sirna-data-grabber 0.1.0__tar.gz

sirna_data_grabber-0.1.0/LICENSE

@@ -0,0 +1,30 @@
+MIT License
+
+Copyright (c) 2026 Brandon Walker
+
+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.
+
+---
+
+NOTE: This license applies only to the code in this repository (the
+`sirna_data` Python package, scripts/, and tests/). It does NOT apply to the
+datasets in data/raw/, which are redistributed under their own original
+licenses -- several of which restrict commercial use. See NOTICE.md and
+data/DATA_SOURCES.md before using the data itself outside non-commercial
+research.

sirna_data_grabber-0.1.0/NOTICE.md

@@ -0,0 +1,50 @@
+# NOTICE — data licenses
+
+This repo's code (`sirna_data`, `tests/`) is MIT licensed (see
+[`LICENSE`](LICENSE)) and may be used, modified, and redistributed freely,
+including commercially.
+
+**The datasets in `data/raw/` are separate from the code and are NOT MIT
+licensed.** Each was fetched from its original publisher and is redistributed
+here under that publisher's own terms. The MIT license on the code does not
+extend to the data, and using this permissively-licensed loader to read the
+data does not lift the data's own restrictions. Most sources below are
+**non-commercial only** — read this table before using the data for anything
+beyond non-commercial research, and see
+[`data/DATA_SOURCES.md`](data/DATA_SOURCES.md) for full terms and provenance
+per source.
+
+## Sources loaded by `load_records()`
+
+| Source | File(s) | License | Commercial use? |
+|---|---|---|---|
+| siRNAEfficacyDB (Zhang et al. 2024) | `sirna_efficacy.csv` | CC BY-NC | **No** — non-commercial only |
+| Monopoli et al. 2023 | `monopoli_extra.csv` | CC BY 4.0 | Yes, with attribution |
+| Shabalina et al. 2006 | `shabalina_extra.csv` | CC BY 2.0 | Yes, with attribution |
+| CMsiRNAdb (He et al. 2026) | `cmsirnadb_full_raw.tsv` | CC BY-NC-ND 4.0 | **No** — non-commercial only, and the "ND" term means only the original unmodified file may be redistributed (see below) |
+| NCBI RefSeq/GenBank transcripts | `*_transcripts.fasta` | Public domain | Yes, unrestricted |
+
+**CMsiRNAdb's "No Derivatives" term**: this repo ships only the untouched
+original `cmsirnadb_full_raw.tsv` download. All filtering, collapsing, and
+transformation happens in code at load time
+(`_load_cmsirnadb_records`/`_load_cmsirnadb_full_records` in
+`src/sirna_data/raw_loader.py`), not as a precomputed derivative file — so no
+adaptation of CMsiRNAdb's data is redistributed, only the original plus code
+that anyone can run themselves. See `data/CMSIRNADB_FULL_RETRIEVAL.md`.
+
+## Other files present in `data/raw/` but not used by anything in `sirna_data`
+
+These were investigated as candidate sources (see
+[`data/DATA_SOURCE_LEDGER.md`](data/DATA_SOURCE_LEDGER.md)) and kept for
+reference/provenance, but nothing in `sirna_data` reads them:
+
+| File(s) | Source | License |
+|---|---|---|
+| `sirecords_efficacy.csv`, `sirecords_new_only.csv` | siRecords (04/28/05 release, via Internet Archive) | **Restricted, not established for redistribution.** Researched: the database's own paper (Ren et al. 2009, NAR 37:D146-D149) is CC BY-NC licensed as an *article*, but its DATA ACCESS section says bulk copies were only ever given to "academic users" who emailed the authors directly — not published as an open download. The data here was recovered from an Internet Archive snapshot, not that channel, so no license actually covers this copy. See `data/sirecords_overlap_analysis.md` for the full writeup and sources. Kept locally but excluded from git (`.gitignore`). |
+
+## If you're not sure whether your use is covered
+
+None of the above is legal advice. If your use case isn't clearly
+non-commercial research, check the original source's license directly (links
+in `data/DATA_SOURCES.md`) or contact the original authors before relying on
+this data.

