add archived_datasets folder with old mappings

.github/workflows/sparql-map-uniprot.yml

@@ -0,0 +1,42 @@
+name: UniProt to BioLink RDF
+# TODO: Add step to manage versioning (delete previous graph, load new graph, generate metadata)
+on:
+  workflow_dispatch:
+    inputs:
+      endpoint:
+        description: 'Upload to SPARQL endpoint'
+        required: true
+        default: 'https://graphdb.dumontierlab.com/repositories/ncats-red-kg/statements'
+      graph:
+        description: 'In the Graph'
+        required: true
+        default: 'https://w3id.org/d2s/graph/uniprot'
+
+jobs:
+  run-sparql:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+
+    - name: Run SPARQL queries to convert UniProt
+      uses: vemonet/sparql-operations-action@v1
+      with:
+        file: datasets/uniprot/mapping
+        endpoint: ${{ github.event.inputs.endpoint }}
+        user: ${{ secrets.GRAPHDB_USER }}
+        password: ${{ secrets.GRAPHDB_PASSWORD }}
+        inputvar: https://sparql.uniprot.org
+        outputvar: ${{ github.event.inputs.graph }}
+        servicevar: https://sparql.uniprot.org
+
+    - name: Compute and insert HCLS descriptive metadata
+      uses: vemonet/sparql-operations-action@v1
+      with:
+        file: https://github.com/MaastrichtU-IDS/d2s-scripts-repository/tree/master/sparql/compute-hcls-stats
+        endpoint: ${{ github.event.inputs.endpoint }}
+        user: ${{ secrets.GRAPHDB_USER }}
+        password: ${{ secrets.GRAPHDB_PASSWORD }}
+        inputvar: ${{ github.event.inputs.graph }}
+        outputvar: https://w3id.org/d2s/metadata
+        servicevar: ${{ github.event.inputs.endpoint }}
+        # servicevar: http://localhost:7200/repositories/ncats-red-kg

.github/workflows/sparql-map-wikipathways.yml

@@ -0,0 +1,42 @@
+name: WikiPathways to BioLink RDF
+# TODO: Add step to manage versioning (delete previous graph, load new graph, generate metadata)
+on:
+  workflow_dispatch:
+    inputs:
+      endpoint:
+        description: 'Upload to SPARQL endpoint'
+        required: true
+        default: 'https://graphdb.dumontierlab.com/repositories/ncats-red-kg/statements'
+      graph:
+        description: 'In the Graph'
+        required: true
+        default: 'https://w3id.org/d2s/graph/wikipathways'
+
+jobs:
+  run-sparql:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+
+    - name: Run SPARQL queries to convert Wikipathways
+      uses: vemonet/sparql-operations-action@v1
+      with:
+        file: datasets/wikipathways/mapping
+        endpoint: ${{ github.event.inputs.endpoint }}
+        user: ${{ secrets.GRAPHDB_USER }}
+        password: ${{ secrets.GRAPHDB_PASSWORD }}
+        inputvar: http://rdf.wikipathways.org/
+        outputvar: ${{ github.event.inputs.graph }}
+        servicevar: http://sparql.wikipathways.org/sparql
+
+    - name: Compute and insert HCLS descriptive metadata
+      uses: vemonet/sparql-operations-action@v1
+      with:
+        file: https://github.com/MaastrichtU-IDS/d2s-scripts-repository/tree/master/sparql/compute-hcls-stats
+        endpoint: ${{ github.event.inputs.endpoint }}
+        user: ${{ secrets.GRAPHDB_USER }}
+        password: ${{ secrets.GRAPHDB_PASSWORD }}
+        inputvar: ${{ github.event.inputs.graph }}
+        outputvar: https://w3id.org/d2s/metadata
+        servicevar: ${{ github.event.inputs.endpoint }}
+        # servicevar: http://localhost:7200/repositories/ncats-red-kg

