Add FastQC to Optimus and SmartSeq2

library/tasks/FastQC.wdl

@@ -0,0 +1,50 @@
+task FastQC {
+    Array[File] fastq_files
+    File? limits_file
+    Int startRead = 250000
+    Int nRead = 250000
+    String docker = "quay.io/biocontainers/fastqc:0.11.8--1"
+    Int machine_mem_mb = 3850
+    Int disk = 100
+    Int preemptible = 3
+
+    String dollar = "$"
+    parameter_meta {
+        fastq_files: "input fastq files"
+        limits_file: "(optional) limits file to use with fastqc"
+        startRead: "(optional) start fastqc at the nth read of the file"
+        nRead: "(optional) use (at most) n reads for fastqc"
+        docker: "(optional) the docker image containing the runtime environment for this task"
+        disk: "(optional) the amount of disk space (GiB) to provision for this task"
+        preemptible: "(optional) if non-zero, request a pre-emptible instance and allow for this number of preemptions before running the task on a non preemptible machine"
+        machine_mem_mb: "(optional) the amount of memory (MiB) to provision for this task"
+
+    }
+
+    command <<<
+        set -e
+
+        mkdir outputs
+        declare -a fastqs=()
+        for fastq in ${sep=' ' fastq_files}
+        do
+            outname=`basename ${dollar}fastq .fastq.gz`_skip${startRead}_read${nRead}.fastq
+            zcat ${dollar}fastq | head -n ${4*(startRead + nRead)} | tail -n ${4*nRead} > ${dollar}outname
+            fastqs+=(${dollar}outname)
+        done
+
+        fastqc ${dollar}{fastqs[@]} -o outputs ${"--limits " + limits_file}
+    >>>
+
+    runtime {
+        docker: docker
+        memory: "${machine_mem_mb} MiB"
+        disks: "local-disk ${disk} HDD"
+        preemptible: preemptible
+    }
+
+    output {
+        Array[File] fastqc_htmls = glob("outputs/*.html")
+        Array[File] fastqc_zips = glob("outputs/*.zip")
+    }
+}

pipelines/optimus/Optimus.wdl

@@ -11,6 +11,7 @@ import "RunEmptyDrops.wdl" as RunEmptyDrops
 import "ZarrUtils.wdl" as ZarrUtils
 import "Picard.wdl" as Picard
 import "UmiCorrection.wdl" as UmiCorrection
+import "FastQC.wdl" as FastQC
 
 workflow Optimus {
   meta {
@@ -25,6 +26,9 @@ workflow Optimus {
   Array[File]? i1_fastq
   String sample_id
 
+  # fastqc input
+  File? fastqc_limits
+
   # organism reference parameters
   File tar_star_reference
   File annotations_gtf
@@ -51,6 +55,7 @@ workflow Optimus {
     r2_fastq: "reverse read, contains cDNA fragment generated from captured mRNA"
     i1_fastq: "(optional) index read, for demultiplexing of multiple samples on one flow cell."
     sample_id: "name of sample matching this file, inserted into read group header"
+    fastqc_limits: "(optional) limits file for fastqc"
     tar_star_reference: "star genome reference"
     annotations_gtf: "gtf containing annotations for gene tagging (must match star reference)"
     ref_genome_fasta: "genome fasta file (must match star reference)"
@@ -77,6 +82,13 @@ workflow Optimus {
           r2_unmapped_bam = FastqToUBam.bam_output,
           whitelist = whitelist
       }
+
+      call FastQC.FastQC as FastQC {
+        input:
+          fastq_files = [r1_fastq[index], r2_fastq[index], non_optional_i1_fastq[index]],
+          limits_file = fastqc_limits,
+          disk = ceil((size(r1_fastq[index], "GiB") + size(r2_fastq[index], "GiB") + size(non_optional_i1_fastq[index], "GiB")) * 1.2 + 10)
+      }
     }
 
