pheval 0.5.2__tar.gz → 0.5.3__tar.gz

{pheval-0.5.2 → pheval-0.5.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: pheval
-Version: 0.5.2
+Version: 0.5.3
 Summary: 
 Author: Yasemin Bridges
 Author-email: y.bridges@qmul.ac.uk

{pheval-0.5.2 → pheval-0.5.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "pheval"
-version = "0.5.2"
+version = "0.5.3"
 description = ""
 authors = ["Yasemin Bridges <y.bridges@qmul.ac.uk>",
   "Julius Jacobsen <j.jacobsen@qmul.ac.uk>",

{pheval-0.5.2 → pheval-0.5.3}/src/pheval/cli_pheval.py

@@ -2,12 +2,16 @@
 Monarch Initiative
 """
 
+import time
 from pathlib import Path
 
 import click
 
 from pheval.implementations import get_implementation_resolver
 from pheval.utils.file_utils import write_metadata
+from pheval.utils.logger import get_logger
+
+logger = get_logger()
 
 
 @click.command()
@@ -84,11 +88,18 @@ def run(
         config (Path): The path of the configuration file (optional e.g., config.yaml)
         version (str): The version of the tool implementation
     """
+    logger.info(f"Executing {runner}.")
+    start_time = time.perf_counter()
     runner_class = get_implementation_resolver().lookup(runner)
     runner_instance = runner_class(input_dir, testdata_dir, tmp_dir, output_dir, config, version)
     runner_instance.build_output_directory_structure()
+    logger.info("Executing prepare phase.")
     runner_instance.prepare()
+    logger.info("Executing run phase.")
     runner_instance.run()
+    logger.info("Executing post-processing phase.")
     runner_instance.post_process()
     run_metadata = runner_instance.construct_meta_data()
+    logger.info(f"Writing metadata for run to {output_dir}.")
     write_metadata(output_dir, run_metadata)
+    logger.info(f"Run completed! Total time: {time.perf_counter() - start_time:.2f} seconds.")

{pheval-0.5.2 → pheval-0.5.3}/src/pheval/config_parser.py

@@ -6,6 +6,10 @@ import yaml
 from serde import serde
 from serde.yaml import from_yaml
 
+from pheval.utils.logger import get_logger
+
+logger = get_logger()
+
 
 @serde
 @dataclass
@@ -34,6 +38,7 @@ class InputDirConfig:
 
 def parse_input_dir_config(input_dir: Path) -> InputDirConfig:
     """Reads the config file."""
+    logger.info(f"Parsing config.yaml located in {input_dir}.")
     with open(Path(input_dir).joinpath("config.yaml"), "r") as config_file:
         config = yaml.safe_load(config_file)
     config_file.close()

{pheval-0.5.2 → pheval-0.5.3}/src/pheval/post_processing/post_processing.py

@@ -180,6 +180,10 @@ def generate_gene_result(
         phenopacket_dir (Path): Path to the Phenopacket directory
     """
     output_file = output_dir.joinpath(f"pheval_gene_results/{result_path.stem}-gene_result.parquet")
+    logger.info(
+        f"Writing classified results for {len(all_files(phenopacket_dir))} "
+        f"phenopackets to {output_dir.joinpath('pheval_gene_results')}"
+    )
     create_empty_pheval_result(
         phenopacket_dir, output_dir.joinpath("pheval_gene_results"), ResultType.GENE
     )
@@ -210,6 +214,10 @@ def generate_variant_result(
     output_file = output_dir.joinpath(
         f"pheval_variant_results/{result_path.stem}-variant_result.parquet"
     )
+    logger.info(
+        f"Writing classified results for {len(all_files(phenopacket_dir))} "
+        f"phenopackets to {output_dir.joinpath('pheval_variant_results')}"
+    )
     create_empty_pheval_result(
         phenopacket_dir, output_dir.joinpath("pheval_variant_results"), ResultType.VARIANT
     )
@@ -242,6 +250,10 @@ def generate_disease_result(
     output_file = output_dir.joinpath(
         f"pheval_disease_results/{result_path.stem}-disease_result.parquet"
     )
+    logger.info(
+        f"Writing classified results for {len(all_files(phenopacket_dir))} "
+        f"phenopackets to {output_dir.joinpath('pheval_disease_results')}"
+    )
     create_empty_pheval_result(
         phenopacket_dir, output_dir.joinpath("pheval_disease_results"), ResultType.DISEASE
     )

