nmrML · NRayya · Feb 11, 2025 · Jan 28, 2025 · Jan 28, 2025 · Jan 28, 2025
diff --git a/docs/odk-workflows/RepositoryFileStructure.md b/docs/odk-workflows/RepositoryFileStructure.md
@@ -21,7 +21,7 @@ These are the current imports in NMRCV
 | omo | http://purl.obolibrary.org/obo/omo.owl | mirror |
 | iao | http://purl.obolibrary.org/obo/iao.owl | None |
 | obi | http://purl.obolibrary.org/obo/obi.owl | custom |
-| chebi | http://purl.obolibrary.org/obo/chebi.owl | None |
+| chebi | http://purl.obolibrary.org/obo/chebi.owl | custom |
 
 ## Components
 Components, in contrast to imports, are considered full members of the ontology. This means that any axiom in a component is also included in the ontology base - which means it is considered _native_ to the ontology. While this sounds complicated, consider this: conceptually, no component should be part of more than one ontology. If that seems to be the case, we are most likely talking about an import. Components are often not needed for ontologies, but there are some use cases:

diff --git a/src/ontology/Makefile b/src/ontology/Makefile
@@ -10,7 +10,7 @@
 # More information: https://github.com/INCATools/ontology-development-kit/
 
 # Fingerprint of the configuration file when this Makefile was last generated
-CONFIG_HASH=                1ba644404ead28f12b159a84d638daf10791c394ce2f9060998152d134df9dcc
+CONFIG_HASH=                fd98f62cea8e98a347fcdcf420367f85a1508e39fd0bcd97b7b3b1b954831e0b
 
 
 # ----------------------------------------
@@ -382,11 +382,8 @@ $(IMPORTDIR)/obi_import.owl: $(MIRRORDIR)/obi.owl
 	echo "ERROR: You have configured your default module type to be custom; this behavior needs to be overwritten in nmrCV.Makefile!" && false
 ## Module for ontology: chebi
 
-$(IMPORTDIR)/chebi_import.owl: $(MIRRORDIR)/chebi.owl $(IMPORTDIR)/chebi_terms_combined.txt
-	if [ $(IMP) = true ] && [ $(IMP_LARGE) = true ]; then $(ROBOT) extract -i $< -T $(IMPORTDIR)/chebi_terms_combined.txt --force true  --copy-ontology-annotations true --individuals include --method BOT \
-		query --update ../sparql/inject-subset-declaration.ru --update ../sparql/inject-synonymtype-declaration.ru --update ../sparql/postprocess-module.ru \
-		$(ANNOTATE_CONVERT_FILE); fi
-
+$(IMPORTDIR)/chebi_import.owl: $(MIRRORDIR)/chebi.owl
+	echo "ERROR: You have configured your default module type to be custom; this behavior needs to be overwritten in nmrCV.Makefile!" && false
 
 .PHONY: refresh-imports
 refresh-imports:

