pheval 0.3.1__py3-none-any.whl → 0.3.3__py3-none-any.whl

pheval/analyse/binary_classification_stats.py

@@ -1,4 +1,4 @@
-from dataclasses import dataclass
+from dataclasses import dataclass, field
 from math import sqrt
 from typing import List, Union
 
@@ -29,6 +29,8 @@ class BinaryClassificationStats:
     true_negatives: int = 0
     false_positives: int = 0
     false_negatives: int = 0
+    labels: List = field(default_factory=list)
+    scores: List = field(default_factory=list)
 
     @staticmethod
     def remove_relevant_ranks(
@@ -84,6 +86,31 @@ class BinaryClassificationStats:
             elif rank != 1:
                 self.true_negatives += 1
 
+    def add_labels_and_scores(
+        self,
+        pheval_results: Union[
+            List[RankedPhEvalGeneResult],
+            List[RankedPhEvalVariantResult],
+            List[RankedPhEvalDiseaseResult],
+        ],
+        relevant_ranks: List[int],
+    ):
+        """
+        Adds scores and labels from the PhEval results.
+
+        Args:
+            pheval_results (Union[List[RankedPhEvalGeneResult], List[RankedPhEvalVariantResult],
+                                  List[RankedPhEvalDiseaseResult]]):
+                List of all PhEval results
+            relevant_ranks (List[int]): A list of the ranks associated with the known entities.
+        """
+        relevant_ranks_copy = relevant_ranks.copy()
+        for result in pheval_results:
+            self.scores.append(result.score)
+            label = 1 if result.rank in relevant_ranks_copy else 0
+            self.labels.append(label)
+            relevant_ranks_copy.remove(result.rank) if label == 1 else None
+
     def add_classification(
         self,
         pheval_results: Union[
@@ -105,6 +132,7 @@ class BinaryClassificationStats:
         self.add_classification_for_other_entities(
             self.remove_relevant_ranks(pheval_results, relevant_ranks)
         )
+        self.add_labels_and_scores(pheval_results, relevant_ranks)
 
     def sensitivity(self) -> float:
         """

pheval/analyse/disease_prioritisation_analysis.py

@@ -10,7 +10,11 @@ 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_closest_file_name
+from pheval.utils.file_utils import (
+    all_files,
+    files_with_suffix,
+    obtain_phenopacket_path_from_pheval_result,
+)
 from pheval.utils.phenopacket_utils import PhenopacketUtil, ProbandDisease, phenopacket_reader
 
 
@@ -234,7 +238,7 @@ 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_closest_file_name(
+    phenopacket_path = obtain_phenopacket_path_from_pheval_result(
         standardised_disease_result, all_files(results_dir_and_input.phenopacket_dir)
     )
     pheval_disease_result = read_standardised_result(standardised_disease_result)

pheval/analyse/gene_prioritisation_analysis.py

@@ -10,7 +10,11 @@ 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_closest_file_name
+from pheval.utils.file_utils import (
+    all_files,
+    files_with_suffix,
+    obtain_phenopacket_path_from_pheval_result,
+)
 from pheval.utils.phenopacket_utils import PhenopacketUtil, ProbandCausativeGene, phenopacket_reader
 
 
@@ -226,7 +230,7 @@ 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_closest_file_name(
+    phenopacket_path = obtain_phenopacket_path_from_pheval_result(
         standardised_gene_result, all_files(results_dir_and_input.phenopacket_dir)
     )
     pheval_gene_result = read_standardised_result(standardised_gene_result)

pheval/analyse/generate_plots.py

@@ -5,6 +5,7 @@ import matplotlib
 import pandas as pd
 import seaborn as sns
 from matplotlib import pyplot as plt
+from sklearn.metrics import auc, precision_recall_curve, roc_curve
 
 from pheval.analyse.benchmark_generator import (
     BenchmarkRunOutputGenerator,
@@ -357,6 +358,82 @@ class PlotGenerator:
             ]
         )
 
