wikipathways · marvinm2 · Mar 6, 2026 · Mar 6, 2026 · Mar 6, 2026 · Mar 6, 2026
diff --git a/.github/workflows/extractRQs.yml b/.github/workflows/extractRQs.yml
@@ -20,6 +20,8 @@ jobs:
         run: pip install rdflib
       - name: Extract
         run: python scripts/transformDotTtlToDotSparql.py
+      - name: Lint headers
+        run: python scripts/lint_headers.py
 
       - name: Commit new .rq files
         run: |

diff --git a/.gitignore b/.gitignore
@@ -0,0 +1 @@
+.planning/
diff --git a/A. Metadata/authors.rq b/A. Metadata/authors.rq
@@ -1,3 +1,8 @@
+# title: Authors of All Pathways
+# category: Metadata
+# description: Lists all pathway authors with their name, homepage, and ORCID,
+#   along with the number of pathways each author created.
+
 PREFIX dc:    <http://purl.org/dc/elements/1.1/>
 PREFIX foaf:  <http://xmlns.com/foaf/0.1/>
 

diff --git a/A. Metadata/datacounts/averageDatanodes.rq b/A. Metadata/datacounts/averageDatanodes.rq
@@ -1,3 +1,8 @@
+# title: Average Data Nodes per Pathway
+# category: Metadata
+# description: Calculates the average, minimum, and maximum number of data nodes per
+#   pathway in WikiPathways.
+
 SELECT (AVG(?no) AS ?avg) 
        (MIN(?no) AS ?min) 
        (MAX(?no) AS ?max) 

diff --git a/A. Metadata/datacounts/averageGeneProducts.rq b/A. Metadata/datacounts/averageGeneProducts.rq
@@ -1,3 +1,8 @@
+# title: Average Gene Products per Pathway
+# category: Metadata
+# description: Calculates the average, minimum, and maximum number of gene products
+#   per pathway in WikiPathways.
+
 SELECT (AVG(?no) AS ?avg) 
        (MIN(?no) AS ?min) 
        (MAX(?no) AS ?max) 

diff --git a/A. Metadata/datacounts/averageInteractions.rq b/A. Metadata/datacounts/averageInteractions.rq
@@ -1,3 +1,8 @@
+# title: Average Interactions per Pathway
+# category: Metadata
+# description: Calculates the average, minimum, and maximum number of interactions
+#   per pathway in WikiPathways.
+
 SELECT (AVG(?no) AS ?avg) 
        (MIN(?no) AS ?min) 
        (MAX(?no) AS ?max) 

diff --git a/A. Metadata/datacounts/averageMetabolites.rq b/A. Metadata/datacounts/averageMetabolites.rq
@@ -1,3 +1,8 @@
+# title: Average Metabolites per Pathway
+# category: Metadata
+# description: Calculates the average, minimum, and maximum number of metabolites per
+#   pathway in WikiPathways.
+
 SELECT (AVG(?no) AS ?avg) 
        (MIN(?no) AS ?min) 
        (MAX(?no) AS ?max) 

diff --git a/A. Metadata/datacounts/averageProteins.rq b/A. Metadata/datacounts/averageProteins.rq
@@ -1,3 +1,8 @@
+# title: Average Proteins per Pathway
+# category: Metadata
+# description: Calculates the average, minimum, and maximum number of proteins per
+#   pathway in WikiPathways.
+
 SELECT (AVG(?no) AS ?avg) 
        (MIN(?no) AS ?min) 
        (MAX(?no) AS ?max) 

diff --git a/A. Metadata/datacounts/countDataNodes.rq b/A. Metadata/datacounts/countDataNodes.rq
@@ -1,3 +1,7 @@
+# title: Count of Data Nodes
+# category: Metadata
+# description: Counts the total number of data nodes in WikiPathways.
+
 SELECT DISTINCT count(?DataNodes) as ?DataNodeCount
 WHERE {
     ?DataNodes a wp:DataNode .

diff --git a/A. Metadata/datacounts/countGeneProducts.rq b/A. Metadata/datacounts/countGeneProducts.rq
@@ -1,3 +1,7 @@
+# title: Count of Gene Products
+# category: Metadata
+# description: Counts the total number of gene products in WikiPathways.
+
 SELECT DISTINCT count(?geneProduct) as ?GeneProductCount
 WHERE {
     ?geneProduct a wp:GeneProduct .

