From 5abc522612c2f51441b51f517b9f6c25616156e6 Mon Sep 17 00:00:00 2001
From: Christopher Kachulis <ckachuli@broadinstitute.org>
Date: Mon, 13 May 2019 16:52:57 -0400
Subject: [PATCH 01/15] Adding FastQC to optimus and SS2

---
 library/tasks/FastQC.wdl                      | 50 +++++++++++++++++++
 pipelines/optimus/Optimus.wdl                 | 11 ++++
 .../SmartSeq2SingleSample.wdl                 |  6 +++
 3 files changed, 67 insertions(+)
 create mode 100644 library/tasks/FastQC.wdl

diff --git a/library/tasks/FastQC.wdl b/library/tasks/FastQC.wdl
new file mode 100644
index 000000000..15d636751
--- /dev/null
+++ b/library/tasks/FastQC.wdl
@@ -0,0 +1,50 @@
+version 1.0
+
+workflow testFastQC {
+    input {
+        Array[File] fastqs
+    }
+
+    call FastQC {
+        input:
+            fastq_files = fastqs
+    }
+
+}
+
+task FastQC {
+    input {
+        Array[File] fastq_files
+        String docker = "quay.io/biocontainers/fastqc:0.11.8--1"
+        Int machine_mem_mb = 3850
+        Int disk = ceil(size(fastq_files, "Gi") * 2.2)
+        Int preemptible = 3
+    }
+
+    parameter_meta {
+        fastq_files : "input fastq files"
+        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
+        fastqc ~{sep=' ' fastq_files} -o outputs
+    >>>
+
+    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")
+    }
+}
\ No newline at end of file
diff --git a/pipelines/optimus/Optimus.wdl b/pipelines/optimus/Optimus.wdl
index d40f73fb8..87d69beba 100644
--- a/pipelines/optimus/Optimus.wdl
+++ b/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 {
@@ -77,6 +78,11 @@ 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]]
+      }
     }
 
     # if the index is not passed, proceed without it.
@@ -87,6 +93,11 @@ workflow Optimus {
           r2_unmapped_bam = FastqToUBam.bam_output,
           whitelist = whitelist
       }
+
+      call FastQC.FastQC as FastQC {
+        input:
+          fastq_files = [r1_fastq[index], r2_fastq[index]]
+      }
     }
 
     File barcoded_bam = select_first([AttachBarcodes.bam_output, AttachBarcodesNoIndex.bam_output])
diff --git a/pipelines/smartseq2_single_sample/SmartSeq2SingleSample.wdl b/pipelines/smartseq2_single_sample/SmartSeq2SingleSample.wdl
index 8e92aa4b4..4c8cd4c6b 100644
--- a/pipelines/smartseq2_single_sample/SmartSeq2SingleSample.wdl
+++ b/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 {
@@ -54,6 +55,11 @@ workflow SmartSeq2SingleCell {
 
   String quality_control_output_basename = output_name + "_qc"
 
+  call FastQC.FastQC {
+    input:
+      fastq_files = [fastq1, fastq2]
+  }
+
   call HISAT2.HISAT2PairedEnd {
     input:
       hisat2_ref = hisat2_ref_index,

From 6646b3cbd8ad636799c5627572e85993fce2f546 Mon Sep 17 00:00:00 2001
From: Christopher Kachulis <ckachuli@broadinstitute.org>
Date: Mon, 13 May 2019 16:59:39 -0400
Subject: [PATCH 02/15] remove test workflow

---
 library/tasks/FastQC.wdl | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/library/tasks/FastQC.wdl b/library/tasks/FastQC.wdl
index 15d636751..d712e8884 100644
--- a/library/tasks/FastQC.wdl
+++ b/library/tasks/FastQC.wdl
@@ -1,17 +1,5 @@
 version 1.0
 
-workflow testFastQC {
-    input {
-        Array[File] fastqs
-    }
-
-    call FastQC {
-        input:
-            fastq_files = fastqs
-    }
-
-}
-
 task FastQC {
     input {
         Array[File] fastq_files

From 497f2a0263ed5acffe68da7fac8166ab8d659123 Mon Sep 17 00:00:00 2001
From: Christopher Kachulis <ckachuli@broadinstitute.org>
Date: Tue, 14 May 2019 12:44:34 -0400
Subject: [PATCH 03/15] run fastqc on only subset of reads in fastqs

