updated chem_dcat_ap base schema and fixed #28

Author: HendrikBorgelt

docs/schema/coremeta4cat.yaml

@@ -0,0 +1,163 @@
+---
+id: https://w3id.org/nfdi-de/dcat-ap-plus/chemistry/
+version: "0.1.0rc2.post36.dev0+e9bd12a9" # Managed by dynamic-versioning. Don't change this line!
+name: chem-dcat-ap
+title: ChemDCAT-AP
+description: |-
+  This is an extension of the DCAT Application Profile PLUS LinkML schema. It is intended to be used by NFDI4Chem & NFDI4Cat as a core that can further be extended in profiles/schemas to provide chemistry specific specific metadata for a dataset.
+license: CC-BY 4.0
+see_also:
+  - https://nfdi-de.github.io/chem-dcat-ap/
+  - https://github.com/HendrikBorgelt/DCAT-ap_as_LinkML_template/blob/main/src/dcatlinkml/schema/dcatlinkml.yaml
+  - https://gitlab.com/opensourcelab/scientificdata/scidats/-/blob/feature/linkml-schemata/schemata/metadata_model_scidats_dcat_ap.yaml?ref_type=heads
+prefixes:
+  chemdcatap: https://w3id.org/nfdi-de/dcat-ap-plus/chemistry/
+  dcatapplus: https://w3id.org/nfdi-de/dcat-ap-plus/
+  linkml: https://w3id.org/linkml/
+  biolink: https://w3id.org/biolink/vocab/
+  schema: http://schema.org/
+  dcterms: http://purl.org/dc/terms/
+  dcat: http://www.w3.org/ns/dcat#
+  adms: http://www.w3.org/ns/adms#
+  prov: http://www.w3.org/ns/prov#
+  sosa: http://www.w3.org/ns/sosa/
+  vcard: http://www.w3.org/2006/vcard/ns#
+  rdf: http://www.w3.org/1999/02/22-rdf-syntax-ns#
+  rdfs: http://www.w3.org/2000/01/rdf-schema#
+  owl: http://www.w3.org/2002/07/owl#
+  skos: http://www.w3.org/2004/02/skos/core#
+  foaf: http://xmlns.com/foaf/0.1/
+  qudt: http://qudt.org/schema/qudt/
+  RO: http://purl.obolibrary.org/obo/RO_
+  PATO: http://purl.obolibrary.org/obo/PATO_
+  OBI: http://purl.obolibrary.org/obo/OBI_
+  IAO: http://purl.obolibrary.org/obo/IAO_
+  CHEBI: http://purl.obolibrary.org/obo/CHEBI_
+  CHMO: http://purl.obolibrary.org/obo/CHMO_
+  BFO: http://purl.obolibrary.org/obo/BFO_
+  T4FS: http://purl.obolibrary.org/obo/T4FS_
+  FOODON: http://purl.obolibrary.org/obo/FOODON_
+  CHEMINF: http://semanticscience.org/resource/CHEMINF_
+  RXNO: http://purl.obolibrary.org/obo/RXNO_
+  MOP: http://purl.obolibrary.org/obo/MOP_
+  ex: http://example.org/
+  NCIT: http://purl.obolibrary.org/obo/NCIT_
+  SIO: http://semanticscience.org/resource/SIO_
+  doi: https://doi.org/
+  NMR: "http://nmrML.org/nmrCV#NMR:"
+  AFE: http://purl.allotrope.org/ontologies/equipment#AFE_
+  AFRL: http://purl.allotrope.org/ontologies/role#AFRL_
+  AFP: http://purl.allotrope.org/ontologies/process#AFP_
+  AFR: http://purl.allotrope.org/ontologies/result#AFR_
+  VOC4CAT: https://w3id.org/nfdi4cat/voc4cat_
+  PROCO: http://purl.obolibrary.org/obo/PROCO_
+  time: http://www.w3.org/2006/time#
+  REX: http://purl.obolibrary.org/obo/REX_
+  ENVO: http://purl.obolibrary.org/obo/ENVO_
+default_prefix: chemdcatap
+default_range: string
+imports:
+  - linkml:types
+  - dcatapplus:latest/schema/dcat_ap_plus
+  - chemical_entities_ap
+  - chemical_reaction_ap
+
+classes:
+  ############
+  # Datasets #
+  ############
+  # The only difference between these classes and their DCAT-AP+ parents are the made range restrictions
+  # This process is described in more depth at:
+  # https://nfdi-de.github.io/dcat-ap-plus/latest/design-patterns/#problems-dcat-ap-addresses
+
+  SubstanceSampleCharacterizationDataset:
+    is_a: Dataset
+    class_uri: dcat:Dataset
+    description: >-
+      A Dataset about a SubstanceSample that was produced by a SubstanceSampleCharacterization activity.
+      This is a coarse-grained convenience shape that conflates measurement and analysis into a single
+      data-generating activity. Domain-specific sub-profiles that need to distinguish raw measurement
+      from post-processing or structure assignment should define their own Dataset subclasses, potentially
+      using the DCAT-AP+ DataAnalysis/AnalysisDataset chain instead of reusing this class.
