-
Notifications
You must be signed in to change notification settings - Fork 3
/
nextflow.config
107 lines (94 loc) · 4.65 KB
/
nextflow.config
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
/*
* -------------------------------------------------
* TRON-Bioinformatics/tronflow-mutect2 Nextflow config file
* -------------------------------------------------
* Default config options for all environments.
*/
profiles {
conda {
params.enable_conda = true
conda.enabled = true
}
debug { process.beforeScript = 'echo $HOSTNAME' }
ci {
params.memory_mutect2 = "2g"
params.cpus_mutect2 = 1
params.memory_read_orientation = "2g"
params.cpus_read_orientation = 1
params.memory_pileup = "2g"
params.cpus_pileup = 1
params.memory_contamination = "2g"
params.cpus_contamination = 1
params.memory_filter = "2g"
params.cpus_filter = 1
timeline.enabled = false
report.enabled = false
trace.enabled = false
dag.enabled = false
}
test {
params.reference = "$baseDir/test_data/ucsc.hg19.minimal.fasta"
params.intervals = "$baseDir/test_data/intervals.minimal.bed"
params.gnomad = "$baseDir/test_data/gnomad.minimal.vcf.gz"
}
}
// Export this variable to prevent local Python libraries from conflicting with those in the container
env {
PYTHONNOUSERSITE = 1
}
// Capture exit codes from upstream processes when piping
process.shell = ['/bin/bash', '-euo', 'pipefail']
VERSION = '1.8.1'
DOI = 'https://zenodo.org/badge/latestdoi/355860788'
manifest {
name = 'TRON-Bioinformatics/tronflow-mutect2'
author = 'Pablo Riesgo-Ferreiro, Özlem Muslu, Luisa Bresadola'
homePage = 'https://github.com/TRON-Bioinformatics/tronflow-mutect2'
description = 'Mutect2 best practices workflow'
mainScript = 'main.nf'
nextflowVersion = '>=19.10.0'
version = VERSION
doi = DOI
}
params.help_message = """
TronFlow Mutect2 v${VERSION} ${DOI}
Usage:
nextflow run tron-bioinformatics/tronflow-mutect2 -profile conda --input_files input_files [--reference reference.fasta]
This workflow is based on the implementation at /code/iCaM/scripts/mutect2_ID.sh
Input:
* input_files: the path to a tab-separated values file containing in each row the sample name, tumor bam and normal bam
The input file does not have header!
Example input file:
name1 tumor_bam1 normal_bam1
name2 tumor_bam2 normal_bam2
* reference: path to the FASTA genome reference (indexes expected *.fai, *.dict)
Optional input:
* input_name: sample name (alternative to --input_files)
* input_tumor_bam: comma separated list of tumor BAMs (alternative to --input_files)
* input_normal_bam: comma separated list of normal BAMs (alternative to --input_files)
* gnomad: path to the gnomad VCF or other germline resource (recommended). If not provided the contamination will
not be estimated and the filter of common germline variants will be disabled
* pon: path to the panel of normals VCF
* intervals: path to a BED file containing the regions to analyse
* output: the folder where to publish output
* enable_bam_output: outputs a new BAM file with the Mutect2 reassembly of reads (default: false)
* disable_common_germline_filter: disable the use of GnomAD to filter out common variants in the population
from the somatic calls. The GnomAD resource is still required though as this common SNPs are used elsewhere to
calculate the contamination (default: false)
* funcotator: To use Funcotator, supply the path to a database to be used. (can be downloaded from GATK FTP server)
* reference_version_funcotator: version of the reference genome (default: "hg19")
* output_format_funcotator: the output format of Funcotator. Can be VCF or MAF (default: "MAF")
* transcript_selection_mode_funcotator: transcript selection method can be CANONICAL, BEST_EFFECT or ALL. (default: CANONICAL)
* memory_mutect2: the ammount of memory used by mutect2 (default: 16g)
* memory_read_orientation: the ammount of memory used by learn read orientation (default: 16g)
* memory_pileup: the ammount of memory used by pileup (default: 32g)
* memory_contamination: the ammount of memory used by contamination (default: 16g)
* memory_filter: the ammount of memory used by filter (default: 16g)
* memory_funcotator: the ammount of memory used by filter (default: 16g)
* args_filter: optional arguments to the FilterMutectCalls function of GATK (e.g.: "--contamination-estimate 0.4 --min-allele-fraction 0.05 --min-reads-per-strand 1 --unique-alt-read-count 4") (see FilterMutectCalls documentation)
* args_funcotator: optional arguments to Funcotator (e.g. "--remove-filtered-variants true") (see Funcotator documentation)
* args_mutect2: optional arguments to Mutect2 (e.g. "--sites-only-vcf-output") (see Mutect2 documentation)
Output:
* Output VCF/MAF
* Other intermediate files
"""