.PubMedIDs chemical2go: GO: data.GoTermID ## HAS PREFIX ## commenting out because data-processing / biolink-modeling issues @@ -567,17 +567,17 @@ components: # related_gene_ncbigene: data.GeneID ## no prefix disease2gene: NCBIGene: data.GeneID - pmid: data.PubMedIDs + ref_pmid: data.PubMedIDs ## commenting out because data-processing / biolink-modeling issues # ctd_gene_disease_interaction_types: data.DirectEvidence # gene2disease_1: # MESH: data.DiseaseID ## HAS PREFIX # ctd_gene_disease_interaction_types: data.DirectEvidence - # pmid: data.PubMedIDs + # ref_pmid: data.PubMedIDs # gene2disease_2: # OMIM: data.DiseaseID ## HAS PREFIX # ctd_gene_disease_interaction_types: data.DirectEvidence - # pmid: data.PubMedIDs + # ref_pmid: data.PubMedIDs # gene2pathway_1: # REACT: data.PathwayID ## HAS PREFIX # output_name: data.PathwayName diff --git a/EBIgene2phenotype/smartapi.yaml b/EBIgene2phenotype/smartapi.yaml index 88e2e05f..24bea767 100644 --- a/EBIgene2phenotype/smartapi.yaml +++ b/EBIgene2phenotype/smartapi.yaml @@ -659,7 +659,7 @@ components: disease-object: OMIM: gene2phenotype.disease.disease_mim ## no prefix output_name: gene2phenotype.disease.disease_name - pmid: gene2phenotype.pmids ## no prefix + ref_pmid: gene2phenotype.pmids ## no prefix ## commenting out because data-processing / biolink-modeling issues # ## similar to "biolink:has_mode_of_inheritance" (predicate) but doesn't use the expected ontology terms and seems a bit different # g2p_allelic_requirement: gene2phenotype.allelic_requirement diff --git a/MGIgene2phenotype/smartapi.yaml b/MGIgene2phenotype/smartapi.yaml index f7549bd3..e72d2847 100644 --- a/MGIgene2phenotype/smartapi.yaml +++ b/MGIgene2phenotype/smartapi.yaml @@ -677,7 +677,7 @@ components: DOID: mgi.associated_with_disease.doid ## has prefix gene_related_to_phenotype: MP: mgi.associated_with_phenotype.mp ## has prefix - pmid: mgi.associated_with_phenotype.pubmed ## no prefix + ref_pmid: mgi.associated_with_phenotype.pubmed ## no prefix ## commenting out because data-processing / biolink-modeling issues # mgi_allele_id: mgi.associated_with_phenotype.allele_id ## MGI curie # mgi_allele_symbol: mgi.associated_with_phenotype.allele_symbol ## free text? diff --git a/bindingdb/smartapi.yaml b/bindingdb/smartapi.yaml index fa07653c..636dc820 100644 --- a/bindingdb/smartapi.yaml +++ b/bindingdb/smartapi.yaml @@ -642,7 +642,7 @@ components: pubchem-object: "PUBCHEM.COMPOUND": object.pubchem_cid ## no prefix "biolink:original_subject": subject.name ## was called "Target Name Assigned by Curator or DataSource" - pmid: relation.pmid ## no prefix + ref_pmid: relation.pmid ## no prefix ## commenting out because data-processing / biolink-modeling issues # in_taxon: subject.organism ## was called "Target Source Organism According to Curator or DataSource" # bindingdb_curation_datasource: relation.curation_datasource ## Curation/DataSource @@ -652,7 +652,7 @@ components: uniprot-subject: UniProtKB: subject.uniprot.accession ## no prefix "biolink:original_subject": subject.name - pmid: relation.pmid ## no prefix + ref_pmid: relation.pmid ## no prefix ## commenting out because data-processing / biolink-modeling issues # in_taxon: subject.organism # bindingdb_curation_datasource: relation.curation_datasource diff --git a/dgidb/openapi.yml b/dgidb/openapi.yml index 4a367d49..e54827b3 100644 --- a/dgidb/openapi.yml +++ b/dgidb/openapi.yml @@ -1979,14 +1979,14 @@ components: x-bte-response-mapping: forward: NCBIGene: object.NCBIGene - pmid: association.pmids # no prefix + ref_pmid: association.pmids # no prefix ## commenting out because data-processing / biolink-modeling issues # dgidb_interaction_claim_source: association.interaction_claim_source # "biolink:original_predicate": association.interaction_types ## or dgidb interaction types # dgidb_interaction_group_score: association.interaction_group_score reverse: "CHEMBL.COMPOUND": subject.CHEMBL_COMPOUND - pmid: association.pmids + ref_pmid: association.pmids ## commenting out because data-processing / biolink-modeling issues # dgidb_interaction_claim_source: association.interaction_claim_source # "biolink:original_predicate": association.interaction_types ## or dgidb interaction types diff --git a/gtrx/gtrx.yaml b/gtrx/gtrx.yaml index 812afc34..a456855f 100644 --- a/gtrx/gtrx.yaml +++ b/gtrx/gtrx.yaml @@ -666,7 +666,7 @@ components: drug: ## using order and language from gtrx website for these fields UNII: object.intervention.inxight ## no prefix - pmid: references.pmid ## no prefix + ref_pmid: references.pmid ## no prefix ## commenting out because data-processing / biolink-modeling issues # type_of_intervention: object.intervention.int_class # intervention_MUST_be_started_within: object.timeframe @@ -679,7 +679,7 @@ components: # clinical_summary: subject.clinical_summary disease: OMIM: subject.omim ## no prefix - pmid: references.pmid ## no prefix + ref_pmid: references.pmid ## no prefix ## commenting out because data-processing / biolink-modeling issues # type_of_intervention: object.intervention.int_class # intervention_MUST_be_started_within: object.timeframe diff --git a/mychem.info/openapi_full.yml b/mychem.info/openapi_full.yml index b3f75de3..a4a69997 100644 --- a/mychem.info/openapi_full.yml +++ b/mychem.info/openapi_full.yml @@ -631,7 +631,7 @@ components: RHEA: chebi.xrefs.rhea drugMechChembl_EnsemblOutput: ENSEMBL: chembl.drug_mechanisms.target_components.ensembl_gene ## no prefix - pmid: chembl.drug_mechanisms.mechanism_refs.PubMed ## no prefix + ref_pmid: chembl.drug_mechanisms.mechanism_refs.PubMed ## no prefix output_name: chembl.drug_mechanisms.target_name ## commenting out because data-processing / biolink-modeling issues # chembl_drug_action_type: chembl.drug_mechanisms.action_type @@ -645,7 +645,7 @@ components: input_name: chembl.drug_mechanisms.target_name drugMechChembl_UniprotOutput: UniProtKB: chembl.drug_mechanisms.target_components.uniprot ## no prefix - pmid: chembl.drug_mechanisms.mechanism_refs.PubMed ## no prefix + ref_pmid: chembl.drug_mechanisms.mechanism_refs.PubMed ## no prefix output_name: chembl.drug_mechanisms.target_name ## commenting out because data-processing / biolink-modeling issues # chembl_drug_action_type: chembl.drug_mechanisms.action_type diff --git a/mydisease.info/smartapi.yaml b/mydisease.info/smartapi.yaml index 4f1ac011..b3dc89e6 100644 --- a/mydisease.info/smartapi.yaml +++ b/mydisease.info/smartapi.yaml @@ -605,7 +605,7 @@ components: ## not including "name" field since BTE isn't ingesting / using it to annotate nodes... disease-gene: NCBIGene: disgenet.genes_related_to_disease.gene_id ## no prefix - pmid: disgenet.genes_related_to_disease.pubmed ## no prefix + ref_pmid: disgenet.genes_related_to_disease.pubmed ## no prefix ## commenting out because data-processing / biolink-modeling issues # disgenet_source: disgenet.genes_related_to_disease.source # ## could remove "disgenet-" prefix from the key @@ -616,7 +616,7 @@ components: # disgenet-score: disgenet.genes_related_to_disease.score disease-variant: DBSNP: disgenet.variants_related_to_disease.rsid ## no prefix - pmid: disgenet.variants_related_to_disease.pubmed ## no prefix + ref_pmid: disgenet.variants_related_to_disease.pubmed ## no prefix ## commenting out because data-processing / biolink-modeling issues # disgenet_source: disgenet.variants_related_to_disease.source # ## could remove "disgenet-" prefix from the key @@ -628,7 +628,7 @@ components: disease-phenotype: HP: hpo.phenotype_related_to_disease.hpo_id ## HAS PREFIX (HP) ## note: there are 6 reference-related fields (parser created based on ID namespace) - pmid: hpo.phenotype_related_to_disease.pmid_refs ## HAS PREFIX (PMID) + ref_pmid: hpo.phenotype_related_to_disease.pmid_refs ## HAS PREFIX (PMID) ## note: there are 4 frequency-related fields (parser created based on different data types) "biolink:has_quotient": hpo.phenotype_related_to_disease.numeric_freq ## decimal freq "biolink:frequency_qualifier": hpo.phenotype_related_to_disease.hp_freq ## HP ontology freq term @@ -652,7 +652,7 @@ components: # hp_sex: hpo.phenotype_related_to_disease.sex disease-chemical: MESH: ctd.chemical_related_to_disease.mesh_chemical_id ## no prefix - pmid: ctd.chemical_related_to_disease.pubmed ## no prefix + ref_pmid: ctd.chemical_related_to_disease.pubmed ## no prefix ## commenting out because data-processing / biolink-modeling issues # # name: ctd.chemical_related_to_disease.chemical_name # ## direct_evidence has two values, 'marker/mechanism' or 'therapeutic' diff --git a/mygene.info/openapi_full.yml b/mygene.info/openapi_full.yml index 1ed6773c..9496ff08 100644 --- a/mygene.info/openapi_full.yml +++ b/mygene.info/openapi_full.yml @@ -1235,19 +1235,19 @@ components: output_name: pathway.biocarta.name biologicalProcess: GO: go.BP.id ## HAS PREFIX (GO) - pmid: go.BP.pubmed + ref_pmid: go.BP.pubmed ## commenting out because data-processing / biolink-modeling issues # evidence: go.BP.evidence ## categorical variable? # go_qualifier: go.BP.qualifier ## seems to be like a relation molecularFunction: GO: go.MF.id ## HAS PREFIX (GO) - pmid: go.MF.pubmed + ref_pmid: go.MF.pubmed ## commenting out because data-processing / biolink-modeling issues # evidence: go.MF.evidence ## categorical variable? # go_qualifier: go.MF.qualifier ## seems to be like a relation cellularComponent: GO: go.CC.id ## HAS PREFIX (GO) - pmid: go.CC.pubmed + ref_pmid: go.CC.pubmed ## commenting out because data-processing / biolink-modeling issues # evidence: go.CC.evidence ## categorical variable? # go_qualifier: go.CC.qualifier ## seems to be like a relation diff --git a/myvariant.info/openapi_full.yml b/myvariant.info/openapi_full.yml index 9d80b4cd..5bc01922 100644 --- a/myvariant.info/openapi_full.yml +++ b/myvariant.info/openapi_full.yml @@ -615,7 +615,7 @@ components: x-bte-response-mapping: civic-geneDisease: DOID: civic.evidence_items.disease.doid - pmid: civic.evidence_items.source.pubmed ## no prefix + ref_pmid: civic.evidence_items.source.pubmed ## no prefix ## commenting out because data-processing / biolink-modeling issues # ## categorical var / relation # civic_clinical_significance: civic.evidence_items.clinical_significance @@ -641,7 +641,7 @@ components: DOID: civic.evidence_items.disease.doid ## variant name input_name: _id - pmid: civic.evidence_items.source.pubmed ## no prefix + ref_pmid: civic.evidence_items.source.pubmed ## no prefix ## commenting out because data-processing / biolink-modeling issues # ## categorical var / relation # civic_clinical_significance: civic.evidence_items.clinical_significance @@ -704,7 +704,7 @@ components: input_name: _id ## variant name ## commenting out because data-processing / biolink-modeling issues ## not taking notes on a bunch of fields about the gene and variant - # pmid: docm.pubmed_id ## no prefix. issue: lists are ", "-delimited strings + # ref_pmid: docm.pubmed_id ## no prefix. issue: lists are ", "-delimited strings # docm_source: docm.source ## issue: sometimes it's just the value "-" or `null` # source_url: docm.url ##: sometimes it's just `null` # variant_consequence_type: docm.trv_type diff --git a/pharmgkb/smartapi.yaml b/pharmgkb/smartapi.yaml index 2f911001..c6d2f73e 100644 --- a/pharmgkb/smartapi.yaml +++ b/pharmgkb/smartapi.yaml @@ -1936,34 +1936,34 @@ components: "PHARMGKB.CHEMICAL": data.obj2Id output_name: data.obj2Name input_name: data.obj1Name - pmid: data.pmid ## no prefix + ref_pmid: data.pmid ## no prefix ## commenting out because data-processing / biolink-modeling issues # pharmgkb_source_of_connection: data.relType connection-obj-pathway: "PHARMGKB.PATHWAYS": data.obj2Id output_name: data.obj2Name input_name: data.obj1Name - pmid: data.pmid + ref_pmid: data.pmid ## commenting out because data-processing / biolink-modeling issues # pharmgkb_source_of_connection: data.relType connection-obj-disease: "PHARMGKB.DISEASE": data.obj2Id output_name: data.obj2Name input_name: data.obj1Name - pmid: data.pmid + ref_pmid: data.pmid ## commenting out because data-processing / biolink-modeling issues # pharmgkb_source_of_connection: data.relType connection-obj-gene: "PHARMGKB.GENE": data.obj2Id output_name: data.obj2Name input_name: data.obj1Name - pmid: data.pmid + ref_pmid: data.pmid ## commenting out because data-processing / biolink-modeling issues # pharmgkb_source_of_connection: data.relType connection-obj-dbsnp: DBSNP: data.obj2Name ## DBSNP rs ID is put there input_name: data.obj1Name - pmid: data.pmid + ref_pmid: data.pmid ## commenting out because data-processing / biolink-modeling issues # pharmgkb_source_of_connection: data.relType pathEnd-chem: diff --git a/rhea/smartapi.yaml b/rhea/smartapi.yaml index 5acde2c9..e3e2fe93 100644 --- a/rhea/smartapi.yaml +++ b/rhea/smartapi.yaml @@ -766,35 +766,35 @@ components: x-bte-response-mapping: side_l-object: CHEBI: side_l.chebi_id ## has CHEBI prefix - pmid: citations ## has PMID prefix + ref_pmid: citations ## has PMID prefix ## commenting out because data-processing / biolink-modeling issues # equation: equation # is_transport: is_transport # reaction_status: status side_r-object: CHEBI: side_r.chebi_id ## has CHEBI prefix - pmid: citations ## has PMID prefix + ref_pmid: citations ## has PMID prefix ## commenting out because data-processing / biolink-modeling issues # equation: equation # is_transport: is_transport # reaction_status: status side_l_reactive-object: CHEBI: side_l.reactive_parts.chebi_id ## has CHEBI prefix - pmid: citations ## has PMID prefix + ref_pmid: citations ## has PMID prefix ## commenting out because data-processing / biolink-modeling issues # equation: equation # is_transport: is_transport # reaction_status: status side_r_reactive-object: CHEBI: side_r.reactive_parts.chebi_id ## has CHEBI prefix - pmid: citations ## has PMID prefix + ref_pmid: citations ## has PMID prefix ## commenting out because data-processing / biolink-modeling issues # equation: equation # is_transport: is_transport # reaction_status: status reaction-object: RHEA: _id ## has RHEA prefix - pmid: citations ## has PMID prefix + ref_pmid: citations ## has PMID prefix ## commenting out because data-processing / biolink-modeling issues # equation: equation # is_transport: is_transport diff --git a/semmeddb/smartapi.yaml b/semmeddb/smartapi.yaml index 0b20faf2..005dbad0 100644 --- a/semmeddb/smartapi.yaml +++ b/semmeddb/smartapi.yaml @@ -3125,7 +3125,7 @@ components: x-bte-response-mapping: umls-obj: UMLS: object.umls ## no prefix - pmid: predication.pmid ## no prefix + ref_pmid: predication.pmid ## no prefix "biolink:supporting_text": predication.sentence "biolink:original_subject": subject.umls "biolink:original_object": object.umls @@ -3137,7 +3137,7 @@ components: # "biolink:original_predicate": predicate umls-subj: UMLS: subject.umls ## no prefix - pmid: predication.pmid ## no prefix + ref_pmid: predication.pmid ## no prefix "biolink:supporting_text": predication.sentence "biolink:original_subject": subject.umls "biolink:original_object": object.umls diff --git a/semmeddb/version_without_operations.yaml b/semmeddb/version_without_operations.yaml index 613bd342..d0e52a5d 100644 --- a/semmeddb/version_without_operations.yaml +++ b/semmeddb/version_without_operations.yaml @@ -627,7 +627,7 @@ components: x-bte-response-mapping: umls-obj: UMLS: object.umls ## no prefix - pmid: predication.pmid ## no prefix + ref_pmid: predication.pmid ## no prefix "biolink:supporting_text": predication.sentence "biolink:original_subject": subject.umls "biolink:original_object": object.umls @@ -639,7 +639,7 @@ components: # "biolink:original_predicate": predicate umls-subj: UMLS: subject.umls ## no prefix - pmid: predication.pmid ## no prefix + ref_pmid: predication.pmid ## no prefix "biolink:supporting_text": predication.sentence "biolink:original_subject": subject.umls "biolink:original_object": object.umls From 8c685db80bd02de381f1ae4309f678e1306ad090 Mon Sep 17 00:00:00 2001 From: Colleen Xu Date: Mon, 24 Jul 2023 22:16:48 -0700 Subject: [PATCH 03/11] multiple service provider kps: add edge url info under keyword ref_url --- bindingdb/smartapi.yaml | 8 ++++---- litvar/smartapi.yaml | 3 +-- mychem.info/openapi_full.yml | 12 ++++++++---- mydisease.info/smartapi.yaml | 6 ++++-- mygene.info/openapi_full.yml | 2 +- myvariant.info/openapi_full.yml | 4 ++-- ncats_rare_source/smartapi.yaml | 16 +++++----------- pfocr/smartapi.yaml | 18 +++++++++--------- pharmgkb/smartapi.yaml | 28 ++++++++++++---------------- 9 files changed, 46 insertions(+), 51 deletions(-) diff --git a/bindingdb/smartapi.yaml b/bindingdb/smartapi.yaml index 636dc820..4b7e40cd 100644 --- a/bindingdb/smartapi.yaml +++ b/bindingdb/smartapi.yaml @@ -599,7 +599,7 @@ components: # relation.curation_datasource,relation.pmid,relation.bindingdb_link,relation.article_doi,relation.patent_number fields: >- object.pubchem_cid, - subject.name,relation.pmid + subject.name,relation.pmid,relation.bindingdb_link size: 1000 predicate: physically_interacts_with source: "infores:bindingdb" @@ -629,7 +629,7 @@ components: # relation.curation_datasource,relation.pmid,relation.bindingdb_link,relation.article_doi,relation.patent_number fields: >- subject.uniprot.accession, - subject.name,relation.pmid + subject.name,relation.pmid,relation.bindingdb_link size: 1000 predicate: physically_interacts_with source: "infores:bindingdb" @@ -643,19 +643,19 @@ components: "PUBCHEM.COMPOUND": object.pubchem_cid ## no prefix "biolink:original_subject": subject.name ## was called "Target Name Assigned by Curator or DataSource" ref_pmid: relation.pmid ## no prefix + ref_url: relation.bindingdb_link ## commenting out because data-processing / biolink-modeling issues # in_taxon: subject.organism ## was called "Target Source Organism According to Curator or DataSource" # bindingdb_curation_datasource: relation.curation_datasource ## Curation/DataSource - # "biolink:source_web_page": relation.bindingdb_link # article_doi: relation.article_doi # patent_number: relation.patent_number uniprot-subject: UniProtKB: subject.uniprot.accession ## no prefix "biolink:original_subject": subject.name ref_pmid: relation.pmid ## no prefix + ref_url: relation.bindingdb_link ## commenting out because data-processing / biolink-modeling issues # in_taxon: subject.organism # bindingdb_curation_datasource: relation.curation_datasource - # "biolink:source_web_page": relation.bindingdb_link # article_doi: relation.article_doi # patent_number: relation.patent_number diff --git a/litvar/smartapi.yaml b/litvar/smartapi.yaml index 2976a883..53293991 100644 --- a/litvar/smartapi.yaml +++ b/litvar/smartapi.yaml @@ -69,5 +69,4 @@ components: x-bte-response-mapping: variant_located_in_gene: NCBIGene: gene.id ## no prefix - ## commenting out because data-processing / biolink-modeling issues - # "biolink:source_web_page": links.url + ref_url: links.url diff --git a/mychem.info/openapi_full.yml b/mychem.info/openapi_full.yml index a4a69997..ed881112 100644 --- a/mychem.info/openapi_full.yml +++ b/mychem.info/openapi_full.yml @@ -632,11 +632,11 @@ components: drugMechChembl_EnsemblOutput: ENSEMBL: chembl.drug_mechanisms.target_components.ensembl_gene ## no prefix ref_pmid: chembl.drug_mechanisms.mechanism_refs.PubMed ## no prefix + ref_url: chembl.drug_mechanisms.mechanism_refs.url output_name: chembl.drug_mechanisms.target_name ## commenting out because data-processing / biolink-modeling issues # chembl_drug_action_type: chembl.drug_mechanisms.action_type # chembl_binding_site_name: chembl.drug_mechanisms.binding_site_name - # reference_url: chembl.drug_mechanisms.mechanism_refs.url # reference_isbn_note: chembl.drug_mechanisms.mechanism_refs.ISBN # in_taxon: chembl.drug_mechanisms.target_organism # chembl_target_type: chembl.drug_mechanisms.target_type @@ -646,22 +646,22 @@ components: drugMechChembl_UniprotOutput: UniProtKB: chembl.drug_mechanisms.target_components.uniprot ## no prefix ref_pmid: chembl.drug_mechanisms.mechanism_refs.PubMed ## no prefix + ref_url: chembl.drug_mechanisms.mechanism_refs.url output_name: chembl.drug_mechanisms.target_name ## commenting out because data-processing / biolink-modeling issues # chembl_drug_action_type: chembl.drug_mechanisms.action_type # chembl_binding_site_name: chembl.drug_mechanisms.binding_site_name - # reference_url: chembl.drug_mechanisms.mechanism_refs.url # reference_isbn_note: chembl.drug_mechanisms.mechanism_refs.ISBN # in_taxon: chembl.drug_mechanisms.target_organism # chembl_target_type: chembl.drug_mechanisms.target_type chembl-treats: MESH: chembl.drug_indications.mesh_id + ref_url: chembl.drug_indications.indication_refs.url ## commenting out because data-processing / biolink-modeling issues # ## edge attributes # max_clinical_phase_for_indication: chembl.drug_indications.max_phase_for_ind # year_first_approved: chembl.drug_indications.first_approval # ## provenance-related field. Sources are ATC, ClinicalTrial, DailyMed, FDA - # "biolink:source_web_page": chembl.drug_indications.indication_refs.url # chembl_source: chembl.drug_indications.indication_refs.type chembl: "CHEMBL.COMPOUND": chembl.molecule_chembl_id ## no prefix @@ -903,6 +903,7 @@ components: # chembl.drug_mechanisms.target_type fields: >- chembl.drug_mechanisms.target_components.ensembl_gene, + chembl.drug_mechanisms.mechanism_refs.url, chembl.drug_mechanisms.mechanism_refs.PubMed, chembl.drug_mechanisms.target_name size: 1000 ## note size limit; added just in case @@ -968,6 +969,7 @@ components: # chembl.drug_mechanisms.target_type fields: >- chembl.drug_mechanisms.target_components.uniprot, + chembl.drug_mechanisms.mechanism_refs.url, chembl.drug_mechanisms.mechanism_refs.PubMed, chembl.drug_mechanisms.target_name size: 1000 ## note size limit; added just in case @@ -1026,7 +1028,9 @@ components: # chembl.drug_indications.indication_refs.url, # chembl.drug_indications.indication_refs.type, # chembl.drug_indications.first_approval - fields: chembl.drug_indications.mesh_id + fields: >- + chembl.drug_indications.mesh_id, + chembl.drug_indications.indication_refs.url size: 1000 ## note size limit; added just in case predicate: treats source: "infores:chembl" diff --git a/mydisease.info/smartapi.yaml b/mydisease.info/smartapi.yaml index b3dc89e6..1f7e467e 100644 --- a/mydisease.info/smartapi.yaml +++ b/mydisease.info/smartapi.yaml @@ -628,7 +628,8 @@ components: disease-phenotype: HP: hpo.phenotype_related_to_disease.hpo_id ## HAS PREFIX (HP) ## note: there are 6 reference-related fields (parser created based on ID namespace) - ref_pmid: hpo.phenotype_related_to_disease.pmid_refs ## HAS PREFIX (PMID) + ref_pmid: hpo.phenotype_related_to_disease.pmid_refs ## HAS PREFIX (PMID) + ref_url: hpo.phenotype_related_to_disease.website_refs ## note: there are 4 frequency-related fields (parser created based on different data types) "biolink:has_quotient": hpo.phenotype_related_to_disease.numeric_freq ## decimal freq "biolink:frequency_qualifier": hpo.phenotype_related_to_disease.hp_freq ## HP ontology freq term @@ -637,7 +638,6 @@ components: ## commenting out because data-processing / biolink-modeling issues # ## note: there are 6 reference-related fields (parser created based on ID namespace) # isbn_refs: hpo.phenotype_related_to_disease.isbn_refs ## HAS PREFIX (ISBN) - # "biolink:source_web_page": hpo.phenotype_related_to_disease.website_refs ## no prefix # decipher_refs: hpo.phenotype_related_to_disease.decipher_refs ## HAS PREFIX (DECIPHER) # omim_refs: hpo.phenotype_related_to_disease.omim_refs ## HAS PREFIX (OMIM) # orphanet_refs: hpo.phenotype_related_to_disease.orphanet_refs ## HAS PREFIX (ORPHANET) @@ -809,6 +809,7 @@ components: fields: >- hpo.phenotype_related_to_disease.hpo_id, hpo.phenotype_related_to_disease.pmid_refs, + hpo.phenotype_related_to_disease.website_refs, hpo.phenotype_related_to_disease.numeric_freq, hpo.phenotype_related_to_disease.hp_freq, hpo.phenotype_related_to_disease.freq_numerator, @@ -858,6 +859,7 @@ components: fields: >- hpo.phenotype_related_to_disease.hpo_id, hpo.phenotype_related_to_disease.pmid_refs, + hpo.phenotype_related_to_disease.website_refs, hpo.phenotype_related_to_disease.numeric_freq, hpo.phenotype_related_to_disease.hp_freq, hpo.phenotype_related_to_disease.freq_numerator, diff --git a/mygene.info/openapi_full.yml b/mygene.info/openapi_full.yml index 9496ff08..d31bf75e 100644 --- a/mygene.info/openapi_full.yml +++ b/mygene.info/openapi_full.yml @@ -1253,10 +1253,10 @@ components: # go_qualifier: go.CC.qualifier ## seems to be like a relation clingen: MONDO: clingen.clinical_validity.mondo ## HAS PREFIX (MONDO) + ref_url: clingen.clinical_validity.online_report ## commenting out because data-processing / biolink-modeling issues # ## possible values for classification: definitive, moderate, limited, disputed, refuted (!!!), no known disease relationship (!!!) # clingen_clinical_validity_classification: clingen.clinical_validity.classification - # "biolink:source_web_page": clingen.clinical_validity.online_report pantherMGI: MGI: pantherdb.ortholog.MGI ## no prefix ## commenting out because data-processing / biolink-modeling issues diff --git a/myvariant.info/openapi_full.yml b/myvariant.info/openapi_full.yml index 5bc01922..54e87d37 100644 --- a/myvariant.info/openapi_full.yml +++ b/myvariant.info/openapi_full.yml @@ -702,11 +702,11 @@ components: docm-disease-variant-start: DOID: docm.doid input_name: _id ## variant name + ref_url: docm.url ## issue: sometimes it's just `null` ## commenting out because data-processing / biolink-modeling issues ## not taking notes on a bunch of fields about the gene and variant # ref_pmid: docm.pubmed_id ## no prefix. issue: lists are ", "-delimited strings # docm_source: docm.source ## issue: sometimes it's just the value "-" or `null` - # source_url: docm.url ##: sometimes it's just `null` # variant_consequence_type: docm.trv_type # variant_type: docm.type # docm_variant_in_gene: docm.genename @@ -1138,7 +1138,7 @@ components: # docm.doid, # _id, # docm.genename - fields: docm.doid,_id + fields: docm.doid,_id,docm.url size: 1000 ## note size limit; added just in case predicate: related_to ## it's curated but there's no relationship info... diff --git a/ncats_rare_source/smartapi.yaml b/ncats_rare_source/smartapi.yaml index 22bf2e70..5133ff61 100644 --- a/ncats_rare_source/smartapi.yaml +++ b/ncats_rare_source/smartapi.yaml @@ -602,10 +602,8 @@ components: - id: ORPHANET semantic: Disease parameters: - ## commenting out because data-processing / biolink-modeling issues ## orphanet ID has no prefix - # fields: raresource.disease.orphanet,raresource.disease.cooccurrence_url - fields: raresource.disease.orphanet + fields: raresource.disease.orphanet,raresource.disease.cooccurrence_url size: 1000 ## note size limit predicate: gene_associated_with_condition source: "infores:rare-source" @@ -653,10 +651,8 @@ components: - id: UMLS semantic: Disease parameters: - ## commenting out because data-processing / biolink-modeling issues ## umls ID has no prefix - # fields: raresource.disease.umls,raresource.disease.cooccurrence_url - fields: raresource.disease.umls + fields: raresource.disease.umls,raresource.disease.cooccurrence_url size: 1000 ## note size limit predicate: gene_associated_with_condition source: "infores:rare-source" @@ -697,13 +693,11 @@ components: ## when they're supposed to show up only on the edge they correspond to diseaseOrphanet-object: ORPHANET: raresource.disease.orphanet ## no prefix - ## commenting out because data-processing / biolink-modeling issues - # "biolink:xref": raresource.disease.cooccurrence_url - # ## this url leads to a webpage with literature supporting the gene-disease relationship + ref_url: raresource.disease.cooccurrence_url + ## this url leads to a webpage with literature supporting the gene-disease relationship diseaseUMLS-object: UMLS: raresource.disease.umls ## no prefix - ## commenting out because data-processing / biolink-modeling issues - # "biolink:xref": raresource.disease.cooccurrence_url + ref_url: raresource.disease.cooccurrence_url gene-object: NCBIGene: entrezgene ## no prefix output_name: symbol ## SRI Node Norm sometimes doesn't know the NCBIGene name. Using "gene" symbol as name diff --git a/pfocr/smartapi.yaml b/pfocr/smartapi.yaml index 71925022..7da22f32 100644 --- a/pfocr/smartapi.yaml +++ b/pfocr/smartapi.yaml @@ -598,7 +598,7 @@ components: # fields: >- # associatedWith.mentions.chemicals.mesh, # associatedWith.figureUrl,associatedWith.pmc,associatedWith.title - fields: associatedWith.mentions.chemicals.mesh + fields: associatedWith.mentions.chemicals.mesh,associatedWith.figureUrl size: 1000 predicate: occurs_together_in_literature_with