Add validation step

conf/modules.config

@@ -143,10 +143,10 @@ process {
     withName: GLIMPSE_LIGATE {
         ext.prefix = { "${meta.id}_D${meta.depth}_P${meta.panel}" }
     }
-    withName: GLIMPSE_CONCORDANCE {
-        ext.prefix = { "${meta.id}_D${meta.depth}_P${meta.panel}_R${meta.region}" }
+    withName: GLIMPSE2_CONCORDANCE {
+        ext.prefix = { "${meta.id}_D${meta.depth}_P${meta.panel}_R${meta.region.replace(':','_')}" }
     }
     withName: ADD_COLUMNS {
-        ext.prefix = { "${meta.id}_D${meta.depth}_P${meta.panel}_R${meta.region}_SNP" }
+        ext.prefix = { "${meta.id}_D${meta.depth}_P${meta.panel}_R${meta.region.replace(':','_')}_SNP" }
     }
 }

conf/test_sim.config

@@ -11,7 +11,7 @@
 */
 
 params {
-    config_profile_name        = 'Test simulation mode'
+    config_profile_name        = 'Test simulation / imputation / validation mode'
     config_profile_description = 'Minimal test dataset to check pipeline function'
 
     // Limit resources so that this can run on GitHub Actions
@@ -24,8 +24,12 @@ params {
     input_region         = "${projectDir}/tests/csv/region.csv"
     depth                = 1
 
+    // Genome references
+    fasta  = "https://raw.githubusercontent.com/nf-core/test-datasets/phaseimpute/data/reference_genome/21_22/hs38DH.chr21_22.fa"
+    panel  = "${projectDir}/tests/csv/panel.csv"
+    phased = true
     map                  = "${projectDir}/tests/csv/map.csv"
-    fasta                = "https://raw.githubusercontent.com/nf-core/test-datasets/phaseimpute/data/reference_genome/21_22/hs38DH.chr21_22.fa"
 
-    step                 = "simulate"
+    step                 = "all"
+    tools                = "glimpse1"
 }

conf/test_validate.config

@@ -0,0 +1,34 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Defines input files and everything required to run a fast and simple pipeline test.
+
+    Use as follows:
+        nextflow run nf-core/phaseimpute -profile test_validate,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+params {
+    config_profile_name        = 'Test validation mode'
+    config_profile_description = 'Minimal test dataset to check pipeline function'
+
+    // Limit resources so that this can run on GitHub Actions
+    max_cpus   = 2
+    max_memory = '6.GB'
+    max_time   = '6.h'
+
+    // Input data
+    input                = "${projectDir}/tests/csv/sample_sim.csv"
+    input_region         = "${projectDir}/tests/csv/region.csv"
+    depth                = 1
+
+    // Genome references
+    fasta  = "https://raw.githubusercontent.com/nf-core/test-datasets/phaseimpute/data/reference_genome/21_22/hs38DH.chr21_22.fa"
+    panel  = "${projectDir}/tests/csv/panel.csv"
+    phased = true
+    map                  = "${projectDir}/tests/csv/map.csv"
+
+    step                 = "validate"
+}

docs/development.md

@@ -21,6 +21,7 @@
 
 ```bash
 nextflow run main.nf -profile singularity,test --outdir results -resume
+nextflow run main.nf -profile singularity,test_sim --outdir results -resume
 ```
 
 ## Problematic
@@ -39,8 +40,7 @@ All channel need to be identified by a meta map as follow:
 - M : map used
 - T : tool used
 - G : reference genome used (is it needed ?)
-- D : depth
-
+- S : simulation (depth or genotype array)
 ## Open questions
 
 How to use different schema ?

