pheval 0.3.5__py3-none-any.whl → 0.3.7__py3-none-any.whl

pheval/analyse/disease_prioritisation_analysis.py

@@ -10,11 +10,7 @@ from pheval.analyse.prioritisation_result_types import DiseasePrioritisationResu
 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,
@@ -230,7 +226,7 @@ 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.
@@ -238,8 +234,8 @@ def assess_phenopacket_disease_prioritisation(
         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,

pheval/analyse/gene_prioritisation_analysis.py

@@ -10,11 +10,7 @@ from pheval.analyse.prioritisation_result_types import GenePrioritisationResult
 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,
@@ -222,7 +218,7 @@ 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.
@@ -230,8 +226,8 @@ def assess_phenopacket_gene_prioritisation(
         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,

pheval/analyse/parse_pheval_result.py

@@ -1,3 +1,4 @@
+import logging
 from pathlib import Path
 from typing import List
 
@@ -5,6 +6,8 @@ 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(

pheval/analyse/variant_prioritisation_analysis.py

@@ -10,11 +10,7 @@ from pheval.analyse.prioritisation_result_types import VariantPrioritisationResu
 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,
@@ -224,7 +220,7 @@ 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.
@@ -232,10 +228,10 @@ def assess_phenopacket_variant_prioritisation(
         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,

pheval/post_processing/post_processing.py

@@ -227,68 +227,7 @@ class ResultSorter:
         )
 
 
-class ScoreRanker:
-    """
-    Class for ranking scores based on a given sort order
-
-    Attributes:
-       rank (int): Represents the current rank, initialised with 0
-       current_score (float): Represents the current score, initialised with positive infinity (float("inf"))
-       count (int): Used for counting, initialised with 0
-    """
-
-    rank: int = 0
-    current_score: float = float("inf")
-    count: int = 0
-
-    def __init__(self, sort_order: SortOrder):
-        """
-        Initialise ScoreRanker
-
-        Args:
-            sort_order (SortOrder): Sorting order to be applied
-        """
-        self.sort_order = sort_order
-
-    def _check_rank_order(self, round_score: float) -> None:
-        """
-        Check if the results are correctly ordered
-
-        Args:
-            round_score (float): Score to be checked against the current score
-
-        Raises:
-            ValueError: If results are not correctly sorted.
-        """
-        if self.sort_order == SortOrder.ASCENDING and round_score < self.current_score != float(
-            "inf"
-        ):
-            raise ValueError("Results are not correctly sorted!")
-        elif self.sort_order == SortOrder.DESCENDING and round_score > self.current_score != float(
-            "inf"
-        ):
-            raise ValueError("Results are not correctly sorted!")
-
-    def rank_scores(self, round_score: float) -> int:
-        """
-        Add ranks to a result; equal scores are given the same rank, e.g., 1, 1, 3
-
-        Args:
-            round_score (float): Score to be ranked
-
-        Returns:
-            int: Rank assigned to the score
-        """
-        self._check_rank_order(round_score)
-        self.count += 1
-        if self.current_score == round_score:
-            return self.rank
-        self.current_score = round_score
-        self.rank = self.count
-        return self.rank
-
-
-def _rank_pheval_result(pheval_result: [PhEvalResult], sort_order: SortOrder) -> [PhEvalResult]:
+def _rank_pheval_result(pheval_result: [PhEvalResult], sort_order: SortOrder) -> pd.DataFrame:
     """
     Rank PhEval results post-processed from tool-specific output, managing tied scores (ex aequo)
 
@@ -297,35 +236,17 @@ def _rank_pheval_result(pheval_result: [PhEvalResult], sort_order: SortOrder) ->
         sort_order (SortOrder): Sorting order based on which ranking is performed
 
     Returns:
-        List[PhEvalResult]: Ranked PhEval results with tied scores managed
+        pd.DataFrame : Ranked PhEval results with tied scores managed
 
