Merge pull request #1738 from microbiomedata/1735-referential-ineggri…

…ty-checking-of-napa-squads-mongodb-via-sparql-in-fuseki

referential integrity checking of napa squads mongodb via sparql in fuseki

assets/other_mixs_yaml_files/mixs_template.yaml

@@ -9,12 +9,18 @@ subsets:
 
 notes:
   - removed several MIxS terms/slots that were sharing slot uris; commented out Biosample assignments
-  - note that the NMDC submission schema in sheets_and_friends takes its MIxS terms from https://raw.githubusercontent.com/GenomicsStandardsConsortium/mixs/main/model/schema/mixs.yaml and then potentially modifies them. Ideally this file would contain MIxS terms, essentially ready-to-use
+  - note that the NMDC submission schema in sheets_and_friends takes its MIxS terms
+    from https://raw.githubusercontent.com/GenomicsStandardsConsortium/mixs/main/model/schema/mixs.yaml
+    and then potentially modifies them. Ideally this file would contain MIxS terms, essentially ready-to-use
   - multiple LinkML representations of MIxS are currently available and one will be blessed soon
 
 prefixes:
   nmdc: https://w3id.org/nmdc/
   MIXS: https://w3id.org/mixs/
+  linkml: https://w3id.org/linkml/
+
+imports:
+  - linkml:types
 
 default_prefix: MIXS
 

assets/sparql/objects-that-are-never-subjects.rq

@@ -0,0 +1,33 @@
+PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
+PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
+SELECT
+distinct
+?st ?p ?o
+# ?p
+WHERE {
+  graph <https://api-napa.microbiomedata.org> {
+    ?s ?p ?o .
+    filter(isuri(?o))
+    minus {
+      ?o ?op ?oo .
+    } minus {
+      ?s <https://w3id.org/nmdc/award_dois> ?o .
+    } minus {
+      ?s <https://w3id.org/nmdc/publication_dois> ?o .
+    } minus {
+      ?s <https://w3id.org/nmdc/massive_study_identifiers> ?o .
+    }
+    optional {
+      ?s a ?st
+    }
+  } minus {
+    graph <https://w3id.org/nmdc/nmdc> {
+      ?o ?op ?oo .
+    }
+  } minus {
+    graph <https://w3id.org/nmdc/nmdc> {
+      ?p rdfs:subPropertyOf* <https://w3id.org/nmdc/alternative_identifiers>
+    }
+  }
+}
+order by ?st ?p ?o

assets/sparql/subjects-lacking-rdf-types.rq

@@ -0,0 +1,13 @@
+PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
+PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
+SELECT
+distinct ?s
+WHERE {
+  graph <https://api-napa.microbiomedata.org> {
+    ?s ?p ?o .
+    minus {
+      ?s a ?st .
+    }
+  }
+}
+order by ?s

assets/sparql/undefined-non-procs-inputs.rq

@@ -0,0 +1,23 @@
+# Alicia and I wrote this together. It might ahve some good bits, but string filtering is usually a bad practice
+PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
+PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
+SELECT
+distinct ?s ?st ?o
+WHERE {
+  graph <https://api-napa.microbiomedata.org> {
+    ?s <https://w3id.org/nmdc/has_input> ?o .
+    filter(!(strstarts(str(?o),"https://w3id.org/nmdc/procsm")))
+    optional {
+      ?s a ?st
+    }
+    filter(isuri(?o))
+    minus {
+      ?o ?op ?oo .
+    }
+  }
+  minus {
+    graph <https://w3id.org/nmdc/nmdc> {
+      ?o ?op ?oo .
+    }
+  }
+}

assets/yq-for-mixs_subset_modified.txt

@@ -156,3 +156,8 @@
 
 # add "M horizon" to soil_horizon_enum
 '.enums.soil_horizon_enum.permissible_values.["M horizon"] = {}'
+
+# as of 2024-01-30:
+# ValueError: Conflicting URIs (https://raw.githubusercontent.com/microbiomedata/nmdc-schema/main/src/schema/mixs.yaml, https://w3id.org/linkml/types) for item: date
+make: *** [Makefile:102: gen-project] Error 1
+'del(.types)'