Click

.github/workflows/pre-commit.yml

@@ -0,0 +1,27 @@
+name: Pre-Commit 
+
+on:
+  push:
+    branches: [ '*' ]
+  pull_request:
+    branches: [ '*' ]
+
+jobs:
+  build-test:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-latest]
+        python-version: [3.8]
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+      - name: Setup Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install dependencies
+        run: |
+          pip install .
+      - name: PreCommit
+        uses: pre-commit/action@v3.0.0

.gitignore

@@ -1,9 +1,137 @@
-*.fastq
-*.fastq.gz
-*.h5ad
-*.hdf5
-*.pdf
-*.zarr
-.idea/
+# MacOS
+
+.DS_Store
+
+### Genomics ###
+
+# *.fastq
+# *.fastq.gz
+# *.h5ad
+# *.hdf5
+# *.pdf
+# *.zarr
+# .idea/
+# __pycache__/
+# out/
+
+### Pytest
+
+
+
+
+### VS Code ###
+
+.vscode/
+
+### Python ###
+
+# Byte-compiled / optimized / DLL files
 __pycache__/
-out/
+*.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
+
+# 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
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Environments
+.env
+.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
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/

.pre-commit-config.yaml

@@ -1,11 +1,12 @@
 repos:
   - repo: https://github.com/psf/black
-    rev: 22.6.0
+    rev: 22.10.0
     hooks:
       - id: black
         language_version: python3
-  - repo: https://github.com/pycqa/isort
-    rev: 5.10.1
+  - repo: https://github.com/PyCQA/isort
+    rev: 5.12.0
     hooks:
       - id: isort
+        name: isort (python)
         args: ["--profile", "black"]

README.md

@@ -0,0 +1,80 @@
+<h1 align="center">
+  <br>
+</h1>
+
+<div class="flex-container" align="center">
+    <a href="https://img.shields.io/badge/Python-3.%7C3.8%7C3.9%7C3.10%7C3.11-blue">
+    <img src="https://img.shields.io/badge/Python-3.7%7C3.8%7C3.9%7C3.10%7C3.11-blue"
+        alt="Python Version">
+    <a href="https://github.com/psf/black">
+    <img src="https://img.shields.io/badge/code%20style-black-000000.svg"
+        alt="Format Version">
+    <a href="https://github.com/pre-commit/pre-commit">
+    <img src="https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white"
+        alt="pre commit">
+    </br>
+    <a href="https://www.docker.com">
+    <img src="https://img.shields.io/badge/docker-%230db7ed.svg?style=for-the-badge&logo=docker&logoColor=white"
+        alt="Docker">
+    <a href="https://www.commonwl.org">
+    <img src="https://img.shields.io/badge/cwltool-red?style=for-the-badge&logo=cwltool&logoColor=white"
+        alt="cwltool">
+</div>
+
+<p align="center" style="color:green">
+  <a href="#about">About</a> •
+  <a href="#requirements">Requirements</a> •
+  <a href="#installation">Installation</a> •
+  <a href="#usage">Usage</a> •
+  <a href="#license">License</a>
+</p>
+
+# About
+
+The HuBMAP scRNA-seq pipeline is built on Salmon, Scanpy, and scVelo, and is
+implemented as a CWL workflow wrapping command-line tools encapsulated in
+Docker containers.
+
+# Requirements
+
+- 28Gbs of RAM
+- Docker
+
+We require [Docker](https://www.docker.com/) to run the pipeline.
+
+Once Docker is installed run the Docker Daemon. On Linux, this is typically
+done by running ``sudo dockerd``. On Mac, this is done by clicking the Docker GUI app. If you are using a M1 or newer silicon Mac, add ``export DOCKER_DEFAULT_PLATFORM=linux/amd64`` to your ``.zshrc`` file to avoid docker warnings and possible errors.
+
+# Installation
+
+Clone the repository and install the requirements. The ``master`` branch and ``latest`` published Docker images may not always
+be in sync; checking out a version like ``v2.0.6`` is *highly* recommended
+before running the pipeline, unless building Docker images locally.
+
+```bash
+git clone https://github.com/tmsincomb/salmon-rnaseq.git
+cd salmon-rnaseq
+pip install -e .
+```
+
+# Usage
+```bash
+salmon-rnaseq --help
+salmon-rnaseq --assay ASSAY --fastq_dir FASTQ_DIR --threads THREADS -o OUTPUT_DIR
+```
+
+Supported assays:
+
+* ``10x_v2`` (single-cell)
+* ``10x_v2_sn`` (single-nucleus)
+* ``10x_v3`` (single-cell)
+* ``10x_v3_sn`` (single-nucleus)
+* ``snareseq``
+* ``sciseq``
+* ``slideseq``
+
+# License
+
+[![License](https://img.shields.io/github/license/hubmapconsortium/salmon-rnaseq)](https://github.com/hubmapconsortium/salmon-rnaseq/blob/main/LICENSE)
+
+Copyright © HuBMAP

bin/analysis/adjust_barcodes.py

@@ -3,11 +3,11 @@
 from pathlib import Path
 from typing import Iterable
 
-import manhole
-
 import correct_snareseq_barcodes
 import expand_sciseq_barcodes
 import extract_slideseq_barcodes
+import manhole
+
 from common import ADJ_OUTPUT_DIR, Assay
 
 adj_funcs = {

bin/analysis/annotate_cells.py

@@ -3,11 +3,11 @@
 from pathlib import Path
 from typing import Optional, Sequence
 
+import add_slideseq_coordinates
 import anndata
+import annotate_sciseq_barcodes
 import manhole
 
-import add_slideseq_coordinates
-import annotate_sciseq_barcodes
 from common import Assay
 
 H5AD_PATH = Path("expr.h5ad")

bin/analysis/fastqc_wrapper.py

@@ -25,7 +25,7 @@ def single_file_fastqc(fastq_file_and_subdir: Tuple[Path, Path]):
     """
     command = [piece.format(out_dir=fastq_file_and_subdir[1]) for piece in FASTQC_COMMAND_TEMPLATE]
     command.append(fspath(fastq_file_and_subdir[0]))
-    print("Running", " ".join(command))
+    print("Running:", " ".join(command))
     check_call(command)
 
 

bin/analysis/scanpy_entry_point.py

@@ -6,9 +6,9 @@
 import manhole
 import matplotlib.pyplot as plt
 import scanpy as sc
+from plot_utils import new_plot
 
 from common import Assay
-from plot_utils import new_plot
 
 
 def main(assay: Assay, h5ad_file: Path):

bin/analysis/scvelo_analysis.py

@@ -9,7 +9,6 @@
 import scanpy as sc
 import scipy.sparse
 import scvelo as scv
-
 from plot_utils import new_plot
 
 component_neighbor_count = 50

bin/salmon/bulk_salmon_wrapper.py

@@ -42,9 +42,9 @@ def main(threads: int, directory: Path):
 
         fastq_extension = [
             "-1",
-            fspath(r1_fastq_file),
+            str(fspath(r1_fastq_file)),
             "-2",
-            fspath(r2_fastq_file),
+            str(fspath(r2_fastq_file)),
         ]
 
         command.extend(fastq_extension)