changeset 36:f6cd698b6f62

"planemo upload"
author rliterman
date Thu, 05 Dec 2024 18:09:26 -0500
parents 106d28c851fa
children f62b9bcf7cf3
files CSP2/.github/workflows/build-docker.yml CSP2/.gitignore CSP2/conf/profiles.config CSP2/docker/Dockerfile CSP2/docker/Makefile csp2_screen.xml csp2_snp.xml
diffstat 7 files changed, 3 insertions(+), 658 deletions(-) [+]
line wrap: on
line diff
--- a/CSP2/.github/workflows/build-docker.yml	Thu Dec 05 16:30:58 2024 -0500
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,34 +0,0 @@
-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 }}
--- a/CSP2/.gitignore	Thu Dec 05 16:30:58 2024 -0500
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,211 +0,0 @@
-# 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 16:30:58 2024 -0500
+++ b/CSP2/conf/profiles.config	Thu Dec 05 18:09:26 2024 -0500
@@ -79,7 +79,7 @@
         params.trim_name = ""
     }
     
-    csp2_galaxy1 {
+    csp2_galaxy {
         conda.enabled = true
         conda.useMicromamba = true
         conda.cacheDir = "${projectDir}/CSP2_env"
@@ -99,25 +99,4 @@
         params.mash_module = ""
         params.trim_name = ""
     }
-    
-    csp2_galaxy2 {
-        conda.enabled = true
-        conda.useMicromamba = true
-        conda.cacheDir = "${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/docker/Dockerfile	Thu Dec 05 16:30:58 2024 -0500
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,246 +0,0 @@
-# CSP2 Dockerfile
-# Based on StaPH-B's Dockerfile for BEDTools, MUmmer, and Skesa
-# Thanks to Erin Young, Curtis Kapsak, John Arnn, and the StaPH-B team
-# https://github.com/StaPH-B/docker-builds/blob/master/bedtools/2.31.1/Dockerfile
-# https://github.com/StaPH-B/docker-builds/blob/master/mummer/4.0.0/Dockerfile
-# https://github.com/StaPH-B/docker-builds/blob/master/skesa/2.4.0/Dockerfile
-
-ARG CSP2_VER="0.9.0"
-ARG BEDTOOLS_VER="2.31.1"
-ARG MUMMER_VER="4.0.0"
-ARG SKESA_VER="2.4.0"
-ARG MASH_VER="2.3"
-ARG BBMAP_VER="38.90"
-ARG PYTHON_VER="3.8"
-
-FROM ubuntu:focal AS build
-
-ARG BEDTOOLS_VER
-ARG MUMMER_VER
-ARG SKESA_VER
-ARG MASH_VER
-ARG BBMAP_VER
-ARG PYTHON_VER
-
-WORKDIR /build
-
-# to prevent tzdata from asking for a region during apt updates; ARG so that variable only 
-# persists at buildtime
-# from https://github.com/StaPH-B/docker-builds/blob/master/mummer/4.0.0/Dockerfile
-ARG DEBIAN_FRONTEND=noninteractive
-
-# Install build dependencies
-RUN apt-get update && apt-get install -y --no-install-recommends \
-    tzdata \
-    gpg-agent \
-    software-properties-common \
-    build-essential \
-    zlib1g-dev \
-    libghc-bzlib-dev \
-    liblzma-dev \
-    wget \
-    ca-certificates 
-
-RUN add-apt-repository 'ppa:deadsnakes/ppa' && apt-get update && apt-get install -y --no-install-recommends \
-    python${PYTHON_VER} \
-#    python${PYTHON_VER}-pip \
-#    python${PYTHON_VER}-full \
-    python${PYTHON_VER}-dev \
-    python${PYTHON_VER}-venv && \
-    python${PYTHON_VER} -m venv --copies /opt/venv
-
-
-ENV PATH="/opt/venv/bin:$PATH"
-
-RUN pip install --no-cache-dir -U pandas~=1.2.0 pybedtools refchooser scikit-learn
-
-ADD https://github.com/arq5x/bedtools2/archive/refs/tags/v${BEDTOOLS_VER}.tar.gz .