diff --git a/src/ontology/imports/chebi_import.owl b/src/ontology/imports/chebi_import.owl
diff --git a/src/ontology/imports/chebi_terms.txt b/src/ontology/imports/chebi_terms.txt
@@ -1,3 +1,29 @@
+# needed root terms
+CHEBI:33250 # atom
+CHEBI:33252 # atomic nucleus
+CHEBI:59999 # 'chemical substance'
+CHEBI:23367 # 'molecular entity'
+    CHEBI:36357 # polyatomic entity
+    CHEBI:33579 # main group molecular entity
+    CHEBI:24835 # inorganic molecular entity
+    CHEBI:33259 # elemental molecular entity
+    CHEBI:33497 # transition element molecular entity
+    CHEBI:35568 # mancude ring
+    CHEBI:24870 # ion
+
+# object relations for needed axioms
+BFO:0000051 # 'has part'
+RO:0000087 # 'has role'
+
+# needed roles 
+CHEBI:51086 # 'chemical role'
+CHEBI:197449 # NMR solvent
+CHEBI:228364 # NMR chemical shift reference compound
+CHEBI:67137 # NMR shift reagent
+
+CHEBI:139358 # isotopically modified compound
+CHEBI:76107  # deuterated compound
+
 CHEBI:156265 # methanol-d4
 CHEBI:193038 # acetonitrile-d3
 CHEBI:193039 # benzene-d6
@@ -24,7 +50,6 @@ CHEBI:41981  # dideuterium oxide
 CHEBI:48236  # trichlorofluoromethane
 CHEBI:78217  # acetone d6
 CHEBI:85365  # deuterated chloroform
-CHEBI:197449 # NMR solvent
 CHEBI:36810  # (trifluoromethyl)benzene
 CHEBI:38585  # 1,4-difluorobenzene
 CHEBI:47032  # 1,4-dioxane
@@ -112,7 +137,7 @@ CHEBI:176578 # cobalt-59 atom
 # TODO: add gallium atom isotopes
 CHEBI:52758  # germanium-73 atom
 CHEBI:176584 # arsenic-75 atom
-CHEBI:52457  # CHEBI:52457
+CHEBI:52457  # selenium-77 atom
 CHEBI:52743  # bromine-79 atom
 # TODO: add bromine atom isotopes
 # TODO: add krypton atom isotopes

diff --git a/src/ontology/nmrCV-edit.owl b/src/ontology/nmrCV-edit.owl
@@ -3868,10 +3868,11 @@ AnnotationAssertion(dce:source <http://nmrML.org/nmrCV#NMR:1000329> "http://www.
 AnnotationAssertion(rdfs:label <http://nmrML.org/nmrCV#NMR:1000329> "AB multiplet pattern"@en)
 SubClassOf(<http://nmrML.org/nmrCV#NMR:1000329> <http://nmrML.org/nmrCV#NMR:1400305>)
 
-# Class: <http://nmrML.org/nmrCV#NMR:1000330> (NMR solvent)
+# Class: <http://nmrML.org/nmrCV#NMR:1000330> (NMR solvent (molecular entity))
 
+AnnotationAssertion(obo:IAO_0000111 <http://nmrML.org/nmrCV#NMR:1000330> "NMR solvent"@en)
 AnnotationAssertion(obo:IAO_0000115 <http://nmrML.org/nmrCV#NMR:1000330> "A molecular entity that is used as a solvent in nuclear magnetic resonance (NMR) spectroscopy"@en)
-AnnotationAssertion(rdfs:label <http://nmrML.org/nmrCV#NMR:1000330> "NMR solvent"@en)
+AnnotationAssertion(Annotation(skos:editorialNote "We needed to add material entity in the label to avoid clashes with the similary labeled role class in CHEBI."@en) rdfs:label <http://nmrML.org/nmrCV#NMR:1000330> "NMR solvent (molecular entity)"@en)
 EquivalentClasses(<http://nmrML.org/nmrCV#NMR:1000330> ObjectIntersectionOf(obo:CHEBI_23367 ObjectSomeValuesFrom(obo:RO_0000087 obo:CHEBI_197449)))
 SubClassOf(Annotation(oboInOwl:is_inferred "true") <http://nmrML.org/nmrCV#NMR:1000330> obo:CHEBI_23367)
 
@@ -6743,10 +6744,6 @@ SubClassOf(<http://nmrML.org/nmrCV#NMR:1400320> <http://nmrML.org/nmrCV#NMR:1400
 AnnotationAssertion(rdfs:label <http://nmrML.org/nmrCV#NMR:1400321> "Bruker WIN NMR format")
 SubClassOf(<http://nmrML.org/nmrCV#NMR:1400321> <http://nmrML.org/nmrCV#NMR:1400285>)
 
-# Class: obo:BFO_0000023 (role)
-
-EquivalentClasses(obo:BFO_0000023 obo:CHEBI_50906)
-
 # Class: obo:CHEBI_156265 (methanol-d4)
 
