Example Files¶
Task nextflow.config¶
This nextflow.config file is copied to the task directory by the command:
#mkdir ./my_task_dir
#cd ./my_task_dir
nextflow run rennelab/CnR-flow --mode initiate
This configuration file contains paramaters for input file and task workflow setup.
…/my_task_dir/nextflow.config (Task Settings)¶
//Daniel Stribling
//Renne Lab, University of Florida
//CnR-flow Configuration File
//
// Config syntax:
// This config file uses the syntax described here:
// https://www.nextflow.io/docs/latest/config.html
// Primarily, "//" acts as a comment and allows removal/deactivation of lines.
//
// Settings within scopes, Ex:
// params {
// setting = value
// ...
// }
// are equivalent to:
// params.setting = value"
//
// Configuration Hierarchy:
// Different Nextflow configuration files have the precedence order:
// task-dir > pipe-dir > user-default > pipe-default
//
// This configruation is (presumably) in the task directory:
// (after running "nextflow CnR-flow --mode initiate" )
// and will therefore superceed pipe-setup, user, and pipe hardcoded defaults.
// For more detail visit: https://www.nextflow.io/docs/latest/config.html
//
// This configuration only includes task-specific paramaters and paramaters
// designed to be modified at runtime. Other parameters are provided in the
// pipe configuration, at CnR-flow/nextflow.config. Parameters
// provided here will override system defaults.
//
// Process Settings (For use of PBS, SLURM, etc)
process {
// --Executor, see: https://www.nextflow.io/docs/latest/executor.html
//executor = 'slurm' // for running processes using SLURM (Default: 'local')
// Process Walltime, See https://www.nextflow.io/docs/latest/process.html#process-time
//time = '12h'
// Process CPUs, See https://www.nextflow.io/docs/latest/process.html#cpus
//cpus = 8
//
// Memory: See https://www.nextflow.io/docs/latest/process.html#process-memory
// Set Memory for specific task sizes (1n/2n/4n scheme recommended)
//withLabel: big_mem { memory = '16 GB' }
//withLabel: norm_mem { memory = '4 GB' }
//withLabel: small_mem { memory = '2 GB' }
// -*OR*- Set Memory for all processes
//memory = "16 GB"
ext.ph = null //Placeholder to prevent errors.
}
params {
//REQUIRED values to enter (all others should work as default):
// ref_fasta (or some other ref-mode/location)
// treat_fastqs (input paired-end fastq[.gz] file paths)
// [OR fastq_groups] (mutli-group input paired-end .fastq[.gz] file paths)
// Automatic alignment reference preparation/usage settings:
ref_mode = 'fasta' // Options: ['name', 'fasta', 'manual']
ref_fasta = '' // REQUIRED: Ex: '/path/to/my/reference.fasta[.gz]'
// Default Pre-Supplied Normalization library is Ecoli:
norm_ref_fasta = "${projectDir}/ref_dbs/gcf_000005845.2_asm584v2_genomic.fasta.gz"
// CnR-flow Input Files:
// Provided fastqs must be in glob pattern matching pairs.
// Example: ['./relpath/to/base*R{1,2}*.fastq']
// Example: ['/abs/path/to/other*R{1,2}*.fastq']
//
treat_fastqs = [] // REQUIRED, Single-group Treatment fastq Pattern
ctrl_fastqs = [] // Single-group Control fastq pattern
// Can specify multiple treat/control groups as Groovy mapping.
// Specified INSTEAD of treat_fasts/ctrl_fastqs paramaters.
