pheval-exomiser 0.1.3__tar.gz → 0.2.1__tar.gz

pheval_exomiser-0.2.1/PKG-INFO

@@ -0,0 +1,183 @@
+Metadata-Version: 2.1
+Name: pheval_exomiser
+Version: 0.2.1
+Summary: 
+Author: Yasemin Bridges
+Author-email: y.bridges@qmul.ac.uk
+Requires-Python: >=3.9,<4.0.0
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Dist: click (>=8.1.3,<9.0.0)
+Requires-Dist: docker (>=6.0.1,<7.0.0)
+Requires-Dist: google (>=3.0.0,<4.0.0)
+Requires-Dist: oaklib (>=0.5.12,<0.6.0)
+Requires-Dist: pandas (>=1.5.2,<2.0.0)
+Requires-Dist: phenopackets (>=2.0.2,<3.0.0)
+Requires-Dist: pheval (>=0.3.1,<0.4.0)
+Requires-Dist: pyaml (>=21.10.1,<22.0.0)
+Requires-Dist: pydantic (>=1.10.7,<2.0.0)
+Description-Content-Type: text/markdown
+
+# Exomiser Runner for PhEval
+
+This is the Exomiser plugin for PhEval. With this plugin, you can leverage the variant prioritisation tool, Exomiser, to run the PhEval pipeline seamlessly. Detailed documentation on how to set up and run the PhEval Makefile pipeline with the Exomiser runner can be found [here](https://monarch-initiative.github.io/pheval/exomiser_pipeline/). The setup process for running the full PhEval Makefile pipeline differs from setting up for a single run. The Makefile pipeline creates directory structures for corpora and configurations to handle multiple run configurations. Detailed instructions on setting up the appropriate directory layout, including the input directory and test data directory, can be found here.
+
+## Installation
+
+Clone the pheval.exomiser repo and set up the poetry environment:
+
+```shell
+git clone https://github.com/monarch-initiative/pheval.exomiser.git
+cd pheval.exomiser
+poetry shell
+poetry install
+```
+
+## Configuring a *single* run:
+
+### Setting up the input directory
+
+A `config.yaml` should be located in the input directory and formatted like so:
+
+```yaml
+tool: exomiser
+tool_version: 13.2.0
+variant_analysis: True
+gene_analysis: True
+disease_analysis: False
+tool_specific_configuration_options:
+  environment: local
+  exomiser_software_directory: exomiser-cli-13.2.0
+  analysis_configuration_file: preset-exome-analysis.yml
+  max_jobs: 0
+  application_properties:
+    remm_version:
+    cadd_version:
+    hg19_data_version: 2302
+    hg19_local_frequency_path: # name of hg19 local frequency file 
+    hg19_whitelist_path: 2302_hg19_clinvar_whitelist.tsv.gz # only required for Exomiser v13.3.0 and earlier, can be left blank for Exomiser v14.0.0 onwards.
+    hg38_data_version: 2302
+    hg38_local_frequency_path: # name of hg38 local frequency file 
+    hg38_whitelist_path:
+    phenotype_data_version: 2302
+    cache_type:
+    cache_caffeine_spec:
+  post_process:
+    score_name: combinedScore
+    sort_order: DESCENDING
+```
+The bare minimum fields are filled to give an idea on the requirements. This is so that the application.properties for Exomiser can be correctly configured. An example config has been provided `pheval.exomiser/config.yaml`.
+
+The Exomiser input data directories (phenotype database and variant database) should also be located in the input directory - or a symlink pointing to the location.
+
+The `exomiser_software_directory` points to the name of the Exomiser distribution directory located in the input directory.
+
+The analysis configuration file (in this case: `preset-exome-analysis.yml`) should be located within the input directory.
+
+The whitelist paths for the hg19 and hg38 dbs need only be specified for Exomiser v13.3.0 and earlier (unless specifying your own whitelist), as Exomiser v14.0.0 now includes this in the db.
+
+If using optional databases, such as REMM/CADD/local frequency the optional data input should look like so in the input
+directory:
+
+```tree
+├── cadd
+│   └── {{CADD-VERSION}}
+│       ├── hg19
+│       │   ├── InDels.tsv.gz
+│       │   └── whole_genome_SNVs.tsv.gz
+│       └── hg38
+│           ├── InDels.tsv.gz
+│           └── whole_genome_SNVs.tsv.gz
+├── local
+│   ├── local_frequency_test_hg19.tsv.gz
+│   └── local_frequency_test_hg38.tsv.gz
+└── remm
+    ├── ReMM.v{{REMM-VERSION}}.hg19.tsv.gz
+    └── ReMM.v{{REMM-VERSION}}.hg38.tsv.gz
+```
+
+
