pheval 0.5.0__tar.gz → 0.5.1__tar.gz

{pheval-0.5.0 → pheval-0.5.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: pheval
-Version: 0.5.0
+Version: 0.5.1
 Summary: 
 Author: Yasemin Bridges
 Author-email: y.bridges@qmul.ac.uk

{pheval-0.5.0 → pheval-0.5.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "pheval"
-version = "0.5.0"
+version = "0.5.1"
 description = ""
 authors = ["Yasemin Bridges <y.bridges@qmul.ac.uk>",
   "Julius Jacobsen <j.jacobsen@qmul.ac.uk>",

{pheval-0.5.0 → pheval-0.5.1}/src/pheval/post_processing/phenopacket_truth_set.py

@@ -12,6 +12,18 @@ from pheval.utils.phenopacket_utils import (
 )
 
 
+def calculate_end_pos(variant_start: int, variant_ref: str) -> int:
+    """Calculate the end position for a variant
+    Args:
+        variant_start (int): The start position of the variant
+        variant_ref (str): The reference allele of the variant
+
+    Returns:
+        int: The end position of the variant
+    """
+    return variant_start + len(variant_ref) - 1
+
+
 class PhenopacketTruthSet:
     """Class for finding the causative gene/disease/variant from a phenopacket"""
 
@@ -139,13 +151,14 @@ class PhenopacketTruthSet:
         return pl.DataFrame(
             {
                 "chrom": [v.chrom for v in variants],
-                "pos": [v.pos for v in variants],
+                "start": [v.pos for v in variants],
+                "end": [calculate_end_pos(v.pos, v.ref) for v in variants],
                 "ref": [v.ref for v in variants],
                 "alt": [v.alt for v in variants],
             }
         ).with_columns(
             [
-                pl.concat_str(["chrom", "pos", "ref", "alt"], separator="-").alias("variant_id"),
+                pl.concat_str(["chrom", "start", "ref", "alt"], separator="-").alias("variant_id"),
                 pl.lit(0.0).cast(pl.Float64).alias("score"),
                 pl.lit(0).cast(pl.Int64).alias("rank"),
                 pl.lit(True).alias("true_positive"),
@@ -166,10 +179,10 @@ class PhenopacketTruthSet:
         return (
             ranked_results.with_columns(
                 [
-                    pl.struct(["chrom", "pos", "ref", "alt"])
+                    pl.struct(["chrom", "start", "end", "ref", "alt"])
                     .is_in(
                         classified_results.select(
-                            pl.struct(["chrom", "pos", "ref", "alt"])
+                            pl.struct(["chrom", "start", "end", "ref", "alt"])
                         ).to_series()
                     )
                     .alias("true_positive")
@@ -179,8 +192,10 @@ class PhenopacketTruthSet:
             .select(classified_results.columns)
             .vstack(
                 classified_results.filter(
-                    ~pl.struct(["chrom", "pos", "ref", "alt"]).is_in(
-                        ranked_results.select(pl.struct(["chrom", "pos", "ref", "alt"])).to_series()
+                    ~pl.struct(["chrom", "start", "end", "ref", "alt"]).is_in(
+                        ranked_results.select(
+                            pl.struct(["chrom", "start", "end", "ref", "alt"])
+                        ).to_series()
                     )
                 )
             )

{pheval-0.5.0 → pheval-0.5.1}/src/pheval/post_processing/post_processing.py

@@ -22,18 +22,6 @@ class ResultType(Enum):
     VARIANT = "variant"
 
 
-def calculate_end_pos(variant_start: int, variant_ref: str) -> int:
-    """Calculate the end position for a variant
-    Args:
-        variant_start (int): The start position of the variant
-        variant_ref (str): The reference allele of the variant
-
-    Returns:
-        int: The end position of the variant
-    """
-    return variant_start + len(variant_ref) - 1
-
-
 class SortOrder(Enum):
     """Enumeration representing sorting orders."""
 