{pheval-0.5.2 → pheval-0.5.3}/src/pheval/prepare/create_noisy_phenopackets.py

@@ -1,4 +1,5 @@
 import random
+import time
 from pathlib import Path
 from typing import List, Union
 
@@ -6,7 +7,8 @@ from oaklib.implementations.pronto.pronto_implementation import ProntoImplementa
 from oaklib.resource import OntologyResource
 from phenopackets import Family, OntologyClass, Phenopacket, PhenotypicFeature
 
-from pheval.utils.file_utils import files_with_suffix
+from pheval.utils.file_utils import all_files, files_with_suffix
+from pheval.utils.logger import get_logger
 from pheval.utils.phenopacket_utils import (
     PhenopacketRebuilder,
     PhenopacketUtil,
@@ -14,6 +16,8 @@ from pheval.utils.phenopacket_utils import (
     write_phenopacket,
 )
 
+logger = get_logger()
+
 
 def load_ontology(local_cached_ontology: Path = None) -> ProntoImplementation:
     """
@@ -24,9 +28,11 @@ def load_ontology(local_cached_ontology: Path = None) -> ProntoImplementation:
         ProntoImplementation: An instance of ProntoImplementation containing the loaded HPO.
     """
     if local_cached_ontology is None:
+        logger.warning("No local cached ontology found, using default ontology.")
         resource = OntologyResource(slug="hp.obo", local=False)
         return ProntoImplementation(resource)
     else:
+        logger.info(f"Loading local ontology from {local_cached_ontology}.")
         resource = OntologyResource(slug=local_cached_ontology, local=True)
         return ProntoImplementation(resource)
 
@@ -241,6 +247,7 @@ class HpoRandomiser:
         """
         phenopacket_files = files_with_suffix(phenopacket_dir, ".json")
         for phenopacket_path in phenopacket_files:
+            logger.info(f"Scrambling {phenopacket_path.name}.")
             phenopacket = phenopacket_reader(phenopacket_path)
             created_noisy_phenopacket = self.add_noise_to_phenotypic_profile(phenopacket)
             write_phenopacket(
@@ -268,14 +275,23 @@ def scramble_phenopackets(
         scramble_factor (float): A factor determining the level of scrambling for phenotypic features.
         local_cached_ontology (Path): The path to the local cached ontology.
     """
+    start_time = time.perf_counter()
+    logger.info("Initiating scrambling.")
+    logger.info(f"Created directory {output_dir}.")
+    logger.info(f"Scramble factor set to {scramble_factor}.")
     output_dir.mkdir(exist_ok=True)
     ontology = load_ontology(local_cached_ontology)
     if phenopacket_path is not None:
+        logger.info(f"Scrambling {phenopacket_path}.")
         HpoRandomiser(ontology, scramble_factor).create_scrambled_phenopacket(
             output_dir, phenopacket_path
         )
     elif phenopacket_dir is not None:
+        logger.info(
+            f"Scrambling {len(all_files(phenopacket_dir))} phenopackets in {phenopacket_dir}."
+        )
         HpoRandomiser(ontology, scramble_factor).create_scrambled_phenopackets(
             output_dir,
             phenopacket_dir,
         )
+    logger.info(f"Finished scrambling! Total time: {time.perf_counter() - start_time:.2f} seconds.")

{pheval-0.5.2 → pheval-0.5.3}/src/pheval/prepare/create_spiked_vcf.py

@@ -1,7 +1,7 @@
 import gzip
-import logging
 import random
 import re
+import time
 import urllib.parse
 from copy import copy
 from dataclasses import dataclass
@@ -12,6 +12,7 @@ from phenopackets import Family, File, Phenopacket
 
 from pheval.prepare.custom_exceptions import InputError
 from pheval.utils.file_utils import all_files, files_with_suffix, is_gzipped
+from pheval.utils.logger import get_logger
 from pheval.utils.phenopacket_utils import (
     IncompatibleGenomeAssemblyError,
     PhenopacketRebuilder,
@@ -21,8 +22,7 @@ from pheval.utils.phenopacket_utils import (
     write_phenopacket,
 )
 
-info_log = logging.getLogger("info")
-
+logger = get_logger()
 genome_assemblies = {
     "GRCh38": {
         "1": 248956422,
@@ -357,9 +357,13 @@ class VcfSpiker:
                 and int(val.split("\t")[1]) < int(variant_entry[1])
             ]
             if matching_indices:
+                logger.info(
+                    f"Successfully spiked variant {variant.variant.chrom}-{variant.variant.pos}-"
+                    f"{variant.variant.ref}-{variant.variant.alt} in {template_vcf_name}"
+                )
                 variant_entry_position = matching_indices[-1] + 1
             else:
-                info_log.warning(
+                logger.warning(
                     f"Could not find entry position for {variant.variant.chrom}-{variant.variant.pos}-"
                     f"{variant.variant.ref}-{variant.variant.alt} in {template_vcf_name}, "
                     "inserting at end of VCF contents."
@@ -518,8 +522,6 @@ def generate_spiked_vcf_file(
     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, hg19_vcf_dir, hg38_vcf_dir
     )
@@ -633,6 +635,7 @@ def create_spiked_vcfs(
     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"):
+        logger.info(f"Creating spiked VCF for: {phenopacket_path.name}")
         spike_and_update_phenopacket(
             hg19_vcf_info, hg38_vcf_info, hg19_vcf_dir, hg38_vcf_dir, output_dir, phenopacket_path
         )
@@ -659,7 +662,12 @@ def spike_vcfs(
         hg19_vcf_dir (Path): The directory containing the hg19 VCF files (optional).
         hg38_vcf_dir (Path): The directory containing the hg38 VCF files (optional).
     """
+    start_time = time.perf_counter()
+    logger.info("Creating spiked VCFs.")
+    output_dir.mkdir(exist_ok=True)
+    logger.info(f" Created output directory: {output_dir}")
     if phenopacket_path is not None:
+        logger.info(f"Spiking variants from {phenopacket_path}.")
         create_spiked_vcf(
             output_dir,
             phenopacket_path,
@@ -669,6 +677,9 @@ def spike_vcfs(
             hg38_vcf_dir,
         )
     elif phenopacket_dir is not None:
+        logger.info(
+            f"Spiking variants from {len(all_files(phenopacket_dir))} phenopackets in {phenopacket_dir}."
+        )
         create_spiked_vcfs(
             output_dir,
             phenopacket_dir,
@@ -677,3 +688,4 @@ def spike_vcfs(
             hg19_vcf_dir,
             hg38_vcf_dir,
         )
+    logger.info(f"Finished spiking! Total time: {time.perf_counter() - start_time:.2f} seconds.")

{pheval-0.5.2 → pheval-0.5.3}/src/pheval/prepare/prepare_corpus.py

@@ -1,13 +1,18 @@
-import logging
 import shutil
+import time
 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
+from pheval.utils.logger import get_logger
+from pheval.utils.phenopacket_utils import (
+    PhenopacketUtil,
+    create_gene_identifier_map,
+    phenopacket_reader,
+)
 
-info_log = logging.getLogger("info")
+logger = get_logger()
 
 
 def prepare_corpus(
@@ -43,39 +48,46 @@ def prepare_corpus(
         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.
     """
+    start_time = time.perf_counter()
+    logger.info(f"Preparing corpus for {phenopacket_dir}")
     output_dir.joinpath("phenopackets").mkdir(exist_ok=True, parents=True)
+    logger.info(f" Created output directory: {output_dir.joinpath('phenopackets')}")
+    identifier_map = create_gene_identifier_map()
     for phenopacket_path in all_files(phenopacket_dir):
         phenopacket_util = PhenopacketUtil(phenopacket_reader(phenopacket_path))
         if not phenopacket_util.observed_phenotypic_features():
-            info_log.warning(
+            logger.warning(
                 f"Removed {phenopacket_path.name} from the corpus due to no observed phenotypic features."
             )
             continue
         if variant_analysis:
             if phenopacket_util.check_incomplete_variant_record():
-                info_log.warning(
+                logger.warning(
                     f"Removed {phenopacket_path.name} from the corpus due to missing variant fields."
                 )
                 continue
             elif phenopacket_util.check_variant_alleles():
-                info_log.warning(
+                logger.warning(
                     f"Removed {phenopacket_path.name} from the corpus due to identical "
                     "reference and alternate allele fields."
                 )
         if gene_analysis:
             if phenopacket_util.check_incomplete_gene_record():
-                info_log.warning(
+                logger.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(
+                logger.warning(
                     f"Removed {phenopacket_path.name} from the corpus due to missing disease fields."
                 )
                 continue
+        logger.info(f"{phenopacket_path.name} OK!")
         if hg19_template_vcf or hg38_template_vcf:
             output_dir.joinpath("vcf").mkdir(exist_ok=True)
+            logger.info(f" Created output directory: {output_dir.joinpath('vcf')}")
+            logger.info(f"Spiking VCF for {phenopacket_path}.")
             create_spiked_vcf(
                 output_dir.joinpath("vcf"),
                 phenopacket_path,
@@ -85,8 +97,12 @@ def prepare_corpus(
                 hg38_vcf_dir,
             )
         if gene_identifier:
+            logger.info(f"Updating gene identifiers to {gene_identifier} for {phenopacket_dir}")
             create_updated_phenopacket(
-                gene_identifier, phenopacket_path, output_dir.joinpath("phenopackets")
+                gene_identifier,
+                phenopacket_path,
+                output_dir.joinpath("phenopackets"),
+                identifier_map,
             )
         else:
             # if not updating phenopacket gene identifiers then copy phenopacket as is to output directory
@@ -97,3 +113,7 @@ def prepare_corpus(
                 if phenopacket_path != output_dir.joinpath(f"phenopackets/{phenopacket_path.name}")
                 else None
             )
+    logger.info(
+        f"Finished preparing corpus for {phenopacket_dir}. "
+        f"Total time: {time.perf_counter() - start_time:.2f} seconds."
+    )