---
 library/tasks/FastQC.wdl                      | 21 ++++++++++++++++---
 pipelines/optimus/Optimus.wdl                 | 10 +++++++--
 .../SmartSeq2SingleSample.wdl                 |  6 +++++-
 3 files changed, 31 insertions(+), 6 deletions(-)

diff --git a/library/tasks/FastQC.wdl b/library/tasks/FastQC.wdl
index d712e8884..e8bdcd81d 100644
--- a/library/tasks/FastQC.wdl
+++ b/library/tasks/FastQC.wdl
@@ -3,6 +3,9 @@ version 1.0
 task FastQC {
     input {
         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 = ceil(size(fastq_files, "Gi") * 2.2)
@@ -10,18 +13,30 @@ task FastQC {
     }
 
     parameter_meta {
-        fastq_files : "input fastq files"
-        docker : "(optional) the docker image containing the runtime environment for this task"
+        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
-        fastqc ~{sep=' ' fastq_files} -o outputs
+        declare -a fastqs=()
+        for fastq in ~{sep=' ' fastq_files}
+        do
+            outname=`basename $fastq .fastq.gz`_skip~{startRead}_read~{nRead}.fastq
+            zcat $fastq | head -n ~{4*(startRead + nRead)} | tail -n ~{4*nRead} > $outname
+            fastqs+=($outname)
+        done
+
+        fastqc ${fastqs[@]} -o outputs ~{"--limits " + limits_file}
     >>>
 
     runtime {
diff --git a/pipelines/optimus/Optimus.wdl b/pipelines/optimus/Optimus.wdl
index 87d69beba..6bb9d790f 100644
--- a/pipelines/optimus/Optimus.wdl
+++ b/pipelines/optimus/Optimus.wdl
@@ -26,6 +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
@@ -52,6 +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)"
@@ -81,7 +85,8 @@ workflow Optimus {
 
       call FastQC.FastQC as FastQC {
         input:
-          fastq_files = [r1_fastq[index], r2_fastq[index], non_optional_i1_fastq[index]]
+          fastq_files = [r1_fastq[index], r2_fastq[index], non_optional_i1_fastq[index]],
+          limits_file = fastqc_limits
       }
     }
 
@@ -96,7 +101,8 @@ workflow Optimus {
 
       call FastQC.FastQC as FastQC {
         input:
-          fastq_files = [r1_fastq[index], r2_fastq[index]]
+          fastq_files = [r1_fastq[index], r2_fastq[index]],
+          limits_file = fastqc_limits
       }
     }
 
diff --git a/pipelines/smartseq2_single_sample/SmartSeq2SingleSample.wdl b/pipelines/smartseq2_single_sample/SmartSeq2SingleSample.wdl
index 4c8cd4c6b..78d473bfc 100644
--- a/pipelines/smartseq2_single_sample/SmartSeq2SingleSample.wdl
+++ b/pipelines/smartseq2_single_sample/SmartSeq2SingleSample.wdl
@@ -29,6 +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
@@ -49,6 +51,7 @@ 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"
   }
@@ -57,7 +60,8 @@ workflow SmartSeq2SingleCell {
 
   call FastQC.FastQC {
     input:
-      fastq_files = [fastq1, fastq2]
+      fastq_files = [fastq1, fastq2],
+      limits_file = fastqc_limits
   }
 
   call HISAT2.HISAT2PairedEnd {

From 6f3bda6f1125a59a35b08fb4f37b5a3a2a4286eb Mon Sep 17 00:00:00 2001
From: Christopher Kachulis <ckachuli@broadinstitute.org>
Date: Tue, 14 May 2019 15:05:50 -0400
Subject: [PATCH 04/15] adding dependencies to fix tests; reverting to draft2

---
 library/tasks/FastQC.wdl                      | 33 +++++++++----------
 pipelines/optimus/Optimus.wdl                 |  8 +++--
 .../SmartSeq2SingleSample.wdl                 |  3 +-
 test/optimus/pr/dependencies.json             |  3 +-
 test/optimus/scientific/dependencies.json     |  3 +-
 .../pr/dependencies.json                      |  3 +-
 6 files changed, 28 insertions(+), 25 deletions(-)

diff --git a/library/tasks/FastQC.wdl b/library/tasks/FastQC.wdl
index e8bdcd81d..4be0fe717 100644
--- a/library/tasks/FastQC.wdl
+++ b/library/tasks/FastQC.wdl
@@ -1,17 +1,14 @@
-version 1.0
-
 task FastQC {
-    input {
-        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 = ceil(size(fastq_files, "Gi") * 2.2)
-        Int preemptible = 3
-    }
-
+    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"
@@ -29,14 +26,14 @@ task FastQC {
 
         mkdir outputs
         declare -a fastqs=()
-        for fastq in ~{sep=' ' fastq_files}
+        for fastq in ${sep=' ' fastq_files}
         do
-            outname=`basename $fastq .fastq.gz`_skip~{startRead}_read~{nRead}.fastq
-            zcat $fastq | head -n ~{4*(startRead + nRead)} | tail -n ~{4*nRead} > $outname
-            fastqs+=($outname)
+            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 ${fastqs[@]} -o outputs ~{"--limits " + limits_file}
+        fastqc ${dollar}{fastqs[@]} -o outputs ${"--limits " + limits_file}
     >>>
 
