.gitignore

@@ -103,9 +103,18 @@ ENV/
 
 # nextflow analysis folders/files
 pipeline_trace*.txt*
+dag.dot*
 .nextflow*.log*
 report*.html*
 timeline*.html*
-/workflow/output/*
-/work/*
-/.nextflow/*
+test_data/*.fastq.gz
+workflow/dag*.dot*
+workflow/trace*.txt*
+workflow/.nextflow/
+workflow/.nextflow*.log*
+workflow/report*.html*
+workflow/timeline*.html*
+workflow/output/*
+workflow/work/*
+workflow/images/
+workflow/cleanup.sh

astrocyte_pkg.yml

@@ -9,15 +9,30 @@
 # A unique identifier for the workflow package, text/underscores only
 name: 'chipseq_analysis_bicf'
 # Who wrote this?
-author: 'Holly Ruess, Spencer D. Barnes, Jeremy A. Mathews, Beibei Chen and Venkat Malladi'
+author: 'Holly Ruess, Spencer D. Barnes, Jeremy A. Mathews, Beibei Chen and Venkat Malladi, Peng Lian, Felix Perez'
 # A contact email address for questions
 email: 'bicf@utsouthwestern.edu'
 # A more informative title for the workflow package
 title: 'BICF ChIP-seq Analysis Workflow'
 # A summary of the workflow package in plain text
 description: |
-  This is a workflow package for the BioHPC/BICF ChIP-seq workflow system.
-  It implements ChIP-seq analysis workflow and visualization application.
+  This is a fully-containerized version of the workflow package for the
+  BioHPC/BICF ChIP-seq workflow system. It implements the ChIP-seq analysis
+  workflow and visualization application.
+
+# The minimum Astrocyte version that requires to run this workflow. For old pipelines, which do not have this label
+# a default value of 0.3.1 will be assigned automatically. A request of minimum version less than 0.4.0 will be ignored.
+minimum_astrocyte_version: '2.0.1'
+# The Nextflow version that requires to run this workflow.  For old pipelines, which do not have this label
+# a default value of 0.31.0 will be assigned automatically. Please make sure the requested nextflow version is available
+# in the module list.
+# nextflow_version: '20.01.0'
+# (Optional) The Nextflow config file to use for this workflow. If provided, the file should exist in workflow/configs
+nextflow_config: 'biohpc.config'
+# The container to use for this workflow, none/singularity. If omitted, the default value 'none' will be used.
+container: 'singularity'
+# The version of singularity to use. This is required if container == 'singularity'
+singularity_version: '3.9.9'
 
 # -----------------------------------------------------------------------------
 # DOCUMENTATION
@@ -39,21 +54,19 @@ documentation_files:
 # A list of cluster environment modules that this workflow requires to run.
 # Specify versioned module names to ensure reproducability.
 workflow_modules:
-  - 'python/3.6.1-2-anaconda'
-  - 'trimgalore/0.4.1'
-  - 'bwa/intel/0.7.12'
-  - 'samtools/1.6'
-  - 'sambamba/0.6.6'
-  - 'bedtools/2.26.0'
-  - 'deeptools/2.5.0.1'
-  - 'phantompeakqualtools/1.2'
-  - 'macs/2.1.0-20151222'
-  - 'UCSC_userApps/v317'
-  - 'R/3.3.2-gccmkl'
-  - 'meme/4.11.1-gcc-openmpi'
-  - 'pandoc/2.7'
-  - 'singularity/3.0.2'
-
+  - None
+
+# A list of container images requires to run this workflow.
+# Specify full path and version names to ensure reproducibility.
+# This keyword is required when 'container' is specified in Astrocyte 0.4.1 and above.
+# Singularity supports different registries, please specify the protocol to use.
+# Such as, "docker://", "shub://", "library://", etc. We encourage you to use the GitLab
+# container registry of BioHPC to save and manage your container images.
+workflow_containers:
+  - docker://git.biohpc.swmed.edu:5050/s219741/chipseq-analysis-containerized/r:3.3.2
+  - docker://git.biohpc.swmed.edu:5050/s219741/chipseq-analysis-containerized/python:3.6.1
+  - docker://git.biohpc.swmed.edu:5050/s219741/chipseq-analysis-containerized/chipseq:1.0.0
+  - docker://git.biohpc.swmed.edu:5050/s219741/chipseq-analysis-containerized/motif-search:meme-4.11.1
 
 # A list of parameters used by the workflow, defining how to present them,
 # options etc in the web interface. For each parameter:

building/docker/chipseq/Dockerfile

+FROM continuumio/miniconda3:24.3.0-0
+
+LABEL IMAGE="chipseq" \
+    IMAGE_VERSION="1.0.0" \
+    AUTHORS="Felix Perez,Peng Lian" \
+    EMAIL="biohpc-help@utsouthwestern.edu"
+
+WORKDIR /chipseq/
+
+# Environment variables for the campus proxy.
+ENV http_proxy="http://proxy.swmed.edu:3128" \
+    https_proxy="http://proxy.swmed.edu:3128"
+
+    # Enable the use of bash-specific conda commands in the layer.
+RUN eval "$(conda shell.bash hook)" && \
+    # Create a Python 3.6.1 conda environment and initialize its use.
+    conda create -y -c bioconda -c defaults -c conda-forge -n py361 python=3.6.1 && \
+    echo "python ==3.6.1" >> /opt/conda/envs/py361/conda-meta/pinned && \
+    conda update conda -y && \
+    conda activate py361 && \
+    # Install the versions of numpy and pandas required for further software installs.
+    pip install numpy==1.12.1 && \
+    pip install pandas==0.20.1 && \
+    # Install BWA 0.7.12
+    conda install -y --solver=libmamba -c bioconda bwa=0.7.12 && \
+    # Install depedencies for the following installations.
+    apt-get update && apt-get install -y gcc make zlib1g-dev libbz2-dev liblzma-dev libcurl4-openssl-dev && \
+    # Install Sambamba 0.6.6
+    conda install -y -c bioconda sambamba=0.6.6 && \
+    sambamba --version && \
+    # Install BEDTools 2.26.0
+    conda install -y -c bioconda bedtools=2.26.0 && \
+    bedtools --version && \
+    # Install Pandoc 2.7
+    conda install -y -c conda-forge pandoc=2.7 && \
+    pandoc --version && \
+    # Install deepTools 2.5.0.1
+    pip install deepTools==2.5.0.1 && \
+    deeptools --version && \
+    pip cache purge && \
+    conda deactivate && \
+    conda clean -y --all && \
+    apt-get remove -y gcc make zlib1g-dev libbz2-dev liblzma-dev libcurl4-openssl-dev && \
+    apt-get clean
+
+RUN eval "$(conda shell.bash hook)" && \
+    # Install MultiQC v.1.9 & SAMtools 1.6 in a separate conda environment - unsatisfiable in py361.
+    conda create -y --solver=libmamba -c defaults -c conda-forge -c bioconda -n extra python=3.7.6 multiqc=1.9 samtools=1.6 && \
+    ln -s /opt/conda/envs/extra/bin/multiqc /usr/bin/multiqc && \
+    ln -s /opt/conda/envs/extra/bin/samtools /usr/bin/samtools && \
+    samtools --version && \
+    multiqc --version && \
+    conda deactivate && \
+    conda clean -y --all
+
+    # Create a Python 2.7 environment.
+RUN eval "$(conda shell.bash hook)" && \
+    conda create -y -n py27 -c conda-forge python=2.7.12 pip=9.0.1 && \
+    conda activate py27  && \
+    apt-get update && apt-get install -y gcc make zlib1g-dev libbz2-dev liblzma-dev libcurl4-openssl-dev && \
+    # Install Trim Galore 0.4.1.
+    conda install -y --solver=libmamba -c bioconda trim-galore=0.4.1 && \
+    trim_galore --version && \
+    # Fix the version of cutadapt for trim galore.
+    conda install -y --solver=libmamba -c bioconda cutadapt=1.9.1 && \
+    cutadapt --version && \
+    # Install MACS2 2.1.0.20151222
+    pip install numpy && \
+    pip install MACS2==2.1.0.20151222 && \
+    macs2 --version && \
+    # Install phantompeakqualtools 1.2
+    conda install -y --solver=libmamba -c conda-forge gcc && \
+    conda install -y --solver=libmamba -c bioconda phantompeakqualtools=1.2 && \
+    # Install MEME 4.11.1
+    conda install -y --solver=libmamba -c bioconda meme=4.11.1 && \
+    meme -version && \
+    conda deactivate && \
+    conda clean -y --all && \
+    apt-get remove -y gcc make zlib1g-dev && \
+    apt-get remove -y libbz2-dev liblzma-dev libcurl4-openssl-dev && \
+    apt-get clean
+
+RUN eval "$(conda shell.bash hook)" && \
+    conda activate py27 && \
+    # Install R 3.4.1 & r-spp 1.14.
+    conda install -y --solver=libmamba -c conda-forge libiconv && \
+    conda install -y --solver=libmamba -c conda-forge r=3.4.1 && \
+    conda install -y --solver=libmamba -c bioconda r-spp=1.14 && \
+    conda deactivate && \
+    conda clean -y --all && \
+    # Setup the symlinks for the software in the py27 environment so that when 
+    # the Python 3.6.1 environment is active, users can still use commands
+    # that are dependent upon Python 2.7.
+    ln -s /opt/conda/envs/py27/bin/trim_galore /usr/bin/trim_galore && \
+    ln -s /opt/conda/envs/py27/bin/cutadapt /usr/bin/cutadapt && \
+    ln -s /opt/conda/envs/py27/bin/R /usr/bin/R && \
+    ln -s /opt/conda/envs/py27/bin/Rscript /usr/bin/Rscript && \
+    ln -s /opt/conda/envs/py27/bin/run_spp.R /usr/bin/run_spp.R && \
+    ln -s /opt/conda/envs/py27/bin/macs2 /usr/bin/macs2 && \
+    ln -s /opt/conda/envs/py27/bin/meme /usr/bin/meme && \
+    ln -s /opt/conda/envs/py27/bin/meme-chip /usr/bin/meme-chip
+
+# Install UCSC_userApps/v317
+RUN apt-get install -y gcc-9 g++-9 make libncurses-dev zlib1g-dev libbz2-dev liblzma-dev libcap-dev libssl-dev libpng-dev libmariadb-dev-compat libcurl4-openssl-dev && \
+    ln -fs /usr/bin/gcc-9 /usr/bin/gcc && \
+    wget http://hgdownload.cse.ucsc.edu/admin/exe/userApps.archive/userApps.v317.src.tgz && \
+    tar -xzf userApps.v317.src.tgz && \
+    rm userApps.v317.src.tgz && \
+    cd userApps && \
+    make clean && \
+    make && \
+    # In entrypoint.sh, an export command is used to add the userApps binaries to the PATH environment variable.
+    apt-get remove -y gcc-9 g++-9 make libncurses-dev zlib1g-dev libbz2-dev liblzma-dev libpcap-dev libssl-dev libpng-dev libmariadb-dev-compat libcurl4-openssl-dev && \
+    apt-get clean
+
+# Copy in the entrypoint script to use for activating the Python 3.6.1 conda environment by default when launching a container.
+COPY entrypoint.sh .
+
+RUN chmod +x entrypoint.sh
+
+ENTRYPOINT ["/chipseq/entrypoint.sh"]
\ No newline at end of file

