pheval 0.3.6__py3-none-any.whl → 0.3.8__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

@@ -1,6 +1,8 @@
+import ast
+import re
 from collections import defaultdict
 from pathlib import Path
-from typing import List
+from typing import List, Union
 
 from pheval.analyse.benchmarking_data import BenchmarkRunResults
 from pheval.analyse.binary_classification_stats import BinaryClassificationStats
@@ -10,11 +12,7 @@ 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
 
 
@@ -144,6 +142,24 @@ class AssessGenePrioritisation:
                 )
             )
 
+    @staticmethod
+    def _check_string_representation(entity: str) -> Union[List[str], str]:
+        """
+        Check if the input string is a representation of a list and returns the list if true, otherwise the string.
+
+        Args:
+            entity (str): The input entity to check.
+
+        Returns:
+            Union[List[str], str]: A list if the input string is a list representation, otherwise
+            the original string.
+        """
+        list_pattern = re.compile(r"^\[\s*(?:[^\[\],\s]+(?:\s*,\s*[^\[\],\s]+)*)?\s*\]$")
+        if list_pattern.match(entity):
+            return ast.literal_eval(entity)
+        else:
+            return entity
+
     def assess_gene_prioritisation(
         self,
         rank_stats: RankStats,
@@ -165,9 +181,21 @@ class AssessGenePrioritisation:
             rank_stats.total += 1
             gene_match = GenePrioritisationResult(self.phenopacket_path, gene.gene_symbol)
             for standardised_gene_result in self.standardised_gene_results:
+                gene_identifier = self._check_string_representation(
+                    standardised_gene_result.gene_identifier
+                )
+                gene_symbol = self._check_string_representation(
+                    standardised_gene_result.gene_symbol
+                )
                 if (
-                    gene.gene_identifier == standardised_gene_result.gene_identifier
-                    or gene.gene_symbol == standardised_gene_result.gene_symbol
+                    isinstance(gene_identifier, list)
+                    and gene.gene_identifier in gene_identifier
+                    or isinstance(gene_identifier, str)
+                    and gene.gene_identifier == str
+                    or isinstance(gene_symbol, list)
+                    and gene.gene_symbol in gene_symbol
+                    or isinstance(gene_symbol, str)
+                    and gene.gene_symbol == gene_symbol
                 ):
                     gene_match = self._record_matched_gene(
                         gene, rank_stats, standardised_gene_result
@@ -209,7 +237,7 @@ 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 +250,7 @@ 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 +258,8 @@ 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 +294,9 @@ 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
 
 
@@ -166,8 +162,8 @@ class AssessVariantPrioritisation:
             variant_match = VariantPrioritisationResult(self.phenopacket_path, variant)
             for result in self.standardised_variant_results:
                 result_variant = GenomicVariant(
-                    chrom=result.chromosome,
-                    pos=result.start,
+                    chrom=str(result.chromosome),
+                    pos=int(result.start),
                     ref=result.ref,
                     alt=result.alt,
                 )
@@ -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/cli_pheval_utils.py

@@ -260,6 +260,8 @@ def update_phenopackets_command(
     required=False,
     help="Template hg19 VCF file",
     type=Path,
+    cls=MutuallyExclusiveOptionError,
+    mutually_exclusive=["hg19_vcf_dir"],
 )
 @click.option(
     "--hg38-template-vcf",
@@ -268,6 +270,28 @@ def update_phenopackets_command(
     required=False,
     help="Template hg38 VCF file",
     type=Path,
+    cls=MutuallyExclusiveOptionError,
+    mutually_exclusive=["hg38_vcf_dir"],
+)
+@click.option(
+    "--hg19-vcf-dir",
+    "-hg19-dir",
+    metavar="PATH",
+    required=False,
+    help="Path to directory containing hg19 VCF templates.",
+    type=Path,
+    cls=MutuallyExclusiveOptionError,
+    mutually_exclusive=["hg19_template_vcf"],
+)
+@click.option(
+    "--hg38-vcf-dir",
+    "-hg38-dir",
+    metavar="PATH",
+    required=False,
+    help="Path to directory containing hg38 VCF templates.",
+    type=Path,
+    cls=MutuallyExclusiveOptionError,
+    mutually_exclusive=["hg38_template_vcf"],
 )
 @click.option(
     "--output-dir",
@@ -284,6 +308,8 @@ def create_spiked_vcfs_command(
     output_dir: Path,
     hg19_template_vcf: Path = None,
     hg38_template_vcf: Path = None,
+    hg19_vcf_dir: Path = None,
+    hg38_vcf_dir: Path = None,
 ):
     """
     Create spiked VCF from either a Phenopacket or a Phenopacket directory.
@@ -294,10 +320,20 @@ def create_spiked_vcfs_command(
         output_dir (Path): The directory to store the generated spiked VCF file(s).
         hg19_template_vcf (Path): Path to the hg19 template VCF file (optional).
         hg38_template_vcf (Path): Path to the hg38 template VCF file (optional).
+        hg19_vcf_dir (Path): Path to the directory containing the hg19 VCF files (optional).
+        hg38_vcf_dir (Path): Path to the directory containing the hg38 VCF files (optional).
     """
     if phenopacket_path is None and phenopacket_dir is None:
         raise InputError("Either a phenopacket or phenopacket directory must be specified")
-    spike_vcfs(output_dir, phenopacket_path, phenopacket_dir, hg19_template_vcf, hg38_template_vcf)
+    spike_vcfs(
+        output_dir,
+        phenopacket_path,
+        phenopacket_dir,
+        hg19_template_vcf,
+        hg38_template_vcf,
+        hg19_vcf_dir,
+        hg38_vcf_dir,
+    )
 
 
 @click.command()
@@ -656,6 +692,8 @@ def generate_stats_plot(
     required=False,
     help="Template hg19 VCF file",
     type=Path,
+    cls=MutuallyExclusiveOptionError,
+    mutually_exclusive=["hg19_vcf_dir"],
 )
 @click.option(
     "--hg38-template-vcf",
@@ -664,6 +702,28 @@ def generate_stats_plot(
     required=False,
     help="Template hg38 VCF file",
     type=Path,
+    cls=MutuallyExclusiveOptionError,
+    mutually_exclusive=["hg38_vcf_dir"],
+)
+@click.option(
+    "--hg19-vcf-dir",
+    "-hg19-dir",
+    metavar="PATH",
+    required=False,
+    help="Path to directory containing hg19 VCF templates.",
+    type=Path,
+    cls=MutuallyExclusiveOptionError,
+    mutually_exclusive=["hg19_template_vcf"],
+)
+@click.option(
+    "--hg38-vcf-dir",
+    "-hg38-dir",
+    metavar="PATH",
+    required=False,
+    help="Path to directory containing hg38 VCF templates.",
+    type=Path,
+    cls=MutuallyExclusiveOptionError,
+    mutually_exclusive=["hg38_template_vcf"],
 )
 @click.option(
     "--output-dir",
@@ -682,23 +742,28 @@ def prepare_corpus_command(
     gene_identifier: str,
     hg19_template_vcf: Path,
     hg38_template_vcf: Path,
+    hg19_vcf_dir: Path,
+    hg38_vcf_dir: Path,
     output_dir: Path,
 ):
     """
     Prepare a corpus of Phenopackets for analysis, optionally checking for complete variant records and updating
     gene identifiers.
 
-        Args:
-            phenopacket_dir (Path): The path to the directory containing Phenopackets.
-            variant_analysis (bool): If True, check for complete variant records in the Phenopackets.
-            gene_analysis (bool): If True, check for complete gene records in the Phenopackets.
-            disease_analysis (bool): If True, check for complete disease records in the Phenopackets.
-            gene_identifier (str): Identifier for updating gene identifiers, if applicable.
-            hg19_template_vcf (Path): Path to the hg19 template VCF file (optional), to spike variants into
-            VCFs for variant-based analysis at least one of hg19_template_vcf or hg38_template_vcf is required.
-            hg38_template_vcf (Path): Path to the hg38 template VCF file (optional), to spike variants into
-            VCFs for variant-based analysis at least one of hg19_template_vcf or hg38_template_vcf is required.
-            output_dir (Path): The directory to save the prepared Phenopackets and, optionally, VCF files.
+    Args:
+        phenopacket_dir (Path): The path to the directory containing Phenopackets.
+        variant_analysis (bool): If True, check for complete variant records in the Phenopackets.
+        gene_analysis (bool): If True, check for complete gene records in the Phenopackets.
+        disease_analysis (bool): If True, check for complete disease records in the Phenopackets.
+        gene_identifier (str): Identifier for updating gene identifiers, if applicable.
+        hg19_template_vcf (Path): Path to the hg19 template VCF file (optional).
+        hg38_template_vcf (Path): Path to the hg38 template VCF file (optional).
+        hg19_vcf_dir (Path): Path to the directory containing the hg19 VCF files (optional).
+        hg38_vcf_dir (Path): Path to the directory containing the hg38 VCF files (optional).
+        output_dir (Path): The directory to save the prepared Phenopackets and, optionally, VCF files.
+    Notes:
+        To spike variants into VCFs for variant-based analysis at least one of hg19_template_vcf, hg38_template_vcf,
+        hg19_vcf_dir or hg38_vcf_dir is required.
     """
     prepare_corpus(
         phenopacket_dir,
@@ -708,5 +773,7 @@ def prepare_corpus_command(
         gene_identifier,
         hg19_template_vcf,
         hg38_template_vcf,
+        hg19_vcf_dir,
+        hg38_vcf_dir,
         output_dir,
     )

pheval/post_processing/post_processing.py

@@ -3,6 +3,7 @@ import operator
 from dataclasses import dataclass
 from enum import Enum
 from pathlib import Path
+from typing import List, Union
 
 import pandas as pd
 
@@ -30,8 +31,8 @@ class PhEvalResult:
 class PhEvalGeneResult(PhEvalResult):
     """Minimal data required from tool-specific output for gene prioritisation result
     Args:
-        gene_symbol (str): The gene symbol for the result entry
-        gene_identifier (str): The ENSEMBL gene identifier for the result entry
+        gene_symbol (Union[List[str], str]): The gene symbol(s) for the result entry
+        gene_identifier (Union[List[str], str]): The ENSEMBL gene identifier(s) for the result entry
         score (float): The score for the gene result entry
     Notes:
         While we recommend providing the gene identifier in the ENSEMBL namespace,
@@ -39,8 +40,8 @@ class PhEvalGeneResult(PhEvalResult):
         in the analysis.
     """
 
-    gene_symbol: str
-    gene_identifier: str
+    gene_symbol: Union[List[str], str]
+    gene_identifier: Union[List[str], str]
     score: float
 
 
@@ -375,11 +376,11 @@ 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

@@ -1,5 +1,6 @@
 import gzip
 import logging
+import random
 import re
 import urllib.parse
 from copy import copy
@@ -10,7 +11,7 @@ from typing import List, Union
 from phenopackets import Family, File, Phenopacket
 
