taxprofiler/conf/test_full.config at 739f5b9c89d8e48ddc0a19a814c4cd82da78a914 · nf-core/taxprofiler · 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
/*
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    Nextflow config file for running full-size tests
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    Defines input files and everything required to run a full size pipeline test.
    Use as follows:
        nextflow run nf-core/taxprofiler -profile test_full,<docker/singularity> --outdir <OUTDIR>
----------------------------------------------------------------------------------------
*/

params {
    config_profile_name                    = 'Full test profile'
    config_profile_description             = 'Full test dataset to check pipeline function'

    // Input data for full size test
    input                                  = params.pipelines_testdata_base_path + 'taxprofiler/samplesheet_full.csv'
    databases                              = params.pipelines_testdata_base_path + 'taxprofiler/database_full_v1.3.csv'

    // Genome references
    hostremoval_reference                  = 'ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/000/819/615/GCA_000819615.1_ViralProj14015/GCA_000819615.1_ViralProj14015_genomic.fna.gz'

    save_preprocessed_reads                = false

    perform_shortread_qc                   = true
    perform_shortread_redundancyestimation = true
    shortread_qc_mergepairs                = true
    perform_shortread_complexityfilter     = false
    save_complexityfiltered_reads          = false

    perform_longread_qc                    = true
    perform_shortread_hostremoval          = true
    perform_longread_hostremoval           = true
    save_hostremoval_index                 = false
    save_hostremoval_bam                   = false
    save_hostremoval_unmapped              = false

    perform_runmerging                     = true
    save_runmerged_reads                   = false

    save_analysis_ready_fastqs             = true

    run_centrifuge                         = true
    centrifuge_save_reads                  = false

    run_diamond                            = true

    run_kaiju                              = true

    run_kraken2                            = true
    kraken2_save_reads                     = false
    kraken2_save_readclassifications       = false
    kraken2_save_minimizers                = false

    run_krakenuniq                         = true
    krakenuniq_save_reads                  = false
    krakenuniq_save_readclassifications    = false

    run_bracken                            = true

    run_malt                               = true
    malt_save_reads                        = false
    malt_generate_megansummary             = true

    run_metaphlan                          = true
    metaphlan_save_samfiles                = true

    run_motus                              = true
    motus_save_mgc_read_counts             = true

    run_ganon                              = true
    ganon_save_readclassifications         = true

    run_kmcp                               = true
    kmcp_save_search                       = true


    run_sylph				                       = true
    sylph_taxonomy                         = params.pipelines_testdata_base_path + 'taxprofiler/data/database/sylph/sylph_taxonomy.tsv.gz'
    run_metacache                          = true
    metacache_abundances                   = true

    run_profile_standardisation            = true
    run_krona                              = true
    run_melon                              = true
}

cleanup = true

process {
    // As estimated by Seqera AI and @edmundmiller in Oct 2025 based on previous test runs on Seqera Platform

    // Minimap2 INDEX - Optimized based on analysis (was 12GB, now 1GB)
    withName: '.*MINIMAP2_INDEX.*' {
        memory        = 1.GB
        errorStrategy = { task.exitStatus in 137..140 ? 'retry' : 'terminate' }
    }

    // Minimap2 ALIGN - Optimized based on analysis (was 72GB, now 8GB)
    withName: '.*MINIMAP2_ALIGN.*' {
        memory        = 8.GB
        errorStrategy = { task.exitStatus in 137..140 ? 'retry' : 'terminate' }
    }

    // === ADDITIONAL FIXED OPTIMIZATIONS ===

    // Kaiju - Extremely consistent usage
    withName: '.*KAIJU_KAIJU.*' {
        memory        = 1.GB
        errorStrategy = { task.exitStatus in 137..140 ? 'retry' : 'terminate' }
    }

    // KRAKEN2 - Very consistent usage
    withName: '.*KRAKEN2_KRAKEN2.*' {
        memory        = 4.GB
        errorStrategy = { task.exitStatus in 137..140 ? 'retry' : 'terminate' }
    }

    // MOTUS - Consistent but higher usage
    withName: '.*MOTUS_PROFILE.*' {
        memory        = 8.GB
        errorStrategy = { task.exitStatus in 137..140 ? 'retry' : 'terminate' }
    }

    // Centrifuge - Very consistent
    withName: '.*CENTRIFUGE_CENTRIFUGE.*' {
        memory        = 2.GB
        errorStrategy = { task.exitStatus in 137..140 ? 'retry' : 'terminate' }
    }

    // FastQC - Conservative optimization
    withName: '.*FASTQC.*' {
        memory        = 4.GB
        errorStrategy = { task.exitStatus in 137..140 ? 'retry' : 'terminate' }
    }
}