genetrek 0.1.0__tar.gz

genetrek-0.1.0/.gitignore

@@ -0,0 +1,150 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+*/.ipynb_checkpoints/*
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# uwsgi
+uwsgi.ini
+
+# .env file
+.env
+
+# uv
+.uv.toml
+
+# GeneTrek database tooling: generated, not source
+resources/processed_data/staging/
+resources/processed_data/.backups/
+resources/processed_data/history.jsonl
+
+# Upstream source files: large, re-downloadable, and read only by `genetrek-db`.
+# The webapp never touches them, so they are neither committed nor shipped in the
+# container image (see .dockerignore).
+resources/original_file/
+
+# macOS
+.DS_Store
+.AppleDouble
+.LSOverride
+Icon?
+._*
+.Spotlight-V100
+.Trashes
+AppleClang/
+
+# Windows
+Thumbs.db
+ehthumbs.db
+Desktop.ini
+$RECYCLE.BIN/
+Windows/
+# Local tooling
+.claude/
+.vscode/

genetrek-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Institut Pasteur
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

genetrek-0.1.0/PKG-INFO

@@ -0,0 +1,116 @@
+Metadata-Version: 2.5
+Name: genetrek
+Version: 0.1.0
+Summary: Python client and command line for GeneTrek: gene lists and annotations for neurodevelopmental disorders.
+Project-URL: Homepage, https://genetrek.pasteur.fr
+Project-URL: Documentation, https://genetrek.pasteur.fr/api-reference
+Project-URL: Repository, https://github.com/bourgeron-lab/genetrek
+Author-email: "Human Genetics and Cognitive Functions, Institut Pasteur" <ghfcgenetics@pasteur.fr>
+License-Expression: MIT
+License-File: LICENSE
+Keywords: api client,autism,gene lists,genomics,neurodevelopmental disorders
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Requires-Python: >=3.10
+Requires-Dist: httpx>=0.27
+Requires-Dist: platformdirs>=3.0
+Requires-Dist: polars>=0.20.0
+Requires-Dist: tomli>=2.0; python_version < '3.11'
+Requires-Dist: typer>=0.12.0
+Provides-Extra: pandas
+Requires-Dist: pandas>=2.0; extra == 'pandas'
+Requires-Dist: pyarrow>=14; extra == 'pandas'
+Description-Content-Type: text/markdown
+
+# genetrek
+
+Python client and command line for [GeneTrek](https://genetrek.pasteur.fr): curated gene lists
+for neurodevelopmental disorders (NDD) and per-gene annotations (constraint, brain expression,
+rare-variant results) in one versioned table.
+
+```bash
+pip install genetrek            # or: uv add genetrek
+pip install "genetrek[pandas]"  # to call .to_pandas() on the tables
+```
+
+Python 3.10 or newer. GeneTrek is for research use only, not for diagnostic use.
+
+## From Python
+
+```python
+from genetrek import GeneTrek, Set
+
+gt = GeneTrek()                                   # the public instance
+
+hc = gt.gene_list("hc_ndd")                       # a gene list's members
+table = gt.genes(["SHANK3", "KIAA1650", "85358"],  # any identifiers, any mix
+                 columns=["loeuf", "hc_ndd"])       # -> polars DataFrame
+gt.convert(["SHANK3", "ENSG00000100888"], to=["hgnc", "ncbi"])
+gt.search("chr22:50,674,408-50,733,212")          # what the search box does
+
+result = gt.compare([
+    Set.field("hc_ndd"),
+    Set.genes(["SHANK3", "CHD8", "SCN2A"], label="my genes"),
+    Set.file("candidates.txt"),
+])
+result.pairs        # overlap, odds ratio with exact 95% CI, Fisher p, FDR, adjusted
+result.methods      # the methods paragraph, with the database release
+result.to_request_json("request.json")   # gt.replay("request.json") later
+```
+
+Tables are [polars](https://pola.rs) DataFrames; with the `pandas` extra, `table.to_pandas()`.
+A null means "not measured" and is never turned into `False`.
+
+Errors are exceptions you can catch: `UnknownGene`, `AmbiguousGene`, `UnknownField`,
+`NotAGeneList`, and `ApiError` (with the server's `.code`) for the rest. Identifiers that
+match no gene, or several, are reported in an `UnresolvedWarning` rather than dropped
+silently.
+
+## From the shell
+
+```bash
+genetrek list hc_ndd > hc_ndd.txt                    # one gene per line
+genetrek genes my_genes.txt --columns loeuf,hc_ndd   # TSV to stdout
+genetrek convert - --to hgnc,ensg < ids.txt
+genetrek search SHANK3 chr22:50674408-50733212
+genetrek compare hc_ndd my_genes.txt:mine --out results/
+genetrek replay results/request.json
+genetrek download -o genetrek.parquet
+genetrek --help
+```
+
+Tables go to stdout as TSV (`NA` for null), messages to stderr; `--json` prints JSON.
+
+## Which server
+
+The public instance, `https://genetrek.pasteur.fr`, is the default. To use another one,
+name it once:
+
+```bash
+genetrek config add local http://localhost:8000
+genetrek config add dev https://genetrek.dev.example.org --default
+genetrek info          # says which server answered, and why it was chosen
+```
+
+The names live in a small TOML file in your configuration directory (`genetrek config list`
+prints where; `$GENETREK_CONFIG` moves it). The first of these that is set wins:
+`GeneTrek(base_url=...)` or `--url`; `GeneTrek(server="dev")` or `--server dev`;
+`$GENETREK_URL`; `$GENETREK_SERVER`; the file's default; the public instance.
+
+## Your genes
+
+Your identifiers travel in request bodies only, never in a URL, so they are not written to
+any server's access log, and nothing you send is cached to disk. A My lists share link is
+read locally: only its token is sent.
+
+## Versions
+
+Every result carries the database release it was computed on (`result.release`,
+`gt.release()`). The client checks the server's API version: `genes()`, `search()` and the
+error codes need API 1.1, which genetrek.pasteur.fr serves from GeneTrek v8; against an
+older server those methods raise `ServerTooOld`, and everything else works.
+
+## Citing and licences
+
+How to cite GeneTrek: <https://genetrek.pasteur.fr/cite>. The code is MIT-licensed; the
+data keep each source's terms, listed per column on <https://genetrek.pasteur.fr/columns>.

