Adding SSSOM profile for literals (#235)

Fixes #197 
Fixes #234 

- [x] `docs/` have been added/updated if necessary
- [x] `make test` has been run locally
- [x] tests have been added/updated (if applicable)
- [ ]
[CHANGELOG.md](https://github.com/mapping-commons/sssom/blob/0.9.0/CHANGELOG.md)
has been updated.

This PR adds a new profile to SSSOM for the representation of literal
mappings, leaving the default SSSOM intact.

---------

Co-authored-by: James McLaughlin <james@mclgh.net>

mkdocs.yml

@@ -50,6 +50,7 @@ nav:
     - 5-Star Entity Mappings - Cheatsheet: 5star-mappings.md
     - Update schema/context and release: update.md
     - Matching tool implementation guide: matching-tool-implementation-guide.md
+    - SSSOM profiles: sssom-profiles.md
     - Glossary: glossary.md
 
 site_url: https://mapping-commons.github.io/sssom/

src/docs/sssom-profiles.md

@@ -0,0 +1,17 @@
+## SSSOM Profiles
+
+- [Literal Mappings](#literal)
+
+<a id="literal"></a>
+
+### Literal Mappings
+
+The SSSOM profile for literal mappings is a version of SSSOM that allows the dissemination and standardisation of mappings between identifers and literals.
+
+As of 01.08.2023, the first version of this profile has been published, and it is still subject to change. We recommend to reach out on the [SSSOM issue tracker](https://github.com/mapping-commons/sssom/issues) if you are interested in using the literal profile. Note: we dont expect there to be any major breaking changes.
+
+**Demand better docs now**: https://github.com/mapping-commons/sssom/issues
+
+- [Slides](https://docs.google.com/presentation/d/1mBZK6KS7JgmXlEtszQiOa_Cl7SXg_Z8wRp0tZHaL57Y/edit)
+- [PR](https://github.com/mapping-commons/sssom/pull/235)
+- [Recording/discussion](events/mc2023.md)

src/sssom_schema/schema/sssom_schema.yaml

@@ -13,6 +13,7 @@ prefixes:
   pav: http://purl.org/pav/
   prov: http://www.w3.org/ns/prov#
   skos: http://www.w3.org/2004/02/skos/core#
+  xsd: http://www.w3.org/2001/XMLSchema#
   semapv: https://w3id.org/semapv/vocab/
 see_also:
 - https://github.com/mapping-commons/sssom
@@ -121,6 +122,26 @@ slots:
     examples:
       - value: HP:0009894
         description: The CURIE denoting the Human Phenotype Ontology concept of 'Thickened ears'
+  literal:
+    description: The literal being mapped
+    range: string
+    required: true
+    mappings:
+    - owl:annotatedSource
+    slot_uri: owl:annotatedSource
+    examples:
+      - value: "Alzheimer"
+        description: A string referring to some thing.
+  literal_datatype:
+    description: The datatype of the literal being mapped
+    range: uri
+    required: false
+    mappings:
+    - rdf:datatype
+    slot_uri: rdf:datatype
+    examples:
+      - value: xsd:string
+        description: A string referring to some thing.
   subject_label:
     description: The label of subject of the mapping
     range: string
@@ -350,6 +371,20 @@ slots:
     examples:
       - value: http://purl.obolibrary.org/obo/mondo/releases/2021-01-30/mondo.owl
         description: (A persistent Version IRI pointing to the Mondo version '2021-01-30')
+  literal_source:
+    description: URI of ontology source for the literal.
+    range: EntityReference
+    examples:
+      - value: obo:mondo.owl
+        description: A persistent OBO CURIE pointing to the latest version of the Mondo ontology.
+      - value: wikidata:Q7876491
+        description: A Wikidata identifier for the Uberon ontology resource.
+  literal_source_version:
+    description: Version IRI or version string of the source of the literal.
+    range: string
+    examples:
+      - value: http://purl.obolibrary.org/obo/mondo/releases/2021-01-30/mondo.owl
+        description: (A persistent Version IRI pointing to the Mondo version '2021-01-30')
   object_source:
     description: URI of vocabulary or identifier source for the object.
     range: EntityReference
@@ -444,6 +479,13 @@ slots:
     examples:
       - value: semapv:Stemming
       - value: semapv:StopWordRemoval
+  literal_preprocessing:
+    description: Method of preprocessing applied to the literal.
+    range: EntityReference
+    multivalued: true
+    examples:
+      - value: semapv:Stemming
+      - value: semapv:StopWordRemoval
   curation_rule:
     description: A curation rule is a (potentially) complex condition executed by an agent that led to the establishment of a mapping. 
       Curation rules often involve complex domain-specific considerations, which are hard to capture in an automated fashion. The curation
@@ -479,6 +521,18 @@ slots:
     examples:
       - value: https://www.wikidata.org/wiki/Q865360
         description: (the Wikidata identifier for the Jaccard index measure).
+  similarity_score:
+    description: A score between 0 and 1 to denote the similarity, where
+      1 denotes equivalence.
+    range: double
+  similarity_measure:
+    description: The measure used for computing the the similarity score.
+      To make processing this field as unambiguous as possible, we recommend using 
+      wikidata identifiers, but wikipedia pages could also be acceptable.
+    range: string
+    examples:
+      - value: https://www.wikidata.org/wiki/Q865360
+        description: (the Wikidata identifier for the Jaccard index measure).
   issue_tracker_item:
     description: The issue tracker item discussing this mapping.
     range: EntityReference
@@ -598,6 +652,50 @@ classes:
     - other
     - comment
     class_uri: owl:Axiom
+  literal mapping:
+    description: Represents an individual mapping between a literal and an entity. 
+      Note that this schema has been created on 01.08.2023 and is subject to change.
+    see_also:
+    - https://mapping-commons.github.io/sssom/sssom-profiles/
+    slots:
+    - literal
+    - literal_datatype
+    - predicate_id
+    - predicate_label
+    - predicate_modifier
+    - object_id
+    - object_label
+    - object_category
+    - mapping_justification
+    - author_id
+    - author_label
+    - reviewer_id
+    - reviewer_label
+    - creator_id
+    - creator_label
+    - license
+    - literal_source
+    - literal_source_version
+    - object_type
+    - object_source
+    - object_source_version
+    - mapping_provider
+    - mapping_source
+    - mapping_cardinality
+    - mapping_tool
+    - mapping_tool_version
+    - mapping_date
+    - confidence
+    - object_match_field
+    - match_string
+    - literal_preprocessing
+    - object_preprocessing
+    - similarity_score
+    - similarity_measure
+    - see_also
+    - other
+    - comment
+    class_uri: owl:Axiom
   mapping registry:
     description: A registry for managing mapping sets. It holds a set of 
       mapping set references, and can import other registries.