gbanyan
8aa66987f8
- Create LiteratureRecord pydantic model with context-specific counts - Implement PubMed query via Biopython Entrez with rate limiting (3/sec default, 10/sec with API key) - Define SEARCH_CONTEXTS for cilia, sensory, cytoskeleton, cell_polarity queries - Implement evidence tier classification: direct_experimental > functional_mention > hts_hit > incidental > none - Implement quality-weighted scoring with bias mitigation via log2(total_pubmed_count) normalization - Add biopython>=1.84 dependency to pyproject.toml - Support checkpoint-restart for long-running PubMed queries (estimated 3-11 hours for 20K genes)
62 lines
1.4 KiB
TOML
62 lines
1.4 KiB
TOML
[build-system]
|
|
requires = ["setuptools>=61.0", "wheel"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[project]
|
|
name = "usher-pipeline"
|
|
version = "0.1.0"
|
|
description = "Reproducible pipeline for discovering under-studied cilia/Usher candidate genes"
|
|
requires-python = ">=3.11"
|
|
authors = [
|
|
{name = "Research Team"}
|
|
]
|
|
readme = "README.md"
|
|
license = {text = "MIT"}
|
|
classifiers = [
|
|
"Development Status :: 3 - Alpha",
|
|
"Intended Audience :: Science/Research",
|
|
"License :: OSI Approved :: MIT License",
|
|
"Programming Language :: Python :: 3.11",
|
|
"Programming Language :: Python :: 3.12",
|
|
"Topic :: Scientific/Engineering :: Bio-Informatics",
|
|
]
|
|
|
|
dependencies = [
|
|
"mygene>=3.2.0",
|
|
"requests>=2.31.0",
|
|
"requests-cache>=1.1.0",
|
|
"tenacity>=8.2.0",
|
|
"pydantic>=2.0",
|
|
"pydantic-yaml>=1.2.0",
|
|
"duckdb>=0.9.0",
|
|
"click>=8.1.0",
|
|
"polars>=0.19.0",
|
|
"pyarrow>=14.0.0",
|
|
"pyyaml>=6.0",
|
|
"httpx>=0.28",
|
|
"structlog>=25.0",
|
|
"biopython>=1.84",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
dev = [
|
|
"pytest>=7.4.0",
|
|
"pytest-cov>=4.1.0",
|
|
]
|
|
expression = [
|
|
"cellxgene-census>=1.19",
|
|
]
|
|
|
|
[project.scripts]
|
|
usher-pipeline = "usher_pipeline.cli.main:cli"
|
|
|
|
[tool.setuptools]
|
|
packages = ["usher_pipeline"]
|
|
package-dir = {"" = "src"}
|
|
|
|
[tool.pytest.ini_options]
|
|
testpaths = ["tests"]
|
|
python_files = ["test_*.py"]
|
|
python_functions = ["test_*"]
|
|
addopts = "-v --strict-markers"
|