Mercurial > repos > rliterman > csp2

changeset 33:6f4e6377ba64

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload"
author rliterman
date Thu, 05 Dec 2024 12:32:42 -0500
parents a12953834916
children 499342837ad7
files CSP2/.github/workflows/build-docker.yml CSP2/.gitignore CSP2/conf/profiles.config csp2_screen.xml csp2_snp.xml
diffstat 5 files changed, 284 insertions(+), 5 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/CSP2/.github/workflows/build-docker.yml	Thu Dec 05 12:32:42 2024 -0500
@@ -0,0 +1,34 @@
+name: docker-build
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  docker:
+    runs-on: ubuntu-latest
+    steps:
+      -
+        name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+      -
+        name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+      -
+        name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+      -
+        name: Build and push
+        uses: docker/build-push-action@v6
+        with:
+          file: docker/Dockerfile
+          platforms: linux/amd64
+          target: release
+          build-args: |
+            VERSION=${{ github.ref_name }}
+            CSP2_BRANCH=${{ github.ref_name }}
+          push: true
+          tags: cfsanbiostatistics/csp2:latest,cfsanbiostatistics/csp2:${{ github.ref_name }}
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/CSP2/.gitignore	Thu Dec 05 12:32:42 2024 -0500
@@ -0,0 +1,211 @@
+# Created by https://www.toptal.com/developers/gitignore/api/python,visualstudiocode,virtualenv
+# Edit at https://www.toptal.com/developers/gitignore?templates=python,visualstudiocode,virtualenv
+
+### Python ###
+# 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/
+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
+
+# 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
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# 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
+.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/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+### VirtualEnv ###
+# Virtualenv
+# http://iamzed.com/2009/05/07/a-primer-on-virtualenv/
+[Bb]in
+[Ii]nclude
+[Ll]ib
+[Ll]ib64
+[Ll]ocal
+[Ss]cripts
+pyvenv.cfg
+pip-selfcheck.json
+
+### VisualStudioCode ###
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
+
+# Local History for Visual Studio Code
+.history/
+
+# Built Visual Studio Code Extensions
+*.vsix
+
+### VisualStudioCode Patch ###
+# Ignore all local history of files
+.history
+.ionide
+
+# End of https://www.toptal.com/developers/gitignore/api/python,visualstudiocode,virtualenv
+
+#Nextflow
+.nextflow*
+work/
\ No newline at end of file
--- a/CSP2/conf/profiles.config	Thu Dec 05 10:47:01 2024 -0500
+++ b/CSP2/conf/profiles.config	Thu Dec 05 12:32:42 2024 -0500
@@ -79,13 +79,13 @@
         params.trim_name = ""
     }
     
-    csp2_galaxy {
+    csp2_galaxy1 {
         conda.enabled = true
         conda.useMicromamba = true
         conda.cacheDir = "${projectDir}/CSP2_env"
         process.conda = "${projectDir}/conf/CSP2.yaml"
         
-        process.queue = "q8cpu"
+        process.queue = "ondemand-small"
 
         executor.$slurm.exitReadTimeout = 120000
 
@@ -99,4 +99,25 @@
         params.mash_module = ""
         params.trim_name = ""
     }
+    
+    csp2_galaxy2 {
+        conda.enabled = true
+        conda.useMicromamba = true
+        conda.cacheDir = "${projectDir}/CSP2_env"
+        process.conda = "${projectDir}/conf/CSP2.yaml"
+        
+        process.queue = "q8cpu"
+
+        executor.$slurm.exitReadTimeout = 120000
+
+        process.executor = 'slurm'
+        params.cores = 8
+        params.python_module = ""
+        params.mummer_module = ""
+        params.skesa_module = ""
+        params.bedtools_module = ""
+        params.bbtools_module = ""
+        params.mash_module = ""
+        params.trim_name = ""
+    }
 }
--- a/csp2_screen.xml	Thu Dec 05 10:47:01 2024 -0500
+++ b/csp2_screen.xml	Thu Dec 05 12:32:42 2024 -0500
@@ -57,7 +57,13 @@
         export REF_ID_ARG="";
 fi;
 
