EasyFuse/nextflow.config at main · TRON-Bioinformatics/EasyFuse · GitHub

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
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
process {

    // Capture exit codes from upstream processes when piping
    shell = ['/bin/bash', '-euo', 'pipefail']

    // extract from https://github.com/nf-core/sarek/blob/6aeac929c924ba382baa42a0fe969b4e0e753ca9/conf/base.config
    cpus   = { 1    * task.attempt }
    memory = { 6.GB * task.attempt }
    time   = { 4.h  * task.attempt }

    // memory errors which should be retried. otherwise error out
    errorStrategy = { task.exitStatus in ((130..145) + 104) ? 'retry' : 'finish' }
    maxRetries    = 1
    maxErrors     = '-1'

    // Process-specific resource requirements
    // See https://www.nextflow.io/docs/latest/config.html#config-process-selectors
    withLabel:error_ignore {
        errorStrategy = 'ignore'
    }
    withLabel:error_retry {
        errorStrategy = 'retry'
        maxRetries    = 2
    }
    withLabel:process_single {
        cpus   = { 1 }
        memory = { 6.GB * task.attempt }
        time   = { 4.h  * task.attempt }
    }
    withLabel:process_low {
        cpus   = { 2     * task.attempt }
        memory = { 12.GB * task.attempt }
        time   = { 4.h   * task.attempt }
    }
    withLabel:process_medium {
        cpus   = { 6     * task.attempt }
        memory = { 36.GB * task.attempt }
        time   = { 8.h   * task.attempt }
    }
}

profiles {
  conda {
    conda.enabled = true
    timeline.enabled = true
    report.enabled = true
    trace.enabled = true
    dag.enabled = true
  }
  test {
    timeline.enabled = false
    report.enabled = false
    trace.enabled = false
    dag.enabled = false
    process {
        // sets all resources to our CI limits
        withLabel:process_single {
            cpus   = { 1 }
            memory = { 1.GB }
            time   = { 1.h }
        }
        withLabel:process_low {
            cpus   = { 1 }
            memory = { 1.GB }
            time   = { 1.h }
        }
        withLabel:process_medium {
            cpus   = { 1 }
            memory = { 1.GB }
            time   = { 1.h }
        }
    }
  }
}

// Export this variable to prevent local Python libraries from conflicting with those in the container
env {
  PYTHONNOUSERSITE = 1
}

VERSION = '2.0.4'
ENSEMBL_VERSION = '110'


manifest {
  name = 'TRON-Bioinformatics/easyfuse'
  author = 'Patrick Sorn, Jonas Ibn-Salem, Christoph Holsträter, David Weber, Pablo Riesgo-Ferreiro'
  homePage = 'https://github.com/TRON-Bioinformatics/easyfuse'
  description = 'EasyFuse workflow'
  mainScript = 'main.nf'
  defaultBranch = 'main'
  nextflowVersion = '>=20.10, <=24.10.1'
  version = VERSION
  doi = 'https://doi.org/10.1038/s41587-022-01247-9'
}


params.help = false
params.input_files = false
params.output = false

params.reference = false
params.fasta = "${params.reference}/Homo_sapiens.GRCh38.dna.primary_assembly.fa"
params.star_index = "${params.reference}/star_index/"
params.starfusion_index = "${params.reference}/starfusion_index/"
params.fusioncatcher_index = "${params.reference}/fusioncatcher_index/"
params.gtf = "${params.reference}/Homo_sapiens.GRCh38.${ENSEMBL_VERSION}.gtf"
params.annotation_db = "${params.reference}/Homo_sapiens.GRCh38.${ENSEMBL_VERSION}.gff3.db"
params.reference_tsl = "${params.reference}/Homo_sapiens.GRCh38.${ENSEMBL_VERSION}.gtf.tsl"
params.model_pred = "${baseDir}/data/model/Fusion_modeling_FFPE_train_v39.random_forest.model_full_data.EF_full.rds"
params.model_threshold = 0.5


params.help_message = """
EasyFuse workflow v${VERSION}

Usage:
    nextflow run tron-bioinformatics/easyfuse -profile conda --input_files input_files --reference reference_lib --output output_folder

Input:
    * input_files: the path to a tab-separated values file containing in each row the sample name, FASTQ 1 and FASTQ 2 files.
      The input file does not have header!
      Example input file:
      name1	fastq1	fastq2
      name2	fastq1	fastq2

    * reference: path to the reference index bundle

    * output: path to an output folder
    """