{pheval-0.5.2 → pheval-0.5.3}/src/pheval/prepare/update_phenopacket.py

@@ -1,3 +1,4 @@
+import time
 from pathlib import Path
 from typing import Union
 
@@ -5,6 +6,7 @@ import polars as pl
 from phenopackets import Family, Phenopacket
 
 from pheval.utils.file_utils import all_files
+from pheval.utils.logger import get_logger
 from pheval.utils.phenopacket_utils import (
     GeneIdentifierUpdater,
     PhenopacketRebuilder,
@@ -14,6 +16,8 @@ from pheval.utils.phenopacket_utils import (
     write_phenopacket,
 )
 
+logger = get_logger()
+
 
 def update_outdated_gene_context(
     phenopacket_path: Path, gene_identifier: str, identifier_map: pl.DataFrame
@@ -43,7 +47,10 @@ def update_outdated_gene_context(
 
 
 def create_updated_phenopacket(
-    gene_identifier: str, phenopacket_path: Path, output_dir: Path
+    gene_identifier: str,
+    phenopacket_path: Path,
+    output_dir: Path,
+    identifier_map: pl.DataFrame = None,
 ) -> None:
     """
     Update the gene context within the interpretations for a Phenopacket and writes the updated Phenopacket.
@@ -52,12 +59,13 @@ def create_updated_phenopacket(
         gene_identifier (str): Identifier used to update the gene context.
         phenopacket_path (Path): The path to the input Phenopacket file.
         output_dir (Path): The directory where the updated Phenopacket will be written.
+        identifier_map (pl.DataFrame): The gene identifier map used for updating.
     Notes:
         The gene_identifier parameter should be chosen from ensembl_id, hgnc_id, or entrez_id
         to update to the current gene identifier in the Phenopacket. We recommend using the ENSEMBL namespace
         to describe the gene identifiers.
     """
-    identifier_map = create_gene_identifier_map()
+    identifier_map = create_gene_identifier_map() if identifier_map is None else identifier_map
     updated_phenopacket = update_outdated_gene_context(
         phenopacket_path, gene_identifier, identifier_map
     )
@@ -82,6 +90,7 @@ def create_updated_phenopackets(
     """
     identifier_map = create_gene_identifier_map()
     for phenopacket_path in all_files(phenopacket_dir):
+        logger.info(f"Updating gene context for: {phenopacket_path.name}")
         updated_phenopacket = update_outdated_gene_context(
             phenopacket_path, gene_identifier, identifier_map
         )
@@ -104,8 +113,17 @@ def update_phenopackets(
         to update to the current gene identifier in the Phenopacket. We recommend using the ENSEMBL namespace
         to describe the gene identifiers.
     """
+    start_time = time.perf_counter()
+    logger.info("Updating phenopackets.")
     output_dir.mkdir(exist_ok=True)
+    logger.info(f"Created directory {output_dir}.")
+    logger.info(f"Gene identifier set to: {gene_identifier}.")
     if phenopacket_path is not None:
+        logger.info(f"Updating {phenopacket_path}.")
         create_updated_phenopacket(gene_identifier, phenopacket_path, output_dir)
     elif phenopacket_dir is not None:
+        logger.info(
+            f"Updating {len(all_files(phenopacket_dir))} phenopackets in {phenopacket_dir}."
+        )
         create_updated_phenopackets(gene_identifier, phenopacket_dir, output_dir)
+    logger.info(f"Updating finished! Total time: {time.perf_counter() - start_time:.2f} seconds.")