+    def generate_roc_curve(
+        self,
+        benchmarking_results: List[BenchmarkRunResults],
+        benchmark_generator: BenchmarkRunOutputGenerator,
+    ):
+        """
+        Generate and plot Receiver Operating Characteristic (ROC) curves for binary classification benchmark results.
+
+        Args:
+            benchmarking_results (List[BenchmarkRunResults]): List of benchmarking results for multiple runs.
+            benchmark_generator (BenchmarkRunOutputGenerator): Object containing benchmarking output generation details.
+        """
+        for i, benchmark_result in enumerate(benchmarking_results):
+            fpr, tpr, thresh = roc_curve(
+                benchmark_result.binary_classification_stats.labels,
+                benchmark_result.binary_classification_stats.scores,
+                pos_label=1,
+            )
+            roc_auc = auc(fpr, tpr)
+
+            plt.plot(
+                fpr,
+                tpr,
+                label=f"{self.return_benchmark_name(benchmark_result)} ROC Curve (AUC = {roc_auc:.2f})",
+                color=self.palette_hex_codes[i],
+            )
+
+        plt.plot(linestyle="--", color="gray")
+        plt.xlabel("False Positive Rate")
+        plt.ylabel("True Positive Rate")
+        plt.title("Receiver Operating Characteristic (ROC) Curve")
+        plt.legend(loc="upper center", bbox_to_anchor=(0.5, -0.15))
+        plt.savefig(
+            f"{benchmark_generator.prioritisation_type_file_prefix}_roc_curve.svg",
+            format="svg",
+            bbox_inches="tight",
+        )
+
+    def generate_precision_recall(
+        self,
+        benchmarking_results: List[BenchmarkRunResults],
+        benchmark_generator: BenchmarkRunOutputGenerator,
+    ):
+        """
+        Generate and plot Precision-Recall curves for binary classification benchmark results.
+
+        Args:
+            benchmarking_results (List[BenchmarkRunResults]): List of benchmarking results for multiple runs.
+            benchmark_generator (BenchmarkRunOutputGenerator): Object containing benchmarking output generation details.
+        """
+        plt.figure()
+        for i, benchmark_result in enumerate(benchmarking_results):
+            precision, recall, thresh = precision_recall_curve(
+                benchmark_result.binary_classification_stats.labels,
+                benchmark_result.binary_classification_stats.scores,
+            )
+            precision_recall_auc = auc(recall, precision)
+            plt.plot(
+                recall,
+                precision,
+                label=f"{self.return_benchmark_name(benchmark_result)} Precision-Recall Curve "
+                f"(AUC = {precision_recall_auc:.2f})",
+                color=self.palette_hex_codes[i],
+            )
+
+        plt.plot(linestyle="--", color="gray")
+        plt.xlabel("Recall")
+        plt.ylabel("Precision")
+        plt.title("Precision-Recall Curve")
+        plt.legend(loc="upper center", bbox_to_anchor=(0.5, -0.15))
+        plt.savefig(
+            f"{benchmark_generator.prioritisation_type_file_prefix}_precision_recall_curve.svg",
+            format="svg",
+            bbox_inches="tight",
+        )
+
     def generate_non_cumulative_bar(
         self,
         benchmarking_results: List[BenchmarkRunResults],
@@ -405,6 +482,7 @@ def generate_plots(
     benchmark_generator: BenchmarkRunOutputGenerator,
     plot_type: str,
     title: str = None,
+    generate_from_tsv: bool = False,
 ) -> None:
     """
     Generate summary statistics bar plots for prioritisation.
@@ -416,8 +494,12 @@ def generate_plots(
         benchmark_generator (BenchmarkRunOutputGenerator): Object containing benchmarking output generation details.
         plot_type (str): Type of plot to be generated ("bar_stacked", "bar_cumulative", "bar_non_cumulative").
         title (str, optional): Title for the generated plot. Defaults to None.
+        generate_from_tsv (bool): Specify whether to generate plots from the TSV file. Defaults to False.
     """
     plot_generator = PlotGenerator()
+    if not generate_from_tsv:
+        plot_generator.generate_roc_curve(benchmarking_results, benchmark_generator)
+        plot_generator.generate_precision_recall(benchmarking_results, benchmark_generator)
     if plot_type == "bar_stacked":
         plot_generator.generate_stacked_bar_plot(benchmarking_results, benchmark_generator, title)
     elif plot_type == "bar_cumulative":
@@ -462,4 +544,4 @@ def generate_plots_from_benchmark_summary_tsv(
         raise ValueError(
             "Specify one analysis type (gene_analysis, variant_analysis, or disease_analysis)"
         )
-    generate_plots(benchmarking_results, benchmark_generator, plot_type, title)
+    generate_plots(benchmarking_results, benchmark_generator, plot_type, title, True)

pheval/analyse/generate_summary_outputs.py

@@ -3,6 +3,7 @@ from collections import defaultdict
 from copy import deepcopy
 from typing import List
 