source: "infores:pfocr" @@ -628,7 +628,7 @@ components: # fields: >- # associatedWith.mentions.genes.ncbigene, # associatedWith.figureUrl,associatedWith.pmc,associatedWith.title - fields: associatedWith.mentions.genes.ncbigene + fields: associatedWith.mentions.genes.ncbigene,associatedWith.figureUrl size: 1000 predicate: occurs_together_in_literature_with source: "infores:pfocr" @@ -660,7 +660,7 @@ components: # fields: >- # associatedWith.mentions.chemicals.mesh, # associatedWith.figureUrl,associatedWith.pmc,associatedWith.title - fields: associatedWith.mentions.chemicals.mesh + fields: associatedWith.mentions.chemicals.mesh,associatedWith.figureUrl size: 1000 predicate: occurs_together_in_literature_with source: "infores:pfocr" @@ -690,7 +690,7 @@ components: # fields: >- # associatedWith.mentions.diseases.mesh, # associatedWith.figureUrl,associatedWith.pmc,associatedWith.title - fields: associatedWith.mentions.diseases.mesh + fields: associatedWith.mentions.diseases.mesh,associatedWith.figureUrl size: 1000 predicate: occurs_together_in_literature_with source: "infores:pfocr" @@ -722,7 +722,7 @@ components: # fields: >- # associatedWith.mentions.diseases.mesh, # associatedWith.figureUrl,associatedWith.pmc,associatedWith.title - fields: associatedWith.mentions.genes.ncbigene + fields: associatedWith.mentions.genes.ncbigene,associatedWith.figureUrl size: 1000 predicate: occurs_together_in_literature_with source: "infores:pfocr" @@ -752,7 +752,7 @@ components: # fields: >- # associatedWith.mentions.diseases.mesh, # associatedWith.figureUrl,associatedWith.pmc,associatedWith.title - fields: associatedWith.mentions.diseases.mesh + fields: associatedWith.mentions.diseases.mesh,associatedWith.figureUrl size: 1000 predicate: occurs_together_in_literature_with source: "infores:pfocr" @@ -767,19 +767,19 @@ components: ## not easy to make it clear with biolink-model terms: the publication (PMC ID) vs the figure (title and url) chem: MESH: associatedWith.mentions.chemicals.mesh ## no prefix + ref_url: associatedWith.figureUrl ## commenting out because data-processing / biolink-modeling issues - # figure_download_url: associatedWith.figureUrl # figure_title: associatedWith.title # pmc_reference: associatedWith.pmc gene: NCBIGene: associatedWith.mentions.genes.ncbigene ## no prefix + ref_url: associatedWith.figureUrl ## commenting out because data-processing / biolink-modeling issues - # figure_download_url: associatedWith.figureUrl # figure_title: associatedWith.title # pmc_reference: associatedWith.pmc disease: MESH: associatedWith.mentions.diseases.mesh ## no prefix + ref_url: associatedWith.figureUrl ## commenting out because data-processing / biolink-modeling issues - # figure_download_url: associatedWith.figureUrl # figure_title: associatedWith.title # pmc_reference: associatedWith.pmc diff --git a/pharmgkb/smartapi.yaml b/pharmgkb/smartapi.yaml index c6d2f73e..4f3c59e5 100644 --- a/pharmgkb/smartapi.yaml +++ b/pharmgkb/smartapi.yaml @@ -1988,15 +1988,14 @@ components: input_name: data.name guidelineEnd-gene: "PHARMGKB.GENE": data.relatedGenes.id - ## guideline annotation info - "biolink:supporting_text": data.summaryMarkdown.html + ref_url: data.literature._sameAs ## in responses I've reviewed, this is always a url (sometimes an expanded PMID, PMCID) ## commenting out because data-processing / biolink-modeling issues # ## related gene alleles # related_gene_alleles: data.relatedAlleles.symbol # ## provenance - # guideline_literature_urls: data.literature._sameAs # clinical_guideline_source: data.source ## probably an enum of {cpic, dpwg, pro} # ## guideline annotation info + # guideline_summary: data.summaryMarkdown.html # clinical_guideline_name: data.name # flag_has_recommendation: data.recommendation # flag_has_alternative_drug_info: data.alternateDrugAvailable @@ -2006,15 +2005,14 @@ components: # flag_has_pediatric_information: data.pediatric guidelineEnd-chem: "PHARMGKB.CHEMICAL": data.relatedChemicals.id - ## guideline annotation info - "biolink:supporting_text": data.summaryMarkdown.html + ref_url: data.literature._sameAs ## in responses I've reviewed, this is always a url (sometimes an expanded PMID, PMCID) ## commenting out because data-processing / biolink-modeling issues # ## related gene alleles # related_gene_alleles: data.relatedAlleles.symbol # ## provenance - # guideline_literature_urls: data.literature._sameAs # clinical_guideline_source: data.source ## probably an enum of {cpic, dpwg, pro} # ## guideline annotation info + # guideline_summary: data.summaryMarkdown.html # clinical_guideline_name: data.name # flag_has_recommendation: data.recommendation # flag_has_alternative_drug_info: data.alternateDrugAvailable @@ -2025,15 +2023,14 @@ components: labelEnd-gene: ## not sure if prescribingGenes provides different info or not. using relatedGenes section instead "PHARMGKB.GENE": data.relatedGenes.id - ## label annotation info - "biolink:supporting_text": data.summaryMarkdown.html + ref_url: data.literature._sameAs ## in responses I've reviewed, this is always a url ## commenting out because data-processing / biolink-modeling issues # ## related gene alleles # related_gene_alleles: data.relatedAlleles.symbol # ## provenance - # label_literature_urls: data.literature._sameAs # label_source: data.source ## probably an enum of {fda, ema, pmda, hcsc} # ## label annotation info + # label_summary: data.summaryMarkdown.html # label_title: data.name # pgx_level: data.testing.term # flag_has_alternative_drug_info: data.alternateDrugAvailable @@ -2042,15 +2039,14 @@ components: # flag_has_pediatric_information: data.pediatric labelEnd-chem: "PHARMGKB.CHEMICAL": data.relatedChemicals.id - ## label annotation info - "biolink:supporting_text": data.summaryMarkdown.html + ref_url: data.literature._sameAs ## in responses I've reviewed, this is always a url ## commenting out because data-processing / biolink-modeling issues # ## related gene alleles # related_gene_alleles: data.relatedAlleles.symbol # ## provenance - # label_literature_urls: data.literature._sameAs # label_source: data.source ## probably an enum of {fda, ema, pmda, hcsc} # ## label annotation info + # label_summary: data.summaryMarkdown.html # label_title: data.name # pgx_level: data.testing.term # flag_has_alternative_drug_info: data.alternateDrugAvailable @@ -2087,12 +2083,12 @@ components: variantAnnotEnd-chem: "PHARMGKB.CHEMICAL": data.relatedChemicals.id ## provenance - "biolink:supporting_text": data.sentence + ref_url: data.literature._sameAs ## in responses I've reviewed, this is always a url ## commenting out because data-processing / biolink-modeling issues # related_genes: data.location.genes.symbol # flag_significant_association: data.significance.term ## yes/no values? # ## provenance - # annotation_literature_urls: data.literature._sameAs + # pharmgkb_sentence_summary: data.sentence # description: data.description # ## phenotypic effect # phenotype_name: data.phenotypes.phenotype @@ -2104,12 +2100,12 @@ components: variantAnnotEnd-variant: DBSNP: data.location.rsid ## provenance - "biolink:supporting_text": data.sentence + ref_url: data.literature._sameAs ## in responses I've reviewed, this is always a url ## commenting out because data-processing / biolink-modeling issues # related_genes: data.location.genes.symbol # flag_significant_association: data.significance.term ## yes/no values? # ## provenance - # annotation_literature_urls: data.literature._sameAs + # pharmgkb_sentence_summary: data.sentence # description: data.description # ## phenotypic effect # phenotype_name: data.phenotypes.phenotype From ad41f3147dded47900531e1805c4096b652c751b Mon Sep 17 00:00:00 2001 From: Colleen Xu Date: Tue, 25 Jul 2023 00:04:11 -0700 Subject: [PATCH 04/11] mychem,myvariant,pharmgkb: expand annotation beyond urls, add comments when urls could be expansions of curies --- mychem.info/openapi_full.yml | 56 +++++++++++++++++++++++++-------- myvariant.info/openapi_full.yml | 2 +- pharmgkb/smartapi.yaml | 12 +++---- 3 files changed, 50 insertions(+), 20 deletions(-) diff --git a/mychem.info/openapi_full.yml b/mychem.info/openapi_full.yml index ed881112..fbdac44b 100644 --- a/mychem.info/openapi_full.yml +++ b/mychem.info/openapi_full.yml @@ -630,39 +630,63 @@ components: chebiXrefs-rhea: RHEA: chebi.xrefs.rhea drugMechChembl_EnsemblOutput: - ENSEMBL: chembl.drug_mechanisms.target_components.ensembl_gene ## no prefix - ref_pmid: chembl.drug_mechanisms.mechanism_refs.PubMed ## no prefix + ENSEMBL: chembl.drug_mechanisms.target_components.ensembl_gene ## no prefix + ref_pmid: chembl.drug_mechanisms.mechanism_refs.PubMed ## no prefix + ref_clinicaltrials: chembl.drug_mechanisms.mechanism_refs.ClinicalTrials ## no prefix + ref_doi: chembl.drug_mechanisms.mechanism_refs.DOI ## no prefix + ref_pmc: chembl.drug_mechanisms.mechanism_refs.PMC ## no prefix (europepcm IDs) + ## this url field will include expanded PMID / clinicaltrials / doi / PMC (aka duplicates!) + ## but is required for other references: + ## DailyMed, Expert, FDA, ISBN, + ## IUPHAR, InterPro, KEGG, Other, + ## Patent, PubChem, UniProt, Wikipedia + ## notes on some specific fields: + ## - chembl.drug_mechanisms.mechanism_refs.ISBN: includes ID and page number + ## - chembl.drug_mechanisms.mechanism_refs.Other: seem to be urls + ## - chembl.drug_mechanisms.mechanism_refs.Patent: related urls seem to be from surechembl + ## - chembl.drug_mechanisms.mechanism_refs.PubMed: related urls seem to be from europepcm... ref_url: chembl.drug_mechanisms.mechanism_refs.url