Configuration File
To download a configuration file template users just use --get_config
parameter. Using a config file your code is lot more clean and concise.
# get config
nextflow run fmalmeida/ngs-preprocess --get_config
# run with config
nextflow run fmalmeida/ngs-preprocess -c [path-to-config]
Default configuration
/*
fmalmeida/ngs-preprocess pipeline configuration file
Maintained by Felipe Marques de Almeida
Contact: almeidafmarques@outlook.com
This file contains all the parameters that are required by the pipeline.
Some of them can be left in blank and other ones need a proper configuration.
Please do not change anything before the = sign. Fields must be configured
and set with values after the = sign.
Since the input file parameters will always work as a pattern match
it is required that it MUST ALWAYS be double quoted as the example below.
The pipeline will process each file that matches the pattern separately.
E.g. param1 = "my_reads/input*.fastq"
*/
params {
// Sets output directory
output = "output"
// inputs from SRA. A file containing on SRA ID per line.
sra_ids = null
/*
Parameters for short reads preprocessing
with fastp
*/
shortreads = null // Path to shortreads. Examples: 'SRR6307304_{1,2}.fastq' | 'SRR7128258*'.
// Must be double quoted and paired end reads must have the pattern {1,2}.
// The pipeline will process each file that matches the pattern separately.
shortreads_type = null // Type of shortreads. Values: paired | single
fastp_average_quality = 20 // Filter reads by its average read quality (it loads the --average_qual fastp param). Default: 20.
fastp_merge_pairs = false // If true, fastp will try to merge paired end reads.
fastp_correct_pairs = false // If true, fastp will try to correct small base errors in paired end reads.
fastp_additional_parameters = null // Pass any other fastp additional parameter that you want.
// See https://github.com/OpenGene/fastp.
/*
Optional parameter for filtering longreads from pacbio or nanopore.
This command uses nanofilt for both technologies. If you prefer to
filter reads from any technology with a different program you can
left it blank and it you not be executed.
*/
lreads_min_quality = 5 // If blank, long reads (lreads) will not be filtered.
lreads_min_length = 500 // If blank, long reads (lreads) will not be filtered.
/*
Parameters for nanopore ONT longreads preprocessing
*/
nanopore_fastq = null // Path to nanopore ONT basecalled reads in fastq
nanopore_is_barcoded = false // Tells wheter or not nanopore reads are barcoded
// It will split barcodes into single files
nanopore_sequencing_summary = null // Path to nanopore 'sequencing_summary.txt'.
// Using this will make the pipeline render a
// sequencing statistics report using pycoQC.
// pycoQC reports will be saved using the
// files basename, so please, use meaningful basename,
// such as: sample1.txt, sample2.txt, etc.
/*
Parameters for PacBio longreads preprocessing
Use bamPath or h5Path, not both.
*/
pacbio_bam = null // Path to PacBio subreads in bam format
pacbio_h5 = null // Path to directory containing legacy *.bas.h5 data (1 per directory)
pacbio_barcodes = null // Path to xml/fasta file containing barcode information.
// It will split barcodes into single files.
pacbio_barcode_design = "same" // By default, only reads with "same" barcodes are given.
// Options: same, different, any
pacbio_get_hifi = false // Whether or not to try to compute CCS reads
// Max resource options
// Defaults only, expecting to be overwritten
max_memory = '6.GB'
max_cpus = 4
max_time = '40.h'
}