feat: define initial schema (#3)

* Use clearer class names based on SPHN and FAIRGenomes conventions
* Base Sample on the widely used BioSample model
* Define cardinalities
* Improve clarity of names

README.md

@@ -1,52 +1,73 @@
 # smoc-schema
 
-Metadata schema for the SMOC Multi-Omics Digital Object
+Metadata schema for the SMOC Multi-Omics Digital Object.
 
 ```mermaid
 erDiagram
-StudyCollection {
+MODOCollection {
 
 }
-Study {
-    datetime start_date
-    datetime completion_date
-    uriorcurie id
-    string name
-    string description
+MODO {
+    datetime creation_date  
+    datetime last_update_date  
+    uri source_uri  
+    uriorcurie id  
+    string name  
+    string description  
 }
-Experiment {
-
+Assay {
+    OmicsTypeList omics_type  
+    uriorcurie id  
+    string name  
+    string description  
 }
-Record {
-    uriorcurie location
-    DataFormat format
+DataEntity {
+    string data_path  
+    DataFormat data_format  
+    uriorcurie id  
+    string name  
+    string description  
 }
 ReferenceGenome {
-    string name
-    integer taxon_id
-    uriorcurie location
-    uriorcurie source_uri
+    string data_path  
+    integerList taxon_id  
+    uri source_uri  
+    string version  
+    uriorcurie id  
+    string name  
+    string description  
 }
 ReferenceSequence {
-    string name
-    string sequence_md5
-    uriorcurie location
-    uriorcurie source_uri
+    string sequence_md5  
+    uri source_uri  
+    string version  
+    uriorcurie id  
+    string name  
+    string description  
 }
 Sample {
-    integer taxon_id
-    string collector
+    string cell_type  
+    string source_material  
+    Sex sex  
+    integerList taxon_id  
+    stringList collector  
+    uriorcurie id  
+    string name  
+    string description  
 }
 
-StudyCollection ||--}o Study : "entries"
-Study ||--|o Experiment : "has_experiment"
-Experiment ||--|o Sample : "has_sample"
-Experiment ||--|o Record : "has_record"
-Record ||--|o Sample : "has_sample"
-Record ||--|o ReferenceGenome : "has_reference"
-ReferenceGenome ||--|o ReferenceSequence : "has_sequence"
+MODOCollection ||--}o MODO : "entries"
+MODO ||--}o Assay : "has_assay"
+Assay ||--}o Sample : "has_sample"
+Assay ||--}o DataEntity : "has_data"
+DataEntity ||--}o Sample : "has_sample"
+DataEntity ||--|o ReferenceGenome : "has_reference"
+ReferenceGenome ||--}o ReferenceSequence : "has_sequence"
+
 ```
 
+
+
 ## Website
 
 [https://sdsc-ordes.github.io/smoc-schema](https://sdsc-ordes.github.io/smoc-schema)

project/graphql/smoc_schema.graphql

@@ -1,23 +1,111 @@
+type AlignmentSet
+  {
+    id: Uriorcurie!
+    name: String
+    description: String
+    dataPath: String!
+    dataFormat: DataFormat!
+    hasSample: [Sample]
+    hasReference: ReferenceGenome
+  }
+
+type Array
+  {
+    id: Uriorcurie!
+    name: String
+    description: String
+    dataPath: String!
+    dataFormat: DataFormat!
+    hasSample: [Sample]
+    hasReference: ReferenceGenome
+  }
+
+type Assay
+  {
+    id: Uriorcurie!
+    name: String
+    description: String
+    hasSample: [Sample]
+    hasData: [DataEntity]
+    omicsType: [OmicsType]!
+  }
+
+type DataEntity
+  {
+    id: Uriorcurie!
+    name: String
+    description: String
+    dataPath: String!
+    dataFormat: DataFormat!
+    hasSample: [Sample]
+    hasReference: ReferenceGenome
+  }
+
+type MODO
+  {
+    id: Uriorcurie!
+    name: String
+    description: String
+    creationDate: Datetime!
+    hasAssay: [Assay]
+    lastUpdateDate: Datetime!
+    sourceUri: Uri
+  }
+
+type MODOCollection
+  {
+    entries: [MODO]
+  }
+
 type NamedThing
   {
     id: Uriorcurie!
     name: String
     description: String
   }
 