+    slot_usage:
+      was_generated_by:
+        range: SubstanceSampleCharacterization
+        multivalued: true
+        inlined_as_list: true
+        description: The slot to specify the SubstanceCharacterization activity that produced this dataset.
+      is_about_entity:
+        range: SubstanceSample
+        multivalued: true
+        inlined_as_list: true
+        description: The slot to specify the SubstanceSample this dataset is about.
+
+  ReactionMonitoringDataset:
+    is_a: Dataset
+    class_uri: dcat:Dataset
+    description: >-
+      A Dataset about a ChemicalReaction that was produced by a ReactionMonitoring activity.
+      This is a coarse-grained convenience shape that conflates experimental documentation and analysis
+      into a single data-generating activity. Domain-specific sub-profiles that need to distinguish
+      reaction monitoring from subsequent data evaluation should define their own Dataset subclasses,
+      potentially using the DCAT-AP+ DataAnalysis/AnalysisDataset chain instead of reusing this class.
+    slot_usage:
+      was_generated_by:
+        range: ReactionMonitoring
+        multivalued: true
+        inlined_as_list: true
+        description: The slot to specify the ReactionMonitoring activity that produced this dataset.
+      is_about_activity:
+        range: ChemicalReaction
+        description: The slot to specify the ChemicalReaction this dataset is about.
+
+  ############################
+  # DataGeneratingActivities #
+  # ##########################
+  # The only difference between these classes and their DCAT-AP+ parents are the made range restrictions
+  # This process is described in more depth at:
+  # https://nfdi-de.github.io/dcat-ap-plus/latest/design-patterns/#problems-dcat-ap-addresses
+
+  SubstanceSampleCharacterization:
+    is_a: DataGeneratingActivity
+    class_uri: prov:Activity
+    broad_mappings:
+      - OBI:0000070
+    description: >-
+      A DataGeneratingActivity that produces data about a SubstanceSample, such as a spectroscopic
+      measurement, a physical property determination, or a combined measurement-and-analysis workflow.
+      This is a coarse-grained convenience shape that does not distinguish between raw data acquisition
+      and subsequent data processing or analysis. Domain-specific sub-profiles that need this distinction
+      should define their own DataGeneratingActivity subclasses and use the DCAT-AP+ DataAnalysis chain
+      to separate raw measurement from derived results.
+    slot_usage:
+      evaluated_entity:
+        range: SubstanceSample
+        multivalued: true
+        inlined_as_list: true
+        description: The slot to specify the SubstanceSample being characterized.
+
+  ReactionMonitoring:
+    is_a: DataGeneratingActivity
+    class_uri: prov:Activity
+    description: >-
+      A DataGeneratingActivity that produces data about a ChemicalReaction, such as reaction monitoring,
+      experimental documentation, or a combined recording-and-evaluation workflow. This is a coarse-grained
+      convenience shape that does not distinguish between raw experimental recording and subsequent data
+      evaluation. Domain-specific sub-profiles that need this distinction should define their own
+      DataGeneratingActivity subclasses and use the DCAT-AP+ DataAnalysis chain to separate raw data
+      from derived results.
+    slot_usage:
+      evaluated_activity:
+        range: ChemicalReaction
+        multivalued: true
+        inlined_as_list: true
+        description: The slot to specify the ChemicalReaction being recorded.
+
+  ################
+  # Surroundings #
+  ################
+
+  Laboratory:
+    is_a: Surrounding
+    class_uri: ENVO:01001405
+    description: A facility that provides controlled conditions in which scientific or technological research, experiments, and measurement may be performed.