 SubClassOf(Annotation(oboInOwl:is_inferred "true") obo:CHEBI_156265 <http://nmrML.org/nmrCV#NMR:1000330>)
@@ -6880,13 +6877,9 @@ SubClassOf(Annotation(oboInOwl:is_inferred "true") obo:CHEBI_229457 <http://nmrM
 
 SubClassOf(Annotation(oboInOwl:is_inferred "true") obo:CHEBI_229458 <http://nmrML.org/nmrCV#NMR:1400033>)
 
-# Class: obo:CHEBI_24431 (chemical entity)
-
-SubClassOf(obo:CHEBI_24431 obo:BFO_0000040)
+# Class: obo:CHEBI_23367 (molecular entity)
 
-# Class: obo:CHEBI_24432 (biological role)
-
-SubClassOf(Annotation(oboInOwl:is_inferred "true") obo:CHEBI_24432 obo:BFO_0000023)
+SubClassOf(obo:CHEBI_23367 obo:BFO_0000040)
 
 # Class: obo:CHEBI_26078 (phosphoric acid)
 
@@ -6934,7 +6927,15 @@ SubClassOf(Annotation(oboInOwl:is_inferred "true") obo:CHEBI_33093 <http://nmrML
 
 # Class: obo:CHEBI_33232 (application)
 
-SubClassOf(Annotation(oboInOwl:is_inferred "true") obo:CHEBI_33232 obo:BFO_0000023)
+SubClassOf(obo:CHEBI_33232 obo:BFO_0000023)
+
+# Class: obo:CHEBI_33250 (atom)
+
+SubClassOf(obo:CHEBI_33250 obo:BFO_0000040)
+
+# Class: obo:CHEBI_33252 (atomic nucleus)
+
+SubClassOf(obo:CHEBI_33252 obo:BFO_0000040)
 
 # Class: obo:CHEBI_33681 (helium(0))
 
@@ -6973,6 +6974,7 @@ SubClassOf(Annotation(oboInOwl:is_inferred "true") obo:CHEBI_39429 <http://nmrML
 # Class: obo:CHEBI_41981 (dideuterium oxide)
 
 SubClassOf(Annotation(oboInOwl:is_inferred "true") obo:CHEBI_41981 <http://nmrML.org/nmrCV#NMR:1000330>)
+SubClassOf(Annotation(oboInOwl:is_inferred "true") obo:CHEBI_41981 <http://nmrML.org/nmrCV#NMR:1400033>)
 
 # Class: obo:CHEBI_45892 (trifluoroacetic acid)
 
@@ -6999,13 +7001,9 @@ SubClassOf(Annotation(oboInOwl:is_inferred "true") obo:CHEBI_47032 <http://nmrML
 SubClassOf(Annotation(oboInOwl:is_inferred "true") obo:CHEBI_48236 <http://nmrML.org/nmrCV#NMR:1000330>)
 SubClassOf(Annotation(oboInOwl:is_inferred "true") obo:CHEBI_48236 <http://nmrML.org/nmrCV#NMR:1400033>)
 
-# Class: obo:CHEBI_50906 (role)
-
-SubClassOf(Annotation(oboInOwl:is_inferred "true") obo:CHEBI_50906 obo:BFO_0000017)
-
 # Class: obo:CHEBI_51086 (chemical role)
 
-SubClassOf(Annotation(oboInOwl:is_inferred "true") obo:CHEBI_51086 obo:BFO_0000023)
+SubClassOf(obo:CHEBI_51086 obo:BFO_0000023)
 
 # Class: obo:CHEBI_5115 (monofluorobenzene)
 
@@ -7019,6 +7017,10 @@ SubClassOf(Annotation(oboInOwl:is_inferred "true") obo:CHEBI_55317 <http://nmrML
 
 SubClassOf(Annotation(oboInOwl:is_inferred "true") obo:CHEBI_59606 <http://nmrML.org/nmrCV#NMR:1400033>)
 