     Raises:
         ValueError: If an incompatible PhEval result type is encountered
     """
-    score_ranker = ScoreRanker(sort_order)
-    ranked_result = []
-    for result in pheval_result:
-        if type(result) == PhEvalGeneResult:
-            ranked_result.append(
-                RankedPhEvalGeneResult.from_gene_result(
-                    result, score_ranker.rank_scores(result.score)
-                )
-            )
-        elif type(result) == PhEvalVariantResult:
-            ranked_result.append(
-                RankedPhEvalVariantResult.from_variant_result(
-                    result, score_ranker.rank_scores(result.score)
-                )
-            )
-        elif type(result) == PhEvalDiseaseResult:
-            ranked_result.append(
-                RankedPhEvalDiseaseResult.from_disease_result(
-                    result, score_ranker.rank_scores(result.score)
-                )
-            )
-        else:
-            raise ValueError("Incompatible PhEval result type.")
-    return ranked_result
+    pheval_result_df = pd.DataFrame([data.__dict__ for data in pheval_result])
+    if sort_order == SortOrder.ASCENDING:
+        pheval_result_df["rank"] = pheval_result_df["score"].rank(method="max", ascending=True)
+    elif sort_order == SortOrder.DESCENDING:
+        pheval_result_df["rank"] = pheval_result_df["score"].rank(method="max", ascending=False)
+    return pheval_result_df
 
 
 def _return_sort_order(sort_order_str: str) -> SortOrder:
@@ -347,7 +268,7 @@ def _return_sort_order(sort_order_str: str) -> SortOrder:
         raise ValueError("Incompatible ordering method specified.")
 
 
-def _create_pheval_result(pheval_result: [PhEvalResult], sort_order_str: str) -> [PhEvalResult]:
+def _create_pheval_result(pheval_result: [PhEvalResult], sort_order_str: str) -> pd.DataFrame:
     """
     Create PhEval results with corresponding ranks based on the specified sorting order.
 
@@ -356,7 +277,7 @@ def _create_pheval_result(pheval_result: [PhEvalResult], sort_order_str: str) ->
         sort_order_str (str): String representation of the desired sorting order.
 
     Returns:
-        List[PhEvalResult]: PhEval results with ranks assigned.
+       pd.DataFrame: PhEval results with ranks assigned.
     """
     sort_order = _return_sort_order(sort_order_str)
     sorted_pheval_result = ResultSorter(pheval_result, sort_order).sort_pheval_results()
@@ -364,7 +285,7 @@ def _create_pheval_result(pheval_result: [PhEvalResult], sort_order_str: str) ->
 
 
 def _write_pheval_gene_result(
-    ranked_pheval_result: [PhEvalResult], output_dir: Path, tool_result_path: Path
+    ranked_pheval_result: pd.DataFrame, output_dir: Path, tool_result_path: Path
 ) -> None:
     """
     Write ranked PhEval gene results to a TSV file
@@ -374,8 +295,9 @@ def _write_pheval_gene_result(
         output_dir (Path): Path to the output directory
         tool_result_path (Path): Path to the tool-specific result file
     """
-    ranked_result = pd.DataFrame([data.__dict__ for data in ranked_pheval_result])
-    pheval_gene_output = ranked_result.loc[:, ["rank", "score", "gene_symbol", "gene_identifier"]]
+    pheval_gene_output = ranked_pheval_result.loc[
+        :, ["rank", "score", "gene_symbol", "gene_identifier"]
+    ]
     pheval_gene_output.to_csv(
         output_dir.joinpath(
             "pheval_gene_results/" + tool_result_path.stem + "-pheval_gene_result.tsv"
@@ -386,7 +308,7 @@ def _write_pheval_gene_result(
 
 
 def _write_pheval_variant_result(
-    ranked_pheval_result: [PhEvalResult], output_dir: Path, tool_result_path: Path
+    ranked_pheval_result: pd.DataFrame, output_dir: Path, tool_result_path: Path
 ) -> None:
     """
     Write ranked PhEval variant results to a TSV file
@@ -396,8 +318,7 @@ def _write_pheval_variant_result(
         output_dir (Path): Path to the output directory
         tool_result_path (Path): Path to the tool-specific result file
     """
-    ranked_result = pd.DataFrame([data.__dict__ for data in ranked_pheval_result])
-    pheval_variant_output = ranked_result.loc[
+    pheval_variant_output = ranked_pheval_result.loc[
         :, ["rank", "score", "chromosome", "start", "end", "ref", "alt"]
     ]
     pheval_variant_output.to_csv(
@@ -410,7 +331,7 @@ def _write_pheval_variant_result(
 
