nf-core-sarek/conf/test.config at 7b57a97d02777532eeecc6e4497574c036948b76 · ggabernet/nf-core-sarek · 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
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
/*
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    Nextflow config file for running minimal tests
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    Defines input files and everything required to run a fast and simple pipeline test.

    Use as follows:
        nextflow run nf-core/sarek -profile test,<extra_test_profile>,<docker/singularity> --outdir <OUTDIR>
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*/

try {
    includeConfig "https://raw.githubusercontent.com/nf-core/modules/master/tests/config/test_data.config"
} catch (Exception e) {
    System.err.println("WARNING: Could not load nf-core/modules test data config")
}

params {

    config_profile_name        = 'Test profile'
    config_profile_description = 'Minimal test dataset to check pipeline function'

    // Limit resources so that this can run on GitHub Actions
    max_cpus   = 2
    max_memory = '6.5GB'
    max_time   = '8.h'

    // Input data
    input = "${projectDir}/tests/csv/3.0/fastq_single.csv"

    // Small reference genome
    genome            = null
    igenomes_ignore   = true
    dbsnp             = params.test_data['homo_sapiens']['genome']['dbsnp_146_hg38_vcf_gz']
    fasta             = params.test_data['homo_sapiens']['genome']['genome_fasta']
    germline_resource = params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_vcf_gz']
    intervals         = params.test_data['homo_sapiens']['genome']['genome_interval_list']
    known_indels      = params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_vcf_gz']
    snpeff_db         = 'WBcel235.99'
    snpeff_genome     = 'WBcel235'
    vep_cache_version = 104
    vep_genome        = 'WBcel235'
    vep_species       = 'caenorhabditis_elegans'

    // Ignore params that will throw warning through params validation
    schema_ignore_params = "genomes,test_data"
}

profiles {
    annotation {
        params.input               = "${projectDir}/tests/csv/3.0/vcf_single.csv"
        params.step                = 'annotate'
    }
    no_intervals {
        params.no_intervals        = true
    }
    pair {
        params.input               = "${projectDir}/tests/csv/3.0/fastq_pair.csv"
    }
    markduplicates_bam {
        params.input               = "${projectDir}/tests/csv/3.0/mapped_single_bam.csv"
        params.step                = 'markduplicates'
    }
    markduplicates_cram {
        params.input               = "${projectDir}/tests/csv/3.0/mapped_single_cram.csv"
        params.step                = 'markduplicates'
    }
    prepare_recalibration_bam {
        params.input               = "${projectDir}/tests/csv/3.0/mapped_single_bam.csv"
        params.step                = 'prepare_recalibration'
    }
    prepare_recalibration_cram {
        params.input               = "${projectDir}/tests/csv/3.0/mapped_single_cram.csv"
        params.step                = 'prepare_recalibration'
    }
    recalibrate_bam {
        params.input               = "${projectDir}/tests/csv/3.0/prepare_recalibration_single_bam.csv"
        params.step                = 'recalibrate'
    }
    recalibrate_cram {
        params.input               = "${projectDir}/tests/csv/3.0/prepare_recalibration_single_cram.csv"
        params.step                = 'recalibrate'
    }
    save_bam_mapped {
        params.save_bam_mapped     = true
    }
    skip_bqsr {
        params.skip_tools          = "baserecalibrator"
    }
    skip_markduplicates {
        params.skip_tools          = "markduplicates"
    }
    split_fastq {
        params.split_fastq         = 150000
        params.save_split_fastqs   = true
    }
    targeted {
        params.intervals               = params.test_data['homo_sapiens']['genome']['genome_multi_interval_bed']
        params.wes                     = true
        params.nucleotides_per_second  = 20
    }
    tools {
        params.input               = "${projectDir}/tests/csv/3.0/recalibrated.csv"
        params.dbsnp               = params.test_data['homo_sapiens']['genome']['dbsnp_138_hg38_21_vcf_gz']
        params.fasta               = params.test_data['homo_sapiens']['genome']['genome_21_fasta']
        params.germline_resource   = params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz']
        params.intervals           = params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed']
        params.pon                 = params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz']
        params.step                = 'variant_calling'
        params.joint_germline      = true
        params.wes                 = true

        params.nucleotides_per_second = 20
    }
    tools_germline {
        params.input               = "${projectDir}/tests/csv/3.0/recalibrated_germline.csv"
        params.dbsnp               = params.test_data['homo_sapiens']['genome']['dbsnp_138_hg38_21_vcf_gz']
        params.known_indels        = params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz']
        params.fasta               = params.test_data['homo_sapiens']['genome']['genome_21_fasta']
        params.intervals           = params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed']
        params.step                = 'variant_calling'
        params.wes                 = true

        params.nucleotides_per_second = 20
    }
    tools_tumoronly {
        params.input               = "${projectDir}/tests/csv/3.0/recalibrated_tumoronly.csv"
        params.dbsnp               = params.test_data['homo_sapiens']['genome']['dbsnp_138_hg38_21_vcf_gz']
        params.fasta               = params.test_data['homo_sapiens']['genome']['genome_21_fasta']
        params.germline_resource   = params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz']
        params.intervals           = params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed']
        params.pon                 = params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz']
        params.step                = 'variant_calling'
        params.joint_germline      = true
        params.wes                 = true

        params.nucleotides_per_second = 20
    }
    tools_somatic {
        params.input               = "${projectDir}/tests/csv/3.0/recalibrated_somatic.csv"
        params.chr_dir             = params.test_data['homo_sapiens']['genome']['genome_21_chromosomes_dir']
        params.dbsnp               = params.test_data['homo_sapiens']['genome']['dbsnp_138_hg38_21_vcf_gz']
        params.fasta               = params.test_data['homo_sapiens']['genome']['genome_21_fasta']
        params.germline_resource   = params.test_data['homo_sapiens']['genome']['gnomad_r2_1_1_21_vcf_gz']
        params.intervals           = params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed']
        params.pon                 = params.test_data['homo_sapiens']['genome']['mills_and_1000g_indels_21_vcf_gz']
        params.step                = 'variant_calling'
        params.joint_germline      = true
        params.wes                 = true

        params.nucleotides_per_second = 20
    }
    trimming {
        params.clip_r1             = 1
        params.clip_r2             = 1
        params.three_prime_clip_r1 = 1
        params.three_prime_clip_r2 = 1
        params.trim_fastq          = true
    }
    umi {
        params.input               = "${projectDir}/tests/csv/3.0/fastq_umi.csv"
        params.umi_read_structure  = '7M1S+T'
    }
    use_gatk_spark {
        params.use_gatk_spark      = 'baserecalibrator,markduplicates'
    }
    variantcalling_channels {
        params.input               = "${projectDir}/tests/csv/3.0/recalibrated.csv"
        params.fasta               = params.test_data['homo_sapiens']['genome']['genome_21_fasta']
        params.intervals           = params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed']
        params.wes                 = true
        params.step                = 'variant_calling'

        params.nucleotides_per_second = 20
    }
    alignment_to_fastq {
        params.input               = "${projectDir}/tests/csv/3.0/bam_for_remapping.csv"
    }
}