building/docker/chipseq/entrypoint.sh

+#!/bin/bash --login
+# The --login ensures the bash configuration is loaded, enabling Conda.
+
+# Temporarily disable strict mode and activate conda:
+# set : Used to set or unset shell attributes (when options are specified, as shown here).
+# -e : Exit on non-zero return status.
+# -u : Treat unset variables and parameters other than special parameters "@" and "*" as an error when performaing parameter expansion.
+# -o : specify an option name. In our case here, we use the "pipefail" option.
+# pipefail : If set, the return value of a pipeline is the value of the last (rightmost) command to exit with a non-zeros status, or zero if all commands in the pipeline exit successfully.
+# Using + rather than - causes these options to be turned off.
+set +euo pipefail
+
+source /opt/conda/etc/profile.d/conda.sh
+
+conda activate py361
+
+# Add the userApps binaries to the PATH.
+export PATH=$PATH:/chipseq/userApps/bin/
+
+# Enable strict mode:
+set -euo pipefail
+
+# exec some commands:
+exec "$@"

building/docker/motif-search/meme-4.11.1/Dockerfile

+FROM continuumio/miniconda3:24.3.0-0
+
+LABEL IMAGE="chipseq-analysis-motifSearch" \
+    IMAGE_VERSION="1.0.0" \
+    AUTHORS="Felix Perez,Peng Lian" \
+    EMAIL="biohpc-help@utsouthwestern.edu"
+
+WORKDIR /motif-search/
+
+# Environment variables for the campus proxy.
+ENV http_proxy="http://proxy.swmed.edu:3128" \
+    https_proxy="http://proxy.swmed.edu:3128"
+
+
+# Original module load order:
+# module load python/3.6.1-2-anaconda
+# module load meme/4.11.1-gcc-openmpi
+# module load bedtools/2.26.0
+
+
+COPY entrypoint.sh .
+
+RUN eval "$(conda shell.bash hook)" && \
+    conda create -y -c bioconda -c conda-forge -c defaults -n motifSearch python=2.7.12 pip=9.0.1 && \
+    echo "python ==2.7.12" >> /opt/conda/envs/motifSearch/conda-meta/pinned && \
+    conda activate motifSearch && \
+    # Install pandas and numpy.
+    pip install numpy==1.12.1 && \
+    pip install pandas==0.20.1 && \
+    # Install MEME 4.11.1
+    conda install -y --solver=libmamba -c conda-forge -c bioconda meme=4.11.1 && \
+    meme -version && \
+    # Install BEDTools 2.26.0
+    conda install -y --solver=libmamba -c bioconda bedtools=2.26.0 && \
+    bedtools --version && \
+    # The stringi installation below solves a dependency issue encountered when DREME is used (meme-4.11.1)
+    conda install -y --solver=libmamba -c conda-forge r-stringi=1.2.4 && \
+    conda deactivate
+
+RUN eval "$(conda shell.bash hook)" && \
+    # Create a Python 3.6.1 conda environment and initialize its use.
+    conda create -y -c bioconda -c defaults -c conda-forge -n py361 python=3.6.1 && \
+    echo "python ==3.6.1" >> /opt/conda/envs/py361/conda-meta/pinned && \
+    conda update conda -y && \
+    conda activate py361 && \
+    # Install the versions of numpy and pandas required for further software installs.
+    pip install numpy==1.12.1 && \
+    pip install pandas==0.20.1 && \
+    conda deactivate && \
+    ln -s /opt/conda/envs/py361/bin/python3 /opt/conda/envs/motifSearch/bin/python3
+
+RUN chmod +x entrypoint.sh
+
+ENTRYPOINT ["/motif-search/entrypoint.sh"]