 
 def _write_pheval_disease_result(
-    ranked_pheval_result: [RankedPhEvalDiseaseResult], output_dir: Path, tool_result_path: Path
+    ranked_pheval_result: pd.DataFrame, output_dir: Path, tool_result_path: Path
 ) -> None:
     """
     Write ranked PhEval disease results to a TSV file
@@ -420,8 +341,7 @@ def _write_pheval_disease_result(
         output_dir (Path): Path to the output directory
         tool_result_path (Path): Path to the tool-specific result file
     """
-    ranked_result = pd.DataFrame([data.__dict__ for data in ranked_pheval_result])
-    pheval_disease_output = ranked_result.loc[
+    pheval_disease_output = ranked_pheval_result.loc[
         :, ["rank", "score", "disease_name", "disease_identifier"]
     ]
     pheval_disease_output.to_csv(
@@ -455,11 +375,11 @@ def generate_pheval_result(
         info_log.warning(f"No results found for {tool_result_path.name}")
         return
     ranked_pheval_result = _create_pheval_result(pheval_result, sort_order_str)
-    if all(isinstance(result, RankedPhEvalGeneResult) for result in ranked_pheval_result):
+    if all(isinstance(result, PhEvalGeneResult) for result in pheval_result):
         _write_pheval_gene_result(ranked_pheval_result, output_dir, tool_result_path)
-    elif all(isinstance(result, RankedPhEvalVariantResult) for result in ranked_pheval_result):
+    elif all(isinstance(result, PhEvalVariantResult) for result in pheval_result):
         _write_pheval_variant_result(ranked_pheval_result, output_dir, tool_result_path)
-    elif all(isinstance(result, RankedPhEvalDiseaseResult) for result in ranked_pheval_result):
+    elif all(isinstance(result, PhEvalDiseaseResult) for result in pheval_result):
         _write_pheval_disease_result(ranked_pheval_result, output_dir, tool_result_path)
     else:
         raise ValueError("Results are not all of the same type.")

pheval/prepare/create_spiked_vcf.py

@@ -328,22 +328,35 @@ class VcfSpiker:
             genotype_codes[proband_variant_data.genotype.lower()] + "\n",
         ]
 
-    def construct_vcf_records(self) -> List[str]:
+    def construct_vcf_records(self, template_vcf_name: str) -> List[str]:
         """
         Construct updated VCF records by inserting spiked variants into the correct positions within the VCF.
 
+        Args:
+            template_vcf_name (str): Name of the template VCF file.
+
         Returns:
             List[str]: Updated VCF records containing the spiked variants.
         """
         updated_vcf_records = copy(self.vcf_contents)
         for variant in self.proband_causative_variants:
-            variant = self.construct_variant_entry(variant)
-            variant_entry_position = [
+            variant_entry = self.construct_variant_entry(variant)
+            matching_indices = [
                 i
                 for i, val in enumerate(updated_vcf_records)
-                if val.split("\t")[0] == variant[0] and int(val.split("\t")[1]) < int(variant[1])
-            ][-1] + 1
-            updated_vcf_records.insert(variant_entry_position, "\t".join(variant))
+                if val.split("\t")[0] == variant_entry[0]
+                and int(val.split("\t")[1]) < int(variant_entry[1])
+            ]
+            if matching_indices:
+                variant_entry_position = matching_indices[-1] + 1
+            else:
+                info_log.warning(
+                    f"Could not find entry position for {variant.variant.chrom}-{variant.variant.pos}-"
+                    f"{variant.variant.ref}-{variant.variant.alt} in {template_vcf_name}, "
+                    "inserting at end of VCF contents."
+                )
+                variant_entry_position = len(updated_vcf_records)
+            updated_vcf_records.insert(variant_entry_position, "\t".join(variant_entry))
         return updated_vcf_records
 
     def construct_header(self, updated_vcf_records: List[str]) -> List[str]:
@@ -358,21 +371,27 @@ class VcfSpiker:
         """
         updated_vcf_file = []
         for line in updated_vcf_records:
-            text = line.replace(
-                self.vcf_header.sample_id,
-                self.proband_causative_variants[0].proband_id,
-            )
+            if line.startswith("#"):
+                text = line.replace(
+                    self.vcf_header.sample_id,
+                    self.proband_causative_variants[0].proband_id,
+                )
+            else:
+                text = line
             updated_vcf_file.append(text)
         return updated_vcf_file
 
