Added kallistobustools

.github/workflows/ci.yml

@@ -19,9 +19,14 @@ jobs:
       NXF_ANSI_LOG: false
     strategy:
       matrix:
-        profile: ['test,docker', 'test_kallisto,docker', 'test,docker --aligner star']
+        profile:
+          [
+            "test,docker --aligner alevin",
+            "test,docker --aligner kallisto",
+            "test,docker --aligner star",
+          ]
         # Nextflow versions: check pipeline minimum and current latest
-        nxf_ver: ['20.10.0', '21.03.0-edge']
+        nxf_ver: ["20.10.0", "21.03.0-edge"]
     steps:
       - name: Check out pipeline code
         uses: actions/checkout@v2
@@ -55,4 +60,3 @@ jobs:
         # Remember that you can parallelise this by using strategy.matrix
         run: |
           nextflow run ${GITHUB_WORKSPACE} -profile ${{ matrix.profile }}
-

conf/base.config

@@ -34,7 +34,4 @@ process {
     errorStrategy = 'retry'
     maxRetries    = 2
   }
-  withName:PLASMIDID {
-    errorStrategy = 'ignore'
-  }
 }

conf/modules.config

@@ -39,7 +39,16 @@ params {
             args                = ""
         }
         'star_align' {
-            args                = "--soloType CB_UMI_Simple --readFilesCommand zcat --runDirPerm All_RWX --outWigType bedGraph --twopassMode Basic --outSAMtype BAM SortedByCoordinate"
+            args                = "--readFilesCommand zcat --runDirPerm All_RWX --outWigType bedGraph --twopassMode Basic --outSAMtype BAM SortedByCoordinate"
+        }
+        'kallistobustools_ref' {
+            args                = ""
+        }
+        'kallistobustools_count' {
+            args                = ""
+        }
+        'multiqc_kb' {
+            args                = ""
         }
     }
 }

conf/test.config

@@ -16,12 +16,10 @@ params {
   max_time = 48.h
 
   // Input data
-  input_paths = [
-    ['S10_L001',
-      ['https://github.com/nf-core/test-datasets/raw/scrnaseq/testdata/S10_L001_R1_001.fastq.gz',
-      'https://github.com/nf-core/test-datasets/raw/scrnaseq/testdata/S10_L001_R2_001.fastq.gz']]]
-  fasta = 'https://github.com/nf-core/test-datasets/raw/scrnaseq/reference/GRCm38.p6.genome.chr19.fa'
+  input = 'https://github.com/nf-core/test-datasets/raw/scrnaseq/samplesheet.csv'
+  genome_fasta = 'https://github.com/nf-core/test-datasets/raw/scrnaseq/reference/GRCm38.p6.genome.chr19.fa'
   gtf = 'https://github.com/nf-core/test-datasets/raw/scrnaseq/reference/gencode.vM19.annotation.chr19.gtf'
+  protocol = '10XV2'
   // Ignore `--input` as otherwise the parameter validation will throw an error
   schema_ignore_params = 'genomes,input_paths,input'
 }

lib/NfcoreSchema.groovy

@@ -191,11 +191,11 @@ class NfcoreSchema {
 
     // Remove an element from a JSONArray
     private static JSONArray removeElement(jsonArray, element){
-        def list = []  
+        def list = []
         int len = jsonArray.length()
-        for (int i=0;i<len;i++){ 
+        for (int i=0;i<len;i++){
             list.add(jsonArray.get(i).toString())
-        } 
+        }
         list.remove(element)
         JSONArray jsArray = new JSONArray(list)
         return jsArray
@@ -213,7 +213,7 @@ class NfcoreSchema {
                             // If the param was required, change this
                             if (definition[key].has("required")) {
                                 def cleaned_required = removeElement(definition[key].required, ignore_param)
-                                definition[key].put("required", cleaned_required) 
+                                definition[key].put("required", cleaned_required)
                             }
                         }
                     }
@@ -243,7 +243,7 @@ class NfcoreSchema {
             }
             // Cast Duration to String
             if (p['value'].getClass() == nextflow.util.Duration) {
-                new_params.replace(p.key, p['value'].toString())
+                new_params.replace(p.key, p['value'].toString().replaceFirst(/d(?!\S)/, "day"))
             }
             // Cast LinkedHashMap to String
             if (p['value'].getClass() == LinkedHashMap) {
@@ -482,10 +482,10 @@ class NfcoreSchema {
         }
         workflow_summary['runName']      = workflow.runName
         if (workflow.containerEngine) {
-            workflow_summary['containerEngine'] = "$workflow.containerEngine"
+            workflow_summary['containerEngine'] = workflow.containerEngine
         }
         if (workflow.container) {
-            workflow_summary['container']       = "$workflow.container"
+            workflow_summary['container'] = workflow.container
         }
         workflow_summary['launchDir']    = workflow.launchDir
         workflow_summary['workDir']      = workflow.workDir
@@ -506,17 +506,7 @@ class NfcoreSchema {
                     def params_value = params.get(param)
                     def schema_value = group_params.get(param).default
                     def param_type   = group_params.get(param).type
-                    if (schema_value == null) {
-                        if (param_type == 'boolean') {
-                            schema_value = false
-                        }
-                        if (param_type == 'string') {
-                            schema_value = ''
-                        }
-                        if (param_type == 'integer') {
-                            schema_value = 0
-                        }
-                    } else {
+                    if (schema_value != null) {
                         if (param_type == 'string') {
                             if (schema_value.contains('$projectDir') || schema_value.contains('${projectDir}')) {
                                 def sub_string = schema_value.replace('\$projectDir', '')
@@ -535,8 +525,13 @@ class NfcoreSchema {
                         }
                     }
 
-                    if (params_value != schema_value) {
-                        sub_params.put("$param", params_value)
+                    // We have a default in the schema, and this isn't it
+                    if (schema_value != null && params_value != schema_value) {
+                        sub_params.put(param, params_value)
+                    }
+                    // No default in the schema, and this isn't empty
+                    else if (schema_value == null && params_value != "" && params_value != null && params_value != false) {
+                        sub_params.put(param, params_value)
                     }
                 }
             }
@@ -549,22 +544,23 @@ class NfcoreSchema {
      * Beautify parameters for summary and return as string
      */
     private static String params_summary_log(workflow, params, json_schema) {
+        Map colors = log_colours(params.monochrome_logs)
         String output  = ''
         def params_map = params_summary_map(workflow, params, json_schema)
         def max_chars  = params_max_chars(params_map)
         for (group in params_map.keySet()) {
             def group_params = params_map.get(group)  // This gets the parameters of that particular group
             if (group_params) {
-                output += group + '\n'
+                output += colors.bold + group + colors.reset + '\n'
                 for (param in group_params.keySet()) {
-                    output += "    \u001B[1m" +  param.padRight(max_chars) + ": \u001B[1m" + group_params.get(param) + '\n'
+                    output += "  " + colors.blue + param.padRight(max_chars) + ": " + colors.green +  group_params.get(param) + colors.reset + '\n'
                 }
                 output += '\n'
             }
         }
-        output += "[Only displaying parameters that differ from pipeline default]\n"
         output += dashed_line(params.monochrome_logs)
-        output += '\n\n' + dashed_line(params.monochrome_logs)
+        output += colors.dim + "\n Only displaying parameters that differ from defaults.\n" + colors.reset
+        output += dashed_line(params.monochrome_logs)
         return output
     }
 