sirna_data_grabber-0.1.0/PKG-INFO

@@ -0,0 +1,183 @@
+Metadata-Version: 2.4
+Name: sirna-data-grabber
+Version: 0.1.0
+Summary: Reusable loader for the siRNA knockdown-efficacy dataset (siRNAEfficacyDB + supplementary sources), plus the fetchers that built it.
+Author-email: Brandon Walker <brandon.walker@ucsf.edu>
+License: MIT
+Project-URL: Homepage, https://github.com/BrandonWalk/sirna-data-grabber
+Project-URL: Repository, https://github.com/BrandonWalk/sirna-data-grabber
+Project-URL: Issues, https://github.com/BrandonWalk/sirna-data-grabber/issues
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Intended Audience :: Science/Research
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE.md
+Requires-Dist: pandas>=2.0
+Requires-Dist: requests>=2.32
+Provides-Extra: test
+Requires-Dist: pytest>=8.0; extra == "test"
+Provides-Extra: lint
+Requires-Dist: ruff>=0.6; extra == "lint"
+Requires-Dist: mypy>=1.10; extra == "lint"
+Requires-Dist: pandas-stubs; extra == "lint"
+Requires-Dist: types-requests; extra == "lint"
+Dynamic: license-file
+
+# sirna-data-grabber
+
+A standalone siRNA knockdown-efficacy dataset: the raw data files, full
+provenance/license documentation, and a small reusable Python package
+(`sirna_data`) for loading it -- and, since `pip install sirna-data-grabber`
+alone can't ship most of this non-commercial data, a bundled `sirna-data-fetch`
+command that re-fetches it from its original sources. Any project that wants
+this dataset can depend on this repo (or just the PyPI package) rather than
+vendoring a copy of the data or the loading code.
+
+## License
+
+**The code in this repo (`sirna_data`, `tests/`) is MIT licensed** — see
+[`LICENSE`](LICENSE). Use it, modify it, ship it commercially, whatever you
+want.
+
+**The data in `data/raw/` is NOT covered by that license.** It's redistributed
+under each original source's own terms, and most of those sources are
+**non-commercial only** (CC BY-NC / CC BY-NC-ND). Loading the data with this
+permissively-licensed code does not lift those restrictions — you still have
+to comply with them separately. See [`NOTICE.md`](NOTICE.md) for the
+per-source summary and [`data/DATA_SOURCES.md`](data/DATA_SOURCES.md) for
+full terms before using the data itself, especially commercially.
+
+## What's here
+
+```
+LICENSE                    MIT license -- covers the code only, not data/raw/
+NOTICE.md                  per-source data license summary (see License section above)
+data/
+  raw/                       fetched CSVs + FASTA transcripts (the actual dataset)
+  DATA_SOURCES.md            full provenance + license terms for every source
+  DATA_SOURCE_LEDGER.md      audit: what's trainable, what's not, and why
+  CMSIRNADB_FULL_RETRIEVAL.md   detail on the CMsiRNAdb full-database retrieval
+  DEMETER2_README.txt        upstream release notes for DepMap DEMETER2 (investigated, not included -- see FUNCTIONAL_GENOMICS_SCREENS.md)
+  FUNCTIONAL_GENOMICS_SCREENS.md   notes on functional-genomics screen sources considered
+  POTENTIAL_DATA_SOURCES.md  landscape of sources investigated
+  sirecords_overlap_analysis.md    siRecords overlap/dedup analysis
+  data_source_ledger.csv     machine-readable companion to DATA_SOURCE_LEDGER.md
+  *.png                      figures referenced by the docs above
+src/sirna_data/
+  raw_loader.py               load + merge every source into SiRNARecord rows
+  ncbi_fetch.py                fetch a gene's RefSeq mRNA transcript by symbol
+  __init__.py                  public API
+  fetch/                       sirna-data-fetch CLI + per-source fetchers (see Install below)
+    cli.py                       `sirna-data-fetch` entry point ([project.scripts])
