Merge pull request #32 from monarch-initiative/sssom-mappings

Implement proper SSSOM validation

.github/workflows/qc.yml

@@ -24,6 +24,10 @@ jobs:
           DEFAULT_BRANCH: main
         run: pip install --upgrade pip && pip install -U sssom 
       - uses: actions/checkout@v2
+      - name: Prepare mappings
+        env:
+          DEFAULT_BRANCH: main
+        run: make RUN="" mappings
       - name: Run Mapping QC checks
         env:
           DEFAULT_BRANCH: main

metadata/gene_mappings.sssom.yml

@@ -0,0 +1,14 @@
+curie_map:
+  owl: http://www.w3.org/2002/07/owl#
+  Xenbase: https://www.xenbase.org/entry/
+  FB: https://flybase.org/reports/
+  RGD: http://rgd.mcw.edu/rgdweb/report/gene/main.html?id=
+  HGNC: http://identifiers.org/hgnc/
+  WB: https://www.wormbase.org/get?name=
+  OMIM: "https://omim.org/MIM:"
+  UniProtKB: http://purl.uniprot.org/uniprot/
+  ZFIN: http://zfin.org/
+license: https://creativecommons.org/licenses/by/4.0/
+mapping_set_description: The monarch gene mappings, based on HGNC and ENSEMBL base mappings.
+mapping_set_id: https://data.monarchinitiative.org/mappings/gene_mappings.sssom.tsv
+mapping_set_source: https://w3id.org/biopragmatics/biomappings/sssom/biomappings.sssom.tsv

metadata/mesh_chebi_biomappings.sssom.yml

@@ -0,0 +1,6 @@
+curie_map:
+  MESH: http://id.nlm.nih.gov/mesh/
+license: https://creativecommons.org/licenses/by/4.0/
+mapping_set_description: A subset of the biomappings containing mesh to chebi associations.
+mapping_set_id: https://data.monarchinitiative.org/mappings/mesh_chebi_biomappings.sssom.tsv
+mapping_set_source: https://w3id.org/biopragmatics/biomappings/sssom/biomappings.sssom.tsv

monarch_mapping_commons.Makefile

@@ -8,18 +8,27 @@ MAPPING_DIR = 					mappings
 SCRIPT_DIR =					scripts
 SRC_DIR = 						sources
 TMP_DIR = 						tmp
+METADATA_DIR = 					metadata
 RUN = poetry run
 
 
 $(MAPPING_DIR)/ $(SCRIPT_DIR)/ $(SRC_DIR)/ $(TMP_DIR)/:
 	mkdir -p $@
 
-$(MAPPING_DIR)/mondo.sssom.tsv: | $(MAPPING_DIR)/
+$(MAPPING_DIR)/mondo.sssom.tsv:
+	mkdir -p $(MAPPING_DIR) $(TMP_DIR)
 	wget http://purl.obolibrary.org/obo/mondo/mappings/mondo.sssom.tsv -O $@
 
-$(MAPPING_DIR)/biomappings.sssom.tsv: | $(MAPPING_DIR)/ $(SCRIPT_DIR)/ $(TMP_DIR)/
+$(MAPPING_DIR)/mesh_chebi_biomappings.sssom.tsv:
+	mkdir -p $(MAPPING_DIR) $(TMP_DIR)
 	wget https://raw.githubusercontent.com/biopragmatics/biomappings/master/docs/_data/sssom/biomappings.sssom.tsv -O $(TMP_DIR)/biomappings.sssom.tsv
-	$(RUN) python3 $(SCRIPT_DIR)/process_biomappings.py --input $(TMP_DIR)/biomappings.sssom.tsv --output $(MAPPING_DIR)/mesh_chebi_biomappings.sssom.tsv
+	$(RUN) python3 $(SCRIPT_DIR)/process_biomappings.py --input $(TMP_DIR)/biomappings.sssom.tsv --output $(TMP_DIR)/mesh_chebi_biomappings.sssom.tsv
+	sssom parse $(TMP_DIR)/mesh_chebi_biomappings.sssom.tsv -m $(METADATA_DIR)/mesh_chebi_biomappings.sssom.yml --prefix-map-mode merged -o $@
 
 $(MAPPING_DIR)/gene_mappings.sssom.tsv:
-	wget http://data.monarchinitiative.org/monarch-gene-mapping/latest/gene_mappings.tsv -O $@
+	mkdir -p $(MAPPING_DIR) $(TMP_DIR)
+	wget http://data.monarchinitiative.org/monarch-gene-mapping/latest/gene_mappings.tsv -O $(TMP_DIR)/gene_mappings.sssom.tsv
+	# see https://github.com/monarch-initiative/monarch-mapping-commons/issues/33
+	grep -v "<NA>" $(TMP_DIR)/gene_mappings.sssom.tsv > $@.tmp && mv $@.tmp $(TMP_DIR)/gene_mappings.sssom.tsv
+	grep -v ";" $(TMP_DIR)/gene_mappings.sssom.tsv > $@.tmp && mv $@.tmp $(TMP_DIR)/gene_mappings.sssom.tsv
+	sssom parse $(TMP_DIR)/gene_mappings.sssom.tsv -m $(METADATA_DIR)/gene_mappings.sssom.yml --prefix-map-mode merged -o $@

pyproject.toml

@@ -11,6 +11,7 @@ cruft = "^2.15.0"
 pandas = "^2.1.1"
 curies = "^0.6.4"
 pytest = "^7.4.2"
+sssom = "^0.3.41"
 
 
 [build-system]

registry.yml

@@ -13,9 +13,9 @@ mapping_set_references:
       local_id: mondo
 
   # Biomappings for CTD
-  - mapping_set_id: http://w3id.org/sssom/commons/monarch/biomappings.sssom.tsv
-    # mapping_set_group: disease_mappings
-    local_name: biomappings.sssom.tsv
+  - mapping_set_id: http://w3id.org/sssom/commons/monarch/mesh_chebi_biomappings.sssom.tsv
+    mapping_set_group: chemical_mappings
+    local_name: mesh_chebi_biomappings.sssom.tsv
     mirror_from: https://raw.githubusercontent.com/biopragmatics/biomappings/master/docs/_data/sssom/biomappings.sssom.tsv
     mapping_set_confidence: "0.9"