     runtime {
diff --git a/pipelines/optimus/Optimus.wdl b/pipelines/optimus/Optimus.wdl
index 6bb9d790f..9c34075cc 100644
--- a/pipelines/optimus/Optimus.wdl
+++ b/pipelines/optimus/Optimus.wdl
@@ -86,7 +86,8 @@ workflow Optimus {
       call FastQC.FastQC as FastQC {
         input:
           fastq_files = [r1_fastq[index], r2_fastq[index], non_optional_i1_fastq[index]],
-          limits_file = fastqc_limits
+          limits_file = fastqc_limits,
+          disk = ceil((size(r1_fastq[index], "GiB") + size(r2_fastq[index], "GiB") + size(non_optional_i1_fastq[index], "GiB")) * 2.2)
       }
     }
 
@@ -99,10 +100,11 @@ workflow Optimus {
           whitelist = whitelist
       }
 
-      call FastQC.FastQC as FastQC {
+      call FastQC.FastQC as FastQCNoIndex {
         input:
           fastq_files = [r1_fastq[index], r2_fastq[index]],
-          limits_file = fastqc_limits
+          limits_file = fastqc_limits,
+          disk = ceil((size(r1_fastq[index], "GiB") + size(r2_fastq[index], "GiB")) * 2.2)
       }
     }
 
diff --git a/pipelines/smartseq2_single_sample/SmartSeq2SingleSample.wdl b/pipelines/smartseq2_single_sample/SmartSeq2SingleSample.wdl
index 78d473bfc..8e85e15dd 100644
--- a/pipelines/smartseq2_single_sample/SmartSeq2SingleSample.wdl
+++ b/pipelines/smartseq2_single_sample/SmartSeq2SingleSample.wdl
@@ -61,7 +61,8 @@ workflow SmartSeq2SingleCell {
   call FastQC.FastQC {
     input:
       fastq_files = [fastq1, fastq2],
-      limits_file = fastqc_limits
+      limits_file = fastqc_limits,
+      disk = ceil((size(fastq1, "GiB") + size(fastq2, "GiB")) * 2.2)
   }
 
   call HISAT2.HISAT2PairedEnd {
diff --git a/test/optimus/pr/dependencies.json b/test/optimus/pr/dependencies.json
index e6add7ae1..b99094612 100644
--- a/test/optimus/pr/dependencies.json
+++ b/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"
 }
diff --git a/test/optimus/scientific/dependencies.json b/test/optimus/scientific/dependencies.json
index 15a4b38d4..834f80ec4 100644
--- a/test/optimus/scientific/dependencies.json
+++ b/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"
 }
diff --git a/test/smartseq2_single_sample/pr/dependencies.json b/test/smartseq2_single_sample/pr/dependencies.json
index 2c10e0518..c01f27f4c 100644
--- a/test/smartseq2_single_sample/pr/dependencies.json
+++ b/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"
 }

From 23e57ed096134121bdb2aaf92d8e38bed960e1e9 Mon Sep 17 00:00:00 2001
From: Christopher Kachulis <ckachuli@broadinstitute.org>
Date: Tue, 14 May 2019 15:56:53 -0400
Subject: [PATCH 05/15] adjusting disk size calculations

---
 pipelines/optimus/Optimus.wdl                               | 4 ++--
 pipelines/smartseq2_single_sample/SmartSeq2SingleSample.wdl | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/pipelines/optimus/Optimus.wdl b/pipelines/optimus/Optimus.wdl
index 9c34075cc..726849296 100644
--- a/pipelines/optimus/Optimus.wdl
+++ b/pipelines/optimus/Optimus.wdl
@@ -87,7 +87,7 @@ workflow Optimus {
         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")) * 2.2)
+          disk = ceil((size(r1_fastq[index], "GiB") + size(r2_fastq[index], "GiB") + size(non_optional_i1_fastq[index], "GiB")) * 1.2 + 10)
       }
     }
 