+The overall structure of the input directory should look like this with the cadd, local and remm directories being optional, depending on the exomiser configuration:
+```tree
+.
+├── 2302_hg19
+│   ├── 2302_hg19_clinvar_whitelist.tsv.gz
+│   ├── 2302_hg19_clinvar_whitelist.tsv.gz.tbi
+│   ├── 2302_hg19_genome.h2.db
+│   ├── 2302_hg19_transcripts_ensembl.ser
+│   ├── 2302_hg19_transcripts_refseq.ser
+│   ├── 2302_hg19_transcripts_ucsc.ser
+│   └── 2302_hg19_variants.mv.db
+├── 2302_phenotype
+│   ├── 2302_phenotype.h2.db
+│   ├── hp.obo
+│   ├── phenix
+│   │   ├── ALL_SOURCES_ALL_FREQUENCIES_genes_to_phenotype.txt
+│   │   ├── hp.obo
+│   │   └── out
+│   └── rw_string_10.mv
+├── config.yaml
+├── exomiser-cli-13.2.0
+│   ├── lib
+│   └── exomiser-cli-13.2.0.jar
+├── preset-exome-analysis.yml
+├── cadd
+│   └── {{CADD-VERSION}}
+│       ├── hg19
+│       │   ├── InDels.tsv.gz
+│       │   └── whole_genome_SNVs.tsv.gz
+│       └── hg38
+│           ├── InDels.tsv.gz
+│           └── whole_genome_SNVs.tsv.gz
+├── local
+│   ├── local_frequency_test_hg19.tsv.gz
+│   └── local_frequency_test_hg38.tsv.gz
+└── remm
+    ├── ReMM.v{{REMM-VERSION}}.hg19.tsv.gz
+    └── ReMM.v{{REMM-VERSION}}.hg38.tsv.gz
+```
+### Setting up the testdata directory
+
+The Exomiser plugin for PhEval accepts phenopackets and vcf files as an input for running Exomiser. The plugin can be run in `phenotype_only` mode, where only phenopackets are required as an input, however, this *must* be specified in the `config.yaml`.
+
+The testdata directory should include subdirectories named `phenopackets` and `vcf` if running with variant prioritisation.
+
+e.g., 
+
+```tree
+├── testdata_dir
+   ├── phenopackets
+   └── vcf
+```
+
+## Run command
+
+Once the testdata and input directories are correctly configured for the run, the `pheval run` command can be executed.
+
+```bash
+pheval run --input-dir /path/to/input_dir \
+--testdata-dir /path/to/testdata_dir \
+--runner exomiserphevalrunner \
+--output-dir /path/to/output_dir \
+--version 13.2.0
+```
+
+## Common errors
+
+You may see an error that is related to the current `setuptools` being used:
+
+```shell
+pkg_resources.extern.packaging.requirements.InvalidRequirement: Expected closing RIGHT_PARENTHESIS
+    requests (<3,>=2.12.*) ; extra == 'parse'
+             ~~~~~~~~~~^
+```
+
+To fix the error, `setuptools` needs to be downgraded to version 66:
+
+```shell
+pip uninstall setuptools
+pip install -U setuptools=="66"
+```

pheval_exomiser-0.2.1/README.md

@@ -0,0 +1,160 @@
+# Exomiser Runner for PhEval
+
+This is the Exomiser plugin for PhEval. With this plugin, you can leverage the variant prioritisation tool, Exomiser, to run the PhEval pipeline seamlessly. Detailed documentation on how to set up and run the PhEval Makefile pipeline with the Exomiser runner can be found [here](https://monarch-initiative.github.io/pheval/exomiser_pipeline/). The setup process for running the full PhEval Makefile pipeline differs from setting up for a single run. The Makefile pipeline creates directory structures for corpora and configurations to handle multiple run configurations. Detailed instructions on setting up the appropriate directory layout, including the input directory and test data directory, can be found here.
+
+## Installation
+
+Clone the pheval.exomiser repo and set up the poetry environment:
+
+```shell
+git clone https://github.com/monarch-initiative/pheval.exomiser.git
+cd pheval.exomiser
+poetry shell
+poetry install
+```
+
+## Configuring a *single* run:
+
+### Setting up the input directory
+
+A `config.yaml` should be located in the input directory and formatted like so:
+
+```yaml
+tool: exomiser
+tool_version: 13.2.0
+variant_analysis: True
+gene_analysis: True
+disease_analysis: False
+tool_specific_configuration_options:
+  environment: local
+  exomiser_software_directory: exomiser-cli-13.2.0
+  analysis_configuration_file: preset-exome-analysis.yml
+  max_jobs: 0
+  application_properties:
+    remm_version:
+    cadd_version:
+    hg19_data_version: 2302
+    hg19_local_frequency_path: # name of hg19 local frequency file 
+    hg19_whitelist_path: 2302_hg19_clinvar_whitelist.tsv.gz # only required for Exomiser v13.3.0 and earlier, can be left blank for Exomiser v14.0.0 onwards.