building/docker/motif-search/meme-4.11.1/entrypoint.sh

+#!/bin/bash --login
+# The --login ensures the bash configuration is loaded, enabling Conda.
+
+# Temporarily disable strict mode and activate conda:
+# set : Used to set or unset shell attributes (when options are specified, as shown here).
+# -e : Exit on non-zero return status.
+# -u : Treat unset variables and parameters other than special parameters "@" and "*" as an error when performaing parameter expansion.
+# -o : specify an option name. In our case here, we use the "pipefail" option.
+# pipefail : If set, the return value of a pipeline is the value of the last (rightmost) command to exit with a non-zeros status, or zero if all commands in the pipeline exit successfully.
+# Using + rather than - causes these options to be turned off.
+set +euo pipefail
+
+source /opt/conda/etc/profile.d/conda.sh
+
+conda activate motifSearch
+
+export PATH=/motif-search/meme/bin/:$PATH
+
+# Enable strict mode:
+set -euo pipefail
+
+# exec the final command:
+exec "$@"

building/docker/podman.py

+#!/usr/bin/python3
+
+import sys
+import json
+import subprocess
+import threading
+
+'''
+This script is a wrapper of the podman command on RHEL 7. It helps podman 1.6.4 to push a correct manifest file the
+remote registry.
+
+Author: Peng Lian
+Date: 10/24/2023
+'''
+
+
+PODMAN_BIN = subprocess.check_output(['which', 'podman']).decode().strip()
+
+def execute_command(command, *args):
+    '''
+    Execute command and print the real time output to stdout
+    '''
+
+    # Function to process and print output in real time
+    def process_output(pipe):
+        for line in pipe:
+            print(line.decode(), end="")
+
+    cmd = [command, *args]
+    with subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE) as process:
+        stdout_thread = threading.Thread(target=process_output, args=(process.stdout,))
+        stderr_thread = threading.Thread(target=process_output, args=(process.stderr,))
+
+        stdout_thread.start()
+        stderr_thread.start()
+
+        # Wait for the process to complete
+        process.wait()
+
+        # Ensure that both threads finish
+        stdout_thread.join()
+        stderr_thread.join()
+
+        return process.returncode
+
+
+def fix_manifest(registry, tag):
+    '''
+    '.gzip' is missing in the 'mediaType' of 'layers' in the manifest file generated by podman 1.6.4.
+    This function scans the 'mediaType' and add the '.gzip' suffix.
+    '''
+    print(f'Fixing manifest for {registry}:{tag} ...')
+
+    # get graph root
+    output = subprocess.check_output([PODMAN_BIN, 'info', '-f', 'json'])
+    info = json.loads(output.decode())
+    graphRoot = info['store']['GraphRoot']
+
+    # get image ID
+    output = subprocess.check_output([PODMAN_BIN, 'inspect', f'{registry}:{tag}'])
+    imageID = eval(output.decode().replace('true', 'True').replace('false', 'False'))[0]['Id']
+
+    # read manifest
+    imageManifestFile = f'{graphRoot}/overlay-images/{imageID}/manifest'
+    manifest = json.loads(open(imageManifestFile).readlines()[0])
+
+    # update the layers mediaType with .gzip
+    changed = False
+    for l in manifest['layers']:
+        if l['mediaType'].endswith('tar'):
+            l['mediaType'] = f"{l['mediaType']}.gzip"
+            changed = True
+
+    # write the fixed manifest to file
+    if changed:
+        with open(imageManifestFile, 'w') as f:
+            f.write(json.dumps(manifest).replace(' ', '') + '\n')
+        f.close()
+        print('Manifest updated.')
+
+    return json.dumps(manifest)
+
+
+if __name__ == "__main__":
+
+    # only engage when 'push' command is called
+    if len(sys.argv) >= 2 and sys.argv[1] == 'push':
+        print(f"Executing push: {' '.join(sys.argv[1:])}")
+
+        # get registry and tag from the last argv
+        last_argv = sys.argv[-1]
+        if last_argv.find(':') > 0:
+            Tag = last_argv.strip().split(':')[-1]
+            Registry = ':'.join(last_argv.strip().split(':')[:-1])
+
+            # fix manifest
+            fix_manifest(registry=Registry, tag=Tag)
+
+        execute_command(PODMAN_BIN, *sys.argv[1:])
+    else:
+        execute_command(PODMAN_BIN, *sys.argv[1:])

building/docker/python-3.6.1/Dockerfile

+FROM continuumio/miniconda3:24.3.0-0
+
+LABEL IMAGE="Python/3.6.1" \
+    IMAGE_VERSION="0.0.1" \
+    AUTHORS="Felix Perez,Peng Lian" \
+    EMAIL="biohpc-help@utsouthwestern.edu"
+
+WORKDIR /python361/
+
+# Environment variables for the campus proxy.
+ENV http_proxy="http://proxy.swmed.edu:3128" \
+    https_proxy="http://proxy.swmed.edu:3128"
+
+# Copy in files to use for activating our Python 3.6.1 conda environment by default when launching a container.
+COPY entrypoint.sh .
+
+RUN chmod +x entrypoint.sh && \
+    conda create -y -c bioconda -c defaults -c conda-forge -n py361 python=3.6.1 && \
+    echo "python ==3.6.1" >> /opt/conda/envs/py361/conda-meta/pinned && \
+    # Enable the use of bash-specific conda commands in the layer.
+    eval "$(conda shell.bash hook)" && \
+    conda update conda -y && \
+    conda activate py361 && \
+    # Install pandas and numpy.
+    pip install numpy==1.12.1 && \
+    pip install pandas==0.20.1 && \
+    conda clean -y --all && \
+    pip cache purge && \
+    conda deactivate
+
+ENV BASH_ENV="/python361/entrypoint.sh"
+
+ENTRYPOINT ["/python361/entrypoint.sh"]
+CMD ["/opt/conda/envs/py361/bin/python"]
+

