first draft linkml schema

docs/notes/linkml.md

@@ -0,0 +1,18 @@
+# LinkML
+
+Features of LinkML to keep in mind while writing the schema.
+
+
+- [Defining slots](https://linkml.io/linkml/schemas/advanced.html#defining-slots) - slots that
+  can be used to infer class identity - would be useful for inferring types in all the recursive
+  shit
+- [multidimensional arrays](https://linkml.io/linkml/howtos/multidimensional-arrays.html)
+- [units](https://linkml.io/linkml-model/docs/unit/)
+  - See also [modeling measurements](https://linkml.io/linkml/howtos/model-measurements.html)
+- modeling conditional presence https://github.com/linkml/linkml-model/issues/126
+
+
+## Python dataclass problems
+
+- Generator doesn't seem to honor the `slot_usage` property - eg. for the `Schema` class,
+  `doc` is marked as required despite the requirement being removed

docs/notes/schema.md

@@ -118,7 +118,7 @@ we need to map:
   - `neurodata_type_inc` -> `is_a`
 - Groups: 
 - Slots: Lots of properties are reused in the nwb spec, and LinkML lets us separate these out as slots
-- `quantity` needs a manual map
+- `quantity` needs a manual map to linkML's cardinality property
 - dims, shape, and dtypes: these should have been just attributes rather than put in the spec
   language, so we'll just make an Array class and use that.
   - dims and shape should probably be a dictionary so you don't need a zillion nulls, eg rather than 

nwb-schema-linkml/examples/Namespaces-001.yaml

@@ -1,7 +0,0 @@
-# Example data object
----
-entries:
-  - id: example:Namespaces001
-    name: foo bar
-    primary_email: foo.bar@example.com
-    age_in_years: 33

nwb-schema-linkml/examples/README.md

@@ -1,5 +0,0 @@
-# Examples of use of nwb_schema_language
-
-This folder contains example data conforming to nwb_schema_language
-
-The source for these is in [src/data](../src/data/examples)

nwb-schema-linkml/project/graphql/nwb_schema_language.graphql

@@ -1,23 +1,104 @@
-type NamedThing
+type AnyType
   {
-    id: Uriorcurie!
+  }
+
+type Attribute implements DtypeMixin
+  {
+    name: String!
+    dims: [String]
+    shape: [String]
+    value: AnyType
+    defaultValue: AnyType
+    doc: String!
+    required: Boolean
+    dtype: String
+  }
+
+type CompoundDtype
+  {
+    name: String!
+    doc: String!
+    dtype: FlatDtype!
+  }
+
+type Dataset implements DtypeMixin, NamingMixin
+  {
+    neurodataTypeDef: String
+    neurodataTypeInc: String
     name: String
-    description: String
+    defaultName: String
+    dims: [String]
+    shape: [String]
+    value: AnyType
+    defaultValue: AnyType
+    doc: String!
+    quantity: String
+    linkable: Boolean
+    attributes: [Attribute]
+    dtype: String
+  }
+
+interface DtypeMixin
+  {
+    dtype: String
+  }
+
+type Group implements NamingMixin
+  {
+    neurodataTypeDef: String
+    neurodataTypeInc: String
+    name: String
+    defaultName: String
+    doc: String!
+    quantity: String
+    linkable: Boolean
+    attributes: [Attribute]
+    datasets: [Dataset]
+    groups: [Group]
+    links: [Link]
+  }
+
+type Link
+  {
+    name: String
+    doc: String!
+    targetType: String!
+    quantity: String
+  }
+
+type Namespace
+  {
+    doc: String!
+    name: String!
+    fullName: String
+    version: String!
+    date: Date
+    author: [String]!
+    contact: [String]!
+    schema: [Schema]
   }
 
 type Namespaces
   {
-    id: Uriorcurie!
+    namespaces: [Namespace]
-    name: String
-    description: String
-    primaryEmail: String
-    birthDate: Date
-    ageInYears: Integer
-    vitalStatus: PersonStatus
   }
 
-type NamespacesCollection
+interface NamingMixin
   {
-    entries: [Namespaces]
+  }
+
+type ReferenceDtype
+  {
+    targetType: String!
+    reftype: ReftypeOptions
+  }
+
+type Schema
+  {
+    source: String
+    namespace: String
+    doc: String!
+    title: String
+    neurodataTypes: [String]
   }
 

nwb-schema-linkml/project/jsonld/nwb_schema_language.context.jsonld

@@ -1,42 +1,49 @@
 {
    "comments": {
       "description": "Auto generated by LinkML jsonld context generator",
-      "generation_date": "2023-08-16T15:57:40",
+      "generation_date": "2023-08-16T23:21:36",
       "source": "nwb_schema_language.yaml"
    },
    "@context": {
-      "PATO": {
-         "@id": "http://purl.obolibrary.org/obo/PATO_",
-         "@prefix": true
-      },
-      "biolink": "https://w3id.org/biolink/",
-      "example": "https://example.org/",
       "linkml": "https://w3id.org/linkml/",
       "nwb_schema_language": "https://w3id.org/p2p_ld/nwb-schema-language/",
-      "schema": "http://schema.org/",
+      "schema": {
-      "skos": "http://www.w3.org/2004/02/skos/core#",
-      "@vocab": "https://w3id.org/p2p_ld/nwb-schema-language/",
-      "age_in_years": {
-         "@type": "xsd:integer"
-      },
-      "birth_date": {
-         "@type": "xsd:date",
-         "@id": "schema:birthDate"
-      },
-      "description": {
-         "@id": "schema:description"
-      },
-      "id": "@id",
-      "name": {
-         "@id": "schema:name"
-      },
-      "entries": {
          "@type": "@id"
       },
-      "primary_email": {
+      "skos": "http://www.w3.org/2004/02/skos/core#",
+      "@vocab": "https://w3id.org/p2p_ld/nwb-schema-language/",
+      "attributes": {
+         "@type": "@id"
+      },
+      "author": {
+         "@id": "schema:author"
+      },
+      "contact": {
          "@id": "schema:email"
       },
-      "vital_status": {
+      "datasets": {
+         "@type": "@id"
+      },
+      "date": {
+         "@type": "xsd:date",
+         "@id": "schema:dateModified"
+      },
+      "default_value": {
+         "@type": "@id"
+      },
+      "groups": {
+         "@type": "@id"
+      },
+      "linkable": {
+         "@type": "xsd:boolean"
+      },
+      "links": {
+         "@type": "@id"
+      },
+      "namespaces": {
+         "@type": "@id"
+      },
+      "reftype": {
          "@context": {
             "@vocab": "@null",
             "text": "skos:notation",
@@ -44,8 +51,14 @@
             "meaning": "@id"
          }
       },
-      "NamedThing": {
+      "required": {
-         "@id": "schema:Thing"
+         "@type": "xsd:boolean"
+      },
+      "value": {
+         "@type": "@id"
+      },
+      "AnyType": {
+         "@id": "linkml:Any"
       }
    }
 }

nwb-schema-linkml/project/jsonschema/nwb_schema_language.schema.json

@@ -1,160 +1,571 @@
 {
     "$defs": {
-        "NamedThing": {
+        "AnyType": {
+            "additionalProperties": true,
+            "description": "",
+            "title": "AnyType",
+            "type": "object"
+        },
+        "Attribute": {
             "additionalProperties": false,
-            "description": "A generic grouping for any identifiable entity",
+            "description": "",
             "properties": {
-                "description": {
+                "default_value": {
-                    "description": "A human-readable description for a thing",
+                    "$ref": "#/$defs/AnyType",
+                    "description": "Optional default value for variable-valued attributes."
+                },
+                "dims": {
+                    "items": {
                         "type": "string"
                     },
-                "id": {
+                    "type": "array"
-                    "description": "A unique identifier for a thing",
+                },
+                "doc": {
+                    "description": "Description of corresponding object.",
+                    "type": "string"
+                },
+                "dtype": {
+                    "oneOf": [
+                        {
+                            "$ref": "#/$defs/FlatDtype"
+                        },
+                        {
+                            "$ref": "#/$defs/CompoundDtype"
+                        },
+                        {
+                            "$ref": "#/$defs/ReferenceDtype"
+                        }
+                    ],
                     "type": "string"
                 },
                 "name": {
-                    "description": "A human-readable name for a thing",
+                    "type": "string"
+                },
+                "required": {
+                    "description": "Optional boolean key describing whether the attribute is required. Default value is True.",
+                    "type": "boolean"
+                },
+                "shape": {
+                    "items": {
+                        "oneOf": [
+                            {
+                                "minimum": 1,
+                                "type": "integer"
+                            },
+                            {
+                                "const": "null"
+                            }
+                        ],
+                        "type": "string"
+                    },
+                    "type": "array"
+                },
+                "value": {
+                    "$ref": "#/$defs/AnyType",
+                    "description": "Optional constant, fixed value for the attribute."
+                }
+            },
+            "required": [
+                "name",
+                "doc"
+            ],
+            "title": "Attribute",
+            "type": "object"
+        },
+        "CompoundDtype": {
+            "additionalProperties": false,
+            "description": "",
+            "properties": {
+                "doc": {
+                    "description": "Description of corresponding object.",
+                    "type": "string"
+                },
+                "dtype": {
+                    "$ref": "#/$defs/FlatDtype"
+                },
+                "name": {
                     "type": "string"
                 }
             },
             "required": [
-                "id"
+                "name",
+                "doc",
+                "dtype"
             ],
-            "title": "NamedThing",
+            "title": "CompoundDtype",
+            "type": "object"
+        },
+        "Dataset": {
+            "additionalProperties": false,
+            "description": "",
+            "properties": {
+                "attributes": {
+                    "items": {
+                        "$ref": "#/$defs/Attribute"
+                    },
+                    "type": "array"
+                },
+                "default_name": {
+                    "type": "string"
+                },
+                "default_value": {
+                    "$ref": "#/$defs/AnyType",
+                    "description": "Optional default value for variable-valued attributes."
+                },
+                "dims": {
+                    "items": {
+                        "type": "string"
+                    },
+                    "type": "array"
+                },
+                "doc": {
+                    "description": "Description of corresponding object.",
+                    "type": "string"
+                },
+                "dtype": {
+                    "oneOf": [
+                        {
+                            "$ref": "#/$defs/FlatDtype"
+                        },
+                        {
+                            "$ref": "#/$defs/CompoundDtype"
+                        },
+                        {
+                            "$ref": "#/$defs/ReferenceDtype"
+                        }
+                    ],
+                    "type": "string"
+                },
+                "linkable": {
+                    "type": "boolean"
+                },
+                "name": {
+                    "type": "string"
+                },
+                "neurodata_type_def": {
+                    "type": "string"
+                },
+                "neurodata_type_inc": {
+                    "type": "string"
+                },
+                "quantity": {
+                    "anyOf": [
+                        {
+                            "minimum": 1,
+                            "type": "integer"
+                        },
+                        {
+                            "$ref": "#/$defs/QuantityEnum"
+                        }
+                    ],
+                    "type": "string"
+                },
+                "shape": {
+                    "items": {
+                        "oneOf": [
+                            {
+                                "minimum": 1,
+                                "type": "integer"
+                            },
+                            {
+                                "const": "null"
+                            }
+                        ],
+                        "type": "string"
+                    },
+                    "type": "array"
+                },
+                "value": {
+                    "$ref": "#/$defs/AnyType",
+                    "description": "Optional constant, fixed value for the attribute."
+                }
+            },
+            "required": [
+                "doc"
+            ],
+            "title": "Dataset",
+            "type": "object"
+        },
+        "FlatDtype": {
+            "description": "",
+            "enum": [
+                "float",
+                "float32",
+                "double",
+                "float64",
+                "long",
+                "int64",
+                "int",
+                "int32",
+                "int16",
+                "short",
+                "int8",
+                "uint",
+                "uint32",
+                "uint16",
+                "uint8",
+                "uint64",
+                "numeric",
+                "text",
+                "utf",
+                "utf8",
+                "utf-8",
+                "ascii",
+                "bool",
+                "isodatetime"
+            ],
+            "title": "FlatDtype",
+            "type": "string"
+        },
+        "Group": {
+            "additionalProperties": false,
+            "description": "",
+            "properties": {
+                "attributes": {
+                    "items": {
+                        "$ref": "#/$defs/Attribute"
+                    },
+                    "type": "array"
+                },
+                "datasets": {
+                    "items": {
+                        "$ref": "#/$defs/Dataset"
+                    },
+                    "type": "array"
+                },
+                "default_name": {
+                    "type": "string"
+                },
+                "doc": {
+                    "description": "Description of corresponding object.",
+                    "type": "string"
+                },
+                "groups": {
+                    "items": {
+                        "$ref": "#/$defs/Group"
+                    },
+                    "type": "array"
+                },
+                "linkable": {
+                    "type": "boolean"
+                },
+                "links": {
+                    "items": {
+                        "$ref": "#/$defs/Link"
+                    },
+                    "type": "array"
+                },
+                "name": {
+                    "type": "string"
+                },
+                "neurodata_type_def": {
+                    "type": "string"
+                },
+                "neurodata_type_inc": {
+                    "type": "string"
+                },
+                "quantity": {
+                    "anyOf": [
+                        {
+                            "minimum": 1,
+                            "type": "integer"
+                        },
+                        {
+                            "$ref": "#/$defs/QuantityEnum"
+                        }
+                    ],
+                    "type": "string"
+                }
+            },
+            "required": [
+                "doc"
+            ],
+            "title": "Group",
+            "type": "object"
+        },
+        "Link": {
+            "additionalProperties": false,
+            "description": "",
+            "properties": {
+                "doc": {
+                    "description": "Description of corresponding object.",
+                    "type": "string"
+                },
+                "name": {
+                    "type": "string"
+                },
+                "quantity": {
+                    "anyOf": [
+                        {
+                            "minimum": 1,
+                            "type": "integer"
+                        },
+                        {
+                            "$ref": "#/$defs/QuantityEnum"
+                        }
+                    ],
+                    "type": "string"
+                },
+                "target_type": {
+                    "anyOf": [
+                        {
+                            "$ref": "#/$defs/Dataset"
+                        },
+                        {
+                            "$ref": "#/$defs/Group"
+                        }
+                    ],
+                    "description": "Describes the neurodata_type of the target that the reference points to",
+                    "type": "string"
+                }
+            },
+            "required": [
+                "doc",
+                "target_type"
+            ],
+            "title": "Link",
+            "type": "object"
+        },
+        "Namespace": {
+            "additionalProperties": false,
+            "description": "",
+            "properties": {
+                "author": {
+                    "description": "List of strings with the names of the authors of the namespace.",
+                    "items": {
+                        "type": "string"
+                    },
+                    "type": "array"
+                },
+                "contact": {
+                    "description": "List of strings with the contact information for the authors. Ordering of the contacts should match the ordering of the authors.",
+                    "items": {
+                        "type": "string"
+                    },
+                    "type": "array"
+                },
+                "date": {
+                    "description": "Date that a namespace was last modified or released",
+                    "format": "date",
+                    "type": "string"
+                },
+                "doc": {
+                    "description": "Description of corresponding object.",
+                    "type": "string"
+                },
+                "full_name": {
+                    "description": "Optional string with extended full name for the namespace.",
+                    "type": "string"
+                },
+                "name": {
+                    "type": "string"
+                },
+                "schema": {
+                    "description": "List of the schema to be included in this namespace.",
+                    "items": {
+                        "$ref": "#/$defs/Schema"
+                    },
+                    "type": "array"
+                },
+                "version": {
+                    "pattern": "^(0|[1-9]\\d*)\\.(0|[1-9]\\d*)\\.(0|[1-9]\\d*)(?:-((?:0|[1-9]\\d*|\\d*[a-zA-Z-][0-9a-zA-Z-]*)(?:\\.(?:0|[1-9]\\d*|\\d*[a-zA-Z-][0-9a-zA-Z-]*))*))?(?:\\+([0-9a-zA-Z-]+(?:\\.[0-9a-zA-Z-]+)*))?$",
+                    "type": "string"
+                }
+            },
+            "required": [
+                "doc",
+                "name",
+                "version",
+                "author",
+                "contact"
+            ],
+            "title": "Namespace",
             "type": "object"
         },
         "Namespaces": {
             "additionalProperties": false,
-            "description": "Represents a Namespaces",
+            "description": "",
             "properties": {
-                "age_in_years": {
+                "namespaces": {
-                    "description": "Number of years since birth",
+                    "items": {
-                    "type": "integer"
+                        "$ref": "#/$defs/Namespace"
                     },
-                "birth_date": {
+                    "type": "array"
-                    "description": "Date on which a person is born",
+                }
-                    "format": "date",
+            },
+            "title": "Namespaces",
+            "type": "object"
+        },
+        "QuantityEnum": {
+            "description": "",
+            "enum": [
+                "*",
+                "?",
+                "+",
+                "zero_or_many",
+                "one_or_many",
+                "zero_or_one"
+            ],
+            "title": "QuantityEnum",
             "type": "string"
         },
-                "description": {
+        "ReferenceDtype": {
-                    "description": "A human-readable description for a thing",
+            "additionalProperties": false,
-                    "type": "string"
+            "description": "",
+            "properties": {
+                "reftype": {
+                    "$ref": "#/$defs/ReftypeOptions",
+                    "description": "describes the kind of reference"
                 },
-                "id": {
+                "target_type": {
-                    "description": "A unique identifier for a thing",
+                    "anyOf": [
-                    "type": "string"
+                        {
+                            "$ref": "#/$defs/Dataset"
                         },
-                "name": {
+                        {
-                    "description": "A human-readable name for a thing",
+                            "$ref": "#/$defs/Group"
+                        }
+                    ],
+                    "description": "Describes the neurodata_type of the target that the reference points to",
                     "type": "string"
-                },
-                "primary_email": {
-                    "description": "The main email address of a person",
-                    "pattern": "^\\S+@[\\S+\\.]+\\S+",
-                    "type": "string"
-                },
-                "vital_status": {
-                    "$ref": "#/$defs/PersonStatus",
-                    "description": "living or dead status"
                 }
             },
             "required": [
-                "id"
+                "target_type"
             ],
-            "title": "Namespaces",
+            "title": "ReferenceDtype",
             "type": "object"
         },
-        "NamespacesCollection": {
+        "ReftypeOptions": {
-            "additionalProperties": false,
-            "description": "A holder for Namespaces objects",
-            "properties": {
-                "entries": {
-                    "additionalProperties": {
-                        "anyOf": [
-                            {
-                                "$ref": "#/$defs/Namespaces__identifier_optional"
-                            },
-                            {
-                                "type": "null"
-                            }
-                        ]
-                    },
-                    "type": "object"
-                }
-            },
-            "title": "NamespacesCollection",
-            "type": "object"
-        },
-        "Namespaces__identifier_optional": {
-            "additionalProperties": false,
-            "description": "Represents a Namespaces",
-            "properties": {
-                "age_in_years": {
-                    "description": "Number of years since birth",
-                    "type": "integer"
-                },
-                "birth_date": {
-                    "description": "Date on which a person is born",
-                    "format": "date",
-                    "type": "string"
-                },
-                "description": {
-                    "description": "A human-readable description for a thing",
-                    "type": "string"
-                },
-                "id": {
-                    "description": "A unique identifier for a thing",
-                    "type": "string"
-                },
-                "name": {
-                    "description": "A human-readable name for a thing",
-                    "type": "string"
-                },
-                "primary_email": {
-                    "description": "The main email address of a person",
-                    "pattern": "^\\S+@[\\S+\\.]+\\S+",
-                    "type": "string"
-                },
-                "vital_status": {
-                    "$ref": "#/$defs/PersonStatus",
-                    "description": "living or dead status"
-                }
-            },
-            "required": [],
-            "title": "Namespaces",
-            "type": "object"
-        },
-        "PersonStatus": {
             "description": "",
             "enum": [
-                "ALIVE",
+                "ref",
-                "DEAD",
+                "reference",
-                "UNKNOWN"
+                "object",
+                "region"
             ],
-            "title": "PersonStatus",
+            "title": "ReftypeOptions",
             "type": "string"
+        },
+        "Schema": {
+            "additionalProperties": false,
+            "allOf": [
+                {
+                    "if": {
+                        "properties": {
+                            "namespace": {}
+                        },
+                        "required": [
+                            "namespace"
+                        ]
+                    },
+                    "then": {
+                        "properties": {
+                            "source": {}
+                        },
+                        "required": [
+                            "source"
+                        ]
+                    }
+                },
+                {
+                    "if": {
+                        "properties": {
+                            "source": {}
+                        },
+                        "required": [
+                            "source"
+                        ]
+                    },
+                    "then": {
+                        "properties": {
+                            "namespace": {}
+                        },
+                        "required": [
+                            "namespace"
+                        ]
+                    }
+                },
+                {
+                    "if": {
+                        "properties": {
+                            "namespace": {}
+                        },
+                        "required": [
+                            "namespace"
+                        ]
+                    },
+                    "then": {
+                        "properties": {
+                            "source": {}
+                        },
+                        "required": [
+                            "source"
+                        ]
+                    }
+                },
+                {
+                    "if": {
+                        "properties": {
+                            "source": {}
+                        },
+                        "required": [
+                            "source"
+                        ]
+                    },
+                    "then": {
+                        "properties": {
+                            "namespace": {}
+                        },
+                        "required": [
+                            "namespace"
+                        ]
+                    }
+                }
+            ],
+            "description": "",
+            "properties": {
+                "doc": {
+                    "description": "Description of corresponding object.",
+                    "type": "string"
+                },
+                "namespace": {
+                    "description": "describes a named reference to another namespace. In contrast to source, this is a reference by name to a known namespace (i.e., the namespace is resolved during the build and must point to an already existing namespace). This mechanism is used to allow, e.g., extension of a core namespace (here the NWB core namespace) without requiring hard paths to the files describing the core namespace. Either source or namespace must be specified, but not both.",
+                    "type": "string"
+                },
+                "neurodata_types": {
+                    "description": "an optional list of strings indicating which data types should be included from the given specification source or namespace. The default is null indicating that all data types should be included.",
+                    "items": {
+                        "anyOf": [
+                            {
+                                "$ref": "#/$defs/Dataset"
+                            },
+                            {
+                                "$ref": "#/$defs/Group"
+                            }
+                        ],
+                        "type": "string"
+                    },
+                    "type": "array"
+                },
+                "source": {
+                    "description": "describes the name of the YAML (or JSON) file with the schema specification. The schema files should be located in the same folder as the namespace file.",
+                    "pattern": ".*\\.(yml|yaml|json)",
+                    "type": "string"
+                },
+                "title": {
+                    "description": "a descriptive title for a file for documentation purposes.",
+                    "type": "string"
+                }
+            },
+            "title": "Schema",
+            "type": "object"
         }
     },
     "$id": "https://w3id.org/p2p_ld/nwb-schema-language",
     "$schema": "http://json-schema.org/draft-07/schema#",
     "additionalProperties": true,
-    "description": "A holder for Namespaces objects",
     "metamodel_version": "1.7.0",
-    "properties": {
-        "entries": {
-            "additionalProperties": {
-                "anyOf": [
-                    {
-                        "$ref": "#/$defs/Namespaces__identifier_optional"
-                    },
-                    {
-                        "type": "null"
-                    }
-                ]
-            },
-            "type": "object"
-        }
-    },
     "title": "nwb-schema-language",
     "type": "object",
     "version": null

nwb-schema-linkml/project/prefixmap/nwb_schema_language.yaml

@@ -1,11 +1,8 @@
 {
-   "PATO": "http://purl.obolibrary.org/obo/PATO_",
-   "biolink": "https://w3id.org/biolink/",
-   "example": "https://example.org/",
    "linkml": "https://w3id.org/linkml/",
    "nwb_schema_language": "https://w3id.org/p2p_ld/nwb-schema-language/",
    "schema": "http://schema.org/",
-   "NamedThing": {
+   "AnyType": {
-      "@id": "schema:Thing"
+      "@id": "linkml:Any"
    }
 }