 from pheval.prepare.custom_exceptions import InputError
-from pheval.utils.file_utils import files_with_suffix, is_gzipped
+from pheval.utils.file_utils import all_files, files_with_suffix, is_gzipped
 from pheval.utils.phenopacket_utils import (
     IncompatibleGenomeAssemblyError,
     PhenopacketRebuilder,
@@ -207,6 +208,8 @@ def select_vcf_template(
     proband_causative_variants: List[ProbandCausativeVariant],
     hg19_vcf_info: VcfFile,
     hg38_vcf_info: VcfFile,
+    hg19_vcf_dir: Path,
+    hg38_vcf_dir: Path,
 ) -> VcfFile:
     """
     Select the appropriate VCF template based on the assembly information of the proband causative variants.
@@ -216,6 +219,8 @@ def select_vcf_template(
         proband_causative_variants (List[ProbandCausativeVariant]): A list of causative variants from the proband.
         hg19_vcf_info (VcfFile): VCF file info for hg19 template vcf.
         hg38_vcf_info (VcfFile): CF file info for hg38 template vcf.
+        hg19_vcf_dir (Path): The directory containing the hg19 VCF files.
+        hg38_vcf_dir (Path): The directory containing the hg38 VCF files.
 
     Returns:
         VcfFile: The selected VCF template file based on the assembly information of the proband causative variants.
@@ -224,11 +229,15 @@ def select_vcf_template(
     if proband_causative_variants[0].assembly in ["hg19", "GRCh37"]:
         if hg19_vcf_info:
             return hg19_vcf_info
+        elif hg19_vcf_dir:
+            return VcfFile.populate_fields(random.choice(all_files(hg19_vcf_dir)))
         else:
             raise InputError("Must specify hg19 template VCF!")
     elif proband_causative_variants[0].assembly in ["hg38", "GRCh38"]:
         if hg38_vcf_info:
             return hg38_vcf_info
+        elif hg38_vcf_dir:
+            return VcfFile.populate_fields(random.choice(all_files(hg38_vcf_dir)))
         else:
             raise InputError("Must specify hg38 template VCF!")
     else:
@@ -445,6 +454,8 @@ def spike_vcf_contents(
     phenopacket_path: Path,
     hg19_vcf_info: VcfFile,
     hg38_vcf_info: VcfFile,
+    hg19_vcf_dir: Path,
+    hg38_vcf_dir: Path,
 ) -> tuple[str, List[str]]:
     """
     Spike VCF records with variants obtained from a Phenopacket or Family.
@@ -454,6 +465,8 @@ def spike_vcf_contents(
         phenopacket_path (Path): Path to the Phenopacket file.
         hg19_vcf_info (VcfFile): VCF file info for hg19 template vcf.
         hg38_vcf_info (VcfFile): VCF file info for hg38 template vcf.
+        hg19_vcf_dir (Path): The directory containing the hg19 VCF files.
+        hg38_vcf_dir (Path): The directory containing the hg38 VCF files.
 
     Returns:
         A tuple containing:
@@ -462,7 +475,12 @@ def spike_vcf_contents(
     """
     phenopacket_causative_variants = PhenopacketUtil(phenopacket).causative_variants()
     chosen_template_vcf = select_vcf_template(
-        phenopacket_path, phenopacket_causative_variants, hg19_vcf_info, hg38_vcf_info
+        phenopacket_path,
+        phenopacket_causative_variants,
+        hg19_vcf_info,
+        hg38_vcf_info,
+        hg19_vcf_dir,
+        hg38_vcf_dir,
     )
     check_variant_assembly(
         phenopacket_causative_variants, chosen_template_vcf.vcf_header, phenopacket_path
@@ -483,6 +501,8 @@ def generate_spiked_vcf_file(
     phenopacket_path: Path,
     hg19_vcf_info: VcfFile,
     hg38_vcf_info: VcfFile,
+    hg19_vcf_dir: Path,
+    hg38_vcf_dir: Path,
 ) -> File:
     """
     Write spiked VCF contents to a new file.
@@ -493,13 +513,15 @@ def generate_spiked_vcf_file(
         phenopacket_path (Path): Path to the Phenopacket file.
         hg19_vcf_info (VcfFile): VCF file info for hg19 template vcf.
         hg38_vcf_info (VcfFile): VCF file info for hg38 template vcf.
+        hg19_vcf_dir (Path): The directory containing the hg19 VCF files.
+        hg38_vcf_dir (Path): The directory containing the hg38 VCF files.
     Returns:
         File: The generated File object representing the newly created spiked VCF file.
     """
     output_dir.mkdir(exist_ok=True)
     info_log.info(f" Created a directory {output_dir}")
     vcf_assembly, spiked_vcf = spike_vcf_contents(
-        phenopacket, phenopacket_path, hg19_vcf_info, hg38_vcf_info
+        phenopacket, phenopacket_path, hg19_vcf_info, hg38_vcf_info, hg19_vcf_dir, hg38_vcf_dir
     )
     spiked_vcf_path = output_dir.joinpath(phenopacket_path.name.replace(".json", ".vcf.gz"))
     VcfWriter(spiked_vcf, spiked_vcf_path).write_vcf_file()
@@ -509,10 +531,38 @@ def generate_spiked_vcf_file(
     )
 