@@ -106,7 +94,7 @@ def _write_variant_result(ranked_results: pl.DataFrame, output_file: Path) -> No
         output_file (Path): Path to the output file.
     """
     variant_output = ranked_results.select(
-        ["rank", "score", "chromosome", "start", "end", "ref", "alt", "variant_id", "true_positive"]
+        ["rank", "score", "chrom", "start", "end", "ref", "alt", "variant_id", "true_positive"]
     )
     _write_results_file(output_file, variant_output)
 
@@ -119,9 +107,7 @@ def _write_disease_result(ranked_results: pl.DataFrame, output_file: Path) -> No
         ranked_results ([PhEvalResult]): List of ranked PhEval disease results.
         output_file (Path): Path to the output file.
     """
-    disease_output = ranked_results.select(
-        ["rank", "score", "disease_name", "disease_identifier", "true_positive"]
-    )
+    disease_output = ranked_results.select(["rank", "score", "disease_identifier", "true_positive"])
     _write_results_file(output_file, disease_output)
 
 
@@ -228,7 +214,7 @@ def generate_variant_result(
         phenopacket_dir, output_dir.joinpath("pheval_variant_results"), ResultType.VARIANT
     )
     ranked_results = _rank_results(results, sort_order).with_columns(
-        pl.concat_str(["chrom", "pos", "ref", "alt"], separator="-").alias("variant_id")
+        pl.concat_str(["chrom", "start", "ref", "alt"], separator="-").alias("variant_id")
     )
     classified_results = PhenopacketTruthSet(phenopacket_dir).merge_variant_results(
         ranked_results, output_file

{pheval-0.5.0 → pheval-0.5.1}/src/pheval/post_processing/validate_result_format.py

@@ -35,18 +35,17 @@ class ResultSchema(Enum):
     )
     DISEASE_RESULT_SCHEMA = pl.Schema(
         {
-            "disease_name": pl.String,
             "disease_identifier": pl.String,
             "score": pl.Float64,
             "grouping_id": pl.Utf8,
         }
     )
 
-    def validate(self, df: pl.DataFrame) -> bool:
+    def validate(self, results: pl.DataFrame) -> bool:
         """
         Validate that a DataFrame follows the expected schema.
         Args:
-            df (pl.DataFrame): The DataFrame to validate.
+            results (pl.DataFrame): The DataFrame to validate.
         Raises:
             ValueError: If a required column is missing or the grouping_id column contains a null value.
             TypeError: If a column exists but has an incorrect data type.
@@ -55,18 +54,18 @@ class ResultSchema(Enum):
         """
         expected_schema = self.value
 
-        if "grouping_id" in df.columns and df["grouping_id"].null_count() > 0:
+        if "grouping_id" in results.columns and results["grouping_id"].null_count() > 0:
             raise ValueError("'grouping_id' column should not contain null values if provided.")
 
         for col_name, expected_type in expected_schema.items():
-            if col_name not in df.schema:
+            if col_name not in results.schema:
                 if col_name == "grouping_id":
                     continue
                 raise ValueError(f"Missing required column: {col_name}")
 
-            if df.schema[col_name] != expected_type:
+            if results.schema[col_name] != expected_type:
                 raise TypeError(
-                    f"Column '{col_name}' has type {df.schema[col_name]}, expected {expected_type}"
+                    f"Column '{col_name}' has type {results.schema[col_name]}, expected {expected_type}"
                 )
 
         return True
@@ -83,9 +82,9 @@ def validate_dataframe(schema: ResultSchema) -> Callable:
 
     def decorator(func: Callable) -> Callable:
         @wraps(func)
-        def wrapper(df: pl.DataFrame, *args, **kwargs):
-            schema.validate(df)
-            return func(df, *args, **kwargs)
+        def wrapper(results: pl.DataFrame, *args, **kwargs):
+            schema.validate(results)
+            return func(results, *args, **kwargs)
 
         return wrapper