Updated yaml schema and examples - plus ShEX shape to go along with it. Still work in progress but getting better and better I guess

5 files changed, 94 insertions, 12 deletions

diff --git a/bh20sequploader/bh20seq-schema.yml b/bh20sequploader/bh20seq-schema.yml
index 2d2e4c9..a901be0 100644
--- a/bh20sequploader/bh20seq-schema.yml
+++ b/bh20sequploader/bh20seq-schema.yml
@@ -23,11 +23,12 @@ $graph:
         type: string
         jsonldPredicate:
           _id: http://semanticscience.org/resource/SIO_000115
-    host_common_name:
-        doc: Text label for the host species (e.g. homo sapiens)
-        type: string?
-        jsonldPredicate:
-          _id: http://purl.obolibrary.org/obo/NOMEN_0000037
+# Removed_common_name. Not necessary since we turned species into IRI
+#    host_common_name:
+#        doc: Text label for the host species (e.g. homo sapiens)
+#        type: string?
+#        jsonldPredicate:
+#          _id: http://purl.obolibrary.org/obo/NOMEN_0000037
     host_sex:
         doc: Sex of the host as define in NCIT, IRI expected (http://purl.obolibrary.org/obo/C20197 (Male), http://purl.obolibrary.org/obo/NCIT_C27993 (Female) or unkown (http://purl.obolibrary.org/obo/NCIT_C17998))
         type: string
@@ -120,7 +121,7 @@ $graph:
   fields:
     virus_species:
       doc: The name of a taxon from the NCBI taxonomy database
-      type: string?
+      type: string
       jsonldPredicate:
           _id: http://edamontology.org/data_1875
           _type: "@id"
@@ -145,7 +146,7 @@ $graph:
         _id: http://www.ebi.ac.uk/efo/EFO_0002699
     sequencing_coverage:
       doc: Sequence coverage defined as the average number of reads representing a given nucleotide (e.g. 100x)
-      type: string?
+      type: int?
       jsonldPredicate:
         _id: http://purl.obolibrary.org/obo/FLU_0000848
 