src/coremeta4cat/datamodel/coremeta4cat.py

@@ -1,13 +1,13 @@
 ---
-id: https://nfdi-de.github.io/chem-dcat-ap/chemical_entities_ap.yaml
+id: https://w3id.org/nfdi-de/dcat-ap-plus/chemistry/entity/
 name: chemical-entities-ap
 title: Chemical Entities Application Profile
 description: |-
   This is an application profile for chemical entities to be used for extending the DCAT-AP-PLUS.
 license: CC-BY 4.0
 prefixes:
-  chemical_entities_ap: https://nfdi-de.github.io/chem-dcat-ap/chemical_entities_ap.yaml#
-  chemdcatap: https://nfdi-de.github.io/chem-dcat-ap/
+  chemical_entities_ap: https://w3id.org/nfdi-de/dcat-ap-plus/chemistry/entity/
+  chemdcatap: https://w3id.org/nfdi-de/dcat-ap-plus/chemistry/
   linkml: https://w3id.org/linkml/
   biolink: https://w3id.org/biolink/vocab/
   schema: http://schema.org/
@@ -41,9 +41,35 @@ imports:
 
 classes:
 
+#####################
+# EvaluatedEntities #
+#####################
+  SubstanceSample:
+    class_uri: SIO:001378
+    is_a: MaterialSample
+    aliases:
+      - analyte
+    description: A MaterialSample derived from a chemical substance that is of interest in an analytical procedure.
+    mixins:
+      - ChemicalSubstanceMixin
+
+  PolymerSample:
+    is_a: SubstanceSample
+    class_uri: SIO:001378
+    description: A SubstanceSample derived from a Polymer.
+    mixins:
+      - PolymerMixin
+    todos:
+      - "Find a better mapping, as it is currently mapped to same ontology class as its parent."
+
+############
+# Entities #
+############
   ChemicalEntity:
-    is_a: MaterialEntity
+    is_a: Entity
     class_uri: CHEBI:23367
+    aliases:
+      - molecular entity
     description: Any constitutionally or isotopically distinct atom, molecule, ion, ion pair, radical, radical ion, complex, conformer etc., identifiable as a separately distinguishable entity.
     slots:
       - inchi
@@ -52,60 +78,31 @@ classes:
       - molecular_formula
       - iupac_name
       - has_molar_mass
+    slot_usage:
+      has_part:
+        slot_uri: BFO:0000051
+        description: The slot to provide the parts of a ChemicalEntity that are themself chemical entities.
+        range: ChemicalEntity
+        multivalued: true
+        inlined_as_list: true
   Atom:
     class_uri: CHEBI:33250
-    is_a: ChemicalEntity
-    description: A MaterialEntity constituting the smallest component of an element having the chemical properties of the element.
+    is_a: Entity
+    description: An Entity constituting the smallest component of a chemical element having the chemical properties of the element.
     slot_usage:
       rdf_type:
         description: The slot to provide the Atom as a ChEBI ID from the atom (CHEBI:33250) branch.
         required: true
 