+import numpy as np
 import pandas as pd
 
 from pheval.analyse.benchmark_generator import BenchmarkRunOutputGenerator
@@ -40,7 +41,19 @@ class RankComparisonGenerator:
             pd.DataFrame: DataFrame containing the calculated rank differences.
         """
         comparison_df = self._generate_dataframe()
-        comparison_df["rank_decrease"] = comparison_df.iloc[:, 3] - comparison_df.iloc[:, 2]
+        comparison_df["rank_change"] = comparison_df.iloc[:, 2] - comparison_df.iloc[:, 3]
+        comparison_df["rank_change"] = np.where(
+            (comparison_df.iloc[:, 2] == 0) & (comparison_df.iloc[:, 3] != 0),
+            "GAINED",
+            np.where(
+                (comparison_df.iloc[:, 3] == 0) & (comparison_df.iloc[:, 2] != 0),
+                "LOST",
+                comparison_df["rank_change"],
+            ),
+        )
+        comparison_df["rank_change"] = comparison_df["rank_change"].apply(
+            lambda x: int(x) if str(x).lstrip("-").isdigit() else x
+        )
         return comparison_df
 
     def generate_output(self, prefix: str, suffix: str) -> None:

pheval/analyse/variant_prioritisation_analysis.py

@@ -10,7 +10,11 @@ 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_closest_file_name
+from pheval.utils.file_utils import (
+    all_files,
+    files_with_suffix,
+    obtain_phenopacket_path_from_pheval_result,
+)
 from pheval.utils.phenopacket_utils import GenomicVariant, PhenopacketUtil, phenopacket_reader
 
 
@@ -228,7 +232,7 @@ 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_closest_file_name(
+    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)

pheval/cli_pheval_utils.py

@@ -253,22 +253,19 @@ def update_phenopackets_command(
     mutually_exclusive=["phenopacket_path"],
 )
 @click.option(
-    "--template-vcf-path",
-    "-t",
-    cls=MutuallyExclusiveOptionError,
+    "--hg19-template-vcf",
+    "-hg19",
     metavar="PATH",
     required=False,
-    help="Template VCF file",
-    mutually_exclusive=["vcf_dir"],
+    help="Template hg19 VCF file",
     type=Path,
 )
 @click.option(
-    "--vcf-dir",
-    "-v",
-    cls=MutuallyExclusiveOptionError,
+    "--hg38-template-vcf",
+    "-hg38",
     metavar="PATH",
-    help="Directory containing template VCF files",
-    mutually_exclusive=["template_vcf"],
+    required=False,
+    help="Template hg38 VCF file",
     type=Path,
 )
 @click.option(
@@ -284,13 +281,22 @@ def create_spiked_vcfs_command(
     phenopacket_path: Path,
     phenopacket_dir: Path,
     output_dir: Path,
-    template_vcf_path: Path = None,
-    vcf_dir: Path = None,
+    hg19_template_vcf: Path = None,
+    hg38_template_vcf: Path = None,
 ):
-    """Spikes variants into a template VCF file for a directory of phenopackets."""
+    """
+    Create spiked VCF from either a Phenopacket or a Phenopacket directory.
+
+    Args:
+        phenopacket_path (Path): Path to a single Phenopacket file (optional).
+        phenopacket_dir (Path): Path to a directory containing Phenopacket files (optional).
+        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).
+    """
     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, template_vcf_path, vcf_dir)
+    spike_vcfs(output_dir, phenopacket_path, phenopacket_dir, hg19_template_vcf, hg38_template_vcf)
 
 
 @click.command()

pheval/prepare/create_spiked_vcf.py

@@ -1,7 +1,6 @@
 import gzip
 import logging
 import re
-import secrets
 import urllib.parse
 from copy import copy
 from dataclasses import dataclass
@@ -10,6 +9,8 @@ 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.phenopacket_utils import (
     IncompatibleGenomeAssemblyError,
     PhenopacketRebuilder,
@@ -19,9 +20,6 @@ from pheval.utils.phenopacket_utils import (
     write_phenopacket,
 )
 
