bam -> cram in CSV

subworkflows/local/markduplicates_csv.nf

@@ -6,18 +6,18 @@
 
 workflow MARKDUPLICATES_CSV {
     take:
-        bam_markduplicates // channel: [mandatory] meta, bam, bai
+        cram_markduplicates // channel: [mandatory] meta, cram, crai
 
     main:
         // Creating csv files to restart from this step
-        bam_markduplicates.collectFile(storeDir: "${params.outdir}/preprocessing/csv") { meta, bam, bai ->
+        cram_markduplicates.collectFile(storeDir: "${params.outdir}/preprocessing/csv") { meta, cram, crai ->
             patient = meta.patient
             sample  = meta.sample
             gender  = meta.gender
             status  = meta.status
-            bam   = "${params.outdir}/preprocessing/${sample}/markduplicates/${sample}.md.bam"
-            bai   = "${params.outdir}/preprocessing/${sample}/markduplicates/${sample}.md.bam.bai"
+            cram   = "${params.outdir}/preprocessing/${sample}/markduplicates/${sample}.md.cram"
+            crai   = "${params.outdir}/preprocessing/${sample}/markduplicates/${sample}.md.cram.crai"
             table = "${params.outdir}/preprocessing/${sample}/recal_table/${sample}.recal.table"
-            ["markduplicates_${sample}.csv", "patient,gender,status,sample,bam,bai,table\n${patient},${gender},${status},${sample},${bam},${bai},${table}\n"]
+            ["markduplicates_${sample}.csv", "patient,gender,status,sample,cram,crai,table\n${patient},${gender},${status},${sample},${cram},${crai},${table}\n"]
         }.collectFile(name: 'markduplicates.csv', keepHeader: true, skip: 1, sort: true, storeDir: "${params.outdir}/preprocessing/csv")
 }

subworkflows/local/prepare_recalibration_csv.nf

@@ -15,8 +15,8 @@ workflow PREPARE_RECALIBRATION_CSV {
             sample  = meta.sample
             gender  = meta.gender
             status  = meta.status
-            bam = "${params.outdir}/preprocessing/${sample}/markduplicates/${sample}.md.bam"
-            bai = "${params.outdir}/preprocessing/${sample}/markduplicates/${sample}.md.bam.bai"
-            ["markduplicates_no_table_${sample}.csv", "patient,gender,status,sample,bam,bai\n${patient},${gender},${status},${sample},${bam},${bai}\n"]
+            cram = "${params.outdir}/preprocessing/${sample}/markduplicates/${sample}.md.cram"
+            crai = "${params.outdir}/preprocessing/${sample}/markduplicates/${sample}.md.cram.crai"
+            ["markduplicates_no_table_${sample}.csv", "patient,gender,status,sample,cram,crai\n${patient},${gender},${status},${sample},${cram},${crai}\n"]
         }.collectFile(name: 'markduplicates_no_table.csv', keepHeader: true, skip: 1, sort: true, storeDir: "${params.outdir}/preprocessing/csv")
 }

subworkflows/local/recalibrate_csv.nf

@@ -6,17 +6,17 @@
 
 workflow RECALIBRATE_CSV {
     take:
-        bam_recalibrated_index // channel: [mandatory] meta, bam, bai
+        cram_recalibrated_index // channel: [mandatory] meta, cram, crai
 
     main:
         // Creating csv files to restart from this step
-        bam_recalibrated_index.collectFile(storeDir: "${params.outdir}/preprocessing/csv") { meta, bam, bai ->
+        cram_recalibrated_index.collectFile(storeDir: "${params.outdir}/preprocessing/csv") { meta, cram, crai ->
             patient = meta.patient
             sample  = meta.sample
             gender  = meta.gender
             status  = meta.status
-            bam = "${params.outdir}/preprocessing/${sample}/recalibrated/${sample}.recal.bam"
-            bai = "${params.outdir}/preprocessing/${sample}/recalibrated/${sample}.recal.bam.bai"
-            ["recalibrated_${sample}.csv", "patient,gender,status,sample,bam,bai\n${patient},${gender},${status},${sample},${bam},${bai}\n"]
+            cram = "${params.outdir}/preprocessing/${sample}/recalibrated/${sample}.recal.cram"
+            crai = "${params.outdir}/preprocessing/${sample}/recalibrated/${sample}.recal.cram.crai"
+            ["recalibrated_${sample}.csv", "patient,gender,status,sample,cram,crai\n${patient},${gender},${status},${sample},${cram},${crai}\n"]
         }.collectFile(name: 'recalibrated.csv', keepHeader: true, skip: 1, sort: true, storeDir: "${params.outdir}/preprocessing/csv")
 }

