pheval 0.3.2__py3-none-any.whl → 0.3.4__py3-none-any.whl

pheval/analyse/generate_plots.py

@@ -482,6 +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.
@@ -493,10 +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()
-    plot_generator.generate_roc_curve(benchmarking_results, benchmark_generator)
-    plot_generator.generate_precision_recall(benchmarking_results, benchmark_generator)
+    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":
@@ -541,4 +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/cli.py

@@ -10,6 +10,7 @@ from .cli_pheval_utils import (
     benchmark_comparison,
     create_spiked_vcfs_command,
     generate_stats_plot,
+    prepare_corpus_command,
     scramble_phenopackets_command,
     semsim_scramble_command,
     semsim_to_exomiserdb_command,
@@ -60,6 +61,7 @@ pheval_utils.add_command(benchmark)
 pheval_utils.add_command(benchmark_comparison)
 pheval_utils.add_command(semsim_to_exomiserdb_command)
 pheval_utils.add_command(generate_stats_plot)
+pheval_utils.add_command(prepare_corpus_command)
 
 if __name__ == "__main__":
     main()

pheval/cli_pheval_utils.py

@@ -15,6 +15,7 @@ from pheval.analyse.run_data_parser import parse_run_data_text_file
 from pheval.prepare.create_noisy_phenopackets import scramble_phenopackets
 from pheval.prepare.create_spiked_vcf import spike_vcfs
 from pheval.prepare.custom_exceptions import InputError, MutuallyExclusiveOptionError
+from pheval.prepare.prepare_corpus import prepare_corpus
 from pheval.prepare.update_phenopacket import update_phenopackets
 from pheval.utils.exomiser import semsim_to_exomiserdb
 from pheval.utils.semsim_utils import percentage_diff, semsim_heatmap_plot
@@ -253,22 +254,19 @@ 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 +282,22 @@ 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()
@@ -600,3 +607,106 @@ def generate_stats_plot(
     generate_plots_from_benchmark_summary_tsv(
         benchmarking_tsv, gene_analysis, variant_analysis, disease_analysis, plot_type, title
     )
+
+
+@click.command("prepare-corpus")
+@click.option(
+    "--phenopacket-dir",
+    "-p",
+    required=True,
+    metavar="PATH",
+    help="Path to phenopacket corpus directory..",
+    type=Path,
+)
+@click.option(
+    "--variant-analysis/--no-variant-analysis",
+    default=False,
+    required=False,
+    type=bool,
+    show_default=True,
+    help="Specify whether to check for complete variant records in the phenopackets.",
+)
+@click.option(
+    "--gene-analysis/--no-gene-analysis",
+    default=False,
+    required=False,
+    type=bool,
+    show_default=True,
+    help="Specify whether to check for complete gene records in the phenopackets.",
+)
+@click.option(
+    "--disease-analysis/--no-disease-analysis",
+    default=False,
+    required=False,
+    type=bool,
+    show_default=True,
+    help="Specify whether to check for complete disease records in the phenopackets.",
+)
+@click.option(
+    "--gene-identifier",
+    "-g",
+    required=False,
+    help="Gene identifier to update in phenopacket",
+    type=click.Choice(["ensembl_id", "entrez_id", "hgnc_id"]),
+)
+@click.option(
+    "--hg19-template-vcf",
+    "-hg19",
+    metavar="PATH",
+    required=False,
+    help="Template hg19 VCF file",
+    type=Path,
+)
+@click.option(
+    "--hg38-template-vcf",
+    "-hg38",
+    metavar="PATH",
+    required=False,
+    help="Template hg38 VCF file",
+    type=Path,
+)
+@click.option(
+    "--output-dir",
+    "-o",
+    metavar="PATH",
+    required=True,
+    help="Path to output prepared corpus.",
+    default="prepared_corpus",
+    type=Path,
+)
+def prepare_corpus_command(
+    phenopacket_dir: Path,
+    variant_analysis: bool,
+    gene_analysis: bool,
+    disease_analysis: bool,
+    gene_identifier: str,
+    hg19_template_vcf: Path,
+    hg38_template_vcf: 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.
+    """
+    prepare_corpus(
+        phenopacket_dir,
+        variant_analysis,
+        gene_analysis,
+        disease_analysis,
+        gene_identifier,
+        hg19_template_vcf,
+        hg38_template_vcf,
+        output_dir,
+    )