+#########################
+# QuantitativeAttributes #
+#########################
   MolarMass:
     class_uri: AFR:0002409
     is_a: Mass
     description: A Mass (physical quality) that quantifies the mass of a homogeneous ChemicalSubstance containing 6.02 x 10^23 atoms or molecules.
     close_mappings:
       - PATO:0001681
-  InChIKey:
-    class_uri: CHEMINF:000059
-    is_a: QualitativeAttribute
-  InChi:
-    class_uri: CHEMINF:000113
-    is_a: QualitativeAttribute
-    description: A structure descriptor which conforms to the InChI format specification.
-  MolecularFormula:
-    class_uri: CHEMINF:000042
-    is_a: QualitativeAttribute
-    description: A structure descriptor which identifies each constituent element by its chemical symbol and indicates the number of atoms of each element found in each discrete molecule of that compound.
-  IUPACName:
-    class_uri: CHEMINF:000107
-    is_a: QualitativeAttribute
-    description: A systematic name which is formulated according to the rules and recommendations for chemical nomenclature set out by the International Union of Pure and Applied Chemistry (IUPAC).
-  SMILES:
-    class_uri: CHEMINF:000018
-    is_a: QualitativeAttribute
-    description: A structure descriptor that denotes a molecular structure as a graph and conforms to the SMILES format specification.
-
-  ChemicalSubstance:
-    class_uri: CHEBI:59999
-    is_a: MaterialEntity
-    mixin: true
-    description: A MaterialEntity of constant composition, composed of chemical entities of the same type or of different types.
-    slots:
-      - has_concentration
-      - has_ph_value
-      - composed_of
-      - has_molar_equivalent
-      - has_amount
-      - has_percentage_of_total
-  Polymer:
-    class_uri: CHEBI:60027
-    is_a: ChemicalSubstance
-    mixin: true
-    description: A ChemicalSubstance that is composed of macromolecules of different kinds and which may be differentiated by composition, length, degree of branching etc..
-    # attributes: # Needed attributes will be defined here
-
   Concentration:
     is_a: QuantitativeAttribute
     class_uri: CHMO:0002820
@@ -147,6 +144,50 @@ classes:
       #has_quantity_type:
       #ifabsent: http://qudt.org/vocab/quantitykind/Acidity
 
+########################
+# QualitativeAttribute #
+########################
+  InChIKey:
+    class_uri: CHEMINF:000059
+    is_a: QualitativeAttribute
+  InChi:
+    class_uri: CHEMINF:000113
+    is_a: QualitativeAttribute
+    description: A structure descriptor which conforms to the InChI format specification.
+  MolecularFormula:
+    class_uri: CHEMINF:000042
+    is_a: QualitativeAttribute
+    description: A structure descriptor which identifies each constituent element by its chemical symbol and indicates the number of atoms of each element found in each discrete molecule of that compound.
+  IUPACName:
+    class_uri: CHEMINF:000107
+    is_a: QualitativeAttribute
+    description: A systematic name which is formulated according to the rules and recommendations for chemical nomenclature set out by the International Union of Pure and Applied Chemistry (IUPAC).
+  SMILES:
+    class_uri: CHEMINF:000018
+    is_a: QualitativeAttribute
+    description: A structure descriptor that denotes a molecular structure as a graph and conforms to the SMILES format specification.
+
+
+##########
+# Mixins #
+##########
+  ChemicalSubstanceMixin:
+    abstract: true
+    mixin: true
+    is_a: MaterialisticMixin
+    description: A LinkML mixin used to pass down properties common to all material entities that are described in a chemical context via being composed of chemical entities (e.g. atom, molecule, ion, ion pair, radical, complex, conformer etc., ) of the same type or of different types.
+    slots:
+      - has_concentration
+      - has_ph_value
+      - composed_of
+      - has_amount
+  PolymerMixin:
+    abstract: true
+    is_a: ChemicalSubstanceMixin
+    mixin: true
+    description: A LinkML mixin used to pass down properties common to all chemical substances that are composed of macromolecules of different kinds and which may be differentiated by composition, length, degree of branching etc..
+    # attributes: # Needed attributes will be defined here
+
 slots:
 
   composed_of: