First pass at functional annotations, #177

schema/annotation.yaml

@@ -0,0 +1,142 @@
+id: https://microbiomedata/schema/annotation
+name: NMDC-Annotation
+title: Annotation Module for NMDC Schema
+description: >-
+  This module in the schema is for representing annotations including functional annotations of proteins and other gene products,
+  as well as controlled terms for describing things like metabolites
+  
+see_also:
+  - https://github.com/microbiomedata/nmdc-metadata/issues/176
+
+prefixes:
+  biolinkml: https://w3id.org/biolink/biolinkml/
+  biolink: https://w3id.org/biolink/vocab/
+
+imports:
+  - biolinkml:types
+  - core
+  - prov
+
+classes:
+
+  functional annotation term:
+    aliases:
+      - function
+      - functional annotation
+    is_a: controlled term value
+    description: >-
+      Abstract grouping class for any term/descriptor that can be applied to a functional unit of a genome (protein, ncRNA, complex).
+    abstract: true
+    todos:
+      - decide if this should be used for product naming
+
+  pathway:
+    aliases:
+      - biological process
+      - metabolic pathway
+      - signaling pathway
+    is_a: functional annotation term
+    description: >-
+      A pathway is a sequence of steps/reactions carried out by an organism or community of organisms
+    id_prefixes:
+      - KEGG.PATHWAY
+      - COG
+    exact_mappings:
+      - biolink:Pathway
+
+  reaction:
+    is_a: functional annotation term
+    description: >-
+      An individual biochemical transformation carried out by a functional unit of an organism, in which a collection of substrates are transformed into a collection of products.
+      Can also represent transporters
+    id_prefixes:
+      - KEGG.REACTION
+      - RHEA
+      - MetaCyc
+      - EC
+      - GO
+    exact_mappings:
+      - biolink:MolecularActivity
+
+  orthology group:
+    is_a: functional annotation term
+    description: >-
+      A set of genes or gene products in which all members are orthologous
+    id_prefixes:
+      - KEGG.ORTHOLOGY
+      - EGGNOG
+      - PFAM
+      - TIGRFAM
+      - SUPFAM
+      - PANTHER.FAMILY
+    exact_mappings:
+      - biolink:GeneFamily
+
+  chemical entity:
+    aliases:
+      - metabolite
+      - chemical substance
+      - chemical compound
+      - chemical
+    is_a: controlled term value
+    description: >-
+      An atom or molecule that can be represented with a chemical formula. Include lipids, glycans, natural products, drugs.
+      There may be different terms for distinct acid-base forms, protonation states
+    slot_usage:
+      inchi:
+        key: true
+        multivalued: false
+      inchi key:
+        key: false # rare; Pletnev I, Erin A, McNaught A, Blinov K, Tchekhovskoi D, Heller S (2012) InChIKey collision resistance: an experimental testing. J Cheminform. 4:12
+        multivalued: false
+      smiles:
+        description: >-
+          A string encoding of a molecular graph, no chiral or isotopic information. There are usually a large number of valid SMILES which represent a given structure. For example, CCO, OCC and C(O)C all specify the structure of ethanol.
+        multivalued: true
+    see_also:
+      - https://bioconductor.org/packages/devel/data/annotation/vignettes/metaboliteIDmapping/inst/doc/metaboliteIDmapping.html
+    id_prefixes:
+      - KEGG.COMPOUND
+      - CHEBI
+      - CHEMBL.COMPOUND
+      - DRUGBANK
+      - PUBCHEM.COMPOUND
+      - CAS
+      - HMDB
+      - MESH
+    exact_mappings:
+      - biolink:ChemicalSubstance
+
+  gene product:
+    description: >-
+      A molecule encoded by a gene that has an evolved function
+    comments:
+      - we may include a more general gene product class in future to allow for ncRNA annotation
+    id_prefixes:
+      - UniProtKB
+      - gtpo
+      - PR
+    exact_mappings:
+      - biolink:GeneProduct
+
+  functional annotation:
+    description: >-
+      An assignment of a function term (e.g. reaction or pathway) that is executed by a gene product, or which the gene product plays an active role in.
+      Functional annotations can be assigned manually by curators, or automatically in workflows. In the context of NMDC, all function annotation is performed
+      automatically, typically using HMM or Blast type methods
+    see_also:
+      - https://img.jgi.doe.gov/docs/functional-annotation.pdf
+      - https://github.com/microbiomedata/mg_annotation/blob/master/functional-annotation.wdl
+    slots:
+      - was generated by
+    slot_usage:
+      subject:
+        range: gene product
+      has function:
+        range: functional annotation term
+      was generated by:
+        description: >-
+          provenance for the annotation. Note to be consistent with the rest of the NMDC schema we use the PROV annotation model, rather than GPAD
+    narrow_mappings:
+      - biolink:GeneToGoTermAssociation
+

schema/nmdc.yaml

@@ -43,6 +43,7 @@ imports:
   - mixs
   - core
   - prov
+  - annotation
 
 subsets:
   workflow subset:
@@ -813,4 +814,4 @@ slots:
     range: string
 
   completion_date:
-    range: string
+    range: string