archived-datasets/date/config.yml

@@ -0,0 +1,55 @@
+
+## For Tabular files workflows
+dataset_to_process: "date"
+
+## For XML workflows
+# dir_to_process:
+#   class: Directory
+#   path: ../../workspace/input/date
+
+sparql_final_graph_uri: "https://w3id.org/d2s/graph/date"
+
+
+# Final SPARQL endpoint to load the BioLink RDF
+# Add /statements for RDF4J server like GraphDB
+sparql_final_triplestore_url: "https://graphdb.dumontierlab.com/repositories/ncats-red-kg/statements"
+# sparql_final_triplestore_url: "http://graphdb:7200/repositories/ncats-red-kg/statements"
+
+sparql_final_triplestore_username: "import_user"
+sparql_final_triplestore_password: "dba"
+
+# R2RML params
+input_data_jdbc: "jdbc:drill:drillbit=drill:31010"
+
+# Temporary triplestore (e.g. Virtuoso). TODO: improve
+sparql_tmp_service_url: "http://tmp-virtuoso:8890/sparql"
+# sparql_tmp_service_url: "http://blazegraph:8082/bigdata/sparql"
+
+sparql_tmp_triplestore_url: "http://tmp-virtuoso:8890/sparql"
+# sparql_tmp_triplestore_url: "http://blazegraph:8082/bigdata/sparql"
+sparql_tmp_triplestore_username: "dba"
+sparql_tmp_triplestore_password: "dba"
+
+sparql_tmp_graph_uri: "https://w3id.org/d2s/graph/date"
+# sparql_tmp_graph_uri: "https://w3id.org/d2s/graph/xml2rdf"
+tmp_triplestore_container_id: "d2s-tmp-virtuoso"
+tmp_triplestore_load_dir: "/usr/local/virtuoso-opensource/var/lib/virtuoso/db"
+
+# Split params
+# split_property: "https://w3id.org/biolink/vocab/has_participant"
+# split_class: "https://w3id.org/biolink/vocab/GeneGrouping"
+# split_delimiter: ","
+# split_quote: '"'
+
+sparql_transform_queries_path: "mapping"
+sparql_insert_metadata_path: "metadata"
+
+cwl_workflow_filename: "csv-virtuoso.cwl"
+
+config_dir:
+  class: Directory
+  path: .
+
+cwl_dir:
+  class: Directory
+  path: ../../d2s-core

archived-datasets/date/download/download.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+
+wget -N http://tatonettilab.org/resources/DATE/date_resource.zip
+
+# Unzip
+# All in same dir
+unzip -o \*.zip
+
+# Convert TSV to CSV
+sed -e 's/"/\\"/g' -e 's/\t/","/g' -e 's/^/"/' -e 's/$/"/'  -e 's/\r//' date_resource/Drug_target_reactome_pathway.tsv > date.csv
+
+# rm date_resource/Drug_target_reactome_pathway_filtered.tsv
+# Should contains 2 tsv
+# date_resource/Drug_target_reactome_pathway.tsv
+# date_resource/Drug_target_reactome_pathway_filtered.tsv