nwb-schema-linkml/project/protobuf/nwb_schema_language.proto

@@ -1,23 +1,82 @@
-// A generic grouping for any identifiable entity
+message Attribute
-message NamedThing
  {
-  uriorcurie id = 0
   string name = 0
-  string description = 0
+ repeated  string dims = 0
+ repeated  string shape = 0
+  anyType value = 0
+  anyType defaultValue = 0
+  string doc = 0
+  boolean required = 0
+  string dtype = 0
+ }
+message CompoundDtype
+ {
+  string name = 0
+  string doc = 0
+  flatDtype dtype = 0
+ }
+message Dataset
+ {
+  string neurodataTypeDef = 0
+  string neurodataTypeInc = 0
+  string name = 0
+  string defaultName = 0
+ repeated  string dims = 0
+ repeated  string shape = 0
+  anyType value = 0
+  anyType defaultValue = 0
+  string doc = 0
+  string quantity = 0
+  boolean linkable = 0
+ repeated  attribute attributes = 0
+  string dtype = 0
+ }
+message Group
+ {
+  string neurodataTypeDef = 0
+  string neurodataTypeInc = 0
+  string name = 0
+  string defaultName = 0
+  string doc = 0
+  string quantity = 0
+  boolean linkable = 0
+ repeated  attribute attributes = 0
+ repeated  dataset datasets = 0
+ repeated  group groups = 0
+ repeated  link links = 0
+ }
+message Link
+ {
+  string name = 0
+  string doc = 0
+  string targetType = 0
+  string quantity = 0
+ }
+message Namespace
+ {
+  string doc = 0
+  string name = 0
+  string fullName = 0
+  string version = 0
+  date date = 0
+ repeated  string author = 0
+ repeated  string contact = 0
+ repeated  schema schema = 0
  }
-// Represents a Namespaces
 message Namespaces
  {
-  uriorcurie id = 0
+ repeated  namespace namespaces = 0
-  string name = 0
-  string description = 0
-  string primaryEmail = 0
-  date birthDate = 0
-  integer ageInYears = 0
-  personStatus vitalStatus = 0
  }
-// A holder for Namespaces objects
+message ReferenceDtype
-message NamespacesCollection
  {
- repeated  namespaces entries = 0
+  string targetType = 0
+  reftypeOptions reftype = 0
+ }
+message Schema
+ {
+  string source = 0
+  string namespace = 0
+  string doc = 0
+  string title = 0
+ repeated  string neurodataTypes = 0
  }

nwb-schema-linkml/project/shex/nwb_schema_language.shex

@@ -43,31 +43,137 @@ linkml:Jsonpath xsd:string
 
 linkml:Sparqlpath xsd:string
 
-<NamedThing>  (
+<AnyType> CLOSED {
-    CLOSED {
+    (  $<AnyType_tes> rdf:type . * ;
-       (  $<NamedThing_tes> (  schema1:name @linkml:String ? ;
+       rdf:type [ linkml:Any ] ?
-             schema1:description @linkml:String ?
+    )
+}
+
+<Attribute> CLOSED {
+    (  $<Attribute_tes> (  &<DtypeMixin_tes> ;
+          rdf:type [ <DtypeMixin> ] ? ;
+          <name> @linkml:String ;
+          <dims> @linkml:String * ;
+          <shape> @linkml:String * ;
+          <value> @<AnyType> ? ;
+          <default_value> @<AnyType> ? ;
+          <doc> @linkml:String ;
+          <required> @linkml:Boolean ? ;
+          <dtype> @linkml:String ?
        ) ;
-          rdf:type [ schema1:Thing ]
+       rdf:type [ <Attribute> ] ?
     )
-    } OR @<Namespaces>
+}
+
+<CompoundDtype> CLOSED {
+    (  $<CompoundDtype_tes> (  <name> @linkml:String ;
+          <doc> @linkml:String ;
+          <dtype> @<FlatDtype>
+       ) ;
+       rdf:type [ <CompoundDtype> ] ?
     )
+}
+
+<Dataset> CLOSED {
+    (  $<Dataset_tes> (  &<DtypeMixin_tes> ;
+          rdf:type [ <DtypeMixin> ] ? ;
+          &<NamingMixin_tes> ;
+          rdf:type [ <NamingMixin> ] ? ;
+          <neurodata_type_def> @linkml:String ? ;
+          <neurodata_type_inc> @linkml:String ? ;
+          <name> @linkml:String ? ;
+          <default_name> @linkml:String ? ;
+          <dims> @linkml:String * ;
+          <shape> @linkml:String * ;
+          <value> @<AnyType> ? ;
+          <default_value> @<AnyType> ? ;
+          <doc> @linkml:String ;
+          <quantity> @linkml:String ? ;
+          <linkable> @linkml:Boolean ? ;
+          <attributes> @<Attribute> * ;
+          <dtype> @linkml:String ?
+       ) ;
+       rdf:type [ <Dataset> ] ?
+    )
+}
+
+<DtypeMixin> {
+    (  $<DtypeMixin_tes> <dtype> @linkml:String ? ;
+       rdf:type [ <DtypeMixin> ] ?
+    )
+}
+
+<Group> CLOSED {
+    (  $<Group_tes> (  &<NamingMixin_tes> ;
+          rdf:type [ <NamingMixin> ] ? ;
+          <neurodata_type_def> @linkml:String ? ;
+          <neurodata_type_inc> @linkml:String ? ;
+          <name> @linkml:String ? ;
+          <default_name> @linkml:String ? ;
+          <doc> @linkml:String ;
+          <quantity> @linkml:String ? ;
+          <linkable> @linkml:Boolean ? ;
+          <attributes> @<Attribute> * ;
+          <datasets> @<Dataset> * ;
+          <groups> @<Group> * ;
+          <links> @<Link> *
+       ) ;
+       rdf:type [ <Group> ] ?
+    )
+}
+
+<Link> CLOSED {
+    (  $<Link_tes> (  <name> @linkml:String ? ;
+          <doc> @linkml:String ;
+          <target_type> @linkml:String ;
+          <quantity> @linkml:String ?
+       ) ;
+       rdf:type [ <Link> ] ?
+    )
+}
+
+<Namespace> CLOSED {
+    (  $<Namespace_tes> (  <doc> @linkml:String ;
+          <name> @linkml:String ;
+          <full_name> @linkml:String ? ;
+          <version> @linkml:String ;
+          schema1:dateModified @linkml:Date ? ;
+          schema1:author @linkml:String + ;
+          schema1:email @linkml:String + ;
+          <schema> @<Schema> *
+       ) ;
+       rdf:type [ <Namespace> ] ?
+    )
+}
 
 <Namespaces> CLOSED {
-    (  $<Namespaces_tes> (  &<NamedThing_tes> ;
+    (  $<Namespaces_tes> <namespaces> @<Namespace> * ;
-          rdf:type [ schema1:Thing ] ? ;
+       rdf:type [ <Namespaces> ] ?
-          schema1:email @linkml:String ? ;
+    )
-          schema1:birthDate @linkml:Date ? ;
+}
-          <age_in_years> @linkml:Integer ? ;
+
-          <vital_status> @<PersonStatus> ?
+<NamingMixin> {
+    (  $<NamingMixin_tes> rdf:type . * ;
+       rdf:type [ <NamingMixin> ] ?
+    )
+}
+
+<ReferenceDtype> CLOSED {
+    (  $<ReferenceDtype_tes> (  <target_type> @linkml:String ;
+          <reftype> @<ReftypeOptions> ?
        ) ;
-       rdf:type [ <Namespaces> ]
+       rdf:type [ <ReferenceDtype> ] ?
     )
 }
 
-<NamespacesCollection> CLOSED {
+<Schema> CLOSED {
-    (  $<NamespacesCollection_tes> <entries> @<Namespaces> * ;
+    (  $<Schema_tes> (  <source> @linkml:String ? ;
-       rdf:type [ <NamespacesCollection> ] ?
+          <namespace> @linkml:String ? ;
+          <doc> @linkml:String ;
+          <title> @linkml:String ? ;
+          <neurodata_types> @linkml:String *
+       ) ;
+       rdf:type [ <Schema> ] ?
     )
 }
 

nwb-schema-linkml/project/sqlschema/nwb_schema_language.sql

@@ -1,24 +1,92 @@
 
 
-CREATE TABLE "NamedThing" (
+CREATE TABLE "Attribute" (
-	id TEXT NOT NULL, 
+	name TEXT NOT NULL, 
+	dims TEXT, 
+	shape TEXT, 
+	value TEXT, 
+	default_value TEXT, 
+	doc TEXT NOT NULL, 
+	required BOOLEAN, 
+	dtype TEXT, 
+	PRIMARY KEY (name, dims, shape, value, default_value, doc, required, dtype)
+);
+
+CREATE TABLE "CompoundDtype" (
+	name TEXT NOT NULL, 
+	doc TEXT NOT NULL, 
+	dtype VARCHAR(11) NOT NULL, 
+	PRIMARY KEY (name, doc, dtype)
+);
+
+CREATE TABLE "Dataset" (
+	neurodata_type_def TEXT, 
+	neurodata_type_inc TEXT, 
 	name TEXT, 
-	description TEXT, 
+	default_name TEXT, 
-	PRIMARY KEY (id)
+	dims TEXT, 
+	shape TEXT, 
+	value TEXT, 
+	default_value TEXT, 
+	doc TEXT NOT NULL, 
+	quantity TEXT, 
+	linkable BOOLEAN, 
+	attributes TEXT, 
+	dtype TEXT, 
+	PRIMARY KEY (neurodata_type_def, neurodata_type_inc, name, default_name, dims, shape, value, default_value, doc, quantity, linkable, attributes, dtype)
+);
+
+CREATE TABLE "Group" (
+	neurodata_type_def TEXT, 
+	neurodata_type_inc TEXT, 
+	name TEXT, 
+	default_name TEXT, 
+	doc TEXT NOT NULL, 
+	quantity TEXT, 
+	linkable BOOLEAN, 
+	attributes TEXT, 
+	datasets TEXT, 
+	groups TEXT, 
+	links TEXT, 
+	PRIMARY KEY (neurodata_type_def, neurodata_type_inc, name, default_name, doc, quantity, linkable, attributes, datasets, groups, links)
+);
+
+CREATE TABLE "Link" (
+	name TEXT, 
+	doc TEXT NOT NULL, 
+	target_type TEXT NOT NULL, 
+	quantity TEXT, 
+	PRIMARY KEY (name, doc, target_type, quantity)
+);
+
+CREATE TABLE "Namespace" (
+	doc TEXT NOT NULL, 
+	name TEXT NOT NULL, 
+	full_name TEXT, 
+	version TEXT NOT NULL, 
+	date DATE, 
+	author TEXT NOT NULL, 
+	contact TEXT NOT NULL, 
+	schema TEXT, 
+	PRIMARY KEY (doc, name, full_name, version, date, author, contact, schema)
 );
 
 CREATE TABLE "Namespaces" (
-	id TEXT NOT NULL, 
+	namespaces TEXT, 
-	name TEXT, 
+	PRIMARY KEY (namespaces)
-	description TEXT, 
-	primary_email TEXT, 
-	birth_date DATE, 
-	age_in_years INTEGER, 
-	vital_status VARCHAR(7), 
-	PRIMARY KEY (id)
 );
 
-CREATE TABLE "NamespacesCollection" (
+CREATE TABLE "ReferenceDtype" (
-	entries TEXT, 
+	target_type TEXT NOT NULL, 
-	PRIMARY KEY (entries)
+	reftype VARCHAR(9), 
+	PRIMARY KEY (target_type, reftype)
+);
+
+CREATE TABLE "Schema" (
+	source TEXT, 
+	namespace TEXT, 
+	doc TEXT NOT NULL, 
+	title TEXT, 
+	neurodata_types TEXT, 
+	PRIMARY KEY (source, namespace, doc, title, neurodata_types)
 );

nwb-schema-linkml/pyproject.toml

@@ -5,6 +5,9 @@ description = "Translation of the nwb-schema-language to LinkML"
 authors = ["Jonny Saunders <j@nny.fyi>"]
 license = "GNU GPL v3.0"
 readme = "README.md"
+packages = [
+    { include = "nwb_schema_language", from="src"}
+]
 include = ["README.md", "src/nwb_schema_language/schema", "project"]
 
 [tool.poetry.dependencies]

nwb-schema-linkml/src/data/examples/Namespaces-001.yaml

@@ -1,7 +0,0 @@
-# Example data object
----
-entries:
-  - id: example:Namespaces001
-    name: foo bar
-    primary_email: foo.bar@example.com
-    age_in_years: 33

nwb-schema-linkml/src/data/tests/nwb.base.yaml

@@ -0,0 +1,264 @@
+datasets:
+- neurodata_type_def: NWBData
+  neurodata_type_inc: Data
+  doc: An abstract data type for a dataset.
+
+- neurodata_type_def: TimeSeriesReferenceVectorData
+  neurodata_type_inc: VectorData
+  default_name: timeseries
+  dtype:
+  - name: idx_start
+    dtype: int32
+    doc: Start index into the TimeSeries 'data' and 'timestamp' datasets of the referenced
+      TimeSeries. The first dimension of those arrays is always time.
+  - name: count
+    dtype: int32
+    doc: Number of data samples available in this time series, during this epoch
+  - name: timeseries
+    dtype:
+      target_type: TimeSeries
+      reftype: object
+    doc: The TimeSeries that this index applies to
+  doc: Column storing references to a TimeSeries (rows). For each TimeSeries this
+    VectorData column stores the start_index and count to indicate the range in time
+    to be selected as well as an object reference to the TimeSeries.
+
+- neurodata_type_def: Image
+  neurodata_type_inc: NWBData
+  dtype: numeric
+  dims:
+  - - x
+    - y
+  - - x
+    - y
+    - r, g, b
+  - - x
+    - y
+    - r, g, b, a
+  shape:
+  - - null
+    - null
+  - - null
+    - null
+    - 3
+  - - null
+    - null
+    - 4
+  doc: An abstract data type for an image. Shape can be 2-D (x, y), or 3-D where the
+    third dimension can have three or four elements, e.g. (x, y, (r, g, b)) or
+    (x, y, (r, g, b, a)).
+  attributes:
+  - name: resolution
+    dtype: float32
+    doc: Pixel resolution of the image, in pixels per centimeter.
+    required: false
+  - name: description
+    dtype: text
+    doc: Description of the image.
+    required: false
+
+- neurodata_type_def: ImageReferences
+  neurodata_type_inc: NWBData
+  dtype:
+    target_type: Image
+    reftype: object
+  dims:
+  - num_images
+  shape:
+  - null
+  doc: Ordered dataset of references to Image objects.
+
+groups:
+- neurodata_type_def: NWBContainer
+  neurodata_type_inc: Container
+  doc: An abstract data type for a generic container storing collections of data and
+    metadata. Base type for all data and metadata containers.
+
+- neurodata_type_def: NWBDataInterface
+  neurodata_type_inc: NWBContainer
+  doc: An abstract data type for a generic container storing collections of data,
+    as opposed to metadata.
+
+- neurodata_type_def: TimeSeries
+  neurodata_type_inc: NWBDataInterface
+  doc: General purpose time series.
+  attributes:
+  - name: description
+    dtype: text
+    default_value: no description
+    doc: Description of the time series.
+    required: false
+  - name: comments
+    dtype: text
+    default_value: no comments
+    doc: Human-readable comments about the TimeSeries. This second descriptive field
+      can be used to store additional information, or descriptive information if the
+      primary description field is populated with a computer-readable string.
+    required: false
+  datasets:
+  - name: data
+    dims:
+    - - num_times
+    - - num_times
+      - num_DIM2
+    - - num_times
+      - num_DIM2
+      - num_DIM3
+    - - num_times
+      - num_DIM2
+      - num_DIM3
+      - num_DIM4
+    shape:
+    - - null
+    - - null
+      - null
+    - - null
+      - null
+      - null
+    - - null
+      - null
+      - null
+      - null
+    doc: Data values. Data can be in 1-D, 2-D, 3-D, or 4-D. The first dimension
+      should always represent time. This can also be used to store binary data
+      (e.g., image frames). This can also be a link to data stored in an external file.
+    attributes:
+    - name: conversion
+      dtype: float32
+      default_value: 1.0
+      doc: Scalar to multiply each element in data to convert it to the specified 'unit'.
+        If the data are stored in acquisition system units or other units
+        that require a conversion to be interpretable, multiply the data by 'conversion'
+        to convert the data to the specified 'unit'. e.g. if the data acquisition system
+        stores values in this object as signed 16-bit integers (int16 range
+        -32,768 to 32,767) that correspond to a 5V range (-2.5V to 2.5V), and the data
+        acquisition system gain is 8000X, then the 'conversion' multiplier to get from
+        raw data acquisition values to recorded volts is 2.5/32768/8000 = 9.5367e-9.
+      required: false
+    - name: offset
+      dtype: float32
+      default_value: 0.0
+      doc: Scalar to add to the data after scaling by 'conversion' to finalize its coercion
+        to the specified 'unit'. Two common examples of this include (a) data stored in an
+        unsigned type that requires a shift after scaling to re-center the data,
+        and (b) specialized recording devices that naturally cause a scalar offset with
+        respect to the true units.
+      required: false
+    - name: resolution
+      dtype: float32
+      default_value: -1.0
+      doc: Smallest meaningful difference between values in data, stored in the specified
+        by unit, e.g., the change in value of the least significant bit, or a larger
+        number if signal noise is known to be present. If unknown, use -1.0.
+      required: false
+    - name: unit
+      dtype: text
+      doc: Base unit of measurement for working with the data. Actual stored values are
+        not necessarily stored in these units. To access the data in these units,
+        multiply 'data' by 'conversion' and add 'offset'.
+    - name: continuity
+      dtype: text
+      doc: Optionally describe the continuity of the data. Can be "continuous", "instantaneous", or
+        "step". For example, a voltage trace would be "continuous", because samples
+        are recorded from a continuous process. An array of lick times would be "instantaneous",
+        because the data represents distinct moments in time. Times of image presentations would be
+        "step" because the picture remains the same until the next timepoint. This field is optional,
+        but is useful in providing information about the underlying data. It may inform the way this
+        data is interpreted, the way it is visualized, and what analysis methods are applicable.
+      required: false
+  - name: starting_time
+    dtype: float64
+    doc: Timestamp of the first sample in seconds. When timestamps are uniformly
+      spaced, the timestamp of the first sample can be specified and all subsequent
+      ones calculated from the sampling rate attribute.
+    quantity: '?'
+    attributes:
+    - name: rate
+      dtype: float32
+      doc: Sampling rate, in Hz.
+    - name: unit
+      dtype: text
+      value: seconds
+      doc: Unit of measurement for time, which is fixed to 'seconds'.
+  - name: timestamps
+    dtype: float64
+    dims:
+    - num_times
+    shape:
+    - null
+    doc: Timestamps for samples stored in data, in seconds, relative to the
+      common experiment master-clock stored in NWBFile.timestamps_reference_time.
+    quantity: '?'
+    attributes:
+    - name: interval
+      dtype: int32
+      value: 1
+      doc: Value is '1'
+    - name: unit
+      dtype: text
+      value: seconds
+      doc: Unit of measurement for timestamps, which is fixed to 'seconds'.
+  - name: control
+    dtype: uint8
+    dims:
+    - num_times
+    shape:
+    - null
+    doc: Numerical labels that apply to each time point in data for the purpose of
+      querying and slicing data by these values. If present, the length of this
+      array should be the same size as the first dimension of data.
+    quantity: '?'
+  - name: control_description
+    dtype: text
+    dims:
+    - num_control_values
+    shape:
+    - null
+    doc: Description of each control value. Must be present if control is present.
+      If present, control_description[0] should describe time points where control == 0.
+    quantity: '?'
+  groups:
+  - name: sync
+    doc: Lab-specific time and sync information as provided directly from hardware
+      devices and that is necessary for aligning all acquired time information to
+      a common timebase. The timestamp array stores time in the common timebase.
+      This group will usually only be populated in TimeSeries that are
+      stored external to the NWB file, in files storing raw data. Once timestamp
+      data is calculated, the contents of 'sync' are mostly for archival purposes.
+    quantity: '?'
+
+- neurodata_type_def: ProcessingModule
+  neurodata_type_inc: NWBContainer
+  doc: A collection of processed data.
+  attributes:
+  - name: description
+    dtype: text
+    doc: Description of this collection of processed data.
+  groups:
+  - neurodata_type_inc: NWBDataInterface
+    doc: Data objects stored in this collection.
+    quantity: '*'
+  - neurodata_type_inc: DynamicTable
+    doc: Tables stored in this collection.
+    quantity: '*'
+
+- neurodata_type_def: Images
+  neurodata_type_inc: NWBDataInterface
+  default_name: Images
+  doc: A collection of images with an optional way to specify the order of the images
+    using the "order_of_images" dataset. An order must be specified if the images are
+    referenced by index, e.g., from an IndexSeries.
+  attributes:
+  - name: description
+    dtype: text
+    doc: Description of this collection of images.
+  datasets:
+  - neurodata_type_inc: Image
+    doc: Images stored in this collection.
+    quantity: '+'
+  - name: order_of_images
+    neurodata_type_inc: ImageReferences
+    doc: Ordered dataset of references to Image objects stored in the parent group.
+      Each Image object in the Images group should be stored once and only once, so
+      the dataset should have the same length as the number of images.
+    quantity: '?'