@@ -104,7 +104,7 @@ workflow Optimus {
         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")) * 2.2)
+          disk = ceil((size(r1_fastq[index], "GiB") + size(r2_fastq[index], "GiB")) * 1.2 + 10)
       }
     }
 
diff --git a/pipelines/smartseq2_single_sample/SmartSeq2SingleSample.wdl b/pipelines/smartseq2_single_sample/SmartSeq2SingleSample.wdl
index 8e85e15dd..0c4264674 100644
--- a/pipelines/smartseq2_single_sample/SmartSeq2SingleSample.wdl
+++ b/pipelines/smartseq2_single_sample/SmartSeq2SingleSample.wdl
@@ -62,7 +62,7 @@ workflow SmartSeq2SingleCell {
     input:
       fastq_files = [fastq1, fastq2],
       limits_file = fastqc_limits,
-      disk = ceil((size(fastq1, "GiB") + size(fastq2, "GiB")) * 2.2)
+      disk = ceil((size(fastq1, "GiB") + size(fastq2, "GiB")) * 1.2 + 10)
   }
 
   call HISAT2.HISAT2PairedEnd {

From 2436d2f477fad041bdb1afc2341b301241137fa2 Mon Sep 17 00:00:00 2001
From: Christopher Kachulis <ckachuli@broadinstitute.org>
Date: Wed, 15 May 2019 13:30:09 -0400
Subject: [PATCH 06/15] tests:

---
 pipelines/optimus/Optimus.wdl                 |  4 ++++
 .../SmartSeq2SingleSample.wdl                 |  4 ++++
 test/optimus/pr/ValidateOptimus.wdl           | 18 ++++++++++++++++++
 test/optimus/pr/test_inputs.json              |  6 ++++++
 test/optimus/pr/test_optimus_PR.wdl           |  8 +++++++-
 .../pr/ValidateSmartSeq2SingleCell.wdl        | 19 +++++++++++++++++++
 .../pr/test_inputs.json                       |  4 +++-
 .../pr/test_smartseq2_single_sample_PR.wdl    |  7 ++++++-
 8 files changed, 67 insertions(+), 3 deletions(-)

diff --git a/pipelines/optimus/Optimus.wdl b/pipelines/optimus/Optimus.wdl
index 726849296..7642b5423 100644
--- a/pipelines/optimus/Optimus.wdl
+++ b/pipelines/optimus/Optimus.wdl
@@ -241,5 +241,9 @@ workflow Optimus {
 
       # zarr
       Array[File]? zarr_output_files = OptimusZarrConversion.zarr_output_files
+
+      # fastqc
+      Array[Array[File]] fastqc_htmls = select_first(FastQC.fastqc_htmls,FastQCNoIndex.fastqc_htmls)
+      Array[Array[File]] fastqc_zips = select_first(FastQC.fastqc_zips,FastQCNoIndex.fastqc_zips)
   }
 }
diff --git a/pipelines/smartseq2_single_sample/SmartSeq2SingleSample.wdl b/pipelines/smartseq2_single_sample/SmartSeq2SingleSample.wdl
index 0c4264674..ec4159f63 100644
--- a/pipelines/smartseq2_single_sample/SmartSeq2SingleSample.wdl
+++ b/pipelines/smartseq2_single_sample/SmartSeq2SingleSample.wdl
@@ -160,5 +160,9 @@ workflow SmartSeq2SingleCell {
 
     # zarr
     Array[File]? zarr_output_files = SmartSeq2ZarrConversion.zarr_output_files
+
+    #fastqc
+    Array[File] fastqc_htmls = FastQC.fastqc_htmls
+    Array[File] fastqc_zips = FastQC.fastqc_zips
   }
 }
diff --git a/test/optimus/pr/ValidateOptimus.wdl b/test/optimus/pr/ValidateOptimus.wdl
index 34ed4f321..467dda8d2 100644
--- a/test/optimus/pr/ValidateOptimus.wdl
+++ b/test/optimus/pr/ValidateOptimus.wdl
@@ -3,6 +3,8 @@ task ValidateOptimus {
       File matrix
       File gene_metrics
       File cell_metrics
+      Array[File] fastqc_htmls
+      Array[File] fastqc_zips
 
       Int required_disk = ceil((size(bam, "G") + size(matrix, "G")) * 1.1)
 
@@ -10,6 +12,8 @@ task ValidateOptimus {
       String expected_matrix_hash
       String expected_gene_metric_hash
       String expected_cell_metric_hash
+      Array[String] expected_fastqc_html_hashes
+      Array[String] expected_fastqc_zip_hashes
 
   command <<<
 
@@ -51,6 +55,20 @@ task ValidateOptimus {
       fail=true
     fi
 
+    for hmtl in ${sep=' ' fastqc_htmls}; do
+      hash=$(md5sum $html | awk '{print $1}')
+      if [[ " ${sep=' ' expected_fastqc_html_hashes} " != *" $hash "* ]]; then
+        fail=true
+      fi
+    done
+
+    for zipfile in ${sep=' ' fastqc_zips}; do
+      hash=$(md5sum $zipfile | awk '{print $1}')
+      if [[ " ${sep=' ' expected_fastqc_zip_hashes} " != *" $hash "* ]]; then
+        fail=true
+      fi
+    done
+
     if [ $fail == "true" ]; then exit 1; fi
 
