Merge branch 'main' into add-docs-badge

scripts/add_association_copyfields.sh

@@ -0,0 +1,47 @@
+#!/bin/sh
+
+# Add two dynamicfields declarations to the schema
+
+# One for text fields, have to replace because _t comes built in
+
+# delete the _t dynamic field
+curl -X POST -H 'Content-type:application/json' --data-binary '{
+    "delete-dynamic-field": {
+        "name": "*_t"
+    }
+}' http://localhost:8983/solr/association/schema
+
+curl -X POST -H 'Content-type:application/json' --data-binary '{
+    "add-dynamic-field": {
+        "name": "*_t",
+        "type": "text",
+        "indexed": true,
+        "stored": false,
+        "multiValued": true
+    }
+}' http://localhost:8983/solr/association/schema
+
+# One for autocomplete fields
+
+curl -X POST -H 'Content-type:application/json' --data-binary '{
+    "add-dynamic-field": {
+        "name": "*_ac",
+        "type": "autocomplete",
+        "indexed": true,
+        "stored": false,
+        "multiValued": true
+    }
+}' http://localhost:8983/solr/association/schema
+
+
+# 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
+do
+  curl -X POST -H 'Content-type:application/json' --data-binary "{
+  \"add-copy-field\": {
+      \"source\":\"$field\",
+      \"dest\": \"${field}_t\"
+  }
+}" http://localhost:8983/solr/association/schema
+done

scripts/add_fieldtypes.sh

@@ -0,0 +1,7 @@
+#!/bin/bash
+
+for core in entity association
+do
+  curl -X POST -H 'Content-type:application/json' -d @scripts/text-fieldtype.json http://localhost:8983/solr/$core/schema
+  curl -X POST -H 'Content-type:application/json' -d @scripts/autocomplete-fieldtype.json http://localhost:8983/solr/$core/schema
+done

scripts/autocomplete-fieldtype.json

@@ -0,0 +1,26 @@
+{
+    "add-field-type": {
+      "name": "autocomplete",
+      "class": "solr.TextField",
+      "positionIncrementGap": "100",
+      "indexAnalyzer": {
+        "tokenizer": { "class": "solr.StandardTokenizerFactory" },
+        "filters": [
+          { "class": "solr.ASCIIFoldingFilterFactory" },
+          { "class": "solr.LowerCaseFilterFactory" },
+          {
+            "class": "solr.EdgeNGramFilterFactory",
+            "minGramSize": "1",
+            "maxGramSize": "25"
+          }
+        ]
+      },
+      "queryAnalyzer": {
+        "tokenizer": { "class": "solr.StandardTokenizerFactory" },
+        "filters": [
+          { "class": "solr.ASCIIFoldingFilterFactory" },
+          { "class": "solr.LowerCaseFilterFactory" }
+        ]
+      }
+    }
+}

scripts/load_solr.sh

@@ -24,7 +24,7 @@ sleep 10
 
 # todo: ideally, this will live in linkml-solr
 echo "Adding additional fieldtypes"
-scripts/add_entity_fieldtypes.sh
+scripts/add_fieldtypes.sh
 sleep 5
 
 echo "Adding entity schema"
@@ -38,6 +38,7 @@ sleep 5
 # todo: this also should live in linkml-solr, and copy-fields should be based on the schema
 echo "Add dynamic fields and copy fields declarations"
 scripts/add_entity_copyfields.sh
+scripts/add_association_copyfields.sh
 sleep 5
 
 echo "Loading entities"

scripts/add_entity_fieldtypes.sh → scripts/text-fieldtype.json

@@ -1,5 +1,4 @@
-#!/bin/sh
-curl -X POST -H 'Content-type:application/json' --data-binary '{
+{
   "add-field-type": {
     "name": "text",
     "class": "solr.TextField",
@@ -52,31 +51,4 @@ curl -X POST -H 'Content-type:application/json' --data-binary '{
       ]
     }
   }
-}' http://localhost:8983/solr/entity/schema
-
-curl -X POST -H 'Content-type:application/json' --data-binary '{
-    "add-field-type": {
-      "name": "autocomplete",
-      "class": "solr.TextField",
-      "positionIncrementGap": "100",
-      "indexAnalyzer": {
-        "tokenizer": { "class": "solr.StandardTokenizerFactory" },
-        "filters": [
-          { "class": "solr.ASCIIFoldingFilterFactory" },
-          { "class": "solr.LowerCaseFilterFactory" },
-          {
-            "class": "solr.EdgeNGramFilterFactory",
-            "minGramSize": "1",
-            "maxGramSize": "25"
-          }
-        ]
-      },
-      "queryAnalyzer": {
-        "tokenizer": { "class": "solr.StandardTokenizerFactory" },
-        "filters": [
-          { "class": "solr.ASCIIFoldingFilterFactory" },
-          { "class": "solr.LowerCaseFilterFactory" }
-        ]
-      }
-    }
-}' http://localhost:8983/solr/entity/schema
+}

src/monarch_ingest/ingests/alliance/gene_to_expression.py

@@ -33,16 +33,14 @@
         #       but may have an UBERON term that we can use
         # stage_term_id = get_data(row, "whenExpressed.stageUberonSlimTerm.uberonTerm")
 