-type Study
+type ReferenceGenome
+  {
+    id: Uriorcurie!
+    name: String
+    description: String
+    dataPath: String!
+    hasSequence: [ReferenceSequence]
+    taxonId: [Integer]
+    sourceUri: Uri
+    version: String
+  }
+
+type ReferenceSequence
+  {
+    id: Uriorcurie!
+    name: String
+    description: String
+    sequenceMd5: String
+    sourceUri: Uri
+    version: String
+  }
+
+type Sample
   {
     id: Uriorcurie!
     name: String
     description: String
-    primaryEmail: String
-    birthDate: Date
-    ageInYears: Integer
-    vitalStatus: PersonStatus
+    cellType: String
+    sourceMaterial: String
+    sex: Sex
+    taxonId: [Integer]
+    collector: [String]
   }
 
-type StudyCollection
+type VariantSet
   {
-    entries: [Study]
+    id: Uriorcurie!
+    name: String
+    description: String
+    dataPath: String!
+    dataFormat: DataFormat!
+    hasSample: [Sample]
+    hasReference: ReferenceGenome
   }
 

project/jsonld/smoc_schema.context.jsonld

@@ -1,49 +1,93 @@
 {
    "comments": {
       "description": "Auto generated by LinkML jsonld context generator",
-      "generation_date": "2023-12-18T22:01:04",
+      "generation_date": "2024-01-12T11:08:46",
       "source": "smoc_schema.yaml"
    },
    "@context": {
-      "PATO": {
-         "@id": "http://purl.obolibrary.org/obo/PATO_",
+      "EDAM": "http://edamontology.org/",
+      "FG": "https://w3id.org/fair-genomes/ontology/",
+      "GENO": {
+         "@id": "http://purl.obolibrary.org/obo/GENO_",
+         "@prefix": true
+      },
+      "NCIT": {
+         "@id": "http://purl.obolibrary.org/obo/NCIT_",
          "@prefix": true
       },
       "biolink": "https://w3id.org/biolink/",
+      "bioschemas": "https://bioschemas.org/",
       "example": "https://example.org/",
       "linkml": "https://w3id.org/linkml/",
       "schema": "http://schema.org/",
       "skos": "http://www.w3.org/2004/02/skos/core#",
-      "smoc_schema": "https://w3id.org/sdsc-ordes/smoc-schema/",
+      "smoc": "https://w3id.org/sdsc-ordes/smoc-schema/",
+      "sphn": "https://biomedit.ch/rdf/sphn-schema/sphn#",
       "@vocab": "https://w3id.org/sdsc-ordes/smoc-schema/",
-      "age_in_years": {
-         "@type": "xsd:integer"
+      "creation_date": {
+         "@type": "xsd:dateTime"
       },
-      "birth_date": {
-         "@type": "xsd:date",
-         "@id": "schema:birthDate"
+      "data_format": {
+         "@context": {
+            "@vocab": "@null",
+            "text": "skos:notation",
+            "description": "skos:prefLabel",
+            "meaning": "@id"
+         }
       },
       "description": {
          "@id": "schema:description"
       },
-      "id": "@id",
-      "name": {
-         "@id": "schema:name"
+      "has_assay": {
+         "@type": "@id"
+      },
+      "has_data": {
+         "@type": "@id"
       },
-      "primary_email": {
-         "@id": "schema:email"
+      "has_part": {
+         "@id": "schema:hasPart"
+      },
+      "has_reference": {
+         "@type": "@id"
+      },
+      "has_sample": {
+         "@type": "@id"
+      },
+      "has_sequence": {
+         "@type": "@id"
+      },
+      "id": "@id",
+      "last_update_date": {
+         "@type": "xsd:dateTime"
       },
       "entries": {
          "@type": "@id"
       },
-      "vital_status": {
+      "name": {
+         "@id": "schema:name"
+      },
+      "omics_type": {
+         "@context": {
+            "@vocab": "@null",
+            "text": "skos:notation",
+            "description": "skos:prefLabel",
+            "meaning": "@id"
+         }
+      },
+      "sex": {
          "@context": {
             "@vocab": "@null",
             "text": "skos:notation",
             "description": "skos:prefLabel",
             "meaning": "@id"
          }
       },
+      "source_uri": {
+         "@type": "@id"
+      },
+      "taxon_id": {
+         "@type": "xsd:integer"
+      },
       "NamedThing": {
          "@id": "schema:Thing"
       }