output_name: chembl.drug_mechanisms.target_name ## commenting out because data-processing / biolink-modeling issues # chembl_drug_action_type: chembl.drug_mechanisms.action_type # chembl_binding_site_name: chembl.drug_mechanisms.binding_site_name - # reference_isbn_note: chembl.drug_mechanisms.mechanism_refs.ISBN # in_taxon: chembl.drug_mechanisms.target_organism # chembl_target_type: chembl.drug_mechanisms.target_type drugMechChembl-rev: "CHEMBL.COMPOUND": chembl.molecule_chembl_id ## no prefix input_name: chembl.drug_mechanisms.target_name drugMechChembl_UniprotOutput: - UniProtKB: chembl.drug_mechanisms.target_components.uniprot ## no prefix - ref_pmid: chembl.drug_mechanisms.mechanism_refs.PubMed ## no prefix + UniProtKB: chembl.drug_mechanisms.target_components.uniprot ## no prefix + ref_pmid: chembl.drug_mechanisms.mechanism_refs.PubMed ## no prefix + ref_clinicaltrials: chembl.drug_mechanisms.mechanism_refs.ClinicalTrials ## no prefix + ref_doi: chembl.drug_mechanisms.mechanism_refs.DOI ## no prefix + ref_pmc: chembl.drug_mechanisms.mechanism_refs.PMC ## no prefix (europepcm IDs) + ## this url field will include expanded PMID / clinicaltrials / doi / PMC (aka duplicates!) + ## but is required for other references: + ## DailyMed, Expert, FDA, ISBN, + ## IUPHAR, InterPro, KEGG, Other, + ## Patent, PubChem, UniProt, Wikipedia + ## notes on some specific fields: + ## - chembl.drug_mechanisms.mechanism_refs.ISBN: includes ID and page number + ## - chembl.drug_mechanisms.mechanism_refs.Other: seem to be urls + ## - chembl.drug_mechanisms.mechanism_refs.Patent: related urls seem to be from surechembl + ## - chembl.drug_mechanisms.mechanism_refs.PubMed: related urls seem to be from europepcm... ref_url: chembl.drug_mechanisms.mechanism_refs.url output_name: chembl.drug_mechanisms.target_name ## commenting out because data-processing / biolink-modeling issues # chembl_drug_action_type: chembl.drug_mechanisms.action_type # chembl_binding_site_name: chembl.drug_mechanisms.binding_site_name - # reference_isbn_note: chembl.drug_mechanisms.mechanism_refs.ISBN # in_taxon: chembl.drug_mechanisms.target_organism # chembl_target_type: chembl.drug_mechanisms.target_type chembl-treats: MESH: chembl.drug_indications.mesh_id - ref_url: chembl.drug_indications.indication_refs.url + ref_clinicaltrials: chembl.drug_mechanisms.mechanism_refs.ClinicalTrials ## no prefix + ## this url field will include expanded clinicaltrials (aka duplicates!) + ## but is required for other references: ATC, DailyMed, FDA + ref_url: chembl.drug_mechanisms.mechanism_refs.url ## commenting out because data-processing / biolink-modeling issues - # ## edge attributes # max_clinical_phase_for_indication: chembl.drug_indications.max_phase_for_ind # year_first_approved: chembl.drug_indications.first_approval - # ## provenance-related field. Sources are ATC, ClinicalTrial, DailyMed, FDA - # chembl_source: chembl.drug_indications.indication_refs.type chembl: "CHEMBL.COMPOUND": chembl.molecule_chembl_id ## no prefix drugcentral-bioactivity: @@ -903,8 +927,11 @@ components: # chembl.drug_mechanisms.target_type fields: >- chembl.drug_mechanisms.target_components.ensembl_gene, - chembl.drug_mechanisms.mechanism_refs.url, chembl.drug_mechanisms.mechanism_refs.PubMed, + chembl.drug_mechanisms.mechanism_refs.ClinicalTrials, + chembl.drug_mechanisms.mechanism_refs.DOI, + chembl.drug_mechanisms.mechanism_refs.PMC, + chembl.drug_mechanisms.mechanism_refs.url, chembl.drug_mechanisms.target_name size: 1000 ## note size limit; added just in case ## using the same predicate as dgidb's no-relationship-specified. @@ -969,8 +996,11 @@ components: # chembl.drug_mechanisms.target_type fields: >- chembl.drug_mechanisms.target_components.uniprot, - chembl.drug_mechanisms.mechanism_refs.url, chembl.drug_mechanisms.mechanism_refs.PubMed, + chembl.drug_mechanisms.mechanism_refs.ClinicalTrials, + chembl.drug_mechanisms.mechanism_refs.DOI, + chembl.drug_mechanisms.mechanism_refs.PMC, + chembl.drug_mechanisms.mechanism_refs.url, chembl.drug_mechanisms.target_name size: 1000 ## note size limit; added just in case ## see drugMechChemblEnsembl operation for more info on predicate @@ -1026,10 +1056,10 @@ components: # chembl.drug_indications.mesh_id, # chembl.drug_indications.max_phase_for_ind, # chembl.drug_indications.indication_refs.url, - # chembl.drug_indications.indication_refs.type, # chembl.drug_indications.first_approval fields: >- chembl.drug_indications.mesh_id, + chembl.drug_mechanisms.mechanism_refs.ClinicalTrials, chembl.drug_indications.indication_refs.url size: 1000 ## note size limit; added just in case predicate: treats diff --git a/myvariant.info/openapi_full.yml b/myvariant.info/openapi_full.yml index 54e87d37..0a2368a8 100644 --- a/myvariant.info/openapi_full.yml +++ b/myvariant.info/openapi_full.yml @@ -702,7 +702,7 @@ components: docm-disease-variant-start: DOID: docm.doid input_name: _id ## variant name - ref_url: docm.url ## issue: sometimes it's just `null` + ref_url: docm.url ## only MyCancerGenome urls? Also, an issue: sometimes it's just `null` ## commenting out because data-processing / biolink-modeling issues ## not taking notes on a bunch of fields about the gene and variant # ref_pmid: docm.pubmed_id ## no prefix. issue: lists are ", "-delimited strings diff --git a/pharmgkb/smartapi.yaml b/pharmgkb/smartapi.yaml index 4f3c59e5..03b29a5b 100644 --- a/pharmgkb/smartapi.yaml +++ b/pharmgkb/smartapi.yaml @@ -1988,7 +1988,7 @@ components: input_name: data.name guidelineEnd-gene: "PHARMGKB.GENE": data.relatedGenes.id - ref_url: data.literature._sameAs ## in responses I've reviewed, this is always a url (sometimes an expanded PMID, PMCID) + ref_url: data.literature._sameAs ## in responses I've reviewed, this is always a url - often an expanded PMID or PMCID (NLM) ## commenting out because data-processing / biolink-modeling issues # ## related gene alleles # related_gene_alleles: data.relatedAlleles.symbol @@ -2005,7 +2005,7 @@ components: # flag_has_pediatric_information: data.pediatric guidelineEnd-chem: "PHARMGKB.CHEMICAL": data.relatedChemicals.id - ref_url: data.literature._sameAs ## in responses I've reviewed, this is always a url (sometimes an expanded PMID, PMCID) + ref_url: data.literature._sameAs ## in responses I've reviewed, this is always a url - often an expanded PMID or PMCID (NLM) ## commenting out because data-processing / biolink-modeling issues # ## related gene alleles # related_gene_alleles: data.relatedAlleles.symbol @@ -2023,7 +2023,7 @@ components: labelEnd-gene: ## not sure if prescribingGenes provides different info or not. using relatedGenes section instead "PHARMGKB.GENE": data.relatedGenes.id - ref_url: data.literature._sameAs ## in responses I've reviewed, this is always a url + ref_url: data.literature._sameAs ## in responses I've reviewed, this is always a url (NOT expanded PMID/PMCID) ## commenting out because data-processing / biolink-modeling issues # ## related gene alleles # related_gene_alleles: data.relatedAlleles.symbol @@ -2039,7 +2039,7 @@ components: # flag_has_pediatric_information: data.pediatric labelEnd-chem: "PHARMGKB.CHEMICAL": data.relatedChemicals.id - ref_url: data.literature._sameAs ## in responses I've reviewed, this is always a url + ref_url: data.literature._sameAs ## in responses I've reviewed, this is always a url (NOT expanded PMID/PMCID) ## commenting out because data-processing / biolink-modeling issues # ## related gene alleles # related_gene_alleles: data.relatedAlleles.symbol @@ -2083,7 +2083,7 @@ components: variantAnnotEnd-chem: "PHARMGKB.CHEMICAL": data.relatedChemicals.id ## provenance - ref_url: data.literature._sameAs ## in responses I've reviewed, this is always a url + ref_url: data.literature._sameAs ## in responses I've reviewed, this is always a url that's an expanded PMID or PMCID (NLM) ## commenting out because data-processing / biolink-modeling issues # related_genes: data.location.genes.symbol # flag_significant_association: data.significance.term ## yes/no values? @@ -2100,7 +2100,7 @@ components: variantAnnotEnd-variant: DBSNP: data.location.rsid ## provenance - ref_url: data.literature._sameAs ## in responses I've reviewed, this is always a url + ref_url: data.literature._sameAs ## in responses I've reviewed, this is always a url that's an expanded PMID or PMCID (NLM) ## commenting out because data-processing / biolink-modeling issues # related_genes: data.location.genes.symbol # flag_significant_association: data.significance.term ## yes/no values? From 7ab848f85dc824de4070473734ef268dffa903a6 Mon Sep 17 00:00:00 2001 From: Colleen Xu Date: Tue, 25 Jul 2023 00:09:58 -0700 Subject: [PATCH 05/11] mygene: add field retrieval for ref_url field --- mygene.info/openapi_full.