// Note: There should be only one ctrl sample per group
// (after optional lane combination)
//Example:
//fastq_groups = [
// 'group_1_name': ['treat': 'relpath/to/treat1*R{1,2}*',
// 'ctrl': 'relpath/to/ctrl1*R{1,2}*',
// ]
// 'group_2_name': ['treat': ['relpath/to/g2_treat1*R{1,2}*'
// '/abs/path/to/g2_treat2*R{1,2}*'
// ],
// 'ctrl': 'relpath/to/g2_ctrl1*R{1,2}*'
// ]
//]
//fastq_groups = []
// ------- Step-Specific Pipeline Paramaters --------
// Step Settings:
do_merge_lanes = true // Merge sample names differing only by lane-ID (Ex: L001, L002)
do_fastqc = true // Perform FastQC Analysis
do_trim = true // Trim tags using Trimmomatic
do_retrim = true // Retrim tags using kseq_test (CUTRUNTools)
do_norm_spike = true // Normalize using aligment count to a spike-in reference
do_make_bigwig = true // Create UCSC bigWig files from final alignments
//FastQC Settings:
fastqc_flags = ''
// Alignment Mode Options (params.use_aln_modes) :
// "all" : Use all reads
// "all_dedup" : Use all reads, and remove duplicates.
// "less_120" : Use trimmed reads <= 120 bp
// "less_120_dedup" : Use trimmed reads <= 120 bp and remove duplicates.
// (Multiple modes can be performed in parallel. Ex: ['all', 'less_120'])
use_aln_modes = ["all"] // Options: ["all", "all_dedup", "less_120", "less_120_dedup"]
// Peak Caller Options (params.peak_callers):
// "macs2" : Call Peaks with Macs2
// "seacr" : Call Peaks with SEACR
// (Multiple callers can be used in parallel. Ex: ['macs2', 'seacr'])
peak_callers = ['macs', 'seacr'] // Options: ['macs', 'seacr']
//Trimmomatic Trim Settings
//--Trimmomatic Adapter Path, Downloaded after "nextflow CnR-flow --mode initiate"
trimmomatic_adapterpath = "${projectDir}/ref_dbs/trimmomatic_adapters/TruSeq3-PE-2.fa"
trimmomatic_settings = "ILLUMINACLIP:${params.trimmomatic_adapterpath}/Truseq3.PE.fa:2:15:4:4:true LEADING:20 TRAILING:20 SLIDINGWINDOW:4:15 MINLEN:25"
trimmomatic_flags = "-phred33"
//kseq_test (CUTRUNTools) Retrim Settings
input_seq_len = 'auto' // Length of untrimmed sequence reads (Ex: '150') or 'auto'
//Bowtie2 Alignment Settings
aln_ref_flags = "--local --very-sensitive-local --phred33 -I 10 -X 700 --dovetail --no-unal --no-mixed --no-discordant"
//Normalization Settings
aln_norm_flags = params.aln_ref_flags
norm_scale = 1000 // Arbitrary value for scaling of normalized counts.
norm_mode = 'adj' // Options: ['adj', 'all']
//Macs2 Settings
macs_qval = '0.01'
macs_flags = ''
//SEACR Settings
seacr_fdr_threshhold = "0.01"
seacr_norm_mode = "auto" // Options: "auto", "norm", "non"
seacr_call_stringent = true
seacr_call_relaxed = true
// ------- General Pipeline Output Paramaters --------
publish_files = 'default' // Options: ["minimal", "default", "all"]
publish_mode = 'copy' // Options: ["symlink", "copy"]
//Name trim guide: ( regex-based )
// ~/groovy-slashy-string/ ; "~" denotes groovy pattern type.
// ~/^/ matches beginning ; ~/$/ matches end
trim_name_prefix = '' // Example: ~/^myprefix./ removes "myprefix." prefix.
trim_name_suffix = '' // Example: ~/_mysuffix$/ removes "_mysuffix" suffix.
// Workflow Output Default Naming Scheme:
// Absolute paths for output:
out_dir = "${launchDir}/cnr_output"
refs_dir = "${launchDir}/cnr_references"
}
Pipe nextflow.config¶
This nextflow.config file is contains configuration paramaters for pipeline setup.
…/CnR-flow/nextflow.config (Pipe Settings)¶
//Daniel Stribling
//Renne Lab, University of Florida
//CnR-flow Configuration File
//
// Config syntax:
// This config file uses the syntax described here:
// https://www.nextflow.io/docs/latest/config.html
// Primarily, "//" acts as a comment and allows removal/deactivation of lines.