tests/test_aligner.yml

@@ -10,12 +10,12 @@
     - path: results/preprocessing/1234N/recal_table/1234N.recal.table
     - path: results/preprocessing/1234N/recalibrated/1234N.recal.cram
     - path: results/preprocessing/1234N/recalibrated/1234N.recal.cram.crai
-    # - path: results/preprocessing/csv/markduplicates.csv
-    # - path: results/preprocessing/csv/markduplicates_1234N.csv
-    # - path: results/preprocessing/csv/markduplicates_no_table.csv
-    # - path: results/preprocessing/csv/markduplicates_no_table_1234N.csv
-    # - path: results/preprocessing/csv/recalibrated.csv
-    # - path: results/preprocessing/csv/recalibrated_1234N.csv
+    - path: results/preprocessing/csv/markduplicates.csv
+    - path: results/preprocessing/csv/markduplicates_1234N.csv
+    - path: results/preprocessing/csv/markduplicates_no_table.csv
+    - path: results/preprocessing/csv/markduplicates_no_table_1234N.csv
+    - path: results/preprocessing/csv/recalibrated.csv
+    - path: results/preprocessing/csv/recalibrated_1234N.csv
     - path: results/reports/fastqc/1234N-1234N_M1
     - path: results/reports/fastqc/1234N-1234N_M2
     - path: results/reports/fastqc/1234N-1234N_M4

tests/test_default.yml

@@ -10,12 +10,12 @@
     - path: results/preprocessing/1234N/recal_table/1234N.recal.table
     - path: results/preprocessing/1234N/recalibrated/1234N.recal.cram
     - path: results/preprocessing/1234N/recalibrated/1234N.recal.cram.crai
-    # - path: results/preprocessing/csv/markduplicates.csv
-    # - path: results/preprocessing/csv/markduplicates_1234N.csv
-    # - path: results/preprocessing/csv/markduplicates_no_table.csv
-    # - path: results/preprocessing/csv/markduplicates_no_table_1234N.csv
-    # - path: results/preprocessing/csv/recalibrated.csv
-    # - path: results/preprocessing/csv/recalibrated_1234N.csv
+    - path: results/preprocessing/csv/markduplicates.csv
+    - path: results/preprocessing/csv/markduplicates_1234N.csv
+    - path: results/preprocessing/csv/markduplicates_no_table.csv
+    - path: results/preprocessing/csv/markduplicates_no_table_1234N.csv
+    - path: results/preprocessing/csv/recalibrated.csv
+    - path: results/preprocessing/csv/recalibrated_1234N.csv
     - path: results/reports/fastqc/1234N-1234N_M1
     - path: results/reports/fastqc/1234N-1234N_M2
     - path: results/reports/fastqc/1234N-1234N_M4