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mygene.info/openapi_full.yml b/mygene.info/openapi_full.yml index d31bf75e..f0662f7c 100644 --- a/mygene.info/openapi_full.yml +++ b/mygene.info/openapi_full.yml @@ -1111,7 +1111,7 @@ components: # clingen.clinical_validity.mondo, # clingen.clinical_validity.classification, # clingen.clinical_validity.online_report - fields: clingen.clinical_validity.mondo + fields: clingen.clinical_validity.mondo,clingen.clinical_validity.online_report species: human size: 1000 ## using related_to because.... From 4ee3bd7a66620d55f50eb0feadb634ba45f51e88 Mon Sep 17 00:00:00 2001 From: Colleen Xu Date: Tue, 25 Jul 2023 16:57:49 -0700 Subject: [PATCH 06/11] multiple service provider kps: add keyword ref_pmcid for PMC fields, adjust comments comments on publications / urls --- mychem.info/openapi_full.yml | 30 ++++------------- mydisease.info/smartapi.yaml | 1 - pfocr/smartapi.yaml | 64 +++++++++++++----------------------- pharmgkb/smartapi.yaml | 24 +++++++++----- 4 files changed, 45 insertions(+), 74 deletions(-) diff --git a/mychem.info/openapi_full.yml b/mychem.info/openapi_full.yml index fbdac44b..9bb3e96c 100644 --- a/mychem.info/openapi_full.yml +++ b/mychem.info/openapi_full.yml @@ -634,8 +634,8 @@ components: ref_pmid: chembl.drug_mechanisms.mechanism_refs.PubMed ## no prefix ref_clinicaltrials: chembl.drug_mechanisms.mechanism_refs.ClinicalTrials ## no prefix ref_doi: chembl.drug_mechanisms.mechanism_refs.DOI ## no prefix - ref_pmc: chembl.drug_mechanisms.mechanism_refs.PMC ## no prefix (europepcm IDs) - ## this url field will include expanded PMID / clinicaltrials / doi / PMC (aka duplicates!) + ref_pmcid: chembl.drug_mechanisms.mechanism_refs.PMC ## no prefix (but IDs start with "PMC") + ## this url field will include expanded PMID / clinicaltrials / doi / PMCID (aka duplicates!) ## but is required for other references: ## DailyMed, Expert, FDA, ISBN, ## IUPHAR, InterPro, KEGG, Other, @@ -656,28 +656,14 @@ components: "CHEMBL.COMPOUND": chembl.molecule_chembl_id ## no prefix input_name: chembl.drug_mechanisms.target_name drugMechChembl_UniprotOutput: + ## basically the same response-mapping as drugMechChembl_EnsemblOutput UniProtKB: chembl.drug_mechanisms.target_components.uniprot ## no prefix ref_pmid: chembl.drug_mechanisms.mechanism_refs.PubMed ## no prefix ref_clinicaltrials: chembl.drug_mechanisms.mechanism_refs.ClinicalTrials ## no prefix ref_doi: chembl.drug_mechanisms.mechanism_refs.DOI ## no prefix - ref_pmc: chembl.drug_mechanisms.mechanism_refs.PMC ## no prefix (europepcm IDs) - ## this url field will include expanded PMID / clinicaltrials / doi / PMC (aka duplicates!) - ## but is required for other references: - ## DailyMed, Expert, FDA, ISBN, - ## IUPHAR, InterPro, KEGG, Other, - ## Patent, PubChem, UniProt, Wikipedia - ## notes on some specific fields: - ## - chembl.drug_mechanisms.mechanism_refs.ISBN: includes ID and page number - ## - chembl.drug_mechanisms.mechanism_refs.Other: seem to be urls - ## - chembl.drug_mechanisms.mechanism_refs.Patent: related urls seem to be from surechembl - ## - chembl.drug_mechanisms.mechanism_refs.PubMed: related urls seem to be from europepcm... + ref_pmcid: chembl.drug_mechanisms.mechanism_refs.PMC ## no prefix (but IDs start with "PMC") ref_url: chembl.drug_mechanisms.mechanism_refs.url output_name: chembl.drug_mechanisms.target_name - ## commenting out because data-processing / biolink-modeling issues - # chembl_drug_action_type: chembl.drug_mechanisms.action_type - # chembl_binding_site_name: chembl.drug_mechanisms.binding_site_name - # in_taxon: chembl.drug_mechanisms.target_organism - # chembl_target_type: chembl.drug_mechanisms.target_type chembl-treats: MESH: chembl.drug_indications.mesh_id ref_clinicaltrials: chembl.drug_mechanisms.mechanism_refs.ClinicalTrials ## no prefix @@ -909,11 +895,7 @@ components: - id: ENSEMBL semantic: Gene parameters: - ## chembl.drug_mechanisms.mechanism_refs.url will get info from: - ## ClinicalTrials, DOI, DailyMed, Expert, FDA, ISBN, IUPHAR, InterPro, KEGG, Other, - ## PMC, Patent, PubChem, Pubmed, UniProt, Wikipedia - ## chembl.drug_mechanisms.mechanism_refs.ISBN will include page number. ex: "9780702034718 PP. 164" - ## chembl.drug_mechanisms.mechanism_refs.PubMed will include only the PMID (no prefix) + ## see response-mapping for more info on fields ## commenting out because data-processing / biolink-modeling issues # fields: >- # chembl.drug_mechanisms.target_components.ensembl_gene, @@ -982,7 +964,7 @@ components: - id: UniProtKB semantic: Gene parameters: - ## see drugMechChemblEnsembl operation for more info on fields + ## see response-mapping drugMechChembl_EnsemblOutput for more info on fields ## commenting out because data-processing / biolink-modeling issues # fields: >- # chembl.drug_mechanisms.target_components.uniprot, diff --git a/mydisease.info/smartapi.yaml b/mydisease.info/smartapi.yaml index 1f7e467e..695a4d1d 100644 --- a/mydisease.info/smartapi.yaml +++ b/mydisease.info/smartapi.yaml @@ -627,7 +627,6 @@ components: # disgenet-score: disgenet.variants_related_to_disease.score disease-phenotype: HP: hpo.phenotype_related_to_disease.hpo_id ## HAS PREFIX (HP) - ## note: there are 6 reference-related fields (parser created based on ID namespace) ref_pmid: hpo.phenotype_related_to_disease.pmid_refs ## HAS PREFIX (PMID) ref_url: hpo.phenotype_related_to_disease.website_refs ## note: there are 4 frequency-related fields (parser created based on different data types) diff --git a/pfocr/smartapi.yaml b/pfocr/smartapi.yaml index 7da22f32..c8efcb4f 100644 --- a/pfocr/smartapi.yaml +++ b/pfocr/smartapi.yaml @@ -594,11 +594,9 @@ components: - id: MESH semantic: SmallMolecule parameters: - ## commenting out because data-processing / biolink-modeling issues - # fields: >- - # associatedWith.mentions.chemicals.mesh, - # associatedWith.figureUrl,associatedWith.pmc,associatedWith.title - fields: associatedWith.mentions.chemicals.mesh,associatedWith.figureUrl + fields: >- + associatedWith.mentions.chemicals.mesh, + associatedWith.figureUrl,associatedWith.pmc size: 1000 predicate: occurs_together_in_literature_with source: "infores:pfocr" @@ -624,11 +622,9 @@ components: - id: NCBIGene semantic: Gene parameters: - ## commenting out because data-processing / biolink-modeling issues - # fields: >- - # associatedWith.mentions.genes.ncbigene, - # associatedWith.figureUrl,associatedWith.pmc,associatedWith.title - fields: associatedWith.mentions.genes.ncbigene,associatedWith.figureUrl + fields: >- + associatedWith.mentions.genes.ncbigene, + associatedWith.figureUrl,associatedWith.pmc size: 1000 predicate: occurs_together_in_literature_with source: "infores:pfocr" @@ -656,11 +652,9 @@ components: - id: MESH semantic: SmallMolecule parameters: - ## commenting out because data-processing / biolink-modeling issues - # fields: >- - # associatedWith.mentions.chemicals.mesh, - # associatedWith.figureUrl,associatedWith.pmc,associatedWith.title - fields: associatedWith.mentions.chemicals.mesh,associatedWith.figureUrl + fields: >- + associatedWith.mentions.chemicals.mesh, + associatedWith.figureUrl,associatedWith.pmc size: 1000 predicate: occurs_together_in_literature_with source: "infores:pfocr" @@ -686,11 +680,9 @@ components: - id: MESH semantic: Disease parameters: - ## commenting out because data-processing / biolink-modeling issues - # fields: >- - # associatedWith.mentions.diseases.mesh, - # associatedWith.figureUrl,associatedWith.pmc,associatedWith.title - fields: associatedWith.mentions.diseases.mesh,associatedWith.figureUrl + fields: >- + associatedWith.mentions.diseases.mesh, + associatedWith.figureUrl,associatedWith.pmc size: 1000 predicate: occurs_together_in_literature_with source: "infores:pfocr" @@ -718,11 +710,9 @@ components: - id: NCBIGene semantic: Gene parameters: - ## commenting out because data-processing / biolink-modeling issues - # fields: >- - # associatedWith.mentions.diseases.mesh, - # associatedWith.figureUrl,associatedWith.pmc,associatedWith.title - fields: associatedWith.mentions.genes.ncbigene,associatedWith.figureUrl + fields: >- + associatedWith.mentions.genes.ncbigene, + associatedWith.figureUrl,associatedWith.pmc size: 1000 predicate: occurs_together_in_literature_with source: "infores:pfocr" @@ -748,11 +738,9 @@ components: - id: MESH semantic: Disease parameters: - ## commenting out because data-processing / biolink-modeling issues - # fields: >- - # associatedWith.mentions.diseases.mesh, - # associatedWith.figureUrl,associatedWith.pmc,associatedWith.title - fields: associatedWith.mentions.diseases.mesh,associatedWith.figureUrl + fields: >- + associatedWith.mentions.diseases.mesh, + associatedWith.figureUrl,associatedWith.pmc size: 1000 predicate: occurs_together_in_literature_with source: "infores:pfocr" @@ -763,23 +751,17 @@ components: # oneOutput: "MESH:D002318" ## Cardiovascular Diseases ## should have 1 figure: https://biothings.ncats.io/pfocr/query?q=associatedWith.mentions.genes.ncbigene:3791%20AND%20associatedWith.mentions.diseases.mesh:D002318 x-bte-response-mapping: - ## pmc_reference kinda matches "biolink:publications". However, it doesn't have a PMC prefix so it doesn't quite have the right value... - ## not easy to make it clear with biolink-model terms: the publication (PMC ID) vs the figure (title and url) + ## not including because because data-processing / biolink-modeling issues + ## - associatedWith.title (title of figure) chem: MESH: associatedWith.mentions.chemicals.mesh ## no prefix ref_url: associatedWith.figureUrl - ## commenting out because data-processing / biolink-modeling issues - # figure_title: associatedWith.title - # pmc_reference: associatedWith.pmc + ref_pmcid: associatedWith.pmc ## no prefix (but IDs start with "PMC") gene: NCBIGene: associatedWith.mentions.genes.ncbigene ## no prefix ref_url: associatedWith.figureUrl - ## commenting out because data-processing / biolink-modeling issues - # figure_title: associatedWith.title - # pmc_reference: associatedWith.pmc + ref_pmcid: associatedWith.pmc disease: MESH: associatedWith.mentions.diseases.mesh ## no prefix ref_url: associatedWith.figureUrl - ## commenting out because data-processing / biolink-modeling issues - # figure_title: associatedWith.title - # pmc_reference: associatedWith.pmc + ref_pmcid: associatedWith.pmc diff --git a/pharmgkb/smartapi.yaml b/pharmgkb/smartapi.yaml index 03b29a5b..835d1b16 100644 --- a/pharmgkb/smartapi.yaml +++ b/pharmgkb/smartapi.yaml @@ -1988,7 +1988,9 @@ components: input_name: data.name guidelineEnd-gene: "PHARMGKB.GENE": data.relatedGenes.id - ref_url: data.literature._sameAs ## in responses I've reviewed, this is always a url - often an expanded PMID or PMCID (NLM) + ## in responses I've reviewed, this is always a url + ## - often an expanded PMID or a PMCID (NLM) like https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3994233 + ref_url: data.literature._sameAs ## commenting out because data-processing / biolink-modeling issues # ## related gene alleles # related_gene_alleles: data.relatedAlleles.symbol @@ -2005,7 +2007,9 @@ components: # flag_has_pediatric_information: data.pediatric guidelineEnd-chem: "PHARMGKB.CHEMICAL": data.relatedChemicals.id - ref_url: data.literature._sameAs ## in responses I've reviewed, this is always a url - often an expanded PMID or PMCID (NLM) + ## in responses I've reviewed, this is always a url + ## - often an expanded PMID or a PMCID (NLM) like https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3994233 + ref_url: data.literature._sameAs ## commenting out because data-processing / biolink-modeling issues # ## related gene alleles # related_gene_alleles: data.relatedAlleles.symbol @@ -2023,7 +2027,8 @@ components: labelEnd-gene: ## not sure if prescribingGenes provides different info or not. using relatedGenes section instead "PHARMGKB.GENE": data.relatedGenes.id - ref_url: data.literature._sameAs ## in responses I've reviewed, this is always a url (NOT expanded PMID/PMCID) + ## in responses I've reviewed, this is always a plain url (NOT an expanded PMID/PMCID) + ref_url: data.literature._sameAs ## commenting out because data-processing / biolink-modeling issues # ## related gene alleles # related_gene_alleles: data.relatedAlleles.symbol @@ -2039,7 +2044,8 @@ components: # flag_has_pediatric_information: data.pediatric labelEnd-chem: "PHARMGKB.CHEMICAL": data.relatedChemicals.id - ref_url: data.literature._sameAs ## in responses I've reviewed, this is always a url (NOT expanded PMID/PMCID) + ## in responses I've reviewed, this is always a plain url (NOT an expanded PMID/PMCID) + ref_url: data.literature._sameAs ## commenting out because data-processing / biolink-modeling issues # ## related gene alleles # related_gene_alleles: data.relatedAlleles.symbol @@ -2082,8 +2088,9 @@ components: # related_diseases: data.relatedDiseases.name variantAnnotEnd-chem: "PHARMGKB.CHEMICAL": data.relatedChemicals.id - ## provenance - ref_url: data.literature._sameAs ## in responses I've reviewed, this is always a url that's an expanded PMID or PMCID (NLM) + ## in responses I've reviewed, this is always a url that's an expanded PMID or + ## a PMCID (NLM) like https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3165308 + ref_url: data.literature._sameAs ## commenting out because data-processing / biolink-modeling issues # related_genes: data.location.genes.symbol # flag_significant_association: data.significance.term ## yes/no values? @@ -2099,8 +2106,9 @@ components: # population_phenotype_name: data.populationPhenotypes.phenotype variantAnnotEnd-variant: DBSNP: data.location.rsid - ## provenance - ref_url: data.literature._sameAs ## in responses I've reviewed, this is always a url that's an expanded PMID or PMCID (NLM) + ## in responses I've reviewed, this is always a url that's an expanded PMID or + ## a PMCID (NLM) like https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3165308 + ref_url: data.literature._sameAs ## commenting out because data-processing / biolink-modeling issues # related_genes: data.location.genes.symbol # flag_significant_association: data.significance.term ## yes/no values? From f281b27d5ce576b11e9b20303337a7e6a7806270 Mon Sep 17 00:00:00 2001 From: Colleen Xu Date: Tue, 25 Jul 2023 17:32:11 -0700 Subject: [PATCH 07/11] mychem,myvariant: add clinicaltrials ref keyword and fields --- mychem.info/openapi_full.yml | 6 +++--- myvariant.info/openapi_full.yml | 21 +++++++++++++-------- 2 files changed, 16 insertions(+), 11 deletions(-) diff --git a/mychem.info/openapi_full.yml b/mychem.info/openapi_full.yml index 9bb3e96c..edc2e0f2 100644 --- a/mychem.info/openapi_full.yml +++ b/mychem.info/openapi_full.yml @@ -666,10 +666,10 @@ components: output_name: chembl.drug_mechanisms.target_name chembl-treats: MESH: chembl.drug_indications.mesh_id - ref_clinicaltrials: chembl.drug_mechanisms.mechanism_refs.ClinicalTrials ## no prefix + ref_clinicaltrials: chembl.drug_indications.indication_refs.ClinicalTrials ## no prefix ## this url field will include expanded clinicaltrials (aka duplicates!) ## but is required for other references: ATC, DailyMed, FDA - ref_url: chembl.drug_mechanisms.mechanism_refs.url + ref_url: chembl.drug_indications.indication_refs.url ## commenting out because data-processing / biolink-modeling issues # max_clinical_phase_for_indication: chembl.drug_indications.max_phase_for_ind # year_first_approved: chembl.drug_indications.first_approval @@ -1041,7 +1041,7 @@ components: # chembl.drug_indications.first_approval fields: >- chembl.drug_indications.mesh_id, - chembl.drug_mechanisms.mechanism_refs.ClinicalTrials, + chembl.drug_indications.indication_refs.ClinicalTrials, chembl.drug_indications.indication_refs.url size: 1000 ## note size limit; added just in case predicate: treats diff --git a/myvariant.info/openapi_full.yml b/myvariant.info/openapi_full.yml index 0a2368a8..27a7f86e 100644 --- a/myvariant.info/openapi_full.yml +++ b/myvariant.info/openapi_full.yml @@ -615,7 +615,8 @@ components: x-bte-response-mapping: civic-geneDisease: DOID: civic.evidence_items.disease.doid - ref_pmid: civic.evidence_items.source.pubmed ## no prefix + ref_pmid: civic.evidence_items.source.pubmed ## no prefix + ref_clinicaltrials: civic.evidence_items.source.clinical_trials.nct_id ## no prefix (ID starts with "NCT") ## commenting out because data-processing / biolink-modeling issues # ## categorical var / relation # civic_clinical_significance: civic.evidence_items.clinical_significance @@ -628,8 +629,6 @@ components: # civic_evidence_direction: civic.evidence_items.evidence_direction # civic_evidence_level: civic.evidence_items.evidence_level # civic_evidence_type: civic.evidence_items.evidence_type - # ## provenance - # clinical_trial_url: civic.evidence_items.source.clinical_trials.clinical_trial_url # ## context: variant involved, could use "biolink:sequence_variant_qualifier" # ## but then ID-namespace would be unclear (this ID doesn't have a prefix) # civic_variant_id: civic.evidence_items.variant_id @@ -641,7 +640,8 @@ components: DOID: civic.evidence_items.disease.doid ## variant name input_name: _id - ref_pmid: civic.evidence_items.source.pubmed ## no prefix + ref_pmid: civic.evidence_items.source.pubmed ## no prefix + ref_clinicaltrials: civic.evidence_items.source.clinical_trials.nct_id ## no prefix (ID starts with "NCT") ## commenting out because data-processing / biolink-modeling issues # ## categorical var / relation # civic_clinical_significance: civic.evidence_items.clinical_significance @@ -656,8 +656,6 @@ components: # civic_evidence_direction: civic.evidence_items.evidence_direction # civic_evidence_level: civic.evidence_items.evidence_level # civic_evidence_type: civic.evidence_items.evidence_type - # ## provenance - # clinical_trial_url: civic.evidence_items.source.clinical_trials.clinical_trial_url # ## context: variant involved was Somatic, unknown... # civic_variant_origin: civic.evidence_items.variant_origin dbsnp-rsid: @@ -749,7 +747,10 @@ components: ## only some records have drug information, and only some drugs have NCIT IDs ## commenting out because data-processing / biolink-modeling issues # fields: civic.evidence_items - fields: civic.evidence_items.disease.doid,civic.evidence_items.source.pubmed + fields: >- + civic.evidence_items.disease.doid, + civic.evidence_items.source.pubmed, + civic.evidence_items.source.clinical_trials.nct_id size: 1000 ## note size limit; added just in case predicate: affects source: "infores:civic" @@ -807,7 +808,11 @@ components: # civic.evidence_items, # civic.entrez_name, # _id - fields: civic.evidence_items.disease.doid,_id,civic.evidence_items.source.pubmed + fields: >- + civic.evidence_items.disease.doid, + _id, + civic.evidence_items.source.pubmed, + civic.evidence_items.source.clinical_trials.nct_id size: 1000 ## note size limit; added just in case predicate: affects source: "infores:civic" From fe2209b067d68efacdd2fcc1045d29255ab14ee0 Mon Sep 17 00:00:00 2001 From: Colleen Xu Date: Tue, 25 Jul 2023 18:21:10 -0700 Subject: [PATCH 08/11] bindingdb: add ref_doi. mychem already annotated for doi --- bindingdb/smartapi.yaml | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/bindingdb/smartapi.yaml b/bindingdb/smartapi.yaml index 4b7e40cd..b481a7c1 100644 --- a/bindingdb/smartapi.yaml +++ b/bindingdb/smartapi.yaml @@ -599,7 +599,7 @@ components: # relation.curation_datasource,relation.pmid,relation.bindingdb_link,relation.article_doi,relation.patent_number fields: >- object.pubchem_cid, - subject.name,relation.pmid,relation.bindingdb_link + subject.name,relation.pmid,relation.bindingdb_link,relation.article_doi size: 1000 predicate: physically_interacts_with source: "infores:bindingdb" @@ -629,7 +629,7 @@ components: # relation.curation_datasource,relation.pmid,relation.bindingdb_link,relation.article_doi,relation.patent_number fields: >- subject.uniprot.accession, - subject.name,relation.pmid,relation.bindingdb_link + subject.name,relation.pmid,relation.bindingdb_link,relation.article_doi size: 1000 predicate: physically_interacts_with source: "infores:bindingdb" @@ -639,23 +639,28 @@ components: # - qInput: "PUBCHEM.COMPOUND:134553288" ## US10736883, Example 387.0 # oneOutput: "UniProtKB:P35414" ## Apelin receptor x-bte-response-mapping: + ## note on references: + ## sometimes the doi + pmid will refer to the same publication (so..."duplicate" references) + ## but there are plenty of cases where relationships have only 1 of these fields: + ## only doi: https://biothings.transltr.io/bindingdb/query?q=_exists_:relation.article_doi%20AND%20(NOT%20_exists_:relation.pmid) + ## only pmid: https://biothings.transltr.io/bindingdb/query?q=_exists_:relation.pmid%20AND%20(NOT%20_exists_:relation.article_doi) pubchem-object: "PUBCHEM.COMPOUND": object.pubchem_cid ## no prefix "biolink:original_subject": subject.name ## was called "Target Name Assigned by Curator or DataSource" ref_pmid: relation.pmid ## no prefix + ref_doi: relation.article_doi ref_url: relation.bindingdb_link ## commenting out because data-processing / biolink-modeling issues # in_taxon: subject.organism ## was called "Target Source Organism According to Curator or DataSource" # bindingdb_curation_datasource: relation.curation_datasource ## Curation/DataSource - # article_doi: relation.article_doi # patent_number: relation.patent_number uniprot-subject: UniProtKB: subject.uniprot.accession ## no prefix "biolink:original_subject": subject.name ref_pmid: relation.pmid ## no prefix + ref_doi: relation.article_doi ref_url: relation.bindingdb_link ## commenting out because data-processing / biolink-modeling issues # in_taxon: subject.organism # bindingdb_curation_datasource: relation.curation_datasource - # article_doi: relation.article_doi # patent_number: relation.patent_number From ca4eca271cb4f1383d904105f1566be9d37d4bca Mon Sep 17 00:00:00 2001 From: Colleen Xu Date: Tue, 25 Jul 2023 18:42:03 -0700 Subject: [PATCH 09/11] mydisease: add ref_isbn --- mydisease.info/smartapi.yaml | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/mydisease.info/smartapi.yaml b/mydisease.info/smartapi.yaml index 695a4d1d..f7a6dd82 100644 --- a/mydisease.info/smartapi.yaml +++ b/mydisease.info/smartapi.yaml @@ -628,6 +628,7 @@ components: disease-phenotype: HP: hpo.phenotype_related_to_disease.hpo_id ## HAS PREFIX (HP) ref_pmid: hpo.phenotype_related_to_disease.pmid_refs ## HAS PREFIX (PMID) + ref_isbn: hpo.phenotype_related_to_disease.isbn_refs ## HAS PREFIX (ISBN) ref_url: hpo.phenotype_related_to_disease.website_refs ## note: there are 4 frequency-related fields (parser created based on different data types) "biolink:has_quotient": hpo.phenotype_related_to_disease.numeric_freq ## decimal freq @@ -636,7 +637,6 @@ components: "biolink:has_total": hpo.phenotype_related_to_disease.freq_denominator ## frequency as a fraction (denominator) ## commenting out because data-processing / biolink-modeling issues # ## note: there are 6 reference-related fields (parser created based on ID namespace) - # isbn_refs: hpo.phenotype_related_to_disease.isbn_refs ## HAS PREFIX (ISBN) # decipher_refs: hpo.phenotype_related_to_disease.decipher_refs ## HAS PREFIX (DECIPHER) # omim_refs: hpo.phenotype_related_to_disease.omim_refs ## HAS PREFIX (OMIM) # orphanet_refs: hpo.phenotype_related_to_disease.orphanet_refs ## HAS PREFIX (ORPHANET) @@ -808,6 +808,7 @@ components: fields: >- hpo.phenotype_related_to_disease.hpo_id, hpo.phenotype_related_to_disease.pmid_refs, + hpo.phenotype_related_to_disease.isbn_refs, hpo.phenotype_related_to_disease.website_refs, hpo.phenotype_related_to_disease.numeric_freq, hpo.phenotype_related_to_disease.hp_freq, @@ -858,6 +859,7 @@ components: fields: >- hpo.phenotype_related_to_disease.hpo_id, hpo.phenotype_related_to_disease.pmid_refs, + hpo.phenotype_related_to_disease.isbn_refs, hpo.phenotype_related_to_disease.website_refs, hpo.phenotype_related_to_disease.numeric_freq, hpo.phenotype_related_to_disease.hp_freq, From 6f7319c3bdbd705719975d277451789211d29a02 Mon Sep 17 00:00:00 2001 From: Colleen Xu Date: Wed, 26 Jul 2023 17:14:51 -0700 Subject: [PATCH 10/11] biolink/monarch api: update to use ref_pmid --- biolink/openapi.yml | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/biolink/openapi.yml b/biolink/openapi.yml index 54883776..bb5d007d 100644 --- a/biolink/openapi.yml +++ b/biolink/openapi.yml @@ -853,7 +853,7 @@ components: x-bte-response-mapping: gene-hgnc: HGNC: associations.object.HGNC - pubmed: associations.publications.id + ref_pmid: associations.publications.id ## commenting out because data-processing / biolink-modeling issues # monarch_source_database: associations.provided_by # ## there's also a relation.id and relation.inverse. @@ -862,7 +862,7 @@ components: gene-hgnc-dbsnp-start: HGNC: associations.object.HGNC input_name: associations.subject.label ## for the dbsnp input - pubmed: associations.publications.id + ref_pmid: associations.publications.id ## commenting out because data-processing / biolink-modeling issues # monarch_source_database: associations.provided_by # ## there's also a relation.id and relation.inverse. @@ -870,52 +870,52 @@ components: # "biolink:original_predicate": associations.relation.label pathway-react: REACT: associations.object.REACT - pubmed: associations.publications.id + ref_pmid: associations.publications.id ## commenting out because data-processing / biolink-modeling issues # monarch_source_database: associations.provided_by # "biolink:original_predicate": associations.relation.label phenotype-hp: HP: associations.object.HP - pubmed: associations.publications.id + ref_pmid: associations.publications.id ## commenting out because data-processing / biolink-modeling issues # monarch_source_database: associations.provided_by # "biolink:original_predicate": associations.relation.label phenotype-hp-dbsnp-start: HP: associations.object.HP input_name: associations.subject.label ## for the dbsnp input - pubmed: associations.publications.id + ref_pmid: associations.publications.id ## commenting out because data-processing / biolink-modeling issues # monarch_source_database: associations.provided_by # "biolink:original_predicate": associations.relation.label variant-dbsnp: DBSNP: associations.object.dbSNP output_name: associations.object.label - pubmed: associations.publications.id + ref_pmid: associations.publications.id ## commenting out because data-processing / biolink-modeling issues # monarch_source_database: associations.provided_by # "biolink:original_predicate": associations.relation.label anatomy-uberon: UBERON: associations.object.UBERON - pubmed: associations.publications.id + ref_pmid: associations.publications.id ## commenting out because data-processing / biolink-modeling issues # monarch_source_database: associations.provided_by # "biolink:original_predicate": associations.relation.label disease-mondo: MONDO: associations.object.MONDO - pubmed: associations.publications.id + ref_pmid: associations.publications.id ## commenting out because data-processing / biolink-modeling issues # monarch_source_database: associations.provided_by # "biolink:original_predicate": associations.relation.label disease-mondo-dbsnp-start: MONDO: associations.object.MONDO input_name: associations.subject.label ## for the dbsnp input - pubmed: associations.publications.id + ref_pmid: associations.publications.id ## commenting out because data-processing / biolink-modeling issues # monarch_source_database: associations.provided_by # "biolink:original_predicate": associations.relation.label orthologGene2diseaseMondo: MONDO: associations.object.MONDO - pubmed: associations.publications.id ## not all of these are pubmed though...saw some WormBase:WBPaper ones + ref_pmid: associations.publications.id ## not all of these are pubmed though...saw some WormBase:WBPaper ones ## commenting out because data-processing / biolink-modeling issues # homologous_gene_model_id: associations.subject.id ## what is directly annotated to the disease # homologous_gene_model_name: associations.subject.label @@ -923,7 +923,7 @@ components: # "biolink:original_predicate": associations.relation.label orthologGene2phenoHP: HP: associations.object.HP - pubmed: associations.publications.id ## not all of these are pubmed though...saw some WormBase:WBPaper ones + ref_pmid: associations.publications.id ## not all of these are pubmed though...saw some WormBase:WBPaper ones ## commenting out because data-processing / biolink-modeling issues # homologous_gene_model_id: associations.subject.id ## what is directly annotated to the disease # homologous_gene_model_name: associations.subject.label From 16b13cd741ee022e6e2ebede82471d8eefff454d Mon Sep 17 00:00:00 2001 From: Colleen Xu Date: Mon, 14 Aug 2023 16:00:18 -0700 Subject: [PATCH 11/11] ebi g2p: update examples in comments --- EBIgene2phenotype/smartapi.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/EBIgene2phenotype/smartapi.yaml b/EBIgene2phenotype/smartapi.yaml index 24bea767..82d90a17 100644 --- a/EBIgene2phenotype/smartapi.yaml +++ b/EBIgene2phenotype/smartapi.yaml @@ -623,8 +623,8 @@ components: response_mapping: "$ref": "#/components/x-bte-response-mapping/disease-object" # testExamples: - # - qInput: "HGNC:10031" ## RMRP - # oneOutput: "OMIM:250250" ## CARTILAGE-HAIR HYPOPLASIA + # - qInput: "HGNC:1020" ## BCS1L + # oneOutput: "OMIM:603358" ## GRACILE SYNDROME disease_to_gene: - supportBatch: true useTemplating: true