archived-datasets/date/mapping/insert-date.rq

@@ -0,0 +1,91 @@
+PREFIX d2smodel: <https://w3id.org/d2s/model/>
+PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
+PREFIX owl: <http://www.w3.org/2002/07/owl#>
+PREFIX dc: <http://purl.org/dc/elements/1.1/>
+PREFIX dcterms: <http://purl.org/dc/terms/>
+PREFIX bl: <https://w3id.org/biolink/vocab/>
+PREFIX w3idvocab: <https://w3id.org/d2s/vocab/>
+INSERT
+{
+  GRAPH <?_output> {  
+    ?drugUri a bl:Drug ;
+      bl:id ?drugId ;
+      bl:name ?drugName . 
+
+    ?targetUniprotUri a bl:Protein .
+
+    ?targetSymbolUri a bl:Gene ;
+      bl:id ?targetSymbol ;
+      bl:has_gene_product ?targetUniprotUri ;
+      bl:systematic_synonym ?targetSymbol .
+    # expressed_in tissue?
+
+    ?pathwayUri a bl:Pathway ; # tissue-specific molecular pathway
+      bl:name ?pathwayName ;
+      bl:part_of ?tissueUri .
+
+    ?tissueUri a bl:GrossAnatomicalStructure ; # tissue
+      bl:name ?tissueName .
+
+
+    ?interactionUri a bl:ChemicalToGeneAssociation ;
+      bl:relation bl:interacts_with ;
+      bl:subject ?drugUri ;
+      bl:object ?targetUniprotUri ;
+      bl:part_of ?pathwayUri .
+
+    # TODO: We also could create a bl:ChemicalToPathwayAssociation. What would be the best choice?
+
+    # TODO: CellLine https://biolink.github.io/biolink-model/docs/CellLineToDiseaseOrPhenotypicFeatureAssociation.html
+    #?cellLineUri a bl:CellLine ;
+    #bl:id ?cellLineId .
+  }
+}
+WHERE {
+  SERVICE <?_service>  {
+    GRAPH <?_input> {
+      # To filter out Drug_target_reactome_pathway_filtered.tsv file
+      # TODO: Be careful the file path in the type can change:
+      # ?s a <http://data2services/data/ncats/date/Drug_target_reactome_pathway.tsv> ;
+      ?s d2smodel:Drug_idStitch ?drugId ; # eg: CID000004927
+        d2smodel:Drug_name ?drugName .
+      BIND( iri(concat("https://identifiers.org/pubchem.compound/", replace(?drugId, "CID", "") ) ) AS ?drugUri )
+
+      ?s d2smodel:TargetUniprot ?targetUniprotId .
+      BIND( iri(concat("https://identifiers.org/uniprot/", ?targetUniprotId ) ) AS ?targetUniprotUri )
+
+      ?s d2smodel:Pathway ?pathwayName . # eg: Retrograde neurotrophin signalling
+      BIND( iri(concat("https://w3id.org/d2s/data/pathway/", md5(?pathwayName) ) ) AS ?pathwayUri )
+
+      BIND( iri(concat("https://w3id.org/d2s/data/protein/interaction/", md5(concat(?drugId, ?targetUniprotId, ?pathwayName)) ) ) AS ?interactionUri )
+      BIND( iri(concat("https://w3id.org/d2s/data/pathway/association/", md5(concat(?drugId, ?targetUniprotId, ?pathwayName)) ) ) AS ?pathwayAssociationUri )
+
+      OPTIONAL {
+        ?s d2smodel:Cell_line_id ?cellLineId . # NA (majority), HT1080, SHSYSY.RA, astrocytes, GM2313...
+        BIND( if( ?cellLineId="NA",
+          iri("") ,
+          iri(concat("https://w3id.org/d2s/data/cell_line/", ?cellLineId) )
+        ) AS ?cellLineUri )
+      } 
+      OPTIONAL { 
+        ?s d2smodel:Tissue ?tissueName . # Fetalbrain
+        BIND( iri(concat("https://w3id.org/d2s/data/tissue/", md5(?tissueName) ) ) AS ?tissueUri )
+      } 
+      OPTIONAL { 
+        ?s d2smodel:Pathway_size ?pathwaySize . # 42...
+      }
+      OPTIONAL { 
+        ?s d2smodel:TargetSymbol ?targetSymbol . # CHRM3
+        FILTER(!contains(?targetSymbol, "c("))    # filter out symbol like c(\"CALM1\", \"CALM2\", \"CALM3\")
+        BIND( iri(concat("https://identifiers.org/hgnc.symbol/", ?targetSymbol ) ) AS ?targetSymbolUri )
+      } 
+      OPTIONAL { 
+        ?s d2smodel:Target_class ?targetClass . # gpcr, enzyme, lgic, vgic, transporter, other_protein, catalytic_receptor, nhr, other_ic
+        BIND( iri(concat("https://w3id.org/d2s/data/protein/class/", md5(?targetClass) ) ) AS ?targetClassUri )
+      } 
+      OPTIONAL { 
+        ?s d2smodel:Dataset ?dataset . # GTEx, U133A, NCI60, HPM_PRT
+      }
+    }
+  }
+}