-ADD https://github.com/mummer4/mummer/releases/download/v${MUMMER_VER}rc1/mummer-${MUMMER_VER}rc1.tar.gz .
-ADD https://github.com/ncbi/SKESA/releases/download/${SKESA_VER}/skesa.centos.7.7 .
-ADD https://github.com/ncbi/SKESA/releases/download/${SKESA_VER}/gfa_connector.centos7.7 .
-ADD https://github.com/ncbi/SKESA/releases/download/${SKESA_VER}/kmercounter.centos7.7 .
-ADD https://github.com/marbl/Mash/releases/download/v${MASH_VER}/mash-Linux64-v${MASH_VER}.tar .
-
-# Install BEDTools
-# per https://github.com/StaPH-B/docker-builds/blob/master/bedtools/2.31.1/Dockerfile
-# python3 required when compiling via `make` command for creating old CLI executables
-# dependencies listed here (albeit for v2.30.0, still should be identical): https://packages.ubuntu.com/jammy/bedtools
-# requires libghc-bzlib-dev, build-essential, zlib1g-dev, and a few others
-# 'make install' should place binary executable files in /usr/local/bin
-RUN tar -xzf v${BEDTOOLS_VER}.tar.gz && \
-    rm v${BEDTOOLS_VER}.tar.gz && \
-   cd bedtools2-${BEDTOOLS_VER} && \
-   make && \
-   make install 
-
- # Install mummer
- # per https://github.com/StaPH-B/docker-builds/blob/master/mummer/4.0.0/Dockerfile
-RUN tar -xvf mummer-${MUMMER_VER}rc1.tar.gz && \
-    rm mummer-${MUMMER_VER}rc1.tar.gz && \
-    cd mummer-${MUMMER_VER}rc1 && \
-    ./configure --prefix=/usr/local && \
-    make && \
-    make install && \
-    ldconfig
-
-# # Install Skesa
-# # per https://github.com/StaPH-B/docker-builds/blob/master/skesa/2.4.0/Dockerfile
-# # get skesa, gfa_connector, and kmercounter binaries, rename them
-RUN mkdir skesa && \
-    cd skesa && \
-    mv /build/skesa.centos.7.7 skesa && \
-    mv /build/gfa_connector.centos7.7 gfa_connector && \
-    mv /build/kmercounter.centos7.7 kmercounter && \
-    chmod +x skesa gfa_connector kmercounter && \
-    mv skesa gfa_connector kmercounter /usr/local/bin
-
-# Install Mash
-RUN tar -xvf mash-Linux64-v${MASH_VER}.tar && \
-    mv mash-Linux64-v${MASH_VER}/mash /usr/local/bin
-
-# Install BBMap
-RUN wget -O BBMap_${BBMAP_VER}.tar.gz https://sourceforge.net/projects/bbmap/files/BBMap_${BBMAP_VER}.tar.gz/download && \
-    tar -xvf BBMap_${BBMAP_VER}.tar.gz && \
-    mv bbmap/* /usr/local/bin
-
-
-FROM ubuntu:focal AS app
-
-ARG CSP2_VER
-ARG CSP2_BRANCH="main"
-ARG PYTHON_VER
-
-LABEL base.image="ubuntu:focal"
-LABEL version=${CSP2_VER}
-LABEL software="CSP2"
-LABEL software.version=${CSP2_VER}
-LABEL description="a Nextflow pipeline for rapid, accurate SNP distance estimation from assembly data"
-LABEL website="https://github.com/CFSAN-Biostatistics/CSP2"
-LABEL licence="https://github.com/CFSAN-Biostatistics/CSP2/blob/main/LICENSE"
-LABEL maintainer="Robert Literman"
-LABEL maintainer.email="Robert.Literman@fda.hhs.gov"
-LABEL maintainer.organization="FDA/CFSAN/Biostatistics"
-LABEL maintainer2="Justin Payne"
-LABEL maintainer2.email="Justin.Payne@fda.hhs.gov"
-LABEL maintainer2.organization="FDA/CFSAN/Biostatistics"
-
-WORKDIR /root/.nextflow
-WORKDIR /app
-
-# copy in all executable files from builder stage to final app stage
-COPY --from=build /usr/local/bin /usr/local/bin
-
-# Lots of perl nonsense
-COPY --from=build /usr/local/lib /usr/local/lib
-COPY --from=build /usr/local/libexec/mummer /usr/local/libexec/mummer
-COPY --from=build /usr/lib/x86_64-linux-gnu/perl /usr/lib/x86_64-linux-gnu/perl
-COPY --from=build /usr/local/share /usr/local/share
-COPY --from=build /usr/share /usr/share
-COPY --from=build /opt/venv /opt/venv
-COPY --from=build /usr/bin/make /usr/local/bin/make
-
-
-# Python stuff
-COPY --from=build /usr/lib/python${PYTHON_VER} /usr/lib/python${PYTHON_VER}
-
-
-#Install JRE
-RUN apt-get update && apt-get install -y --no-install-recommends \
-    ca-certificates \
-    openjdk-17-jre-headless \
-    curl
-
-# Install Nextflow
-# per https://www.nextflow.io/docs/latest/getstarted.html
-RUN export CAPSULE_LOG=debug && curl -s https://get.nextflow.io | bash && \
-    chmod +x nextflow && \
-    mv nextflow /usr/local/bin && \
-    nextflow run hello
-
-ADD docker/Makefile .