nwb-schema-linkml/src/data/tests/nwb.behavior.yaml

@@ -0,0 +1,124 @@
+groups:
+- neurodata_type_def: SpatialSeries
+  neurodata_type_inc: TimeSeries
+  doc: "Direction, e.g., of gaze or travel, or position. The TimeSeries::data field\
+    \ is a 2D array storing position or direction relative to some reference frame.\
+    \ Array structure: [num measurements] [num dimensions]. Each SpatialSeries has\
+    \ a text dataset reference_frame that indicates the zero-position, or the zero-axes\
+    \ for direction. For example, if representing gaze direction, 'straight-ahead'\
+    \ might be a specific pixel on the monitor, or some other point in space. For\
+    \ position data, the 0,0 point might be the top-left corner of an enclosure, as\
+    \ viewed from the tracking camera. The unit of data will indicate how to interpret\
+    \ SpatialSeries values."
+  datasets:
+  - name: data
+    dtype: numeric
+    dims:
+    - - num_times
+    - - num_times
+      - x
+    - - num_times
+      - x,y
+    - - num_times
+      - x,y,z
+    shape:
+    - - null
+    - - null
+      - 1
+    - - null
+      - 2
+    - - null
+      - 3
+    doc: 1-D or 2-D array storing position or direction relative to some reference frame.
+    attributes:
+    - name: unit
+      dtype: text
+      default_value: meters
+      doc: Base unit of measurement for working with the data. The default value
+        is 'meters'. Actual stored values are not necessarily stored in these units.
+        To access the data in these units, multiply 'data' by 'conversion' and add 'offset'.
+      required: false
+  - name: reference_frame
+    dtype: text
+    doc: Description defining what exactly 'straight-ahead' means.
+    quantity: '?'
+
+- neurodata_type_def: BehavioralEpochs
+  neurodata_type_inc: NWBDataInterface
+  default_name: BehavioralEpochs
+  doc: TimeSeries for storing behavioral epochs.  The objective of this and the other
+    two Behavioral interfaces (e.g. BehavioralEvents and BehavioralTimeSeries) is
+    to provide generic hooks for software tools/scripts. This allows a tool/script
+    to take the output one specific interface (e.g., UnitTimes) and plot that data
+    relative to another data modality (e.g., behavioral events) without having to
+    define all possible modalities in advance. Declaring one of these interfaces means
+    that one or more TimeSeries of the specified type is published. These TimeSeries
+    should reside in a group having the same name as the interface. For example, if
+    a BehavioralTimeSeries interface is declared, the module will have one or more
+    TimeSeries defined in the module sub-group 'BehavioralTimeSeries'. BehavioralEpochs
+    should use IntervalSeries. BehavioralEvents is used for irregular events. BehavioralTimeSeries
+    is for continuous data.
+  groups:
+  - neurodata_type_inc: IntervalSeries
+    doc: IntervalSeries object containing start and stop times of epochs.
+    quantity: '*'
+
+- neurodata_type_def: BehavioralEvents
+  neurodata_type_inc: NWBDataInterface
+  default_name: BehavioralEvents
+  doc: TimeSeries for storing behavioral events. See description of <a href="#BehavioralEpochs">BehavioralEpochs</a>
+    for more details.
+  groups:
+  - neurodata_type_inc: TimeSeries
+    doc: TimeSeries object containing behavioral events.
+    quantity: '*'
+
+- neurodata_type_def: BehavioralTimeSeries
+  neurodata_type_inc: NWBDataInterface
+  default_name: BehavioralTimeSeries
+  doc: TimeSeries for storing Behavoioral time series data. See description of <a href="#BehavioralEpochs">BehavioralEpochs</a>
+    for more details.
+  groups:
+  - neurodata_type_inc: TimeSeries
+    doc: TimeSeries object containing continuous behavioral data.
+    quantity: '*'
+
+- neurodata_type_def: PupilTracking
+  neurodata_type_inc: NWBDataInterface
+  default_name: PupilTracking
+  doc: Eye-tracking data, representing pupil size.
+  groups:
+  - neurodata_type_inc: TimeSeries
+    doc: TimeSeries object containing time series data on pupil size.
+    quantity: '+'
+
+- neurodata_type_def: EyeTracking
+  neurodata_type_inc: NWBDataInterface
+  default_name: EyeTracking
+  doc: Eye-tracking data, representing direction of gaze.
+  groups:
+  - neurodata_type_inc: SpatialSeries
+    doc: SpatialSeries object containing data measuring direction of gaze.
+    quantity: '*'
+
+- neurodata_type_def: CompassDirection
+  neurodata_type_inc: NWBDataInterface
+  default_name: CompassDirection
+  doc: With a CompassDirection interface, a module publishes a SpatialSeries object
+    representing a floating point value for theta. The SpatialSeries::reference_frame
+    field should indicate what direction corresponds to 0 and which is the direction
+    of rotation (this should be clockwise). The si_unit for the SpatialSeries should
+    be radians or degrees.
+  groups:
+  - neurodata_type_inc: SpatialSeries
+    doc: SpatialSeries object containing direction of gaze travel.
+    quantity: '*'
+
+- neurodata_type_def: Position
+  neurodata_type_inc: NWBDataInterface
+  default_name: Position
+  doc: Position data, whether along the x, x/y or x/y/z axis.
+  groups:
+  - neurodata_type_inc: SpatialSeries
+    doc: SpatialSeries object containing position data.
+    quantity: '+'

nwb-schema-linkml/src/data/tests/nwb.device.yaml

@@ -0,0 +1,14 @@
+groups:
+- neurodata_type_def: Device
+  neurodata_type_inc: NWBContainer
+  doc: Metadata about a data acquisition device, e.g., recording system, electrode, microscope.
+  attributes:
+  - name: description
+    dtype: text
+    doc: Description of the device (e.g., model, firmware version, processing software version, etc.)
+      as free-form text.
+    required: false
+  - name: manufacturer
+    dtype: text
+    doc: The name of the manufacturer of the device.
+    required: false

nwb-schema-linkml/src/data/tests/nwb.ecephys.yaml

@@ -0,0 +1,333 @@
+groups:
+- neurodata_type_def: ElectricalSeries
+  neurodata_type_inc: TimeSeries
+  doc: A time series of acquired voltage data from extracellular recordings.
+    The data field is an int or float array storing data in volts. The first
+    dimension should always represent time. The second dimension, if present,
+    should represent channels.
+  attributes:
+  - name: filtering
+    dtype: text
+    doc: Filtering applied to all channels of the data. For example, if this ElectricalSeries represents
+      high-pass-filtered data (also known as AP Band), then this value could be "High-pass 4-pole Bessel filter
+      at 500 Hz". If this ElectricalSeries represents low-pass-filtered LFP data and the type of filter is unknown,
+      then this value could be "Low-pass filter at 300 Hz". If a non-standard filter type is used, provide as much
+      detail about the filter properties as possible.
+    required: false
+  datasets:
+  - name: data
+    dtype: numeric
+    dims:
+    - - num_times
+    - - num_times
+      - num_channels
+    - - num_times
+      - num_channels
+      - num_samples
+    shape:
+    - - null
+    - - null
+      - null
+    - - null
+      - null
+      - null
+    doc: Recorded voltage data.
+    attributes:
+    - name: unit
+      dtype: text
+      value: volts
+      doc: Base unit of measurement for working with the data. This value is fixed to
+        'volts'. Actual stored values are not necessarily stored in these units. To
+        access the data in these units, multiply 'data' by 'conversion', followed by
+        'channel_conversion' (if present), and then add 'offset'.
+  - name: electrodes
+    neurodata_type_inc: DynamicTableRegion
+    doc: DynamicTableRegion pointer to the electrodes that this time series was generated from.
+  - name: channel_conversion
+    dtype: float32
+    dims:
+    - num_channels
+    shape:
+    - null
+    doc: Channel-specific conversion factor. Multiply the data in the 'data' dataset by these
+      values along the channel axis (as indicated by axis attribute) AND by the global
+      conversion factor in the 'conversion' attribute of 'data' to get the data values in
+      Volts, i.e, data in Volts = data * data.conversion * channel_conversion. This
+      approach allows for both global and per-channel data conversion factors needed
+      to support the storage of electrical recordings as native values generated by data
+      acquisition systems. If this dataset is not present, then there is no channel-specific
+      conversion factor, i.e. it is 1 for all channels.
+    quantity: '?'
+    attributes:
+    - name: axis
+      dtype: int32
+      value: 1
+      doc: The zero-indexed axis of the 'data' dataset that the channel-specific conversion
+        factor corresponds to. This value is fixed to 1.
+
+- neurodata_type_def: SpikeEventSeries
+  neurodata_type_inc: ElectricalSeries
+  doc: "Stores snapshots/snippets of recorded spike events (i.e., threshold crossings). This
+    may also be raw data, as reported by ephys hardware. If so, the TimeSeries::description
+    field should describe how events were detected. All SpikeEventSeries should
+    reside in a module (under EventWaveform interface) even if the spikes were reported
+    and stored by hardware. All events span the same recording channels and store
+    snapshots of equal duration. TimeSeries::data array structure: [num events]
+    [num channels] [num samples] (or [num events] [num samples] for single electrode)."
+  datasets:
+  - name: data
+    dtype: numeric
+    dims:
+    - - num_events
+      - num_samples
+    - - num_events
+      - num_channels
+      - num_samples
+    shape:
+    - - null
+      - null
+    - - null
+      - null
+      - null
+    doc: Spike waveforms.
+    attributes:
+    - name: unit
+      dtype: text
+      value: volts
+      doc: Unit of measurement for waveforms, which is fixed to 'volts'.
+  - name: timestamps
+    dtype: float64
+    dims:
+    - num_times
+    shape:
+    - null
+    doc: Timestamps for samples stored in data, in seconds, relative to the
+      common experiment master-clock stored in NWBFile.timestamps_reference_time.
+      Timestamps are required for the events. Unlike for TimeSeries, timestamps are
+      required for SpikeEventSeries and are thus re-specified here.
+    attributes:
+    - name: interval
+      dtype: int32
+      value: 1
+      doc: Value is '1'
+    - name: unit
+      dtype: text
+      value: seconds
+      doc: Unit of measurement for timestamps, which is fixed to 'seconds'.
+
+- neurodata_type_def: FeatureExtraction
+  neurodata_type_inc: NWBDataInterface
+  default_name: FeatureExtraction
+  doc: Features, such as PC1 and PC2, that are extracted from signals stored in a
+    SpikeEventSeries or other source.
+  datasets:
+  - name: description
+    dtype: text
+    dims:
+    - num_features
+    shape:
+    - null
+    doc: Description of features (eg, ''PC1'') for each of the extracted features.
+  - name: features
+    dtype: float32
+    dims:
+    - num_events
+    - num_channels
+    - num_features
+    shape:
+    - null
+    - null
+    - null
+    doc: Multi-dimensional array of features extracted from each event.
+  - name: times
+    dtype: float64
+    dims:
+    - num_events
+    shape:
+    - null
+    doc: Times of events that features correspond to (can be a link).
+  - name: electrodes
+    neurodata_type_inc: DynamicTableRegion
+    doc: DynamicTableRegion pointer to the electrodes that this time series was generated from.
+
+- neurodata_type_def: EventDetection
+  neurodata_type_inc: NWBDataInterface
+  default_name: EventDetection
+  doc: Detected spike events from voltage trace(s).
+  datasets:
+  - name: detection_method
+    dtype: text
+    doc: Description of how events were detected, such as voltage threshold, or dV/dT
+      threshold, as well as relevant values.
+  - name: source_idx
+    dtype: int32
+    dims:
+    - num_events
+    shape:
+    - null
+    doc: Indices (zero-based) into source ElectricalSeries::data array corresponding
+      to time of event. ''description'' should define what is meant by time of
+      event (e.g., .25 ms before action potential peak, zero-crossing time, etc).
+      The index points to each event from the raw data.
+  - name: times
+    dtype: float64
+    dims:
+    - num_events
+    shape:
+    - null
+    doc: Timestamps of events, in seconds.
+    attributes:
+    - name: unit
+      dtype: text
+      value: seconds
+      doc: Unit of measurement for event times, which is fixed to 'seconds'.
+  links:
+  - name: source_electricalseries
+    target_type: ElectricalSeries
+    doc: Link to the ElectricalSeries that this data was calculated from. Metadata
+      about electrodes and their position can be read from that ElectricalSeries so
+      it's not necessary to include that information here.
+
+- neurodata_type_def: EventWaveform
+  neurodata_type_inc: NWBDataInterface
+  default_name: EventWaveform
+  doc: Represents either the waveforms of detected events, as extracted from a raw
+    data trace in /acquisition, or the event waveforms that were stored during experiment
+    acquisition.
+  groups:
+  - neurodata_type_inc: SpikeEventSeries
+    doc: SpikeEventSeries object(s) containing detected spike event waveforms.
+    quantity: '*'
+
+- neurodata_type_def: FilteredEphys
+  neurodata_type_inc: NWBDataInterface
+  default_name: FilteredEphys
+  doc: Electrophysiology data from one or more channels that has been subjected to filtering.
+    Examples of filtered data include Theta and Gamma (LFP has its own interface).
+    FilteredEphys modules publish an ElectricalSeries for each filtered channel or
+    set of channels. The name of each ElectricalSeries is arbitrary but should be
+    informative. The source of the filtered data, whether this is from analysis of
+    another time series or as acquired by hardware, should be noted in each's TimeSeries::description
+    field. There is no assumed 1::1 correspondence between filtered ephys signals
+    and electrodes, as a single signal can apply to many nearby electrodes, and one
+    electrode may have different filtered (e.g., theta and/or gamma) signals represented.
+    Filter properties should be noted in the ElectricalSeries 'filtering' attribute.
+  groups:
+  - neurodata_type_inc: ElectricalSeries
+    doc: ElectricalSeries object(s) containing filtered electrophysiology data.
+    quantity: '+'
+
+- neurodata_type_def: LFP
+  neurodata_type_inc: NWBDataInterface
+  default_name: LFP
+  doc: LFP data from one or more channels. The electrode map in each published ElectricalSeries
+    will identify which channels are providing LFP data. Filter properties should
+    be noted in the ElectricalSeries 'filtering' attribute.
+  groups:
+  - neurodata_type_inc: ElectricalSeries
+    doc: ElectricalSeries object(s) containing LFP data for one or more channels.
+    quantity: '+'
+
+- neurodata_type_def: ElectrodeGroup
+  neurodata_type_inc: NWBContainer
+  doc: A physical grouping of electrodes, e.g. a shank of an array.
+  attributes:
+  - name: description
+    dtype: text
+    doc: Description of this electrode group.
+  - name: location
+    dtype: text
+    doc: Location of electrode group. Specify the area, layer, comments on estimation
+      of area/layer, etc. Use standard atlas names for anatomical regions when possible.
+  datasets:
+  - name: position
+    dtype:
+    - name: x
+      dtype: float32
+      doc: x coordinate
+    - name: y
+      dtype: float32
+      doc: y coordinate
+    - name: z
+      dtype: float32
+      doc: z coordinate
+    doc: stereotaxic or common framework coordinates
+    quantity: '?'
+  links:
+  - name: device
+    target_type: Device
+    doc: Link to the device that was used to record from this electrode group.
+
+# The types below have been deprecated
+- neurodata_type_def: ClusterWaveforms
+  neurodata_type_inc: NWBDataInterface
+  default_name: ClusterWaveforms
+  doc: DEPRECATED The mean waveform shape, including standard deviation, of the different
+    clusters. Ideally, the waveform analysis should be performed on data that is only
+    high-pass filtered. This is a separate module because it is expected to require
+    updating. For example, IMEC probes may require different storage requirements
+    to store/display mean waveforms, requiring a new interface or an extension of
+    this one.
+  datasets:
+  - name: waveform_filtering
+    dtype: text
+    doc: Filtering applied to data before generating mean/sd
+  - name: waveform_mean
+    dtype: float32
+    dims:
+    - num_clusters
+    - num_samples
+    shape:
+    - null
+    - null
+    doc: The mean waveform for each cluster, using the same indices for each wave
+      as cluster numbers in the associated Clustering module (i.e, cluster 3 is in
+      array slot [3]). Waveforms corresponding to gaps in cluster sequence should
+      be empty (e.g., zero- filled)
+  - name: waveform_sd
+    dtype: float32
+    dims:
+    - num_clusters
+    - num_samples
+    shape:
+    - null
+    - null
+    doc: Stdev of waveforms for each cluster, using the same indices as in mean
+  links:
+  - name: clustering_interface
+    target_type: Clustering
+    doc: Link to Clustering interface that was the source of the clustered data
+
+- neurodata_type_def: Clustering
+  neurodata_type_inc: NWBDataInterface
+  default_name: Clustering
+  doc: DEPRECATED Clustered spike data, whether from automatic clustering tools (e.g.,
+    klustakwik) or as a result of manual sorting.
+  datasets:
+  - name: description
+    dtype: text
+    doc: Description of clusters or clustering, (e.g. cluster 0 is noise, clusters
+      curated using Klusters, etc)
+  - name: num
+    dtype: int32
+    dims:
+    - num_events
+    shape:
+    - null
+    doc: Cluster number of each event
+  - name: peak_over_rms
+    dtype: float32
+    dims:
+    - num_clusters
+    shape:
+    - null
+    doc: Maximum ratio of waveform peak to RMS on any channel in the cluster (provides
+      a basic clustering metric).
+  - name: times
+    dtype: float64
+    dims:
+    - num_events
+    shape:
+    - null
+    doc: Times of clustered events, in seconds. This may be a link to times field
+      in associated FeatureExtraction module.

nwb-schema-linkml/src/data/tests/nwb.epoch.yaml

@@ -0,0 +1,31 @@
+groups:
+- neurodata_type_def: TimeIntervals
+  neurodata_type_inc: DynamicTable
+  doc: A container for aggregating epoch data and the TimeSeries that each epoch applies
+    to.
+  datasets:
+  - name: start_time
+    neurodata_type_inc: VectorData
+    dtype: float32
+    doc: Start time of epoch, in seconds.
+  - name: stop_time
+    neurodata_type_inc: VectorData
+    dtype: float32
+    doc: Stop time of epoch, in seconds.
+  - name: tags
+    neurodata_type_inc: VectorData
+    dtype: text
+    doc: User-defined tags that identify or categorize events.
+    quantity: '?'
+  - name: tags_index
+    neurodata_type_inc: VectorIndex
+    doc: Index for tags.
+    quantity: '?'
+  - name: timeseries
+    neurodata_type_inc: TimeSeriesReferenceVectorData
+    doc: An index into a TimeSeries object.
+    quantity: '?'
+  - name: timeseries_index
+    neurodata_type_inc: VectorIndex
+    doc: Index for timeseries.
+    quantity: '?'