diff --git a/A. Metadata/datacounts/countInteractions.rq b/A. Metadata/datacounts/countInteractions.rq
@@ -1,3 +1,7 @@
+# title: Count of Interactions
+# category: Metadata
+# description: Counts the total number of interactions in WikiPathways.
+
 SELECT DISTINCT count(?Interaction) as ?InteractionCount
 WHERE {
     ?Interaction a wp:Interaction .

diff --git a/A. Metadata/datacounts/countMetabolites.rq b/A. Metadata/datacounts/countMetabolites.rq
@@ -1,3 +1,7 @@
+# title: Count of Metabolites
+# category: Metadata
+# description: Counts the total number of metabolites in WikiPathways.
+
 SELECT DISTINCT count(?Metabolite) as ?MetaboliteCount
 WHERE {
     ?Metabolite a wp:Metabolite .

diff --git a/A. Metadata/datacounts/countPathways.rq b/A. Metadata/datacounts/countPathways.rq
@@ -1,3 +1,7 @@
+# title: Count of Pathways
+# category: Metadata
+# description: Counts the total number of pathways in WikiPathways.
+
 SELECT DISTINCT count(?Pathway) as ?PathwayCount
 WHERE {
     ?Pathway a wp:Pathway, skos:Collection .

diff --git a/A. Metadata/datacounts/countProteins.rq b/A. Metadata/datacounts/countProteins.rq
@@ -1,3 +1,7 @@
+# title: Count of Proteins
+# category: Metadata
+# description: Counts the total number of proteins in WikiPathways.
+
 SELECT DISTINCT count(?protein) as ?ProteinCount
 WHERE {
     ?protein a wp:Protein .

diff --git a/A. Metadata/datacounts/countSignalingPathways.rq b/A. Metadata/datacounts/countSignalingPathways.rq
@@ -1,3 +1,8 @@
+# title: Count of Signaling Pathways
+# category: Metadata
+# description: Counts the total number of signaling pathways in WikiPathways by
+#   filtering on the signaling pathway ontology tag.
+
 SELECT count(distinct ?pathway) as ?pathwaycount
 WHERE {
   ?tag1 a owl:Class ;

diff --git a/A. Metadata/datacounts/linkoutCounts.rq b/A. Metadata/datacounts/linkoutCounts.rq
@@ -1,3 +1,8 @@
+# title: External Linkout Counts
+# category: Metadata
+# description: Counts the number of distinct entities linked to each external database
+#   (ChEBI, ChemSpider, HMDB, PubChem, Ensembl, NCBI Gene, HGNC, Rhea, UniProt).
+
 SELECT ?pred (COUNT(DISTINCT ?entity) AS ?count) WHERE {
   VALUES ?pred {
     # metabolites

diff --git a/A. Metadata/datasources/WPforChemSpider.rq b/A. Metadata/datasources/WPforChemSpider.rq
@@ -1,4 +1,7 @@
-#List of WikiPathways for ChemSpider identifiers
+# title: WikiPathways for ChemSpider Identifiers
+# category: Data Sources
+# description: Lists pathways containing metabolites with ChemSpider identifiers,
+#   showing the pathway title and extracted ChemSpider ID.
 
 select distinct ?pathwayRes (str(?wpid) as ?pathway) (str(?title) as ?pathwayTitle) (fn:substring(?csId,36) as ?chemspider) where {
   ?gene a wp:Metabolite ;

diff --git a/A. Metadata/datasources/WPforEnsembl.rq b/A. Metadata/datasources/WPforEnsembl.rq
@@ -1,11 +1,14 @@
-#List of WikiPathways for Ensembl identifiers
-
-select distinct ?pathwayRes (str(?wpid) as ?pathway) (str(?title) as ?pathwayTitle) (fn:substring(?ensId,32) as ?ensembl) where {
-  ?gene a wp:GeneProduct ;
-    dcterms:identifier ?id ;
-    dcterms:isPartOf ?pathwayRes ;
-    wp:bdbEnsembl ?ensId .
-  ?pathwayRes a wp:Pathway ;
-    dcterms:identifier ?wpid ;
-    dc:title ?title .
-}
+# title: WikiPathways for Ensembl Identifiers
+# category: Data Sources
+# description: Lists pathways containing gene products with Ensembl identifiers,
+#   showing the pathway title and extracted Ensembl ID.
+
+select distinct ?pathwayRes (str(?wpid) as ?pathway) (str(?title) as ?pathwayTitle) (fn:substring(?ensId,32) as ?ensembl) where {
+  ?gene a wp:GeneProduct ;
+    dcterms:identifier ?id ;
+    dcterms:isPartOf ?pathwayRes ;
+    wp:bdbEnsembl ?ensId .
+  ?pathwayRes a wp:Pathway ;
+    dcterms:identifier ?wpid ;
+    dc:title ?title .
+}
diff --git a/A. Metadata/datasources/WPforHGNC.rq b/A. Metadata/datasources/WPforHGNC.rq
@@ -1,4 +1,7 @@
-#List of WikiPathways for HGNC symbols
+# title: WikiPathways for HGNC Symbols
+# category: Data Sources
+# description: Lists pathways containing gene products with HGNC symbol identifiers,
+#   showing the pathway title and extracted HGNC symbol.
 