//
// Settings within scopes, Ex:
// params {
// setting = value
// ...
// }
// are equivalent to:
// params.setting = value"
//
// Configuration Hierarchy:
// Different Nextflow configuration files have the precedence order:
// task-dir > pipe-dir > user-default > pipe-default
//
// (presumably) This configruation is in the CnR-flow/nextflow.config,
// and will therefore superceed user and pipe defaults,
// but be overridden by the task-specific configuration file
// in the case of conflicting settings.
// For more detail visit: https://www.nextflow.io/docs/latest/config.html
//
// Users wishing to modify dependency configuration should specifically
// direct attention to the conda/module section.
// Other default paramaters are provided below.
// Pipeline Details
manifest {
author = 'Daniel Stribling, Rolf Renne'
defaultBranch = 'master'
description = """\
CUT&RUN-Flow, A Nextflow pipeline for QC, tag trimming, normalization, and peak
calling for paired-end sequence data from CUT&RUN experiments.
""".stripIndent()
//doi
homePage = 'http://www.rennelab.com'
mainScript = 'CnR-flow.nf'
name = 'CUT&RUN-Flow'
nextflowVersion = '20.07.1'
version = '0.10'
}
// Process Settings (For use of PBS, SLURM, etc)
process {
// --Executor, see: https://www.nextflow.io/docs/latest/executor.html
//executor = 'slurm' // for running processes using SLURM (Default: 'local')
// Process Walltime, See https://www.nextflow.io/docs/latest/process.html#process-time
//time = '12h'
// Process CPUs, See https://www.nextflow.io/docs/latest/process.html#cpus
//cpus = 8
//
// Memory: See https://www.nextflow.io/docs/latest/process.html#process-memory
// Set Memory for specific task sizes (1n/2n/4n scheme recommended)
//withLabel: big_mem { memory = '16 GB' }
//withLabel: norm_mem { memory = '4 GB' }
//withLabel: small_mem { memory = '2 GB' }
// -*OR*- Set Memory for all processes
//memory = "16 GB"
ext.ph = null //Placeholder to prevent errors.
}
params {
// ------- Dependency Configuration --------
// Configuration using conda is recommended for most systems.
// Each dependency can only have one type of resource configured:
// (Ex: bowtie2_module OR bowtie2_conda)
// Dependency Configuration Using Anaconda
// Miniconda Install Instructions:
// https://docs.conda.io/en/latest/miniconda.html
//
// -- External Conda Environments:
facount_conda = 'bioconda::ucsc-facount=366=*_0'
bowtie2_conda = 'bioconda::bowtie2=2.4.1'
fastqc_conda = 'bioconda::fastqc=0.11.9'
trimmomatic_conda = 'bioconda::trimmomatic=0.39'
bedtools_conda = 'bioconda::bedtools=2.29.2'
macs2_conda = 'bioconda::macs2=2.2.6'
R_conda = 'r=3.6.0'
samtools_conda = 'bioconda::samtools=1.9=*_11'
bedgraphtobigwig_conda = 'libgcc-ng libpng conda-forge::libuuid mysql-connector-c openssl zlib bioconda::ucsc-bedgraphtobigwig=377'
// -- Packaged/Installed Tool Conda Environments (Changes should not be necessary):
seacr_conda = "${params.R_conda} ${params.bedtools_conda}"
//kseqtest_conda = "" // (uses binary, should not be needed)
// -- Comprehensive Conda Environment (If provided, is used for all execution)
//all_conda = ""
// Dependency Configuration Using Environment Modules
// (values will vary depending on system)
// To enable, comment ("//") / delete the conda-configuration and uncomment this configuration.
