MultiSeqDemux

modules/nf-core/multiseqdemux/environment.yml

@@ -0,0 +1,8 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - "conda-forge::r-seurat=5.3.0"
+  - "conda-forge::r-seuratobject=5.1.0"

modules/nf-core/multiseqdemux/main.nf

@@ -0,0 +1,47 @@
+process MULTISEQDEMUX {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'oras://community.wave.seqera.io/library/r-seurat_r-seuratobject:4c5a804804327d29':
+        'community.wave.seqera.io/library/r-seurat_r-seuratobject:b11306d1bdc82827' }"
+
+    input:
+    tuple val(meta), path(seurat_object), val(assay)
+
+    output:
+    tuple val(meta), path("*_params_multiseqdemux.csv")       , emit: params
+    tuple val(meta), path("*_res_multiseqdemux.csv")          , emit: results
+    tuple val(meta), path("*_multiseqdemux.rds")              , emit: rds
+    path "versions.yml"                                       , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    quantile = task.ext.assay ?: "0.7"
+    autoThresh = task.ext.autoThresh ?: "TRUE"
+    maxiter = task.ext.maxiter ?: "5"
+    qrangeFrom = task.ext.qrangeFrom ?: "0.1"
+    qrangeTo = task.ext.qrangeTo ?: "0.9"
+    qrangeBy = task.ext.qrangeBy ?: "0.05"
+    verbose = task.ext.verbose ?: 'TRUE'
+    prefix = task.ext.prefix ?: "${meta.id}"
+
+    template 'MultiSeqDemux.R'
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}_params_multiseqdemux.csv
+    touch ${prefix}_res_multiseqdemux.csv
+    touch ${prefix}_multiseqdemux.rds
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        multiseqdemux: \$(Rscript -e "library(Seurat); cat(as.character(packageVersion('Seurat')))")
+        r-base: \$(Rscript -e "cat(strsplit(R.version[['version.string']], ' ')[[1]][3])")
+    END_VERSIONS
+    """
+}

modules/nf-core/multiseqdemux/meta.yml

@@ -0,0 +1,78 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "multiseqdemux"
+description: Identify singlets, doublets and negative cells from multiplexing experiments. Annotate singlets by tags.
+keywords:
+  - demultiplexing
+  - hashing-based deconvolution
+  - single-cell
+tools:
+  - "multiseqdemux":
+      description: "MULTIseqDemux is the demultiplexing module of Seurat, which demultiplex samples based on data from cell hashing."
+      homepage: "https://satijalab.org/seurat/reference/multiseqdemux"
+      documentation: "https://satijalab.org/seurat/reference/multiseqdemux"
+      tool_dev_url: "https://github.com/satijalab/seurat"
+      doi: "10.1038/s41592-019-0433-8"
+      licence: ["MIT"]
+      identifier: ""
+
+input:
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1' ]`
+    - seurat_object:
+        type: file
+        description: |
+          A `.rds` file containing the seurat object. Assumes that the hash tag oligo (HTO) data has been added and normalized.
+    - assay:
+        type: string
+        description: |
+          Name of the Hashtag assay, usually called "HTO" by default. Use the custom name if the assay has been named differently.
+
+output:
+
+  - params:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1' ]`
+      - "*_params_multiseqdemux.csv":
+          type: file
+          description: The used parameters to call MULTIseqDemux in the R-Script.
+          pattern: "_params_multiseqdemux.csv"
+
+  - results:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1' ]`
+      - "*_res_multiseqdemux.csv":
+          type: file
+          description: Resuls of MULTIseqDemux.
+          pattern: "_res_multiseqdemux.csv"
+
+  - rds:
+      - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. `[ id:'sample1' ]`
+      - "*_multiseqdemux.rds":
+          type: file
+          description: SeuratObject saved as RDS.
+          pattern: "_multiseqdemux.rds"
+
+  - versions:
+      - "versions.yml":
+          type: file
+          description: File containing software versions
+          pattern: "versions.yml"
+
+authors:
+  - "@LuisHeinzlmeier"
+maintainers:
+  - "@LuisHeinzlmeier"

