pheval 0.3.3__tar.gz → 0.3.5__tar.gz

{pheval-0.3.3 → pheval-0.3.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pheval
-Version: 0.3.3
+Version: 0.3.5
 Summary: 
 Author: Yasemin Bridges
 Author-email: y.bridges@qmul.ac.uk

{pheval-0.3.3 → pheval-0.3.5}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "pheval"
-version = "0.3.3"
+version = "0.3.5"
 description = ""
 authors = ["Yasemin Bridges <y.bridges@qmul.ac.uk>",
   "Julius Jacobsen <j.jacobsen@qmul.ac.uk>",

{pheval-0.3.3 → pheval-0.3.5}/src/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-0.3.3 → pheval-0.3.5}/src/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
@@ -606,3 +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-0.3.5/src/pheval/prepare/prepare_corpus.py

@@ -0,0 +1,73 @@
+import logging
+import shutil
+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 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
+            )
+        if gene_identifier:
+            create_updated_phenopacket(
+                gene_identifier, phenopacket_path, output_dir.joinpath("phenopackets")
+            )
+        else:
+            # if not updating phenopacket gene identifiers then copy phenopacket as is to output directory
+            shutil.copy(
+                phenopacket_path, output_dir.joinpath(f"phenopackets/{phenopacket_path.name}")
+            )

{pheval-0.3.3 → pheval-0.3.5}/src/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-0.3.3 → pheval-0.3.5}/src/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."""
@@ -477,6 +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"""
@@ -655,7 +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.
@@ -669,10 +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(