     # if the index is not passed, proceed without it.
@@ -87,6 +99,13 @@ workflow Optimus {
           r2_unmapped_bam = FastqToUBam.bam_output,
           whitelist = whitelist
       }
+
+      call FastQC.FastQC as FastQCNoIndex {
+        input:
+          fastq_files = [r1_fastq[index], r2_fastq[index]],
+          limits_file = fastqc_limits,
+          disk = ceil((size(r1_fastq[index], "GiB") + size(r2_fastq[index], "GiB")) * 1.2 + 10)
+      }
     }
 
     File barcoded_bam = select_first([AttachBarcodes.bam_output, AttachBarcodesNoIndex.bam_output])

pipelines/smartseq2_single_sample/SmartSeq2SingleSample.wdl

@@ -3,6 +3,7 @@ import "Picard.wdl" as Picard
 import "RSEM.wdl" as RSEM
 import "GroupMetricsOutputs.wdl" as GroupQCs
 import "ZarrUtils.wdl" as ZarrUtils
+import "FastQC.wdl" as FastQC
 
 workflow SmartSeq2SingleCell {
   meta {
@@ -28,6 +29,8 @@ workflow SmartSeq2SingleCell {
   String output_name
   File fastq1
   File fastq2
+  # fastqc
+  File? fastqc_limits
   Int max_retries = 0
 
   # whether to convert the outputs to Zarr format, by default it's set to true
@@ -48,12 +51,20 @@ workflow SmartSeq2SingleCell {
     output_name: "Output name, can include path"
     fastq1: "R1 in paired end reads"
     fastq2: "R2 in paired end reads"
+    fastqc_limits: "(optional) limits file for fastqc"
     max_retries: "(optional) retry this number of times if task fails -- use with caution, see skylab README for details"
     output_zarr: "whether to run the taks that converts the outputs to Zarr format, by default it's true"
   }
 
   String quality_control_output_basename = output_name + "_qc"
 
+  call FastQC.FastQC {
+    input:
+      fastq_files = [fastq1, fastq2],
+      limits_file = fastqc_limits,
+      disk = ceil((size(fastq1, "GiB") + size(fastq2, "GiB")) * 1.2 + 10)
+  }
+
   call HISAT2.HISAT2PairedEnd {
     input:
       hisat2_ref = hisat2_ref_index,

test/optimus/pr/dependencies.json

@@ -14,5 +14,6 @@
   "RunEmptyDrops.wdl": "library/tasks/RunEmptyDrops.wdl",
   "ZarrUtils.wdl": "library/tasks/ZarrUtils.wdl",
   "Picard.wdl": "library/tasks/Picard.wdl",
-  "UmiCorrection.wdl": "library/tasks/UmiCorrection.wdl"
+  "UmiCorrection.wdl": "library/tasks/UmiCorrection.wdl",
+  "FastQC.wdl": "library/tasks/FastQC.wdl"
 }

test/optimus/scientific/dependencies.json

@@ -12,5 +12,6 @@
   "SequenceDataWithMoleculeTagMetrics.wdl": "library/tasks/SequenceDataWithMoleculeTagMetrics.wdl",
   "TagSortBam.wdl": "library/tasks/TagSortBam.wdl",
   "Picard.wdl": "library/tasks/Picard.wdl",
-  "UmiCorrection.wdl": "library/tasks/UmiCorrection.wdl"
+  "UmiCorrection.wdl": "library/tasks/UmiCorrection.wdl",
+  "FastQC.wdl": "library/tasks/FastQC.wdl"
 }

test/smartseq2_single_sample/pr/dependencies.json

@@ -5,5 +5,6 @@
   "Picard.wdl": "library/tasks/Picard.wdl",
   "RSEM.wdl": "library/tasks/RSEM.wdl",
   "GroupMetricsOutputs.wdl": "library/tasks/GroupMetricsOutputs.wdl",
-  "ZarrUtils.wdl": "library/tasks/ZarrUtils.wdl"
+  "ZarrUtils.wdl": "library/tasks/ZarrUtils.wdl",
+  "FastQC.wdl": "library/tasks/FastQC.wdl"
 }