+    sirna_efficacy.py            siRNAEfficacyDB + NCBI -> sirna_efficacy.csv, mrna_transcripts.fasta
+    monopoli.py                  Monopoli et al. 2023 supplementary data -> monopoli_*
+    shabalina.py                 Shabalina et al. 2006 supplementary data -> shabalina_*
+    cmsirnadb.py                 CMsiRNAdb + NCBI -> cmsirnadb_full_raw.tsv, cmsirnadb*_transcripts.fasta
+tests/
+  test_raw_loader.py          unit tests for raw_loader.py (fixtures, no real data needed)
+  test_ncbi_fetch.py          unit tests for ncbi_fetch.py (mocked HTTP calls)
+  conftest.py                 shared pytest fixtures
+```
+
+Start with [`data/DATA_SOURCES.md`](data/DATA_SOURCES.md) for what's in the
+dataset and where it came from; [`data/DATA_SOURCE_LEDGER.md`](data/DATA_SOURCE_LEDGER.md)
+for the bottom-line audit (6,577 trainable records across 87 genes, 4
+sources — 16,178 records / 97 genes if the optional CMsiRNAdb full-database
+retrieval is also included). Primary source is **siRNAEfficacyDB** (Zhang
+et al. 2024, CC BY-NC); see the docs for the rest and their individual
+license terms before reusing this data outside this project.
+
+## Install
+
+```
+python3 -m venv .venv && source .venv/bin/activate
+pip install -e .
+```
+
+This installs the `sirna_data` package in editable mode, so it resolves
+`data/raw/` relative to this checkout automatically. If you copy the `data/`
+folder somewhere else, point at it explicitly instead:
+
+```
+export SIRNA_DATA_DIR=/path/to/data/raw
+```
+
+Re-fetching the raw data from scratch (not required if `data/raw/` already
+has the files) uses the `sirna-data-fetch` command, installed automatically
+with the package -- no extras needed:
+
+```
+sirna-data-fetch --dest data/raw
+```
+
+This also means a plain `pip install sirna-data-grabber` from PyPI (with no
+git checkout at all) can reconstruct the full dataset itself:
+
+```
+pip install sirna-data-grabber
+sirna-data-fetch --dest ./my_data
+export SIRNA_DATA_DIR=./my_data
+```
+
+`sirna-data-fetch --only sirna_efficacy monopoli` fetches a subset instead of
+all four sources; see `sirna-data-fetch --help`.
+
+## Usage
+
+```python
+from sirna_data import load_records, fetch_mrna_by_gene
+
+records = load_records()  # list[SiRNARecord]
+print(len(records), "records across", len({r.gene for r in records}), "genes")
+
+r = records[0]
+r.guide_seq       # siRNA antisense strand
+r.mrna_window      # local mRNA context around the real target site
+r.label            # experimental %knockdown / %inhibition
+r.source           # provenance, e.g. "siRNAEfficacyDB"
+
+# Look up any gene's RefSeq transcript live from NCBI:
+transcript = fetch_mrna_by_gene("TP53")
+transcript.accession, transcript.sequence
+```
+
+`load_records()` takes `include_monopoli` / `include_shabalina` /
+`include_cmsirnadb` / `include_cmsirnadb_full` flags to exclude any
+supplementary source and use only the primary siRNAEfficacyDB set.
+
+## Using this from another project
+
+Install as a sibling checkout in editable mode:
+
+```
+pip install -e ../sirna-data-grabber
+```
+
+That gives you `import sirna_data` with no other coupling — this repo only
+depends on pandas and requests, and knows nothing about any particular
+downstream model or feature-engineering pipeline.
+
+## Tests
+
+```
+pip install -e ".[test]"
+pytest
+```
+
+Tests run entirely against small in-memory/tmp-dir fixtures (see
+`tests/conftest.py`) and mocked HTTP calls, so they don't touch the real
+dataset or the network.
+
+## Linting and type checking
+
+```
+pip install -e ".[lint]"
+ruff check .
+mypy
+```
+
+Both run in CI on every pull request (`.github/workflows/tests.yml`), alongside
+the test matrix.