diff --git a/bh20sequploader/supporting_webuploader.yml b/bh20sequploader/supporting_webuploader.yml
new file mode 100644
index 0000000..5ad8f6c
--- /dev/null
+++ b/bh20sequploader/supporting_webuploader.yml
@@ -0,0 +1,20 @@
+host_age_unit:
+  year: http://purl.obolibrary.org/obo/UO_0000036
+  month: http://purl.obolibrary.org/obo/UO_0000035
+  week: http://purl.obolibrary.org/obo/UO_0000035
+  day: http://purl.obolibrary.org/obo/UO_0000034
+  hour: http://purl.obolibrary.org/obo/UO_0000032
+
+host_sex:
+  Male: http://purl.obolibrary.org/obo/C20197
+  Female: http://purl.obolibrary.org/obo/NCIT_C27993
+  unknown: http://purl.obolibrary.org/obo/NCIT_C17998
+
+host_species:
+  OLS-ontology: ncbitaxon
+
+virus_species:
+  OLS-ontology: ncbitaxon
+
+collection_location:
+  OLS-ontology: gaz
\ No newline at end of file
diff --git a/bh20sequploader/validation_shape.rdf b/bh20sequploader/validation_shape.rdf
new file mode 100644
index 0000000..1d1e7d2
--- /dev/null
+++ b/bh20sequploader/validation_shape.rdf
@@ -0,0 +1,59 @@
+PREFIX : <http://whatever/>
+PREFIX MainSchema: <http://biohackathon.org/bh20-seq-schema#MainSchema/>
+PREFIX hostSchema: <http://biohackathon.org/bh20-seq-schema#hostSchema/>
+PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
+PREFIX obo: <http://purl.obolibrary.org/obo/>
+PREFIX sio: <http://semanticscience.org/resource/>
+PREFIX efo: <http://www.ebi.ac.uk/efo/>
+PREFIX evs: <http://ncicb.nci.nih.gov/xml/owl/EVS/Thesaurus.owl#>
+PREFIX edam: <http://edamontology.org/>
+
+:submissionShape {
+  MainSchema:host   @:hostShape ;
+  MainSchema:sample @:sampleShape ;
+  MainSchema:submitter @:submitterShape ;
+  MainSchema:technology @:technologyShape ;
+  MainSchema:virus @:virusShape;
+}
+
+:hostShape  {
+  	efo:EFO_0000532 [ obo:NCBITaxon_~ ] ;
+    obo:PATO_0000047 [ obo:NCIT_C20197  obo:NCIT_C27993  obo:NCIT_C17998 ] ;
+    sio:SIO_000115 xsd:string ;
+    obo:PATO_0000011 xsd:integer ?;
+    obo:NCIT_C42574 [ obo:UO_~ ] ?;
+    sio:SIO_001167 xsd:string ?;
+    efo:EFO_0000727 xsd:string ?;
+}
+
+:sampleShape  {
+    obo:OBI_0001895 xsd:string ;
+    sio:SIO_000115 xsd:string ;
+    sio:SIO_001167 xsd:string ;
+	evs:C25164 xsd:string ?;
+    obo:GAZ_00000448 [obo:GAZ_~] ?;
+    obo:OBI_0001472 xsd:string ?;
+    obo:OBI_0001479 xsd:string ?;
+}
+
+:submitterShape {
+    sio:SIO_000116 xsd:string ;
+	obo:NCIT_C37984 xsd:string ;
+	obo:NCIT_C37900 xsd:string ?;
+    obo:NCIT_C42781 xsd:string ?;
+    obo:OBI_0600047 xsd:string ?;
+    sio:SIO_000115 /https:\u002F\u002Forcid.org\u002F[0-9]{4}-[0-9]{4}-[0-9]{4}-[0-9]{4}/?;
+    sio:SIO_000172 xsd:string ?;
+    efo:EFO_0001741 xsd:string ?;
+}
+
+:technologyShape {
+    obo:OBI_0600047 xsd:string ;
+    obo:FLU_0000848 xsd:integer ?;
+    efo:EFO_0002699 xsd:string ?;
+}
+
+:virusShape{
+	edam:data_1875 [ obo:NCBITaxon_~ ] ;
+  	sio:SIO_010055 xsd:string ?;
+}
\ No newline at end of file
diff --git a/example/metadata.yaml b/example/metadata.yaml
index 15e4e44..5d9cffc 100644
--- a/example/metadata.yaml
+++ b/example/metadata.yaml
@@ -3,7 +3,6 @@ id: placeholder
 host:
     host_id: XX1
     host_species: http://purl.obolibrary.org/obo/NCBITaxon_9606
-    host_common_name: string
     host_sex: http://purl.obolibrary.org/obo/NCIT_C27993
     host_age: 20
     host_age_unit: http://purl.obolibrary.org/obo/UO_0000036
@@ -16,8 +15,8 @@ sample:
     collector_name: XXX
     collecting_institution: XXX
     specimen_source: XXX
-    collection_date: XXX
-    collection_location: http://purl.obolibrary.org/obo/NCIT_C16428
+    collection_date: 2020-01
+    collection_location: http://purl.obolibrary.org/obo/GAZ_00002459
     sample_storage_conditions: XXX
     additional_collection_information: XXX
 
@@ -28,7 +27,7 @@ virus:
 technology:
     sample_sequencing_technology: XX
     sequence_assembly_method: XX
-    sequencing_coverage: 70x
+    sequencing_coverage: 70
 
 submitter:
     submitter_name: tester
@@ -38,4 +37,4 @@ submitter:
     provider_sample_id: string
     submitter_sample_id: string
     authors: testAuthor
-    submitter_orchid: X12
+    submitter_orchid: https://orcid.org/0000-0002-1825-0097
diff --git a/example/minimal_example.yaml b/example/minimal_example.yaml
index 43adfa8..0080c6d 100644
--- a/example/minimal_example.yaml
+++ b/example/minimal_example.yaml
@@ -10,6 +10,9 @@ sample:
     collector_name: XXX
     collecting_institution: XXX
 
+virus:
+    virus_species: http://purl.obolibrary.org/obo/NCBITaxon_2697049
+
 technology:
     sample_sequencing_technology: XX