 select distinct ?pathwayRes (str(?wpid) as ?pathway) (str(?title) as ?pathwayTitle) (fn:substring(?hgncId,37) as ?HGNC) where {
   ?gene a wp:GeneProduct ;

diff --git a/A. Metadata/datasources/WPforHMDB.rq b/A. Metadata/datasources/WPforHMDB.rq
@@ -1,4 +1,7 @@
-#ist of WikiPathways for HMDB identifiers
+# title: WikiPathways for HMDB Identifiers
+# category: Data Sources
+# description: Lists pathways containing metabolites with HMDB identifiers, showing
+#   the pathway title and extracted HMDB ID.
 
 select distinct ?pathwayRes (str(?wpid) as ?pathway) (str(?title) as ?pathwayTitle) (fn:substring(?hmdbId,29) as ?hmdb) where {
   ?gene a wp:Metabolite ;

diff --git a/A. Metadata/datasources/WPforNCBI.rq b/A. Metadata/datasources/WPforNCBI.rq
@@ -1,4 +1,7 @@
-#List of WikiPathways for NCBI Gene identifiers
+# title: WikiPathways for NCBI Gene Identifiers
+# category: Data Sources
+# description: Lists pathways containing gene products with NCBI Gene identifiers,
+#   showing the pathway title and extracted NCBI Gene ID.
 
 select distinct ?pathwayRes (str(?wpid) as ?pathway) (str(?title) as ?pathwayTitle) (fn:substring(?ncbiGeneId,33) as ?NCBIGene) where {
   ?gene a wp:GeneProduct ;

diff --git a/A. Metadata/datasources/WPforPubChemCID.rq b/A. Metadata/datasources/WPforPubChemCID.rq
@@ -1,11 +1,14 @@
-#List of WikiPathways for PubChem CID identifiers
-
-select distinct ?pathwayRes (str(?wpid) as ?pathway) (str(?title) as ?pathwayTitle) (fn:substring(?cid,46) as ?PubChem) where {
-  ?gene a wp:Metabolite ;
-    dcterms:identifier ?id ;
-    dcterms:isPartOf ?pathwayRes ;
-    wp:bdbPubChem ?cid .
-  ?pathwayRes a wp:Pathway ;
-    dcterms:identifier ?wpid ;
-    dc:title ?title .
-}
+# title: WikiPathways for PubChem CID Identifiers
+# category: Data Sources
+# description: Lists pathways containing metabolites with PubChem compound identifiers,
+#   showing the pathway title and extracted PubChem CID.
+
+select distinct ?pathwayRes (str(?wpid) as ?pathway) (str(?title) as ?pathwayTitle) (fn:substring(?cid,46) as ?PubChem) where {
+  ?gene a wp:Metabolite ;
+    dcterms:identifier ?id ;
+    dcterms:isPartOf ?pathwayRes ;
+    wp:bdbPubChem ?cid .
+  ?pathwayRes a wp:Pathway ;
+    dcterms:identifier ?wpid ;
+    dc:title ?title .
+}
diff --git a/A. Metadata/linksets.rq b/A. Metadata/linksets.rq
@@ -1,3 +1,8 @@
+# title: Linksets Overview
+# category: Metadata
+# description: Returns all VoID linksets in the WikiPathways RDF with their title,
+#   creation date, and license information.
+
 SELECT DISTINCT ?dataset (str(?titleLit) as ?title) ?date ?license 
 WHERE {
    ?dataset a void:Linkset ;