// -- External Tool Modules:
//facount_module = "" // Ex: "ucsc/20200320"
//bowtie2_module = "" // Ex: "bowtie2/2.3.5.1"
//fastqc_module = "" // Ex: "fastqc/0.11.7"
//trimmomatic_module = "" // Ex: "trimmomatic/0.39"
//bedtools_module = "" // Ex: "bedtools/2.29.2"
//macs2_module = "" // Ex: "macs/2.2.7.1"
//R_module = "" // Ex: "R/4.0"
//bedgraphtobigwig_module = "" // Ex: "ucsc/20200320"
// -- Packaged/Installed Tool Modules (Changes should not be necessary):
//seacr_module = "${params.R_module}:${params.bedtools_module}"
//kseqtest_module = "" // (uses binary, should not be needed)
// -- Comprehensive Tool Modules (If provided, is used for all execution)
//all_module = "" // Ex: "cutruntools/20200104"
// System Call Settings
// Call executed on the system, defaults assume that each tool is available
// on the system PATH (as with conda setup)
// Can replace with direct path as desired:
// Ex:
// samtools_call = "samtools"
// or samtools_call = "/path/to/samtools/dir/samtools"
java_call = "java"
bowtie2_build_call = "bowtie2-build"
facount_call = "faCount"
samtools_call = "samtools"
fastqc_call = "fastqc"
trimmomatic_call = "trimmomatic"
bowtie2_call = "bowtie2"
bedtools_call = "bedtools"
macs2_call = "macs2"
bedgraphtobigwig_call = "bedGraphToBigWig"
kseqtest_call = "${projectDir}/CUTRUNTools/kseq_test" //Installed with --mode initiate
seacr_call = "${projectDir}/SEACR/SEACR_1.3.sh" //Packaged with download
seacr_R_script = "${projectDir}/SEACR/SEACR_1.3.R" //Packaged with download
// ------- Step-Specific Pipeline Paramaters --------
// Step Settings:
do_merge_lanes = true // Merge sample names differing only by lane-ID (Ex: L001, L002)
do_fastqc = true // Perform FastQC Analysis
do_trim = true // Trim tags using Trimmomatic
do_retrim = true // Retrim tags using kseq_test (CUTRUNTools)
do_norm_spike = true // Normalize using aligment count to a spike-in reference
do_make_bigwig = true // Create UCSC bigWig files from final alignments
//FastQC Settings:
fastqc_flags = ''
// Alignment Mode Options (params.use_aln_modes) :
// "all" : Use all reads
// "all_dedup" : Use all reads, and remove duplicates.
// "less_120" : Use trimmed reads <= 120 bp
// "less_120_dedup" : Use trimmed reads <= 120 bp and remove duplicates.
// (Multiple modes can be performed in parallel. Ex: ['all', 'less_120'])
use_aln_modes = ["all"] // Options: ["all", "all_dedup", "less_120", "less_120_dedup"]
// Peak Caller Options (params.peak_callers):
// "macs2" : Call Peaks with Macs2
// "seacr" : Call Peaks with SEACR
// (Multiple callers can be used in parallel. Ex: ['macs2', 'seacr'])
peak_callers = ['macs', 'seacr'] // Options: ['macs', 'seacr']
//Trimmomatic Trim Settings
//--Trimmomatic Adapter Path, Downloaded after "nextflow CnR-flow --mode initiate"
trimmomatic_adapterpath = "${projectDir}/ref_dbs/trimmomatic_adapters/TruSeq3-PE-2.fa"
trimmomatic_settings = "ILLUMINACLIP:${params.trimmomatic_adapterpath}/Truseq3.PE.fa:2:15:4:4:true LEADING:20 TRAILING:20 SLIDINGWINDOW:4:15 MINLEN:25"
trimmomatic_flags = "-phred33"
//kseq_test (CUTRUNTools) Retrim Settings
input_seq_len = 'auto' // Length of untrimmed sequence reads (Ex: '150') or 'auto'
//Bowtie2 Alignment Settings
aln_ref_flags = "--local --very-sensitive-local --phred33 -I 10 -X 700 --dovetail --no-unal --no-mixed --no-discordant"
//Normalization Settings
aln_norm_flags = params.aln_ref_flags
norm_scale = 1000 // Arbitrary value for scaling of normalized counts.
