refactor: rename inSilicoPredictors to variantEffect in merged files

opentargets · Feb 10, 2025 · 89e1785 · 89e1785
1 parent 597cf05
commit 89e1785
Show file tree

Hide file tree

Showing 3 changed files with 20 additions and 20 deletions.
diff --git a/src/gentropy/assets/schemas/amino_acid_variants.json b/src/gentropy/assets/schemas/amino_acid_variants.json
@@ -14,7 +14,7 @@
     },
     {
       "metadata": {},
-      "name": "inSilicoPredictors",
+      "name": "variantEffect",
       "nullable": true,
       "type": {
         "containsNull": true,

diff --git a/src/gentropy/dataset/variant_index.py b/src/gentropy/dataset/variant_index.py
@@ -284,15 +284,15 @@ def get_distance_to_gene(
     def annotate_with_amino_acid_consequences(
         self: VariantIndex, annotation: AminoAcidVariants
     ) -> VariantIndex:
-        """Enriching in silico predictors with amino-acid derived predicted consequences.
+        """Enriching variant effect assessments with amino-acid derived predicted consequences.
 
         Args:
             annotation (AminoAcidVariants): amio-acid level variant consequences.
 
         Returns:
             VariantIndex: where amino-acid causing variants are enriched with extra annotation
         """
-        w = Window.partitionBy("variantId").orderBy(f.size("inSilicoPredictors").desc())
+        w = Window.partitionBy("variantId").orderBy(f.size("variantEffect").desc())
 
         return VariantIndex(
             _df=self.df
@@ -313,17 +313,17 @@ def annotate_with_amino_acid_consequences(
             )
             # Joining with amino-acid predictions:
             .join(
-                annotation.df.withColumnRenamed("inSilicoPredictors", "annotations"),
+                annotation.df.withColumnRenamed("variantEffect", "annotations"),
                 on=["uniprotAccession", "aminoAcidChange"],
                 how="left",
             )
             # Merge predictors:
             .withColumn(
-                "inSilicoPredictors",
+                "variantEffect",
                 f.when(
                     f.col("annotations").isNotNull(),
-                    f.array_union("inSilicoPredictors", "annotations"),
-                ).otherwise(f.col("inSilicoPredictors")),
+                    f.array_union("variantEffect", "annotations"),
+                ).otherwise(f.col("variantEffect")),
             )
             # Dropping unused columns:
             .drop("uniprotAccession", "aminoAcidChange", "annotations")
@@ -460,7 +460,7 @@ def _rescaleColumnValue(
 
     @classmethod
     def _normalise_foldx(
-        cls: type[InSilicoPredictorNormaliser], score: Column
+        cls: type[VariantEffectNormaliser], score: Column
     ) -> Column:
         """Normalise FoldX ddG energies.
 

diff --git a/src/gentropy/datasource/open_targets/foldex_integration.py b/src/gentropy/datasource/open_targets/foldex_integration.py
@@ -8,26 +8,26 @@
 
 from gentropy.common.spark_helpers import enforce_schema
 from gentropy.dataset.amino_acid_variants import AminoAcidVariants
-from gentropy.dataset.variant_index import InSilicoPredictorNormaliser
+from gentropy.dataset.variant_index import VariantEffectNormaliser
 
 
 class OpenTargetsFoldX:
     """Class to parser FoldX dataset generated by the OTAR2081 project."""
 
-    INSILICO_SCHEMA = AminoAcidVariants.get_schema()[
-        "inSilicoPredictors"
+    VARIANT_EFFECT_SCHEMA = AminoAcidVariants.get_schema()[
+        "variantEffect"
     ].dataType.elementType
 
     @staticmethod
-    @enforce_schema(INSILICO_SCHEMA)
+    @enforce_schema(VARIANT_EFFECT_SCHEMA)
     def get_foldx_prediction(score_column: Column) -> Column:
-        """Generate inSilicoPredictor object from ddG column.
+        """Generate variantEffect object from ddG column.
 
         Args:
             score_column (Column): ddG column from the FoldX dataset.
 
         Returns:
-            Column: struct with the right shape of the in silico predictors.
+            Column: struct with the right shape of the variantEffect field.
         """
         return f.struct(
             f.lit("FoldX").alias("method"),
@@ -58,21 +58,21 @@ def ingest_foldx_data(
                         f.col("wild_type"), f.col("position"), f.col("mutated_type")
                     ).alias("aminoAcidChange"),
                     cls.get_foldx_prediction(f.col("foldx_ddg")).alias(
-                        "inSilicoPredictor"
+                        "foldx_prediction"
                     ),
                 )
                 # Collapse all predictors for a single array object to avoid variant explosions:
                 .groupBy("uniprotAccession", "aminoAcidChange")
                 .agg(
-                    f.collect_set(f.col("inSilicoPredictor")).alias(
-                        "inSilicoPredictors"
+                    f.collect_set(f.col("fold_prediction")).alias(
+                        "variantEffect"
                     )
                 )
                 # Normalise FoldX free energy changes:
                 .withColumn(
-                    "inSilicoPredictors",
-                    InSilicoPredictorNormaliser.normalise_in_silico_predictors(
-                        f.col("inSilicoPredictors")
+                    "variantEffect",
+                    VariantEffectNormaliser.normalise_variant_effect(
+                        f.col("variantEffect")
                     ),
                 )
             ),