-    def construct_vcf(self) -> List[str]:
+    def construct_vcf(self, template_vcf_name: str) -> List[str]:
         """
         Construct the entire spiked VCF file by incorporating the spiked variants into the VCF.
 
+        Args:
+            template_vcf_name (str): Name of the template VCF file.
+
         Returns:
             List[str]: The complete spiked VCF file content as a list of strings.
         """
-        return self.construct_header(self.construct_vcf_records())
+        return self.construct_header(self.construct_vcf_records(template_vcf_name))
 
 
 class VcfWriter:
@@ -454,7 +473,7 @@ def spike_vcf_contents(
             chosen_template_vcf.vcf_contents,
             phenopacket_causative_variants,
             chosen_template_vcf.vcf_header,
-        ).construct_vcf(),
+        ).construct_vcf(chosen_template_vcf.vcf_file_name),
     )
 
 

pheval/prepare/prepare_corpus.py

@@ -39,6 +39,11 @@ def prepare_corpus(
     output_dir.joinpath("phenopackets").mkdir(exist_ok=True, parents=True)
     for phenopacket_path in all_files(phenopacket_dir):
         phenopacket_util = PhenopacketUtil(phenopacket_reader(phenopacket_path))
+        if not phenopacket_util.observed_phenotypic_features():
+            info_log.warning(
+                f"Removed {phenopacket_path.name} from the corpus due to no observed phenotypic features."
+            )
+            continue
         if variant_analysis:
             if phenopacket_util.check_incomplete_variant_record():
                 info_log.warning(

pheval/utils/file_utils.py

@@ -70,35 +70,6 @@ def normalise_file_name(file_path: Path) -> str:
     return re.sub("[\u0300-\u036f]", "", normalised_file_name)
 
 
-def obtain_phenopacket_path_from_pheval_result(
-    pheval_result_path: Path, phenopacket_paths: list[Path]
-) -> Path:
-    """
-    Obtains the phenopacket file name when given a pheval result file name
-    and a list of full paths of phenopackets to be queried.
-
-    Args:
-        pheval_result_path (Path): The PhEval result.
-        phenopacket_paths (list[Path]): List of full paths of phenopackets to be queried.
-
-    Returns:
-        Path: The matching phenopacket file path from the provided list.
-    """
-    pheval_result_path_stem_stripped = pheval_result_path.stem.split("-pheval_")[0]
-    matching_phenopacket_paths = [
-        phenopacket_path
-        for phenopacket_path in phenopacket_paths
-        if phenopacket_path.stem == pheval_result_path_stem_stripped
-    ]
-    if matching_phenopacket_paths:
-        return matching_phenopacket_paths[0]
-    else:
-        raise FileNotFoundError(
-            f"Unable to find matching phenopacket file named "
-            f"{pheval_result_path_stem_stripped}.json for {pheval_result_path.name}"
-        )
-
-
 def ensure_file_exists(*files: str):
     """Ensures the existence of files passed as parameter
     Raises:

{pheval-0.3.5.dist-info → pheval-0.3.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pheval
-Version: 0.3.5
+Version: 0.3.7
 Summary: 
 Author: Yasemin Bridges
 Author-email: y.bridges@qmul.ac.uk

