prs-pipeline 0.2.2__tar.gz

prs_pipeline-0.2.2/.gitignore

@@ -0,0 +1,238 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$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
+
+# 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
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.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
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursor/
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Data directories (all data must live outside the source tree)
+data/
+output/
+pgs_metadata/
+pgs_scores/
+scores/
+
+# Uploaded files (UI uploads must go to data/input/, never source dirs)
+**/uploaded_files/
+
+# Large data files (NEVER commit these — GitHub rejects files > 100 MB)
+*.vcf
+*.vcf.gz
+*.vcf.bgz
+*.parquet
+*.fa
+*.fasta
+*.fa.gz
+*.fasta.gz
+*.bam
+*.cram
+*.bai
+*.crai
+*.bgz
+*.tbi
+
+#cursor
+.cursor/
+*.code-workspace

prs_pipeline-0.2.2/PKG-INFO

@@ -0,0 +1,48 @@
+Metadata-Version: 2.4
+Name: prs-pipeline
+Version: 0.2.2
+Summary: Dagster pipeline for computing PRS reference distributions from the 1000G panel
+Author-email: antonkulaga <antonkulaga@gmail.com>
+Requires-Python: >=3.13
+Requires-Dist: dagster-polars>=0.27.9
+Requires-Dist: dagster-webserver>=1.12.19
+Requires-Dist: dagster>=1.12.19
+Requires-Dist: just-prs>=0.3.1
+Requires-Dist: psutil>=7.2.2
+Requires-Dist: python-dotenv>=1.2.2
+Requires-Dist: typer>=0.24.1
+Description-Content-Type: text/markdown
+
+# prs-pipeline
+
+Dagster pipeline for computing PRS reference distributions from the 1000 Genomes reference panel.
+
+## Overview
+
+This pipeline downloads the PGS Catalog 1000G reference panel (~7 GB), computes polygenic risk scores
+for all 2,504 reference individuals across all PGS Catalog scores, aggregates per-superpopulation
+distribution statistics, and pushes `reference_distributions.parquet` to HuggingFace
+(`just-dna-seq/prs-percentiles`).
+
+End users of `just-prs` automatically pull this tiny parquet via `PRSCatalog.reference_distributions()`.
+
+## Running
+
+```bash
+cd prs-pipeline
+uv run dagster dev -m prs_pipeline.definitions
+```
+
+Then open http://localhost:3000 in your browser.
+
+## Assets
+
+| Asset | Group | Description |
+|-------|-------|-------------|
+| `ebi_reference_panel_fingerprint` | download | HTTP fingerprint for freshness tracking of the remote reference panel |
+| `ebi_scoring_files_fingerprint` | download | HTTP fingerprint for the remote scoring file manifest |
+| `scoring_files` | download | Bulk-download all harmonized PGS scoring `.txt.gz` files from EBI FTP |
+| `scoring_files_parquet` | compute | Convert all `.txt.gz` scoring files to spec-driven parquet caches (zstd-9, embedded headers). Deletes `.txt.gz` after verified conversion to save ~5.5 GB disk space. Tracks per-file failures in `conversion_failures.parquet` |
+| `reference_panel` | download | Download + extract reference panel binary files (.pgen/.pvar/.psam) |
+| `reference_scores` | compute | Score all PGS IDs against the reference panel via `compute_reference_prs_batch()` |
+| `hf_prs_percentiles` | upload | Enrich distributions with metadata and push to HuggingFace |

prs_pipeline-0.2.2/README.md

@@ -0,0 +1,33 @@
+# prs-pipeline
+
+Dagster pipeline for computing PRS reference distributions from the 1000 Genomes reference panel.
+
+## Overview
+
+This pipeline downloads the PGS Catalog 1000G reference panel (~7 GB), computes polygenic risk scores
+for all 2,504 reference individuals across all PGS Catalog scores, aggregates per-superpopulation
+distribution statistics, and pushes `reference_distributions.parquet` to HuggingFace
+(`just-dna-seq/prs-percentiles`).
+
+End users of `just-prs` automatically pull this tiny parquet via `PRSCatalog.reference_distributions()`.
+
+## Running
+
+```bash
+cd prs-pipeline
+uv run dagster dev -m prs_pipeline.definitions
+```
+
+Then open http://localhost:3000 in your browser.
+
+## Assets
+
+| Asset | Group | Description |
+|-------|-------|-------------|
+| `ebi_reference_panel_fingerprint` | download | HTTP fingerprint for freshness tracking of the remote reference panel |
+| `ebi_scoring_files_fingerprint` | download | HTTP fingerprint for the remote scoring file manifest |
+| `scoring_files` | download | Bulk-download all harmonized PGS scoring `.txt.gz` files from EBI FTP |
+| `scoring_files_parquet` | compute | Convert all `.txt.gz` scoring files to spec-driven parquet caches (zstd-9, embedded headers). Deletes `.txt.gz` after verified conversion to save ~5.5 GB disk space. Tracks per-file failures in `conversion_failures.parquet` |
+| `reference_panel` | download | Download + extract reference panel binary files (.pgen/.pvar/.psam) |
+| `reference_scores` | compute | Score all PGS IDs against the reference panel via `compute_reference_prs_batch()` |
+| `hf_prs_percentiles` | upload | Enrich distributions with metadata and push to HuggingFace |

prs_pipeline-0.2.2/pyproject.toml

@@ -0,0 +1,32 @@
+[project]
+name = "prs-pipeline"
+version = "0.2.2"
+description = "Dagster pipeline for computing PRS reference distributions from the 1000G panel"
+readme = "README.md"
+authors = [
+    { name = "antonkulaga", email = "antonkulaga@gmail.com" }
+]
+requires-python = ">=3.13"
+dependencies = [
+    "just-prs>=0.3.1",
+    "dagster>=1.12.19",
+    "dagster-webserver>=1.12.19",
+    "dagster-polars>=0.27.9",
+    "python-dotenv>=1.2.2",
+    "typer>=0.24.1",
+    "psutil>=7.2.2",
+]
+
+[project.scripts]
+prs-pipeline = "prs_pipeline.definitions:main"
+pipeline = "prs_pipeline.cli:app"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/prs_pipeline"]
+
+[tool.uv.sources]
+just-prs = { workspace = true }

prs_pipeline-0.2.2/src/prs_pipeline/__init__.py

@@ -0,0 +1 @@
+"""PRS reference panel pipeline — Dagster Software-Defined Assets."""