genelastic 0.6.1__py3-none-any.whl → 0.7.0__py3-none-any.whl

genelastic/ui/server.py

@@ -0,0 +1,87 @@
+import requests
+from flask import Flask, render_template
+
+app = Flask(__name__)
+app.config.from_object("src.genelastic.ui.settings.Config")
+
+
+@app.route("/")
+def home() -> str:
+    api_url = app.config["GENUI_API_URL"]
+    try:
+        version_reponse = requests.get(f"{api_url}version", timeout=20)
+        version = version_reponse.json().get("version")
+        wet_processes_reponse = requests.get(
+            f"{api_url}wet_processes", timeout=20
+        )
+        wet_processes = wet_processes_reponse.json()
+        bi_processes_reponse = requests.get(
+            f"{api_url}bi_processes", timeout=20
+        )
+        bi_processes = bi_processes_reponse.json()
+        analyses_reponse = requests.get(f"{api_url}analyses", timeout=20)
+        analyses = analyses_reponse.json()
+    except requests.exceptions.RequestException:
+        version = "API not reachable"
+        wet_processes = []
+        bi_processes = []
+        analyses = []
+    return render_template(
+        "home.html",
+        version=version,
+        wet_processes=wet_processes,
+        bi_processes=bi_processes,
+        analyses=analyses,
+    )
+
+
+@app.route("/analyses")
+def show_analyses() -> str:
+    api_url = app.config["GENUI_API_URL"]
+    try:
+        analyses_reponse = requests.get(f"{api_url}analyses", timeout=20)
+        analyses = analyses_reponse.json()
+    except requests.exceptions.RequestException:
+        analyses = ["Error fetching data."]
+
+    return render_template("analyses.html", analyses=analyses)
+
+
+@app.route("/bi_processes")
+def show_bi_processes() -> str:
+    api_url = app.config["GENUI_API_URL"]
+    try:
+        bi_processes_reponse = requests.get(
+            f"{api_url}bi_processes", timeout=20
+        )
+        bi_processes = bi_processes_reponse.json()
+    except requests.exceptions.RequestException:
+        bi_processes = ["Error fetching data."]
+
+    return render_template("bi_processes.html", bi_processes=bi_processes)
+
+
+@app.route("/wet_processes")
+def show_wet_processes() -> str:
+    api_url = app.config["GENUI_API_URL"]
+    try:
+        wet_processes_reponse = requests.get(
+            f"{api_url}wet_processes", timeout=20
+        )
+        wet_processes = wet_processes_reponse.json()
+    except requests.exceptions.RequestException:
+        wet_processes = ["Error fetching data."]
+
+    return render_template("wet_processes.html", wet_processes=wet_processes)
+
+
+@app.route("/version")
+def show_version() -> str:
+    api_url = app.config["GENUI_API_URL"]
+    try:
+        version_reponse = requests.get(f"{api_url}version", timeout=20)
+        version = version_reponse.json().get("version", "Version not found")
+    except requests.exceptions.RequestException:
+        version = "Error fetching version."
+
+    return render_template("version.html", version=version)

genelastic/ui/settings.py

@@ -0,0 +1,11 @@
+from environs import Env
+
+env = Env()
+env.read_env()
+
+
+class Config:
+    """Flask config class."""
+
+    # Charger toutes les variables d'environnement nécessaires
+    GENUI_API_URL = env.url("GENUI_API_URL").geturl()