 
-def spike_and_update_phenopacket(hg19_vcf_info, hg38_vcf_info, output_dir, phenopacket_path):
+def spike_and_update_phenopacket(
+    hg19_vcf_info: VcfFile,
+    hg38_vcf_info: VcfFile,
+    hg19_vcf_dir: Path,
+    hg38_vcf_dir: Path,
+    output_dir: Path,
+    phenopacket_path: Path,
+) -> None:
+    """
+    Spike the VCF files with genetic variants relevant to the provided Phenopacket, update the Phenopacket
+    accordingly, and write the updated Phenopacket to the specified output directory.
+
+    Args:
+        hg19_vcf_info (VcfFile): VCF file info for hg19 template vcf.
+        hg38_vcf_info (VcfFile): VCF file info for hg38 template vcf.
+        hg19_vcf_dir (Path): The directory containing the hg19 VCF files.
+        hg38_vcf_dir (Path): The directory containing the hg38 VCF files.
+        output_dir (Path): Directory where the updated Phenopacket will be saved.
+        phenopacket_path (Path): Path to the original Phenopacket file.
+
+    Returns:
+        None
+    """
     phenopacket = phenopacket_reader(phenopacket_path)
     spiked_vcf_file_message = generate_spiked_vcf_file(
-        output_dir, phenopacket, phenopacket_path, hg19_vcf_info, hg38_vcf_info
+        output_dir,
+        phenopacket,
+        phenopacket_path,
+        hg19_vcf_info,
+        hg38_vcf_info,
+        hg19_vcf_dir,
+        hg38_vcf_dir,
     )
     updated_phenopacket = PhenopacketRebuilder(phenopacket).add_spiked_vcf_path(
         spiked_vcf_file_message
@@ -521,7 +571,12 @@ def spike_and_update_phenopacket(hg19_vcf_info, hg38_vcf_info, output_dir, pheno
 
 
 def create_spiked_vcf(
-    output_dir: Path, phenopacket_path: Path, hg19_template_vcf: Path, hg38_template_vcf: Path
+    output_dir: Path,
+    phenopacket_path: Path,
+    hg19_template_vcf: Path,
+    hg38_template_vcf: Path,
+    hg19_vcf_dir: Path,
+    hg38_vcf_dir: Path,
 ) -> None:
     """
     Create a spiked VCF for a Phenopacket.
@@ -531,6 +586,8 @@ def create_spiked_vcf(
         phenopacket_path (Path): Path to the Phenopacket file.
         hg19_template_vcf (Path): Path to the hg19 template VCF file (optional).
         hg38_template_vcf (Path): Path to the hg38 template VCF file (optional).
+        hg19_vcf_dir (Path): The directory containing the hg19 VCF files (optional).
+        hg38_vcf_dir (Path): The directory containing the hg38 VCF files (optional).
 