genetrek-0.1.0/README.md

@@ -0,0 +1,92 @@
+# genetrek
+
+Python client and command line for [GeneTrek](https://genetrek.pasteur.fr): curated gene lists
+for neurodevelopmental disorders (NDD) and per-gene annotations (constraint, brain expression,
+rare-variant results) in one versioned table.
+
+```bash
+pip install genetrek            # or: uv add genetrek
+pip install "genetrek[pandas]"  # to call .to_pandas() on the tables
+```
+
+Python 3.10 or newer. GeneTrek is for research use only, not for diagnostic use.
+
+## From Python
+
+```python
+from genetrek import GeneTrek, Set
+
+gt = GeneTrek()                                   # the public instance
+
+hc = gt.gene_list("hc_ndd")                       # a gene list's members
+table = gt.genes(["SHANK3", "KIAA1650", "85358"],  # any identifiers, any mix
+                 columns=["loeuf", "hc_ndd"])       # -> polars DataFrame
+gt.convert(["SHANK3", "ENSG00000100888"], to=["hgnc", "ncbi"])
+gt.search("chr22:50,674,408-50,733,212")          # what the search box does
+
+result = gt.compare([
+    Set.field("hc_ndd"),
+    Set.genes(["SHANK3", "CHD8", "SCN2A"], label="my genes"),
+    Set.file("candidates.txt"),
+])
+result.pairs        # overlap, odds ratio with exact 95% CI, Fisher p, FDR, adjusted
+result.methods      # the methods paragraph, with the database release
+result.to_request_json("request.json")   # gt.replay("request.json") later
+```
+
+Tables are [polars](https://pola.rs) DataFrames; with the `pandas` extra, `table.to_pandas()`.
+A null means "not measured" and is never turned into `False`.
+
+Errors are exceptions you can catch: `UnknownGene`, `AmbiguousGene`, `UnknownField`,
+`NotAGeneList`, and `ApiError` (with the server's `.code`) for the rest. Identifiers that
+match no gene, or several, are reported in an `UnresolvedWarning` rather than dropped
+silently.
+
+## From the shell
+
+```bash
+genetrek list hc_ndd > hc_ndd.txt                    # one gene per line
+genetrek genes my_genes.txt --columns loeuf,hc_ndd   # TSV to stdout
+genetrek convert - --to hgnc,ensg < ids.txt
+genetrek search SHANK3 chr22:50674408-50733212
+genetrek compare hc_ndd my_genes.txt:mine --out results/
+genetrek replay results/request.json
+genetrek download -o genetrek.parquet
+genetrek --help
+```
+
+Tables go to stdout as TSV (`NA` for null), messages to stderr; `--json` prints JSON.
+
+## Which server
+
+The public instance, `https://genetrek.pasteur.fr`, is the default. To use another one,
+name it once:
+
+```bash
+genetrek config add local http://localhost:8000
+genetrek config add dev https://genetrek.dev.example.org --default
+genetrek info          # says which server answered, and why it was chosen
+```
+
+The names live in a small TOML file in your configuration directory (`genetrek config list`
+prints where; `$GENETREK_CONFIG` moves it). The first of these that is set wins:
+`GeneTrek(base_url=...)` or `--url`; `GeneTrek(server="dev")` or `--server dev`;
+`$GENETREK_URL`; `$GENETREK_SERVER`; the file's default; the public instance.
+
+## Your genes
+
+Your identifiers travel in request bodies only, never in a URL, so they are not written to
+any server's access log, and nothing you send is cached to disk. A My lists share link is
+read locally: only its token is sent.
+
+## Versions
+
+Every result carries the database release it was computed on (`result.release`,
+`gt.release()`). The client checks the server's API version: `genes()`, `search()` and the
+error codes need API 1.1, which genetrek.pasteur.fr serves from GeneTrek v8; against an
+older server those methods raise `ServerTooOld`, and everything else works.
+
+## Citing and licences
+
+How to cite GeneTrek: <https://genetrek.pasteur.fr/cite>. The code is MIT-licensed; the
+data keep each source's terms, listed per column on <https://genetrek.pasteur.fr/columns>.

