Initial commit

.baseline_version

@@ -0,0 +1 @@
+0.4.2-baseline-version

.editorconfig

@@ -0,0 +1,15 @@
+# EditorConfig is awesome: http://EditorConfig.org
+
+# top-most EditorConfig file
+root = true
+
+[*]
+end_of_line = lf
+insert_final_newline = true
+charset = utf-8
+indent_style = space
+indent_size = 4
+
+[*.{yml,yaml}]
+indent_style = space
+indent_size = 2

.gitattributes

@@ -0,0 +1,2 @@
+*.smk linguist-language=Python
+Snakefile linguist-language=Python

.github/workflows/docs.yml

@@ -0,0 +1,18 @@
+name: docs
+on:
+  workflow_dispatch:
+  push:
+    paths:
+      - 'docs/**'
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - uses: actions/setup-python@v2
+        with:
+          python-version: 3.9
+      - run: pip install --upgrade pip
+      - run: pip install -r docs/requirements.txt
+      - run: mkdocs gh-deploy --force

.github/workflows/main.yaml

@@ -0,0 +1,34 @@
+name: tests
+
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - master
+      - main
+  pull_request:
+    branches_ignore: []
+
+jobs:
+  Dry_Run_and_Lint:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - uses: docker://snakemake/snakemake:v5.24.2
+    - name: Dry Run with test data
+      run: |
+        docker run -v $PWD:/opt2 snakemake/snakemake:v5.24.2 \
+        /opt2/baseline run --input \
+        /opt2/.tests/WT_S1.R1.fastq.gz /opt2/.tests/WT_S1.R2.fastq.gz \
+        /opt2/.tests/WT_S2_R1.fastq.gz /opt2/.tests/WT_S2_R2.fastq.gz \
+        /opt2/.tests/WT_S3_1.fastq.gz /opt2/.tests/WT_S3_2.fastq.gz \
+        /opt2/.tests/WT_S4_R1.001.fastq.gz /opt2/.tests/WT_S4_R2.001.fastq.gz \
+        --output /opt2/output --mode local --dry-run
+    - name: View the pipeline config file
+      run: |
+        echo "Generated config file for pipeline...." && cat $PWD/output/config.json
+    - name: Lint Workflow
+      continue-on-error: true
+      run: |
+        docker run -v $PWD:/opt2 snakemake/snakemake:v5.24.2 snakemake --lint -s /opt2/output/workflow/Snakefile -d /opt2/output || \
+        echo 'There may have been a few warnings or errors. Please read through the log to determine if its harmless.'

.gitignore

@@ -0,0 +1,171 @@
+# 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/
+pip-wheel-metadata/
+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/
+
+# 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
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.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
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+site/
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# DS_Store
+.DS_Store
+._*
+**/.DS_Store
+**/._*
+
+.snakemake*
+**/.snakemake*
+.venv
+.venv/*
+
+# Pipeline Results or Output
+results/
+output/
+tmp/
+scratch/
+
+# mkdocs documentation
+site/
+
+# Pipeline generated files or directories
+.tests/*/
+.snakemake/
+
+# Cached Java directories
+.oracle_jre_usage/
+.java/
+
+# GNU Parallel
+.parallel/
+
+# Temp files
+*.tmp
+**/*.tmp
+
+# Test script and test 
+# output directories
+test.sh
+test_*/
+tmp_*/

CHANGELOG.md

@@ -0,0 +1,9 @@
+# Changelog
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [0.1.0] - 2022-08-22
+### Added
+  - Recommended [scaffold](https://github.com/OpenOmics/baseline) for building a snakemake pipeline

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 OpenOmics
+
+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.