-from .custom_exceptions import InputError
-from ..utils.file_utils import all_files, files_with_suffix, is_gzipped
-
 info_log = logging.getLogger("info")
 
 genome_assemblies = {
@@ -91,39 +89,6 @@ class VcfHeader:
     chr_status: bool
 
 
-class VcfPicker:
-    """Choose a VCF file randomly from a directory if provided, otherwise selects the single template."""
-
-    def __init__(self, template_vcf: Path or None, vcf_dir: Path or None):
-        """
-        Initialise the VcfPicker.
-
-        Args:
-            template_vcf (Path or None): The path to a template VCF file, or None if not provided.
-            vcf_dir (Path or None): The directory containing VCF files, or None if not provided.
-        """
-        self.template_vcf = template_vcf
-        self.vcf_dir = vcf_dir
-
-    def pick_file_from_dir(self) -> Path:
-        """
-        Selects a VCF file from a directory at random.
-
-        Returns:
-            Path: The randomly selected VCF file path from the directory.
-        """
-        return secrets.choice(all_files(self.vcf_dir))
-
-    def pick_file(self) -> Path:
-        """
-        Select a VCF file randomly when given a directory; if not, the template VCF is assigned.
-
-        Returns:
-            Path: The selected VCF file path.
-        """
-        return self.pick_file_from_dir() if self.vcf_dir is not None else self.template_vcf
-
-
 def read_vcf(vcf_file: Path) -> List[str]:
     """
     Read the contents of a VCF file into memory, handling both uncompressed and gzipped files.
@@ -206,6 +171,72 @@ class VcfHeaderParser:
         return VcfHeader(sample_id, assembly, chr_status)
 
 
+@dataclass
+class VcfFile:
+    """
+    Represents a VCF file with its name, contents, and header information.
+
+    Attributes:
+        vcf_file_name (str): The name of the VCF file.
+        vcf_contents (List[str]): The contents of the VCF file.
+        vcf_header (VcfHeader): The parsed header information of the VCF file.
+    """
+
+    vcf_file_name: str = None
+    vcf_contents: List[str] = None
+    vcf_header: VcfHeader = None
+
+    @staticmethod
+    def populate_fields(template_vcf: Path):
+        """
+        Populate the fields of the VcfFile instance using the contents of a template VCF file.
+
+        Args:
+            template_vcf (Path): The path to the template VCF file.
+
+        Returns:
+            VcfFile: An instance of VcfFile with populated fields.
+
+        """
+        contents = read_vcf(template_vcf)
+        return VcfFile(template_vcf.name, contents, VcfHeaderParser(contents).parse_vcf_header())
+
+
+def select_vcf_template(
+    phenopacket_path: Path,
+    proband_causative_variants: List[ProbandCausativeVariant],
+    hg19_vcf_info: VcfFile,
+    hg38_vcf_info: VcfFile,
+) -> VcfFile:
+    """
+    Select the appropriate VCF template based on the assembly information of the proband causative variants.
+
+    Args:
+        phenopacket_path (Path): The path to the Phenopacket file.
+        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.
+
+    Returns:
+        VcfFile: The selected VCF template file based on the assembly information of the proband causative variants.
+
+    """
+    if proband_causative_variants[0].assembly in ["hg19", "GRCh37"]:
+        if hg19_vcf_info:
+            return hg19_vcf_info
+        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
+        else:
+            raise InputError("Must specify hg38 template VCF!")
+    else:
+        raise IncompatibleGenomeAssemblyError(
+            proband_causative_variants[0].assembly, phenopacket_path
+        )
+
+
 def check_variant_assembly(
     proband_causative_variants: list[ProbandCausativeVariant],
     vcf_header: VcfHeader,
@@ -229,7 +260,13 @@ def check_variant_assembly(
         raise ValueError("Too many genome assemblies!")
     if phenopacket_assembly[0] not in compatible_genome_assembly:
         raise IncompatibleGenomeAssemblyError(phenopacket_assembly, phenopacket_path)
-    if phenopacket_assembly[0] != vcf_header.assembly:
+    if (
+        phenopacket_assembly[0] in {"hg19", "GRCh37"}
+        and vcf_header.assembly not in {"hg19", "GRCh37"}
+    ) or (
+        phenopacket_assembly[0] in {"hg38", "GRCh38"}
+        and vcf_header.assembly not in {"hg38", "GRCh38"}
+    ):
         raise IncompatibleGenomeAssemblyError(
             assembly=phenopacket_assembly, phenopacket=phenopacket_path
         )
@@ -387,7 +424,8 @@ class VcfWriter:
 def spike_vcf_contents(
     phenopacket: Union[Phenopacket, Family],
     phenopacket_path: Path,
-    chosen_template_vcf: Path,
+    hg19_vcf_info: VcfFile,
+    hg38_vcf_info: VcfFile,
 ) -> tuple[str, List[str]]:
     """
     Spike VCF records with variants obtained from a Phenopacket or Family.
@@ -395,22 +433,28 @@ def spike_vcf_contents(
     Args:
         phenopacket (Union[Phenopacket, Family]): Phenopacket or Family containing causative variants.
         phenopacket_path (Path): Path to the Phenopacket file.
-        chosen_template_vcf (Path): Path to the chosen template VCF file.
+        hg19_vcf_info (VcfFile): VCF file info for hg19 template vcf.
+        hg38_vcf_info (VcfFile): VCF file info for hg38 template vcf.
 