nwb-schema-linkml/src/data/tests/nwb.file.yaml

@@ -0,0 +1,502 @@
+groups:
+- neurodata_type_def: NWBFile
+  neurodata_type_inc: NWBContainer
+  name: root
+  doc: An NWB file storing cellular-based neurophysiology data from a single
+    experimental session.
+  attributes:
+  - name: nwb_version
+    dtype: text
+    value: "2.6.0"
+    doc: File version string. Use semantic versioning, e.g. 1.2.1. This will be the
+      name of the format with trailing major, minor and patch numbers.
+  datasets:
+  - name: file_create_date
+    dtype: isodatetime
+    dims:
+    - num_modifications
+    shape:
+    - null
+    doc: 'A record of the date the file was created and of subsequent modifications.
+      The date is stored in UTC with local timezone offset as ISO 8601
+      extended formatted strings: 2018-09-28T14:43:54.123+02:00. Dates stored in
+      UTC end in "Z" with no timezone offset. Date accuracy is up to milliseconds.
+      The file can be created after the experiment was run, so this may differ from
+      the experiment start time. Each modification to the nwb file adds a new entry
+      to the array.'
+  - name: identifier
+    dtype: text
+    doc: A unique text identifier for the file. For example, concatenated lab name,
+      file creation date/time and experimentalist, or a hash of these and/or other
+      values. The goal is that the string should be unique to all other files.
+  - name: session_description
+    dtype: text
+    doc: A description of the experimental session and data in the file.
+  - name: session_start_time
+    dtype: isodatetime
+    doc: 'Date and time of the experiment/session start. The date is stored
+      in UTC with local timezone offset as ISO 8601 extended formatted string:
+      2018-09-28T14:43:54.123+02:00.
+      Dates stored in UTC end in "Z" with no timezone offset. Date accuracy is
+      up to milliseconds.'
+  - name: timestamps_reference_time
+    dtype: isodatetime
+    doc: 'Date and time corresponding to time zero of all timestamps. The
+      date is stored in UTC with local timezone offset as ISO 8601 extended formatted
+      string: 2018-09-28T14:43:54.123+02:00. Dates stored in UTC end in "Z" with
+      no timezone offset. Date accuracy is up to milliseconds. All times stored
+      in the file use this time as reference (i.e., time zero).'
+  groups:
+  - name: acquisition
+    doc: Data streams recorded from the system, including ephys, ophys, tracking,
+      etc. This group should be read-only after the experiment is completed and
+      timestamps are corrected to a common timebase. The data stored here may be links
+      to raw data stored in external NWB files. This will allow keeping bulky raw
+      data out of the file while preserving the option of keeping some/all in the
+      file. Acquired data includes tracking and experimental data streams
+      (i.e., everything measured from the system). If bulky data is stored in the /acquisition
+      group, the data can exist in a separate NWB file that is linked to by the file
+      being used for processing and analysis.
+    groups:
+    - neurodata_type_inc: NWBDataInterface
+      doc: Acquired, raw data.
+      quantity: '*'
+    - neurodata_type_inc: DynamicTable
+      doc: Tabular data that is relevant to acquisition
+      quantity: '*'
+  - name: analysis
+    doc: Lab-specific and custom scientific analysis of data. There is no defined
+      format for the content of this group - the format is up to the individual user/lab.
+      To facilitate sharing analysis data between labs, the contents here
+      should be stored in standard types (e.g., neurodata_types) and appropriately documented.
+      The file can store lab-specific and custom data analysis without
+      restriction on its form or schema, reducing data formatting restrictions on
+      end users. Such data should be placed in the analysis group. The analysis data
+      should be documented so that it could be shared with other labs.
+    groups:
+    - neurodata_type_inc: NWBContainer
+      doc: Custom analysis results.
+      quantity: '*'
+    - neurodata_type_inc: DynamicTable
+      doc: Tabular data that is relevant to data stored in analysis
+      quantity: '*'
+  - name: scratch
+    doc: 'A place to store one-off analysis results. Data placed here is not intended for
+      sharing. By placing data here, users acknowledge that there is no guarantee that
+      their data meets any standard.'
+    quantity: '?'
+    groups:
+    - neurodata_type_inc: NWBContainer
+      doc: Any one-off containers
+      quantity: '*'
+    - neurodata_type_inc: DynamicTable
+      doc: Any one-off tables
+      quantity: '*'
+    datasets:
+    - neurodata_type_inc: ScratchData
+      doc: Any one-off datasets
+      quantity: '*'
+  - name: processing
+    doc: "The home for ProcessingModules. These modules perform intermediate analysis\
+      \ of data that is necessary to perform before scientific analysis. Examples\
+      \ include spike clustering, extracting position from tracking data, stitching\
+      \ together image slices. ProcessingModules can be large\
+      \ and express many data sets from relatively complex analysis (e.g., spike detection\
+      \ and clustering) or small, representing extraction of position information\
+      \ from tracking video, or even binary lick/no-lick decisions. Common software\
+      \ tools (e.g., klustakwik, MClust) are expected to read/write data here. \
+      \ 'Processing' refers to intermediate analysis of the acquired data to make\
+      \ it more amenable to scientific analysis."
+    groups:
+    - neurodata_type_inc: ProcessingModule
+      doc: Intermediate analysis of acquired data.
+      quantity: '*'
+  - name: stimulus
+    doc: 'Data pushed into the system (eg, video stimulus, sound, voltage, etc) and
+      secondary representations of that data (eg, measurements of something used as
+      a stimulus). This group should be made read-only after experiment complete and timestamps
+      are corrected to common timebase. Stores both presented stimuli and stimulus
+      templates, the latter in case the same stimulus is presented multiple times,
+      or is pulled from an external stimulus library. Stimuli are here
+      defined as any signal that is pushed into the system as part of the experiment
+      (eg, sound, video, voltage, etc). Many different experiments can use the same
+      stimuli, and stimuli can be re-used during an experiment. The stimulus group
+      is organized so that one version of template stimuli can be stored and these
+      be used multiple times. These templates can exist in the present file or can
+      be linked to a remote library file.'
+    groups:
+    - name: presentation
+      doc: Stimuli presented during the experiment.
+      groups:
+      - neurodata_type_inc: TimeSeries
+        doc: TimeSeries objects containing data of presented stimuli.
+        quantity: '*'
+    - name: templates
+      doc: 'Template stimuli. Timestamps in templates are based on stimulus
+        design and are relative to the beginning of the stimulus. When templates are
+        used, the stimulus instances must convert presentation times to the experiment`s
+        time reference frame.'
+      groups:
+      - neurodata_type_inc: TimeSeries
+        doc: TimeSeries objects containing template data of presented stimuli.
+        quantity: '*'
+      - neurodata_type_inc: Images
+        doc: Images objects containing images of presented stimuli.
+        quantity: '*'
+  - name: general
+    doc: "Experimental metadata, including protocol, notes and description of hardware\
+      \ device(s).  The metadata stored in this section should be used to\
+      \ describe the experiment. Metadata necessary for interpreting the data is stored\
+      \ with the data. General experimental metadata, including animal\
+      \ strain, experimental protocols, experimenter, devices, etc, are stored under\
+      \ 'general'. Core metadata (e.g., that required to interpret data fields) is\
+      \ stored with the data itself, and implicitly defined by the file specification\
+      \ (e.g., time is in seconds). The strategy used here for storing non-core metadata\
+      \ is to use free-form text fields, such as would appear in sentences or paragraphs\
+      \ from a Methods section. Metadata fields are text to enable them to be more\
+      \ general, for example to represent ranges instead of numerical values. Machine-readable\
+      \ metadata is stored as attributes to these free-form datasets. All entries\
+      \ in the below table are to be included when data is present. Unused groups\
+      \ (e.g., intracellular_ephys in an optophysiology experiment) should not be\
+      \ created unless there is data to store within them."
+    datasets:
+    - name: data_collection
+      dtype: text
+      doc: Notes about data collection and analysis.
+      quantity: '?'
+    - name: experiment_description
+      dtype: text
+      doc: General description of the experiment.
+      quantity: '?'
+    - name: experimenter
+      dtype: text
+      doc: Name of person(s) who performed the experiment. Can also specify roles
+        of different people involved.
+      quantity: '?'
+      dims:
+      - num_experimenters
+      shape:
+      - null
+    - name: institution
+      dtype: text
+      doc: Institution(s) where experiment was performed.
+      quantity: '?'
+    - name: keywords
+      dtype: text
+      dims:
+      - num_keywords
+      shape:
+      - null
+      doc: Terms to search over.
+      quantity: '?'
+    - name: lab
+      dtype: text
+      doc: Laboratory where experiment was performed.
+      quantity: '?'
+    - name: notes
+      dtype: text
+      doc: Notes about the experiment.
+      quantity: '?'
+    - name: pharmacology
+      dtype: text
+      doc: Description of drugs used, including how and when they were administered.
+        Anesthesia(s), painkiller(s), etc., plus dosage, concentration, etc.
+      quantity: '?'
+    - name: protocol
+      dtype: text
+      doc: Experimental protocol, if applicable. e.g., include IACUC protocol number.
+      quantity: '?'
+    - name: related_publications
+      dtype: text
+      doc: Publication information. PMID, DOI, URL, etc.
+      dims:
+      - num_publications
+      shape:
+      - null
+      quantity: '?'
+    - name: session_id
+      dtype: text
+      doc: Lab-specific ID for the session.
+      quantity: '?'
+    - name: slices
+      dtype: text
+      doc: Description of slices, including information about preparation thickness,
+        orientation, temperature, and bath solution.
+      quantity: '?'
+    - name: source_script
+      dtype: text
+      doc: Script file or link to public source code used to create this NWB file.
+      quantity: '?'
+      attributes:
+      - name: file_name
+        dtype: text
+        doc: Name of script file.
+    - name: stimulus
+      dtype: text
+      doc: Notes about stimuli, such as how and where they were presented.
+      quantity: '?'
+    - name: surgery
+      dtype: text
+      doc: Narrative description about surgery/surgeries, including date(s) and who
+        performed surgery.
+      quantity: '?'
+    - name: virus
+      dtype: text
+      doc: Information about virus(es) used in experiments, including virus ID, source,
+        date made, injection location, volume, etc.
+      quantity: '?'
+    groups:
+    - neurodata_type_inc: LabMetaData
+      doc: Place-holder than can be extended so that lab-specific meta-data can be
+        placed in /general.
+      quantity: '*'
+    - name: devices
+      doc: Description of hardware devices used during experiment, e.g., monitors,
+        ADC boards, microscopes, etc.
+      quantity: '?'
+      groups:
+      - neurodata_type_inc: Device
+        doc: Data acquisition devices.
+        quantity: '*'
+    - name: subject
+      neurodata_type_inc: Subject
+      doc: Information about the animal or person from which the data was measured.
+      quantity: '?'
+    - name: extracellular_ephys
+      doc: Metadata related to extracellular electrophysiology.
+      quantity: '?'
+      groups:
+      - neurodata_type_inc: ElectrodeGroup
+        doc: Physical group of electrodes.
+        quantity: '*'
+      - name: electrodes
+        neurodata_type_inc: DynamicTable
+        doc: A table of all electrodes (i.e. channels) used for recording.
+        quantity: '?'
+        datasets:
+        - name: x
+          neurodata_type_inc: VectorData
+          dtype: float32
+          doc: x coordinate of the channel location in the brain (+x is posterior).
+          quantity: '?'
+        - name: y
+          neurodata_type_inc: VectorData
+          dtype: float32
+          doc: y coordinate of the channel location in the brain (+y is inferior).
+          quantity: '?'
+        - name: z
+          neurodata_type_inc: VectorData
+          dtype: float32
+          doc: z coordinate of the channel location in the brain (+z is right).
+          quantity: '?'
+        - name: imp
+          neurodata_type_inc: VectorData
+          dtype: float32
+          doc: Impedance of the channel, in ohms.
+          quantity: '?'
+        - name: location
+          neurodata_type_inc: VectorData
+          dtype: text
+          doc: Location of the electrode (channel). Specify the area, layer, comments
+            on estimation of area/layer, stereotaxic coordinates if in vivo, etc. Use
+            standard atlas names for anatomical regions when possible.
+        - name: filtering
+          neurodata_type_inc: VectorData
+          dtype: text
+          doc: Description of hardware filtering, including the filter name and frequency cutoffs.
+          quantity: '?'
+        - name: group
+          neurodata_type_inc: VectorData
+          dtype:
+            target_type: ElectrodeGroup
+            reftype: object
+          doc: Reference to the ElectrodeGroup this electrode is a part of.
+        - name: group_name
+          neurodata_type_inc: VectorData
+          dtype: text
+          doc: Name of the ElectrodeGroup this electrode is a part of.
+        - name: rel_x
+          neurodata_type_inc: VectorData
+          dtype: float32
+          doc: x coordinate in electrode group
+          quantity: '?'
+        - name: rel_y
+          neurodata_type_inc: VectorData
+          dtype: float32
+          doc: y coordinate in electrode group
+          quantity: '?'
+        - name: rel_z
+          neurodata_type_inc: VectorData
+          dtype: float32
+          doc: z coordinate in electrode group
+          quantity: '?'
+        - name: reference
+          neurodata_type_inc: VectorData
+          dtype: text
+          doc: Description of the reference electrode and/or reference scheme used for this electrode, e.g.,
+            "stainless steel skull screw" or "online common average referencing".
+          quantity: '?'
+    - name: intracellular_ephys
+      doc: Metadata related to intracellular electrophysiology.
+      quantity: '?'
+      datasets:
+      - name: filtering
+        dtype: text
+        doc: '[DEPRECATED] Use IntracellularElectrode.filtering instead. Description
+          of filtering used. Includes filtering type and parameters, frequency fall-off,
+          etc. If this changes between TimeSeries, filter description should be stored
+          as a text attribute for each TimeSeries.'
+        quantity: '?'
+      groups:
+      - neurodata_type_inc: IntracellularElectrode
+        doc: An intracellular electrode.
+        quantity: '*'
+      - name: sweep_table
+        neurodata_type_inc: SweepTable
+        doc: '[DEPRECATED] Table used to group different PatchClampSeries. SweepTable
+              is being replaced by IntracellularRecordingsTable and SimultaneousRecordingsTable
+              tables. Additional SequentialRecordingsTable, RepetitionsTable and
+              ExperimentalConditions tables provide enhanced support for experiment metadata.'
+        quantity: '?'
+      - name: intracellular_recordings
+        neurodata_type_inc: IntracellularRecordingsTable
+        doc: A table to group together a stimulus and response from a single electrode
+          and a single simultaneous recording. Each row in the table represents a
+          single recording consisting typically of a stimulus and a corresponding
+          response. In some cases, however, only a stimulus or a response are recorded
+          as as part of an experiment. In this case both, the stimulus and response
+          will point to the same TimeSeries while the idx_start and count of the invalid
+          column will be set to -1, thus, indicating that no values have been recorded
+          for the stimulus or response, respectively. Note, a recording MUST contain
+          at least a stimulus or a response. Typically the stimulus and response are
+          PatchClampSeries. However, the use of AD/DA channels that are not associated
+          to an electrode is also common in intracellular electrophysiology, in which
+          case other TimeSeries may be used.
+        quantity: '?'
+      - name: simultaneous_recordings
+        neurodata_type_inc: SimultaneousRecordingsTable
+        doc: A table for grouping different intracellular recordings from the IntracellularRecordingsTable
+          table together that were recorded simultaneously from different electrodes
+        quantity: '?'
+      - name: sequential_recordings
+        neurodata_type_inc: SequentialRecordingsTable
+        doc: A table for grouping different sequential recordings from the SimultaneousRecordingsTable
+          table together. This is typically used to group together sequential recordings
+          where the a sequence of stimuli of the same type with varying parameters
+          have been presented in a sequence.
+        quantity: '?'
+      - name: repetitions
+        neurodata_type_inc: RepetitionsTable
+        doc: A table for grouping different sequential intracellular recordings together.
+          With each SequentialRecording typically representing a particular type of
+          stimulus, the RepetitionsTable table is typically used to group sets of
+          stimuli applied in sequence.
+        quantity: '?'
+      - name: experimental_conditions
+        neurodata_type_inc: ExperimentalConditionsTable
+        doc: A table for grouping different intracellular recording repetitions together
+          that belong to the same experimental experimental_conditions.
+        quantity: '?'
+    - name: optogenetics
+      doc: Metadata describing optogenetic stimuluation.
+      quantity: '?'
+      groups:
+      - neurodata_type_inc: OptogeneticStimulusSite
+        doc: An optogenetic stimulation site.
+        quantity: '*'
+    - name: optophysiology
+      doc: Metadata related to optophysiology.
+      quantity: '?'
+      groups:
+      - neurodata_type_inc: ImagingPlane
+        doc: An imaging plane.
+        quantity: '*'
+  - name: intervals
+    doc: Experimental intervals, whether that be logically distinct sub-experiments
+      having a particular scientific goal, trials (see trials subgroup) during an
+      experiment, or epochs (see epochs subgroup) deriving from analysis of data.
+    quantity: '?'
+    groups:
+    - name: epochs
+      neurodata_type_inc: TimeIntervals
+      doc: Divisions in time marking experimental stages or sub-divisions of a single
+        recording session.
+      quantity: '?'
+    - name: trials
+      neurodata_type_inc: TimeIntervals
+      doc: Repeated experimental events that have a logical grouping.
+      quantity: '?'
+    - name: invalid_times
+      neurodata_type_inc: TimeIntervals
+      doc: Time intervals that should be removed from analysis.
+      quantity: '?'
+    - neurodata_type_inc: TimeIntervals
+      doc: Optional additional table(s) for describing other experimental time intervals.
+      quantity: '*'
+  - name: units
+    neurodata_type_inc: Units
+    doc: Data about sorted spike units.
+    quantity: '?'
+
+- neurodata_type_def: LabMetaData
+  neurodata_type_inc: NWBContainer
+  doc: Lab-specific meta-data.
+
+- neurodata_type_def: Subject
+  neurodata_type_inc: NWBContainer
+  doc: Information about the animal or person from which the data was measured.
+  datasets:
+  - name: age
+    dtype: text
+    doc: Age of subject. Can be supplied instead of 'date_of_birth'.
+    quantity: '?'
+    attributes:
+      - name: reference
+        doc: "Age is with reference to this event. Can be 'birth' or
+          'gestational'. If reference is omitted, 'birth' is implied."
+        dtype: text
+        required: false
+        default_value: birth
+  - name: date_of_birth
+    dtype: isodatetime
+    doc: Date of birth of subject. Can be supplied instead of 'age'.
+    quantity: '?'
+  - name: description
+    dtype: text
+    doc: Description of subject and where subject came from (e.g., breeder, if
+      animal).
+    quantity: '?'
+  - name: genotype
+    dtype: text
+    doc: Genetic strain. If absent, assume Wild Type (WT).
+    quantity: '?'
+  - name: sex
+    dtype: text
+    doc: Gender of subject.
+    quantity: '?'
+  - name: species
+    dtype: text
+    doc: Species of subject.
+    quantity: '?'
+  - name: strain
+    dtype: text
+    doc: Strain of subject.
+    quantity: '?'
+  - name: subject_id
+    dtype: text
+    doc: ID of animal/person used/participating in experiment (lab convention).
+    quantity: '?'
+  - name: weight
+    dtype: text
+    doc: Weight at time of experiment, at time of surgery and at other important
+      times.
+    quantity: '?'
+
+datasets:
+- neurodata_type_def: ScratchData
+  neurodata_type_inc: NWBData
+  doc: Any one-off datasets
+  attributes:
+  - name: notes
+    doc: 'Any notes the user has about the dataset being stored'
+    dtype: text

nwb-schema-linkml/src/data/tests/nwb.icephys.yaml

@@ -0,0 +1,426 @@
+groups:
+- neurodata_type_def: PatchClampSeries
+  neurodata_type_inc: TimeSeries
+  doc: An abstract base class for patch-clamp data - stimulus or response,
+    current or voltage.
+  attributes:
+  - name: stimulus_description
+    dtype: text
+    doc: Protocol/stimulus name for this patch-clamp dataset.
+  - name: sweep_number
+    dtype: uint32
+    doc: Sweep number, allows to group different PatchClampSeries together.
+    required: false
+  datasets:
+  - name: data
+    dtype: numeric
+    dims:
+    - num_times
+    shape:
+    - null
+    doc: Recorded voltage or current.
+    attributes:
+    - name: unit
+      dtype: text
+      doc: Base unit of measurement for working with the data. Actual stored values are
+        not necessarily stored in these units. To access the data in these units,
+        multiply 'data' by 'conversion' and add 'offset'.
+  - name: gain
+    dtype: float32
+    doc: Gain of the recording, in units Volt/Amp (v-clamp) or Volt/Volt (c-clamp).
+    quantity: '?'
+  links:
+  - name: electrode
+    target_type: IntracellularElectrode
+    doc: Link to IntracellularElectrode object that describes the electrode that was
+      used to apply or record this data.
+
+- neurodata_type_def: CurrentClampSeries
+  neurodata_type_inc: PatchClampSeries
+  doc: Voltage data from an intracellular current-clamp recording. A
+    corresponding CurrentClampStimulusSeries (stored separately as a stimulus) is
+    used to store the current injected.
+  datasets:
+  - name: data
+    doc: Recorded voltage.
+    attributes:
+    - name: unit
+      dtype: text
+      value: volts
+      doc: Base unit of measurement for working with the data. which is fixed to 'volts'.
+        Actual stored values are not necessarily stored in these units. To access the data in these units,
+        multiply 'data' by 'conversion' and add 'offset'.
+  - name: bias_current
+    dtype: float32
+    doc: Bias current, in amps.
+    quantity: '?'
+  - name: bridge_balance
+    dtype: float32
+    doc: Bridge balance, in ohms.
+    quantity: '?'
+  - name: capacitance_compensation
+    dtype: float32
+    doc: Capacitance compensation, in farads.
+    quantity: '?'
+
+- neurodata_type_def: IZeroClampSeries
+  neurodata_type_inc: CurrentClampSeries
+  doc: Voltage data from an intracellular recording when all current
+    and amplifier settings are off (i.e., CurrentClampSeries fields will be zero).
+    There is no CurrentClampStimulusSeries associated with an IZero series because
+    the amplifier is disconnected and no stimulus can reach the cell.
+  attributes:
+  - name: stimulus_description
+    dtype: text
+    doc: An IZeroClampSeries has no stimulus, so this attribute is automatically set to "N/A"
+    value: N/A
+  datasets:
+  - name: bias_current
+    dtype: float32
+    value: 0.0
+    doc: Bias current, in amps, fixed to 0.0.
+  - name: bridge_balance
+    dtype: float32
+    value: 0.0
+    doc: Bridge balance, in ohms, fixed to 0.0.
+  - name: capacitance_compensation
+    dtype: float32
+    value: 0.0
+    doc: Capacitance compensation, in farads, fixed to 0.0.
+
+- neurodata_type_def: CurrentClampStimulusSeries
+  neurodata_type_inc: PatchClampSeries
+  doc: Stimulus current applied during current clamp recording.
+  datasets:
+  - name: data
+    doc: Stimulus current applied.
+    attributes:
+    - name: unit
+      dtype: text
+      value: amperes
+      doc: Base unit of measurement for working with the data. which is fixed to 'amperes'.
+        Actual stored values are not necessarily stored in these units. To access the data in these units,
+        multiply 'data' by 'conversion' and add 'offset'.
+
+- neurodata_type_def: VoltageClampSeries
+  neurodata_type_inc: PatchClampSeries
+  doc: Current data from an intracellular voltage-clamp recording. A
+    corresponding VoltageClampStimulusSeries (stored separately as a stimulus) is
+    used to store the voltage injected.
+  datasets:
+  - name: data
+    doc: Recorded current.
+    attributes:
+    - name: unit
+      dtype: text
+      value: amperes
+      doc: Base unit of measurement for working with the data. which is fixed to 'amperes'.
+        Actual stored values are not necessarily stored in these units. To access the data in these units,
+        multiply 'data' by 'conversion' and add 'offset'.
+  - name: capacitance_fast
+    dtype: float32
+    doc: Fast capacitance, in farads.
+    quantity: '?'
+    attributes:
+    - name: unit
+      dtype: text
+      value: farads
+      doc: Unit of measurement for capacitance_fast, which is fixed to 'farads'.
+  - name: capacitance_slow
+    dtype: float32
+    doc: Slow capacitance, in farads.
+    quantity: '?'
+    attributes:
+    - name: unit
+      dtype: text
+      value: farads
+      doc: Unit of measurement for capacitance_fast, which is fixed to 'farads'.
+  - name: resistance_comp_bandwidth
+    dtype: float32
+    doc: Resistance compensation bandwidth, in hertz.
+    quantity: '?'
+    attributes:
+    - name: unit
+      dtype: text
+      value: hertz
+      doc: Unit of measurement for resistance_comp_bandwidth, which is fixed to 'hertz'.
+  - name: resistance_comp_correction
+    dtype: float32
+    doc: Resistance compensation correction, in percent.
+    quantity: '?'
+    attributes:
+    - name: unit
+      dtype: text
+      value: percent
+      doc: Unit of measurement for resistance_comp_correction, which is fixed to 'percent'.
+  - name: resistance_comp_prediction
+    dtype: float32
+    doc: Resistance compensation prediction, in percent.
+    quantity: '?'
+    attributes:
+    - name: unit
+      dtype: text
+      value: percent
+      doc: Unit of measurement for resistance_comp_prediction, which is fixed to 'percent'.
+  - name: whole_cell_capacitance_comp
+    dtype: float32
+    doc: Whole cell capacitance compensation, in farads.
+    quantity: '?'
+    attributes:
+    - name: unit
+      dtype: text
+      value: farads
+      doc: Unit of measurement for whole_cell_capacitance_comp, which is fixed to 'farads'.
+  - name: whole_cell_series_resistance_comp
+    dtype: float32
+    doc: Whole cell series resistance compensation, in ohms.
+    quantity: '?'
+    attributes:
+    - name: unit
+      dtype: text
+      value: ohms
+      doc: Unit of measurement for whole_cell_series_resistance_comp, which is fixed to 'ohms'.
+
+- neurodata_type_def: VoltageClampStimulusSeries
+  neurodata_type_inc: PatchClampSeries
+  doc: Stimulus voltage applied during a voltage clamp recording.
+  datasets:
+  - name: data
+    doc: Stimulus voltage applied.
+    attributes:
+    - name: unit
+      dtype: text
+      value: volts
+      doc: Base unit of measurement for working with the data. which is fixed to 'volts'.
+        Actual stored values are not necessarily stored in these units. To access the data in these units,
+        multiply 'data' by 'conversion' and add 'offset'.
+
+- neurodata_type_def: IntracellularElectrode
+  neurodata_type_inc: NWBContainer
+  doc: An intracellular electrode and its metadata.
+  datasets:
+  - name: cell_id
+    dtype: text
+    doc: unique ID of the cell
+    quantity: '?'
+  - name: description
+    dtype: text
+    doc: Description of electrode (e.g.,  whole-cell, sharp, etc.).
+  - name: filtering
+    dtype: text
+    doc: Electrode specific filtering.
+    quantity: '?'
+  - name: initial_access_resistance
+    dtype: text
+    doc: Initial access resistance.
+    quantity: '?'
+  - name: location
+    dtype: text
+    doc: Location of the electrode. Specify the area, layer, comments on estimation
+      of area/layer, stereotaxic coordinates if in vivo, etc. Use standard atlas
+      names for anatomical regions when possible.
+    quantity: '?'
+  - name: resistance
+    dtype: text
+    doc: Electrode resistance, in ohms.
+    quantity: '?'
+  - name: seal
+    dtype: text
+    doc: Information about seal used for recording.
+    quantity: '?'
+  - name: slice
+    dtype: text
+    doc: Information about slice used for recording.
+    quantity: '?'
+  links:
+  - name: device
+    target_type: Device
+    doc: Device that was used to record from this electrode.
+
+- neurodata_type_def: SweepTable
+  neurodata_type_inc: DynamicTable
+  doc: '[DEPRECATED] Table used to group different PatchClampSeries. SweepTable
+        is being replaced by IntracellularRecordingsTable and SimultaneousRecordingsTable
+        tables. Additional SequentialRecordingsTable, RepetitionsTable, and
+        ExperimentalConditions tables provide enhanced support for experiment metadata.'
+  datasets:
+  - name: sweep_number
+    neurodata_type_inc: VectorData
+    dtype: uint32
+    doc: Sweep number of the PatchClampSeries in that row.
+  - name: series
+    neurodata_type_inc: VectorData
+    dtype:
+      target_type: PatchClampSeries
+      reftype: object
+    doc: The PatchClampSeries with the sweep number in that row.
+  - name: series_index
+    neurodata_type_inc: VectorIndex
+    doc: Index for series.
+
+- neurodata_type_def: IntracellularElectrodesTable
+  neurodata_type_inc: DynamicTable
+  doc: Table for storing intracellular electrode related metadata.
+  attributes:
+  - name: description
+    dtype: text
+    value: Table for storing intracellular electrode related metadata.
+    doc: Description of what is in this dynamic table.
+  datasets:
+  - name: electrode
+    neurodata_type_inc: VectorData
+    dtype:
+      target_type: IntracellularElectrode
+      reftype: object
+    doc: Column for storing the reference to the intracellular electrode.
+
+- neurodata_type_def: IntracellularStimuliTable
+  neurodata_type_inc: DynamicTable
+  doc: Table for storing intracellular stimulus related metadata.
+  attributes:
+  - name: description
+    dtype: text
+    value: Table for storing intracellular stimulus related metadata.
+    doc: Description of what is in this dynamic table.
+  datasets:
+  - name: stimulus
+    neurodata_type_inc: TimeSeriesReferenceVectorData
+    doc: Column storing the reference to the recorded stimulus for the recording (rows).
+
+- neurodata_type_def: IntracellularResponsesTable
+  neurodata_type_inc: DynamicTable
+  doc: Table for storing intracellular response related metadata.
+  attributes:
+  - name: description
+    dtype: text
+    value: Table for storing intracellular response related metadata.
+    doc: Description of what is in this dynamic table.
+  datasets:
+  - name: response
+    neurodata_type_inc: TimeSeriesReferenceVectorData
+    doc: Column storing the reference to the recorded response for the recording (rows)
+
+- neurodata_type_def: IntracellularRecordingsTable
+  neurodata_type_inc: AlignedDynamicTable
+  name: intracellular_recordings
+  doc: A table to group together a stimulus and response from a single electrode and
+    a single simultaneous recording. Each row in the table represents a single recording
+    consisting typically of a stimulus and a corresponding response. In some cases,
+    however, only a stimulus or a response is recorded as part of an experiment.
+    In this case, both the stimulus and response will point to the same TimeSeries
+    while the idx_start and count of the invalid column will be set to -1, thus, indicating
+    that no values have been recorded for the stimulus or response, respectively.
+    Note, a recording MUST contain at least a stimulus or a response. Typically the
+    stimulus and response are PatchClampSeries. However, the use of AD/DA channels
+    that are not associated to an electrode is also common in intracellular electrophysiology,
+    in which case other TimeSeries may be used.
+  attributes:
+  - name: description
+    dtype: text
+    value: A table to group together a stimulus and response from a single electrode
+      and a single simultaneous recording and for storing metadata about the intracellular
+      recording.
+    doc: Description of the contents of this table. Inherited from AlignedDynamicTable
+      and overwritten here to fix the value of the attribute.
+  groups:
+  - name: electrodes
+    neurodata_type_inc: IntracellularElectrodesTable
+    doc: Table for storing intracellular electrode related metadata.
+  - name: stimuli
+    neurodata_type_inc: IntracellularStimuliTable
+    doc: Table for storing intracellular stimulus related metadata.
+  - name: responses
+    neurodata_type_inc: IntracellularResponsesTable
+    doc: Table for storing intracellular response related metadata.
+
+- neurodata_type_def: SimultaneousRecordingsTable
+  neurodata_type_inc: DynamicTable
+  name: simultaneous_recordings
+  doc: A table for grouping different intracellular recordings from the IntracellularRecordingsTable
+    table together that were recorded simultaneously from different electrodes.
+  datasets:
+  - name: recordings
+    neurodata_type_inc: DynamicTableRegion
+    doc: A reference to one or more rows in the IntracellularRecordingsTable table.
+    attributes:
+    - name: table
+      dtype:
+        target_type: IntracellularRecordingsTable
+        reftype: object
+      doc: Reference to the IntracellularRecordingsTable table that this table region
+        applies to. This specializes the attribute inherited from DynamicTableRegion
+        to fix the type of table that can be referenced here.
+  - name: recordings_index
+    neurodata_type_inc: VectorIndex
+    doc: Index dataset for the recordings column.
+
+- neurodata_type_def: SequentialRecordingsTable
+  neurodata_type_inc: DynamicTable
+  name: sequential_recordings
+  doc: A table for grouping different sequential recordings from the SimultaneousRecordingsTable
+    table together. This is typically used to group together sequential recordings
+    where a sequence of stimuli of the same type with varying parameters have
+    been presented in a sequence.
+  datasets:
+  - name: simultaneous_recordings
+    neurodata_type_inc: DynamicTableRegion
+    doc: A reference to one or more rows in the SimultaneousRecordingsTable table.
+    attributes:
+    - name: table
+      dtype:
+        target_type: SimultaneousRecordingsTable
+        reftype: object
+      doc: Reference to the SimultaneousRecordingsTable table that this table region
+        applies to. This specializes the attribute inherited from DynamicTableRegion
+        to fix the type of table that can be referenced here.
+  - name: simultaneous_recordings_index
+    neurodata_type_inc: VectorIndex
+    doc: Index dataset for the simultaneous_recordings column.
+  - name: stimulus_type
+    neurodata_type_inc: VectorData
+    dtype: text
+    doc: The type of stimulus used for the sequential recording.
+
+- neurodata_type_def: RepetitionsTable
+  neurodata_type_inc: DynamicTable
+  name: repetitions
+  doc: A table for grouping different sequential intracellular recordings together.
+    With each SequentialRecording typically representing a particular type of stimulus,
+    the RepetitionsTable table is typically used to group sets of stimuli applied
+    in sequence.
+  datasets:
+  - name: sequential_recordings
+    neurodata_type_inc: DynamicTableRegion
+    doc: A reference to one or more rows in the SequentialRecordingsTable table.
+    attributes:
+    - name: table
+      dtype:
+        target_type: SequentialRecordingsTable
+        reftype: object
+      doc: Reference to the SequentialRecordingsTable table that this table region
+        applies to. This specializes the attribute inherited from DynamicTableRegion
+        to fix the type of table that can be referenced here.
+  - name: sequential_recordings_index
+    neurodata_type_inc: VectorIndex
+    doc: Index dataset for the sequential_recordings column.
+
+- neurodata_type_def: ExperimentalConditionsTable
+  neurodata_type_inc: DynamicTable
+  name: experimental_conditions
+  doc: A table for grouping different intracellular recording repetitions together
+    that belong to the same experimental condition.
+  datasets:
+  - name: repetitions
+    neurodata_type_inc: DynamicTableRegion
+    doc: A reference to one or more rows in the RepetitionsTable table.
+    attributes:
+    - name: table
+      dtype:
+        target_type: RepetitionsTable
+        reftype: object
+      doc: Reference to the RepetitionsTable table that this table region applies
+        to. This specializes the attribute inherited from DynamicTableRegion to fix
+        the type of table that can be referenced here.
+  - name: repetitions_index
+    neurodata_type_inc: VectorIndex
+    doc: Index dataset for the repetitions column.