building/docker/python-3.6.1/entrypoint.sh

+#!/bin/bash --login
+# The --login ensures the bash configuration is loaded, enabling Conda.
+
+# Temporarily disable strict mode and activate conda:
+# set : Used to set or unset shell attributes (when options are specified, as shown here).
+# -e : Exit on non-zero return status.
+# -u : Treat unset variables and parameters other than special parameters "@" and "*" as an error when performaing parameter expansion.
+# -o : specify an option name. In our case here, we use the "pipefail" option.
+# pipefail : If set, the return value of a pipeline is the value of the last (rightmost) command to exit with a non-zeros status, or zero if all commands in the pipeline exit successfully.
+# Using + rather than - causes these options to be turned off.
+set +euo pipefail
+
+source /opt/conda/etc/profile.d/conda.sh
+
+conda activate py361
+
+# Enable strict mode:
+set -euo pipefail
+
+# exec the final command:
+exec "$@"

building/docker/r-3.3.2/Dockerfile

+FROM continuumio/miniconda3:24.3.0-0
+
+LABEL IMAGE="R-3.3.2" \
+    IMAGE_VERSION="1.0.0" \
+    AUTHORS="Felix Perez,Peng Lian" \
+    EMAIL="biohpc-help@utsouthwestern.edu"
+
+WORKDIR /r-332/
+
+# Environment variables for the campus proxy.
+ENV http_proxy="http://proxy.swmed.edu:3128" \
+    https_proxy="http://proxy.swmed.edu:3128"
+
+RUN conda create -y -c bioconda -c defaults -c conda-forge -n r332 r-base=3.3.2 && \
+    echo "r-base ==3.3.2" >> /opt/conda/envs/r332/conda-meta/pinned && \
+    # Enable the use of bash-specific conda commands in the layer.
+    eval "$(conda shell.bash hook)" && \
+    conda update conda -y && \
+    conda activate r332 && \
+    # Install ChIPseeker, GenomicFeatures, and DiffBind from Bioconductor
+    conda install -y --solver=libmamba -c bioconda bioconductor-chipseeker=1.10.0 && \
+    conda install -y --solver=libmamba -c bioconda bioconductor-genomicfeatures=1.26.4 && \
+    conda install -y --solver=libmamba -c bioconda bioconductor-diffbind=2.2.12 && \
+    # The below install solves a dependency issue with libicui18n.so
+    conda install -y --solver=libmamba -c conda-forge r-stringi && \
+    R -e "as.data.frame(installed.packages()[,c(1,3:4)])" && \
+    conda clean -y --all && \
+    conda deactivate
+
+# Copy in the entrypoint.sh script used to activate the R 3.3.2 conda environment by default when launching a container.
+COPY entrypoint.sh .
+
+RUN chmod +x entrypoint.sh
+
+ENTRYPOINT ["/r-332/entrypoint.sh"]
+CMD ["/opt/conda/envs/r-332/bin/R"]
+

building/docker/r-3.3.2/Rprofile.site

+options(repos = c(CRAN = 'https://cloud.r-project.org'), download.file.method = 'libcurl')
+options(repos = c(CRAN = 'https://cran.rstudio.com/'), download.file.method = 'libcurl')
+options(Ncpus = 6)
+

building/docker/r-3.3.2/entrypoint.sh

+#!/bin/bash --login
+# The --login ensures the bash configuration is loaded, enabling Conda.
+
+# Temporarily disable strict mode and activate conda:
+# set : Used to set or unset shell attributes (when options are specified, as shown here).
+# -e : Exit on non-zero return status.
+# -u : Treat unset variables and parameters other than special parameters "@" and "*" as an error when performaing parameter expansion.
+# -o : specify an option name. In our case here, we use the "pipefail" option.
+# pipefail : If set, the return value of a pipeline is the value of the last (rightmost) command to exit with a non-zeros status, or zero if all commands in the pipeline exit successfully.
+# Using + rather than - causes these options to be turned off.
+set +euo pipefail
+
+source /opt/conda/etc/profile.d/conda.sh
+
+conda activate r332
+
+# Enable strict mode:
+set -euo pipefail
+
+# exec the final command:
+exec "$@"

workflow/conf/biohpc.config → workflow/configs/biohpc.config

+singularity {
+  enabled = true
+  runOptions = ''                             // Please do NOT use "--disable-cache" in this runOptions. 
+                                              // Starting from version 2.0.0, the astrocyte_cli will clean up the cache automatically.
+  // runOptions = '--bind /vagrant:/vagrant'  // Use this one for vagrant development env only
+  cacheDir = "$baseDir/images/singularity"    // Singularity images specified in `workflow_containers` of astrocyte_pkg.yml will be saved to 
+                                              // this folder automatically, before running the workflow. The images will be renamed as
+                                              // "NAME-TAG.img", e.g. ubuntu-latest.img, centos-centos8.img, r-4.1.1.img, etc.
+}
+
 process {
   executor = 'slurm'
   queue = 'super'
@@ -5,68 +15,75 @@ process {
   beforeScript= 'ulimit -Ss unlimited'
 