sirna_data_grabber-0.1.0/README.md

@@ -0,0 +1,155 @@
+# sirna-data-grabber
+
+A standalone siRNA knockdown-efficacy dataset: the raw data files, full
+provenance/license documentation, and a small reusable Python package
+(`sirna_data`) for loading it -- and, since `pip install sirna-data-grabber`
+alone can't ship most of this non-commercial data, a bundled `sirna-data-fetch`
+command that re-fetches it from its original sources. Any project that wants
+this dataset can depend on this repo (or just the PyPI package) rather than
+vendoring a copy of the data or the loading code.
+
+## License
+
+**The code in this repo (`sirna_data`, `tests/`) is MIT licensed** — see
+[`LICENSE`](LICENSE). Use it, modify it, ship it commercially, whatever you
+want.
+
+**The data in `data/raw/` is NOT covered by that license.** It's redistributed
+under each original source's own terms, and most of those sources are
+**non-commercial only** (CC BY-NC / CC BY-NC-ND). Loading the data with this
+permissively-licensed code does not lift those restrictions — you still have
+to comply with them separately. See [`NOTICE.md`](NOTICE.md) for the
+per-source summary and [`data/DATA_SOURCES.md`](data/DATA_SOURCES.md) for
+full terms before using the data itself, especially commercially.
+
+## What's here
+
+```
+LICENSE                    MIT license -- covers the code only, not data/raw/
+NOTICE.md                  per-source data license summary (see License section above)
+data/
+  raw/                       fetched CSVs + FASTA transcripts (the actual dataset)
+  DATA_SOURCES.md            full provenance + license terms for every source
+  DATA_SOURCE_LEDGER.md      audit: what's trainable, what's not, and why
+  CMSIRNADB_FULL_RETRIEVAL.md   detail on the CMsiRNAdb full-database retrieval
+  DEMETER2_README.txt        upstream release notes for DepMap DEMETER2 (investigated, not included -- see FUNCTIONAL_GENOMICS_SCREENS.md)
+  FUNCTIONAL_GENOMICS_SCREENS.md   notes on functional-genomics screen sources considered
+  POTENTIAL_DATA_SOURCES.md  landscape of sources investigated
+  sirecords_overlap_analysis.md    siRecords overlap/dedup analysis
+  data_source_ledger.csv     machine-readable companion to DATA_SOURCE_LEDGER.md
+  *.png                      figures referenced by the docs above
+src/sirna_data/
+  raw_loader.py               load + merge every source into SiRNARecord rows
+  ncbi_fetch.py                fetch a gene's RefSeq mRNA transcript by symbol
+  __init__.py                  public API
+  fetch/                       sirna-data-fetch CLI + per-source fetchers (see Install below)
+    cli.py                       `sirna-data-fetch` entry point ([project.scripts])
+    sirna_efficacy.py            siRNAEfficacyDB + NCBI -> sirna_efficacy.csv, mrna_transcripts.fasta
+    monopoli.py                  Monopoli et al. 2023 supplementary data -> monopoli_*
+    shabalina.py                 Shabalina et al. 2006 supplementary data -> shabalina_*
+    cmsirnadb.py                 CMsiRNAdb + NCBI -> cmsirnadb_full_raw.tsv, cmsirnadb*_transcripts.fasta
+tests/
+  test_raw_loader.py          unit tests for raw_loader.py (fixtures, no real data needed)
+  test_ncbi_fetch.py          unit tests for ncbi_fetch.py (mocked HTTP calls)
+  conftest.py                 shared pytest fixtures
+```
+
+Start with [`data/DATA_SOURCES.md`](data/DATA_SOURCES.md) for what's in the
+dataset and where it came from; [`data/DATA_SOURCE_LEDGER.md`](data/DATA_SOURCE_LEDGER.md)
+for the bottom-line audit (6,577 trainable records across 87 genes, 4
+sources — 16,178 records / 97 genes if the optional CMsiRNAdb full-database
+retrieval is also included). Primary source is **siRNAEfficacyDB** (Zhang
+et al. 2024, CC BY-NC); see the docs for the rest and their individual
+license terms before reusing this data outside this project.
+
+## Install
+
+```
+python3 -m venv .venv && source .venv/bin/activate
+pip install -e .
+```
+
+This installs the `sirna_data` package in editable mode, so it resolves
+`data/raw/` relative to this checkout automatically. If you copy the `data/`
+folder somewhere else, point at it explicitly instead:
+
+```
+export SIRNA_DATA_DIR=/path/to/data/raw
+```
+
+Re-fetching the raw data from scratch (not required if `data/raw/` already
+has the files) uses the `sirna-data-fetch` command, installed automatically
+with the package -- no extras needed:
+
+```
+sirna-data-fetch --dest data/raw
+```
+
+This also means a plain `pip install sirna-data-grabber` from PyPI (with no
+git checkout at all) can reconstruct the full dataset itself:
+
+```
+pip install sirna-data-grabber
+sirna-data-fetch --dest ./my_data
+export SIRNA_DATA_DIR=./my_data
+```
+
+`sirna-data-fetch --only sirna_efficacy monopoli` fetches a subset instead of
+all four sources; see `sirna-data-fetch --help`.
+
+## Usage
+
+```python
+from sirna_data import load_records, fetch_mrna_by_gene
+
+records = load_records()  # list[SiRNARecord]
+print(len(records), "records across", len({r.gene for r in records}), "genes")
+
+r = records[0]
+r.guide_seq       # siRNA antisense strand
+r.mrna_window      # local mRNA context around the real target site
+r.label            # experimental %knockdown / %inhibition
+r.source           # provenance, e.g. "siRNAEfficacyDB"
+
+# Look up any gene's RefSeq transcript live from NCBI:
+transcript = fetch_mrna_by_gene("TP53")
+transcript.accession, transcript.sequence
+```
+
+`load_records()` takes `include_monopoli` / `include_shabalina` /
+`include_cmsirnadb` / `include_cmsirnadb_full` flags to exclude any
+supplementary source and use only the primary siRNAEfficacyDB set.
+
+## Using this from another project
+
+Install as a sibling checkout in editable mode:
+
+```
+pip install -e ../sirna-data-grabber
+```
+
+That gives you `import sirna_data` with no other coupling — this repo only
+depends on pandas and requests, and knows nothing about any particular
+downstream model or feature-engineering pipeline.
+
+## Tests
+
+```
+pip install -e ".[test]"
+pytest
+```
+
+Tests run entirely against small in-memory/tmp-dir fixtures (see
+`tests/conftest.py`) and mocked HTTP calls, so they don't touch the real
+dataset or the network.
+
+## Linting and type checking
+
+```
+pip install -e ".[lint]"
+ruff check .
+mypy
+```
+
+Both run in CI on every pull request (`.github/workflows/tests.yml`), alongside
+the test matrix.

