bambu-pipe/nextflow.config at main · GoekeLab/bambu-pipe · 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
manifest {
    name        = 'Bambu-Pipe'
    description = 'Context-aware transcript quantification from long-read single-cell and spatial transcriptomics data'
    author      = 'Andre Sim, Chin Hao Lee, Min Hao Ling'
    version     = 'v0.9-beta'
    mainScript  = 'main.nf'
    nextflowVersion = '!>=26.04.0'
}

params {
    // Mandatory input
    input                   = null                          // Path to samplesheet .csv file
    genome                  = null                          // Path to .fa or .fasta file
    annotation              = null                          // Path to .gtf or .gff file

    // Optional: Output directory
    output_dir              = "output"                      // Path to output directory

    /*
    Optional: Samplesheet settings (Non Visium HD samples only)
    Note: Use this if all samples share the same chemistry/technology
    */
    chemistry               = null                          // Examples: "10x3v2", "10x3v3", "10x5v2", "visium-v1"
    technology              = null                          // Options: "ONT", "PacBio"

    // Optional: Stop after alignment and save BAM files only
    bam_only                = false                         // boolean

    // Optional: Q-score filtering
    qscore_filtering        = true                          // boolean

    // Optional: Bambu parameters
    ndr                     = null                          // null or float
    deduplicate_umis        = true                          // boolean

    // Optional: Quantification mode
    quantification_mode     = "clusteredEM"                 // Options: "no_quant", "EM", "clusteredEM"

    // Optional: Seurat clustering
    seurat_resolution       = 0.8                           // float

    /*
    Optional: Manual clustering
    Note: Set --manual_clustering true to quantify from clusters generated outside the pipeline.
    The samplesheet takes 'clusters_path' and 'quant_data_path' columns instead of the usual ones,
    and --annotation takes the extended_annotations.rds written by the earlier run.
    */
    manual_clustering       = false                         // boolean

    /*
    Optional: Visium HD
    Note: Set --visium_hd true for a single-sample run starting from a pre-aligned, barcode-tagged BAM file.
    The samplesheet only needs 'sample' and 'path' columns — 'chemistry' and 'technology' are not used.
    Counts are produced at 2um and at every resolution listed in the bins samplesheet.
    */
    visium_hd                = false                        // boolean
    bins                     = null                         // CSV samplesheet of resolutions (columns: resolution,tissue_positions); must include a 2 row (native base) plus any bins; required when --visium_hd true
    barcode_mappings         = null                         // Path to barcode_mappings.parquet; required when any bin coarser than 2um is used

    // Optional: Visium HD clustering
    clustering_bin           = 8                            // Integer bin size to cluster at; must be listed in the bins samplesheet
    banksy                   = true                         // boolean; spatially aware clustering
    banksy_lambda            = 0.8                          // float; 0.8 segments tissue domains, 0.2 gives spatially informed cell types
    banksy_k_geom            = 50                           // integer; spatial neighbours per bin

}

includeConfig 'conf/base.config'
includeConfig 'conf/containers.config'
includeConfig 'conf/dev.config'

profiles {
    // Container profiles
	singularity {
        singularity.enabled           = true
        singularity.autoMounts        = true
        docker.enabled                = false
	    singularity.runOptions        = "--bind ${env('PWD')}"
        singularity.envWhitelist      = "JAVA_HOME"
    }

    docker {
        docker.enabled           = true
        singularity.enabled      = false
	    docker.runOptions        = '-u $(id -u):$(id -g)'
    }

    arm {
            docker.runOptions = '-u $(id -u):$(id -g) --platform=linux/amd64'
        }

    hpc {
        process.executor = 'slurm' // Examples: 'slurm', 'pbs', 'sge'
    }

    // For running on a local machine with small samples only.
    // Not recommended for full-size datasets — memory and CPU limits below will likely cause failures.
    local {
        process.executor = 'local'

        process {
            withLabel: 'low_cpu'    { cpus   = 2     }
            withLabel: 'medium_cpu' { cpus   = 8     }
            withLabel: 'high_cpu'   { cpus   = 16    }
            withLabel: 'low_mem'    { memory = '8.GB'  }
            withLabel: 'medium_mem' { memory = '32.GB' }
            withLabel: 'high_mem'   { memory = '64.GB' }
        }
    }

}

includeConfig 'conf/smoke_test.config'

// Output an html timeline report
timeline { enabled = true; file = "${params.output_dir}/pipeline_info/execution_timeline.html" }

// Output resource and runtime reports for a workflow run
report   { enabled = true; file = "${params.output_dir}/pipeline_info/execution_report.html" }

// Output process execution trace file
trace    { enabled = true; file = "${params.output_dir}/pipeline_info/execution_trace.txt" }

// Produce a workflow diagram
dag      { enabled = true; file = "${params.output_dir}/pipeline_info/pipeline_dag.svg" }