-nextflow run ${__tool_directory__}/CSP2/CSP2.nf -profile csp2_galaxy --cores 2 --runmode screen \$QUERY_FASTA_ARG \$REF_FASTA_ARG \$QUERY_READS_ARG \$REF_READS_ARG \$REF_ID_ARG \$TRIM_ARG --readext $readext --forward $forward --reverse $reverse --ref_readext $readext --ref_forward $forward --ref_reverse $reverse --min_cov $min_cov --min_iden $min_iden --min_len $min_len --ref_edge $ref_edge --query_edge $query_edge --dwin $dwin --wsnps $wsnps --out \$CSP2_DIR/CSP2_Screen_Output > Nextflow_Log.txt 2>&1;
+if [[ "$ondemand" == "true" ]]; then
+        export PROFILE_ARG="-profile csp2_galaxy1";
+else
+        export PROFILE_ARG="-profile csp2_galaxy2";
+fi;
+
+nextflow run ${__tool_directory__}/CSP2/CSP2.nf \$PROFILE_ARG --runmode screen \$QUERY_FASTA_ARG \$REF_FASTA_ARG \$QUERY_READS_ARG \$REF_READS_ARG \$REF_ID_ARG \$TRIM_ARG --readext $readext --forward $forward --reverse $reverse --ref_readext $readext --ref_forward $forward --ref_reverse $reverse --min_cov $min_cov --min_iden $min_iden --min_len $min_len --ref_edge $ref_edge --query_edge $query_edge --dwin $dwin --wsnps $wsnps --out \$CSP2_DIR/CSP2_Screen_Output > Nextflow_Log.txt 2>&1;
 zip -r CSP2_Output.zip CSP2_Screen_Output;
 ]]>
         </command>
@@ -78,6 +84,7 @@
                 <param name="reverse" type="text" value="_2.fastq.gz" label="Forward read suffix (e.g. _2.fastq.gz)" optional="true" />
                 <param name="trim_name" type="text" value="" label="Text to remove from all file names (e.g., _contigs_skesa)" optional="true" />
                 <param name="ref_id" type="text" value="" label="Comma-separated list of desired Reference IDs (e.g., Sample_A,Sample_B)" optional="true" />
+                <param name="ondemand" type="boolean" value="true" label="Use -profile csp2_galaxy1 (ondemand-small queue; set to false to use csp2_galaxy2 q8cpu)" optional="true" />
         </inputs>
         <outputs>
                 <data name="raw_mummer" format="tabular" label="Raw MUMmer Output" from_work_dir="CSP2_Screen_Output/Raw_MUMmer_Summary.tsv" />
--- a/csp2_snp.xml	Thu Dec 05 10:47:01 2024 -0500
+++ b/csp2_snp.xml	Thu Dec 05 12:32:42 2024 -0500
@@ -63,7 +63,13 @@
         export RESCUE_ARG="";
 fi;
 
-nextflow run ${__tool_directory__}/CSP2/CSP2.nf -profile csp2_galaxy --cores 2 --runmode snp \$QUERY_FASTA_ARG \$REF_FASTA_ARG \$QUERY_READS_ARG \$REF_READS_ARG \$REF_ID_ARG \$TRIM_ARG \$RESCUE_ARG --readext $readext --forward $forward --reverse $reverse --ref_readext $readext --ref_forward $forward --ref_reverse $reverse --min_cov $min_cov --min_iden $min_iden --min_len $min_len --ref_edge $ref_edge --query_edge $query_edge --dwin $dwin --wsnps $wsnps --max_missing $max_missing --n_ref $n_ref --out \$CSP2_DIR/CSP2_SNP_Output > Nextflow_Log.txt 2>&1;
+if [[ "$ondemand" == "true" ]]; then
+        export PROFILE_ARG="-profile csp2_galaxy1";
+else
+        export PROFILE_ARG="-profile csp2_galaxy2";
+fi;
+
+nextflow run ${__tool_directory__}/CSP2/CSP2.nf \$PROFILE_ARG --runmode snp \$QUERY_FASTA_ARG \$REF_FASTA_ARG \$QUERY_READS_ARG \$REF_READS_ARG \$REF_ID_ARG \$TRIM_ARG \$RESCUE_ARG --readext $readext --forward $forward --reverse $reverse --ref_readext $readext --ref_forward $forward --ref_reverse $reverse --min_cov $min_cov --min_iden $min_iden --min_len $min_len --ref_edge $ref_edge --query_edge $query_edge --dwin $dwin --wsnps $wsnps --max_missing $max_missing --n_ref $n_ref --out \$CSP2_DIR/CSP2_SNP_Output > Nextflow_Log.txt 2>&1;
 zip -r CSP2_Output.zip CSP2_SNP_Output;
         ]]>
         </command>
@@ -87,7 +93,7 @@
                 <param name="rescue" type="boolean" value="false" label="Enable SNP edge rescue mode" optional="true" />
                 <param name="max_missing" type="float" value="50" label="Maximum percent of isolates allowed to have missing data to retain a SNP" optional="true" />
                 <param name="n_ref" type="integer" value="1" label="Number of reference isolates for CSP2 to select" optional="true" />
-
+                <param name="ondemand" type="boolean" value="true" label="Use -profile csp2_galaxy1 (ondemand-small queue; set to false to use csp2_galaxy2 q8cpu)" optional="true" />
         </inputs>
         <outputs>
                 <data name="raw_mummer" format="tabular" label="Raw MUMmer Output" from_work_dir="CSP2_SNP_Output/Raw_MUMmer_Summary.tsv" />