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

chore(l2ggoldstandard): add studyId to schema #305

Merged
merged 8 commits into from
Dec 5, 2023
Merged

chore(l2ggoldstandard): add studyId to schema #305

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
8a81293
chore(l2ggoldstandard): add studyId to schema
ireneisdoomed Dec 4, 2023
311d0c6
Merge branch 'main' into il-gs-add-study
ireneisdoomed Dec 4, 2023
e643da5
fix: add `studyId` to gold standards testing fixtures
ireneisdoomed Dec 4, 2023
eca90bd
Merge branch 'main' of https://github.com/opentargets/genetics_etl_py…
ireneisdoomed Dec 5, 2023
ec1e4df
Merge branch 'il-gs-add-study' of https://github.com/opentargets/gene…
ireneisdoomed Dec 5, 2023
2e6f685
Merge branch 'main' into il-gs-add-study
ireneisdoomed Dec 5, 2023
50b3f97
Merge branch 'main' into il-gs-add-study
ireneisdoomed Dec 5, 2023
11bd282
Merge branch 'main' into il-gs-add-study
d0choa Dec 5, 2023
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
6 changes: 6 additions & 0 deletions src/otg/assets/schemas/l2g_gold_standard.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,12 @@
"nullable": false,
"metadata": {}
},
{
"name": "studyId",
"type": "string",
"nullable": false,
"metadata": {}
},
{
"name": "geneId",
"type": "string",
Expand Down
6 changes: 2 additions & 4 deletions src/otg/datasource/open_targets/l2g_gold_standard.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,10 +116,8 @@ def as_l2g_gold_standard(
L2GGoldStandard: L2G Gold Standard dataset. False negatives have not yet been removed.
"""
return L2GGoldStandard(
_df=cls.parse_positive_curation(gold_standard_curation)
.transform(cls.expand_gold_standard_with_negatives, v2g)
.drop(
"studyId",
_df=cls.parse_positive_curation(gold_standard_curation).transform(
cls.expand_gold_standard_with_negatives, v2g
),
_schema=L2GGoldStandard.get_schema(),
)
30 changes: 18 additions & 12 deletions tests/dataset/test_l2g.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,27 +40,30 @@ def test_filter_unique_associations(spark: SparkSession) -> None:
"""Test filter_unique_associations."""
mock_l2g_gs_df = spark.createDataFrame(
[
(1, "variant1", "gene1", "positive"),
(1, "variant1", "study1", "gene1", "positive"),
(
2,
"variant2",
"study1",
"gene1",
"negative",
), # in the same locus as sl1 and pointing to same gene, has to be dropped
(
3,
"variant3",
"study1",
"gene1",
"positive",
), # in diff locus as sl1 and pointing to same gene, has to be kept
(
4,
"variant4",
"study1",
"gene2",
"positive",
), # in same locus as sl1 and pointing to diff gene, has to be kept
],
"studyLocusId LONG, variantId STRING, geneId STRING, goldStandardSet STRING",
"studyLocusId LONG, variantId STRING, studyId STRING, geneId STRING, goldStandardSet STRING",
)

mock_sl_overlap_df = spark.createDataFrame(
Expand All @@ -70,11 +73,11 @@ def test_filter_unique_associations(spark: SparkSession) -> None:

expected_df = spark.createDataFrame(
[
(1, "variant1", "gene1", "positive"),
(3, "variant3", "gene1", "positive"),
(4, "variant4", "gene2", "positive"),
(1, "variant1", "study1", "gene1", "positive"),
(3, "variant3", "study1", "gene1", "positive"),
(4, "variant4", "study1", "gene2", "positive"),
],
"studyLocusId LONG, variantId STRING, geneId STRING, goldStandardSet STRING",
"studyLocusId LONG, variantId STRING, studyId STRING, geneId STRING, goldStandardSet STRING",
)

mock_l2g_gs = L2GGoldStandard(
Expand All @@ -93,27 +96,30 @@ def test_remove_false_negatives(spark: SparkSession) -> None:
"""Test `remove_false_negatives`."""
mock_l2g_gs_df = spark.createDataFrame(
[
(1, "variant1", "gene1", "positive"),
(1, "variant1", "study1", "gene1", "positive"),
(
2,
"variant2",
"study1",
"gene2",
"negative",
), # gene2 is a partner of gene1, has to be dropped
(
3,
"variant3",
"study1",
"gene3",
"negative",
), # gene 3 is not a partner of gene1, has to be kept
(
4,
"variant4",
"study1",
"gene4",
"positive",
), # gene 4 is a partner of gene1, has to be kept because it's positive
],
"studyLocusId LONG, variantId STRING, geneId STRING, goldStandardSet STRING",
"studyLocusId LONG, variantId STRING, studyId STRING, geneId STRING, goldStandardSet STRING",
)

mock_interactions_df = spark.createDataFrame(
Expand All @@ -127,11 +133,11 @@ def test_remove_false_negatives(spark: SparkSession) -> None:

expected_df = spark.createDataFrame(
[
(1, "variant1", "gene1", "positive"),
(3, "variant3", "gene3", "negative"),
(4, "variant4", "gene4", "positive"),
(1, "variant1", "study1", "gene1", "positive"),
(3, "variant3", "study1", "gene3", "negative"),
(4, "variant4", "study1", "gene4", "positive"),
],
"studyLocusId LONG, variantId STRING, geneId STRING, goldStandardSet STRING",
"studyLocusId LONG, variantId STRING, studyId STRING, geneId STRING, goldStandardSet STRING",
)

mock_l2g_gs = L2GGoldStandard(
Expand Down