Merge branch 'main' into 317-add-arguments-hg19-vcf-dir-and-hg38-vcf-…

…dir-to-spike-vcf-command

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "pheval"
-version = "0.3.3"
+version = "0.3.7"
 description = ""
 authors = ["Yasemin Bridges <[email protected]>",
   "Julius Jacobsen <[email protected]>",

src/pheval/analyse/disease_prioritisation_analysis.py

@@ -10,11 +10,7 @@
 from pheval.analyse.rank_stats import RankStats
 from pheval.analyse.run_data_parser import TrackInputOutputDirectories
 from pheval.post_processing.post_processing import RankedPhEvalDiseaseResult
-from pheval.utils.file_utils import (
-    all_files,
-    files_with_suffix,
-    obtain_phenopacket_path_from_pheval_result,
-)
+from pheval.utils.file_utils import all_files
 from pheval.utils.phenopacket_utils import PhenopacketUtil, ProbandDisease, phenopacket_reader
 
 
@@ -217,7 +213,7 @@ def _obtain_causative_diseases(phenopacket_path: Path) -> List[ProbandDisease]:
 
 
 def assess_phenopacket_disease_prioritisation(
-    standardised_disease_result: Path,
+    phenopacket_path: Path,
     score_order: str,
     results_dir_and_input: TrackInputOutputDirectories,
     threshold: float,
@@ -230,16 +226,16 @@ def assess_phenopacket_disease_prioritisation(
     against the recorded causative diseases for a proband in the Phenopacket.
 
     Args:
-        standardised_disease_result (Path): Path to the PhEval standardised disease result file.
+        phenopacket_path (Path): Path to the Phenopacket.
         score_order (str): The order in which scores are arranged, either ascending or descending.
         results_dir_and_input (TrackInputOutputDirectories): Input and output directories.
         threshold (float): Threshold for assessment.
         disease_rank_stats (RankStats): RankStats class instance.
         disease_rank_comparison (defaultdict): Default dictionary for disease rank comparisons.
         disease_binary_classification_stats (BinaryClassificationStats): BinaryClassificationStats class instance.
     """
-    phenopacket_path = obtain_phenopacket_path_from_pheval_result(
-        standardised_disease_result, all_files(results_dir_and_input.phenopacket_dir)
+    standardised_disease_result = results_dir_and_input.results_dir.joinpath(
+        f"pheval_disease_results/{phenopacket_path.stem}-pheval_disease_result.tsv"
     )
     pheval_disease_result = read_standardised_result(standardised_disease_result)
     proband_diseases = _obtain_causative_diseases(phenopacket_path)
@@ -276,12 +272,9 @@ def benchmark_disease_prioritisation(
     """
     disease_rank_stats = RankStats()
     disease_binary_classification_stats = BinaryClassificationStats()
-    for standardised_result in files_with_suffix(
-        results_directory_and_input.results_dir.joinpath("pheval_disease_results/"),
-        ".tsv",
-    ):
+    for phenopacket_path in all_files(results_directory_and_input.phenopacket_dir):
         assess_phenopacket_disease_prioritisation(
-            standardised_result,
+            phenopacket_path,
             score_order,
             results_directory_and_input,
             threshold,

src/pheval/analyse/gene_prioritisation_analysis.py

@@ -10,11 +10,7 @@
 from pheval.analyse.rank_stats import RankStats
 from pheval.analyse.run_data_parser import TrackInputOutputDirectories
 from pheval.post_processing.post_processing import RankedPhEvalGeneResult
-from pheval.utils.file_utils import (
-    all_files,
-    files_with_suffix,
-    obtain_phenopacket_path_from_pheval_result,
-)
+from pheval.utils.file_utils import all_files
 from pheval.utils.phenopacket_utils import PhenopacketUtil, ProbandCausativeGene, phenopacket_reader
 
 
@@ -209,7 +205,7 @@ def _obtain_causative_genes(phenopacket_path: Path) -> List[ProbandCausativeGene
 
 
 def assess_phenopacket_gene_prioritisation(
-    standardised_gene_result: Path,
+    phenopacket_path: Path,
     score_order: str,
     results_dir_and_input: TrackInputOutputDirectories,
     threshold: float,
@@ -222,16 +218,16 @@ def assess_phenopacket_gene_prioritisation(
     against the recorded causative genes for a proband in the Phenopacket.
 