{pheval-0.3.5.dist-info → pheval-0.3.7.dist-info}/RECORD

@@ -4,17 +4,17 @@ pheval/analyse/analysis.py,sha256=ponm3P8nvzJNmcrNZ2_KudEhWSaWshd_Gd30D-aau8s,77
 pheval/analyse/benchmark_generator.py,sha256=AeuwbaPb4j_dyBGPRgEBxQk2NahDb5u4xHyFiqp5Fes,5943
 pheval/analyse/benchmarking_data.py,sha256=aNZkWdmWemlnC1Tg35MtR60S9YC71QWS2rMuzkUc3w0,768
 pheval/analyse/binary_classification_stats.py,sha256=E35YjvGM-zFnuEt8M3pgN03vBab4MH6ih726QKvuogg,12519
-pheval/analyse/disease_prioritisation_analysis.py,sha256=qadEVhBMtBgtjGCJLhNQA510F8Pd0Ll4NAQXoT23BYs,12649
-pheval/analyse/gene_prioritisation_analysis.py,sha256=lAN171xfXqweK8ie6191s_6WPPGjZKJXL1Z0dIqp54k,12373
+pheval/analyse/disease_prioritisation_analysis.py,sha256=mGfGYF5Eu7LxyBkAy6xMG1nDURaPiJY4rRQyKDcQe-4,12451
+pheval/analyse/gene_prioritisation_analysis.py,sha256=KSEQV6EvqtWESmO4Zc3Q9CwrjoMzxRiFUDKuAVvQtuM,12190
 pheval/analyse/generate_plots.py,sha256=MFORnFTgoelYAahFlu3Dc3Rul4cwCg8Bloxe62vONSc,21350
 pheval/analyse/generate_summary_outputs.py,sha256=s9pXMSW6xm4ZBe1aCd0UJSaFiKBvpUfPwJ2BI4qfTas,6591
 pheval/analyse/parse_benchmark_summary.py,sha256=Y8uPTlHTEiaeVBOqxMcdOqjY3ZBtOS3DoRycL78Dzxg,2384
-pheval/analyse/parse_pheval_result.py,sha256=j8YFVA0YXfySOkm8gMwrfIuV45DI9AX3ETn7h-r8ayE,1211
+pheval/analyse/parse_pheval_result.py,sha256=2-J_c90KSs49EDjMukl8dgQyWJ0lZMlF-9ZYzD9hWzg,1438
 pheval/analyse/prioritisation_rank_recorder.py,sha256=EVe8DoEvvp0_WMAcjfVxmDGGRFPEELi7hEVjH3sIpLY,3223
 pheval/analyse/prioritisation_result_types.py,sha256=qJoB6O-lFYmzAMcTQeDJZQNLJ6hleoKDYATTkhvFF98,1228
 pheval/analyse/rank_stats.py,sha256=knj1tsKrly17QgtOUVpqA14UjbO99N3ydkWN4xU6c2k,15785
 pheval/analyse/run_data_parser.py,sha256=HzBKsJL2skjmrRZdrF3VYzswtKNgbX6U5qhY_kqq9mA,1552
-pheval/analyse/variant_prioritisation_analysis.py,sha256=ApmUeTW0cl_BPh7LusbApxtgjEXEkhuNFyh0DxKKpgU,12384
+pheval/analyse/variant_prioritisation_analysis.py,sha256=eF3SIvU6MNv1KR8ZmwXvTF4IoNu2qfwaBHA0uKZ8uMc,12186
 pheval/cli.py,sha256=X4tDi7e3VB3v2RawkqIbfv4SFPCBuQwMXMnYCPTGtIo,1570
 pheval/cli_pheval.py,sha256=fWbKUcPTZZSa1EJEtH_lNn1XE6qRApRHihqUZS5owrA,2424
 pheval/cli_pheval_utils.py,sha256=kySsSa7NyewwVwYBMu93y8l5_qSJaVkdXklGchcXExU,20504
@@ -24,12 +24,12 @@ pheval/implementations/__init__.py,sha256=BMUTotjTdgy5j5xubWCIQgRXrSQ1ZIcjooer7r
 pheval/infra/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pheval/infra/exomiserdb.py,sha256=pM9-TfjrgurtH4OtM1Enk5oVhIxGQN3rKRlrxHuObTM,5080
 pheval/post_processing/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-pheval/post_processing/post_processing.py,sha256=2srdlw2D3qMh2B3PUSDvA6COYlbXINC08Wt4eccMZp8,16030