   // Process specific configuration
+  withName: trackStart {
+    executor = 'local'
+  }
+
   withName: checkDesignFile {
-    module = ['python/3.6.1-2-anaconda']
+    container = 'docker://git.biohpc.swmed.edu:5050/s219741/chipseq-analysis-containerized/python:3.6.1'
     executor = 'local'
   }
   withName: trimReads {
-    module = ['python/3.6.1-2-anaconda', 'trimgalore/0.4.1']
+    container = 'docker://git.biohpc.swmed.edu:5050/s219741/chipseq-analysis-containerized/chipseq:1.0.0'
     cpus = 32
   }
   withName: alignReads{
-    module = ['python/3.6.1-2-anaconda', 'bwa/intel/0.7.12', 'samtools/1.6']
+    container = 'docker://git.biohpc.swmed.edu:5050/s219741/chipseq-analysis-containerized/chipseq:1.0.0'
     queue = '128GB,256GB,256GBv1'
+    cpus = 32
   }
   withName: filterReads{
-    module = ['python/3.6.1-2-anaconda', 'samtools/1.6', 'sambamba/0.6.6', 'bedtools/2.26.0']
+    container = 'docker://git.biohpc.swmed.edu:5050/s219741/chipseq-analysis-containerized/chipseq:1.0.0'
     queue = '128GB,256GB,256GBv1'
   }
   withName: experimentQC {
-    module = ['python/3.6.1-2-anaconda', 'deeptools/2.5.0.1']
+    container = 'docker://git.biohpc.swmed.edu:5050/s219741/chipseq-analysis-containerized/chipseq:1.0.0'
     queue = '128GB,256GB,256GBv1'
   }
   withName: convertReads {
-    module = ['python/3.6.1-2-anaconda',  'samtools/1.6', 'bedtools/2.26.0']
+    container = 'docker://git.biohpc.swmed.edu:5050/s219741/chipseq-analysis-containerized/chipseq:1.0.0'
     queue = '128GB,256GB,256GBv1'
   }
   withName: crossReads {
-    module = ['python/3.6.1-2-anaconda', 'phantompeakqualtools/1.2']
+    container = 'docker://git.biohpc.swmed.edu:5050/s219741/chipseq-analysis-containerized/chipseq:1.0.0'
     cpus = 32
   }
   withName: defineExpDesignFiles {
-    module = ['python/3.6.1-2-anaconda']
+    container = 'docker://git.biohpc.swmed.edu:5050/s219741/chipseq-analysis-containerized/python:3.6.1'
     executor = 'local'
   }
   withName: poolAndPsuedoReads {
-    module = ['python/3.6.1-2-anaconda']
+    container = 'docker://git.biohpc.swmed.edu:5050/s219741/chipseq-analysis-containerized/python:3.6.1'
     executor = 'local'
   }
   withName: callPeaksMACS {
-    module = ['python/3.6.1-2-anaconda', 'macs/2.1.0-20151222', 'UCSC_userApps/v317', 'bedtools/2.26.0', 'phantompeakqualtools/1.2']
+    container = 'docker://git.biohpc.swmed.edu:5050/s219741/chipseq-analysis-containerized/chipseq:1.0.0'
     queue = '128GB,256GB,256GBv1'
   }
   withName: plotProfile {
-    module = ['deeptools/2.5.0.1']
+    container = 'docker://git.biohpc.swmed.edu:5050/s219741/chipseq-analysis-containerized/chipseq:1.0.0'
+    queue = '128GB,256GB,256GBv1'
     cpus = 32
   }
   withName: consensusPeaks {
-    module = ['python/3.6.1-2-anaconda', 'bedtools/2.26.0']
+    container = 'docker://git.biohpc.swmed.edu:5050/s219741/chipseq-analysis-containerized/chipseq:1.0.0'
     executor = 'local'
   }
   withName: peakAnnotation {
-    module = ['R/3.3.2-gccmkl']
+    container = 'docker://git.biohpc.swmed.edu:5050/s219741/chipseq-analysis-containerized/r:3.3.2'
     executor = 'local'
   }
   withName: diffPeaks {
-    module = ['R/3.3.2-gccmkl']
+    container = 'docker://git.biohpc.swmed.edu:5050/s219741/chipseq-analysis-containerized/r:3.3.2'
     cpus = 32
   }
   withName: motifSearch {
-    module = ['python/3.6.1-2-anaconda', 'meme/4.11.1-gcc-openmpi', 'bedtools/2.26.0']
-    cpus = 32
+    executor = 'local'
+    container = 'docker://git.biohpc.swmed.edu:5050/s219741/chipseq-analysis-containerized/motif-search:meme-4.11.1'
+    //cpus = 32
   }
   withName: multiqcReport {
-    module = ['python/3.6.1-2-anaconda', 'pandoc/2.7', 'singularity/3.0.2']
+    container = 'docker://git.biohpc.swmed.edu:5050/s219741/chipseq-analysis-containerized/chipseq:1.0.0'
     executor = 'local'
   }
 }

workflow/main.nf

@@ -27,7 +27,7 @@ params.skipDiff = false
 params.skipMotif = false
 params.skipPlotProfile = false
 params.references = "$baseDir/../docs/references.md"
-params.multiqc =  "$baseDir/conf/multiqc_config.yaml"
+params.multiqc =  "$baseDir/configs/multiqc_config.yaml"
 params.ci = false
 params.dev = false
 