+    hg38_data_version: 2302
+    hg38_local_frequency_path: # name of hg38 local frequency file 
+    hg38_whitelist_path:
+    phenotype_data_version: 2302
+    cache_type:
+    cache_caffeine_spec:
+  post_process:
+    score_name: combinedScore
+    sort_order: DESCENDING
+```
+The bare minimum fields are filled to give an idea on the requirements. This is so that the application.properties for Exomiser can be correctly configured. An example config has been provided `pheval.exomiser/config.yaml`.
+
+The Exomiser input data directories (phenotype database and variant database) should also be located in the input directory - or a symlink pointing to the location.
+
+The `exomiser_software_directory` points to the name of the Exomiser distribution directory located in the input directory.
+
+The analysis configuration file (in this case: `preset-exome-analysis.yml`) should be located within the input directory.
+
+The whitelist paths for the hg19 and hg38 dbs need only be specified for Exomiser v13.3.0 and earlier (unless specifying your own whitelist), as Exomiser v14.0.0 now includes this in the db.
+
+If using optional databases, such as REMM/CADD/local frequency the optional data input should look like so in the input
+directory:
+
+```tree
+├── cadd
+│   └── {{CADD-VERSION}}
+│       ├── hg19
+│       │   ├── InDels.tsv.gz
+│       │   └── whole_genome_SNVs.tsv.gz
+│       └── hg38
+│           ├── InDels.tsv.gz
+│           └── whole_genome_SNVs.tsv.gz
+├── local
+│   ├── local_frequency_test_hg19.tsv.gz
+│   └── local_frequency_test_hg38.tsv.gz
+└── remm
+    ├── ReMM.v{{REMM-VERSION}}.hg19.tsv.gz
+    └── ReMM.v{{REMM-VERSION}}.hg38.tsv.gz
+```
+
+
+The overall structure of the input directory should look like this with the cadd, local and remm directories being optional, depending on the exomiser configuration:
+```tree
+.
+├── 2302_hg19
+│   ├── 2302_hg19_clinvar_whitelist.tsv.gz
+│   ├── 2302_hg19_clinvar_whitelist.tsv.gz.tbi
+│   ├── 2302_hg19_genome.h2.db
+│   ├── 2302_hg19_transcripts_ensembl.ser
+│   ├── 2302_hg19_transcripts_refseq.ser
+│   ├── 2302_hg19_transcripts_ucsc.ser
+│   └── 2302_hg19_variants.mv.db
+├── 2302_phenotype
+│   ├── 2302_phenotype.h2.db
+│   ├── hp.obo
+│   ├── phenix
+│   │   ├── ALL_SOURCES_ALL_FREQUENCIES_genes_to_phenotype.txt
+│   │   ├── hp.obo
+│   │   └── out
+│   └── rw_string_10.mv
+├── config.yaml
+├── exomiser-cli-13.2.0
+│   ├── lib
+│   └── exomiser-cli-13.2.0.jar
+├── preset-exome-analysis.yml
+├── cadd
+│   └── {{CADD-VERSION}}
+│       ├── hg19
+│       │   ├── InDels.tsv.gz
+│       │   └── whole_genome_SNVs.tsv.gz
+│       └── hg38
+│           ├── InDels.tsv.gz
+│           └── whole_genome_SNVs.tsv.gz
+├── local
+│   ├── local_frequency_test_hg19.tsv.gz
+│   └── local_frequency_test_hg38.tsv.gz
+└── remm
+    ├── ReMM.v{{REMM-VERSION}}.hg19.tsv.gz
+    └── ReMM.v{{REMM-VERSION}}.hg38.tsv.gz
+```
+### Setting up the testdata directory
+
+The Exomiser plugin for PhEval accepts phenopackets and vcf files as an input for running Exomiser. The plugin can be run in `phenotype_only` mode, where only phenopackets are required as an input, however, this *must* be specified in the `config.yaml`.
+
+The testdata directory should include subdirectories named `phenopackets` and `vcf` if running with variant prioritisation.
+
+e.g., 
+
+```tree
+├── testdata_dir
+   ├── phenopackets
+   └── vcf
+```
+
+## Run command
+
+Once the testdata and input directories are correctly configured for the run, the `pheval run` command can be executed.
+
+```bash
+pheval run --input-dir /path/to/input_dir \
+--testdata-dir /path/to/testdata_dir \
+--runner exomiserphevalrunner \
+--output-dir /path/to/output_dir \
+--version 13.2.0
+```
+
+## Common errors
+
+You may see an error that is related to the current `setuptools` being used:
+
+```shell
+pkg_resources.extern.packaging.requirements.InvalidRequirement: Expected closing RIGHT_PARENTHESIS
+    requests (<3,>=2.12.*) ; extra == 'parse'
+             ~~~~~~~~~~^
+```
+
+To fix the error, `setuptools` needs to be downgraded to version 66:
+
+```shell
+pip uninstall setuptools
+pip install -U setuptools=="66"
+```

