fix(eqtl): correct pattern that extracts geneid in study index

opentargets · Dec 21, 2023 · 14e9f65 · 14e9f65 · ireneisdoomed · Dec 21, 2023
1 parent 3e372a4
commit 14e9f65
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/src/otg/datasource/eqtl_catalogue/study_index.py b/src/otg/datasource/eqtl_catalogue/study_index.py
@@ -160,7 +160,7 @@ def add_gene_to_study_id(
             # Explode the list of full study IDs into separate rows
             .withColumn("studyId", f.explode("fullStudyIdList"))
             # Add geneId column
-            .withColumn("geneId", f.regexp_extract(f.col("studyId"), r"(.*)_[^_]+", 1))
+            .withColumn("geneId", f.regexp_extract(f.col("studyId"), r"([^_]+)$", 1))
             .drop("fullStudyIdList")
         )
         return StudyIndex(_df=study_index_df, _schema=StudyIndex.get_schema())