+# Class: obo:CHEBI_59999 (chemical substance)
+
+SubClassOf(obo:CHEBI_59999 obo:BFO_0000040)
+
 # Class: obo:CHEBI_63005 (sodium nitrate)
 
 SubClassOf(Annotation(oboInOwl:is_inferred "true") obo:CHEBI_63005 <http://nmrML.org/nmrCV#NMR:1400033>)

diff --git a/src/ontology/nmrCV-odk.yaml b/src/ontology/nmrCV-odk.yaml
@@ -52,4 +52,6 @@ import_group:
   - id: chebi
     is_large: true
     use_gzipped: true
+    # Using ROBOT filter in chmo.Makefile because the default ODK ROBOT extract method pulls in too much from CHEBI.
+    module_type: custom
 
diff --git a/src/ontology/nmrCV.Makefile b/src/ontology/nmrCV.Makefile
@@ -13,4 +13,32 @@ $(IMPORTDIR)/obi_import.owl: $(MIRRORDIR)/obi.owl $(IMPORTDIR)/obi_terms.txt
         extract -T $(IMPORTDIR)/obi_terms.txt --force true --copy-ontology-annotations true --individuals exclude --method BOT \
         query --update ../sparql/inject-subset-declaration.ru --update ../sparql/inject-synonymtype-declaration.ru --update ../sparql/postprocess-module.ru \
         remove -T $(IMPORTDIR)/obi_remove_list.txt --select "self descendants instances" --signature true \
-        $(ANNOTATE_CONVERT_FILE); fi
+        $(ANNOTATE_CONVERT_FILE); fi
+
+
+## Module for ontology: chebi
+
+# We use ROBOT filter instead of the default ODK ROBOT extract method because the latter pulls in too much from ChEBI.
+# Using ROBOT filter like this allows us to only import the terms we need under their very general CHEBI 'root' parents.
+# This ROBOT filter approach entails, that not all axioms of the imported terms are imported as well, 
+# e.g. currently only 'part of' and 'has role' relations between the terms specified in the chebi_import.txt are 
+# imported.
+# If other axioms are needed in the future the nmrCV editors need to make sure to include the needed object properties 
+# and classes used in these, which is quite a time consuming task, but needed, as ROBOT extract pulls in too much 
+# and the CHEBI module would otherwise be too big to load. 
+# Since we also define classes based on the roles borne by some CHEBI terms, e.g. a 'chemical shift reference compound'
+# is equivalent to "'molecular entity' and ('has role' some ''NMR chemical shift reference compound [role]')" 
+# we additionally run a reasoning step to materialize the subclassOf axioms needed to group these CHEBI terms under 
+# the classes we define.
+
+$(IMPORTDIR)/chebi_import.owl: $(MIRRORDIR)/chebi.owl $(IMPORTDIR)/chebi_terms_combined.txt
+	if [ $(IMP) = true ] && [ $(IMP_LARGE) = true ]; then $(ROBOT) \
+	    filter -i $< -T $(IMPORTDIR)/chebi_terms_combined.txt --signature false --select "annotations self" \
+            --exclude-term http://purl.obolibrary.org/obo/CHEBI_24431 \
+            --exclude-term http://purl.obolibrary.org/obo/CHEBI_24432 \
+            --exclude-term http://purl.obolibrary.org/obo/CHEBI_50906 \
+		query --update ../sparql/inject-subset-declaration.ru --update ../sparql/inject-synonymtype-declaration.ru \
+		    --update ../sparql/postprocess-module.ru \
+		$(ANNOTATE_CONVERT_FILE); fi
+	$(ROBOT) reason --reasoner ELK -i $(SRC) --exclude-duplicate-axioms true --exclude-tautologies all --equivalent-classes-allowed asserted-only \
+	--annotate-inferred-axioms true --axiom-generators "SubClass" convert -f ofn --output $(SRC)