-
-# set PATH, set perl locale settings for singularity compatibility
-ENV PATH="/opt/venv/bin:/usr/local/bin:/skesa:$PATH" \
-    LC_ALL=C \
-    NXF_OFFLINE='true'
-
-ADD bin ./bin
-ADD conf ./conf
-ADD subworkflows ./subworkflows
-ADD CSP2.nf ./CSP2.nf
-ADD nextflow.config ./nextflow.config
-
-
-FROM app AS pretest
-
-# set PATH, set perl locale settings for singularity compatibility
-ENV PATH="/opt/venv/bin:/usr/local/bin:/skesa:$PATH" \
-    LC_ALL=C \
-    NXF_OFFLINE='true'
-
-#Alternate test data directory
-ADD https://github.com/CFSAN-Biostatistics/CSP2_TestData#main:assets assets/
-
-
-# Test MUmmer installation
-# per https://github.com/StaPH-B/docker-builds/blob/master/mummer/4.0.0/Dockerfile
-
-ADD https://mummer4.github.io/tutorial/exampleFiles/2.1/in/H_pylori26695_Eslice.fasta .
-ADD https://mummer4.github.io/tutorial/exampleFiles/2.1/in/H_pyloriJ99_Eslice.fasta .
-ADD https://mummer4.github.io/tutorial/exampleFiles/2.2/in/B_anthracis_Mslice.fasta .
-ADD https://mummer4.github.io/tutorial/exampleFiles/2.2/in/B_anthracis_contigs.fasta .
-ADD http://mummer.sourceforge.net/examples/data/H_pylori26695_Eslice.fasta .
-ADD http://mummer.sourceforge.net/examples/data/H_pyloriJ99_Eslice.fasta .
-ADD https://raw.githubusercontent.com/artic-network/artic-ncov2019/master/primer_schemes/nCoV-2019/V5.3.2/SARS-CoV-2.primer.bed ./V5.3.2.artic.bed
-ADD https://raw.githubusercontent.com/artic-network/artic-ncov2019/master/primer_schemes/nCoV-2019/V4.1/SARS-CoV-2.primer.bed ./V4.1.artic.bed
-
-FROM pretest AS test
-
-# Test MASH
-
-RUN nucmer -h && \
-  promer -h && \
-  mummer -mum -b -c H_pylori26695_Eslice.fasta H_pyloriJ99_Eslice.fasta > mummer.mums && \
-  nucmer  -c 100 -p nucmer B_anthracis_Mslice.fasta B_anthracis_contigs.fasta && \
-  show-snps -C nucmer.delta > nucmer.snps && \
-  promer -p promer_100 -c 100  H_pylori26695_Eslice.fasta H_pyloriJ99_Eslice.fasta
-
-# Test bedtools installation
-# check help options and version
-RUN bedtools --help && \
-    bedtools --version
-
-# downloads two bedfiles for ARTIC SARS-CoV-2 artic schemes, fixes their formatting, uses bedtools sort, intersect, and merge
-# per https://github.com/StaPH-B/docker-builds/blob/master/bedtools/2.31.1/Dockerfile
-RUN awk '{print $1 "\t" $2 "\t" $3 "\t" $4 "\t" $5 "\t" $6}' V5.3.2.artic.bed > V5.3.2.unsorted.bed && \
-    bedtools sort -i V5.3.2.unsorted.bed > V5.3.2.bed && \