@@ -147,13 +147,13 @@ process checkDesignFile {
 
   if (pairedEnd) {
     """
-    module load python/3.6.1-2-anaconda
+    source /python361/entrypoint.sh
     python3 $baseDir/scripts/check_design.py -d $designFile -f $readsList -p
     """
   }
   else {
     """
-    module load python/3.6.1-2-anaconda
+    source /python361/entrypoint.sh
     python $baseDir/scripts/check_design.py -d $designFile -f $readsList
     """
   }
@@ -191,15 +191,13 @@ process trimReads {
 
   if (pairedEnd) {
     """
-    module load python/3.6.1-2-anaconda
-    module load trimgalore/0.4.1
+    source /chipseq/entrypoint.sh
     python3 $baseDir/scripts/trim_reads.py -f ${reads[0]} ${reads[1]} -s $sampleId -p
     """
   }
   else {
     """
-    module load python/3.6.1-2-anaconda
-    module load trimgalore/0.4.1
+    source /chipseq/entrypoint.sh
     python3 $baseDir/scripts/trim_reads.py -f ${reads[0]} -s $sampleId
     """
   }
@@ -228,17 +226,15 @@ process alignReads {
 
   if (pairedEnd) {
     """
-    module load python/3.6.1-2-anaconda
-    module load bwa/intel/0.7.12
-    module load samtools/1.6
+    source /chipseq/entrypoint.sh
+    free -hm
     python3 $baseDir/scripts/map_reads.py -f ${reads[0]} ${reads[1]} -r ${index}/genome.fa -s $sampleId -p
     """
   }
   else {
     """
-    module load python/3.6.1-2-anaconda
-    module load bwa/intel/0.7.12
-    module load samtools/1.6
+    source /chipseq/entrypoint.sh
+    free -hm
     python3 $baseDir/scripts/map_reads.py -f $reads -r ${index}/genome.fa -s $sampleId
     """
   }
@@ -269,19 +265,13 @@ process filterReads {
 
   if (pairedEnd) {
     """
-    module load python/3.6.1-2-anaconda
-    module load samtools/1.6
-    module load sambamba/0.6.6
-    module load bedtools/2.26.0
+    source /chipseq/entrypoint.sh
     python3 $baseDir/scripts/map_qc.py -b $mapped -p
     """
   }
   else {
     """
-    module load python/3.6.1-2-anaconda
-    module load samtools/1.6
-    module load sambamba/0.6.6
-    module load bedtools/2.26.0
+    source /chipseq/entrypoint.sh
     python3 $baseDir/scripts/map_qc.py -b $mapped
     """
   }
@@ -313,8 +303,7 @@ process experimentQC {
   script:
 
   """
-  module load python/3.6.1-2-anaconda
-  module load deeptools/2.5.0.1
+  source /chipseq/entrypoint.sh
   python3 $baseDir/scripts/experiment_qc.py -d $dedupDesign -e $extendReadsLen
   """
 
@@ -340,17 +329,13 @@ process convertReads {
 
   if (pairedEnd) {
     """
-    module load python/3.6.1-2-anaconda
-    module load samtools/1.6
-    module load bedtools/2.26.0
+    source /chipseq/entrypoint.sh
     python3 $baseDir/scripts/convert_reads.py -b $deduped -p
     """
   }
   else {
     """
-    module load python/3.6.1-2-anaconda
-    module load samtools/1.6
-    module load bedtools/2.26.0
+    source /chipseq/entrypoint.sh
     python3 $baseDir/scripts/convert_reads.py -b $deduped
     """
   }
@@ -377,15 +362,13 @@ process crossReads {
 
   if (pairedEnd) {
     """
-    module load python/3.6.1-2-anaconda
-    module load phantompeakqualtools/1.2
+    source /chipseq/entrypoint.sh
     python3 $baseDir/scripts/xcor.py -t $seTagAlign -p
     """
   }
   else {
     """
-    module load python/3.6.1-2-anaconda
-    module load phantompeakqualtools/1.2
+    source /chipseq/entrypoint.sh
     python3 $baseDir/scripts/xcor.py -t $seTagAlign
     """
   }
@@ -414,7 +397,7 @@ process defineExpDesignFiles {
   script:
 
   """
-  module load python/3.6.1-2-anaconda
+  source /python361/entrypoint.sh
   python3 $baseDir/scripts/experiment_design.py -d $xcorDesign
   """
 