nwb-schema-linkml/src/data/tests/nwb.image.yaml

@@ -0,0 +1,222 @@
+datasets:
+- neurodata_type_def: GrayscaleImage
+  neurodata_type_inc: Image
+  dims:
+  - x
+  - y
+  shape:
+  - null
+  - null
+  doc: A grayscale image.
+  dtype: numeric
+
+- neurodata_type_def: RGBImage
+  neurodata_type_inc: Image
+  dims:
+  - x
+  - y
+  - r, g, b
+  shape:
+  - null
+  - null
+  - 3
+  doc: A color image.
+  dtype: numeric
+
+- neurodata_type_def: RGBAImage
+  neurodata_type_inc: Image
+  dims:
+  - x
+  - y
+  - r, g, b, a
+  shape:
+  - null
+  - null
+  - 4
+  doc: A color image with transparency.
+  dtype: numeric
+
+groups:
+- neurodata_type_def: ImageSeries
+  neurodata_type_inc: TimeSeries
+  doc: General image data that is common between acquisition and stimulus time series.
+    Sometimes the image data is stored in the file in a raw format while other
+    times it will be stored as a series of external image files in the host file system.
+    The data field will either be binary data, if the data is stored in the NWB file, or
+    empty, if the data is stored in an external image stack. [frame][x][y] or [frame][x][y][z].
+  datasets:
+  - name: data
+    dtype: numeric
+    dims:
+    - - frame
+      - x
+      - y
+    - - frame
+      - x
+      - y
+      - z
+    shape:
+    - - null
+      - null
+      - null
+    - - null
+      - null
+      - null
+      - null
+    doc: Binary data representing images across frames. If data are stored in an external
+      file, this should be an empty 3D array.
+  - name: dimension
+    dtype: int32
+    dims:
+    - rank
+    shape:
+    - null
+    doc: Number of pixels on x, y, (and z) axes.
+    quantity: '?'
+  - name: external_file
+    dtype: text
+    dims:
+    - num_files
+    shape:
+    - null
+    doc: Paths to one or more external file(s). The field is only present if format='external'.
+      This is only relevant if the image series is stored in the file system as one
+      or more image file(s). This field should NOT be used if the image is stored
+      in another NWB file and that file is linked to this file.
+    quantity: '?'
+    attributes:
+    - name: starting_frame
+      dtype: int32
+      dims:
+      - num_files
+      shape:
+      - null
+      doc: Each external image may contain one or more consecutive frames of the full
+        ImageSeries. This attribute serves as an index to indicate which frames each file
+        contains, to facilitate random access. The 'starting_frame' attribute, hence,
+        contains a list of frame numbers within the full ImageSeries of the first frame
+        of each file listed in the parent 'external_file' dataset. Zero-based indexing is
+        used (hence, the first element will always be zero). For example, if the
+        'external_file' dataset has three paths to files and the first file has 5 frames,
+        the second file has 10 frames, and the third file has 20 frames, then this
+        attribute will have values [0, 5, 15]. If there is a single external file that
+        holds all of the frames of the ImageSeries (and so there is a single element in
+        the 'external_file' dataset), then this attribute should have value [0].
+  - name: format
+    dtype: text
+    default_value: raw
+    doc: Format of image. If this is 'external', then the attribute 'external_file'
+      contains the path information to the image files. If this is 'raw', then the raw
+      (single-channel) binary data is stored in the 'data' dataset. If this attribute
+      is not present, then the default format='raw' case is assumed.
+    quantity: '?'
+  links:
+  - name: device
+    target_type: Device
+    doc: Link to the Device object that was used to capture these images.
+    quantity: '?'
+
+- neurodata_type_def: ImageMaskSeries
+  neurodata_type_inc: ImageSeries
+  doc: An alpha mask that is applied to a presented visual stimulus. The 'data' array
+    contains an array of mask values that are applied to the displayed image. Mask
+    values are stored as RGBA. Mask can vary with time. The timestamps array indicates
+    the starting time of a mask, and that mask pattern continues until it's explicitly
+    changed.
+  links:
+  - name: masked_imageseries
+    target_type: ImageSeries
+    doc: Link to ImageSeries object that this image mask is applied to.
+
+- neurodata_type_def: OpticalSeries
+  neurodata_type_inc: ImageSeries
+  doc: Image data that is presented or recorded. A stimulus template movie will be
+    stored only as an image. When the image is presented as stimulus, additional data
+    is required, such as field of view (e.g., how much of the visual field the image
+    covers, or how what is the area of the target being imaged). If the OpticalSeries
+    represents acquired imaging data, orientation is also important.
+  datasets:
+  - name: distance
+    dtype: float32
+    doc: Distance from camera/monitor to target/eye.
+    quantity: '?'
+  - name: field_of_view
+    dtype: float32
+    dims:
+    - - width, height
+    - - width, height, depth
+    shape:
+    - - 2
+    - - 3
+    doc: Width, height and depth of image, or imaged area, in meters.
+    quantity: '?'
+  - name: data
+    dtype: numeric
+    dims:
+    - - frame
+      - x
+      - y
+    - - frame
+      - x
+      - y
+      - r, g, b
+    shape:
+    - - null
+      - null
+      - null
+    - - null
+      - null
+      - null
+      - 3
+    doc: Images presented to subject, either grayscale or RGB
+  - name: orientation
+    dtype: text
+    doc: Description of image relative to some reference frame (e.g., which way is
+      up). Must also specify frame of reference.
+    quantity: '?'
+
+- neurodata_type_def: IndexSeries
+  neurodata_type_inc: TimeSeries
+  doc: Stores indices to image frames stored in an ImageSeries. The purpose of the
+    IndexSeries is to allow a static image stack to be stored in an Images
+    object, and the images in the stack to be referenced out-of-order. This can be for
+    the display of individual images, or of movie segments (as a movie is simply a
+    series of images). The data field stores the index of the frame in the referenced
+    Images object, and the timestamps array indicates when that image
+    was displayed.
+  datasets:
+  - name: data
+    dtype: uint32
+    dims:
+    - num_times
+    shape:
+    - null
+    doc: Index of the image (using zero-indexing) in the linked Images object.
+    attributes:
+    - name: conversion
+      dtype: float32
+      doc: This field is unused by IndexSeries.
+      required: false
+    - name: resolution
+      dtype: float32
+      doc: This field is unused by IndexSeries.
+      required: false
+    - name: offset
+      dtype: float32
+      doc: This field is unused by IndexSeries.
+      required: false
+    - name: unit
+      dtype: text
+      value: N/A
+      doc: This field is unused by IndexSeries and has the value N/A.
+  links:
+  - name: indexed_timeseries
+    target_type: ImageSeries
+    doc: Link to ImageSeries object containing images that are indexed. Use of this link
+      is discouraged and will be deprecated. Link to an Images type instead.
+    quantity: '?'
+  - name: indexed_images
+    target_type: Images
+    doc: Link to Images object containing an ordered set of images that are indexed. The Images object
+      must contain a 'ordered_images' dataset specifying the order of the images in the Images type.
+    quantity: '?'

nwb-schema-linkml/src/data/tests/nwb.misc.yaml

@@ -0,0 +1,329 @@
+groups:
+- neurodata_type_def: AbstractFeatureSeries
+  neurodata_type_inc: TimeSeries
+  doc: Abstract features, such as quantitative descriptions of sensory stimuli. The
+    TimeSeries::data field is a 2D array, storing those features (e.g., for visual
+    grating stimulus this might be orientation, spatial frequency and contrast). Null
+    stimuli (eg, uniform gray) can be marked as being an independent feature (eg,
+    1.0 for gray, 0.0 for actual stimulus) or by storing NaNs for feature values,
+    or through use of the TimeSeries::control fields. A set of features is considered
+    to persist until the next set of features is defined. The final set of features
+    stored should be the null set. This is useful when storing the raw stimulus
+    is impractical.
+  datasets:
+  - name: data
+    dtype: numeric
+    dims:
+    - - num_times
+    - - num_times
+      - num_features
+    shape:
+    - - null
+    - - null
+      - null
+    doc: Values of each feature at each time.
+    attributes:
+    - name: unit
+      dtype: text
+      default_value: see 'feature_units'
+      doc: Since there can be different units for different features, store the units
+        in 'feature_units'. The default value for this attribute is "see 'feature_units'".
+      required: false
+  - name: feature_units
+    dtype: text
+    dims:
+    - num_features
+    shape:
+    - null
+    doc: Units of each feature.
+    quantity: '?'
+  - name: features
+    dtype: text
+    dims:
+    - num_features
+    shape:
+    - null
+    doc: Description of the features represented in TimeSeries::data.
+
+- neurodata_type_def: AnnotationSeries
+  neurodata_type_inc: TimeSeries
+  doc: Stores user annotations made during an experiment. The data[]
+    field stores a text array, and timestamps are stored for each annotation (ie,
+    interval=1). This is largely an alias to a standard TimeSeries storing a text
+    array but that is identifiable as storing annotations in a machine-readable way.
+  datasets:
+  - name: data
+    dtype: text
+    dims:
+    - num_times
+    shape:
+    - null
+    doc: Annotations made during an experiment.
+    attributes:
+    - name: resolution
+      dtype: float32
+      value: -1.0
+      doc: Smallest meaningful difference between values in data. Annotations have
+        no units, so the value is fixed to -1.0.
+    - name: unit
+      dtype: text
+      value: n/a
+      doc: Base unit of measurement for working with the data. Annotations have
+        no units, so the value is fixed to 'n/a'.
+
+- neurodata_type_def: IntervalSeries
+  neurodata_type_inc: TimeSeries
+  doc: Stores intervals of data. The timestamps field stores the beginning and end
+    of intervals. The data field stores whether the interval just started (>0 value)
+    or ended (<0 value). Different interval types can be represented in the same series
+    by using multiple key values (eg, 1 for feature A, 2 for feature B, 3 for feature
+    C, etc). The field data stores an 8-bit integer. This is largely an alias of a
+    standard TimeSeries but that is identifiable as representing time intervals in
+    a machine-readable way.
+  datasets:
+  - name: data
+    dtype: int8
+    dims:
+    - num_times
+    shape:
+    - null
+    doc: Use values >0 if interval started, <0 if interval ended.
+    attributes:
+    - name: resolution
+      dtype: float32
+      value: -1.0
+      doc: Smallest meaningful difference between values in data. Annotations have
+        no units, so the value is fixed to -1.0.
+    - name: unit
+      dtype: text
+      value: n/a
+      doc: Base unit of measurement for working with the data. Annotations have
+        no units, so the value is fixed to 'n/a'.
+
+- neurodata_type_def: DecompositionSeries
+  neurodata_type_inc: TimeSeries
+  doc: Spectral analysis of a time series, e.g. of an LFP or a speech signal.
+  datasets:
+  - name: data
+    dtype: numeric
+    dims:
+    - num_times
+    - num_channels
+    - num_bands
+    shape:
+    - null
+    - null
+    - null
+    doc: Data decomposed into frequency bands.
+    attributes:
+    - name: unit
+      dtype: text
+      default_value: no unit
+      doc: Base unit of measurement for working with the data. Actual stored values are
+        not necessarily stored in these units. To access the data in these units,
+        multiply 'data' by 'conversion'.
+  - name: metric
+    dtype: text
+    doc: The metric used, e.g. phase, amplitude, power.
+  - name: source_channels
+    neurodata_type_inc: DynamicTableRegion
+    doc: DynamicTableRegion pointer to the channels that this decomposition series was generated from.
+    quantity: '?'
+  groups:
+  - name: bands
+    neurodata_type_inc: DynamicTable
+    doc: Table for describing the bands that this series was generated from. There
+      should be one row in this table for each band.
+    datasets:
+    - name: band_name
+      neurodata_type_inc: VectorData
+      dtype: text
+      doc: Name of the band, e.g. theta.
+    - name: band_limits
+      neurodata_type_inc: VectorData
+      dtype: float32
+      dims:
+      - num_bands
+      - low, high
+      shape:
+      - null
+      - 2
+      doc: Low and high limit of each band in Hz. If it is a Gaussian filter, use
+        2 SD on either side of the center.
+    - name: band_mean
+      neurodata_type_inc: VectorData
+      dtype: float32
+      dims:
+      - num_bands
+      shape:
+      - null
+      doc: The mean Gaussian filters, in Hz.
+    - name: band_stdev
+      neurodata_type_inc: VectorData
+      dtype: float32
+      dims:
+      - num_bands
+      shape:
+      - null
+      doc: The standard deviation of Gaussian filters, in Hz.
+  links:
+  - name: source_timeseries
+    target_type: TimeSeries
+    doc: Link to TimeSeries object that this data was calculated from. Metadata about
+      electrodes and their position can be read from that ElectricalSeries so it is
+      not necessary to store that information here.
+    quantity: '?'
+
+- neurodata_type_def: Units
+  neurodata_type_inc: DynamicTable
+  default_name: Units
+  doc: Data about spiking units. Event times of observed units (e.g. cell, synapse,
+    etc.) should be concatenated and stored in spike_times.
+  datasets:
+  - name: spike_times_index
+    neurodata_type_inc: VectorIndex
+    doc: Index into the spike_times dataset.
+    quantity: '?'
+  - name: spike_times
+    neurodata_type_inc: VectorData
+    dtype: float64
+    doc: Spike times for each unit in seconds.
+    quantity: '?'
+    attributes:
+    - name: resolution
+      dtype: float64
+      doc: The smallest possible difference between two spike times. Usually 1 divided by the acquisition sampling rate
+        from which spike times were extracted, but could be larger if the acquisition time series was downsampled or
+        smaller if the acquisition time series was smoothed/interpolated and it is possible for the spike time to be
+        between samples.
+      required: false
+  - name: obs_intervals_index
+    neurodata_type_inc: VectorIndex
+    doc: Index into the obs_intervals dataset.
+    quantity: '?'
+  - name: obs_intervals
+    neurodata_type_inc: VectorData
+    dtype: float64
+    dims:
+    - num_intervals
+    - start|end
+    shape:
+    - null
+    - 2
+    doc: Observation intervals for each unit.
+    quantity: '?'
+  - name: electrodes_index
+    neurodata_type_inc: VectorIndex
+    doc: Index into electrodes.
+    quantity: '?'
+  - name: electrodes
+    neurodata_type_inc: DynamicTableRegion
+    doc: Electrode that each spike unit came from, specified using a DynamicTableRegion.
+    quantity: '?'
+  - name: electrode_group
+    neurodata_type_inc: VectorData
+    dtype:
+      target_type: ElectrodeGroup
+      reftype: object
+    doc: Electrode group that each spike unit came from.
+    quantity: '?'
+  - name: waveform_mean
+    neurodata_type_inc: VectorData
+    dtype: float32
+    dims:
+    - - num_units
+      - num_samples
+    - - num_units
+      - num_samples
+      - num_electrodes
+    shape:
+    - - null
+      - null
+    - - null
+      - null
+      - null
+    doc: Spike waveform mean for each spike unit.
+    quantity: '?'
+    attributes:
+    - name: sampling_rate
+      dtype: float32
+      doc: Sampling rate, in hertz.
+      required: false
+    - name: unit
+      dtype: text
+      value: volts
+      doc: Unit of measurement. This value is fixed to 'volts'.
+      required: false
+  - name: waveform_sd
+    neurodata_type_inc: VectorData
+    dtype: float32
+    dims:
+    - - num_units
+      - num_samples
+    - - num_units
+      - num_samples
+      - num_electrodes
+    shape:
+    - - null
+      - null
+    - - null
+      - null
+      - null
+    doc: Spike waveform standard deviation for each spike unit.
+    quantity: '?'
+    attributes:
+    - name: sampling_rate
+      dtype: float32
+      doc: Sampling rate, in hertz.
+      required: false
+    - name: unit
+      dtype: text
+      value: volts
+      doc: Unit of measurement. This value is fixed to 'volts'.
+      required: false
+  - name: waveforms
+    neurodata_type_inc: VectorData
+    dtype: numeric
+    dims:
+      - num_waveforms
+      - num_samples
+    shape:
+      - null
+      - null
+    doc: "Individual waveforms for each spike on each electrode. This is a doubly indexed column. The 'waveforms_index'
+      column indexes which waveforms in this column belong to the same spike event for a given unit, where each waveform
+      was recorded from a different electrode. The 'waveforms_index_index' column indexes the 'waveforms_index' column
+      to indicate which spike events belong to a given unit. For example, if the
+      'waveforms_index_index' column has values [2, 5, 6], then the first 2 elements of the 'waveforms_index' column
+      correspond to the 2 spike events of the first unit, the next 3 elements of the 'waveforms_index' column correspond
+      to the 3 spike events of the second unit, and the next 1 element of the 'waveforms_index' column corresponds to
+      the 1 spike event of the third unit. If the 'waveforms_index' column has values [3, 6, 8, 10, 12, 13], then
+      the first 3 elements of the 'waveforms' column contain the 3 spike waveforms that were recorded from 3 different
+      electrodes for the first spike time of the first unit. See
+      https://nwb-schema.readthedocs.io/en/stable/format_description.html#doubly-ragged-arrays for a graphical
+      representation of this example. When there is only one electrode for each unit (i.e., each spike time is
+      associated with a single waveform), then the 'waveforms_index' column will have values 1, 2, ..., N, where N is
+      the number of spike events. The number of electrodes for each spike event should be the same within a given unit.
+      The 'electrodes' column should be used to indicate which electrodes are associated with each unit, and the order
+      of the waveforms within a given unit x spike event should be in the same order as the electrodes referenced in
+      the 'electrodes' column of this table. The number of samples for each waveform must be the same."
+    quantity: '?'
+    attributes:
+      - name: sampling_rate
+        dtype: float32
+        doc: Sampling rate, in hertz.
+        required: false
+      - name: unit
+        dtype: text
+        value: volts
+        doc: Unit of measurement. This value is fixed to 'volts'.
+        required: false
+  - name: waveforms_index
+    neurodata_type_inc: VectorIndex
+    doc: Index into the waveforms dataset. One value for every spike event. See 'waveforms' for more detail.
+    quantity: '?'
+  - name: waveforms_index_index
+    neurodata_type_inc: VectorIndex
+    doc: Index into the waveforms_index dataset. One value for every unit (row in the table). See 'waveforms' for more
+      detail.
+    quantity: '?'

nwb-schema-linkml/src/data/tests/nwb.namespace.yaml

@@ -0,0 +1,60 @@
+namespaces:
+- name: core
+  doc: NWB namespace
+  author:
+  - Andrew Tritt
+  - Oliver Ruebel
+  - Ryan Ly
+  - Ben Dichter
+  - Keith Godfrey
+  - Jeff Teeters
+  contact:
+  - ajtritt@lbl.gov
+  - oruebel@lbl.gov
+  - rly@lbl.gov
+  - bdichter@lbl.gov
+  - keithg@alleninstitute.org
+  - jteeters@berkeley.edu
+  full_name: NWB core
+  schema:
+  - namespace: hdmf-common
+  - doc: This source module contains base data types used throughout the NWB data
+      format.
+    source: nwb.base.yaml
+    title: Base data types
+  - doc: This source module contains neurodata_types for device data.
+    source: nwb.device.yaml
+    title: Devices
+  - doc: This source module contains neurodata_types for epoch data.
+    source: nwb.epoch.yaml
+    title: Epochs
+  - doc: This source module contains neurodata_types for image data.
+    source: nwb.image.yaml
+    title: Image data
+  - doc: Main NWB file specification.
+    source: nwb.file.yaml
+    title: NWB file
+  - doc: Miscellaneous types.
+    source: nwb.misc.yaml
+    title: Miscellaneous neurodata_types.
+  - doc: This source module contains neurodata_types for behavior data.
+    source: nwb.behavior.yaml
+    title: Behavior
+  - doc: This source module contains neurodata_types for extracellular electrophysiology
+      data.
+    source: nwb.ecephys.yaml
+    title: Extracellular electrophysiology
+  - doc: This source module contains neurodata_types for intracellular electrophysiology
+      data.
+    source: nwb.icephys.yaml
+    title: Intracellular electrophysiology
+  - doc: This source module contains neurodata_types for opto-genetics data.
+    source: nwb.ogen.yaml
+    title: Optogenetics
+  - doc: This source module contains neurodata_types for optical physiology data.
+    source: nwb.ophys.yaml
+    title: Optical physiology
+  - doc: This source module contains neurodata_type for retinotopy data.
+    source: nwb.retinotopy.yaml
+    title: Retinotopy
+  version: "2.6.0-alpha"

nwb-schema-linkml/src/data/tests/nwb.ogen.yaml

@@ -0,0 +1,42 @@
+groups:
+- neurodata_type_def: OptogeneticSeries
+  neurodata_type_inc: TimeSeries
+  doc: An optogenetic stimulus.
+  datasets:
+  - name: data
+    dtype: numeric
+    dims:
+    - num_times
+    shape:
+    - null
+    doc: Applied power for optogenetic stimulus, in watts.
+    attributes:
+    - name: unit
+      dtype: text
+      value: watts
+      doc: Unit of measurement for data, which is fixed to 'watts'.
+  links:
+  - name: site
+    target_type: OptogeneticStimulusSite
+    doc: Link to OptogeneticStimulusSite object that describes the site to which this
+      stimulus was applied.
+
+- neurodata_type_def: OptogeneticStimulusSite
+  neurodata_type_inc: NWBContainer
+  doc: A site of optogenetic stimulation.
+  datasets:
+  - name: description
+    dtype: text
+    doc: Description of stimulation site.
+  - name: excitation_lambda
+    dtype: float32
+    doc: Excitation wavelength, in nm.
+  - name: location
+    dtype: text
+    doc: Location of the stimulation site. Specify the area, layer, comments on estimation
+      of area/layer, stereotaxic coordinates if in vivo, etc. Use standard atlas
+      names for anatomical regions when possible.
+  links:
+  - name: device
+    target_type: Device
+    doc: Device that generated the stimulus.