sirna_data_grabber-0.1.0/pyproject.toml

@@ -0,0 +1,68 @@
+[build-system]
+requires = ["setuptools>=68", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "sirna-data-grabber"
+version = "0.1.0"
+description = "Reusable loader for the siRNA knockdown-efficacy dataset (siRNAEfficacyDB + supplementary sources), plus the fetchers that built it."
+readme = "README.md"
+requires-python = ">=3.10"
+license = { text = "MIT" }
+authors = [
+    { name = "Brandon Walker", email = "brandon.walker@ucsf.edu" },
+]
+classifiers = [
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Intended Audience :: Science/Research",
+    "Topic :: Scientific/Engineering :: Bio-Informatics",
+]
+dependencies = [
+    "pandas>=2.0",
+    "requests>=2.32",
+]
+
+[project.urls]
+Homepage = "https://github.com/BrandonWalk/sirna-data-grabber"
+Repository = "https://github.com/BrandonWalk/sirna-data-grabber"
+Issues = "https://github.com/BrandonWalk/sirna-data-grabber/issues"
+
+[project.optional-dependencies]
+test = ["pytest>=8.0"]
+lint = ["ruff>=0.6", "mypy>=1.10", "pandas-stubs", "types-requests"]
+
+# Installed automatically -- `sirna-data-fetch` fetches every source
+# load_records() reads into a local directory (data/DATA_SOURCES.md), so a
+# plain `pip install sirna-data-grabber` can reconstruct the dataset without
+# cloning the git repo. No extra dependencies: everything under
+# sirna_data/fetch/ only needs pandas (already required above) plus the
+# standard library.
+[project.scripts]
+sirna-data-fetch = "sirna_data.fetch.cli:main"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = "-ra"
+
+[tool.ruff]
+line-length = 100
+target-version = "py310"
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "UP", "B"]
+
+[tool.ruff.lint.per-file-ignores]
+# long single-line TSV fixture rows are more readable unwrapped
+"tests/conftest.py" = ["E501"]
+
+[tool.mypy]
+python_version = "3.10"
+files = ["src"]
+ignore_missing_imports = true
+warn_unused_ignores = true
+warn_redundant_casts = true
+check_untyped_defs = true