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/prepare/prepare_corpus.py

@@ -0,0 +1,67 @@
+import logging
+from pathlib import Path
+
+from pheval.prepare.create_spiked_vcf import create_spiked_vcf
+from pheval.prepare.update_phenopacket import create_updated_phenopacket
+from pheval.utils.file_utils import all_files
+from pheval.utils.phenopacket_utils import PhenopacketUtil, phenopacket_reader
+
+info_log = logging.getLogger("info")
+
+
+def prepare_corpus(
+    phenopacket_dir: Path,
+    variant_analysis: bool,
+    gene_analysis: bool,
+    disease_analysis: bool,
+    gene_identifier: str,
+    hg19_template_vcf: Path,
+    hg38_template_vcf: Path,
+    output_dir: Path,
+) -> None:
+    """
+    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.
+    """
+    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 variant_analysis:
+            if phenopacket_util.check_incomplete_variant_record():
+                info_log.warning(
+                    f"Removed {phenopacket_path.name} from the corpus due to missing variant fields."
+                )
+                continue
+        if gene_analysis:
+            if phenopacket_util.check_incomplete_gene_record():
+                info_log.warning(
+                    f"Removed {phenopacket_path.name} from the corpus due to missing gene fields."
+                )
+                continue
+        if disease_analysis:
+            if phenopacket_util.check_incomplete_disease_record():
+                info_log.warning(
+                    f"Removed {phenopacket_path.name} from the corpus due to missing disease fields."
+                )
+                continue
+        if gene_identifier:
+            create_updated_phenopacket(
+                gene_identifier, phenopacket_path, output_dir.joinpath("phenopackets")
+            )
+        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
+            )

pheval/prepare/update_phenopacket.py

@@ -38,8 +38,7 @@ def update_outdated_gene_context(
     interpretations = PhenopacketUtil(phenopacket).interpretations()
     updated_interpretations = GeneIdentifierUpdater(
         hgnc_data=hgnc_data, gene_identifier=gene_identifier
-    ).update_genomic_interpretations_gene_identifier(interpretations)
-
+    ).update_genomic_interpretations_gene_identifier(interpretations, phenopacket_path)
     return PhenopacketRebuilder(phenopacket).update_interpretations(updated_interpretations)
 
 

pheval/utils/phenopacket_utils.py

@@ -1,6 +1,5 @@
 import json
-
-# import logging
+import logging
 import os
 from collections import defaultdict
 from copy import copy
@@ -22,6 +21,8 @@ from phenopackets import (
 
 from pheval.prepare.custom_exceptions import IncorrectFileFormatError
 
+info_log = logging.getLogger("info")
+
 
 class IncompatibleGenomeAssemblyError(Exception):
     """Exception raised for incompatible genome assembly."""
@@ -467,7 +468,9 @@ 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,
@@ -475,6 +478,59 @@ class PhenopacketUtil:
                 variants.append(variant)
         return variants
 
+    def check_incomplete_variant_record(self) -> bool:
+        """
+        Check if any variant record in the phenopacket has incomplete information.
+
+        This method iterates through the diagnosed variant records and checks if any of them
+        have missing or incomplete information such as empty chromosome, position, reference,
+        or alternate allele.
+
+        Returns:
+            bool: True if any variant record is incomplete, False otherwise.
+        """
+        variants = self.diagnosed_variants()
+        for variant in variants:
+            if (
+                variant.chrom == ""
+                or variant.pos == 0
+                or variant.pos == ""
+                or variant.ref == ""
+                or variant.alt == ""
+            ):
+                return True
+        return False
+
+    def check_incomplete_gene_record(self) -> bool:
+        """
+        Check if any gene record in the phenopacket has incomplete information.
+
+        This method iterates through the diagnosed gene records and checks if any of them
+        have missing or incomplete information such as gene name, or gene identifier.
+
+        Returns:
+            bool: True if any gene record is incomplete, False otherwise.
+        """
+        genes = self.diagnosed_genes()
+        for gene in genes:
+            if gene.gene_symbol == "" or gene.gene_identifier == "":
+                return True
+        return False
+
+    def check_incomplete_disease_record(self) -> bool:
+        """
+        Check if any disease record in the phenopacket has incomplete information.
+
+        This method iterates through the diagnosed disease records and checks if any of them
+        have missing or incomplete information such as empty disease name, or disease identifier.
+
+        Returns:
+            bool: True if any disease record is incomplete, False otherwise.
+        """
+        if len(self.diagnoses()) == 0:
+            return True
+        return False
+
 
 class PhenopacketRebuilder:
     """Class for rebuilding a Phenopacket"""
@@ -653,7 +709,7 @@ class GeneIdentifierUpdater:
                         ]
 