     Returns:
         A tuple containing:
             assembly (str): The genome assembly information extracted from VCF header.
             modified_vcf_contents (List[str]): Modified VCF records with spiked variants.
     """
-    # this is a separate function to a click command as it will fail if annotated with click annotations
-    # and referenced from another click command
     phenopacket_causative_variants = PhenopacketUtil(phenopacket).causative_variants()
-    vcf_contents = read_vcf(chosen_template_vcf)
-    vcf_header = VcfHeaderParser(vcf_contents).parse_vcf_header()
-    check_variant_assembly(phenopacket_causative_variants, vcf_header, phenopacket_path)
+    chosen_template_vcf = select_vcf_template(
+        phenopacket_path, phenopacket_causative_variants, hg19_vcf_info, hg38_vcf_info
+    )
+    check_variant_assembly(
+        phenopacket_causative_variants, chosen_template_vcf.vcf_header, phenopacket_path
+    )
     return (
-        vcf_header.assembly,
-        VcfSpiker(vcf_contents, phenopacket_causative_variants, vcf_header).construct_vcf(),
+        chosen_template_vcf.vcf_header.assembly,
+        VcfSpiker(
+            chosen_template_vcf.vcf_contents,
+            phenopacket_causative_variants,
+            chosen_template_vcf.vcf_header,
+        ).construct_vcf(),
     )
 
 
@@ -418,7 +462,8 @@ def generate_spiked_vcf_file(
     output_dir: Path,
     phenopacket: Union[Phenopacket, Family],
     phenopacket_path: Path,
-    chosen_template_vcf: Path,
+    hg19_vcf_info: VcfFile,
+    hg38_vcf_info: VcfFile,
 ) -> File:
     """
     Write spiked VCF contents to a new file.
@@ -427,21 +472,17 @@ def generate_spiked_vcf_file(
         output_dir (Path): Path to the directory to store the generated file.
         phenopacket (Union[Phenopacket, Family]): Phenopacket or Family containing causative variants.
         phenopacket_path (Path): Path to the Phenopacket file.
-        chosen_template_vcf (Path): Path to the chosen template VCF file.
-
+        hg19_vcf_info (VcfFile): VCF file info for hg19 template vcf.
+        hg38_vcf_info (VcfFile): VCF file info for hg38 template vcf.
     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, chosen_template_vcf
-    )
-    spiked_vcf_path = (
-        output_dir.joinpath(phenopacket_path.name.replace(".json", ".vcf.gz"))
-        if is_gzipped(chosen_template_vcf)
-        else output_dir.joinpath(phenopacket_path.name.replace(".json", ".vcf"))
+        phenopacket, phenopacket_path, hg19_vcf_info, hg38_vcf_info
     )
+    spiked_vcf_path = output_dir.joinpath(phenopacket_path.name.replace(".json", ".vcf.gz"))
     VcfWriter(spiked_vcf, spiked_vcf_path).write_vcf_file()
     return File(
         uri=urllib.parse.unquote(spiked_vcf_path.as_uri()),
@@ -449,8 +490,19 @@ def generate_spiked_vcf_file(
     )
 