     Raises:
         InputError: If both hg19_template_vcf and hg38_template_vcf are None.
@@ -539,11 +596,18 @@ def create_spiked_vcf(
         raise InputError("Either a hg19 template vcf or hg38 template vcf must be specified")
     hg19_vcf_info = VcfFile.populate_fields(hg19_template_vcf) if hg19_template_vcf else None
     hg38_vcf_info = VcfFile.populate_fields(hg38_template_vcf) if hg38_template_vcf else None
-    spike_and_update_phenopacket(hg19_vcf_info, hg38_vcf_info, output_dir, phenopacket_path)
+    spike_and_update_phenopacket(
+        hg19_vcf_info, hg38_vcf_info, hg19_vcf_dir, hg38_vcf_dir, output_dir, phenopacket_path
+    )
 
 
 def create_spiked_vcfs(
-    output_dir: Path, phenopacket_dir: Path, hg19_template_vcf: Path, hg38_template_vcf: Path
+    output_dir: Path,
+    phenopacket_dir: Path,
+    hg19_template_vcf: Path,
+    hg38_template_vcf: Path,
+    hg19_vcf_dir: Path,
+    hg38_vcf_dir: Path,
 ) -> None:
     """
     Create a spiked VCF for a directory of Phenopackets.
@@ -553,16 +617,25 @@ def create_spiked_vcfs(
         phenopacket_dir (Path): Path to the Phenopacket directory.
         hg19_template_vcf (Path): Path to the template hg19 VCF file (optional).
         hg38_template_vcf (Path): Path to the template hg19 VCF file (optional).
+        hg19_vcf_dir (Path): The directory containing the hg19 VCF files (optional).
+        hg38_vcf_dir (Path): The directory containing the hg38 VCF files (optional).
 
     Raises:
         InputError: If both hg19_template_vcf and hg38_template_vcf are None.
     """
-    if hg19_template_vcf is None and hg38_template_vcf is None:
-        raise InputError("Either a hg19 template vcf or hg38 template vcf must be specified")
+    if (
+        hg19_template_vcf is None
+        and hg38_template_vcf is None
+        and hg19_vcf_dir is None
+        and hg38_vcf_dir is None
+    ):
+        raise InputError("Need to specify a VCF!")
     hg19_vcf_info = VcfFile.populate_fields(hg19_template_vcf) if hg19_template_vcf else None
     hg38_vcf_info = VcfFile.populate_fields(hg38_template_vcf) if hg38_template_vcf else None
     for phenopacket_path in files_with_suffix(phenopacket_dir, ".json"):
-        spike_and_update_phenopacket(hg19_vcf_info, hg38_vcf_info, output_dir, phenopacket_path)
+        spike_and_update_phenopacket(
+            hg19_vcf_info, hg38_vcf_info, hg19_vcf_dir, hg38_vcf_dir, output_dir, phenopacket_path
+        )
 
 
 def spike_vcfs(
@@ -571,6 +644,8 @@ def spike_vcfs(
     phenopacket_dir: Path,
     hg19_template_vcf: Path,
     hg38_template_vcf: Path,
+    hg19_vcf_dir: Path,
+    hg38_vcf_dir: Path,
 ) -> None:
     """
     Create spiked VCF from either a Phenopacket or a Phenopacket directory.
@@ -581,8 +656,24 @@ def spike_vcfs(
         phenopacket_dir (Path): Path to a directory containing Phenopacket files (optional).
         hg19_template_vcf (Path): Path to the hg19 template VCF file (optional).
         hg38_template_vcf (Path): Path to the hg38 template VCF file (optional).
+        hg19_vcf_dir (Path): The directory containing the hg19 VCF files (optional).
+        hg38_vcf_dir (Path): The directory containing the hg38 VCF files (optional).
     """
     if phenopacket_path is not None:
-        create_spiked_vcf(output_dir, phenopacket_path, hg19_template_vcf, hg38_template_vcf)
+        create_spiked_vcf(
+            output_dir,
+            phenopacket_path,
+            hg19_template_vcf,
+            hg38_template_vcf,
+            hg19_vcf_dir,
+            hg38_vcf_dir,
+        )
     elif phenopacket_dir is not None:
-        create_spiked_vcfs(output_dir, phenopacket_dir, hg19_template_vcf, hg38_template_vcf)
+        create_spiked_vcfs(
+            output_dir,
+            phenopacket_dir,
+            hg19_template_vcf,
+            hg38_template_vcf,
+            hg19_vcf_dir,
+            hg38_vcf_dir,
+        )