docs/images/metro/txt2image.md

@@ -14,8 +14,9 @@ To use drawio
 drawio --version
 drawio docs/images/metro/MetroMap.xml --export --format png --page-index 0 --output docs/images/metro/MetroMap.png --scale 3
 drawio docs/images/metro/MetroMap.xml --export --format png --layers 0 --page-index 1 --output docs/images/metro/PostProcessing.png --scale 3
-drawio docs/images/metro/MetroMap.xml --export --format png --layers 1 --page-index 1 --output docs/images/metro/Concordance.png --scale 3
+drawio docs/images/metro/MetroMap.xml --export --format png --layers 1 --page-index 1 --output docs/images/metro/Concordance2.png --scale 3
 drawio docs/images/metro/MetroMap.xml --export --format png --layers 2 --page-index 1 --output docs/images/metro/Simulate.png --scale 3
 drawio docs/images/metro/MetroMap.xml --export --format png --layers 3 --page-index 1 --output docs/images/metro/Phase.png --scale 3
 drawio docs/images/metro/MetroMap.xml --export --format png --layers 4 --page-index 1 --output docs/images/metro/PreProcessing.png --scale 3
+drawio docs/images/metro/MetroMap.xml --export --format png --layers 5 --page-index 1 --output docs/images/metro/Concordance.png --scale 3
 ```

main.nf

@@ -42,11 +42,31 @@ workflow NFCORE_PHASEIMPUTE {
     ch_versions // channel: versions of software used
 
     main:
+
+    //
+    // Initialise input channels
+    //
+
+    input_impute         = Channel.empty()
+    input_simulate       = Channel.empty()
+    input_validate       = Channel.empty()
+
+    if (params.step == "impute") {
+        input_impute   = ch_input
+    } else if (params.step == "simulate" || params.step == "all") {
+        input_simulate = ch_input
+    } else if (params.step == "validate") {
+        input_validate = ch_input
+    }
+
+
     //
     // WORKFLOW: Run pipeline
     //
     PHASEIMPUTE (
-        ch_input,
+        input_impute,
+        input_simulate,
+        input_validate,
         ch_fasta,
         ch_panel,
         ch_regions,

modules.json

@@ -53,6 +53,11 @@
                         "git_sha": "7e56daae390ff896b292ddc70823447683a79936",
                         "installed_by": ["vcf_impute_glimpse"]
                     },
+                    "glimpse/concordance": {
+                        "branch": "master",
+                        "git_sha": "7e56daae390ff896b292ddc70823447683a79936",
+                        "installed_by": ["modules"]
+                    },
                     "glimpse/ligate": {
                         "branch": "master",
                         "git_sha": "7e56daae390ff896b292ddc70823447683a79936",
@@ -68,6 +73,11 @@
                         "git_sha": "14ba46490cae3c78ed8e8f48d2c0f8f3be1e7c03",
                         "installed_by": ["multiple_impute_glimpse2"]
                     },
+                    "glimpse2/concordance": {
+                        "branch": "master",
+                        "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",
+                        "installed_by": ["modules"]
+                    },
                     "glimpse2/ligate": {
                         "branch": "master",
                         "git_sha": "ee7fee68281944b002bd27a8ff3f19200b4d3fad",
@@ -83,6 +93,11 @@
                         "git_sha": "fa12139827a18b324bd63fce654818586a8e9cc7",
                         "installed_by": ["multiple_impute_glimpse2"]
                     },
+                    "gunzip": {
+                        "branch": "master",
+                        "git_sha": "3a5fef109d113b4997c9822198664ca5f2716208",
+                        "installed_by": ["modules"]
+                    },
                     "multiqc": {
                         "branch": "master",
                         "git_sha": "b7ebe95761cd389603f9cc0e0dc384c0f663815a",

modules/local/addcolumns/main.nf

@@ -0,0 +1,32 @@
+process ADD_COLUMNS {
+    label 'process_single'
+
+    input:
+    tuple val(meta), path(input)
+
+    output:
+    tuple val(meta), path('*.txt'), emit: txt
+    path "versions.yml", emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    awk '(NR>=2) && (NR<=10)' $input | \\
+    awk 'NR==1{\$(NF+1)="ID"} NR>1{\$(NF+1)="${meta.id}"}1' | \\
+    awk 'NR==1{\$(NF+1)="Region"} NR>1{\$(NF+1)="${meta.region}"}1' | \\
+    awk 'NR==1{\$(NF+1)="Depth"} NR>1{\$(NF+1)="${meta.depth}"}1' | \\
+    awk 'NR==1{\$(NF+1)="GPArray"} NR>1{\$(NF+1)="${meta.gparray}"}1' | \\
+    awk 'NR==1{\$(NF+1)="Tools"} NR>1{\$(NF+1)="${meta.tools}"}1' | \\
+    awk 'NR==1{\$(NF+1)="Panel"} NR>1{\$(NF+1)="${meta.panel}"}1' > \\
+    ${prefix}.txt
+
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        awk: \$(awk --version | head -1 | grep -o -E '([0-9]+.){1,2}[0-9]')
+    END_VERSIONS
+    """
+}

modules/local/concatenate/main.nf

@@ -0,0 +1,25 @@
+process CONCATENATE {
+    label 'process_single'
+
+    input:
+    tuple val(meta), path(input)
+
+    output:
+    tuple val(meta), path('*.txt'), emit: txt
+    path "versions.yml", emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    awk '(NR == 1) || (FNR > 1)' $input > ${prefix}.txt
+
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        awk: \$(awk --version | head -1 | grep -o -E '([0-9]+.){1,2}[0-9]')
+    END_VERSIONS
+    """
+}