archived-datasets/date/mapping/map-date.rml.ttl

@@ -0,0 +1,88 @@
+@prefix rr: <http://www.w3.org/ns/r2rml#>.
+@prefix rml: <http://semweb.mmlab.be/ns/rml#>.
+@prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>.
+@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#>.
+@prefix ql: <http://semweb.mmlab.be/ns/ql#>.
+@prefix map: <http://mapping.example.com/>.
+
+map:fn_0 rml:logicalSource map:source_0;
+    rr:predicateObjectMap map:pomexec_0, map:pom_7.
+map:map_interactions_0 rml:logicalSource map:source_0;
+    a rr:TriplesMap;
+    rdfs:label "interactions";
+    rr:subjectMap map:s_0;
+    rr:predicateObjectMap map:pom_0, map:pom_1, map:pom_2, map:pom_3, map:pom_4, map:pom_5, map:pom_6.
+map:om_0 a rr:ObjectMap;
+    rr:constant "https://w3id.org/biolink/vocab/PairwiseGeneToGeneInteraction";
+    rr:termType rr:IRI.
+map:om_1 a rr:ObjectMap;
+    rr:template "https://identifiers.org/pubchem.compound/{Drug_ID_Stitch}";
+    rr:termType rr:IRI.
+map:om_2 a rr:ObjectMap;
+    rr:template "https://identifiers.org/uniprot:{Target(uniprot)}";
+    rr:termType rr:IRI.
+map:om_3 a rr:ObjectMap;
+    rr:constant "https://w3id.org/biolink/vocab/interacts_with";
+    rr:termType rr:IRI.
+map:om_4 a rr:ObjectMap;
+    rr:template "https://w3id.org/d2s/dataset/date/{Dataset}";
+    rr:termType rr:IRI.
+map:om_5 a rr:ObjectMap;
+    rml:reference "Pathway";
+    rr:termType rr:Literal.
+map:om_6 a <http://semweb.mmlab.be/ns/fnml#FunctionTermMap>;
+    rr:termType rr:IRI;
+    <http://semweb.mmlab.be/ns/fnml#functionValue> map:fn_0.
+map:om_7 a rr:ObjectMap;
+    rr:template "https://w3id.org/d2s/data/date/pathway/{Pathway}";
+    rr:termType rr:Literal.
+map:omexec_0 rr:constant "http://example.com/idlab/function/toUpperCaseURL";
+    rr:termType rr:IRI.
+map:pm_0 a rr:PredicateMap;
+    rr:constant rdf:type.
+map:pm_1 a rr:PredicateMap;
+    rr:constant <https://w3id.org/biolink/vocab/subject>.
+map:pm_2 a rr:PredicateMap;
+    rr:constant <https://w3id.org/biolink/vocab/object>.
+map:pm_3 a rr:PredicateMap;
+    rr:constant <https://w3id.org/biolink/vocab/relation>.
+map:pm_4 a rr:PredicateMap;
+    rr:constant <https://w3id.org/biolink/vocab/provided_by>.
+map:pm_5 a rr:PredicateMap;
+    rr:constant <https://w3id.org/biolink/vocab/part_of>.
+map:pm_6 a rr:PredicateMap;
+    rr:constant <https://w3id.org/biolink/vocab/part_of>.
+map:pm_7 a rr:PredicateMap;
+    rr:constant <http://example.com/idlab/function/str>.
+map:pmexec_0 rr:constant <https://w3id.org/function/ontology#executes>.
+map:pom_0 a rr:PredicateObjectMap;
+    rr:predicateMap map:pm_0;
+    rr:objectMap map:om_0.
+map:pom_1 a rr:PredicateObjectMap;
+    rr:predicateMap map:pm_1;
+    rr:objectMap map:om_1.
+map:pom_2 a rr:PredicateObjectMap;
+    rr:predicateMap map:pm_2;
+    rr:objectMap map:om_2.
+map:pom_3 a rr:PredicateObjectMap;
+    rr:predicateMap map:pm_3;
+    rr:objectMap map:om_3.
+map:pom_4 a rr:PredicateObjectMap;
+    rr:predicateMap map:pm_4;
+    rr:objectMap map:om_4.
+map:pom_5 a rr:PredicateObjectMap;
+    rr:predicateMap map:pm_5;
+    rr:objectMap map:om_5.
+map:pom_6 a rr:PredicateObjectMap;
+    rr:predicateMap map:pm_6;
+    rr:objectMap map:om_6.
+map:pom_7 a rr:PredicateObjectMap;
+    rr:predicateMap map:pm_7;
+    rr:objectMap map:om_7.
+map:pomexec_0 rr:predicateMap map:pmexec_0;
+    rr:objectMap map:omexec_0.
+map:s_0 a rr:SubjectMap;
+    rr:template "https://w3id.org/d2s/data/date/interaction/{Drug_ID_Stitch}_{Target(uniprot)}".
+map:source_0 a rml:LogicalSource;
+    rml:source "date.csv";
+    rml:referenceFormulation ql:CSV.