pheval/prepare/prepare_corpus.py

@@ -18,6 +18,8 @@ def prepare_corpus(
     gene_identifier: str,
     hg19_template_vcf: Path,
     hg38_template_vcf: Path,
+    hg19_vcf_dir: Path,
+    hg38_vcf_dir: Path,
     output_dir: Path,
 ) -> None:
     """
@@ -34,7 +36,12 @@ def prepare_corpus(
         VCFs for variant-based analysis at least one of hg19_template_vcf or hg38_template_vcf is required.
         hg38_template_vcf (Path): Path to the hg38 template VCF file (optional), to spike variants into
         VCFs for variant-based analysis at least one of hg19_template_vcf or hg38_template_vcf is required.
+        hg19_vcf_dir (Path): Path to the directory containing hg19 template VCF files (optional).
+        hg38_vcf_dir (Path): Path to the directory containing hg38 template VCF files (optional).
         output_dir (Path): The directory to save the prepared Phenopackets and, optionally, VCF files.
+    Notes:
+        To spike variants into VCFs for variant-based analysis at least one of hg19_template_vcf, hg38_template_vcf,
+        hg19_vcf_dir or hg38_vcf_dir is required.
     """
     output_dir.joinpath("phenopackets").mkdir(exist_ok=True, parents=True)
     for phenopacket_path in all_files(phenopacket_dir):
@@ -65,7 +72,12 @@ def prepare_corpus(
         if hg19_template_vcf or hg38_template_vcf:
             output_dir.joinpath("vcf").mkdir(exist_ok=True)
             create_spiked_vcf(
-                output_dir.joinpath("vcf"), phenopacket_path, hg19_template_vcf, hg38_template_vcf
+                output_dir.joinpath("vcf"),
+                phenopacket_path,
+                hg19_template_vcf,
+                hg38_template_vcf,
+                hg19_vcf_dir,
+                hg38_vcf_dir,
             )
         if gene_identifier:
             create_updated_phenopacket(

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/utils/phenopacket_utils.py

@@ -468,10 +468,12 @@ class PhenopacketUtil:
         for i in pheno_interpretation:
             for g in i.diagnosis.genomic_interpretations:
                 variant = GenomicVariant(
-                    chrom=g.variant_interpretation.variation_descriptor.vcf_record.chrom.replace(
-                        "chr", ""
+                    chrom=str(
+                        g.variant_interpretation.variation_descriptor.vcf_record.chrom.replace(
+                            "chr", ""
+                        )
                     ),
-                    pos=g.variant_interpretation.variation_descriptor.vcf_record.pos,
+                    pos=int(g.variant_interpretation.variation_descriptor.vcf_record.pos),
                     ref=g.variant_interpretation.variation_descriptor.vcf_record.ref,
                     alt=g.variant_interpretation.variation_descriptor.vcf_record.alt,
                 )

{pheval-0.3.6.dist-info → pheval-0.3.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pheval
-Version: 0.3.6
+Version: 0.3.8
 Summary: 
 Author: Yasemin Bridges
 Author-email: y.bridges@qmul.ac.uk