norm_mode = 'adj' // Options: ['adj', 'all']
//Macs2 Settings
macs_qval = '0.01'
macs_flags = ''
//SEACR Settings
seacr_fdr_threshhold = "0.01"
seacr_norm_mode = "auto" // Options: "auto", "norm", "non"
seacr_call_stringent = true
seacr_call_relaxed = true
// ------- General Pipeline Output Paramaters --------
publish_files = 'default' // Options: ["minimal", "default", "all"]
publish_mode = 'copy' // Options: ["symlink", "copy"]
//Name trim guide: ( regex-based )
// ~/groovy-slashy-string/ ; "~" denotes groovy pattern type.
// ~/^/ matches beginning ; ~/$/ matches end
trim_name_prefix = '' // Example: ~/^myprefix./ removes "myprefix." prefix.
trim_name_suffix = '' // Example: ~/_mysuffix$/ removes "_mysuffix" suffix.
// Workflow Output Default Naming Scheme:
// Absolute paths for output:
out_dir = "${launchDir}/cnr_output"
refs_dir = "${launchDir}/cnr_references"
// Subdirectory Settigns:
log_dir = 'logs'
merge_fastqs_dir = 'S0_B_merged_reads'
fastqc_pre_dir = 'S0_C_FastQC_pre'
trim_dir = 'S1_A_fastq_trimomatic'
retrim_dir = 'S1_B_fastq_kseqtest'
fastqc_post_dir = 'S1_C_FastQC_post'
aln_dir_ref = 'S2_A_aln_ref'
aln_dir_mod = 'S2_B_aln_mod'
aln_dir_bdg = 'S2_C_aln_bdg'
aln_dir_spike = 'S3_A_aln_spikein'
aln_dir_norm = 'S3_B_aln_norm'
aln_bigwig_dir = 'S4_A_aln_bigWig'
peaks_dir_macs = 'S5_A_peaks_macs'
peaks_dir_seacr = 'S5_B_peaks_seacr'
prep_bt2db_suf = 'bt2_db'
}
// Location to store conda environments for reuse.
conda.cacheDir = "${projectDir}/conda_envs/"
// ------- Individual Task Settings, Included for Completeness --------
//params {
//REQUIRED values to enter (all others should work as default):
// ref_fasta (or some other ref-mode/location)
// treat_fastqs (input paired-end fastq[.gz] file paths)
// [OR fastq_groups] (mutli-group input paired-end .fastq[.gz] file paths)
// Automatic alignment reference preparation/usage settings:
//ref_mode = 'fasta' // Options: ['name', 'fasta', 'manual']
//ref_fasta = '' // REQUIRED: Ex: '/path/to/my/reference.fasta[.gz]'
// Default Pre-Supplied Normalization library is Ecoli:
//norm_ref_fasta = "${projectDir}/ref_dbs/gcf_000005845.2_asm584v2_genomic.fasta.gz"
// CnR-flow Input Files:
// Provided fastqs must be in glob pattern matching pairs.
// Example: ['./relpath/to/base*R{1,2}*.fastq']
// Example: ['/abs/path/to/other*R{1,2}*.fastq']
//
//treat_fastqs = [] // REQUIRED, Single-group Treatment fastq Pattern
//ctrl_fastqs = [] // Single-group Control fastq pattern
// Can specify multiple treat/control groups as Groovy mapping.
// Specified INSTEAD of treat_fasts/ctrl_fastqs paramaters.
// Note: There should be only one ctrl sample per group
// (after optional lane combination)
//Example:
//fastq_groups = [
// 'group_1_name': ['treat': 'relpath/to/treat1*R{1,2}*',
// 'ctrl': 'relpath/to/ctrl1*R{1,2}*',
// ]
// 'group_2_name': ['treat': ['relpath/to/g2_treat1*R{1,2}*'
// '/abs/path/to/g2_treat2*R{1,2}*'
// ],
// 'ctrl': 'relpath/to/g2_ctrl1*R{1,2}*'
// ]
//]
//fastq_groups = []