-    awk '{print $1 "\t" $2 "\t" $3 "\t" $4 "\t" $5 "\t" $6}' V4.1.artic.bed   > V4.1.bed   && \
-    bedtools intersect -a V5.3.2.bed -b V4.1.bed > intersect_test.bed && \
-    mergeBed -i V5.3.2.bed > merged_test.bed && \
-    head intersect_test.bed merged_test.bed
-
-RUN /bin/bash -c 'make test'
-
-FROM app AS release
-
-ARG CSP2_VER
-ARG BEDTOOLS_VER
-ARG MUMMER_VER
-ARG SKESA_VER
-ARG MASH_VER
-ARG BBMAP_VER
-ARG PYTHON_VER
-ENV CSP2_VER=${CSP2_VER}
-ENV BEDTOOLS_VER=${BEDTOOLS_VER}
-ENV MUMMER_VER=${MUMMER_VER}
-ENV SKESA_VER=${SKESA_VER}
-ENV MASH_VER=${MASH_VER}
-ENV BBMAP_VER=${BBMAP_VER}
-ENV PYTHON_VER=${PYTHON_VER}
-
-# set PATH, set perl locale settings for singularity compatibility
-ENV PATH="/opt/venv/bin:/usr/local/bin:/skesa:$PATH" \
-    LC_ALL=C \
-    NXF_OFFLINE='true'
-
-ENTRYPOINT ["make", "--makefile=/app/Makefile"]
\ No newline at end of file
--- a/CSP2/docker/Makefile	Thu Dec 05 16:30:58 2024 -0500
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,143 +0,0 @@
-.PHONY:
-
-.ONESHELL:
-
-
-
-usage: ## Show this menu
-	@grep -E '^[a-zA-Z_-]+:.*?##.*$$' $(MAKEFILE_LIST) | awk 'BEGIN {FS = ":.*?##"}; {printf "\033[36m%-30s\033[0m %s\n", $$1, $$2}'
-
-version: ## Show version and branch
-	@echo "CSP2 v$${CSP2_VER}/$${CSP2_BRANCH}"
-
-# ENV CSP2_VER=${CSP2_VER}
-# ENV BEDTOOLS_VER=${BEDTOOLS_VER}
-# ENV MIUMMER_VER=${MUMMER_VER}
-# ENV SKESA_VER=${SKESA_VER}
-# ENV MASH_VER=${MASH_VER}
-# ENV BBMAP_VER=${BBMAP_VER}
-# ENV PYTHON_VER=${PYTHON_VER}
-
-versions: version ## Show versions of key installed depedencies
-	@echo `nextflow -v`
-	@echo `python3 --version` " (container says ${PYTHON_VER})"
-	@echo `bedtools --version` " (container says ${BEDTOOLS_VER})"
-	@echo "mummer " `mummer --version` " (container says ${MUMMER_VER})"
-	@echo `skesa --version 2>&1` " (container says ${SKESA_VER})"
-	@echo "mash " `mash --version` " (container says ${MASH_VER})"
-	@echo `bbmap.sh --version 2>&1` " (container says ${BBMAP_VER})"
-
-help: ## Show help
-	@echo "Citation: CFSAN SNP Pipeline 2, v$${CSP2_VER}, Literman et al. 2024"
-	@echo
-	@echo "CSP2 is a Nextflow pipeline for rapid, accurate SNP distance estimation"
-	@echo "from assembly data."
-	@echo 
-	@echo "Please see: https://github.com/CFSAN-Biostatistics/CSP2"
-	@echo
-	@echo "CSP2 runs are managed via Nextflow, providing the user with an array of"
-	@echo "customizations while also facilitating module development and additions in"
-	@echo "future releases."