genetrek-0.1.0/pyproject.toml

@@ -0,0 +1,55 @@
+[project]
+name = "genetrek"
+version = "0.1.0"
+description = "Python client and command line for GeneTrek: gene lists and annotations for neurodevelopmental disorders."
+readme = "README.md"
+requires-python = ">=3.10"
+license = "MIT"
+license-files = ["LICENSE"]
+authors = [
+    { name = "Human Genetics and Cognitive Functions, Institut Pasteur", email = "ghfcgenetics@pasteur.fr" },
+]
+keywords = ["genomics", "neurodevelopmental disorders", "autism", "gene lists", "api client"]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Topic :: Scientific/Engineering :: Bio-Informatics",
+]
+dependencies = [
+    "httpx>=0.27",
+    "polars>=0.20.0",
+    "typer>=0.12.0",
+    "platformdirs>=3.0",
+    "tomli>=2.0; python_version < '3.11'",
+]
+
+[project.optional-dependencies]
+pandas = ["pandas>=2.0", "pyarrow>=14"]
+
+[project.scripts]
+genetrek = "genetrek.cli:main"
+
+[project.urls]
+Homepage = "https://genetrek.pasteur.fr"
+Documentation = "https://genetrek.pasteur.fr/api-reference"
+Repository = "https://github.com/bourgeron-lab/genetrek"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/genetrek"]
+
+[tool.ruff]
+extend = "../pyproject.toml"
+target-version = "py310"
+
+[tool.ruff.lint]
+# Raised only for a py310 target: exceptions are zero-cost from 3.11, and the
+# loop that skips a damaged stored list is clearer as written.
+extend-ignore = ["PERF203"]
+
+[tool.ruff.lint.per-file-ignores]
+# Typer reads each option from a boolean parameter's default.
+"src/genetrek/cli.py" = ["FBT001", "FBT002"]
+"tests/*.py" = ["S101", "ANN001", "ANN201", "ANN202", "PLR2004", "INP001"]

genetrek-0.1.0/src/genetrek/__init__.py

@@ -0,0 +1,49 @@
+"""GeneTrek from Python: the client for GeneTrek's API, and the ``genetrek`` command.
+
+>>> from genetrek import GeneTrek, Set
+>>> gt = GeneTrek()
+>>> gt.gene_list("hc_ndd")[:3]
+>>> gt.compare([Set.field("hc_ndd"), Set.genes(["SHANK3", "CHD8"], label="mine")])
+"""
+
+from __future__ import annotations
+
+from importlib.metadata import PackageNotFoundError, version
+
+try:
+    __version__ = version("genetrek")
+except PackageNotFoundError:  # pragma: no cover - running from a source tree
+    __version__ = "0+unknown"
+
+# After __version__: the client reads it.
+from genetrek.client import GeneTrek, UnresolvedWarning
+from genetrek.errors import (
+    AmbiguousGene,
+    ApiError,
+    ConfigError,
+    ConnectionFailed,
+    GeneTrekError,
+    NotAGeneList,
+    ServerTooOld,
+    UnknownField,
+    UnknownGene,
+)
+from genetrek.models import Comparison
+from genetrek.sets import Set
+
+__all__ = [
+    "AmbiguousGene",
+    "ApiError",
+    "Comparison",
+    "ConfigError",
+    "ConnectionFailed",
+    "GeneTrek",
+    "GeneTrekError",
+    "NotAGeneList",
+    "ServerTooOld",
+    "Set",
+    "UnknownField",
+    "UnknownGene",
+    "UnresolvedWarning",
+    "__version__",
+]