genelastic-0.7.0.dist-info/METADATA

@@ -0,0 +1,105 @@
+Metadata-Version: 2.2
+Name: genelastic
+Version: 0.7.0
+Summary: Generate and store genetic data into an Elasticsearch database.
+Author: CNRGH
+Author-email: Pierrick ROGER <pierrick.roger@cnrgh.fr>, Maxime BLANCHON <maxime.blanchon@cnrgh.fr>
+License: CeCILL
+Keywords: CNRGH,genelastic,generation,storage,elasticsearch,database
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: CEA CNRS Inria Logiciel Libre License, version 2.1 (CeCILL-2.1)
+Classifier: Programming Language :: Python :: 3.11
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+Requires-Dist: elasticsearch
+Requires-Dist: PyVCF3
+Requires-Dist: schema
+Requires-Dist: PyYAML
+Requires-Dist: biophony>=1.2.1
+Requires-Dist: colorlog
+Provides-Extra: tests
+Requires-Dist: pytest; extra == "tests"
+Requires-Dist: mypy; extra == "tests"
+Requires-Dist: coverage; extra == "tests"
+Requires-Dist: yamllint; extra == "tests"
+Requires-Dist: types-PyYAML; extra == "tests"
+Requires-Dist: ruff<0.9,>=0.8.1; extra == "tests"
+Requires-Dist: pre-commit<4.1,>=4.0.1; extra == "tests"
+Requires-Dist: types-requests; extra == "tests"
+Requires-Dist: ansible<10.5,>=10.4.0; extra == "tests"
+Requires-Dist: ansible-lint<25,>=24.12.2; extra == "tests"
+Provides-Extra: docs
+Requires-Dist: sphinx; extra == "docs"
+Requires-Dist: sphinx-autoapi; extra == "docs"
+Requires-Dist: furo; extra == "docs"
+Provides-Extra: api
+Requires-Dist: flask; extra == "api"
+Requires-Dist: elasticsearch; extra == "api"
+Requires-Dist: environs; extra == "api"
+Requires-Dist: connexion[flask,swagger-ui,uvicorn]; extra == "api"
+Provides-Extra: ui
+Requires-Dist: flask; extra == "ui"
+Requires-Dist: requests; extra == "ui"
+Requires-Dist: environs; extra == "ui"
+
+# genelastic
+
+Storing of genetics data into an Elasticsearch database.
+
+## Prerequisites
+
+- `python` >= 3.11
+- `make`
+
+## Installation
+
+To install dependencies, run the following command:
+
+```bash
+python -m venv .venv
+source .venv/bin/activate
+make install.deps
+```
+
+## Configuration
+
+To start the **API server**, the following environment variables should be defined:
+
+- `GENAPI_ES_URL`: URL of the Elasticsearch server,
+- `GENAPI_ES_ENCODED_API_KEY`: Encoded API key,
+- `GENAPI_ES_INDEX_PREFIX`: Prefix to identify indices of interest,
+- `GENAPI_ES_CERT_FP`: Certificate fingerprint of the Elasticsearch server.
+
+Then, run the following command:
+
+```bash
+make start-api
+```
+
+To start the **UI server**, the following environment variables should be defined:
+
+- `GENUI_API_URL`: URL of the API server.
+
+Then, run the following command:
+
+```bash
+make start-ui
+```
+
+## Developers
+
+This project uses [pre-commit](https://pre-commit.com/) to manage Git hooks scripts. To install project hooks, run:
+
+```bash
+pre-commit install
+```
+
+After that, each commit will succeed only if all hooks (defined in `.pre-commit-config.yaml`) pass.
+
+If necessary (though not recommended),
+you can skip these hooks by using the `--no-verify` / `-n` option when committing:
+
+```bash
+git commit -m "My commit message" --no-verify # This commit will not run installed hooks.
+```

