rliterman@0: /*
rliterman@0: ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
rliterman@0:     CSP2 Nextflow config file
rliterman@0: ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
rliterman@0:     Default config options for all compute environments
rliterman@0: ----------------------------------------------------------------------------------------
rliterman@0: */
rliterman@0: 
rliterman@0: // Enable conda
rliterman@0: conda.enabled = true
rliterman@0: 
rliterman@0: // Import profile settings
rliterman@0: includeConfig "conf/profiles.config"
rliterman@0: 
rliterman@0: // Global default params
rliterman@0: params {
rliterman@0: 
rliterman@0:     // Setting output directory 
rliterman@0: 
rliterman@0:     // Set name for output folder/file prefixes
rliterman@0:     out = "CSP2_${new java.util.Date().getTime()}"
rliterman@0: 
rliterman@0:     // Set output parent directory [Default: CWD; Set this to have all output go to the same parent folder, with unique IDs set by --out]
rliterman@0:     outroot = ""
rliterman@0: 
rliterman@0:     // CSP2 can run in the following run-modes:
rliterman@0: 
rliterman@0:     // assemble: Assemble read data (--reads/--ref_reads) into FASTA via SKESA (ignores --fasta/--ref_fasta/--snpdiffs)
rliterman@0:     // align: Given query data (--reads/--fasta) and reference data (--ref_reads/--ref_fasta), run MUMmer alignment analysis for each query/ref combination (ignores --snpdiffs)
rliterman@0:     // screen: Given query data (--reads/--fasta) and reference data (--ref_reads/--ref_fasta) and/or MUMmer output (.snpdiffs), create a report for raw SNP distances between each query and reference assembly
rliterman@0:     // snp: Given query data (--reads/--fasta) and reference data (--ref_reads/--ref_fasta) and/or MUMmer output (.snpdiffs), generate alignments and pairwise distances for all queries based on each reference dataset
rliterman@0:     
rliterman@0:     runmode = ""
rliterman@0: 
rliterman@0:     // Location for isolate sequence data
rliterman@0:     reads = ""
rliterman@0:     fasta = ""
rliterman@0: 
rliterman@0:     // Location for reference sequence data
rliterman@0:     ref_reads = ""
rliterman@0:     ref_fasta = ""
rliterman@0: 
rliterman@0:     // IDs for reference sequences (Comma-separated list)
rliterman@0:     ref_id = ""
rliterman@0: 
rliterman@0:     // Location for snpdiffs files
rliterman@0:     snpdiffs = ""
rliterman@0:     
rliterman@0:     // Read read_info
rliterman@0:     readext = "fastq.gz"
rliterman@0:     forward = "_1.fastq.gz"
rliterman@0:     reverse = "_2.fastq.gz"
rliterman@0: 
rliterman@0:     ref_readext = "fastq.gz"
rliterman@0:     ref_forward = "_1.fastq.gz"
rliterman@0:     ref_reverse = "_2.fastq.gz"
rliterman@0: 
rliterman@0:     // Analytical variables
rliterman@0: 
rliterman@0:     // Only consider queries if the reference genome is covered by at least <min_cov>% [Default: 85]
rliterman@0:     min_cov = 85
rliterman@0: 
rliterman@0:     // Only consider SNPs from contig alignments longer than <min_len> bp [Default: 500]
rliterman@0:     min_len = 500
rliterman@0: 
rliterman@0:     // Only consider SNPs from contig alignments with <min_iden>% identity [Default: 99]
rliterman@0:     min_iden = 99
rliterman@0: 
rliterman@0:     // Remove SNPs that occur within <ref_edge>bp from the end of the reference contig [Default: 150]
rliterman@0:     ref_edge = 150
rliterman@0: 
rliterman@0:     // Remove SNPs that occur within <query_edge>bp from the end of the query contig [Default: 150]
rliterman@0:     query_edge = 150
rliterman@0: 
rliterman@0:     // SNP density filters: Given density windows provided by dwin, purge windows where more than the allowable window SNPs (wsnps) are found
rliterman@0:     // Default: 3 max per 1000bp, 2 max per 125bp, 1 max per 15bp, filtered from biggest window to smallest
rliterman@0:     // Set --dwin 0 to disable density filtering
rliterman@0:     dwin = "1000,125,15"
rliterman@0:     wsnps = "3,2,1"
rliterman@0: 
rliterman@0:     // If running refchooser in snp mode, compare queries to the top X references [Default: 1]
rliterman@0:     n_ref = 1
rliterman@0: 
rliterman@0:     // If the assembly file contains the string <trim_name>, remove it from the sample name (e.g. '_contigs_skesa')
rliterman@0:     trim_name = '""'
rliterman@0: 
rliterman@0:     // If running SNP pipeline, set the maximum percent of isolates with missing data allowed in the final alignment/distances [Default: 50]
rliterman@0:     max_missing = 50
rliterman@0: 
rliterman@0:     // Alternate directory for pybedtools tmp files [Default: "" (system default)]
rliterman@0:     tmp_dir = ""
rliterman@0: 
rliterman@0:     // Set IDs for isolates to exclude from analysis (Comma-separated list)
rliterman@0:     exclude = ""
rliterman@0: 
rliterman@0:     // By default, do not perform edge-filtered SNP rescuing
rliterman@0:     rescue = "norescue"
rliterman@0: 
rliterman@0:     // Help function
rliterman@0:     help = "nohelp"
rliterman@0:     h = "nohelp"
rliterman@0: }