Merge pull request #10 from Materials-Consortia/component-stdinchi

Introduce standard InChIs for connected components

Author: merkys

src/v0.1.0/entrytypes/structures.yaml

@@ -9,6 +9,20 @@ x-optimade-definition:
   name: "structures"
   label: "structures_entrytype_cheminformatics"
 properties:
+  _cheminfo_components_stdinchi:
+    $$inherit: "/properties/structures/_cheminfo_components_stdinchi"
+    x-optimade-implementation:
+      support: "may"
+      sortable: false
+      query-support: "none"
+      response-level: "yes"
+  _cheminfo_components_stdinchi_counts:
+    $$inherit: "/properties/structures/_cheminfo_components_stdinchi_counts"
+    x-optimade-implementation:
+      support: "may"
+      sortable: false
+      query-support: "none"
+      response-level: "yes"
   _cheminfo_preferred_iupac_name:
     $$inherit: "/properties/structures/_cheminfo_preferred_iupac_name"
     x-optimade-implementation:

src/v0.1.0/properties/structures/_cheminfo_components_stdinchi.yaml

@@ -0,0 +1,54 @@
+$$schema: "https://schemas.optimade.org/meta/v1.2/optimade/property_definition"
+$id: "https://schemas.optimade.org/namespaces/cheminformatics/v0.1/properties/structures/_cheminfo_components_stdinchi"
+title: "The standard InChI identifiers for molecular entities of the structure"
+x-optimade-type: "list"
+x-optimade-definition:
+  kind: "property"
+  version: "0.1.0"
+  format: "1.2"
+  name: "_cheminfo_components_stdinchi"
+  label: "_cheminfo_components_stdinchi_structures"
+type:
+  - "array"
+  - "null"
+x-optimade-dimensions:
+  names: ["dim__cheminfo_components"]
+description: |-
+  The standard InChI identifiers for the molecular entities of the structure.
+  The InChI identifier is defined by the InChI Trust (https://www.inchi-trust.org).
+  Values MUST start with `InChI=` and MUST be unique.
+  Molecular entities MUST NOT overlap, i.e., any atom of a structure MUST NOT appear in more than one entity.
+  There MAY be atoms participating in none of the molecular entities: providers are allowed to exclude certain entities if they wish.
+
+  **Explained examples**:
+
+  - `["InChI=1S/ClH/h1H/p-1", "InChI=1S/Na/q+1"]`: NaCl (salt) broken into constituent ions.
+  - `["InChI=1S/C7H6O3/c8-6-4-2-1-3-5(6)7(9)10/h1-4,8H,(H,9,10)", "InChI=1S/C8H10N4O2/c1-10-4-9-6-5(10)7(13)12(3)8(14)11(6)2/h4H,1-3H3"]`: a co-crystal of two organic compounds.
+examples:
+  - ["InChI=1S/ClH/h1H/p-1", "InChI=1S/Na/q+1"]
+  - ["InChI=1S/C7H6O3/c8-6-4-2-1-3-5(6)7(9)10/h1-4,8H,(H,9,10)", "InChI=1S/C8H10N4O2/c1-10-4-9-6-5(10)7(13)12(3)8(14)11(6)2/h4H,1-3H3"]
+x-optimade-metadata-definition:
+  title: "Metadata for the _cheminfo_components_stdinchi field"
+  description: "This dictionary contains the per-entry metadata for the _cheminfo_components_stdinchi field."
+  x-optimade-type: "dictionary"
+  type:
+    - "object"
+    - "null"
+  properties:
+    _cheminfo_library_version:
+      description: |-
+        The version of the InChI software library (https://github.com/IUPAC-InChI/InChI) used to generate the standard InChI values.
+        MUST NOT start with 'v'.
+      x-optimade-type: "string"
+      type:
+        - "string"
+      examples:
+        - "1.07.4"
+      x-optimade-unit: "inapplicable"
+  x-optimade-unit: "inapplicable"
+x-optimade-unit: "inapplicable"
+items:
+  type:
+    - "string"
+  x-optimade-type: "string"
+  x-optimade-unit: "inapplicable"

src/v0.1.0/properties/structures/_cheminfo_components_stdinchi_counts.yaml

@@ -0,0 +1,29 @@
+$$schema: "https://schemas.optimade.org/meta/v1.2/optimade/property_definition"
+$id: "https://schemas.optimade.org/namespaces/cheminformatics/v0.1/properties/structures/_cheminfo_components_stdinchi_counts"
+title: "The counts of molecular entities of the structure as expressed in '_cheminfo_components_stdinchi' property"
+x-optimade-type: "list"
+x-optimade-definition:
+  kind: "property"
+  version: "0.1.0"
+  format: "1.2"
+  name: "_cheminfo_components_stdinchi_counts"
+  label: "_cheminfo_components_stdinchi_counts_structures"
+type:
+  - "array"
+  - "null"
+x-optimade-dimensions:
+  names: ["dim__cheminfo_components"]
+description: |-
+  The occurrence count of the molecular entities in the structure as given in '_cheminfo_components_stdinchi' property.
+  It MUST be a list of length equal to the length of '_cheminfo_components_stdinchi'.
+examples:
+  - [1, 1]
+  - [2, 10]
+  - [1, 0.5]
+x-optimade-unit: "inapplicable"
+items:
+  type:
+    - "number"
+  x-optimade-type: "float"
+  x-optimade-unit: "dimensionless"
+  minimum: 0.0