split-flow/main.nf at main · RippeLab/split-flow · 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
#!/usr/bin/env nextflow

log.info """\

==========================================================================================
          split-flow - PIPELINE for Droplet-based single-cell data pre-processing
==========================================================================================
split-flow single cell analysis pipeline v1. 2024-03-24.
German Cancer Research Center (DKFZ), Heidelberg - Germany

#### README: Documentation can be found here: ####
https://github.com/RippeLab/split-flow

#### Authors ####
Ezgi Sen <ezgi.sen@dkfz.de>
Mislav Basic <mislav.basic@dkfz.de>
Simon Steiger <s.steiger@dkfz.de>

Possible Modes:
    -Hashed scRNA-seq
    -Multiome (scRNA + scATAC - hashed)
    -CITE-seq (scRNA + surface proteins - hashes)

========================================================================================
========================================================================================


"""
/*
Worklow steps:
    1. Cell Calling & Ambient Molecule Correction on cellranger-multi (CR) output
        # Runs CellBender
        # Gets union barcodes called as plausible cells by CR and CB
        # Pysam converts the CellBender output to be Seurat-readable for downstream analysis

    2. Demultiplexing - Hashing-Based
        # Apply HTODemux on HTO counts using CR counts, save results as a table for barcodes
        # Apply MultiSeqDemux on HTO counts using CR counts, saves results as a table for barcodes

    3. Demultiplexing - SNP-based (Genotype-free approach is taken)
        # cellsnp-lite + vireo using a filtered .VCF file from 1000Genomes
        # souporcell using a filtered .VCF file from 1000Genomes

    4. Doublet Detection
        # scds [cxds_bcds_hybrid()]
        # scDblFinder
        # Amulet (offerred for multiome mode only)

    5. Create seurat and muon objects and annotated barcodes with metaData

    6. Translate Donors: Hash - SNP based donor matching

    7. Visualization & Reporting

    8. Guiding the exploration of the concordance across demultiplexing/doublet detecion methods
*/


nextflow.enable.dsl=2

include{ CELL_CALLING } from "${projectDir}/subworkflows/CELL_CALLING"
include{ DEMULTIPLEXING } from "${projectDir}/subworkflows/DEMULTIPLEXING"
include{ CREATE_OBJECTS } from "${projectDir}/subworkflows/CREATE_OBJECTS"
include{ VISUALIZE } from "${projectDir}/subworkflows/VISUALIZE"


workflow {
    // Create a channel from a (;) separated CSV file: specified with the --pool_file
    //Channel.fromPath(params.pool_file, checkIfExists: true)
    //.splitCsv(header: true, sep: ";")
    //.map { row ->
      //      meta = row.subMap(["sample","sample_no"])
        //    [meta, row.path_cr_raw, row.path_cr_filtered]
        //}
        //.set { input_channel }
    Channel.fromPath(params.pool_file, checkIfExists: true)
    .splitCsv(header: true, sep: ";")
    .map { row ->
        // Create a meta map that includes the sample and sample_no fields
        meta = row.subMap(["sample","sample_no"])
        // Extract the raw and filtered cellranger-multi paths as file objects
        def path_cr_raw = file(row.path_cr_raw)
        def path_cr_filtered = file(row.path_cr_filtered)
        // Return the meta map along with the processed paths
        [meta, path_cr_raw, path_cr_filtered]
    }
    .set { raw_input_channel }
    raw_input_channel.view()

    //input_channel.view()
    //Choose the workflow based on the params.workflow values
    if (params.workflow == "CITE-seq" || params.workflow == "Multiome" || params.workflow == "scRNA-seq") {
        CELL_CALLING(raw_input_channel)
        DEMULTIPLEXING(CELL_CALLING.out)
        CREATE_OBJECTS(DEMULTIPLEXING.out)
        VISUALIZE(CREATE_OBJECTS.out)
    } else {
        log.error "split-flow does not analyze this type of omic input!! Please refer to the documentation at: https://github.com/RippeLab/split-flow for more information regarding the capacities and proper application of split-flow."
        exit 1
    }
}


workflow.onComplete {
println ( workflow.success ? """
    Pipeline execution summary
    ---------------------------
    Completed at: ${workflow.complete}
    Duration    : ${workflow.duration}
    Success     : ${workflow.success}
    workDir     : ${workflow.workDir}
    exit status : ${workflow.exitStatus}
    """ : """
    Failed: ${workflow.errorReport}
    exit status : ${workflow.exitStatus}
    """
)
}