From 014508e5d1d0a2113f0ad20376dff37c18f6f60e Mon Sep 17 00:00:00 2001
From: Beibei Chen <beibei.chen@utsouthwestern.edu>
Date: Wed, 8 Feb 2017 09:09:17 -0600
Subject: [PATCH] Got rid of abs path
---
astrocyte_package.yml | 132 --------------------------------
workflow/main.nf | 66 +++++++++-------
workflow/scripts/runMemechip.py | 2 +-
3 files changed, 38 insertions(+), 162 deletions(-)
delete mode 100644 astrocyte_package.yml
diff --git a/astrocyte_package.yml b/astrocyte_package.yml
deleted file mode 100644
index 2a9f17c..0000000
--- a/astrocyte_package.yml
+++ /dev/null
@@ -1,132 +0,0 @@
-#
-# metadata for the example astrocyte ChipSeq workflow package
-#
-
-# -----------------------------------------------------------------------------
-# BASIC INFORMATION
-# -----------------------------------------------------------------------------
-
-# A unique identifier for the workflow package, text/underscores only
-name: 'chipseq_analysis_bicf'
-# Who wrote this?
-author: 'Beibei Chen'
-# A contact email address for questions
-email: 'biohpc-help@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 a simple ChIP-seq analysis workflow using deepTools, Diffbind, ChipSeeker and MEME-ChIP, visualization application.
-
-# -----------------------------------------------------------------------------
-# DOCUMENTATION
-# -----------------------------------------------------------------------------
-
-# A list of documentation file in .md format that should be viewable from the
-# web interface. These files are in the 'docs' subdirectory. The first file
-# listed will be used as a documentation index and is index.md by convention
-documentation_files:
- - 'index.md'
-
-# -----------------------------------------------------------------------------
-# NEXTFLOW WORKFLOW CONFIGURATION
-# -----------------------------------------------------------------------------
-
-# Remember - The workflow file is always named 'workflow/main.f'
-# The workflow must publish all final output into $baseDir
-
-# A list of clueter environment modules that this workflow requires to run.
-# Specify versioned module names to ensure reproducability.
-workflow_modules:
- - 'deeptools/2.3.5'
- - 'meme/4.11.1-gcc-openmpi'
-
-# A list of parameters used by the workflow, defining how to present them,
-# options etc in the web interface. For each parameter:
-#
-# REQUIRED INFORMATION
-# id: The name of the parameter in the NEXTFLOW workflow
-# type: The type of the parameter, one of:
-# string - A free-format string
-# integer - An integer
-# real - A real number
-# file - A single file from user data
-# files - One or more files from user data
-# select - A selection from a list of values
-# required: true/false, must the parameter be entered/chosen?
-# description: A user friendly description of the meaning of the parameter
-#
-# OPTIONAL INFORMATION
-# default: A default value for the parameter (optional)
-# min: Minium value/characters/files for number/string/files types
-# max: Maxumum value/characters/files for number/string/files types
-# regex: A regular expression that describes valid entries / filenames
-#
-# SELECT TYPE
-# choices: A set of choices presented to the user for the parameter.
-# Each choice is a pair of value and description, e.g.
-#
-# choices:
-# - [ 'myval', 'The first option']
-# - [ 'myval', 'The second option']
-#
-# NOTE - All parameters are passed to NEXTFLOW as strings... but they
-# are validated by astrocyte using the information provided above
-
-workflow_parameters:
-
- - id: design
- type: file
- required: true
- regex: ".*csv"
- description: |
- A design file listing pairs of sample name and sample group.
- Columns must include: SampleID,Tissue, Factor, Condition, Replicate, Peaks, bamReads, bamControl, ControlID, PeakCaller
-
- - id: genome
- type: select
- choices:
- - [ '/project/shared/bicf_workflow_ref/GRCh38', 'Human GRCh38']
- - [ '/project/shared/bicf_workflow_ref/GRCh37', 'Human GRCh37']
- - [ '/project/shared/bicf_workflow_ref/GRCm38', 'Mouse GRCh38']
- required: true
- description: |
- Reference genome for annotation
-
- - id: toppeak
- type: integer
- required: true
- description: |
- The number of top peaks to use for motif discovery.