tests/test_gatk_spark.yml

@@ -11,12 +11,12 @@
     - path: results/preprocessing/1234N/recal_table/1234N.recal.table
     - path: results/preprocessing/1234N/recalibrated/1234N.recal.cram
     - path: results/preprocessing/1234N/recalibrated/1234N.recal.cram.crai
-    # - path: results/preprocessing/csv/markduplicates.csv
-    # - path: results/preprocessing/csv/markduplicates_1234N.csv
-    # - path: results/preprocessing/csv/markduplicates_no_table.csv
-    # - path: results/preprocessing/csv/markduplicates_no_table_1234N.csv
-    # - path: results/preprocessing/csv/recalibrated.csv
-    # - path: results/preprocessing/csv/recalibrated_1234N.csv
+    - path: results/preprocessing/csv/markduplicates.csv
+    - path: results/preprocessing/csv/markduplicates_1234N.csv
+    - path: results/preprocessing/csv/markduplicates_no_table.csv
+    - path: results/preprocessing/csv/markduplicates_no_table_1234N.csv
+    - path: results/preprocessing/csv/recalibrated.csv
+    - path: results/preprocessing/csv/recalibrated_1234N.csv
     - path: results/reports/fastqc/1234N-1234N_M1
     - path: results/reports/fastqc/1234N-1234N_M2
     - path: results/reports/fastqc/1234N-1234N_M4

tests/test_pair.yml

@@ -15,15 +15,15 @@
     - path: results/preprocessing/9876T/recal_table/9876T.recal.table
     - path: results/preprocessing/9876T/recalibrated/9876T.recal.cram
     - path: results/preprocessing/9876T/recalibrated/9876T.recal.cram.crai
-    # - path: results/preprocessing/csv/markduplicates.csv
-    # - path: results/preprocessing/csv/markduplicates_1234N.csv
-    # - path: results/preprocessing/csv/markduplicates_9876T.csv
-    # - path: results/preprocessing/csv/markduplicates_no_table.csv
-    # - path: results/preprocessing/csv/markduplicates_no_table_1234N.csv
-    # - path: results/preprocessing/csv/markduplicates_no_table_9876T.csv
-    # - path: results/preprocessing/csv/recalibrated.csv
-    # - path: results/preprocessing/csv/recalibrated_1234N.csv
-    # - path: results/preprocessing/csv/recalibrated_9876T.csv
+    - path: results/preprocessing/csv/markduplicates.csv
+    - path: results/preprocessing/csv/markduplicates_1234N.csv
+    - path: results/preprocessing/csv/markduplicates_9876T.csv
+    - path: results/preprocessing/csv/markduplicates_no_table.csv
+    - path: results/preprocessing/csv/markduplicates_no_table_1234N.csv
+    - path: results/preprocessing/csv/markduplicates_no_table_9876T.csv
+    - path: results/preprocessing/csv/recalibrated.csv
+    - path: results/preprocessing/csv/recalibrated_1234N.csv
+    - path: results/preprocessing/csv/recalibrated_9876T.csv
     - path: results/reports/fastqc/1234N-1234N_M1
     - path: results/reports/fastqc/1234N-1234N_M2
     - path: results/reports/fastqc/1234N-1234N_M4

tests/test_targeted.yml

@@ -10,12 +10,12 @@
     - path: results/preprocessing/1234N/recal_table/1234N.recal.table
     - path: results/preprocessing/1234N/recalibrated/1234N.recal.cram
     - path: results/preprocessing/1234N/recalibrated/1234N.recal.cram.crai
-    # - path: results/preprocessing/csv/markduplicates.csv
-    # - path: results/preprocessing/csv/markduplicates_1234N.csv
-    # - path: results/preprocessing/csv/markduplicates_no_table.csv
-    # - path: results/preprocessing/csv/markduplicates_no_table_1234N.csv
-    # - path: results/preprocessing/csv/recalibrated.csv
-    # - path: results/preprocessing/csv/recalibrated_1234N.csv
+    - path: results/preprocessing/csv/markduplicates.csv
+    - path: results/preprocessing/csv/markduplicates_1234N.csv
+    - path: results/preprocessing/csv/markduplicates_no_table.csv
+    - path: results/preprocessing/csv/markduplicates_no_table_1234N.csv
+    - path: results/preprocessing/csv/recalibrated.csv
+    - path: results/preprocessing/csv/recalibrated_1234N.csv
     - path: results/reports/fastqc/1234N-1234N_M1
     - path: results/reports/fastqc/1234N-1234N_M2
     - path: results/reports/fastqc/1234N-1234N_M4

workflows/sarek.nf

@@ -339,13 +339,11 @@ workflow SAREK {
                             'samtools' in params.skip_qc,
                             target_bed)
 