-	@echo
-	@echo "Important Note: The software continues to be focused on the analysis of"
-	@echo "groups of bacterial genomes with limited evolutionary differences (<1000"
-	@echo "SNPs). Testing is underway to determine how the underlying cluster"
-	@echo "diversity impacts distances estimates."
-	@echo 
-	@echo "CSP2 has two main run modes:"
-	@echo "1) "Screening Mode" (screen): Used to determine whether query isolates are"
-	@echo "close to a set of reference isolates (e.g., lab control strains, strains"
-	@echo "related to an outbreak, etc.) Given one or more user-provided reference"
-	@echo "isolates (--ref_reads; --ref_fasta), get alignment statistics and SNP"
-	@echo "distances between all reference and query isolates (--reads; --fasta)"
-	@echo 
-	@echo "2) "SNP Pipeline Mode" (snp): Used to generate pairwise distances and"
-	@echo "alignments for a set of query isolates Generate pairwise SNP distances and"
-	@echo "alignments for 2+ isolates (--reads; --fasta) based on comparisons to:"
-	@echo 
-	@echo "One or more user-provided references (--ref_reads; --ref_fasta), or One or"
-	@echo "more reference isolates selected by RefChooser (--n_ref)"
-	@echo 
-	@echo "Usage: screen [options] {--fasta PATH {--reads=PATH | --forward=STR --reverse=STR} --out=PATH}"
-	@echo "  or   snp [options] {--fasta {--reads=PATH | --forward=STR --reverse=STR} --out=PATH}"
-	@echo 
-	@echo "Options:"
-	@echo "  --outroot=PATH\tBase directory to create output folder  [default=$CWD] "
-	@echo "  --out=PATH\t\tName of the output folder to create (must not exist)"
-	@echo "\t\t\t  [default=CSP2_<current_datetime>]"
-	@echo "  --forward=STR\t\tFull file extension for forward/left reads of query"
-	@echo "\t\t\t  [default='_1.fastq.gz']"
-	@echo "  --reverse=STR\t\tFull file extension for reverse/right reads of reference"
-	@echo "\t\t\t  [default='_2.fastq.gz']"
-	@echo "  --ref_forward=STR\tFull file extension for forward/left reads of reference"
-	@echo "\t\t\t  [default='_1.fastq.gz']"
-	@echo "  --ref_reverse=STR\tFull file extension for reverse/right reads of reference"
-	@echo "\t\t\t  [default='_2.fastq.gz']"
-	@echo "  --readext=STR\t\tExtension for single-end reads for query [default='fastq.gz']"
-	@echo "  --ref_readext=STR\tExtension for single-end reads for reference"
-	@echo "\t\t\t  [default='fastq.gz']"
-	@echo "  --min_cov=NUM\t\tDo not analyze queries that cover less than <min_cov>% of the"
-	@echo "\t\t\treference assembly [default=85]"
-	@echo "  --min_iden=NUM\tOnly consider alignments where the percent identity is at least"
-	@echo "\t\t\t  <min_iden> [default=99]"
-	@echo "  --min_len=NUM\t\tOnly consider alignments that span at least <min_len> in bp"
-	@echo "\t\t\t  [default=500]"
-	@echo "  --dwin=LIST\t\tA comma-separated list of windows to check SNP densities"
-	@echo "\t\t\t  [default=1000,125,15]"
-	@echo "  --wsnps=LIST\t\tThe maximum number of SNPs allowed in the corresponding window from"
-	@echo "\t\t\t  --dwin  [default=3,2,1]"
-	@echo "  --query_edge=NUM\tOnly consider SNPs that occur within <query_edge>bp of the end"
-	@echo "\t\t\t  of a query contig [default=250]"
-	@echo "  --ref_edge=NUM\tOnly consider SNPs that occur within <query_edge>bp of the end"
-	@echo "\t\t\t  of a reference contig [default=250]"
-	@echo "  --n_ref=NUM\t\tThe number of RefChooser reference isolates to consider (only"