-# -----------------------------------------------------------------------------
-# SHINY APP CONFIGURATION
-# -----------------------------------------------------------------------------
-
-# Remember - The vizapp is always 'vizapp/server.R' 'vizapp/ui.R'
-# The workflow must publish all final output into $baseDir
-
-# Name of the R module that the vizapp will run against
-vizapp_r_module: 'R/3.2.1-intel'
-
-# List of any CRAN packages, not provided by the modules, that must be made
-# available to the vizapp
-vizapp_cran_packages:
- - sqldf
- - shiny
- - Vennerable
- - DT
- - ggplot2
- - gplots
- - gtools
- - RColorBrewer
-
-
-# # List of any Bioconductor packages, not provided by the modules, that must be made
-# available to the vizapp
-vizapp_bioc_packages:
- - qusage
- - ballgown
-vizapp_github_packages:
- - js229/Vennerable
-
diff --git a/workflow/main.nf b/workflow/main.nf
index 2095ec6..937e9ba 100644
--- a/workflow/main.nf
+++ b/workflow/main.nf
@@ -1,36 +1,37 @@
#!/usr/bin/env nextflow
-
-// Default parameter values to run tests
-// params.bams="$baseDir/../test/*.bam"
- params.testpath="/project/BICF/BICF_Core/bchen4/chipseq_analysis/test/"
- params.design="/project/BICF/BICF_Core/bchen4/chipseq_analysis/test/samplesheet.csv"
- params.genomepath="/project/BICF/BICF_Core/bchen4/chipseq_analysis/test/genome/hg19/"
+ params.design="$baseDir/../test/samplesheet.csv"
+ params.bams = "$baseDir/../test/*.bam"
+ params.peaks = "$baseDir/../test/*/broadPeak"
+ params.genomepath="/project/shared/bicf_workflow_ref/hg19/"
species = "hg19"
toppeakcount = 200
-// design_file = file(params.design)
-// bams=file(params.bams)
-//gtf_file = file("$params.genome/gencode.gtf")
-//genenames = file("$params.genome/genenames.txt")
-//geneset = file("$params.genome/gsea_gmt/$params.geneset")
+ design_file = file(params.design)
+ deeptools_design = Channel.fromPath(params.design)
+ diffbind_design = Channel.fromPath(params.design)
+ chipseeker_design = Channel.fromPath(params.design)
+ meme_design = Channel.fromPath(params.design)
+ index_bams = Channel.fromPath(params.bams)
+ deeptools_bams = Channel.fromPath(params.bams)
+ deeptools_peaks = Channel.fromPath(params.peaks)
+ chipseeker_peaks = Channel.fromPath(params.peaks)
+ diffbind_bams = Channel.fromPath(params.bams)
+ diffbind_peaks = Channel.fromPath(params.peaks)
+ meme_peaks = Channel.fromPath(params.peaks)
-
-process processdesign {
+process bamindex {
publishDir "$baseDir/output/", mode: 'copy'
-// input:
-// file design_file from input
-// file annotation Tdx
+ input:
+ file index_bam_files from index_bams
output:
- file "new_design" into deeptools_design
- file "new_design" into diffbind_design
- file "new_design" into chipseeker_design
- file "new_design" into meme_design
-
+ file "*bai" into deeptools_bamindex
+ file "*bai" into diffbind_bamindex
- script:
+ script:
"""
module load python/2.7.x-anaconda
source activate /project/shared/bicf_workflow_ref/chipseq_bchen4/
- python $baseDir/scripts/preprocessDesign.py -i ${params.design}
+ module load samtools/intel/1.3
+ samtools index ${index_bam_files}
"""
}
@@ -38,23 +39,28 @@ process run_deeptools {
publishDir "$baseDir/output", mode: 'copy'
input:
file deeptools_design_file from deeptools_design
- file annotation Tdx
+ file deeptools_bam_files from deeptools_bams.toList()
+ file deeptools_peak_files from deeptools_peaks.toList()
+ file deeptools_bam_indexes from deeptools_bamindex.toList()
output:
stdout result
script:
"""
module load python/2.7.x-anaconda
source activate /project/shared/bicf_workflow_ref/chipseq_bchen4/
- module load deeptools/2.3.5
- python $baseDir/scripts/runDeepTools.py -i $deeptools_design_file -g ${params.genomepath}}
+ module load deeptools/2.3.5
+ python $baseDir/scripts/runDeepTools.py -i ${params.design} -g ${params.genomepath}}
"""
}
process run_diffbind {
-// publishDir "$baseDir/output", mode: 'copy'
+ publishDir "$baseDir/output", mode: 'copy'
input:
file diffbind_design_file from diffbind_design
+ file diffbind_bam_files from diffbind_bams.toList()
+ file diffbind_peak_files from diffbind_peaks.toList()
+ file diffbind_ban_indexes from diffbind_bamindex.toList()
output:
file "diffpeak.design" into diffpeaksdesign_chipseeker
file "diffpeak.design" into diffpeaksdesign_meme
@@ -74,7 +80,7 @@ process run_chipseeker_diffpeak {
file diffpeak_design_file from diffpeaksdesign_chipseeker
file diffpeaks from diffpeaks_chipseeker
output:
- stdout result
+ stdout result_chipseeker
script:
"""
module load python/2.7.x-anaconda
@@ -84,9 +90,10 @@ process run_chipseeker_diffpeak {
}
process run_chipseeker_originalpeak {
-// publishDir "$baseDir/output", mode: 'copy'
+ publishDir "$baseDir/output", mode: 'copy'
input:
file design_file from chipseeker_design
+ file chipseeker_peak_files from chipseeker_peaks
output:
stdout result1
script:
@@ -101,6 +108,7 @@ process run_meme_original {
publishDir "$baseDir/output", mode: 'copy'
input:
file design_meme from meme_design
+ file meme_peak_files from meme_peaks
output:
stdout result_meme_original
script:
diff --git a/workflow/scripts/runMemechip.py b/workflow/scripts/runMemechip.py
index 0bc79d6..b2a15a3 100644
--- a/workflow/scripts/runMemechip.py
+++ b/workflow/scripts/runMemechip.py
@@ -40,7 +40,7 @@ def main():
#run(args.infile, args.genome, args.limit, args.output)
#get Pool ready
dfile = pd.read_csv(args.infile)
- meme_arglist = zip(dfile['Peaks'].tolist(),[args.genome+"hg19.2bit"]*dfile.shape[0],[str(args.limit)]*dfile.shape[0],dfile['SampleID'].tolist())
+ meme_arglist = zip(dfile['Peaks'].tolist(),[args.genome+"genome.2bit"]*dfile.shape[0],[str(args.limit)]*dfile.shape[0],dfile['SampleID'].tolist())
work_pool = Pool(min(12,dfile.shape[0]))
resultList = work_pool.map(run_wrapper, meme_arglist)
work_pool.close()
--
GitLab