genelastic-0.7.0.dist-info/RECORD

@@ -0,0 +1,40 @@
+genelastic/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+genelastic/api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+genelastic/api/routes.py,sha256=O_bZGhKex04tWauE1fYRXjNmR2smIA4JZShwcakbJJA,6938
+genelastic/api/server.py,sha256=XkkHpv_28OrfrY6CMDnImBFlDiEQSA8f1BpSSn2LGL4,2248
+genelastic/api/settings.py,sha256=vLfj8ASLqq9f6c3eGg30L_WSBiaOIpnCsk-S-TUZRlk,403
+genelastic/api/extends/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+genelastic/api/extends/example.py,sha256=5vOw2ToYWzOj-vYkOLbqoa1MCnXIvKuv7xW6qBQ-eHU,164
+genelastic/common/__init__.py,sha256=GfM4XaiaHsA2v8N0T3VgnXpZsLXjTc1wIPpRi4BlkZ8,937
+genelastic/common/cli.py,sha256=cDbgc2m20Y1NO0CZR1qaTrCttcf0cjFAP885tuPZsH0,1770
+genelastic/common/elastic.py,sha256=0XpECyNMC9RzQN1X7u-0IXmHp_KbSjkmGizArLjxTS0,7260
+genelastic/common/exceptions.py,sha256=l4sQBW91OuzV2R7DhrVzEMDrfsyKM-iVYufp2Cv6rR8,159
+genelastic/common/types.py,sha256=JeQ6XzIemIF1QgvprGA0UxFHyJSKjEkgMaIumOvpbNg,1013
+genelastic/import_data/__init__.py,sha256=Ir_fI0BrdC44JiiQaWm29_SyHbDe2CQsElKHgQxELCI,602
+genelastic/import_data/analyses.py,sha256=yA4DKtXIUR7JTCp7PEndEjI6FOooW-6lR9vkqTZ0Izs,1861
+genelastic/import_data/analysis.py,sha256=MuHYfIWFFwHfCp9tDkWTtVKkg5AasASwrdOUZ177EeM,7799
+genelastic/import_data/bi_process.py,sha256=CBBGx6oO7KYzUypXzpaopGY4J_nAKcDi2UPJe7B63Bs,650
+genelastic/import_data/bi_processes.py,sha256=Kv93NOntycEiB_BldoMxHNfM6sJvgHQvVqrUSSEb_VA,1365
+genelastic/import_data/cli_gen_data.py,sha256=WYvSgiC30pDvhQuGMxtDKookUF9IQpjQP6UMANvvHSU,3012
+genelastic/import_data/cli_import.py,sha256=Ej-EqaBUNoVHGCefzLsmFbKaXNTaOBs8xJsEdRhbbLo,11622
+genelastic/import_data/cli_info.py,sha256=ue0Pf5cJvrmJ_bBZKG2CXkXDsQO3zQ6CIXhtUwpqXhU,7301
+genelastic/import_data/cli_integrity.py,sha256=lOMA-I1iPXiJD4X80Xg91NKO-fa3Su0uSqBUtdMKU4Q,12282
+genelastic/import_data/cli_validate.py,sha256=AcirmmJQWFDrpiPUNTYnpFjSnvD6YyStYJHIbfi1Ly0,1515
+genelastic/import_data/constants.py,sha256=AKYXdDqWkDzvt-laZqbWlN6C9IoQSSqD70mpSWMU6NQ,760
+genelastic/import_data/data_file.py,sha256=P5oe_yCVQQAALetrUs93Kl1XuqoLQS0iMkeEqPKaY7g,2661
+genelastic/import_data/filename_pattern.py,sha256=3QXOF5ZG9vFA8KG7XXucpA7EIN3dqZmmtXnuFbh0bUQ,1709
+genelastic/import_data/import_bundle.py,sha256=7W0hKwoxwGDtWEGV_NQvyesiNx1lCMpSaqKohpTLmtY,5030
+genelastic/import_data/import_bundle_factory.py,sha256=COdMLTTrx_Y4svZAHVJ5Y0rHM4eQj027rFJiQ66u36M,9546
+genelastic/import_data/logger.py,sha256=X12LBoNTmV6iR8vEPyYIMYSUeQ3LpTvDO69tQYDiOuA,1915
+genelastic/import_data/random_bundle.py,sha256=Fk4oudK42pboGI14aaJjh8tTJxSxYNyF_89BBJ532RY,13821
+genelastic/import_data/tags.py,sha256=N6_dGYqQy2QTN6AEzoEXPxRFmtq3GgTfpId-RjBstJY,4195
+genelastic/import_data/wet_process.py,sha256=2SgN1yZFQA8Hb4ZNNeHpUhmeWlJDApqdjc_oq6ZF0jA,694
+genelastic/import_data/wet_processes.py,sha256=mVUfFG0QUboTEoD3c-Hd1Z2_Tvid_yrKJG_XdC4n6oA,1535
+genelastic/ui/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+genelastic/ui/server.py,sha256=7QX-54tT7CbpKje34kVVXnktI0wuZJOSLUChxeUGd20,2805
+genelastic/ui/settings.py,sha256=hmgDNMVKk_OkKSBKyV8Eth57ULCTINwzeBCFAH7DdeU,218
+genelastic-0.7.0.dist-info/METADATA,sha256=dj4cFcq7LXEv9v-turnGvHnK2KZ4zXrDxG0YKe11zPU,3127
+genelastic-0.7.0.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+genelastic-0.7.0.dist-info/entry_points.txt,sha256=KHtfefg-7-v0MZ0jAcHrb6z3V6hq7UdCiYYIAlD6hIg,284
+genelastic-0.7.0.dist-info/top_level.txt,sha256=ra4gCsuKH1d0sXygcnwD_u597ir6bYYxWTS7dkA6vdM,11
+genelastic-0.7.0.dist-info/RECORD,,