-	@echo "\t\t\t  applied if using RefChooser) [default=3]"
-	@echo "  --reads=PATH\t\tLocation of query read data (Path to directory, or path to file with"
-	@echo "\t\t\t  multiple directories)"
-	@echo "  --fasta=PATH\t\tLocation of query assembly data (Path to directory containing"
-	@echo "\t\t\t  FASTAs, path to FASTA, path to multiple FASTAs)"
-	@echo "  --ref_reads=PATH\tLocation of reference read data (Path to directory, or path to"
-	@echo "\t\t\t  file with multiple directories)"
-	@echo "  --ref_fasta=PATH\tLocation of reference assembly data (Path to directory"
-	@echo "\t\t\t  containing FASTAs, path to FASTA, path to multiple FASTAs)"
-	@echo "  --trim_name=STR\tA string in assembly file names that you want to remove from"
-	@echo "\t\t\t  sample IDs (e.g., _contigs_skesa)"
-
-config:
-	@cat <<- EOF
-	profiles {
-		standard {
-			process.executor = 'local'
-			params.cores = `nproc --all`
-		}
-	}
-	EOF > ~/.nextflow/config
-
-
-ifeq (screen, $(firstword $(MAKECMDGOALS)))
-	runargs := $(wordlist 2, $(words $(MAKECMDGOALS)), $(MAKECMDGOALS))
-	$(eval $(runargs):;@true)
-endif
-
-ifeq (snp, $(firstword $(MAKECMDGOALS)))
-	runargs := $(wordlist 2, $(words $(MAKECMDGOALS)), $(MAKECMDGOALS))
-	$(eval $(runargs):;@true)
-endif
-
-screen: config ## determine whether query isolates are close to a reference
-	nextflow run CSP2.nf -profile standard --runmode screen $(runargs)
-
-snp: config ## generate pairwise distances for a set of query isolates
-	nextflow run CSP2.nf -profile standard --runmode snp $(runargs)
-
-snpdiffs: config
-
-test_screen:
-	nextflow run CSP2.nf -profile standard --runmode screen --fasta assets/Screen/Assembly/Week_42_Assembly.fasta --reads assets/Screen/Reads/ --ref_fasta assets/Screen/Assembly/Lab_Control.fasta --out ./CSP2_Test_Screen --readext fq.gz --forward _1.fq.gz --reverse _2.fq.gz
-
-test_snp:
-	nextflow run CSP2.nf -profile standard --runmode snp --fasta assets/SNP/ --n_ref 3 --out ./CSP2_Test_SNP --max_missing 50
-
-test: config test_screen test_snp
-	ls -lah assets/Screen/Output/Contamination_Screen/
-	diff -bur ./CSP2_Test_SNP/snpdiffs assets/SNP/Output/Soil_Analysis/snpdiffs
\ No newline at end of file
--- a/csp2_screen.xml	Thu Dec 05 16:30:58 2024 -0500
+++ b/csp2_screen.xml	Thu Dec 05 18:09:26 2024 -0500
@@ -57,7 +57,7 @@
         export REF_ID_ARG="";
 fi;
 
-nextflow run ${__tool_directory__}/CSP2/CSP2.nf -profile csp2_galaxy1 --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;
+nextflow run ${__tool_directory__}/CSP2/CSP2.nf -profile csp2_galaxy --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>
--- a/csp2_snp.xml	Thu Dec 05 16:30:58 2024 -0500
+++ b/csp2_snp.xml	Thu Dec 05 18:09:26 2024 -0500
@@ -57,7 +57,7 @@
         export RESCUE_ARG="";
 fi;
 
-nextflow run ${__tool_directory__}/CSP2/CSP2.nf -profile csp2_galaxy1 --runmode snp \$QUERY_FASTA_ARG \$REF_FASTA_ARG \$QUERY_READS_ARG \$REF_READS_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 --out \$CSP2_DIR/CSP2_SNP_Output > Nextflow_Log.txt 2>&1;
+nextflow run ${__tool_directory__}/CSP2/CSP2.nf -profile csp2_galaxy --runmode snp \$QUERY_FASTA_ARG \$REF_FASTA_ARG \$QUERY_READS_ARG \$REF_READS_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 --out \$CSP2_DIR/CSP2_SNP_Output > Nextflow_Log.txt 2>&1;
 
 mkdir -p Output; for file in CSP2_SNP_Output/SNP_Analysis/*/*; do ln -sf "\$file" Output/; done;
 zip -r CSP2_Output.zip CSP2_SNP_Output;