 
+def spike_and_update_phenopacket(hg19_vcf_info, hg38_vcf_info, output_dir, phenopacket_path):
+    phenopacket = phenopacket_reader(phenopacket_path)
+    spiked_vcf_file_message = generate_spiked_vcf_file(
+        output_dir, phenopacket, phenopacket_path, hg19_vcf_info, hg38_vcf_info
+    )
+    updated_phenopacket = PhenopacketRebuilder(phenopacket).add_spiked_vcf_path(
+        spiked_vcf_file_message
+    )
+    write_phenopacket(updated_phenopacket, phenopacket_path)
+
+
 def create_spiked_vcf(
-    output_dir: Path, phenopacket_path: Path, template_vcf_path: Path, vcf_dir: Path
+    output_dir: Path, phenopacket_path: Path, hg19_template_vcf: Path, hg38_template_vcf: Path
 ) -> None:
     """
     Create a spiked VCF for a Phenopacket.
@@ -458,27 +510,21 @@ def create_spiked_vcf(
     Args:
         output_dir (Path): The directory to store the generated spiked VCF file.
         phenopacket_path (Path): Path to the Phenopacket file.
-        template_vcf_path (Path): Path to the template VCF file (optional).
-        vcf_dir (Path): Path to the directory containing VCF 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).
 
     Raises:
-        InputError: If both template_vcf_path and vcf_dir are None.
+        InputError: If both hg19_template_vcf and hg38_template_vcf are None.
     """
-    if template_vcf_path is None and vcf_dir is None:
-        raise InputError("Either a template_vcf or vcf_dir must be specified")
-    vcf_file_path = VcfPicker(template_vcf_path, vcf_dir).pick_file()
-    phenopacket = phenopacket_reader(phenopacket_path)
-    spiked_vcf_file_message = generate_spiked_vcf_file(
-        output_dir, phenopacket, phenopacket_path, vcf_file_path
-    )
-    updated_phenopacket = PhenopacketRebuilder(phenopacket).add_spiked_vcf_path(
-        spiked_vcf_file_message
-    )
-    write_phenopacket(updated_phenopacket, phenopacket_path)
+    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")
+    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)
 
 
 def create_spiked_vcfs(
-    output_dir: Path, phenopacket_dir: Path, template_vcf_path: Path, vcf_dir: Path
+    output_dir: Path, phenopacket_dir: Path, hg19_template_vcf: Path, hg38_template_vcf: Path
 ) -> None:
     """
     Create a spiked VCF for a directory of Phenopackets.
@@ -486,35 +532,26 @@ def create_spiked_vcfs(
     Args:
         output_dir (Path): The directory to store the generated spiked VCF file.
         phenopacket_dir (Path): Path to the Phenopacket directory.
-        template_vcf_path (Path): Path to the template VCF file (optional).
-        vcf_dir (Path): Path to the directory containing VCF files (optional).
+        hg19_template_vcf (Path): Path to the template hg19 VCF file (optional).
+        hg38_template_vcf (Path): Path to the template hg19 VCF file (optional).
 
     Raises:
-        InputError: If both template_vcf_path and vcf_dir are None.
+        InputError: If both hg19_template_vcf and hg38_template_vcf are None.
     """
-    if template_vcf_path is None and vcf_dir is None:
-        raise InputError("Either a template_vcf or vcf_dir must be specified")
+    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")
+    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"):
-        vcf_file_path = VcfPicker(template_vcf_path, vcf_dir).pick_file()
-        phenopacket = phenopacket_reader(phenopacket_path)
-        spiked_vcf_file_message = generate_spiked_vcf_file(
-            output_dir, phenopacket, phenopacket_path, vcf_file_path
-        )
-        updated_phenopacket = PhenopacketRebuilder(phenopacket).add_spiked_vcf_path(
-            spiked_vcf_file_message
-        )
-        write_phenopacket(updated_phenopacket, phenopacket_path)
-    # or made a lambda one-liner for maximum wtf...
-    # [spike_vcf(path, output_dir, template_vcf, vcf_dir) for path in phenopacket_dir.iterdir() if path.suffix ==
-    # ".json"]
+        spike_and_update_phenopacket(hg19_vcf_info, hg38_vcf_info, output_dir, phenopacket_path)
 