-        evidence = list()
-        assay = get_data(row, "assay")  # e.g. "MMO:0000658"
-        if assay:
-            evidence.append(assay)
+
+
+        publication_ids = [get_data(row, "evidence.publicationId")]
 
         xref = get_data(row, "crossReference.id")
         if xref:
-            evidence.append(xref)
+            publication_ids.append(xref)
 
-        publication_ids = get_data(row, "evidence.publicationId")
 
         # Our current ingest policy is to first use a reported Anatomical structure term...
         if anatomical_entity_id:
@@ -53,8 +51,8 @@
                     predicate='biolink:expressed_in',
                     object=anatomical_entity_id,
                     stage_qualifier=stage_term_id,
-                    has_evidence=evidence,
-                    publications=[publication_ids],
+                    qualifiers=([get_data(row, "assay")] if get_data(row, "assay") else None),
+                    publications=publication_ids,
                     aggregator_knowledge_source=["infores:monarchinitiative", "infores:alliancegenome"],
                     primary_knowledge_source=source
                 )
@@ -70,8 +68,8 @@
                     predicate='biolink:expressed_in',
                     object=cellular_component_id,
                     stage_qualifier=stage_term_id,
-                    has_evidence=evidence,
-                    publications=[publication_ids],
+                    qualifiers=([get_data(row, "assay")] if get_data(row, "assay") else None),
+                    publications=publication_ids,
                     aggregator_knowledge_source=["infores:monarchinitiative", "infores:alliancegenome"],
                     primary_knowledge_source=source
                 )

src/monarch_ingest/ingests/alliance/gene_to_expression.yaml

@@ -46,7 +46,7 @@ edge_properties:
   - 'object'
   - 'stage_qualifier'
   - 'category'
-  - 'has_evidence'
+  - 'qualifiers'
   - 'publications'
   - 'aggregator_knowledge_source'
   - 'primary_knowledge_source'

tests/unit/alliance/test_alliance_gene_to_expression.py

@@ -1,22 +1,6 @@
 import pytest
 from biolink.pydanticmodel import GeneToExpressionSiteAssociation
 
-#
-# test of utility function - proven to work, unless modified in the future?
-#
-# def test_get_data():
-#     entry = {
-#         "testing": {
-#             "one": {
-#                 "two": {
-#                     "three": "Success!"
-#                 }
-#             }
-#         }
-#     }
-#     assert get_data(entry, "testing.one.two.three") == "Success!"
-
-
 @pytest.fixture
 def source_name():
     return "alliance_gene_to_expression"
@@ -75,7 +59,7 @@ def test_rattus_association(rattus):
     assert association.object == "GO:0030141"
     assert not association.stage_qualifier
     assert "PMID:12615975" in association.publications
-    assert "MMO:0000640" in association.has_evidence
+    assert "MMO:0000640" in association.qualifiers
     assert association.primary_knowledge_source == "infores:rgd"
     assert aggregator_knowledge_sources(association)
 
@@ -126,8 +110,8 @@ def test_mouse_association(mouse):
     assert association.object == "EMAPA:16039"
     assert association.stage_qualifier is None
     assert "MGI:1199209" in association.publications
-    assert "MMO:0000655" in association.has_evidence
-    assert "MGI:1203979" in association.has_evidence
+    assert "MGI:1203979" in association.publications
+    assert "MMO:0000655" in association.qualifiers
     assert association.primary_knowledge_source == "infores:mgi"
     assert aggregator_knowledge_sources(association)
 
@@ -183,8 +167,8 @@ def test_zebrafish_association(zebrafish):
     assert association.object == "ZFA:0001094"
     assert association.stage_qualifier == "ZFS:0000035"
     assert "PMID:18544660" in association.publications
-    assert "MMO:0000655" in association.has_evidence
-    assert "ZFIN:ZDB-FIG-080908-4" in association.has_evidence
+    assert "ZFIN:ZDB-FIG-080908-4" in association.publications
+    assert "MMO:0000655" in association.qualifiers
     assert association.primary_knowledge_source == "infores:zfin"
     assert aggregator_knowledge_sources(association)
 
@@ -231,7 +215,7 @@ def test_drosophila_association(drosophila):
     assert association.object == "FBbt:00003007"
     assert association.stage_qualifier == "FBdv:00005369"
     assert "FB:FBrf0231198" in association.publications
-    assert "MMO:0000534" in association.has_evidence
+    assert "MMO:0000534" in association.qualifiers
     assert association.primary_knowledge_source == "infores:flybase"
     assert aggregator_knowledge_sources(association)
 
@@ -282,8 +266,8 @@ def test_worm_association(worm):
     assert association.object == "WBbt:0000100"
     assert association.stage_qualifier == "WBls:0000057"
     assert association.publications[0] == "PMID:1782857"
-    assert "MMO:0000670" in association.has_evidence
-    assert "WB:Expr1" in association.has_evidence
+    assert "WB:Expr1" in association.publications
+    assert "MMO:0000670" in association.qualifiers
     assert association.primary_knowledge_source == "infores:wormbase"
     assert aggregator_knowledge_sources(association)
 
@@ -327,6 +311,6 @@ def test_yeast_association(yeast):
     assert association.object == "GO:1990316"
     assert not association.stage_qualifier
     assert association.publications[0] == "PMID:26753620"
-    assert "MMO:0000642" in association.has_evidence
+    assert "MMO:0000642" in association.qualifiers
     assert association.primary_knowledge_source == "infores:sgd"
     assert aggregator_knowledge_sources(association)