   >>>
diff --git a/test/optimus/pr/test_inputs.json b/test/optimus/pr/test_inputs.json
index 0e33ab9c6..e9d8d811f 100644
--- a/test/optimus/pr/test_inputs.json
+++ b/test/optimus/pr/test_inputs.json
@@ -3,6 +3,12 @@
   "TestOptimusPR.expected_matrix_hash": "aec7a79dc7b85a5d621509a3f4fa2192",
   "TestOptimusPR.expected_cell_metric_hash": "45cc8be253445201b02d102d2d096a0c",
   "TestOptimusPR.expected_gene_metric_hash": "d636671dfcff6ec8068987d0f5780334",
+  "TestOptimusPR.expected_fastqc_html_hashes": ["cb0bbb7d52198c38f2cfa87621c92e31",
+    "6697992484d279d15683b5124ab75554",
+    "26e07b94eaff3a7ea3dcc9a191bd1194"],
+  "TestOptimusPR.expected_fastqc_zip_hashes": ["5fde235436cf1f3b207bc8dba2f1d268",
+    "0f670305b6e5433feb449978ef23e7e4",
+    "75cec13e04808d13a874bea44f439dd5"],
   "TestOptimusPR.r1_fastq": [
     "gs://hca-dcp-mint-test-data/10x/demo/fastqs/pbmc8k_S1_L007_R1_001.fastq.gz",
     "gs://hca-dcp-mint-test-data/10x/demo/fastqs/pbmc8k_S1_L007_R1_001.fastq.gz"
diff --git a/test/optimus/pr/test_optimus_PR.wdl b/test/optimus/pr/test_optimus_PR.wdl
index 4d097694e..4c34470a7 100644
--- a/test/optimus/pr/test_optimus_PR.wdl
+++ b/test/optimus/pr/test_optimus_PR.wdl
@@ -10,6 +10,8 @@ workflow TestOptimusPR {
   String expected_matrix_hash
   String expected_gene_metric_hash
   String expected_cell_metric_hash
+  Array[String] expected_fastqc_html_hashes
+  Array[String] expected_fastqc_zip_hashes
 
   # Optimus inputs
   Array[File] r1_fastq
@@ -40,10 +42,14 @@ workflow TestOptimusPR {
       matrix = target.matrix,
       gene_metrics = target.gene_metrics,
       cell_metrics = target.cell_metrics,
+      fastqc_htmls = flatten(target.fastqc_htmls),
+      fastqc_zips = flatten(target.fastqc_zips),
       expected_bam_hash = expected_bam_hash,
       expected_matrix_hash = expected_matrix_hash,
       expected_cell_metric_hash = expected_cell_metric_hash,
-      expected_gene_metric_hash = expected_gene_metric_hash
+      expected_gene_metric_hash = expected_gene_metric_hash,
+      expected_fastqc_html_hashes = expected_fastqc_html_hashes,
+      expected_fastqc_zip_hashes = expected_fastqc_zip_hashes
   }
 
 }
diff --git a/test/smartseq2_single_sample/pr/ValidateSmartSeq2SingleCell.wdl b/test/smartseq2_single_sample/pr/ValidateSmartSeq2SingleCell.wdl
index 4f0244148..ff721c914 100644
--- a/test/smartseq2_single_sample/pr/ValidateSmartSeq2SingleCell.wdl
+++ b/test/smartseq2_single_sample/pr/ValidateSmartSeq2SingleCell.wdl
@@ -5,6 +5,11 @@ task ValidateSmartSeq2SingleCell {
       File target_metrics
       String expected_metrics_hash
 
+      Array[File] fastqc_zips
+      Array[File] fastqc_htmls
+      Array[String] expected_fastqc_zip_hashes
+      Array[String] expected_fastqc_html_hashes
+
   command <<<
 
     # catch intermittent failures
@@ -28,6 +33,20 @@ task ValidateSmartSeq2SingleCell {
       fail=true
     fi
 
+    for hmtl in ${sep=' ' fastqc_htmls}; do
+          hash=$(md5sum $html | awk '{print $1}')
+          if [[ " ${sep=' ' expected_fastqc_html_hashes} " != *" $hash "* ]]; then
+            fail=true
+          fi
+        done
+
+    for zipfile in ${sep=' ' fastqc_zips}; do
+      hash=$(md5sum $zipfile | awk '{print $1}')
+      if [[ " ${sep=' ' expected_fastqc_zip_hashes} " != *" $hash "* ]]; then
+        fail=true
+      fi
+    done
+
     if [ $fail == "true" ]; then exit 1; fi
 