 
 def spike_vcfs(
     output_dir: Path,
     phenopacket_path: Path,
     phenopacket_dir: Path,
-    template_vcf_path: Path,
-    vcf_dir: Path,
+    hg19_template_vcf: Path,
+    hg38_template_vcf: Path,
 ) -> None:
     """
     Create spiked VCF from either a Phenopacket or a Phenopacket directory.
@@ -523,10 +560,10 @@ def spike_vcfs(
         output_dir (Path): The directory to store the generated spiked VCF file(s).
         phenopacket_path (Path): Path to a single Phenopacket file (optional).
         phenopacket_dir (Path): Path to a directory containing Phenopacket files (optional).
-        template_vcf_path (Path): Path to the template VCF file (optional).
-        vcf_dir (Path): Path to the directory containing VCF 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).
     """
     if phenopacket_path is not None:
-        create_spiked_vcf(output_dir, phenopacket_path, template_vcf_path, vcf_dir)
+        create_spiked_vcf(output_dir, phenopacket_path, hg19_template_vcf, hg38_template_vcf)
     elif phenopacket_dir is not None:
-        create_spiked_vcfs(output_dir, phenopacket_dir, template_vcf_path, vcf_dir)
+        create_spiked_vcfs(output_dir, phenopacket_dir, hg19_template_vcf, hg38_template_vcf)

pheval/utils/file_utils.py

@@ -1,4 +1,3 @@
-import difflib
 import itertools
 import re
 import unicodedata
@@ -71,23 +70,33 @@ def normalise_file_name(file_path: Path) -> str:
     return re.sub("[\u0300-\u036f]", "", normalised_file_name)
 
 
-def obtain_closest_file_name(file_to_be_queried: Path, file_paths: list[Path]) -> Path:
+def obtain_phenopacket_path_from_pheval_result(
+    pheval_result_path: Path, phenopacket_paths: list[Path]
+) -> Path:
     """
-    Obtains the closest file name when given a template file name
-    and a list of full paths of files to be queried.
+    Obtains the phenopacket file name when given a pheval result file name
+    and a list of full paths of phenopackets to be queried.
 
     Args:
-        file_to_be_queried (Path): The template file name to find the closest match.
-        file_paths (list[Path]): List of full paths of files to be queried.
+        pheval_result_path (Path): The PhEval result.
+        phenopacket_paths (list[Path]): List of full paths of phenopackets to be queried.
 
     Returns:
-        Path: The closest matching file path from the provided list.
+        Path: The matching phenopacket file path from the provided list.
     """
-    stems = [Path(file_path).stem for file_path in file_paths]
-    closest_file_match = difflib.get_close_matches(
-        str(Path(file_to_be_queried).stem), stems, cutoff=0.1, n=1
-    )[0]
-    return [file_path for file_path in file_paths if closest_file_match == str(file_path.stem)][0]
+    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):

pheval/utils/phenopacket_utils.py

@@ -467,7 +467,9 @@ 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,
+                    chrom=g.variant_interpretation.variation_descriptor.vcf_record.chrom.replace(
+                        "chr", ""
+                    ),
                     pos=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-0.3.1.dist-info → pheval-0.3.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pheval
-Version: 0.3.1
+Version: 0.3.3
 Summary: 
 Author: Yasemin Bridges
 Author-email: y.bridges@qmul.ac.uk