-        // Create CSV to restart from this step
-        // MARKDUPLICATES_CSV(bam_markduplicates)
-        //TODO: Check with Maxime and add this
-        //CRAM_CSV(cram_markduplicates)
-
         cram_markduplicates = QC_MARKDUPLICATES.out.cram
 
+        // Create CSV to restart from this step
+        MARKDUPLICATES_CSV(cram_markduplicates)
+
         qc_reports = qc_reports.mix(QC_MARKDUPLICATES.out.qc)
     }
 
@@ -469,9 +467,7 @@ workflow SAREK {
         }
     }
 
-    if (step == 'mapping') {
-        ch_software_versions = ch_software_versions.mix(FASTQC_TRIMGALORE.out.fastqc_version.first().ifEmpty(null))
-    }
+    if (step == 'mapping') ch_software_versions = ch_software_versions.mix(FASTQC_TRIMGALORE.out.fastqc_version.first().ifEmpty(null))
 
     ch_software_versions
         .map { it -> if (it) [ it.baseName, it ] }
@@ -491,9 +487,7 @@ workflow SAREK {
     ch_multiqc_files = ch_multiqc_files.mix(ch_multiqc_custom_config.collect().ifEmpty([]))
     ch_multiqc_files = ch_multiqc_files.mix(ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml'))
     ch_multiqc_files = ch_multiqc_files.mix(GET_SOFTWARE_VERSIONS.out.yaml.collect())
-    if (step == 'mapping') {
-        ch_multiqc_files = ch_multiqc_files.mix(FASTQC_TRIMGALORE.out.fastqc_zip.collect{it[1]}.ifEmpty([]))
-    }
+    if (step == 'mapping') ch_multiqc_files = ch_multiqc_files.mix(FASTQC_TRIMGALORE.out.fastqc_zip.collect{it[1]}.ifEmpty([]))
 
     MULTIQC(ch_multiqc_files.collect())
     multiqc_report       = MULTIQC.out.report.toList()
@@ -504,13 +498,13 @@ workflow SAREK {
 def extract_csv(csv_file) {
     Channel.from(csv_file).splitCsv(header: true)
     //Retrieves number of lanes by grouping together by patient and sample and counting how many entries there are for this combination
-                        .map{ row -> [[row.patient.toString(), row.sample.toString()], row]}
-                        .groupTuple()
-                        .map{ meta, rows ->
-                            size = rows.size()
-                            return [rows, size]
-                        }.transpose()
-                        .map{ row, numLanes -> //from here do the usual thing for csv parsing
+        .map{ row -> [[row.patient.toString(), row.sample.toString()], row]}
+        .groupTuple()
+        .map{ meta, rows ->
+            size = rows.size()
+            return [rows, size]
+        }.transpose()
+        .map{ row, numLanes -> //from here do the usual thing for csv parsing
         def meta = [:]
 
         meta.numLanes = numLanes.toInteger()
@@ -544,16 +538,16 @@ def extract_csv(csv_file) {
         } else if (row.table) {
         // recalibration
             meta.id   = meta.sample
-            def bam   = file(row.bam,   checkIfExists: true)
-            def bai   = file(row.bai,   checkIfExists: true)
+            def cram  = file(row.cram,  checkIfExists: true)
+            def crai  = file(row.crai,  checkIfExists: true)
             def table = file(row.table, checkIfExists: true)
-            return [meta, bam, bai, table]
-        } else if (row.bam) {
+            return [meta, cram, crai, table]
+        } else if (row.cram) {
         // prepare_recalibration or variant_calling
             meta.id = meta.sample
-            def bam = file(row.bam, checkIfExists: true)
-            def bai = file(row.bai, checkIfExists: true)
-            return [meta, bam, bai]
+            def cram = file(row.cram, checkIfExists: true)
+            def crai = file(row.crai, checkIfExists: true)
+            return [meta, cram, crai]
         } else if (row.vcf) {
         // annotation
             meta.id = meta.sample