modules/nf-core/multiseqdemux/templates/MultiSeqDemux.R

@@ -0,0 +1,86 @@
+#!/usr/bin/env Rscript
+
+################################################
+################################################
+## USE PARAMETERS FROM NEXTFLOW               ##
+################################################
+################################################
+
+# cast parameters from nextflow
+seuratObj = '$seurat_object'
+options(digits=5)
+quantile = as.double('$quantile')
+autoThresh = as.logical('$autoThresh')
+maxiter = as.integer('$maxiter')
+qrangeFrom = as.double('$qrangeFrom')
+qrangeTo = as.double('$qrangeTo')
+qrangeBy = as.double('$qrangeBy')
+verbose = as.logical('$verbose')
+assay ='$assay'
+prefix = '$prefix'
+
+if (! file.exists(seuratObj)){
+    stop(paste0(seuratObj, ' is not a valid file'))
+}
+
+################################################
+################################################
+## Finish loading libraries                   ##
+################################################
+################################################
+
+library(Seurat)
+
+################################################
+################################################
+## Main Process                               ##
+################################################
+################################################
+
+# Loading Seurat object
+hashtag <- readRDS(seuratObj)
+
+# Demultiplex cells
+if (autoThresh == TRUE) {
+  hashtag <- MULTIseqDemux(hashtag, assay = assay, quantile = quantile, autoThresh = TRUE, maxiter = maxiter, qrange = seq(from = qrangeFrom, to = qrangeTo, by = qrangeBy), verbose = verbose)
+} else {
+  hashtag <- MULTIseqDemux(hashtag, assay = assay, quantile = quantile, verbose = verbose)
+}
+
+################################################
+################################################
+## SAVING RESULTS                             ##
+################################################
+################################################
+
+# create a data frame to save the used parameters in a csv file
+Argument <- c("seuratObjectPath", "quantile", "autoThresh", "maxiter", "qrangeFrom", "qrangeTo", "qrangeBy", "verbose", "assay")
+Value <- c(seuratObj, quantile, autoThresh, maxiter, qrangeFrom, qrangeTo, qrangeBy, verbose, assay)
+params <- data.frame(Argument, Value)
+write.csv(params, paste0(prefix ,"_params_multiseqdemux.csv"))
+
+# save the results from MULTIseqDemux()
+write.csv(hashtag\$MULTI_ID, paste0(prefix , "_res_multiseqdemux.csv"))
+saveRDS(hashtag, file = paste0(prefix ,"_multiseqdemux.rds"))
+
+################################################
+################################################
+## VERSIONS FILE                              ##
+################################################
+################################################
+
+r.version <- paste(R.version[['major']],R.version[['minor']], sep = ".")
+seurat.version <- as.character(packageVersion('Seurat'))
+
+writeLines(
+    c(
+        '"${task.process}":',
+        paste('    r-base:', r.version),
+        paste('    r-seurat:', seurat.version)
+    ),
+'versions.yml')
+
+################################################
+################################################
+################################################
+################################################

modules/nf-core/multiseqdemux/tests/main.nf.test

@@ -0,0 +1,59 @@
+nextflow_process {
+
+    name "Test Process MULTISEQDEMUX"
+    script "../main.nf"
+    process "MULTISEQDEMUX"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "multiseqdemux"
+
+    test("seuratObject - rds") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test'], // meta map
+                    file(params.modules_testdata_base_path + '/genomics/homo_sapiens/10xgenomics/cellranger/hashing_demultiplexing/htodemux.rds', checkIfExists: true),
+                    "HTO"
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+    test("seuratObject - rds - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test'], // meta map
+                    file(params.modules_testdata_base_path + '/genomics/homo_sapiens/10xgenomics/cellranger/hashing_demultiplexing/htodemux.rds', checkIfExists: true),
+                    "HTO"
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+}