Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Attribute mapping from node to dug element #203

Merged
merged 6 commits into from
Apr 1, 2022
Merged

Attribute mapping from node to dug element #203

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
60b473a
Release/2.8.0 (#198)
YaphetKG Feb 8, 2022
bb661be
Release/v2.9.0 (#201)
YaphetKG Mar 29, 2022
a6d7b4c
Merge branch 'master' into develop
YaphetKG Mar 29, 2022
a37534c
Merge branch 'develop' of https://github.com/helxplatform/dug into de…
YaphetKG Mar 30, 2022
2e359b5
adding more config options for node extraction
Mar 31, 2022
e4b236c
some refactoring
Mar 31, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 9 additions & 1 deletion src/dug/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,7 +67,15 @@ class Config:
# Dug element type to cast the query kg nodes to
"cde": {
# Parse nodes matching criteria in kg
"node_type": "biolink:Publication"
"node_type": "biolink:Publication",
"curie_prefix": "HEALCDE",
"attribute_mapping": {
# "DugElement Attribute" : "KG Node attribute"
"name": "name",
"desc": "summary",
"collection_name": "cde_category",
"collection_id": "cde_category"
}
}
})

Expand Down
22 changes: 12 additions & 10 deletions src/dug/core/crawler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -206,6 +206,8 @@ def expand_to_dug_element(self,
elements = []
# using node_type as the primary criteria for matching nodes to element type.
target_node_type = casting_config["node_type"]
curie_filter = casting_config["curie_prefix"]
attribute_mapping = casting_config["attribute_mapping"]
target_node_type_snake_case = biolink_snake_case(target_node_type.replace("biolink:", ""))
for ident_id, identifier in concept.identifiers.items():

Expand Down Expand Up @@ -244,14 +246,14 @@ def expand_to_dug_element(self,
# and return the variables.
for node_id, node in answer.nodes.items():
if target_node_type in node["category"]:
# @TODO make element creation more generic
# @TODO need to encode more data into the graph nodes, to parse them properly
element = DugElement(
elem_id=node_id,
name=node.get('name', ""),
desc=node.get('summary', ""),
elem_type=dug_element_type
)
element.add_concept(concept)
elements.append(element)
if node['id'].startswith(curie_filter):
element_attribute_args = {"elem_id": node_id, "elem_type": dug_element_type}
element_attribute_args.update({key: node.get(attribute_mapping[key], "")
for key in attribute_mapping
})
element = DugElement(
**element_attribute_args
)
element.add_concept(concept)
elements.append(element)
return elements
4 changes: 3 additions & 1 deletion src/dug/core/factory.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,7 +96,9 @@ def build_element_extraction_parameters(self, source=None):
{
"output_dug_type": dug_type,
"casting_config": {
"node_type": queries[dug_type]['node_type']
"node_type": queries[dug_type]["node_type"],
"curie_prefix": queries[dug_type]["curie_prefix"],
"attribute_mapping": queries[dug_type]["attribute_mapping"]
# CDE's are only ones
# but if we had two biolink:Publication nodes we want to conditionally
# cast to other output_dug_type, we could extend this config
Expand Down
36 changes: 30 additions & 6 deletions tests/unit/mocks/data/tranql_response.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,14 +8,14 @@
}
},
"nodes": {
"publication": {
"category": "biolink:Publication"
},
"disease": {
"category": "biolink:Disease",
"id": [
"MONDO:0008187"
]
},
"publication": {
"category": "biolink:Publication"
}
}
},
Expand All @@ -25,11 +25,11 @@
"name": "panic disorder 1",
"category": [
"biolink:Disease",
"biolink:Entity",
"biolink:DiseaseOrPhenotypicFeature",
"biolink:ThingWithTaxon",
"biolink:BiologicalEntity",
"biolink:NamedThing",
"biolink:DiseaseOrPhenotypicFeature"
"biolink:Entity",
"biolink:NamedThing"
],
"attributes": [
{
Expand Down Expand Up @@ -72,6 +72,30 @@
"value": "Filename: Photosensitivity_PAQ_CDE_v1.0.json; File path: Supplemental Questionnaires/Sensory/Photosensitivity Assessment Questionnaire (PAQ); Photosensitivity Assessment Questionnaire",
"name": "summary"
},
{
"type": "NA",
"value": [
"Supplemental Questionnaires",
"Sensory",
"Photosensitivity Assessment Questionnaire (PAQ)"
],
"name": "cde_categories"
},
{
"type": "NA",
"value": [
"Supplemental Questionnaires",
"Adult/Pediatric",
"Acute/Chronic Pain",
"Photosensitivity Assessment Questionnaire (PAQ)"
],
"name": "cde_category_extended"
},
{
"type": "NA",
"value": "Supplemental Questionnaires",
"name": "cde_category"
},
{
"type": "NA",
"value": [
Expand Down
11 changes: 10 additions & 1 deletion tests/unit/test_crawler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,7 +84,16 @@ def test_expand_to_dug_element(crawler):
concept.add_identifier(identifier)
new_elements = crawler.expand_to_dug_element(
concept=concept,
casting_config={"node_type": "biolink:Publication"},
casting_config={
"node_type": "biolink:Publication",
"curie_prefix": "HEALCDE",
"attribute_mapping": {
"name": "name",
"desc": "summary",
"collection_name": "cde_category",
"collection_id": "cde_category"
}
},
dug_element_type="test-element",
tranql_source="test:graph"
)
Expand Down