{genelastic-0.6.1.dist-info → genelastic-0.7.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.4.0)
+Generator: setuptools (75.8.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

genelastic-0.7.0.dist-info/entry_points.txt

@@ -0,0 +1,6 @@
+[console_scripts]
+gnl-data = genelastic.import_data.cli_gen_data:main
+gnl-import = genelastic.import_data.cli_import:main
+gnl-info = genelastic.import_data.cli_info:main
+gnl-integrity = genelastic.import_data.cli_integrity:main
+gnl-validate = genelastic.import_data.cli_validate:main

genelastic/import_data/gen_data.py

@@ -1,194 +0,0 @@
-# pylint: disable=missing-module-docstring
-import argparse
-import logging
-import os
-import random
-import subprocess  # nosec
-import sys
-from typing import Dict, List, Sequence, Collection
-
-import yaml
-from genelastic.common import add_verbose_control_args
-
-from .logger import configure_logging
-
-logger = logging.getLogger('genelastic')
-
-
-def read_args() -> argparse.Namespace:
-    # pylint: disable=R0801
-    """Read arguments from command line."""
-    parser = argparse.ArgumentParser(description='Genetics data random generator.',
-                                     formatter_class=argparse.ArgumentDefaultsHelpFormatter,
-                                     allow_abbrev=False)
-    add_verbose_control_args(parser)
-    parser.add_argument('-d', '--data-folder', dest='data_folder', required=True,
-                        help='Data destination folder.')
-    parser.add_argument('--log-file', dest='log_file', help='Path to a log file.')
-    parser.add_argument('-n', '--chrom-nb', dest='chrom_nb', type=int, default=5,
-                        help='Number of chromosomes to generate.')
-    parser.add_argument('-o', '--output-yaml-file', dest='output_file', default='-',
-                        help='Output YAML file.')
-    parser.add_argument('-s', '--chrom-size', dest='chrom_size', type=int, default=2000,
-                        help='Data size (number of nucleotides) for each chromosome.')
-    return parser.parse_args()
-
-
-def gen_cov_files(folder: str, nb_chrom: int, chrom_sz: int, prefix: str) -> List[str]:
-    """Generate dummy coverage files. If an error occurs while generating coverage files, exit."""
-    files = []
-    chrom_end = chrom_sz - 1
-
-    for chrom in range(1, nb_chrom + 1):
-        output_path = os.path.join(folder, f"{prefix}_chr{chrom}_cov.tsv")
-
-        # gen-cov will output a coverage file to stdout.
-        gen_cov_cmd = ["gen-cov", "-c", str(chrom), "-p", f"0-{chrom_end}", "-d", "5-15",
-                       "-r", "0.1"]
-
-        try:
-            with open(output_path, "w", encoding="utf-8") as f:
-                # Redirect the gen-cov output to a file.
-                subprocess.run(gen_cov_cmd, stdout=f, check=True)  # nosec
-
-        except (subprocess.CalledProcessError, FileNotFoundError, OSError) as e:
-            logger.error(e)
-            sys.exit(1)
-
-        files.append(output_path)
-
-    return files
-
-
-def gen_vcf_files(folder: str, nb_chrom: int, chrom_sz: int, prefix: str) -> List[str]:
-    """Generate dummy VCF files. If an error occurs while generating VCFs, exit."""
-    files = []
-    for chrom in range(1, nb_chrom + 1):
-        output_path = os.path.join(folder, f"{prefix}_chr{chrom}.vcf")
-
-        # gen-fasta will output a FASTA to stdout.
-        gen_fasta_cmd = ["gen-fasta", "-s", f"chr{chrom}", "-n", str(chrom_sz)]
-        # gen-vcf will output a VCF to stdout.
-        gen_vcf_cmd = ["gen-vcf", "--snp-rate", "0.02", "--ins-rate", "0.01", "--del-rate", "0.01"]
-
-        try:
-            # Pipe the output of gen-fasta to the stdin of gen-vcf.
-            with subprocess.Popen(gen_fasta_cmd, stdout=subprocess.PIPE) as gen_fasta_proc:  # nosec
-                # Redirect the gen-vcf output to a file.
-                with open(output_path, "w", encoding="utf-8") as f:
-                    subprocess.run(gen_vcf_cmd,
-                                   stdin=gen_fasta_proc.stdout, stdout=f, check=True)  # nosec
-        except (subprocess.CalledProcessError, FileNotFoundError, OSError) as e:
-            logger.error(e)
-            sys.exit(1)
-
-        files.append(output_path)
-
-    return files
-
-
-def gen_name(chars: str = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789', n: int = 4) -> str:
-    """Generate a random alphanumerical name."""
-    return ''.join(random.sample(list(chars), n))
-
-
-def gen_data(folder: str, nb_chrom: int, chrom_sz: int) -> (
-        Dict)[str, int | Sequence[Collection[str]]]:
-    """Generate dummy analysis following the V3 YAML schema."""
-    # Set metadata
-    sample_name = "HG0003"
-    source = "CNRGH"
-    barcode = gen_name(n=6)
-    wet_process = "novaseqxplus-10b"
-    bi_process = "dragen-4123"
-    reference_genome = "hg38"
-    prefix = f'{sample_name}_{source}_{wet_process}_{bi_process}_{barcode}_{reference_genome}'
-
-    wet_processes = [{
-        "proc_id": "novaseqxplus-10b",
-        "manufacturer": "illumina",
-        "sequencer": "novaseqxplus",
-        "generic_kit": "truseq-illumina",
-        "fragmentation": 350,
-        "reads_size": 300,
-        "input_type": "gdna",
-        "amplification": "pcr-free",
-        "flowcell_type": "10b",
-        "sequencing_type": "wgs",
-    }]
-
-    bi_processes = [{
-        "proc_id": "dragen-4123",
-        "name": "dragen",
-        "pipeline_version": "4.1.2.3",
-        "steps": [
-            {"name": "basecalling", "cmd": "bclconvert", "version": "3.9.3.2"},
-            {"name": "trimming", "cmd": "dragen"},
-            {"name": "mapping", "cmd": "dragmap"},
-            {"name": "postmapping", "cmd": "dragen", "version": "4.1.23"},
-            {"name": "smallvarcalling", "cmd": "dragen", "version": "4.1.23"},
-            {"name": "svcalling", "cmd": "dragen", "version": "4.1.23"},
-            {"name": "secondary_qc", "cmd": "dragen", "version": "4.1.23"}
-        ],
-        "sequencing_type": "wgs"
-    }]
-
-    analyses = [{
-        'file_prefix': '%S_%F_%W_%B_%A_%R_chr[0-9]+',
-        'sample_name': sample_name,
-        'source': source,
-        'barcode': barcode,
-        'wet_process': "novaseqxplus-10b",
-        'bi_process': "dragen-4123",
-        'reference_genome': reference_genome,
-        'flowcell': gen_name(n=8),
-        'lanes': [random.randint(1, 10)],  # nosec
-        'seq_indices': ['DUAL219', 'DUAL222', 'DUAL225', 'DUAL228', 'DUAL289'],
-        'qc_comment': "",
-        'data_path': folder,
-    }]
-
-    gen_vcf_files(folder, nb_chrom=nb_chrom, chrom_sz=chrom_sz, prefix=prefix)
-    gen_cov_files(folder, nb_chrom=nb_chrom, chrom_sz=chrom_sz, prefix=prefix)
-
-    return {
-        'version': 3,
-        'analyses': analyses,
-        'bi_processes': bi_processes,
-        'wet_processes': wet_processes
-    }
-
-
-# Write import bundle YAML
-def write_yaml(file: str, data: Dict[str, int | Sequence[Collection[str]]]) -> None:
-    """Write YAML to stdout or in a file."""
-    # Standard output
-    if file == '-':
-        print('---')
-        yaml.dump(data, sys.stdout)
-
-    # File
-    else:
-        with open(file, 'w', encoding="utf-8") as f:
-            print('---', file=f)
-            yaml.dump(data, f)
-
-
-def main() -> None:
-    """Entry point of the gen-data script."""
-    # Read command line arguments
-    args = read_args()
-
-    # Configure logging
-    configure_logging(args.verbose, log_file=args.log_file)
-    logger.debug("Arguments: %s", args)
-
-    # Generate data
-    data = gen_data(args.data_folder, nb_chrom=args.chrom_nb, chrom_sz=args.chrom_size)
-
-    # Write to stdout or file
-    write_yaml(args.output_file, data)
-
-
-if __name__ == '__main__':
-    main()