merge main & repair lock file

monarch-initiative · Sep 27, 2023 · a510497 · a510497
2 parents c090619 + 0f47ae2
commit a510497
Show file tree

Hide file tree

Showing 8 changed files with 311 additions and 330 deletions.
diff --git a/docs/Sources/hpoa.md b/docs/Sources/hpoa.md
@@ -83,7 +83,7 @@ __**Biolink captured**__
     * onset_qualifier (Onset.id)
     * frequency_qualifier (Note [3])
     * aggregating_knowledge_source (["infores:monarchinitiative"])
-    * primary_knowledge_source ("infores:hpoa")
+    * primary_knowledge_source ("infores:hpo-annotations")
 
 Notes:
 1. CURIE of [Evidence and Conclusion Ontology(https://bioportal.bioontology.org/ontologies/ECO)] term

diff --git a/poetry.lock b/poetry.lock
diff --git a/scripts/add_association_copyfields.sh b/scripts/add_association_copyfields.sh
@@ -36,7 +36,7 @@ curl -X POST -H 'Content-type:application/json' --data-binary '{
 
 # now add copyfields declarations for subject_label, subject_closure_label, object_label, object_closure_label
 
-for field in subject_label subject_closure_label subject_taxon subject_taxon_label predicate object_label object_closure_label object_taxon object_taxon_label primary_knowledge_source in_taxon_label qualifier_label onset_qualifier_label frequency_qualifier_label sex_qualifier_label
+for field in subject_label subject_closure_label subject_taxon subject_taxon_label predicate object_label object_closure_label object_taxon object_taxon_label primary_knowledge_source qualifier_label onset_qualifier_label frequency_qualifier_label sex_qualifier_label
 do
   curl -X POST -H 'Content-type:application/json' --data-binary "{
   \"add-copy-field\": {

diff --git a/scripts/after_download.sh b/scripts/after_download.sh
@@ -13,3 +13,6 @@ awk '{ if ($2 == "rdfs:subClassOf" || $2 == "BFO:0000050" || $2 == "UPHENO:00000
 
 # Extract NCBITaxon node names into their own basic tsv for gene ingests
 tar xfO data/monarch/kg-phenio.tar.gz merged-kg_nodes.tsv | grep ^NCBITaxon | cut -f 1,3 > data/monarch/taxon_labels.tsv
+
+# Repair Orphanet prefixes in MONDO sssom rows as necessary
+sed -i 's/\torphanet.ordo\:/\tOrphanet\:/g' data/monarch/mondo.sssom.tsv
diff --git a/scripts/load_sqlite.sh b/scripts/load_sqlite.sh
@@ -30,5 +30,11 @@ rm output/monarch-kg_*.tsv
 gzip --force output/qc/monarch-kg-dangling-edges.tsv
 gzip --force output/monarch-kg-denormalized-edges.tsv
 
-echo "Compressing database"
+echo "Populate phenio db term_association..."
+cp data/monarch/phenio.db.gz output/phenio.db.gz
+gunzip output/phenio.db.gz
+sqlite3 -cmd "attach 'monarch-kg.db' as monarch" phenio.db "insert into term_association (id, subject, predicate, object, evidence_type, publication, source) select id, subject, predicate, object, has_evidence as evidence_type, publications as publication, primary_knowledge_source as source from monarch.edges where predicate = 'biolink:has_phenotype' and negated <> 'True'"
+
+echo "Compressing databases"
+gzip --force output/phenio.db
 gzip --force output/monarch-kg.db
diff --git a/src/monarch_ingest/download.yaml b/src/monarch_ingest/download.yaml
@@ -306,6 +306,10 @@
   url: https://github.com/monarch-initiative/phenio/releases/latest/download/phenio-relation-graph.tar.gz
   local_name: data/monarch/phenio-relation-graph.tar.gz
   tag: phenio
+-
+  url: https://s3.amazonaws.com/bbop-sqlite/phenio.db.gz
+  local_name: data/monarch/phenio.db.gz
+  tag: phenio
 
 # -
 #   url: https://ci.monarchinitiative.org/job/monarch-ontology-json-sri/lastSuccessfulBuild/artifact/build/monarch-ontology-final.json

diff --git a/src/monarch_ingest/ingests/panther/orthology_utils.py b/src/monarch_ingest/ingests/panther/orthology_utils.py
@@ -50,7 +50,7 @@ def ncbitaxon_by_name(species_tag: str) -> Optional[str]:
     "FlyBase": "FB",
     "Ensembl": "ENSEMBL",
     "EnsemblGenome": "ENSEMBL",  # TODO: review and fix this later?
-    "PomBase": "POMBASE",
+    "PomBase": "PomBase",
     "WormBase": "WB",  # Wormbase supports 'WormBase:' but alliancegenome.org and identifiers.org supports 'WB:'
     "GeneID": "NCBIGene",          # seems to be Entrez Gene ID => map onto the NCBIGene: namespace
     "Gene": None,                  # seems to be the gene symbol - we ignore it for now?

diff --git a/tests/unit/panther/test_genome_orthologs.py b/tests/unit/panther/test_genome_orthologs.py
@@ -49,7 +49,7 @@ def script():
         "RO:HOM0000017",
         "PANTHER.FAMILY:PTHR12434",
     ],
-    "POMBASE:SPAC20G8.06": [
+    "PomBase:SPAC20G8.06": [
         "ZFIN:ZDB-GENE-040915-1",
         "NCBITaxon:7955",
         "NCBITaxon:4896",