README.md

@@ -0,0 +1,108 @@
+<div align="center">
+
+  <h1>baseline 🔬</h1>
+
+  **_long pipeline name_**
+
+  [![tests](https://github.com/OpenOmics/baseline/workflows/tests/badge.svg)](https://github.com/OpenOmics/baseline/actions/workflows/main.yaml) [![docs](https://github.com/OpenOmics/baseline/workflows/docs/badge.svg)](https://github.com/OpenOmics/baseline/actions/workflows/docs.yml) [![GitHub issues](https://img.shields.io/github/issues/OpenOmics/baseline?color=brightgreen)](https://github.com/OpenOmics/baseline/issues)  [![GitHub license](https://img.shields.io/github/license/OpenOmics/baseline)](https://github.com/OpenOmics/baseline/blob/main/LICENSE) 
+
+  <i>
+    This is the home of the pipeline, baseline. Its long-term goals: to accurately ...insert goal, to infer ...insert goal, and to boldly ...insert goal like no pipeline before!
+  </i>
+</div>
+
+## Overview
+Welcome to baseline! Before getting started, we highly recommend reading through [baseline's documentation](https://openomics.github.io/baseline/).
+
+The **`./baseline`** pipeline is composed several inter-related sub commands to setup and run the pipeline across different systems. Each of the available sub commands perform different functions: 
+
+ * [<code>baseline <b>run</b></code>](https://openomics.github.io/baseline/usage/run/): Run the baseline pipeline with your input files.
+ * [<code>baseline <b>unlock</b></code>](https://openomics.github.io/baseline/usage/unlock/): Unlocks a previous runs output directory.
+ * [<code>baseline <b>install</b></code>](https://openomics.github.io/baseline/usage/install/): Download reference files locally.
+ * [<code>baseline <b>cache</b></code>](https://openomics.github.io/baseline/usage/cache/): Cache remote resources locally, coming soon!
+
+**baseline** is a comprehensive ...insert long description. It relies on technologies like [Singularity<sup>1</sup>](https://singularity.lbl.gov/) to maintain the highest-level of reproducibility. The pipeline consists of a series of data processing and quality-control steps orchestrated by [Snakemake<sup>2</sup>](https://snakemake.readthedocs.io/en/stable/), a flexible and scalable workflow management system, to submit jobs to a cluster.
+
+The pipeline is compatible with data generated from Illumina short-read sequencing technologies. As input, it accepts a set of FastQ files and can be run locally on a compute instance or on-premise using a cluster. A user can define the method or mode of execution. The pipeline can submit jobs to a cluster using a job scheduler like SLURM (more coming soon!). A hybrid approach ensures the pipeline is accessible to all users.
+
+Before getting started, we highly recommend reading through the [usage](https://openomics.github.io/baseline/usage/run/) section of each available sub command.
+
+For more information about issues or trouble-shooting a problem, please checkout our [FAQ](https://openomics.github.io/baseline/faq/questions/) prior to [opening an issue on Github](https://github.com/OpenOmics/baseline/issues).
+
+## Dependencies
+**Requires:** `singularity>=3.5`  `snakemake>=6.0`
+
+At the current moment, the pipeline uses a mixture of enviroment modules and docker images; however, this will be changing soon! In the very near future, the pipeline will only use docker images. With that being said, [snakemake](https://snakemake.readthedocs.io/en/stable/getting_started/installation.html) and [singularity](https://singularity.lbl.gov/all-releases) must be installed on the target system. Snakemake orchestrates the execution of each step in the pipeline. To guarantee the highest level of reproducibility, each step of the pipeline will rely on versioned images from [DockerHub](https://hub.docker.com/orgs/nciccbr/repositories). Snakemake uses singularity to pull these images onto the local filesystem prior to job execution, and as so, snakemake and singularity will be the only two dependencies in the future.
+
+## Installation
+Please clone this repository to your local filesystem using the following command:
+```bash
+# Clone Repository from Github
+git clone https://github.com/OpenOmics/baseline.git
+# Change your working directory
+cd baseline/
+# Add dependencies to $PATH
+# Biowulf users should run
+module load snakemake singularity
+# Get usage information
+./baseline -h
+```
+
+## Contribute 
+This site is a living document, created for and by members like you. baseline is maintained by the members of OpenOmics and is improved by continous feedback! We encourage you to contribute new content and make improvements to existing content via pull request to our [GitHub repository](https://github.com/OpenOmics/baseline).
+
+
+## Cite
+
+If you use this software, please cite it as below:  
+
+<details>
+  <summary><b><i>@BibText</i></b></summary>
+
+```text
+Citation coming soon!
+```
+
+</details>
+
+<details>
+  <summary><b><i>@APA</i></b></summary>
+
+```text
+Citation coming soon!
+```
+
+</details>
+
+<!---
+# Setup from baseline template
+```bash
+# Add your new pipeline name here,
+# whatever you set here will be the
+# name of your cli too. Please make 
+# sure it does not contain any spaces
+# It should only contain, alpha-numeric
+# characters and hyphens. 
+new_pipeline_name="add_your_pipeline_name_here"
+
+# Dry-run: This step automagically builds a 
+# command to update any instances of the string
+# baseline with your new pipeline name, please
+# make sure to set the variable above to whatever
+# you want to name the pipeline and CLI.
+find . -type f -not -path '*/.baseline_version' -not -path '*./CHANGELOG.md' -not -path '*/.git/*' -exec grep 'baseline' {} /dev/null \; | awk -F ':' '{print $1}' | sort | uniq | sed "s/^/sed -i 's@basline@$new_pipeline_name@g' /g"
+
+# Updates any instances of the string baseline
+# with the name you decided/set above.
+find . -type f -not -path '*/.baseline_version' -not -path '*./CHANGELOG.md' -not -path '*/.git/*' -exec grep 'baseline' {} /dev/null \; | awk -F ':' '{print $1}' | sort | uniq | sed "s/^/sed -i 's@basline@$new_pipeline_name@g' /g" | bash
+
+# Rename the cli or main entry point 
+# of the pipeline
+mv baseline "$new_pipeline_name"
+```
+-->
+
+
+## References
+<sup>**1.**  Kurtzer GM, Sochat V, Bauer MW (2017). Singularity: Scientific containers for mobility of compute. PLoS ONE 12(5): e0177459.</sup>  
+<sup>**2.**  Koster, J. and S. Rahmann (2018). "Snakemake-a scalable bioinformatics workflow engine." Bioinformatics 34(20): 3600.</sup>  

VERSION

@@ -0,0 +1 @@
+0.1.0