   >>>
diff --git a/test/smartseq2_single_sample/pr/test_inputs.json b/test/smartseq2_single_sample/pr/test_inputs.json
index b28535cba..d689cf26b 100644
--- a/test/smartseq2_single_sample/pr/test_inputs.json
+++ b/test/smartseq2_single_sample/pr/test_inputs.json
@@ -14,5 +14,7 @@
   "TestSmartSeq2SingleCellPR.sample_name":"SRR1294925",
   "TestSmartSeq2SingleCellPR.output_name":"SRR1294925",
   "TestSmartSeq2SingleCellPR.expected_counts_hash": "135a3fbb959583db17713dc8b9d7fe33",
-  "TestSmartSeq2SingleCellPR.expected_metrics_hash": "99bd9903ac8dc77eb1c047ffa8eb42ed"
+  "TestSmartSeq2SingleCellPR.expected_metrics_hash": "99bd9903ac8dc77eb1c047ffa8eb42ed",
+  "TestSmartSeq2SingleCellPR.expected_fastqc_zip_hashes": ["2080c23507ce431aab4491f8aecfff39","7ad3130042307ca8db85e228e1a30f77"],
+  "TestSmartSeq2SingleCellPR.expected_fastqc_html_hashes": ["7e126084d99342c7dd78e7b80429d9f3","26934543205d10a70488ba7920557e42"]
 }
diff --git a/test/smartseq2_single_sample/pr/test_smartseq2_single_sample_PR.wdl b/test/smartseq2_single_sample/pr/test_smartseq2_single_sample_PR.wdl
index 75b7826f8..e3f29fb38 100644
--- a/test/smartseq2_single_sample/pr/test_smartseq2_single_sample_PR.wdl
+++ b/test/smartseq2_single_sample/pr/test_smartseq2_single_sample_PR.wdl
@@ -23,6 +23,8 @@ workflow TestSmartSeq2SingleCellPR {
   String output_name
   File fastq1
   File fastq2
+  Array[String] expected_fastqc_zip_hashes
+  Array[String] expected_fastqc_html_hashes
 
   call target_wdl.SmartSeq2SingleCell as target_workflow {
     input:
@@ -47,7 +49,10 @@ workflow TestSmartSeq2SingleCellPR {
      counts = target_workflow.rsem_gene_results,
      expected_counts_hash = expected_counts_hash,
      target_metrics = target_workflow.insert_size_metrics,
-     expected_metrics_hash = expected_metrics_hash
+     expected_metrics_hash = expected_metrics_hash,
+     fastqc_htmls = flatten(target_workflow.fastqc_htmls),
+     fastqc_zips = flatten(target_workflow.fastqc_zips),
+
   }
 
 }

From 0905e0458b6d0a6fbc196321d67bb62e79e2acce Mon Sep 17 00:00:00 2001
From: Christopher Kachulis <ckachuli@broadinstitute.org>
Date: Wed, 15 May 2019 13:43:17 -0400
Subject: [PATCH 07/15] fixing tests

---
 pipelines/optimus/Optimus.wdl                                | 4 ++--
 .../pr/test_smartseq2_single_sample_PR.wdl                   | 5 ++---
 2 files changed, 4 insertions(+), 5 deletions(-)

diff --git a/pipelines/optimus/Optimus.wdl b/pipelines/optimus/Optimus.wdl
index 7642b5423..eb5dbcc42 100644
--- a/pipelines/optimus/Optimus.wdl
+++ b/pipelines/optimus/Optimus.wdl
@@ -243,7 +243,7 @@ workflow Optimus {
       Array[File]? zarr_output_files = OptimusZarrConversion.zarr_output_files
 
       # fastqc
-      Array[Array[File]] fastqc_htmls = select_first(FastQC.fastqc_htmls,FastQCNoIndex.fastqc_htmls)
-      Array[Array[File]] fastqc_zips = select_first(FastQC.fastqc_zips,FastQCNoIndex.fastqc_zips)
+      Array[Array[File]] fastqc_htmls = select_first([FastQC.fastqc_htmls,FastQCNoIndex.fastqc_htmls])
+      Array[Array[File]] fastqc_zips = select_first([FastQC.fastqc_zips,FastQCNoIndex.fastqc_zips])
   }
 }
diff --git a/test/smartseq2_single_sample/pr/test_smartseq2_single_sample_PR.wdl b/test/smartseq2_single_sample/pr/test_smartseq2_single_sample_PR.wdl
index e3f29fb38..ba553a42e 100644
--- a/test/smartseq2_single_sample/pr/test_smartseq2_single_sample_PR.wdl
+++ b/test/smartseq2_single_sample/pr/test_smartseq2_single_sample_PR.wdl
@@ -50,9 +50,8 @@ workflow TestSmartSeq2SingleCellPR {
      expected_counts_hash = expected_counts_hash,
      target_metrics = target_workflow.insert_size_metrics,
      expected_metrics_hash = expected_metrics_hash,
-     fastqc_htmls = flatten(target_workflow.fastqc_htmls),
-     fastqc_zips = flatten(target_workflow.fastqc_zips),
-
+     fastqc_htmls = target_workflow.fastqc_htmls,
+     fastqc_zips = target_workflow.fastqc_zips
   }
 