diff --git a/A. Metadata/metadata.rq b/A. Metadata/metadata.rq
@@ -1,7 +1,12 @@
+# title: Dataset Metadata
+# category: Metadata
+# description: Returns all VoID datasets in the WikiPathways RDF with their title,
+#   creation date, and license information.
+
 SELECT DISTINCT ?dataset (str(?titleLit) as ?title) ?date ?license 
 WHERE {
    ?dataset a void:Dataset ;
    dcterms:title ?titleLit ;
    dcterms:license ?license ;
    pav:createdOn ?date .
-}
+}
diff --git a/A. Metadata/prefixes.rq b/A. Metadata/prefixes.rq
@@ -1,3 +1,8 @@
+# title: SPARQL Prefixes
+# category: Metadata
+# description: Lists all namespace prefixes declared in the WikiPathways SPARQL
+#   endpoint via SHACL prefix declarations.
+
 PREFIX sh: <http://www.w3.org/ns/shacl#>
 PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
 
@@ -6,4 +11,4 @@ SELECT ?prefix ?namespace WHERE {
     sh:prefix ?prefix ;
     sh:namespace ?namespace
   ] .
-}
+}
diff --git a/A. Metadata/species/PWsforSpecies.rq b/A. Metadata/species/PWsforSpecies.rq
@@ -1,8 +1,14 @@
+# title: Pathways for a Species
+# category: Metadata
+# description: Lists all pathways for a given species, returning the WikiPathways
+#   identifier and page URL. Default species is Mus musculus.
+# param: species | string | Homo sapiens | Species
+
 SELECT DISTINCT ?wpIdentifier ?pathway ?page
 WHERE {
     ?pathway dc:title ?title .
     ?pathway foaf:page ?page .
     ?pathway dc:identifier ?wpIdentifier .
-    ?pathway wp:organismName "Mus musculus" . #Replace "Mus musculus" with other species: "Homo sapiens", "Rattus norvegicus", "Danio rerio"
+    ?pathway wp:organismName "{{species}}" .
  }
 ORDER BY ?wpIdentifier
diff --git a/A. Metadata/species/countDataNodePerSpecies.rq b/A. Metadata/species/countDataNodePerSpecies.rq
@@ -1,3 +1,8 @@
+# title: Data Nodes per Species
+# category: Metadata
+# description: Counts the number of distinct data nodes per species in WikiPathways,
+#   ordered by count descending.
+
 select (count(distinct ?datanode) as ?count) (str(?label) as ?species) where {
   ?datanode a wp:DataNode ;
     dcterms:isPartOf ?pw .

diff --git a/A. Metadata/species/countGeneProductsPerSpecies.rq b/A. Metadata/species/countGeneProductsPerSpecies.rq
@@ -1,3 +1,8 @@
+# title: Gene Products per Species
+# category: Metadata
+# description: Counts the number of distinct gene products per species in WikiPathways,
+#   ordered by count descending.
+
 select (count(distinct ?gene) as ?count) (str(?label) as ?species) where {
   ?gene a wp:GeneProduct ;
     dcterms:isPartOf ?pw .

diff --git a/A. Metadata/species/countMetabolitesPerSpecies.rq b/A. Metadata/species/countMetabolitesPerSpecies.rq
@@ -1,3 +1,8 @@
+# title: Metabolites per Species
+# category: Metadata
+# description: Counts the number of distinct metabolites per species in WikiPathways,
+#   ordered by count descending.
+
 select (str(?label) as ?species) (count(distinct ?metabolite) as ?count) where {
   ?metabolite a wp:Metabolite ;
     dcterms:isPartOf ?pw .

diff --git a/A. Metadata/species/countPathwaysPerSpecies.rq b/A. Metadata/species/countPathwaysPerSpecies.rq
@@ -1,3 +1,8 @@
+# title: Pathways per Species
+# category: Metadata
+# description: Counts the number of pathways per species in WikiPathways, returning
+#   the species name, organism URI, and pathway count.
+
 SELECT DISTINCT (str(?label) as ?name) ?organism (count(?pw) as ?pathwayCount)
 WHERE {
     ?pw dc:title ?title ;

diff --git a/A. Metadata/species/countProteinsPerSpecies.rq b/A. Metadata/species/countProteinsPerSpecies.rq
@@ -1,3 +1,8 @@
+# title: Proteins per Species
+# category: Metadata
+# description: Counts the number of distinct proteins per species in WikiPathways,
+#   ordered by count descending.
+
 select (count(distinct ?protein) as ?count) (str(?label) as ?species) where {
   ?protein a wp:Protein ;
     dcterms:isPartOf ?pw .