+pheval/post_processing/post_processing.py,sha256=Xzcrb7I0DiLBT3tp0oM8_L8Ld64fTgRHBstQuNSrFHk,13329
 pheval/prepare/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pheval/prepare/create_noisy_phenopackets.py,sha256=UbBRWDD95BFHPv03VYx04v35AGwJ9ynLltYKqQJHbZ0,11236
-pheval/prepare/create_spiked_vcf.py,sha256=KZIyjtDDTqJj3hxL3u4YP6P0toA4RN1oPeDrzLMB2z4,20235
+pheval/prepare/create_spiked_vcf.py,sha256=A_nIAhoU48nAeocpIu5UE41db4oBGj2cSoT-U-3qQ1Q,21111
 pheval/prepare/custom_exceptions.py,sha256=_G3_95dPtHIs1SviYBV1j7cYc-hxlhuw8hhnYdzByYY,1719
-pheval/prepare/prepare_corpus.py,sha256=BzRra3VyPWHeT7zwH78vYEabo_hddBanJxVwPzw0YEU,3456
+pheval/prepare/prepare_corpus.py,sha256=FweWoYMkS-kzi5RqgrSzkdp_8iWLyoGWMC_GF0szcUg,3692
 pheval/prepare/update_phenopacket.py,sha256=21fzUPbwKN6Ey5TSh9PFzjT2x86U19RAE6WmkjG8u28,4770
 pheval/resources/alternate_ouputs/CADA_results.txt,sha256=Rinn2TtfwFNsx0aEWegKJOkjKnBm-Mf54gdaT3bWP0k,547
 pheval/resources/alternate_ouputs/DeepPVP_results.txt,sha256=MF9MZJYa4r4PEvFzALpi-lNGLxjENOnq_YgrgFMn-oQ,1508
@@ -46,12 +46,12 @@ pheval/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pheval/utils/docs_gen.py,sha256=6FGtHicBC0rZKi0tdL3Epsg8d4osE44I9f1Ga0j4JLA,3193
 pheval/utils/docs_gen.sh,sha256=LyKLKjaZuf4UJ962CWfM-XqkxtvM8O2N9wHZS5mcb9A,477
 pheval/utils/exomiser.py,sha256=m2u0PH2z9lFPaB3LVkZCmPmH5e55q1NoTzNl46zRRP8,683
-pheval/utils/file_utils.py,sha256=9HoCmtF73D3wY6bBhFLefMBI5uhvCe_meZeHXQzF_ts,4640
+pheval/utils/file_utils.py,sha256=m21cz-qjDYqnI8ClUv3J9fKizex98a-9bSEerQ75i_c,3576
 pheval/utils/phenopacket_utils.py,sha256=4inrnhZ4UjYgO0Y85ls_Nxq6voAIIXQV57_fMeIX-24,26792
 pheval/utils/semsim_utils.py,sha256=s7ZCR2VfPYnOh7ApX6rv66eGoVSm9QJaVYOWBEhlXpo,6151
 pheval/utils/utils.py,sha256=9V6vCT8l1g4O2-ZATYqsVyd7AYZdWGd-Ksy7_oIC3eE,2343
-pheval-0.3.5.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-pheval-0.3.5.dist-info/METADATA,sha256=LB8Oe6wFj-iebn32q3kH5Yqk23ElXvF6My1w_cytWds,1810
-pheval-0.3.5.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-pheval-0.3.5.dist-info/entry_points.txt,sha256=o9gSwDkvT4-lqKy4mlsftd1nzP9WUOXQCfnbqycURd0,81
-pheval-0.3.5.dist-info/RECORD,,
+pheval-0.3.7.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+pheval-0.3.7.dist-info/METADATA,sha256=BwicFNwmR9Hm8o2YxBJUJvrIeGwAevFFk-DT2pm07S4,1810
+pheval-0.3.7.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+pheval-0.3.7.dist-info/entry_points.txt,sha256=o9gSwDkvT4-lqKy4mlsftd1nzP9WUOXQCfnbqycURd0,81
+pheval-0.3.7.dist-info/RECORD,,