sirna_data_grabber-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

sirna_data_grabber-0.1.0/src/sirna_data/__init__.py

@@ -0,0 +1,29 @@
+"""sirna_data: reusable loader for the siRNA knockdown-efficacy dataset.
+
+    from sirna_data import load_records, SiRNARecord, fetch_mrna_by_gene
+
+`load_records()` returns the full merged, provenance-documented dataset
+(siRNAEfficacyDB + supplementary sources) as a list of `SiRNARecord`, each
+pairing an siRNA guide with its real local mRNA target context and
+experimentally measured knockdown label. See ../../data/DATA_SOURCES.md for
+where every row comes from.
+
+`fetch_mrna_by_gene()` looks up a gene's RefSeq mRNA transcript live from
+NCBI, for callers that only have a gene symbol.
+"""
+from __future__ import annotations
+
+from .ncbi_fetch import FetchedTranscript, GeneNotFoundError, fetch_mrna_by_gene
+from .raw_loader import DATA_DIR, SiRNARecord, load_records, read_fasta
+
+__all__ = [
+    "load_records",
+    "SiRNARecord",
+    "read_fasta",
+    "DATA_DIR",
+    "fetch_mrna_by_gene",
+    "FetchedTranscript",
+    "GeneNotFoundError",
+]
+
+__version__ = "0.1.0"

sirna_data_grabber-0.1.0/src/sirna_data/fetch/__init__.py

@@ -0,0 +1,22 @@
+"""Fetch the raw data `sirna_data.load_records()` reads, from each source's
+original location, into a local directory -- so a plain `pip install
+sirna-data-grabber` install can reconstruct the dataset without cloning the
+git repo.
+
+    from sirna_data.fetch import cmsirnadb, monopoli, shabalina, sirna_efficacy
+    sirna_efficacy.fetch(Path("./my_data"))
+
+Or from the command line (installed automatically, no extras required --
+every fetcher here only needs pandas, already a core dependency, plus the
+standard library):
+
+    sirna-data-fetch --dest ./my_data
+    export SIRNA_DATA_DIR=./my_data
+
+This only covers the four sources `load_records()` actually reads
+(siRNAEfficacyDB, Monopoli 2023, Shabalina 2006, CMsiRNAdb). See
+../../../data/DATA_SOURCES.md for full provenance/license notes per source,
+and NOTICE.md before using the fetched data commercially -- most of it is
+non-commercial only.
+"""
+from __future__ import annotations

sirna_data_grabber-0.1.0/src/sirna_data/fetch/cli.py

@@ -0,0 +1,70 @@
+"""Command-line entry point: `sirna-data-fetch` (registered via
+[project.scripts] in pyproject.toml). Fetches every source
+`sirna_data.load_records()` reads, from its original location, into a local
+directory.
+
+    sirna-data-fetch --dest ./my_data
+    export SIRNA_DATA_DIR=./my_data
+
+This is installed automatically with `pip install sirna-data-grabber` --
+no extras needed, since every fetcher here only needs pandas (already a
+core dependency) plus the standard library.
+"""
+from __future__ import annotations
+
+import argparse
+import os
+from pathlib import Path
+
+from . import cmsirnadb, monopoli, shabalina, sirna_efficacy
+
+# Order matters only for display; each fetcher is independent.
+SOURCES = {
+    "sirna_efficacy": sirna_efficacy.fetch,
+    "monopoli": monopoli.fetch,
+    "shabalina": shabalina.fetch,
+    "cmsirnadb": cmsirnadb.fetch,
+}
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(
+        prog="sirna-data-fetch",
+        description=(
+            "Fetch the siRNA knockdown-efficacy dataset (siRNAEfficacyDB + "
+            "supplementary sources) from its original sources into a local "
+            "directory, for use with sirna_data.load_records()."
+        ),
+    )
+    parser.add_argument(
+        "--dest",
+        type=Path,
+        default=Path(os.environ.get("SIRNA_DATA_DIR", "data/raw")),
+        help=(
+            "Directory to write the fetched files into "
+            "(default: $SIRNA_DATA_DIR if set, else ./data/raw)."
+        ),
+    )
+    parser.add_argument(
+        "--only",
+        nargs="+",
+        choices=sorted(SOURCES),
+        metavar="SOURCE",
+        help=f"Fetch only these sources instead of all four ({', '.join(sorted(SOURCES))}).",
+    )
+    args = parser.parse_args()
+
+    dest: Path = args.dest.resolve()
+    dest.mkdir(parents=True, exist_ok=True)
+    names = args.only or sorted(SOURCES)
+
+    for name in names:
+        print(f"=== {name} ===")
+        SOURCES[name](dest)
+        print()
+
+    print(f"Done. To use this data:\n  export SIRNA_DATA_DIR={dest}")
+
+
+if __name__ == "__main__":
+    main()