 }

From 5adc1a62eba426be8c0b61d9d49de73a9cf3ceea Mon Sep 17 00:00:00 2001
From: Christopher Kachulis <ckachuli@broadinstitute.org>
Date: Wed, 15 May 2019 13:59:25 -0400
Subject: [PATCH 08/15] fixing tests

---
 pipelines/optimus/Optimus.wdl                               | 6 ++++--
 .../pr/test_smartseq2_single_sample_PR.wdl                  | 4 +++-
 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/pipelines/optimus/Optimus.wdl b/pipelines/optimus/Optimus.wdl
index eb5dbcc42..8490bedb7 100644
--- a/pipelines/optimus/Optimus.wdl
+++ b/pipelines/optimus/Optimus.wdl
@@ -109,6 +109,8 @@ workflow Optimus {
     }
 
     File barcoded_bam = select_first([AttachBarcodes.bam_output, AttachBarcodesNoIndex.bam_output])
+    Array[File] fastqc_output_htmls = select_first([FastQC.fastqc_htmls,FastQCNoIndex.fastqc_htmls])
+    Array[File] fastqc_output_zips = select_first([FastQC.fastqc_zips,FastQCNoIndex.fastqc_zips])
   }
 
   call Merge.MergeSortBamFiles as MergeUnsorted {
@@ -243,7 +245,7 @@ workflow Optimus {
       Array[File]? zarr_output_files = OptimusZarrConversion.zarr_output_files
 
       # fastqc
-      Array[Array[File]] fastqc_htmls = select_first([FastQC.fastqc_htmls,FastQCNoIndex.fastqc_htmls])
-      Array[Array[File]] fastqc_zips = select_first([FastQC.fastqc_zips,FastQCNoIndex.fastqc_zips])
+      Array[Array[File]] fastqc_htmls = fastqc_output_htmls
+      Array[Array[File]] fastqc_zips = fastqc_output_zips
   }
 }
diff --git a/test/smartseq2_single_sample/pr/test_smartseq2_single_sample_PR.wdl b/test/smartseq2_single_sample/pr/test_smartseq2_single_sample_PR.wdl
index ba553a42e..bf00ce994 100644
--- a/test/smartseq2_single_sample/pr/test_smartseq2_single_sample_PR.wdl
+++ b/test/smartseq2_single_sample/pr/test_smartseq2_single_sample_PR.wdl
@@ -51,7 +51,9 @@ workflow TestSmartSeq2SingleCellPR {
      target_metrics = target_workflow.insert_size_metrics,
      expected_metrics_hash = expected_metrics_hash,
      fastqc_htmls = target_workflow.fastqc_htmls,
-     fastqc_zips = target_workflow.fastqc_zips
+     fastqc_zips = target_workflow.fastqc_zips,
+     expected_fastqc_zip_hashes = expected_fastqc_zip_hashes,
+     expected_fastqc_html_hashes = expected_fastqc_html_hashes
   }
 
 }

From e8669094806e723ef457e0c2bc4f8a765d2b3c37 Mon Sep 17 00:00:00 2001
From: Christopher Kachulis <ckachuli@broadinstitute.org>
Date: Wed, 15 May 2019 14:41:35 -0400
Subject: [PATCH 09/15] tests

---
 test/optimus/pr/ValidateOptimus.wdl | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/test/optimus/pr/ValidateOptimus.wdl b/test/optimus/pr/ValidateOptimus.wdl
index 467dda8d2..8c17aea34 100644
--- a/test/optimus/pr/ValidateOptimus.wdl
+++ b/test/optimus/pr/ValidateOptimus.wdl
@@ -58,6 +58,7 @@ task ValidateOptimus {
     for hmtl in ${sep=' ' fastqc_htmls}; do
       hash=$(md5sum $html | awk '{print $1}')
       if [[ " ${sep=' ' expected_fastqc_html_hashes} " != *" $hash "* ]]; then
+        >&2 echo "fastq_html_hash ($hash) did not match expected hash (${expected_fastqc_html_hashes})"
         fail=true
       fi
     done
@@ -65,6 +66,7 @@ task ValidateOptimus {
     for zipfile in ${sep=' ' fastqc_zips}; do
       hash=$(md5sum $zipfile | awk '{print $1}')
       if [[ " ${sep=' ' expected_fastqc_zip_hashes} " != *" $hash "* ]]; then
+        >&2 echo "fastq_zip_hash ($hash) did not match expected hash (${expected_fastqc_zip_hashes})"
         fail=true
       fi
     done