nwb-schema-linkml/src/data/tests/nwb.ophys.yaml

@@ -0,0 +1,360 @@
+groups:
+- neurodata_type_def: OnePhotonSeries
+  neurodata_type_inc: ImageSeries
+  doc: Image stack recorded over time from 1-photon microscope.
+  attributes:
+  - name: pmt_gain
+    dtype: float32
+    doc: Photomultiplier gain.
+    required: false
+  - name: scan_line_rate
+    dtype: float32
+    doc: Lines imaged per second. This is also stored in /general/optophysiology but
+      is kept here as it is useful information for analysis, and so good to be stored
+      w/ the actual data.
+    required: false
+  - name: exposure_time
+    dtype: float32
+    doc: Exposure time of the sample; often the inverse of the frequency.
+    required: false
+  - name: binning
+    dtype: uint8
+    doc: Amount of pixels combined into 'bins'; could be 1, 2, 4, 8, etc.
+    required: false
+  - name: power
+    dtype: float32
+    doc: Power of the excitation in mW, if known.
+    required: false
+  - name: intensity
+    dtype: float32
+    doc: Intensity of the excitation in mW/mm^2, if known.
+    required: false
+  links:
+  - name: imaging_plane
+    target_type: ImagingPlane
+    doc: Link to ImagingPlane object from which this TimeSeries data was generated.
+
+- neurodata_type_def: TwoPhotonSeries
+  neurodata_type_inc: ImageSeries
+  doc: Image stack recorded over time from 2-photon microscope.
+  attributes:
+  - name: pmt_gain
+    dtype: float32
+    doc: Photomultiplier gain.
+    required: false
+  - name: scan_line_rate
+    dtype: float32
+    doc: Lines imaged per second. This is also stored in /general/optophysiology but
+      is kept here as it is useful information for analysis, and so good to be stored
+      w/ the actual data.
+    required: false
+  datasets:
+  - name: field_of_view
+    dtype: float32
+    dims:
+    - - width|height
+    - - width|height|depth
+    shape:
+    - - 2
+    - - 3
+    doc: Width, height and depth of image, or imaged area, in meters.
+    quantity: '?'
+  links:
+  - name: imaging_plane
+    target_type: ImagingPlane
+    doc: Link to ImagingPlane object from which this TimeSeries data was generated.
+
+- neurodata_type_def: RoiResponseSeries
+  neurodata_type_inc: TimeSeries
+  doc: ROI responses over an imaging plane. The first dimension represents time.
+    The second dimension, if present, represents ROIs.
+  datasets:
+  - name: data
+    dtype: numeric
+    dims:
+    - - num_times
+    - - num_times
+      - num_ROIs
+    shape:
+    - - null
+    - - null
+      - null
+    doc: Signals from ROIs.
+  - name: rois
+    neurodata_type_inc: DynamicTableRegion
+    doc: DynamicTableRegion referencing into an ROITable containing information on the ROIs
+      stored in this timeseries.
+
+- neurodata_type_def: DfOverF
+  neurodata_type_inc: NWBDataInterface
+  default_name: DfOverF
+  doc: dF/F information about a region of interest (ROI). Storage hierarchy of dF/F
+    should be the same as for segmentation (i.e., same names for ROIs and for image
+    planes).
+  groups:
+  - neurodata_type_inc: RoiResponseSeries
+    doc: RoiResponseSeries object(s) containing dF/F for a ROI.
+    quantity: '+'
+
+- neurodata_type_def: Fluorescence
+  neurodata_type_inc: NWBDataInterface
+  default_name: Fluorescence
+  doc: Fluorescence information about a region of interest (ROI). Storage hierarchy
+    of fluorescence should be the same as for segmentation (ie, same names for ROIs
+    and for image planes).
+  groups:
+  - neurodata_type_inc: RoiResponseSeries
+    doc: RoiResponseSeries object(s) containing fluorescence data for a ROI.
+    quantity: '+'
+
+- neurodata_type_def: ImageSegmentation
+  neurodata_type_inc: NWBDataInterface
+  default_name: ImageSegmentation
+  doc: Stores pixels in an image that represent different regions of interest (ROIs)
+    or masks. All segmentation for a given imaging plane is stored together, with
+    storage for multiple imaging planes (masks) supported. Each ROI is stored in its
+    own subgroup, with the ROI group containing both a 2D mask and a list of pixels
+    that make up this mask. Segments can also be used for masking neuropil. If segmentation
+    is allowed to change with time, a new imaging plane (or module) is required and
+    ROI names should remain consistent between them.
+  groups:
+  - neurodata_type_inc: PlaneSegmentation
+    doc: Results from image segmentation of a specific imaging plane.
+    quantity: '+'
+
+- neurodata_type_def: PlaneSegmentation
+  neurodata_type_inc: DynamicTable
+  doc: Results from image segmentation of a specific imaging plane.
+  datasets:
+  - name: image_mask
+    neurodata_type_inc: VectorData
+    dims:
+    - - num_roi
+      - num_x
+      - num_y
+    - - num_roi
+      - num_x
+      - num_y
+      - num_z
+    shape:
+    - - null
+      - null
+      - null
+    - - null
+      - null
+      - null
+      - null
+    doc: ROI masks for each ROI. Each image mask is the size of the original imaging
+      plane (or volume) and members of the ROI are finite non-zero.
+    quantity: '?'
+  - name: pixel_mask_index
+    neurodata_type_inc: VectorIndex
+    doc: Index into pixel_mask.
+    quantity: '?'
+  - name: pixel_mask
+    neurodata_type_inc: VectorData
+    dtype:
+    - name: x
+      dtype: uint32
+      doc: Pixel x-coordinate.
+    - name: y
+      dtype: uint32
+      doc: Pixel y-coordinate.
+    - name: weight
+      dtype: float32
+      doc: Weight of the pixel.
+    doc: 'Pixel masks for each ROI: a list of indices and weights for the ROI. Pixel
+      masks are concatenated and parsing of this dataset is maintained by the PlaneSegmentation'
+    quantity: '?'
+  - name: voxel_mask_index
+    neurodata_type_inc: VectorIndex
+    doc: Index into voxel_mask.
+    quantity: '?'
+  - name: voxel_mask
+    neurodata_type_inc: VectorData
+    dtype:
+    - name: x
+      dtype: uint32
+      doc: Voxel x-coordinate.
+    - name: y
+      dtype: uint32
+      doc: Voxel y-coordinate.
+    - name: z
+      dtype: uint32
+      doc: Voxel z-coordinate.
+    - name: weight
+      dtype: float32
+      doc: Weight of the voxel.
+    doc: 'Voxel masks for each ROI: a list of indices and weights for the ROI. Voxel
+      masks are concatenated and parsing of this dataset is maintained by the PlaneSegmentation'
+    quantity: '?'
+  groups:
+  - name: reference_images
+    doc: Image stacks that the segmentation masks apply to.
+    groups:
+    - neurodata_type_inc: ImageSeries
+      doc: One or more image stacks that the masks apply to (can be one-element
+        stack).
+      quantity: '*'
+  links:
+  - name: imaging_plane
+    target_type: ImagingPlane
+    doc: Link to ImagingPlane object from which this data was generated.
+
+- neurodata_type_def: ImagingPlane
+  neurodata_type_inc: NWBContainer
+  doc: An imaging plane and its metadata.
+  datasets:
+  - name: description
+    dtype: text
+    doc: Description of the imaging plane.
+    quantity: '?'
+  - name: excitation_lambda
+    dtype: float32
+    doc: Excitation wavelength, in nm.
+  - name: imaging_rate
+    dtype: float32
+    doc: Rate that images are acquired, in Hz. If the corresponding TimeSeries is present, the rate should be stored
+      there instead.
+    quantity: '?'
+  - name: indicator
+    dtype: text
+    doc: Calcium indicator.
+  - name: location
+    dtype: text
+    doc: Location of the imaging plane. Specify the area, layer, comments on estimation
+      of area/layer, stereotaxic coordinates if in vivo, etc. Use standard atlas
+      names for anatomical regions when possible.
+  - name: manifold
+    dtype: float32
+    dims:
+    - - height
+      - width
+      - x, y, z
+    - - height
+      - width
+      - depth
+      - x, y, z
+    shape:
+    - - null
+      - null
+      - 3
+    - - null
+      - null
+      - null
+      - 3
+    doc: "DEPRECATED Physical position of each pixel. 'xyz' represents the position\
+      \ of the pixel relative to the defined coordinate space. Deprecated in favor of origin_coords and grid_spacing."
+    quantity: '?'
+    attributes:
+    - name: conversion
+      dtype: float32
+      default_value: 1.0
+      doc: Scalar to multiply each element in data to convert it to the specified 'unit'.
+        If the data are stored in acquisition system units or other units
+        that require a conversion to be interpretable, multiply the data by 'conversion'
+        to convert the data to the specified 'unit'. e.g. if the data acquisition system
+        stores values in this object as pixels from x = -500 to 499, y = -500 to 499
+        that correspond to a 2 m x 2 m range, then the 'conversion' multiplier to get
+        from raw data acquisition pixel units to meters is 2/1000.
+      required: false
+    - name: unit
+      dtype: text
+      default_value: meters
+      doc: Base unit of measurement for working with the data. The default value is 'meters'.
+      required: false
+  - name: origin_coords
+    dtype: float32
+    dims:
+    - - x, y
+    - - x, y, z
+    shape:
+    - - 2
+    - - 3
+    doc: Physical location of the first element of the imaging plane (0, 0) for 2-D data or (0, 0, 0) for 3-D data.
+      See also reference_frame for what the physical location is relative to (e.g., bregma).
+    quantity: '?'
+    attributes:
+    - name: unit
+      dtype: text
+      default_value: meters
+      doc: Measurement units for origin_coords. The default value is 'meters'.
+  - name: grid_spacing
+    dtype: float32
+    dims:
+    - - x, y
+    - - x, y, z
+    shape:
+    - - 2
+    - - 3
+    doc: Space between pixels in (x, y) or voxels in (x, y, z) directions, in the specified unit.
+      Assumes imaging plane is a regular grid. See also reference_frame to interpret the grid.
+    quantity: '?'
+    attributes:
+    - name: unit
+      dtype: text
+      default_value: meters
+      doc: Measurement units for grid_spacing. The default value is 'meters'.
+  - name: reference_frame
+    dtype: text
+    doc: Describes reference frame of origin_coords and grid_spacing.
+      For example, this can be a text description of the anatomical location and orientation of the grid
+      defined by origin_coords and grid_spacing or the vectors needed to transform or rotate the grid to
+      a common anatomical axis (e.g., AP/DV/ML). This field is necessary to interpret origin_coords and grid_spacing.
+      If origin_coords and grid_spacing are not present, then this field is not required.
+      For example, if the microscope takes 10 x 10 x 2 images, where the first value of the data matrix
+      (index (0, 0, 0)) corresponds to (-1.2, -0.6, -2) mm relative to bregma, the spacing between pixels is 0.2 mm in
+      x, 0.2 mm in y and 0.5 mm in z, and larger numbers in x means more anterior, larger numbers in y means more
+      rightward, and larger numbers in z means more ventral, then enter the following --
+      origin_coords = (-1.2, -0.6, -2)
+      grid_spacing = (0.2, 0.2, 0.5)
+      reference_frame = "Origin coordinates are relative to bregma. First dimension corresponds to anterior-posterior
+      axis (larger index = more anterior). Second dimension corresponds to medial-lateral axis (larger index = more
+      rightward). Third dimension corresponds to dorsal-ventral axis (larger index = more ventral)."
+    quantity: '?'
+  groups:
+  - neurodata_type_inc: OpticalChannel
+    doc: An optical channel used to record from an imaging plane.
+    quantity: '+'
+  links:
+  - name: device
+    target_type: Device
+    doc: Link to the Device object that was used to record from this electrode.
+
+- neurodata_type_def: OpticalChannel
+  neurodata_type_inc: NWBContainer
+  doc: An optical channel used to record from an imaging plane.
+  datasets:
+  - name: description
+    dtype: text
+    doc: Description or other notes about the channel.
+  - name: emission_lambda
+    dtype: float32
+    doc: Emission wavelength for channel, in nm.
+
+- neurodata_type_def: MotionCorrection
+  neurodata_type_inc: NWBDataInterface
+  default_name: MotionCorrection
+  doc: 'An image stack where all frames are shifted (registered) to a common coordinate
+    system, to account for movement and drift between frames. Note: each frame at
+    each point in time is assumed to be 2-D (has only x & y dimensions).'
+  groups:
+  - neurodata_type_inc: CorrectedImageStack
+    doc: Reuslts from motion correction of an image stack.
+    quantity: '+'
+
+- neurodata_type_def: CorrectedImageStack
+  neurodata_type_inc: NWBDataInterface
+  doc: Reuslts from motion correction of an image stack.
+  groups:
+  - name: corrected
+    neurodata_type_inc: ImageSeries
+    doc: Image stack with frames shifted to the common coordinates.
+  - name: xy_translation
+    neurodata_type_inc: TimeSeries
+    doc: Stores the x,y delta necessary to align each frame to the common coordinates,
+      for example, to align each frame to a reference image.
+  links:
+  - name: original
+    target_type: ImageSeries
+    doc: Link to ImageSeries object that is being registered.

nwb-schema-linkml/src/data/tests/nwb.retinotopy.yaml

@@ -0,0 +1,234 @@
+groups:
+- neurodata_type_def: ImagingRetinotopy
+  neurodata_type_inc: NWBDataInterface
+  default_name: ImagingRetinotopy
+  doc: 'Intrinsic signal optical imaging or widefield imaging for measuring retinotopy.
+    Stores orthogonal maps (e.g., altitude/azimuth; radius/theta) of responses to
+    specific stimuli and a combined polarity map from which to identify visual areas.
+    This group does not store the raw responses imaged during retinotopic mapping or the
+    stimuli presented, but rather the resulting phase and power maps after applying a Fourier
+    transform on the averaged responses.
+    Note: for data consistency, all images and arrays are stored in the format [row][column]
+    and [row, col], which equates to [y][x]. Field of view and dimension arrays may
+    appear backward (i.e., y before x).'
+  datasets:
+  - name: axis_1_phase_map
+    dtype: float32
+    dims:
+    - num_rows
+    - num_cols
+    shape:
+    - null
+    - null
+    doc: Phase response to stimulus on the first measured axis.
+    attributes:
+    - name: dimension
+      dtype: int32
+      dims:
+      - num_rows, num_cols
+      shape:
+      - 2
+      doc: 'Number of rows and columns in the image. NOTE: row, column representation
+        is equivalent to height, width.'
+    - name: field_of_view
+      dtype: float32
+      dims:
+      - height, width
+      shape:
+      - 2
+      doc: Size of viewing area, in meters.
+    - name: unit
+      dtype: text
+      doc: Unit that axis data is stored in (e.g., degrees).
+  - name: axis_1_power_map
+    dtype: float32
+    dims:
+    - num_rows
+    - num_cols
+    shape:
+    - null
+    - null
+    doc: Power response on the first measured axis. Response is scaled so 0.0 is no
+      power in the response and 1.0 is maximum relative power.
+    quantity: '?'
+    attributes:
+    - name: dimension
+      dtype: int32
+      dims:
+      - num_rows, num_cols
+      shape:
+      - 2
+      doc: 'Number of rows and columns in the image. NOTE: row, column representation
+        is equivalent to height, width.'
+    - name: field_of_view
+      dtype: float32
+      dims:
+      - height, width
+      shape:
+      - 2
+      doc: Size of viewing area, in meters.
+    - name: unit
+      dtype: text
+      doc: Unit that axis data is stored in (e.g., degrees).
+  - name: axis_2_phase_map
+    dtype: float32
+    dims:
+    - num_rows
+    - num_cols
+    shape:
+    - null
+    - null
+    doc: Phase response to stimulus on the second measured axis.
+    attributes:
+    - name: dimension
+      dtype: int32
+      dims:
+      - num_rows, num_cols
+      shape:
+      - 2
+      doc: 'Number of rows and columns in the image. NOTE: row, column representation
+        is equivalent to height, width.'
+    - name: field_of_view
+      dtype: float32
+      dims:
+      - height, width
+      shape:
+      - 2
+      doc: Size of viewing area, in meters.
+    - name: unit
+      dtype: text
+      doc: Unit that axis data is stored in (e.g., degrees).
+  - name: axis_2_power_map
+    dtype: float32
+    dims:
+    - num_rows
+    - num_cols
+    shape:
+    - null
+    - null
+    doc: Power response on the second measured axis. Response is scaled so 0.0 is
+      no power in the response and 1.0 is maximum relative power.
+    quantity: '?'
+    attributes:
+    - name: dimension
+      dtype: int32
+      dims:
+      - num_rows, num_cols
+      shape:
+      - 2
+      doc: 'Number of rows and columns in the image. NOTE: row, column representation
+        is equivalent to height, width.'
+    - name: field_of_view
+      dtype: float32
+      dims:
+      - height, width
+      shape:
+      - 2
+      doc: Size of viewing area, in meters.
+    - name: unit
+      dtype: text
+      doc: Unit that axis data is stored in (e.g., degrees).
+  - name: axis_descriptions
+    dtype: text
+    dims:
+    - axis_1, axis_2
+    shape:
+    - 2
+    doc: Two-element array describing the contents of the two response axis fields.
+      Description should be something like ['altitude', 'azimuth'] or '['radius',
+      'theta'].
+  - name: focal_depth_image
+    dtype: uint16
+    dims:
+    - num_rows
+    - num_cols
+    shape:
+    - null
+    - null
+    doc: 'Gray-scale image taken with same settings/parameters (e.g., focal depth,
+      wavelength) as data collection. Array format: [rows][columns].'
+    quantity: '?'
+    attributes:
+    - name: bits_per_pixel
+      dtype: int32
+      doc: Number of bits used to represent each value. This is necessary to determine
+        maximum (white) pixel value.
+    - name: dimension
+      dtype: int32
+      dims:
+      - num_rows, num_cols
+      shape:
+      - 2
+      doc: 'Number of rows and columns in the image. NOTE: row, column representation
+        is equivalent to height, width.'
+    - name: field_of_view
+      dtype: float32
+      dims:
+      - height, width
+      shape:
+      - 2
+      doc: Size of viewing area, in meters.
+    - name: focal_depth
+      dtype: float32
+      doc: Focal depth offset, in meters.
+    - name: format
+      dtype: text
+      doc: Format of image. Right now only 'raw' is supported.
+  - name: sign_map
+    dtype: float32
+    dims:
+    - num_rows
+    - num_cols
+    shape:
+    - null
+    - null
+    doc: Sine of the angle between the direction of the gradient in axis_1 and axis_2.
+    quantity: '?'
+    attributes:
+    - name: dimension
+      dtype: int32
+      dims:
+      - num_rows, num_cols
+      shape:
+      - 2
+      doc: 'Number of rows and columns in the image. NOTE: row, column representation
+        is equivalent to height, width.'
+    - name: field_of_view
+      dtype: float32
+      dims:
+      - height, width
+      shape:
+      - 2
+      doc: Size of viewing area, in meters.
+  - name: vasculature_image
+    dtype: uint16
+    dims:
+    - num_rows
+    - num_cols
+    shape:
+    - null
+    - null
+    doc: 'Gray-scale anatomical image of cortical surface. Array structure: [rows][columns]'
+    attributes:
+    - name: bits_per_pixel
+      dtype: int32
+      doc: Number of bits used to represent each value. This is necessary to determine
+        maximum (white) pixel value
+    - name: dimension
+      dtype: int32
+      dims:
+      - num_rows, num_cols
+      shape:
+      - 2
+      doc: 'Number of rows and columns in the image. NOTE: row, column representation
+        is equivalent to height, width.'
+    - name: field_of_view
+      dtype: float32
+      dims:
+      - height, width
+      shape:
+      - 2
+      doc: Size of viewing area, in meters.
+    - name: format
+      dtype: text
+      doc: Format of image. Right now only 'raw' is supported.

nwb-schema-linkml/src/nwb_schema_language/datamodel/nwb_schema_language.py

@@ -1,5 +1,5 @@
 # Auto generated from nwb_schema_language.yaml by pythongen.py version: 0.0.1
-# Generation date: 2023-08-16T15:57:41
+# Generation date: 2023-08-16T23:21:37
 # Schema: nwb-schema-language
 #
 # id: https://w3id.org/p2p_ld/nwb-schema-language
@@ -21,8 +21,8 @@ from linkml_runtime.utils.formatutils import camelcase, underscore, sfx
 from linkml_runtime.utils.enumerations import EnumDefinitionImpl
 from rdflib import Namespace, URIRef
 from linkml_runtime.utils.curienamespace import CurieNamespace
-from linkml_runtime.linkml_model.types import Date, Integer, String, Uriorcurie
+from linkml_runtime.linkml_model.types import Boolean, Date, String
-from linkml_runtime.utils.metamodelcore import URIorCURIE, XSDDate
+from linkml_runtime.utils.metamodelcore import Bool, XSDDate
 
 metamodel_version = "1.7.0"
 version = None
@@ -31,9 +31,6 @@ version = None
 dataclasses._init_fn = dataclasses_init_fn_with_kwargs
 
 # Namespaces
-PATO = CurieNamespace('PATO', 'http://purl.obolibrary.org/obo/PATO_')
-BIOLINK = CurieNamespace('biolink', 'https://w3id.org/biolink/')
-EXAMPLE = CurieNamespace('example', 'https://example.org/')
 LINKML = CurieNamespace('linkml', 'https://w3id.org/linkml/')
 NWB_SCHEMA_LANGUAGE = CurieNamespace('nwb_schema_language', 'https://w3id.org/p2p_ld/nwb-schema-language/')
 SCHEMA = CurieNamespace('schema', 'http://schema.org/')
@@ -43,50 +40,71 @@ DEFAULT_ = NWB_SCHEMA_LANGUAGE
 # Types
 
 # Class references
-class NamedThingId(URIorCURIE):
-    pass
 
 
-class NamespacesId(NamedThingId):
-    pass
-
 
 @dataclass
-class NamedThing(YAMLRoot):
+class Namespace(YAMLRoot):
-    """
-    A generic grouping for any identifiable entity
-    """
     _inherited_slots: ClassVar[List[str]] = []
 
-    class_class_uri: ClassVar[URIRef] = SCHEMA.Thing
+    class_class_uri: ClassVar[URIRef] = NWB_SCHEMA_LANGUAGE.Namespace
-    class_class_curie: ClassVar[str] = "schema:Thing"
+    class_class_curie: ClassVar[str] = "nwb_schema_language:Namespace"
-    class_name: ClassVar[str] = "NamedThing"
+    class_name: ClassVar[str] = "Namespace"
-    class_model_uri: ClassVar[URIRef] = NWB_SCHEMA_LANGUAGE.NamedThing
+    class_model_uri: ClassVar[URIRef] = NWB_SCHEMA_LANGUAGE.Namespace
 
-    id: Union[str, NamedThingId] = None
+    doc: str = None
-    name: Optional[str] = None
+    name: str = None
-    description: Optional[str] = None
+    version: str = None
+    author: Union[str, List[str]] = None
+    contact: Union[str, List[str]] = None
+    full_name: Optional[str] = None
+    date: Optional[Union[str, XSDDate]] = None
+    schema: Optional[Union[Union[dict, "Schema"], List[Union[dict, "Schema"]]]] = empty_list()
 
     def __post_init__(self, *_: List[str], **kwargs: Dict[str, Any]):
-        if self._is_empty(self.id):
+        if self._is_empty(self.doc):
-            self.MissingRequiredField("id")
+            self.MissingRequiredField("doc")
-        if not isinstance(self.id, NamedThingId):
+        if not isinstance(self.doc, str):
-            self.id = NamedThingId(self.id)
+            self.doc = str(self.doc)
 
-        if self.name is not None and not isinstance(self.name, str):
+        if self._is_empty(self.name):
+            self.MissingRequiredField("name")
+        if not isinstance(self.name, str):
             self.name = str(self.name)
 
-        if self.description is not None and not isinstance(self.description, str):
+        if self._is_empty(self.version):
-            self.description = str(self.description)
+            self.MissingRequiredField("version")
+        if not isinstance(self.version, str):
+            self.version = str(self.version)
+
+        if self._is_empty(self.author):
+            self.MissingRequiredField("author")
+        if not isinstance(self.author, list):
+            self.author = [self.author] if self.author is not None else []
+        self.author = [v if isinstance(v, str) else str(v) for v in self.author]
+
+        if self._is_empty(self.contact):
+            self.MissingRequiredField("contact")
+        if not isinstance(self.contact, list):
+            self.contact = [self.contact] if self.contact is not None else []
+        self.contact = [v if isinstance(v, str) else str(v) for v in self.contact]
+
+        if self.full_name is not None and not isinstance(self.full_name, str):
+            self.full_name = str(self.full_name)
+
+        if self.date is not None and not isinstance(self.date, XSDDate):
+            self.date = XSDDate(self.date)
+
+        print(self.schema)
+        if not isinstance(self.schema, list):
+            self.schema = [self.schema] if self.schema is not None else []
+        self.schema = [v if isinstance(v, Schema) else Schema(**as_dict(v)) for v in self.schema]
 
         super().__post_init__(**kwargs)
 