{pheval-0.5.2 → pheval-0.5.3}/src/pheval/runners/runner.py

@@ -7,6 +7,9 @@ from pathlib import Path
 
 from pheval.config_parser import parse_input_dir_config
 from pheval.run_metadata import BasicOutputRunMetaData
+from pheval.utils.logger import get_logger
+
+logger = get_logger()
 
 
 @dataclass
@@ -86,6 +89,10 @@ class PhEvalRunner(ABC):
 
     def build_output_directory_structure(self):
         """build output directory structure"""
+        logger.info(
+            f"Building output directory structure for {self.input_dir_config.tool} "
+            f"version {self.input_dir_config.tool_version}"
+        )
         self.tool_input_commands_dir.mkdir(exist_ok=True)
         self.raw_results_dir.mkdir(exist_ok=True)
         if self._get_variant_analysis():

{pheval-0.5.2 → pheval-0.5.3}/src/pheval/utils/phenopacket_utils.py

@@ -1,5 +1,4 @@
 import json
-import logging
 import os
 from copy import copy
 from dataclasses import dataclass
@@ -19,8 +18,9 @@ from phenopackets import (
 )
 
 from pheval.prepare.custom_exceptions import IncorrectFileFormatError
+from pheval.utils.logger import get_logger
 
-info_log = logging.getLogger("info")
+logger = get_logger()
 
 
 class IncompatibleGenomeAssemblyError(Exception):
@@ -161,6 +161,7 @@ def create_gene_identifier_map() -> pl.DataFrame:
     Returns:
         pl.DataFrame: A mapping of gene identifiers to gene symbols.
     """
+    logger.info("Creating gene identifier map.")
     hgnc_df = parse_hgnc_data()
     return hgnc_df.melt(
         id_vars=["gene_symbol", "prev_symbols"],
@@ -192,6 +193,7 @@ def phenopacket_reader(file: Path) -> Union[Phenopacket, Family]:
     Returns:
         Union[Phenopacket, Family]: Contents of the Phenopacket file as a Phenopacket or Family object
     """
+    logger.info(f"Parsing Phenopacket: {file.name}")
     file = open(file, "r")
     phenopacket = json.load(file)
     file.close()
@@ -593,6 +595,7 @@ class PhenopacketRebuilder:
         Returns:
         - Phenopacket or Family: The Phenopacket or Family object with the added spiked VCF path.
         """
+        logger.info(f"Adding spiked VCF path {spiked_vcf_file_data.uri} to phenopacket.")
         phenopacket = copy(self.phenopacket)
         phenopacket_files = [
             file for file in phenopacket.files if file.file_attributes["fileFormat"] != "vcf"
@@ -627,6 +630,7 @@ def write_phenopacket(phenopacket: Union[Phenopacket, Family], output_file: Path
     Returns:
         None
     """
+    logger.info(f"Writing Phenopacket to {output_file}.")
     phenopacket_json = create_json_message(phenopacket)
     with open(output_file, "w") as outfile:
         outfile.write(phenopacket_json)
@@ -675,6 +679,7 @@ class GeneIdentifierUpdater:
         )
         if prev_symbol_matches.height > 0:
             return prev_symbol_matches["identifier"][0]
+        logger.warn(f"Could not find {self.gene_identifier} for {gene_symbol}.")
         return None
 
     def obtain_gene_symbol_from_identifier(self, query_gene_identifier: str) -> str:
@@ -735,10 +740,10 @@ class GeneIdentifierUpdater:
                 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 "
+                logger.info(
+                    f"Updating gene identifier in {phenopacket_path.name} from "
                     f"{g.variant_interpretation.variation_descriptor.gene_context.value_id}"
-                    f"to {updated_gene_identifier}"
+                    f" to {updated_gene_identifier}"
                 )
                 g.variant_interpretation.variation_descriptor.gene_context.value_id = (
                     updated_gene_identifier