comparison CSP2/nextflow.config @ 0:01431fa12065

"planemo upload"
author rliterman
date Mon, 02 Dec 2024 10:40:55 -0500
parents
children 0d775868ee62
comparison
equal deleted inserted replaced
-1:000000000000 0:01431fa12065
1 /*
2 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
3 CSP2 Nextflow config file
4 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
5 Default config options for all compute environments
6 ----------------------------------------------------------------------------------------
7 */
8
9 // Enable conda
10 conda.enabled = true
11
12 // Import profile settings
13 includeConfig "conf/profiles.config"
14
15 // Global default params
16 params {
17
18 // Setting output directory
19
20 // Set name for output folder/file prefixes
21 out = "CSP2_${new java.util.Date().getTime()}"
22
23 // Set output parent directory [Default: CWD; Set this to have all output go to the same parent folder, with unique IDs set by --out]
24 outroot = ""
25
26 // CSP2 can run in the following run-modes:
27
28 // assemble: Assemble read data (--reads/--ref_reads) into FASTA via SKESA (ignores --fasta/--ref_fasta/--snpdiffs)
29 // align: Given query data (--reads/--fasta) and reference data (--ref_reads/--ref_fasta), run MUMmer alignment analysis for each query/ref combination (ignores --snpdiffs)
30 // 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
31 // 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
32
33 runmode = ""
34
35 // Location for isolate sequence data
36 reads = ""
37 fasta = ""
38
39 // Location for reference sequence data
40 ref_reads = ""
41 ref_fasta = ""
42
43 // IDs for reference sequences (Comma-separated list)
44 ref_id = ""
45
46 // Location for snpdiffs files
47 snpdiffs = ""
48
49 // Read read_info
50 readext = "fastq.gz"
51 forward = "_1.fastq.gz"
52 reverse = "_2.fastq.gz"
53
54 ref_readext = "fastq.gz"
55 ref_forward = "_1.fastq.gz"
56 ref_reverse = "_2.fastq.gz"
57
58 // Analytical variables
59
60 // Only consider queries if the reference genome is covered by at least <min_cov>% [Default: 85]
61 min_cov = 85
62
63 // Only consider SNPs from contig alignments longer than <min_len> bp [Default: 500]
64 min_len = 500
65
66 // Only consider SNPs from contig alignments with <min_iden>% identity [Default: 99]
67 min_iden = 99
68
69 // Remove SNPs that occur within <ref_edge>bp from the end of the reference contig [Default: 150]
70 ref_edge = 150
71
72 // Remove SNPs that occur within <query_edge>bp from the end of the query contig [Default: 150]
73 query_edge = 150
74
75 // SNP density filters: Given density windows provided by dwin, purge windows where more than the allowable window SNPs (wsnps) are found
76 // Default: 3 max per 1000bp, 2 max per 125bp, 1 max per 15bp, filtered from biggest window to smallest
77 // Set --dwin 0 to disable density filtering
78 dwin = "1000,125,15"
79 wsnps = "3,2,1"
80
81 // If running refchooser in snp mode, compare queries to the top X references [Default: 1]
82 n_ref = 1
83
84 // If the assembly file contains the string <trim_name>, remove it from the sample name (e.g. '_contigs_skesa')
85 trim_name = '""'
86
87 // If running SNP pipeline, set the maximum percent of isolates with missing data allowed in the final alignment/distances [Default: 50]
88 max_missing = 50
89
90 // Alternate directory for pybedtools tmp files [Default: "" (system default)]
91 tmp_dir = ""
92
93 // Set IDs for isolates to exclude from analysis (Comma-separated list)
94 exclude = ""
95
96 // By default, do not perform edge-filtered SNP rescuing
97 rescue = "norescue"
98
99 // Help function
100 help = "nohelp"
101 h = "nohelp"
102 }