     def update_genomic_interpretations_gene_identifier(
-        self, interpretations: List[Interpretation]
+        self, interpretations: List[Interpretation], phenopacket_path: Path
     ) -> List[Interpretation]:
         """
         Update the genomic interpretations of a Phenopacket.
@@ -667,10 +723,16 @@ class GeneIdentifierUpdater:
         updated_interpretations = copy(list(interpretations))
         for updated_interpretation in updated_interpretations:
             for g in updated_interpretation.diagnosis.genomic_interpretations:
+                updated_gene_identifier = self.find_identifier(
+                    g.variant_interpretation.variation_descriptor.gene_context.symbol
+                )
+                info_log.info(
+                    f"Updating gene identifier in {phenopacket_path} from "
+                    f"{g.variant_interpretation.variation_descriptor.gene_context.value_id}"
+                    f"to {updated_gene_identifier}"
+                )
                 g.variant_interpretation.variation_descriptor.gene_context.value_id = (
-                    self.find_identifier(
-                        g.variant_interpretation.variation_descriptor.gene_context.symbol
-                    )
+                    updated_gene_identifier
                 )
                 del g.variant_interpretation.variation_descriptor.gene_context.alternate_ids[:]
                 g.variant_interpretation.variation_descriptor.gene_context.alternate_ids.extend(

{pheval-0.3.2.dist-info → pheval-0.3.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pheval
-Version: 0.3.2
+Version: 0.3.4
 Summary: 
 Author: Yasemin Bridges
 Author-email: y.bridges@qmul.ac.uk

{pheval-0.3.2.dist-info → pheval-0.3.4.dist-info}/RECORD

@@ -6,7 +6,7 @@ pheval/analyse/benchmarking_data.py,sha256=aNZkWdmWemlnC1Tg35MtR60S9YC71QWS2rMuz
 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=zjsVzf-WsMG7jb5Y_FVYeOHQwu9lz_V90a9LApUlsDo,21163
+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
@@ -15,9 +15,9 @@ pheval/analyse/prioritisation_result_types.py,sha256=qJoB6O-lFYmzAMcTQeDJZQNLJ6h
 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/cli.py,sha256=4l9xZfxBfLCcm7PDdhMWgTvTKbQt5sJ2bYHf7kU1dO4,1493
+pheval/cli.py,sha256=X4tDi7e3VB3v2RawkqIbfv4SFPCBuQwMXMnYCPTGtIo,1570
 pheval/cli_pheval.py,sha256=fWbKUcPTZZSa1EJEtH_lNn1XE6qRApRHihqUZS5owrA,2424
-pheval/cli_pheval_utils.py,sha256=wVLH0Bk2WrvTBkH-G5wC3Xgo6KftX9zSwonC2DVBpP8,16929
+pheval/cli_pheval_utils.py,sha256=kySsSa7NyewwVwYBMu93y8l5_qSJaVkdXklGchcXExU,20504
 pheval/config_parser.py,sha256=lh-Dy_FflXJUnRC3HYaEdSvPAsNZWQZlEr1hHQigrTM,1227
 pheval/constants.py,sha256=TWBgWOc05FGXFu63fs-hEHS2IJkLLAPHtMppiWBfBOg,349
 pheval/implementations/__init__.py,sha256=BMUTotjTdgy5j5xubWCIQgRXrSQ1ZIcjooer7r299Zo,1228
@@ -27,9 +27,10 @@ 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/prepare/prepare_corpus.py,sha256=q9sCTfpzEHeJpzo0nNc8WhdZPeXq_bm_udQaLCAbAJI,3187
+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
 pheval/resources/alternate_ouputs/OVA_results.txt,sha256=_5XFCR4W04D-W7DObpALLsa0-693g2kiIUB_uo79aHk,9845
@@ -46,11 +47,11 @@ 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=hBEWl9mOP9D7odSaL6lIY__dbXn7Sc3TZX0Si-nPYaE,24379
+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-0.3.2.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-pheval-0.3.2.dist-info/METADATA,sha256=8dvmkrDAkmmwiOvMWltnb_oXGo8IQTC1-iJImlsW-m8,1810
-pheval-0.3.2.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-pheval-0.3.2.dist-info/entry_points.txt,sha256=o9gSwDkvT4-lqKy4mlsftd1nzP9WUOXQCfnbqycURd0,81
-pheval-0.3.2.dist-info/RECORD,,
+pheval-0.3.4.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+pheval-0.3.4.dist-info/METADATA,sha256=pG569TPPJkj7dQ6C-SmMXRBRN-B2aw7hWSoMoa5k-0E,1810
+pheval-0.3.4.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+pheval-0.3.4.dist-info/entry_points.txt,sha256=o9gSwDkvT4-lqKy4mlsftd1nzP9WUOXQCfnbqycURd0,81
+pheval-0.3.4.dist-info/RECORD,,