{pheval_exomiser-0.1.3 → pheval_exomiser-0.2.1}/pyproject.toml

@@ -1,13 +1,13 @@
 [tool.poetry]
 name = "pheval_exomiser"
-version = "0.1.3"
+version = "0.2.1"
 description = ""
 authors = ["Yasemin Bridges <y.bridges@qmul.ac.uk>",
-  "Julius Jacobsen <j.jacobsen@qmul.ac.uk>",
-  "Nico Matentzoglu <nicolas.matentzoglu@gmail.com>",
-  "Vinícius de Souza <souzadevinicius@gmail.com>"]
+    "Julius Jacobsen <j.jacobsen@qmul.ac.uk>",
+    "Nico Matentzoglu <nicolas.matentzoglu@gmail.com>",
+    "Vinícius de Souza <souzadevinicius@gmail.com>"]
 readme = "README.md"
-packages = [{include = "pheval_exomiser", from = "src"}]
+packages = [{ include = "pheval_exomiser", from = "src" }]
 
 [tool.poetry.dependencies]
 python = ">=3.9,<4.0.0"
@@ -16,14 +16,22 @@ pandas = "^1.5.2"
 phenopackets = "^2.0.2"
 google = "^3.0.0"
 pyaml = "^21.10.1"
-oaklib = "^0.1.55"
-pyserde = "^0.9.7"
+oaklib = "^0.5.12"
 docker = "^6.0.1"
+pydantic = "^1.10.7"
+pheval = "^0.3.1"
 
 [tool.poetry.dev-dependencies]
 pytest = "^7.1.2"
 pylint = "^2.15.6"
 pycodestyle = "^2.10.0"
+coverage = "^6.5.0"
+
+
+[tool.pytest.ini_options]
+pythonpath = [
+    "src"
+]
 
 [tool.poetry.scripts]
 pheval-exomiser = "pheval_exomiser.cli:main"

pheval_exomiser-0.2.1/src/pheval_exomiser/constants.py

@@ -0,0 +1,8 @@
+PHENOPACKET_TARGET_DIRECTORY_DOCKER = "/exomiser-testdata-phenopacket/"
+RAW_RESULTS_TARGET_DIRECTORY_DOCKER = "/exomiser-results/"
+OUTPUT_OPTIONS_TARGET_DIRECTORY_DOCKER = "/exomiser-testdata-output-options/"
+VCF_TARGET_DIRECTORY_DOCKER = "/exomiser-testdata-vcf/"
+EXOMISER_YAML_TARGET_DIRECTORY_DOCKER = "/exomiser-yaml-template/"
+EXOMISER_DATA_DIRECTORY_TARGET_DOCKER = "/exomiser-data/"
+INPUT_COMMANDS_TARGET_DIRECTORY_DOCKER = "/exomiser-batch-file/"
+EXOMISER_CONFIG_TARGET_DIRECTORY_DOCKER = "/exomiser-config/"

pheval_exomiser-0.2.1/src/pheval_exomiser/post_process/post_process.py

@@ -0,0 +1,26 @@
+from pathlib import Path
+
+from pheval_exomiser.post_process.post_process_results_format import create_standardised_results
+from pheval_exomiser.prepare.tool_specific_configuration_options import ExomiserConfigurations
+
+
+def post_process_result_format(
+    config: ExomiserConfigurations,
+    raw_results_dir: Path,
+    output_dir: Path,
+    variant_analysis: bool,
+    gene_analysis: bool,
+    disease_analysis: bool,
+):
+    """Standardise Exomiser json format to separated gene and variant results."""
+    print("...standardising results format...")
+    create_standardised_results(
+        results_dir=raw_results_dir,
+        output_dir=output_dir,
+        score_name=config.post_process.score_name,
+        sort_order=config.post_process.sort_order,
+        variant_analysis=variant_analysis,
+        gene_analysis=gene_analysis,
+        disease_analysis=disease_analysis,
+    )
+    print("done")