diff --git a/B. Communities/AOP/allPathways.rq b/B. Communities/AOP/allPathways.rq
@@ -1,3 +1,7 @@
+# title: AOP Community Pathways
+# category: Communities
+# description: Lists all pathways tagged with the AOP community curation tag.
+
 PREFIX wp: <http://vocabularies.wikipathways.org/wp#>
 PREFIX dc: <http://purl.org/dc/elements/1.1/>
 PREFIX cur: <http://vocabularies.wikipathways.org/wp#Curation:>
@@ -7,4 +11,4 @@ WHERE {
   ?pathway wp:ontologyTag cur:AOP ; 
   a wp:Pathway ; 
   dc:title ?title .
-}
+}
diff --git a/B. Communities/AOP/allProteins.rq b/B. Communities/AOP/allProteins.rq
@@ -1,3 +1,7 @@
+# title: AOP Community Proteins
+# category: Communities
+# description: Lists all proteins found in AOP community pathways.
+
 SELECT DISTINCT ?pathway (str(?label) as ?Protein)
 WHERE {
 ?pathway wp:ontologyTag cur:AOP ;

diff --git a/B. Communities/CIRM Stem Cell Pathways/allPathways.rq b/B. Communities/CIRM Stem Cell Pathways/allPathways.rq
@@ -1,3 +1,7 @@
+# title: CIRM Stem Cell Pathways
+# category: Communities
+# description: Lists all pathways tagged with the CIRM Stem Cell community curation tag.
+
 SELECT DISTINCT ?pathway (str(?title) as ?PathwayTitle)
 WHERE {
 ?pathway wp:ontologyTag cur:CIRM_Related ; 

diff --git a/B. Communities/CIRM Stem Cell Pathways/allProteins.rq b/B. Communities/CIRM Stem Cell Pathways/allProteins.rq
@@ -1,3 +1,7 @@
+# title: CIRM Stem Cell Proteins
+# category: Communities
+# description: Lists all proteins found in CIRM Stem Cell community pathways.
+
 SELECT DISTINCT ?pathway (str(?label) as ?Protein)
 WHERE {
 ?pathway wp:ontologyTag cur:CIRM_Related ;

diff --git a/B. Communities/COVID19/allPathways.rq b/B. Communities/COVID19/allPathways.rq
@@ -1,3 +1,7 @@
+# title: COVID-19 Community Pathways
+# category: Communities
+# description: Lists all pathways tagged with the COVID-19 community curation tag.
+
 SELECT DISTINCT ?pathway (str(?title) as ?PathwayTitle)
 WHERE {
 ?pathway wp:ontologyTag cur:COVID19 ; 

diff --git a/B. Communities/COVID19/allProteins.rq b/B. Communities/COVID19/allProteins.rq
@@ -1,3 +1,7 @@
+# title: COVID-19 Community Proteins
+# category: Communities
+# description: Lists all proteins found in COVID-19 community pathways.
+
 SELECT DISTINCT ?pathway (str(?label) as ?Protein)
 WHERE {
 ?pathway wp:ontologyTag cur:COVID19 ;

diff --git a/B. Communities/Inborn Errors of Metabolism/allMetabolicPWs.rq b/B. Communities/Inborn Errors of Metabolism/allMetabolicPWs.rq
@@ -1,3 +1,8 @@
+# title: Inborn Errors of Metabolism Metabolic Pathways
+# category: Communities
+# description: Retrieves pathways classified under metabolic pathway ontology terms,
+#   filtering by label to find metabolic pathway annotations.
+
 SELECT distinct ?pathway ?label ?tag
 WHERE {
   ?tag1 a owl:Class ;

diff --git a/B. Communities/Inborn Errors of Metabolism/allPathways.rq b/B. Communities/Inborn Errors of Metabolism/allPathways.rq
@@ -1,3 +1,7 @@
+# title: Inborn Errors of Metabolism Pathways
+# category: Communities
+# description: Lists all pathways tagged with the Inborn Errors of Metabolism (IEM) community curation tag.
+
 SELECT DISTINCT ?pathway (str(?title) as ?PathwayTitle)
 WHERE {
 ?pathway wp:ontologyTag cur:IEM ;