{pheval-0.3.6.dist-info → pheval-0.3.8.dist-info}/RECORD

@@ -4,32 +4,32 @@ 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=UK41VqcO605zRamJMwj2jIaMWJ0_uYeDlrU0liJzdn0,13449
 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=XSlAV2G7psXewPIoiUD_4jgFivcG1aOcy1jSPlSil5M,12196
 pheval/cli.py,sha256=X4tDi7e3VB3v2RawkqIbfv4SFPCBuQwMXMnYCPTGtIo,1570
 pheval/cli_pheval.py,sha256=fWbKUcPTZZSa1EJEtH_lNn1XE6qRApRHihqUZS5owrA,2424
-pheval/cli_pheval_utils.py,sha256=kySsSa7NyewwVwYBMu93y8l5_qSJaVkdXklGchcXExU,20504
+pheval/cli_pheval_utils.py,sha256=4jLSJm4AEXu0SBtXbg4eNYLbCNQqQgjroDpRxQX34-M,22333
 pheval/config_parser.py,sha256=lh-Dy_FflXJUnRC3HYaEdSvPAsNZWQZlEr1hHQigrTM,1227
 pheval/constants.py,sha256=TWBgWOc05FGXFu63fs-hEHS2IJkLLAPHtMppiWBfBOg,349
 pheval/implementations/__init__.py,sha256=BMUTotjTdgy5j5xubWCIQgRXrSQ1ZIcjooer7r299Zo,1228
 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=tjdk-LKj5TORwGDKNzEiLViy9oMRLVR9hG1b7E8RfkI,13368
+pheval/post_processing/post_processing.py,sha256=tqeVRWF6PMHpOe681ONeGaqxdviLgVJgze3o6qSpXEg,13438
 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=A_nIAhoU48nAeocpIu5UE41db4oBGj2cSoT-U-3qQ1Q,21111
+pheval/prepare/create_spiked_vcf.py,sha256=90A-Mi8QKhvN036vtFEVWAHgzHO37itiLYrqYlG4LiA,23953
 pheval/prepare/custom_exceptions.py,sha256=_G3_95dPtHIs1SviYBV1j7cYc-hxlhuw8hhnYdzByYY,1719
-pheval/prepare/prepare_corpus.py,sha256=FweWoYMkS-kzi5RqgrSzkdp_8iWLyoGWMC_GF0szcUg,3692
+pheval/prepare/prepare_corpus.py,sha256=eRvozzezIgAqHAumtqul0WfXfBO1iOBaSlN8fPSn0Nw,4223
 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/phenopacket_utils.py,sha256=4inrnhZ4UjYgO0Y85ls_Nxq6voAIIXQV57_fMeIX-24,26792
+pheval/utils/file_utils.py,sha256=m21cz-qjDYqnI8ClUv3J9fKizex98a-9bSEerQ75i_c,3576
+pheval/utils/phenopacket_utils.py,sha256=W9T_X48EJ-xn5GghzbZlt-lI-DxWoSm7_SHr8DCJg2Q,26856
 pheval/utils/semsim_utils.py,sha256=s7ZCR2VfPYnOh7ApX6rv66eGoVSm9QJaVYOWBEhlXpo,6151
 pheval/utils/utils.py,sha256=9V6vCT8l1g4O2-ZATYqsVyd7AYZdWGd-Ksy7_oIC3eE,2343
-pheval-0.3.6.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-pheval-0.3.6.dist-info/METADATA,sha256=VC-lX9dK2KZUkh91WuDK4ygdu6tTw3WSBRkrVe-EZJ0,1810
-pheval-0.3.6.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-pheval-0.3.6.dist-info/entry_points.txt,sha256=o9gSwDkvT4-lqKy4mlsftd1nzP9WUOXQCfnbqycURd0,81
-pheval-0.3.6.dist-info/RECORD,,
+pheval-0.3.8.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+pheval-0.3.8.dist-info/METADATA,sha256=e9Go9hmem0wD_ek3KPtZ4Zfjz4m-Vy7lLOThsbAioXA,1810
+pheval-0.3.8.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+pheval-0.3.8.dist-info/entry_points.txt,sha256=o9gSwDkvT4-lqKy4mlsftd1nzP9WUOXQCfnbqycURd0,81
+pheval-0.3.8.dist-info/RECORD,,