Initial commit

.github/workflows/release.yml

@@ -0,0 +1,34 @@
+on:
+  push:
+    branches:
+      - main
+
+name: Release
+
+jobs:
+  bump-version:
+    name: Release version
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: GoogleCloudPlatform/release-please-action@v3
+        id: release
+        with:
+          release-type: python # just keep a changelog, no version anywhere outside of git tags
+          package-name: juno_template
+  lint:
+    name: Lint Code Base
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout Code
+        uses: actions/checkout@v3
+
+      - name: Lint Code Base
+        uses: github/super-linter@v4
+        env:
+          VALIDATE_ALL_CODEBASE: false
+          DEFAULT_BRANCH: main
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+          VALIDATE_SNAKEMAKE_SNAKEFMT: true

.gitignore

@@ -0,0 +1,144 @@
+# 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
+
+# Vscode stuff:
+.vscode
+
+# 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
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# Added stuff
+.snakemake
+envs/src
+input
+output
+sample_sheet.yaml
+config/sample_sheet.yaml
+config/variables.yaml
+config/juno_call.txt 
+config/user_parameters.yaml
+core.*

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "juno-library"]
+	path = base_juno_pipeline
+	url = https://github.com/RIVM-bioinformatics/base_juno_pipeline.git

CHANGELOG.md

@@ -0,0 +1,8 @@
+# Changelog
+
+## [1.0.1](https://github.com/RIVM-bioinformatics/juno-template/compare/v1.0.0...v1.0.1) (2023-07-12)
+
+
+### Dependencies
+
+* remove anaconda and defaults and add no defaults channel ([0b4fccb](https://github.com/RIVM-bioinformatics/juno-template/commit/0b4fccb29d192570060ed81f6222b78293e195a7))

README.md

@@ -0,0 +1,7 @@
+# Juno-Template
+A template pipeline where the other juno pipelines are based on.
+
+## Contribution guidelines
+Juno pipelines use a [feature branch workflow](https://www.atlassian.com/git/tutorials/comparing-workflows/feature-branch-workflow). To work on features, create a branch from the `main` branch to make changes to. This branch can be merged to the main branch via a pull request. Hotfixes for bugs can be committed to the `main` branch.
+
+Please adhere to the [conventional commits](https://www.conventionalcommits.org/) specification for commit messages. These commit messages can be picked up by [release please](https://github.com/googleapis/release-please) to create meaningful release messages.

Snakefile

@@ -0,0 +1,25 @@
+import yaml
+
+
+sample_sheet=config["sample_sheet"]
+with open(sample_sheet) as f:
+    SAMPLES = yaml.safe_load(f)
+
+for param in ["threads", "mem_gb"]:
+    for k in config[param]:
+        config[param][k] = int(config[param][k])
+
+# print(SAMPLES)
+
+OUT = config["output_dir"]
+
+localrules:
+    all,
+
+
+include: "workflow/rules/rule.smk"
+
+
+rule all:
+    input:
+        expand(OUT + "/{sample}_combined.fastq", sample=SAMPLES),

config/pipeline_parameters.yaml

@@ -0,0 +1,5 @@
+threads:
+    template_rule: 1
+
+mem_gb:
+    template_rule: 1

envs/mamba.yaml

@@ -0,0 +1,5 @@
+name: mamba
+channels:
+  - conda-forge
+dependencies:
+  - mamba

envs/template_master.yaml

@@ -0,0 +1,15 @@
+name: juno_template
+channels:
+  - conda-forge
+  - bioconda
+  - biocore
+  - nodefaults
+dependencies:
+  - git=2.40.*
+  - mamba=1.3.*
+  - pandas=1.5.*
+  - snakemake=7.18.*
+  - pip=23.*
+  - python=3.11.*
+  - pip:
+    - "--editable=git+https://github.com/RIVM-bioinformatics/[email protected]#egg=juno_library"

run_pipeline.sh

@@ -0,0 +1,86 @@
+#!/bin/bash
+
+set -euo pipefail
+
+#----------------------------------------------#
+# User parameters
+if [ ! -z "${1}" ] || [ ! -z "${2}" ] #|| [ ! -z "${irods_input_projectID}" ]
+then
+   input_dir="${1}"
+   output_dir="${2}"
+#    PROJECT_NAME="${irods_input_projectID}"
+else
+    echo "One of the parameters is missing, make sure there is an input directory, output directory and project name(param 1, 2 or irods_input_projectID)."
+    exit 1
+fi
+
+if [ ! -d "${input_dir}" ] || [ ! -d "${output_dir}" ]
+then
+  echo "The input directory $input_dir, output directory $output_dir or fastq dir ${input_dir}/clean_fastq does not exist"
+  exit 1
+else
+  input_fastq="${input_dir}/clean_fastq"
+fi
+
+#----------------------------------------------#
+# Create/update necessary environments
+PATH_MAMBA_YAML="envs/mamba.yaml"
+PATH_MASTER_YAML="envs/template_master.yaml"
+MAMBA_NAME=$(head -n 1 ${PATH_MAMBA_YAML} | cut -f2 -d ' ')
+MASTER_NAME=$(head -n 1 ${PATH_MASTER_YAML} | cut -f2 -d ' ')
+
+echo -e "\nUpdating necessary environments to run the pipeline..."
+
+# Removing strict mode because it sometimes breaks the code for 
+# activating an environment and for testing whether some variables
+# are set or not
+set +euo pipefail 
+
+conda env update -f "${PATH_MAMBA_YAML}"
+source activate "${MAMBA_NAME}"
+
+mamba env update -f "${PATH_MASTER_YAML}"
+
+source activate "${MASTER_NAME}"
+
+#----------------------------------------------#
+# Run the pipeline
+
+echo -e "\nRun pipeline..."
+
+if [ ! -z ${irods_runsheet_sys__runsheet__lsf_queue} ]; then
+    QUEUE="${irods_runsheet_sys__runsheet__lsf_queue}"
+else
+    QUEUE="bio"
+fi
+
+set -euo pipefail
+
+python template.py --queue "${QUEUE}" -i "${input_dir}" -o "${output_dir}"
+
+result=$?
+
+# Propagate metadata
+
+set +euo pipefail
+
+SEQ_KEYS=
+SEQ_ENV=`env | grep irods_input_sequencing`
+for SEQ_AVU in ${SEQ_ENV}
+do
+    SEQ_KEYS="${SEQ_KEYS} ${SEQ_AVU%%=*}"
+done
+
+for key in $SEQ_KEYS irods_input_illumina__Flowcell irods_input_illumina__Instrument \
+    irods_input_illumina__Date irods_input_illumina__Run_number irods_input_illumina__Run_Id
+do
+    if [ ! -z ${!key} ] ; then
+        attrname=${key:12}
+        attrname=${attrname/__/::}
+        echo "${attrname}: '${!key}'" >> ${OUTPUTDIR}/metadata.yml
+    fi
+done
+
+set -euo pipefail
+
+exit ${result}