     Args:
-        standardised_gene_result (Path): Path to the PhEval standardised gene result file.
+        phenopacket_path (Path): Path to the Phenopacket.
         score_order (str): The order in which scores are arranged, either ascending or descending.
         results_dir_and_input (TrackInputOutputDirectories): Input and output directories.
         threshold (float): Threshold for assessment.
         gene_rank_stats (RankStats): RankStats class instance.
         gene_rank_comparison (defaultdict): Default dictionary for gene rank comparisons.
         gene_binary_classification_stats (BinaryClassificationStats): BinaryClassificationStats class instance.
     """
-    phenopacket_path = obtain_phenopacket_path_from_pheval_result(
-        standardised_gene_result, all_files(results_dir_and_input.phenopacket_dir)
+    standardised_gene_result = results_dir_and_input.results_dir.joinpath(
+        f"pheval_gene_results/{phenopacket_path.stem}-pheval_gene_result.tsv"
     )
     pheval_gene_result = read_standardised_result(standardised_gene_result)
     proband_causative_genes = _obtain_causative_genes(phenopacket_path)
@@ -266,11 +262,9 @@ def benchmark_gene_prioritisation(
     """
     gene_rank_stats = RankStats()
     gene_binary_classification_stats = BinaryClassificationStats()
-    for standardised_result in files_with_suffix(
-        results_directory_and_input.results_dir.joinpath("pheval_gene_results/"), ".tsv"
-    ):
+    for phenopacket_path in all_files(results_directory_and_input.phenopacket_dir):
         assess_phenopacket_gene_prioritisation(
-            standardised_result,
+            phenopacket_path,
             score_order,
             results_directory_and_input,
             threshold,

src/pheval/analyse/parse_pheval_result.py

@@ -1,10 +1,13 @@
+import logging
 from pathlib import Path
 from typing import List
 
 import pandas as pd
 
 from pheval.post_processing.post_processing import PhEvalResult
 
+info_log = logging.getLogger("info")
+
 
 def read_standardised_result(standardised_result_path: Path) -> List[dict]:
     """
@@ -16,7 +19,11 @@ def read_standardised_result(standardised_result_path: Path) -> List[dict]:
     Returns:
         List[dict]: A list of dictionaries representing the content of the standardised result file.
     """
-    return pd.read_csv(standardised_result_path, delimiter="\t").to_dict("records")
+    if standardised_result_path.is_file():
+        return pd.read_csv(standardised_result_path, delimiter="\t").to_dict("records")
+    else:
+        info_log.info(f"Could not find {standardised_result_path}")
+        return pd.DataFrame().to_dict("records")
 
 
 def parse_pheval_result(

src/pheval/analyse/variant_prioritisation_analysis.py

@@ -10,11 +10,7 @@
 from pheval.analyse.rank_stats import RankStats
 from pheval.analyse.run_data_parser import TrackInputOutputDirectories
 from pheval.post_processing.post_processing import RankedPhEvalVariantResult
-from pheval.utils.file_utils import (
-    all_files,
-    files_with_suffix,
-    obtain_phenopacket_path_from_pheval_result,
-)
+from pheval.utils.file_utils import all_files
 from pheval.utils.phenopacket_utils import GenomicVariant, PhenopacketUtil, phenopacket_reader
 
 
@@ -211,7 +207,7 @@ def _obtain_causative_variants(phenopacket_path: Path) -> List[GenomicVariant]:
 
 
 def assess_phenopacket_variant_prioritisation(
-    standardised_variant_result: Path,
+    phenopacket_path: Path,
     score_order: str,
     results_dir_and_input: TrackInputOutputDirectories,
     threshold: float,
@@ -224,18 +220,18 @@ def assess_phenopacket_variant_prioritisation(
     against the recorded causative variants for a proband in the Phenopacket.
 
     Args:
-        standardised_variant_result (Path): Path to the PhEval standardised variant result file.
+        phenopacket_path (Path): Path to the Phenopacket.
         score_order (str): The order in which scores are arranged, either ascending or descending.
         results_dir_and_input (TrackInputOutputDirectories): Input and output directories.
         threshold (float): Threshold for assessment.
         variant_rank_stats (RankStats): RankStats class instance.
         variant_rank_comparison (defaultdict): Default dictionary for variant rank comparisons.
         variant_binary_classification_stats (BinaryClassificationStats): BinaryClassificationStats class instance.
     """
-    phenopacket_path = obtain_phenopacket_path_from_pheval_result(
-        standardised_variant_result, all_files(results_dir_and_input.phenopacket_dir)
-    )
     proband_causative_variants = _obtain_causative_variants(phenopacket_path)
+    standardised_variant_result = results_dir_and_input.results_dir.joinpath(
+        f"pheval_variant_results/{phenopacket_path.stem}-pheval_variant_result.tsv"
+    )
     pheval_variant_result = read_standardised_result(standardised_variant_result)
     AssessVariantPrioritisation(
         phenopacket_path,
@@ -270,12 +266,9 @@ def benchmark_variant_prioritisation(
     """
     variant_rank_stats = RankStats()
     variant_binary_classification_stats = BinaryClassificationStats()
-    for standardised_result in files_with_suffix(
-        results_directory_and_input.results_dir.joinpath("pheval_variant_results/"),
-        ".tsv",
-    ):
+    for phenopacket_path in all_files(results_directory_and_input.phenopacket_dir):
         assess_phenopacket_variant_prioritisation(
-            standardised_result,
+            phenopacket_path,
             score_order,
             results_directory_and_input,
             threshold,