lib/Workflow.groovy

@@ -54,4 +54,86 @@ class Workflow {
         yaml_file_text        += "${summary_section}"
         return yaml_file_text
     }
+
+    /*
+    * Format the protocol
+    * Given the protocol paramter (params.protocol) and the aligner (params.aligner),
+    * this function formats the protocol such that it is fit for the respective
+    * subworkflow
+    */
+    static formatProtocol(protocol, aligner) {
+        String new_protocol = protocol
+        String chemistry = ""
+
+        // alevin
+        if (aligner == "alevin") {
+            switch(protocol) {
+                case "10XV1":
+                    new_protocol = "chromium"
+                    chemistry = "V1"
+                    break
+                case "10XV2":
+                    new_protocol = "chromium"
+                    chemistry = "V2"
+                    break
+                case "10XV3":
+                    new_protocol = "chromiumV3"
+                    chemistry = "V3"
+                    break
+                case "dropseq":
+                    new_protocol = "dropseq"
+            }
+        }
+
+        // star
+        else if (aligner == "star") {
+            switch(protocol) {
+                case "10XV1":
+                    new_protocol = "CB_UMI_Simple"
+                    chemistry = "V1"
+                    break
+                case "10XV2":
+                    new_protocol = "CB_UMI_Simple"
+                    chemistry = "V2"
+                    break
+                case "10XV3":
+                    new_protocol = "CB_UMI_Simple"
+                    chemistry = "V3"
+                    break
+                case "dropseq":
+                    new_protocol = "CB_UMI_Simple"
+                    break
+                case "smartseq":
+                    new_protocol = "SmartSeq"
+            }
+        }
+
+        // kallisto bustools
+        else if (aligner = "kallisto" ) {
+            switch(protocol) {
+                case "10XV1":
+                    new_protocol = "10XV1"
+                    chemistry = "V1"
+                    break
+                case "10XV2":
+                    new_protocol = "10XV2"
+                    chemistry = "V2"
+                    break
+                case "10XV3":
+                    new_protocol = "10XV3"
+                    chemistry = "V3"
+                    break
+                case "dropseq":
+                    new_protocol = "DROPSEQ"
+                    break
+                case "smartseq":
+                    new_protocol = "SMARTSEQ"
+            }
+        }
+        else {
+        exit 1, "Aligner not recognized."
+        }
+
+        return [new_protocol, chemistry]
+    }
 }

modules/local/gene_map.nf

@@ -0,0 +1,40 @@
+// Import generic module functions
+include { saveFiles } from './functions'
+
+params.options = [:]
+
+/*
+ * Reformat design file and check validity
+ */
+process GENE_MAP {
+    tag "$gtf"
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:'pipeline_info', publish_id:'') }
+
+    conda (params.enable_conda ? "conda-forge::python=3.8.3" : null)
+    if (workflow.containerEngine == 'singularity' && !params.pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/python:3.8.3"
+    } else {
+        container "quay.io/biocontainers/python:3.8.3"
+    }
+
+    input:
+    path gtf
+
+    output:
+    path "transcripts_to_genes.txt" , emit: gene_map
+
+    script:
+    if("${gtf}".endsWith('.gz')){
+      name = "${gtf.baseName}"
+      unzip = "gunzip -f ${gtf}"
+    } else {
+      unzip = ""
+      name = "${gtf}"
+    }
+    """
+    $unzip
+    cat $name | t2g.py --use_version > transcripts_to_genes.txt
+    """
+}

modules/local/kallistobustools_count.nf

@@ -0,0 +1,56 @@
+// Import generic module functions
+include { initOptions; saveFiles; getSoftwareName } from './functions'
+
+params.options = [:]
+options        = initOptions(params.options)
+
+process KALLISTOBUSTOOLS_COUNT {
+    tag "$meta.id"
+    label 'process_medium'
+    publishDir "${params.outdir}",
+        mode: params.publish_dir_mode,
+        saveAs: { filename -> saveFiles(filename:filename, options:params.options, publish_dir:getSoftwareName(task.process), publish_id:meta.id) }
+
+    conda (params.enable_conda ? "bioconda::kb-python=0.25.1" : null)
+    if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+        container "https://depot.galaxyproject.org/singularity/kb-python:0.25.1--py_0"
+    } else {
+        container "quay.io/biocontainers/kb-python:0.25.1--py_0"
+    }
+
+    input:
+    tuple   val(meta),  path(reads)
+    path    index
+    path    t2g
+    path    t1c
+    path    t2c
+    val     use_t1c
+    val     use_t2c
+    val     workflow
+    val     technology
+
+    output:
+    tuple val(meta), path ("*_kallistobustools_count*") , emit: counts
+    path "*.version.txt"                               , emit: version
+
+    script:
+    def software    = getSoftwareName(task.process)
+    def prefix      = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
+    def cdna        = use_t1c ? "-c1 $t1c" : ''
+    def introns     = use_t2c ? "-c2 $t2c" : ''
+    """
+    kb count \\
+    -t $task.cpus \\
+    -i $index \\
+    -g $t2g \\
+    $cdna \\
+    $introns \\
+    --workflow $workflow \\
+    -x $technology \\
+    $options.args \\
+    -o ${prefix}_kallistobustools_count \\
+    ${reads[0]} ${reads[1]}
+
+    echo \$(kb 2>&1) | sed 's/^kb_python //; s/Usage.*\$//' > ${software}.version.txt
+    """
+}