 
 @dataclass
-class Namespaces(NamedThing):
+class Namespaces(YAMLRoot):
-    """
-    Represents a Namespaces
-    """
     _inherited_slots: ClassVar[List[str]] = []
 
     class_class_uri: ClassVar[URIRef] = NWB_SCHEMA_LANGUAGE.Namespaces
@@ -94,100 +112,579 @@ class Namespaces(NamedThing):
     class_name: ClassVar[str] = "Namespaces"
     class_model_uri: ClassVar[URIRef] = NWB_SCHEMA_LANGUAGE.Namespaces
 
-    id: Union[str, NamespacesId] = None
+    namespaces: Optional[Union[Union[dict, Namespace], List[Union[dict, Namespace]]]] = empty_list()
-    primary_email: Optional[str] = None
-    birth_date: Optional[Union[str, XSDDate]] = None
-    age_in_years: Optional[int] = None
-    vital_status: Optional[Union[str, "PersonStatus"]] = None
 
     def __post_init__(self, *_: List[str], **kwargs: Dict[str, Any]):
-        if self._is_empty(self.id):
+        self._normalize_inlined_as_dict(slot_name="namespaces", slot_type=Namespace, key_name="doc", keyed=False)
-            self.MissingRequiredField("id")
-        if not isinstance(self.id, NamespacesId):
-            self.id = NamespacesId(self.id)
-
-        if self.primary_email is not None and not isinstance(self.primary_email, str):
-            self.primary_email = str(self.primary_email)
-
-        if self.birth_date is not None and not isinstance(self.birth_date, XSDDate):
-            self.birth_date = XSDDate(self.birth_date)
-
-        if self.age_in_years is not None and not isinstance(self.age_in_years, int):
-            self.age_in_years = int(self.age_in_years)
-
-        if self.vital_status is not None and not isinstance(self.vital_status, PersonStatus):
-            self.vital_status = PersonStatus(self.vital_status)
 
         super().__post_init__(**kwargs)
 
 
 @dataclass
-class NamespacesCollection(YAMLRoot):
+class Schema(YAMLRoot):
-    """
-    A holder for Namespaces objects
-    """
     _inherited_slots: ClassVar[List[str]] = []
 
-    class_class_uri: ClassVar[URIRef] = NWB_SCHEMA_LANGUAGE.NamespacesCollection
+    class_class_uri: ClassVar[URIRef] = NWB_SCHEMA_LANGUAGE.Schema
-    class_class_curie: ClassVar[str] = "nwb_schema_language:NamespacesCollection"
+    class_class_curie: ClassVar[str] = "nwb_schema_language:Schema"
-    class_name: ClassVar[str] = "NamespacesCollection"
+    class_name: ClassVar[str] = "Schema"
-    class_model_uri: ClassVar[URIRef] = NWB_SCHEMA_LANGUAGE.NamespacesCollection
+    class_model_uri: ClassVar[URIRef] = NWB_SCHEMA_LANGUAGE.Schema
 
-    entries: Optional[Union[Dict[Union[str, NamespacesId], Union[dict, Namespaces]], List[Union[dict, Namespaces]]]] = empty_dict()
+    doc: str = None
+    source: Optional[str] = None
+    namespace: Optional[str] = None
+    title: Optional[str] = None
+    neurodata_types: Optional[Union[str, List[str]]] = empty_list()
 
     def __post_init__(self, *_: List[str], **kwargs: Dict[str, Any]):
-        self._normalize_inlined_as_dict(slot_name="entries", slot_type=Namespaces, key_name="id", keyed=True)
+        if self._is_empty(self.doc):
+            self.MissingRequiredField("doc")
+        if not isinstance(self.doc, str):
+            self.doc = str(self.doc)
+
+        if self.source is not None and not isinstance(self.source, str):
+            self.source = str(self.source)
+
+        if self.namespace is not None and not isinstance(self.namespace, str):
+            self.namespace = str(self.namespace)
+
+        if self.title is not None and not isinstance(self.title, str):
+            self.title = str(self.title)
+
+        if not isinstance(self.neurodata_types, list):
+            self.neurodata_types = [self.neurodata_types] if self.neurodata_types is not None else []
+        self.neurodata_types = [v if isinstance(v, str) else str(v) for v in self.neurodata_types]
 
         super().__post_init__(**kwargs)
 
 
-# Enumerations
+@dataclass
-class PersonStatus(EnumDefinitionImpl):
+class Group(YAMLRoot):
+    _inherited_slots: ClassVar[List[str]] = []
 
-    ALIVE = PermissibleValue(
+    class_class_uri: ClassVar[URIRef] = NWB_SCHEMA_LANGUAGE.Group
-        text="ALIVE",
+    class_class_curie: ClassVar[str] = "nwb_schema_language:Group"
-        description="the person is living",
+    class_name: ClassVar[str] = "Group"
-        meaning=PATO["0001421"])
+    class_model_uri: ClassVar[URIRef] = NWB_SCHEMA_LANGUAGE.Group
-    DEAD = PermissibleValue(
+
-        text="DEAD",
+    doc: str = None
-        description="the person is deceased",
+    neurodata_type_def: Optional[str] = None
-        meaning=PATO["0001422"])
+    neurodata_type_inc: Optional[str] = None
-    UNKNOWN = PermissibleValue(
+    name: Optional[str] = None
-        text="UNKNOWN",
+    default_name: Optional[str] = None
-        description="the vital status is not known")
+    quantity: Optional[str] = 1
+    linkable: Optional[Union[bool, Bool]] = None
+    attributes: Optional[Union[Union[dict, "Attribute"], List[Union[dict, "Attribute"]]]] = empty_list()
+    datasets: Optional[Union[Union[dict, "Dataset"], List[Union[dict, "Dataset"]]]] = empty_list()
+    groups: Optional[Union[Union[dict, "Group"], List[Union[dict, "Group"]]]] = empty_list()
+    links: Optional[Union[Union[dict, "Link"], List[Union[dict, "Link"]]]] = empty_list()
+
+    def __post_init__(self, *_: List[str], **kwargs: Dict[str, Any]):
+        if self._is_empty(self.doc):
+            self.MissingRequiredField("doc")
+        if not isinstance(self.doc, str):
+            self.doc = str(self.doc)
+
+        if self.neurodata_type_def is not None and not isinstance(self.neurodata_type_def, str):
+            self.neurodata_type_def = str(self.neurodata_type_def)
+
+        if self.neurodata_type_inc is not None and not isinstance(self.neurodata_type_inc, str):
+            self.neurodata_type_inc = str(self.neurodata_type_inc)
+
+        if self.name is not None and not isinstance(self.name, str):
+            self.name = str(self.name)
+
+        if self.default_name is not None and not isinstance(self.default_name, str):
+            self.default_name = str(self.default_name)
+
+        if self.quantity is not None and not isinstance(self.quantity, str):
+            self.quantity = str(self.quantity)
+
+        if self.linkable is not None and not isinstance(self.linkable, Bool):
+            self.linkable = Bool(self.linkable)
+
+        self._normalize_inlined_as_dict(slot_name="attributes", slot_type=Attribute, key_name="name", keyed=False)
+
+        self._normalize_inlined_as_dict(slot_name="datasets", slot_type=Dataset, key_name="doc", keyed=False)
+
+        self._normalize_inlined_as_dict(slot_name="groups", slot_type=Group, key_name="doc", keyed=False)
+
+        self._normalize_inlined_as_dict(slot_name="links", slot_type=Link, key_name="doc", keyed=False)
+
+        super().__post_init__(**kwargs)
+
+
+@dataclass
+class Attribute(YAMLRoot):
+    _inherited_slots: ClassVar[List[str]] = []
+
+    class_class_uri: ClassVar[URIRef] = NWB_SCHEMA_LANGUAGE.Attribute
+    class_class_curie: ClassVar[str] = "nwb_schema_language:Attribute"
+    class_name: ClassVar[str] = "Attribute"
+    class_model_uri: ClassVar[URIRef] = NWB_SCHEMA_LANGUAGE.Attribute
+
+    name: str = None
+    doc: str = None
+    dims: Optional[Union[str, List[str]]] = empty_list()
+    shape: Optional[Union[str, List[str]]] = empty_list()
+    value: Optional[Union[dict, "AnyType"]] = None
+    default_value: Optional[Union[dict, "AnyType"]] = None
+    required: Optional[Union[bool, Bool]] = True
+    dtype: Optional[str] = None
+
+    def __post_init__(self, *_: List[str], **kwargs: Dict[str, Any]):
+        if self._is_empty(self.name):
+            self.MissingRequiredField("name")
+        if not isinstance(self.name, str):
+            self.name = str(self.name)
+
+        if self._is_empty(self.doc):
+            self.MissingRequiredField("doc")
+        if not isinstance(self.doc, str):
+            self.doc = str(self.doc)
+
+        if not isinstance(self.dims, list):
+            self.dims = [self.dims] if self.dims is not None else []
+        self.dims = [v if isinstance(v, str) else str(v) for v in self.dims]
+
+        if not isinstance(self.shape, list):
+            self.shape = [self.shape] if self.shape is not None else []
+        self.shape = [v if isinstance(v, str) else str(v) for v in self.shape]
+
+        if self.required is not None and not isinstance(self.required, Bool):
+            self.required = Bool(self.required)
+
+        if self.dtype is not None and not isinstance(self.dtype, str):
+            self.dtype = str(self.dtype)
+
+        super().__post_init__(**kwargs)
+
+
+@dataclass
+class Link(YAMLRoot):
+    _inherited_slots: ClassVar[List[str]] = []
+
+    class_class_uri: ClassVar[URIRef] = NWB_SCHEMA_LANGUAGE.Link
+    class_class_curie: ClassVar[str] = "nwb_schema_language:Link"
+    class_name: ClassVar[str] = "Link"
+    class_model_uri: ClassVar[URIRef] = NWB_SCHEMA_LANGUAGE.Link
+
+    doc: str = None
+    target_type: str = None
+    name: Optional[str] = None
+    quantity: Optional[str] = 1
+
+    def __post_init__(self, *_: List[str], **kwargs: Dict[str, Any]):
+        if self._is_empty(self.doc):
+            self.MissingRequiredField("doc")
+        if not isinstance(self.doc, str):
+            self.doc = str(self.doc)
+
+        if self._is_empty(self.target_type):
+            self.MissingRequiredField("target_type")
+        if not isinstance(self.target_type, str):
+            self.target_type = str(self.target_type)
+
+        if self.name is not None and not isinstance(self.name, str):
+            self.name = str(self.name)
+
+        if self.quantity is not None and not isinstance(self.quantity, str):
+            self.quantity = str(self.quantity)
+
+        super().__post_init__(**kwargs)
+
+
+@dataclass
+class Dataset(YAMLRoot):
+    _inherited_slots: ClassVar[List[str]] = []
+
+    class_class_uri: ClassVar[URIRef] = NWB_SCHEMA_LANGUAGE.Dataset
+    class_class_curie: ClassVar[str] = "nwb_schema_language:Dataset"
+    class_name: ClassVar[str] = "Dataset"
+    class_model_uri: ClassVar[URIRef] = NWB_SCHEMA_LANGUAGE.Dataset
+
+    doc: str = None
+    neurodata_type_def: Optional[str] = None
+    neurodata_type_inc: Optional[str] = None
+    name: Optional[str] = None
+    default_name: Optional[str] = None
+    dims: Optional[Union[str, List[str]]] = empty_list()
+    shape: Optional[Union[str, List[str]]] = empty_list()
+    value: Optional[Union[dict, "AnyType"]] = None
+    default_value: Optional[Union[dict, "AnyType"]] = None
+    quantity: Optional[str] = 1
+    linkable: Optional[Union[bool, Bool]] = None
+    attributes: Optional[Union[Union[dict, Attribute], List[Union[dict, Attribute]]]] = empty_list()
+    dtype: Optional[str] = None
+
+    def __post_init__(self, *_: List[str], **kwargs: Dict[str, Any]):
+        if self._is_empty(self.doc):
+            self.MissingRequiredField("doc")
+        if not isinstance(self.doc, str):
+            self.doc = str(self.doc)
+
+        if self.neurodata_type_def is not None and not isinstance(self.neurodata_type_def, str):
+            self.neurodata_type_def = str(self.neurodata_type_def)
+
+        if self.neurodata_type_inc is not None and not isinstance(self.neurodata_type_inc, str):
+            self.neurodata_type_inc = str(self.neurodata_type_inc)
+
+        if self.name is not None and not isinstance(self.name, str):
+            self.name = str(self.name)
+
+        if self.default_name is not None and not isinstance(self.default_name, str):
+            self.default_name = str(self.default_name)
+
+        if not isinstance(self.dims, list):
+            self.dims = [self.dims] if self.dims is not None else []
+        self.dims = [v if isinstance(v, str) else str(v) for v in self.dims]
+
+        if not isinstance(self.shape, list):
+            self.shape = [self.shape] if self.shape is not None else []
+        self.shape = [v if isinstance(v, str) else str(v) for v in self.shape]
+
+        if self.quantity is not None and not isinstance(self.quantity, str):
+            self.quantity = str(self.quantity)
+
+        if self.linkable is not None and not isinstance(self.linkable, Bool):
+            self.linkable = Bool(self.linkable)
+
+        self._normalize_inlined_as_dict(slot_name="attributes", slot_type=Attribute, key_name="name", keyed=False)
+
+        if self.dtype is not None and not isinstance(self.dtype, str):
+            self.dtype = str(self.dtype)
+
+        super().__post_init__(**kwargs)
+
+
+@dataclass
+class ReferenceDtype(YAMLRoot):
+    _inherited_slots: ClassVar[List[str]] = []
+
+    class_class_uri: ClassVar[URIRef] = NWB_SCHEMA_LANGUAGE.ReferenceDtype
+    class_class_curie: ClassVar[str] = "nwb_schema_language:ReferenceDtype"
+    class_name: ClassVar[str] = "ReferenceDtype"
+    class_model_uri: ClassVar[URIRef] = NWB_SCHEMA_LANGUAGE.ReferenceDtype
+
+    target_type: str = None
+    reftype: Optional[Union[str, "ReftypeOptions"]] = None
+
+    def __post_init__(self, *_: List[str], **kwargs: Dict[str, Any]):
+        if self._is_empty(self.target_type):
+            self.MissingRequiredField("target_type")
+        if not isinstance(self.target_type, str):
+            self.target_type = str(self.target_type)
+
+        if self.reftype is not None and not isinstance(self.reftype, ReftypeOptions):
+            self.reftype = ReftypeOptions(self.reftype)
+
+        super().__post_init__(**kwargs)
+
+
+@dataclass
+class CompoundDtype(YAMLRoot):
+    _inherited_slots: ClassVar[List[str]] = []
+
+    class_class_uri: ClassVar[URIRef] = NWB_SCHEMA_LANGUAGE.CompoundDtype
+    class_class_curie: ClassVar[str] = "nwb_schema_language:CompoundDtype"
+    class_name: ClassVar[str] = "CompoundDtype"
+    class_model_uri: ClassVar[URIRef] = NWB_SCHEMA_LANGUAGE.CompoundDtype
+
+    name: str = None
+    doc: str = None
+    dtype: Union[str, "FlatDtype"] = None
+
+    def __post_init__(self, *_: List[str], **kwargs: Dict[str, Any]):
+        if self._is_empty(self.name):
+            self.MissingRequiredField("name")
+        if not isinstance(self.name, str):
+            self.name = str(self.name)
+
+        if self._is_empty(self.doc):
+            self.MissingRequiredField("doc")
+        if not isinstance(self.doc, str):
+            self.doc = str(self.doc)
+
+        if self._is_empty(self.dtype):
+            self.MissingRequiredField("dtype")
+        if not isinstance(self.dtype, FlatDtype):
+            self.dtype = FlatDtype(self.dtype)
+
+        super().__post_init__(**kwargs)
+
+
+@dataclass
+class DtypeMixin(YAMLRoot):
+    _inherited_slots: ClassVar[List[str]] = []
+
+    class_class_uri: ClassVar[URIRef] = NWB_SCHEMA_LANGUAGE.DtypeMixin
+    class_class_curie: ClassVar[str] = "nwb_schema_language:DtypeMixin"
+    class_name: ClassVar[str] = "DtypeMixin"
+    class_model_uri: ClassVar[URIRef] = NWB_SCHEMA_LANGUAGE.DtypeMixin
+
+    dtype: Optional[str] = None
+
+    def __post_init__(self, *_: List[str], **kwargs: Dict[str, Any]):
+        if self.dtype is not None and not isinstance(self.dtype, str):
+            self.dtype = str(self.dtype)
+
+        super().__post_init__(**kwargs)
+
+
+class NamingMixin(YAMLRoot):
+    """
+    require either neurodata_type_def or name to be present
+    """
+    _inherited_slots: ClassVar[List[str]] = []
+
+    class_class_uri: ClassVar[URIRef] = NWB_SCHEMA_LANGUAGE.NamingMixin
+    class_class_curie: ClassVar[str] = "nwb_schema_language:NamingMixin"
+    class_name: ClassVar[str] = "NamingMixin"
+    class_model_uri: ClassVar[URIRef] = NWB_SCHEMA_LANGUAGE.NamingMixin
+
+
+AnyType = Any
+
+# Enumerations
+class ReftypeOptions(EnumDefinitionImpl):
+
+    ref = PermissibleValue(
+        text="ref",
+        description="Reference to another group or dataset of the given target_type")
+    reference = PermissibleValue(
+        text="reference",
+        description="Reference to another group or dataset of the given target_type")
+    object = PermissibleValue(
+        text="object",
+        description="Reference to another group or dataset of the given target_type")
+    region = PermissibleValue(
+        text="region",
+        description="Reference to a region (i.e. subset) of another dataset of the given target_type")
 
     _defn = EnumDefinition(
-        name="PersonStatus",
+        name="ReftypeOptions",
     )
 
+class QuantityEnum(EnumDefinitionImpl):
+
+    zero_or_many = PermissibleValue(
+        text="zero_or_many",
+        description="Zero or more instances, equivalent to *")
+    one_or_many = PermissibleValue(
+        text="one_or_many",
+        description="One or more instances, equivalent to +")
+    zero_or_one = PermissibleValue(
+        text="zero_or_one",
+        description="Zero or one instances, equivalent to ?")
+
+    _defn = EnumDefinition(
+        name="QuantityEnum",
+    )
+
+    @classmethod
+    def _addvals(cls):
+        setattr(cls, "*",
+            PermissibleValue(
+                text="*",
+                description="Zero or more instances, equivalent to zero_or_many"))
+        setattr(cls, "?",
+            PermissibleValue(
+                text="?",
+                description="Zero or one instances, equivalent to zero_or_one"))
+        setattr(cls, "+",
+            PermissibleValue(
+                text="+",
+                description="One or more instances, equivalent to one_or_many"))
+
+class FlatDtype(EnumDefinitionImpl):
+
+    float = PermissibleValue(
+        text="float",
+        description="single precision floating point (32 bit)")
+    float32 = PermissibleValue(
+        text="float32",
+        description="single precision floating point (32 bit)")
+    double = PermissibleValue(
+        text="double",
+        description="double precision floating point (64 bit)")
+    float64 = PermissibleValue(
+        text="float64",
+        description="double precision floating point (64 bit)")
+    long = PermissibleValue(
+        text="long",
+        description="signed 64 bit integer")
+    int64 = PermissibleValue(
+        text="int64",
+        description="signed 64 bit integer")
+    int = PermissibleValue(
+        text="int",
+        description="signed 32 bit integer")
+    int32 = PermissibleValue(
+        text="int32",
+        description="signed 32 bit integer")
+    int16 = PermissibleValue(
+        text="int16",
+        description="signed 16 bit integer")
+    short = PermissibleValue(
+        text="short",
+        description="signed 16 bit integer")
+    int8 = PermissibleValue(
+        text="int8",
+        description="signed 8 bit integer")
+    uint = PermissibleValue(
+        text="uint",
+        description="unsigned 32 bit integer")
+    uint32 = PermissibleValue(
+        text="uint32",
+        description="unsigned 32 bit integer")
+    uint16 = PermissibleValue(
+        text="uint16",
+        description="unsigned 16 bit integer")
+    uint8 = PermissibleValue(
+        text="uint8",
+        description="unsigned 8 bit integer")
+    uint64 = PermissibleValue(
+        text="uint64",
+        description="unsigned 64 bit integer")
+    numeric = PermissibleValue(
+        text="numeric",
+        description="any numeric type (i.e., any int, uint, float)")
+    text = PermissibleValue(
+        text="text",
+        description="8-bit Unicode")
+    utf = PermissibleValue(
+        text="utf",
+        description="8-bit Unicode")
+    utf8 = PermissibleValue(
+        text="utf8",
+        description="8-bit Unicode")
+    ascii = PermissibleValue(
+        text="ascii",
+        description="ASCII text")
+    bool = PermissibleValue(
+        text="bool",
+        description="8 bit integer with valid values 0 or 1")
+    isodatetime = PermissibleValue(
+        text="isodatetime",
+        description="ISO 8601 datetime string")
+
+    _defn = EnumDefinition(
+        name="FlatDtype",
+    )
+
+    @classmethod
+    def _addvals(cls):
+        setattr(cls, "utf-8",
+            PermissibleValue(
+                text="utf-8",
+                description="8-bit Unicode"))
+
 # Slots
 class slots:
     pass
 
-slots.id = Slot(uri=SCHEMA.identifier, name="id", curie=SCHEMA.curie('identifier'),
+slots.doc = Slot(uri=NWB_SCHEMA_LANGUAGE.doc, name="doc", curie=NWB_SCHEMA_LANGUAGE.curie('doc'),
-                   model_uri=NWB_SCHEMA_LANGUAGE.id, domain=None, range=URIRef)
+                   model_uri=NWB_SCHEMA_LANGUAGE.doc, domain=None, range=str)
 
-slots.name = Slot(uri=SCHEMA.name, name="name", curie=SCHEMA.curie('name'),
+slots.name = Slot(uri=NWB_SCHEMA_LANGUAGE.name, name="name", curie=NWB_SCHEMA_LANGUAGE.curie('name'),
                    model_uri=NWB_SCHEMA_LANGUAGE.name, domain=None, range=Optional[str])
 
-slots.description = Slot(uri=SCHEMA.description, name="description", curie=SCHEMA.curie('description'),
+slots.full_name = Slot(uri=NWB_SCHEMA_LANGUAGE.full_name, name="full_name", curie=NWB_SCHEMA_LANGUAGE.curie('full_name'),
-                   model_uri=NWB_SCHEMA_LANGUAGE.description, domain=None, range=Optional[str])
+                   model_uri=NWB_SCHEMA_LANGUAGE.full_name, domain=None, range=Optional[str])
 
-slots.primary_email = Slot(uri=SCHEMA.email, name="primary_email", curie=SCHEMA.curie('email'),
+slots.version = Slot(uri=NWB_SCHEMA_LANGUAGE.version, name="version", curie=NWB_SCHEMA_LANGUAGE.curie('version'),
-                   model_uri=NWB_SCHEMA_LANGUAGE.primary_email, domain=None, range=Optional[str])
+                   model_uri=NWB_SCHEMA_LANGUAGE.version, domain=None, range=str,
+                   pattern=re.compile(r'^(0|[1-9]\d*)\.(0|[1-9]\d*)\.(0|[1-9]\d*)(?:-((?:0|[1-9]\d*|\d*[a-zA-Z-][0-9a-zA-Z-]*)(?:\.(?:0|[1-9]\d*|\d*[a-zA-Z-][0-9a-zA-Z-]*))*))?(?:\+([0-9a-zA-Z-]+(?:\.[0-9a-zA-Z-]+)*))?$'))
 
-slots.birth_date = Slot(uri=SCHEMA.birthDate, name="birth_date", curie=SCHEMA.curie('birthDate'),
+slots.date = Slot(uri=SCHEMA.dateModified, name="date", curie=SCHEMA.curie('dateModified'),
-                   model_uri=NWB_SCHEMA_LANGUAGE.birth_date, domain=None, range=Optional[Union[str, XSDDate]])
+                   model_uri=NWB_SCHEMA_LANGUAGE.date, domain=None, range=Optional[Union[str, XSDDate]])
 