{pheval-0.3.1.dist-info → pheval-0.3.3.dist-info}/RECORD

@@ -3,21 +3,21 @@ pheval/analyse/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pheval/analyse/analysis.py,sha256=ponm3P8nvzJNmcrNZ2_KudEhWSaWshd_Gd30D-aau8s,7743
 pheval/analyse/benchmark_generator.py,sha256=AeuwbaPb4j_dyBGPRgEBxQk2NahDb5u4xHyFiqp5Fes,5943
 pheval/analyse/benchmarking_data.py,sha256=aNZkWdmWemlnC1Tg35MtR60S9YC71QWS2rMuzkUc3w0,768
-pheval/analyse/binary_classification_stats.py,sha256=ZBAvhMVPYSFg3asONUG1w24JhYTjG03RG_C9uohQntI,11373
-pheval/analyse/disease_prioritisation_analysis.py,sha256=ttdgUX5ZKT74gKgsRrnyH8zKFxhcJxVOtZTsAdheGxU,12596
-pheval/analyse/gene_prioritisation_analysis.py,sha256=raEjzJFvAvS3wE0yrYcSIQzBe6s_lOgJMqe_p_AFgZY,12320
-pheval/analyse/generate_plots.py,sha256=gU7NYr1zgnXEXAZR-nHLql3farQEaUN5gkgu2ywTJho,17779
-pheval/analyse/generate_summary_outputs.py,sha256=tpHjbyme3FlkflGcTIgQ4H4xyN6FZ5Jmm-ImjAbSpYU,6071
+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/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/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=_yYgknFHqL0_nlpBeQdo9D1Jnd99BcUkA733uxTPpcg,12331
+pheval/analyse/variant_prioritisation_analysis.py,sha256=ApmUeTW0cl_BPh7LusbApxtgjEXEkhuNFyh0DxKKpgU,12384
 pheval/cli.py,sha256=4l9xZfxBfLCcm7PDdhMWgTvTKbQt5sJ2bYHf7kU1dO4,1493
 pheval/cli_pheval.py,sha256=fWbKUcPTZZSa1EJEtH_lNn1XE6qRApRHihqUZS5owrA,2424
-pheval/cli_pheval_utils.py,sha256=wVLH0Bk2WrvTBkH-G5wC3Xgo6KftX9zSwonC2DVBpP8,16929
+pheval/cli_pheval_utils.py,sha256=i5rSLR_moti1VM0of4uOLdX7wbwUcM7spLO9zw6bHrc,17257
 pheval/config_parser.py,sha256=lh-Dy_FflXJUnRC3HYaEdSvPAsNZWQZlEr1hHQigrTM,1227
 pheval/constants.py,sha256=TWBgWOc05FGXFu63fs-hEHS2IJkLLAPHtMppiWBfBOg,349
 pheval/implementations/__init__.py,sha256=BMUTotjTdgy5j5xubWCIQgRXrSQ1ZIcjooer7r299Zo,1228
@@ -27,7 +27,7 @@ pheval/post_processing/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3
 pheval/post_processing/post_processing.py,sha256=2srdlw2D3qMh2B3PUSDvA6COYlbXINC08Wt4eccMZp8,16030
 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=jd_OxcSVh25qBcrDNkD1d586jNuNyOjjxArwgCSCKN0,18755
+pheval/prepare/create_spiked_vcf.py,sha256=KZIyjtDDTqJj3hxL3u4YP6P0toA4RN1oPeDrzLMB2z4,20235
 pheval/prepare/custom_exceptions.py,sha256=_G3_95dPtHIs1SviYBV1j7cYc-hxlhuw8hhnYdzByYY,1719
 pheval/prepare/update_phenopacket.py,sha256=36dLIUSO_4EakGkjVwlecu-he-lOPXMhoWoOkeRYMV4,4753
 pheval/resources/alternate_ouputs/CADA_results.txt,sha256=Rinn2TtfwFNsx0aEWegKJOkjKnBm-Mf54gdaT3bWP0k,547
@@ -45,12 +45,12 @@ 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=ESAXWtfpCAZX6T6nU6vb1x0of5S-eYhu639geJBu1es,4361
-pheval/utils/phenopacket_utils.py,sha256=hBEWl9mOP9D7odSaL6lIY__dbXn7Sc3TZX0Si-nPYaE,24379
+pheval/utils/file_utils.py,sha256=9HoCmtF73D3wY6bBhFLefMBI5uhvCe_meZeHXQzF_ts,4640
+pheval/utils/phenopacket_utils.py,sha256=iWYWfneaI47lx5w56-ILwvyLRaxHVoHnJ3EbVrja8-k,24444
 pheval/utils/semsim_utils.py,sha256=s7ZCR2VfPYnOh7ApX6rv66eGoVSm9QJaVYOWBEhlXpo,6151
 pheval/utils/utils.py,sha256=9V6vCT8l1g4O2-ZATYqsVyd7AYZdWGd-Ksy7_oIC3eE,2343
-pheval-0.3.1.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-pheval-0.3.1.dist-info/METADATA,sha256=wVyoDa-Xs4ztciDaO56ogC3rjhukYhCe3HFqmqEtClA,1810
-pheval-0.3.1.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
-pheval-0.3.1.dist-info/entry_points.txt,sha256=o9gSwDkvT4-lqKy4mlsftd1nzP9WUOXQCfnbqycURd0,81
-pheval-0.3.1.dist-info/RECORD,,
+pheval-0.3.3.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+pheval-0.3.3.dist-info/METADATA,sha256=I0Njs6iBWs0Ag1bf81pNaRKYPcw8dkRKaG454m-6bJA,1810
+pheval-0.3.3.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+pheval-0.3.3.dist-info/entry_points.txt,sha256=o9gSwDkvT4-lqKy4mlsftd1nzP9WUOXQCfnbqycURd0,81
+pheval-0.3.3.dist-info/RECORD,,

{pheval-0.3.1.dist-info → pheval-0.3.3.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 1.8.1
+Generator: poetry-core 1.9.0
 Root-Is-Purelib: true
 Tag: py3-none-any