archived-datasets/date/mapping/map-date.yarrr.yml

@@ -0,0 +1,52 @@
+prefixes:
+  grel: "http://users.ugent.be/~bjdmeest/function/grel.ttl#"
+  idlab: "http://example.com/idlab/function/"
+  xsd: "http://www.w3.org/2001/XMLSchema#"
+  rdfs: "http://www.w3.org/2000/01/rdf-schema#"
+  bl: "https://w3id.org/biolink/vocab/"
+  d2s: "https://w3id.org/d2s/"
+  pubmed: "https://identifiers.org/pubmed:"
+
+mappings:
+  interactions:
+    sources:
+      - ['date.csv~csv']
+      # Dataset Drug_name Drug_ID(Stitch) Tissue  Cell_line_ID  Target(uniprot) Target(symbol)  Target_class  Pathway Pathway_size
+      # U133A leuprolide acetate  CID000003911  Pituitary NA  P30968  GNRHR gpcr   Eukaryotic Translation Elongation  89
+      # U133A leuprolide acetate  CID000003911  Pituitary NA  P30968  GNRHR gpcr   Growth hormone receptor signaling  41
+
+    s: https://w3id.org/d2s/data/date/interaction/$(Drug_ID_Stitch)_$(Target(uniprot\))
+    po:
+      - [a, bl:ChemicalToGeneAssociation]
+      - p: bl:subject
+        o: https://identifiers.org/pubchem.compound/$(Drug_ID_Stitch)~iri
+        # TODO: remove CID from the ID for proper URI
+      - p: bl:object
+        o: https://identifiers.org/uniprot:$(Target(uniprot\))~iri
+      - p: bl:relation
+        o: bl:interacts_with~iri
+      - p: bl:provided_by
+        o: d2s:dataset/date/$(Dataset)~iri
+      - p: bl:participates_in
+        o: $(Pathway)
+      - p: bl:part_of
+        o: $(Tissue)
+      # - p: bl:part_of
+      #   o:
+      #       function: idlab:toUpperCaseURL
+      #       parameters:
+      #           - [idlab:str, "https://w3id.org/d2s/data/date/pathway/$(Pathway)"]
+      #       type: iri
+
+      # Also pathway part_of tissue
+      # TODO: generate a URI for Pathway (do it through preprocessing?)
+      # We could have a python script which iterates over Pathway row to resolve the URI
+
+  drugs:
+    sources:
+      - ['date.csv~csv']
+    s: https://identifiers.org/pubchem.compound/$(Drug_ID_Stitch)~iri
+    po:
+      - [a, bl:ChemicalSubstance]
+      - p: bl:name
+        o: $(Drug_name)