@@ -440,13 +423,13 @@ process poolAndPsuedoReads {
 
   if (pairedEnd) {
     """
-    module load python/3.6.1-2-anaconda
+    source /python361/entrypoint.sh
     python3 $baseDir/scripts/pool_and_psuedoreplicate.py -d $experimentObjs -c $cutoffRatio -p
     """
   }
   else {
     """
-    module load python/3.6.1-2-anaconda
+    source /python361/entrypoint.sh
     python3 $baseDir/scripts/pool_and_psuedoreplicate.py -d $experimentObjs -c $cutoffRatio
     """
   }
@@ -478,21 +461,13 @@ process callPeaksMACS {
 
   if (pairedEnd) {
     """
-    module load python/3.6.1-2-anaconda
-    module load macs/2.1.0-20151222
-    module load UCSC_userApps/v317
-    module load bedtools/2.26.0
-    module load phantompeakqualtools/1.2
+    source /chipseq/entrypoint.sh
     python3 $baseDir/scripts/call_peaks_macs.py -t $tagAlign -x $xcor -c $controlTagAlign -s $sampleId -g $genomeSize -z $chromSizes -p
     """
   }
   else {
     """
-    module load python/3.6.1-2-anaconda
-    module load macs/2.1.0-20151222
-    module load UCSC_userApps/v317
-    module load bedtools/2.26.0
-    module load phantompeakqualtools/1.2
+    source /chipseq/entrypoint.sh
     python3 $baseDir/scripts/call_peaks_macs.py -t $tagAlign -x $xcor -c $controlTagAlign -s $sampleId -g $genomeSize -z $chromSizes
     """
   }
@@ -523,8 +498,8 @@ process plotProfile {
 
   script:
   """
-  module load deeptools/2.5.0.1
-  bash $baseDir/scripts/plot_profile.sh -g $gtfFile
+  source /chipseq/entrypoint.sh
+  /bin/bash $baseDir/scripts/plot_profile.sh -g $gtfFile
   """
 }
 
@@ -551,8 +526,7 @@ process consensusPeaks {
   script:
 
   """
-  module load python/3.6.1-2-anaconda
-  module load bedtools/2.26.0
+  source /chipseq/entrypoint.sh
   python3 $baseDir/scripts/overlap_peaks.py -d $peaksDesign -f $preDiffDesign
   """
 
@@ -575,7 +549,7 @@ process peakAnnotation {
   script:
 
   """
-  module load R/3.3.2-gccmkl
+  source /r-332/entrypoint.sh
   Rscript $baseDir/scripts/annotate_peaks.R $designAnnotatePeaks $gtfFile $geneNames
   """
 
@@ -603,10 +577,8 @@ process motifSearch {
   script:
 
   """
-  module load python/3.6.1-2-anaconda
-  module load meme/4.11.1-gcc-openmpi
-  module load bedtools/2.26.0
-  python3 $baseDir/scripts/motif_search.py -d $designMotifSearch -g $fasta -p $topPeakCount
+  source /motif-search/entrypoint.sh
+  python $baseDir/scripts/motif_search.py -d $designMotifSearch -g $fasta -p $topPeakCount
   """
 }
 
@@ -639,13 +611,12 @@ process diffPeaks {
   script:
 
   """
-  module load python/3.6.1-2-anaconda
-  module load R/3.3.2-gccmkl
+  source /r-332/entrypoint.sh
   Rscript $baseDir/scripts/diff_peaks.R $designDiffPeaks
   """
 }
 
-// Generate Multiqc Report, gerernate Software Versions and references
+// Generate Multiqc Report, generate software versions and references
 process multiqcReport {
   publishDir "$outDir/${task.process}", mode: 'copy'
 
@@ -677,14 +648,12 @@ process multiqcReport {
   script:
 
   """
-  module load python/3.6.1-2-anaconda
-  module load pandoc/2.7
-  module load singularity/3.0.2
+  source /chipseq/entrypoint.sh
   echo $workflow.nextflow.version > version_nextflow.txt
-  singularity exec /project/shared/bicf_workflow_ref/singularity_images/bicf-multiqc-2.0.0.img multiqc --version > version_multiqc.txt
+  multiqc --version > version_multiqc.txt
   python --version &> version_python.txt
   python3 $baseDir/scripts/generate_references.py -r $references -o software_references
   python3 $baseDir/scripts/generate_versions.py -o software_versions
-  singularity exec /project/shared/bicf_workflow_ref/singularity_images/bicf-multiqc-2.0.0.img multiqc -c $multiqc .
+  multiqc -c $multiqc .
   """
-}
+}
\ No newline at end of file

workflow/nextflow.config

-profiles {
-  standard {
-    includeConfig 'conf/biohpc.config'
-  }
-}
-
-trace {
-  enabled = true
-  file = 'pipeline_trace.txt'
-  fields = 'task_id,native_id,process,name,status,exit,submit,start,complete,duration,realtime,%cpu,%mem,rss'
-}
-
-timeline {
-  enabled = true
-  file = 'timeline.html'
-}
-
-report {
-  enabled = true
-  file = 'report.html'
-}
-
-
-manifest {
-  name = 'chipseq_analysis'
-  description = 'BICF ChIP-seq Analysis Workflow.'
-  homePage = 'https://git.biohpc.swmed.edu/BICF/Astrocyte/chipseq_analysis'
-  version = '1.1.2'
-  mainScript = 'main.nf'
-  nextflowVersion = '>=0.31.0'
-}