-slots.age_in_years = Slot(uri=NWB_SCHEMA_LANGUAGE.age_in_years, name="age_in_years", curie=NWB_SCHEMA_LANGUAGE.curie('age_in_years'),
+slots.author = Slot(uri=SCHEMA.author, name="author", curie=SCHEMA.curie('author'),
-                   model_uri=NWB_SCHEMA_LANGUAGE.age_in_years, domain=None, range=Optional[int])
+                   model_uri=NWB_SCHEMA_LANGUAGE.author, domain=None, range=Union[str, List[str]])
 
-slots.vital_status = Slot(uri=NWB_SCHEMA_LANGUAGE.vital_status, name="vital_status", curie=NWB_SCHEMA_LANGUAGE.curie('vital_status'),
+slots.contact = Slot(uri=SCHEMA.email, name="contact", curie=SCHEMA.curie('email'),
-                   model_uri=NWB_SCHEMA_LANGUAGE.vital_status, domain=None, range=Optional[Union[str, "PersonStatus"]])
+                   model_uri=NWB_SCHEMA_LANGUAGE.contact, domain=None, range=Union[str, List[str]])
 
-slots.namespacesCollection__entries = Slot(uri=NWB_SCHEMA_LANGUAGE.entries, name="namespacesCollection__entries", curie=NWB_SCHEMA_LANGUAGE.curie('entries'),
+slots.schema = Slot(uri=NWB_SCHEMA_LANGUAGE.schema, name="schema", curie=NWB_SCHEMA_LANGUAGE.curie('schema'),
-                   model_uri=NWB_SCHEMA_LANGUAGE.namespacesCollection__entries, domain=None, range=Optional[Union[Dict[Union[str, NamespacesId], Union[dict, Namespaces]], List[Union[dict, Namespaces]]]])
+                   model_uri=NWB_SCHEMA_LANGUAGE.schema, domain=None, range=Optional[Union[Union[dict, Schema], List[Union[dict, Schema]]]])
 
-slots.Namespaces_primary_email = Slot(uri=SCHEMA.email, name="Namespaces_primary_email", curie=SCHEMA.curie('email'),
+slots.source = Slot(uri=NWB_SCHEMA_LANGUAGE.source, name="source", curie=NWB_SCHEMA_LANGUAGE.curie('source'),
-                   model_uri=NWB_SCHEMA_LANGUAGE.Namespaces_primary_email, domain=Namespaces, range=Optional[str],
+                   model_uri=NWB_SCHEMA_LANGUAGE.source, domain=None, range=Optional[str],
-                   pattern=re.compile(r'^\S+@[\S+\.]+\S+'))
+                   pattern=re.compile(r'.*\.(yml|yaml|json)'))
+
+slots.namespace = Slot(uri=NWB_SCHEMA_LANGUAGE.namespace, name="namespace", curie=NWB_SCHEMA_LANGUAGE.curie('namespace'),
+                   model_uri=NWB_SCHEMA_LANGUAGE.namespace, domain=None, range=Optional[str])
+
+slots.namespaces = Slot(uri=NWB_SCHEMA_LANGUAGE.namespaces, name="namespaces", curie=NWB_SCHEMA_LANGUAGE.curie('namespaces'),
+                   model_uri=NWB_SCHEMA_LANGUAGE.namespaces, domain=None, range=Optional[Union[Union[dict, Namespace], List[Union[dict, Namespace]]]])
+
+slots.neurodata_types = Slot(uri=NWB_SCHEMA_LANGUAGE.neurodata_types, name="neurodata_types", curie=NWB_SCHEMA_LANGUAGE.curie('neurodata_types'),
+                   model_uri=NWB_SCHEMA_LANGUAGE.neurodata_types, domain=None, range=Optional[Union[str, List[str]]])
+
+slots.title = Slot(uri=NWB_SCHEMA_LANGUAGE.title, name="title", curie=NWB_SCHEMA_LANGUAGE.curie('title'),
+                   model_uri=NWB_SCHEMA_LANGUAGE.title, domain=None, range=Optional[str])
+
+slots.neurodata_type_def = Slot(uri=NWB_SCHEMA_LANGUAGE.neurodata_type_def, name="neurodata_type_def", curie=NWB_SCHEMA_LANGUAGE.curie('neurodata_type_def'),
+                   model_uri=NWB_SCHEMA_LANGUAGE.neurodata_type_def, domain=None, range=Optional[str])
+
+slots.neurodata_type_inc = Slot(uri=NWB_SCHEMA_LANGUAGE.neurodata_type_inc, name="neurodata_type_inc", curie=NWB_SCHEMA_LANGUAGE.curie('neurodata_type_inc'),
+                   model_uri=NWB_SCHEMA_LANGUAGE.neurodata_type_inc, domain=None, range=Optional[str])
+
+slots.default_name = Slot(uri=NWB_SCHEMA_LANGUAGE.default_name, name="default_name", curie=NWB_SCHEMA_LANGUAGE.curie('default_name'),
+                   model_uri=NWB_SCHEMA_LANGUAGE.default_name, domain=None, range=Optional[str])
+
+slots.quantity = Slot(uri=NWB_SCHEMA_LANGUAGE.quantity, name="quantity", curie=NWB_SCHEMA_LANGUAGE.curie('quantity'),
+                   model_uri=NWB_SCHEMA_LANGUAGE.quantity, domain=None, range=Optional[str])
+
+slots.linkable = Slot(uri=NWB_SCHEMA_LANGUAGE.linkable, name="linkable", curie=NWB_SCHEMA_LANGUAGE.curie('linkable'),
+                   model_uri=NWB_SCHEMA_LANGUAGE.linkable, domain=None, range=Optional[Union[bool, Bool]])
+
+slots.attributes = Slot(uri=NWB_SCHEMA_LANGUAGE.attributes, name="attributes", curie=NWB_SCHEMA_LANGUAGE.curie('attributes'),
+                   model_uri=NWB_SCHEMA_LANGUAGE.attributes, domain=None, range=Optional[Union[Union[dict, Attribute], List[Union[dict, Attribute]]]])
+
+slots.datasets = Slot(uri=NWB_SCHEMA_LANGUAGE.datasets, name="datasets", curie=NWB_SCHEMA_LANGUAGE.curie('datasets'),
+                   model_uri=NWB_SCHEMA_LANGUAGE.datasets, domain=None, range=Optional[Union[Union[dict, Dataset], List[Union[dict, Dataset]]]])
+
+slots.groups = Slot(uri=NWB_SCHEMA_LANGUAGE.groups, name="groups", curie=NWB_SCHEMA_LANGUAGE.curie('groups'),
+                   model_uri=NWB_SCHEMA_LANGUAGE.groups, domain=None, range=Optional[Union[Union[dict, Group], List[Union[dict, Group]]]])
+
+slots.links = Slot(uri=NWB_SCHEMA_LANGUAGE.links, name="links", curie=NWB_SCHEMA_LANGUAGE.curie('links'),
+                   model_uri=NWB_SCHEMA_LANGUAGE.links, domain=None, range=Optional[Union[Union[dict, Link], List[Union[dict, Link]]]])
+
+slots.dtype = Slot(uri=NWB_SCHEMA_LANGUAGE.dtype, name="dtype", curie=NWB_SCHEMA_LANGUAGE.curie('dtype'),
+                   model_uri=NWB_SCHEMA_LANGUAGE.dtype, domain=None, range=Optional[str])
+
+slots.dims = Slot(uri=NWB_SCHEMA_LANGUAGE.dims, name="dims", curie=NWB_SCHEMA_LANGUAGE.curie('dims'),
+                   model_uri=NWB_SCHEMA_LANGUAGE.dims, domain=None, range=Optional[Union[str, List[str]]])
+
+slots.shape = Slot(uri=NWB_SCHEMA_LANGUAGE.shape, name="shape", curie=NWB_SCHEMA_LANGUAGE.curie('shape'),
+                   model_uri=NWB_SCHEMA_LANGUAGE.shape, domain=None, range=Optional[Union[str, List[str]]])
+
+slots.value = Slot(uri=NWB_SCHEMA_LANGUAGE.value, name="value", curie=NWB_SCHEMA_LANGUAGE.curie('value'),
+                   model_uri=NWB_SCHEMA_LANGUAGE.value, domain=None, range=Optional[Union[dict, AnyType]])
+
+slots.default_value = Slot(uri=NWB_SCHEMA_LANGUAGE.default_value, name="default_value", curie=NWB_SCHEMA_LANGUAGE.curie('default_value'),
+                   model_uri=NWB_SCHEMA_LANGUAGE.default_value, domain=None, range=Optional[Union[dict, AnyType]])
+
+slots.required = Slot(uri=NWB_SCHEMA_LANGUAGE.required, name="required", curie=NWB_SCHEMA_LANGUAGE.curie('required'),
+                   model_uri=NWB_SCHEMA_LANGUAGE.required, domain=None, range=Optional[Union[bool, Bool]])
+
+slots.target_type = Slot(uri=NWB_SCHEMA_LANGUAGE.target_type, name="target_type", curie=NWB_SCHEMA_LANGUAGE.curie('target_type'),
+                   model_uri=NWB_SCHEMA_LANGUAGE.target_type, domain=None, range=str)
+
+slots.reftype = Slot(uri=NWB_SCHEMA_LANGUAGE.reftype, name="reftype", curie=NWB_SCHEMA_LANGUAGE.curie('reftype'),
+                   model_uri=NWB_SCHEMA_LANGUAGE.reftype, domain=None, range=Optional[Union[str, "ReftypeOptions"]])
+
+slots.Namespace_name = Slot(uri=NWB_SCHEMA_LANGUAGE.name, name="Namespace_name", curie=NWB_SCHEMA_LANGUAGE.curie('name'),
+                   model_uri=NWB_SCHEMA_LANGUAGE.Namespace_name, domain=Namespace, range=str)
+
+slots.Schema_doc = Slot(uri=NWB_SCHEMA_LANGUAGE.doc, name="Schema_doc", curie=NWB_SCHEMA_LANGUAGE.curie('doc'),
+                   model_uri=NWB_SCHEMA_LANGUAGE.Schema_doc, domain=Schema, range=str)
+
+slots.Attribute_name = Slot(uri=NWB_SCHEMA_LANGUAGE.name, name="Attribute_name", curie=NWB_SCHEMA_LANGUAGE.curie('name'),
+                   model_uri=NWB_SCHEMA_LANGUAGE.Attribute_name, domain=Attribute, range=str)
+
+slots.CompoundDtype_name = Slot(uri=NWB_SCHEMA_LANGUAGE.name, name="CompoundDtype_name", curie=NWB_SCHEMA_LANGUAGE.curie('name'),
+                   model_uri=NWB_SCHEMA_LANGUAGE.CompoundDtype_name, domain=CompoundDtype, range=str)
+
+slots.CompoundDtype_dtype = Slot(uri=NWB_SCHEMA_LANGUAGE.dtype, name="CompoundDtype_dtype", curie=NWB_SCHEMA_LANGUAGE.curie('dtype'),
+                   model_uri=NWB_SCHEMA_LANGUAGE.CompoundDtype_dtype, domain=CompoundDtype, range=Union[str, "FlatDtype"])

nwb-schema-linkml/src/nwb_schema_language/schema/nwb_schema_language.yaml

@@ -11,86 +11,373 @@ see_also:
 prefixes:
   nwb_schema_language: https://w3id.org/p2p_ld/nwb-schema-language/
   linkml: https://w3id.org/linkml/
-  biolink: https://w3id.org/biolink/
   schema: http://schema.org/
-  PATO: http://purl.obolibrary.org/obo/PATO_
+
-  example: https://example.org/
 default_prefix: nwb_schema_language
 default_range: string
 
 imports:
   - linkml:types
 
-classes:
+settings:
+  email: "\\S+@\\S+{\\.\\w}+"
+  protected_string: "^[A-Za-z_][A-Za-z0-9_]*$"
 
-  NamedThing:
+classes:
-    description: >-
+  Namespace:
-      A generic grouping for any identifiable entity
     slots:
-      - id
+      - doc
       - name
-      - description
+      - full_name
-    class_uri: schema:Thing
+      - version
+      - date
+      - author
+      - contact
+      - schema
+    slot_usage:
+      name:
+        required: true
 
   Namespaces:
-    is_a: NamedThing
-    description: >-
-      Represents a Namespaces
     slots:
-      - primary_email
+      - namespaces
-      - birth_date
+
-      - age_in_years
+  Schema:
-      - vital_status
+    slots:
+      - source
+      - namespace
+      - doc
+      - title
+      - neurodata_types
     slot_usage:
-      primary_email:
+      doc:
-        pattern: "^\\S+@[\\S+\\.]+\\S+"
+        required: false
+    rules:
+      - preconditions: {slot_conditions: { namespace: { value_presence: ABSENT }}}
+        postconditions: {slot_conditions: { source: {required: true }}}
+        description: If namespace is absent, source is required
+      - preconditions: {slot_conditions: { source: { value_presence: ABSENT }}}
+        postconditions: {slot_conditions: { namespace: {required: true }}}
+        description: If source is absent, namespace is required.
+      - preconditions: { slot_conditions: { namespace: { value_presence: PRESENT }}}
+        postconditions: { slot_conditions: { source: { value_presence: ABSENT }}}
+        description: If namespace is present, source is cannot be
+      - preconditions: { slot_conditions: { source: { value_presence: PRESENT }}}
+        postconditions: { slot_conditions: { namespace: { value_presence: ABSENT }}}
+        description: If source is present, namespace cannot be.
 
-  NamespacesCollection:
+  Group:
-    tree_root: true
+    mixins:
-    description: >-
+      - NamingMixin
-      A holder for Namespaces objects
+    slots:
-    attributes:
+      - neurodata_type_def
-      entries:
+      - neurodata_type_inc
-        range: Namespaces
+      - name
+      - default_name
+      - doc
+      - quantity
+      - linkable
+      - attributes
+      - datasets
+      - groups
+      - links
+
+  Attribute:
+    mixins:
+      - DtypeMixin
+    slots:
+      - name
+      - dims
+      - shape
+      - value
+      - default_value
+      - doc
+      - required
+    slot_usage:
+      name:
+        required: true
+
+  Link:
+    slots:
+      - name
+      - doc
+      - target_type
+      - quantity
+
+  Dataset:
+    mixins:
+      - DtypeMixin
+      - NamingMixin
+    slots:
+      - neurodata_type_def
+      - neurodata_type_inc
+      - name
+      - default_name
+      - dims
+      - shape
+      - value
+      - default_value
+      - doc
+      - quantity
+      - linkable
+      - attributes
+
+  ReferenceDtype:
+    slots:
+      - target_type
+      - reftype
+
+  CompoundDtype:
+    slots:
+      - name
+      - doc
+      - dtype
+    slot_usage:
+      name:
+        required: true
+      dtype:
+        required: true
+        range: FlatDtype
+
+  DtypeMixin:
+    mixin: true
+    slots:
+      - dtype
+    rules:
+      - preconditions:
+          slot_conditions:
+            dtype:
+              range: CompoundDtype
+        postconditions:
+          slot_conditions:
+            dtype:
               multivalued: true
-        inlined: true
+
+  NamingMixin:
+    mixin: true
+    description: require either neurodata_type_def or name to be present
+    rules:
+      - preconditions: { slot_conditions: { neurodata_type_def: { value_presence: ABSENT } } }
+        postconditions: { slot_conditions: { name: { required: true } } }
+        description: If not defining a new type, a name is required
+      - preconditions: { slot_conditions: { name: { value_presence: ABSENT } } }
+        postconditions: { slot_conditions: { neurodata_type_def: { required: true } } }
+        description: If a name is not given, must be defining a new type
+
+  AnyType:
+    class_uri: linkml:Any
+
 
 slots:
-  id:
+  # namespaces
-    identifier: true
+  doc:
-    slot_uri: schema:identifier
+    required: true
-    range: uriorcurie
+    description: Description of corresponding object.
-    description: A unique identifier for a thing
   name:
-    slot_uri: schema:name
+    structured_pattern:
-    description: A human-readable name for a thing
+      syntax: "{protected_string}"
-  description:
+      interpolated: true
-    slot_uri: schema:description
+  full_name:
-    description: A human-readable description for a thing
+    description: Optional string with extended full name for the namespace.
-  primary_email:
+  version:
-    slot_uri: schema:email
+    required: true
-    description: The main email address of a person
+    pattern: "^(0|[1-9]\\d*)\\.(0|[1-9]\\d*)\\.(0|[1-9]\\d*)(?:-((?:0|[1-9]\\d*|\\d*[a-zA-Z-][0-9a-zA-Z-]*)(?:\\.(?:0|[1-9]\\d*|\\d*[a-zA-Z-][0-9a-zA-Z-]*))*))?(?:\\+([0-9a-zA-Z-]+(?:\\.[0-9a-zA-Z-]+)*))?$"
-  birth_date:
+  date:
-    slot_uri: schema:birthDate
     range: date
-    description: Date on which a person is born
+    slot_uri: schema:dateModified
-  age_in_years:
+    description: Date that a namespace was last modified or released
-    range: integer
+    examples:
-    description: Number of years since birth
+      - value: 2017-04-25 17:14:13
-  vital_status:
+  author:
-    range: PersonStatus
+    multivalued: true
-    description: living or dead status
+    required: true
+    slot_uri: schema:author
+    description: List of strings with the names of the authors of the namespace.
+  contact:
+    multivalued: true
+    required: true
+    slot_uri: schema:email
+    structured_pattern:
+      syntax: "{email}"
+      interpolated: true
+    description: List of strings with the contact information for the authors. Ordering of the contacts should match the ordering of the authors.
+  schema:
+    multivalued: true
+    range: Schema
+    description: List of the schema to be included in this namespace.
+    inlined_as_list: true
+
+  # schema
+  source:
+    description: describes the name of the YAML (or JSON) file with the schema specification. The schema files should be located in the same folder as the namespace file.
+    pattern: ".*\\.(yml|yaml|json)"
+  namespace:
+    description: describes a named reference to another namespace. In contrast to source, this is a reference by name to a known namespace (i.e., the namespace is resolved during the build and must point to an already existing namespace). This mechanism is used to allow, e.g., extension of a core namespace (here the NWB core namespace) without requiring hard paths to the files describing the core namespace. Either source or namespace must be specified, but not both.
+  namespaces:
+    multivalued: true
+    range: Namespace
+  neurodata_types:
+    multivalued: true
+    any_of:
+      - range: Dataset
+      - range: Group
+    description: an optional list of strings indicating which data types should be included from the given specification source or namespace. The default is null indicating that all data types should be included.
+  title:
+    description: a descriptive title for a file for documentation purposes.
+
+  # groups
+  neurodata_type_def:
+    structured_pattern:
+      syntax: "{protected_string}"
+      interpolated: true
+  neurodata_type_inc:
+    structured_pattern:
+      syntax: "{protected_string}"
+      interpolated: true
+  default_name:
+    structured_pattern:
+      syntax: "{protected_string}"
+      interpolated: true
+  quantity:
+    any_of:
+      - range: integer
+        minimum_value: 1
+      - range: QuantityEnum
+    ifabsent: int(1)
+    todos:
+      - logic to check that the corresponding class can only be implemented quantity times.
+  linkable:
+    range: boolean
+
+  # Recursive properties
+  attributes:
+    range: Attribute
+    multivalued: true
+  datasets:
+    range: Dataset
+    multivalued: true
+  groups:
+    range: Group
+    multivalued: true
+  links:
+    range: Link
+    multivalued: true
+
+  # attributes
+  dtype:
+    exactly_one_of:
+      - range: FlatDtype
+      - range: CompoundDtype
+      - range: ReferenceDtype
+  dims:
+    multivalued: true
+    range: string
+    todos:
+      - Can't quite figure out how to allow an array of arrays
+  shape:
+    multivalued: true
+    exactly_one_of:
+      - range: integer
+        minimum_value: 1
+      - equals_string: "null"
+    todos:
+      - Can't quite figure out how to allow an array of arrays
+  value:
+    range: AnyType
+    description: Optional constant, fixed value for the attribute.
+  default_value:
+    range: AnyType
+    description: Optional default value for variable-valued attributes.
+  required:
+    range: boolean
+    description: Optional boolean key describing whether the attribute is required. Default value is True.
+    ifabsent: "true"
+
+  # links
+  target_type:
+    description: Describes the neurodata_type of the target that the reference points
+      to
+    required: true
+    any_of:
+      - range: Dataset
+      - range: Group
+  reftype:
+    description: describes the kind of reference
+    range: reftype_options
+
+
 
 enums:
-  PersonStatus:
+  reftype_options:
     permissible_values:
-      ALIVE:
+      ref: { description: Reference to another group or dataset of the given target_type }
-        description: the person is living
+      reference: { description: Reference to another group or dataset of the given target_type }
-        meaning: PATO:0001421
+      object: { description: Reference to another group or dataset of the given target_type }
-      DEAD:
+      region: { description: Reference to a region (i.e. subset) of another dataset of the given target_type}
-        description: the person is deceased
+  QuantityEnum:
-        meaning: PATO:0001422
+    permissible_values:
-      UNKNOWN:
+      "*":
-        description: the vital status is not known
+        description: Zero or more instances, equivalent to zero_or_many
-        todos:
+      "?":
-          - map this to an ontology
+        description: Zero or one instances, equivalent to zero_or_one
+      "+":
+        description: One or more instances, equivalent to one_or_many
+      "zero_or_many":
+        description: Zero or more instances, equivalent to *
+      "one_or_many":
+        description: One or more instances, equivalent to +
+      "zero_or_one":
+        description: Zero or one instances, equivalent to ?
+  FlatDtype:
+    permissible_values:
+      "float":
+        description: single precision floating point (32 bit)
+      "float32":
+        description: single precision floating point (32 bit)
+      "double":
+        description: double precision floating point (64 bit)
+      "float64":
+        description: double precision floating point (64 bit)
+      "long":
+        description: signed 64 bit integer
+      "int64":
+        description: signed 64 bit integer
+      "int":
+        description: signed 32 bit integer
+      "int32":
+        description: signed 32 bit integer
+      "int16":
+        description: signed 16 bit integer
+      "short":
+        description: signed 16 bit integer
+      "int8":
+        description: signed 8 bit integer
+      "uint":
+        description: unsigned 32 bit integer
+      "uint32":
+        description: unsigned 32 bit integer
+      "uint16":
+        description: unsigned 16 bit integer
+      "uint8":
+        description: unsigned 8 bit integer
+      "uint64":
+        description: unsigned 64 bit integer
+      "numeric":
+        description: any numeric type (i.e., any int, uint, float)
+      "text":
+        description: 8-bit Unicode
+      "utf":
+        description: 8-bit Unicode
+      "utf8":
+        description: 8-bit Unicode
+      "utf-8":
+        description: 8-bit Unicode
+      "ascii":
+        description: ASCII text
+      "bool":
+        description: 8 bit integer with valid values 0 or 1
+      "isodatetime":
+        description: ISO 8601 datetime string
+        examples:
+          - value: 2018-09-28T14:43:54.123+02:00
+

nwb-schema-linkml/tests/test_data.py

@@ -7,7 +7,7 @@ from linkml_runtime.loaders import yaml_loader
 from nwb_schema_language.datamodel.nwb_schema_language import Namespaces
 
 ROOT = os.path.join(os.path.dirname(__file__), '..')
-DATA_DIR = os.path.join(ROOT, "src", "data", "examples")
+DATA_DIR = os.path.join(ROOT, "src", "data", "tests")
 
 EXAMPLE_FILES = glob.glob(os.path.join(DATA_DIR, '*.yaml'))
 
@@ -15,8 +15,8 @@ EXAMPLE_FILES = glob.glob(os.path.join(DATA_DIR, '*.yaml'))
 class TestData(unittest.TestCase):
     """Test data and datamodel."""
 
-    def test_data(self):
+    def test_namespaces(self):
         """Date test."""
-        for path in EXAMPLE_FILES:
+        namespace_file = [f for f in EXAMPLE_FILES if 'namespace.yaml' in f][0]
-            obj = yaml_loader.load(path, target_class=Namespaces)
+        obj = yaml_loader.load(namespace_file, target_class=Namespaces)
         assert obj