fix(l2g): remove custom session params + other fixes (#841)

* chore: delete l2g custom spark session * fix: add neighbourhood features in `LocusToGeneFeatureMatrixConfig` * fix(feature_matrix): use right config for default values
opentargets · Oct 14, 2024 · 6817aad · 6817aad
1 parent d461e38
commit 6817aad
Show file tree

Hide file tree

Showing 2 changed files with 11 additions and 14 deletions.
diff --git a/src/gentropy/config.py b/src/gentropy/config.py
@@ -222,16 +222,7 @@ class LDBasedClumpingConfig(StepConfig):
 class LocusToGeneConfig(StepConfig):
     """Locus to gene step configuration."""
 
-    session: Any = field(
-        default_factory=lambda: {
-            "extended_spark_conf": {
-                "spark.dynamicAllocation.enabled": "false",
-                "spark.driver.memory": "48g",
-                "spark.executor.memory": "48g",
-                "spark.sql.shuffle.partitions": "800",
-            }
-        }
-    )
+    session: Any = field(default_factory=lambda: {"extended_spark_conf": None})
     run_mode: str = MISSING
     predictions_path: str = MISSING
     credible_set_path: str = MISSING
@@ -313,12 +304,18 @@ class LocusToGeneFeatureMatrixConfig(StepConfig):
             "eQtlColocClppMaximum",
             "pQtlColocClppMaximum",
             "sQtlColocClppMaximum",
-            "tuQtlColocClppMaximum",
             # max H4 for each (study, locus, gene) aggregating over a specific qtl type
             "eQtlColocH4Maximum",
             "pQtlColocH4Maximum",
             "sQtlColocH4Maximum",
-            "tuQtlColocH4Maximum",
+            # max CLPP for each (study, locus, gene) aggregating over a specific qtl type and in relation with the mean in the vicinity
+            "eQtlColocClppMaximumNeighbourhood",
+            "pQtlColocClppMaximumNeighbourhood",
+            "sQtlColocClppMaximumNeighbourhood",
+            # max H4 for each (study, locus, gene) aggregating over a specific qtl type and in relation with the mean in the vicinity
+            "eQtlColocH4MaximumNeighbourhood",
+            "pQtlColocH4MaximumNeighbourhood",
+            "sQtlColocH4MaximumNeighbourhood",
             # distance to gene footprint
             "distanceSentinelFootprint",
             "distanceSentinelFootprintNeighbourhood",

diff --git a/src/gentropy/l2g.py b/src/gentropy/l2g.py
@@ -10,7 +10,7 @@
 
 from gentropy.common.session import Session
 from gentropy.common.utils import access_gcp_secret
-from gentropy.config import LocusToGeneConfig
+from gentropy.config import LocusToGeneConfig, LocusToGeneFeatureMatrixConfig
 from gentropy.dataset.colocalisation import Colocalisation
 from gentropy.dataset.gene_index import GeneIndex
 from gentropy.dataset.l2g_feature_matrix import L2GFeatureMatrix
@@ -31,7 +31,7 @@ def __init__(
         self,
         session: Session,
         *,
-        features_list: list[str] = LocusToGeneConfig().features_list,
+        features_list: list[str] = LocusToGeneFeatureMatrixConfig().features_list,
         credible_set_path: str,
         variant_index_path: str | None = None,
         colocalisation_path: str | None = None,