From 78b4ef324d896eb4b95dd76bfb4344f9d31e9936 Mon Sep 17 00:00:00 2001
From: Christopher Kachulis <ckachuli@broadinstitute.org>
Date: Wed, 15 May 2019 16:24:16 -0400
Subject: [PATCH 10/15] tests

---
 test/optimus/pr/ValidateOptimus.wdl                       | 8 ++++----
 test/optimus/pr/test_inputs.json                          | 6 +++---
 .../pr/ValidateSmartSeq2SingleCell.wdl                    | 4 ++--
 3 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/test/optimus/pr/ValidateOptimus.wdl b/test/optimus/pr/ValidateOptimus.wdl
index 8c17aea34..2545a2eea 100644
--- a/test/optimus/pr/ValidateOptimus.wdl
+++ b/test/optimus/pr/ValidateOptimus.wdl
@@ -55,10 +55,10 @@ task ValidateOptimus {
       fail=true
     fi
 
-    for hmtl in ${sep=' ' fastqc_htmls}; do
-      hash=$(md5sum $html | awk '{print $1}')
+    for htmlfile in ${sep=' ' fastqc_htmls}; do
+      hash=$(md5sum $htmlfile | awk '{print $1}')
       if [[ " ${sep=' ' expected_fastqc_html_hashes} " != *" $hash "* ]]; then
-        >&2 echo "fastq_html_hash ($hash) did not match expected hash (${expected_fastqc_html_hashes})"
+        >&2 echo "fastq_html_hash ($hash) did not match expected hash (${sep=' ' expected_fastqc_html_hashes})"
         fail=true
       fi
     done
@@ -66,7 +66,7 @@ task ValidateOptimus {
     for zipfile in ${sep=' ' fastqc_zips}; do
       hash=$(md5sum $zipfile | awk '{print $1}')
       if [[ " ${sep=' ' expected_fastqc_zip_hashes} " != *" $hash "* ]]; then
-        >&2 echo "fastq_zip_hash ($hash) did not match expected hash (${expected_fastqc_zip_hashes})"
+        >&2 echo "fastq_zip_hash ($hash) did not match expected hash (${sep=' ' expected_fastqc_zip_hashes})"
         fail=true
       fi
     done
diff --git a/test/optimus/pr/test_inputs.json b/test/optimus/pr/test_inputs.json
index e9d8d811f..61a82d7a9 100644
--- a/test/optimus/pr/test_inputs.json
+++ b/test/optimus/pr/test_inputs.json
@@ -6,9 +6,9 @@
   "TestOptimusPR.expected_fastqc_html_hashes": ["cb0bbb7d52198c38f2cfa87621c92e31",
     "6697992484d279d15683b5124ab75554",
     "26e07b94eaff3a7ea3dcc9a191bd1194"],
-  "TestOptimusPR.expected_fastqc_zip_hashes": ["5fde235436cf1f3b207bc8dba2f1d268",
-    "0f670305b6e5433feb449978ef23e7e4",
-    "75cec13e04808d13a874bea44f439dd5"],
+  "TestOptimusPR.expected_fastqc_zip_hashes": ["5e26169ee4d626328146065e192a966f",
+    "df5188daf7bb40e2915caca6213e3585",
+    "b11a50d4b0945fe6c49a84dbe3181aea"],
   "TestOptimusPR.r1_fastq": [
     "gs://hca-dcp-mint-test-data/10x/demo/fastqs/pbmc8k_S1_L007_R1_001.fastq.gz",
     "gs://hca-dcp-mint-test-data/10x/demo/fastqs/pbmc8k_S1_L007_R1_001.fastq.gz"
diff --git a/test/smartseq2_single_sample/pr/ValidateSmartSeq2SingleCell.wdl b/test/smartseq2_single_sample/pr/ValidateSmartSeq2SingleCell.wdl
index ff721c914..85a22c0bf 100644
--- a/test/smartseq2_single_sample/pr/ValidateSmartSeq2SingleCell.wdl
+++ b/test/smartseq2_single_sample/pr/ValidateSmartSeq2SingleCell.wdl
@@ -33,8 +33,8 @@ task ValidateSmartSeq2SingleCell {
       fail=true
     fi
 
-    for hmtl in ${sep=' ' fastqc_htmls}; do
-          hash=$(md5sum $html | awk '{print $1}')
+    for htmlfile in ${sep=' ' fastqc_htmls}; do
+          hash=$(md5sum $htmlfile | awk '{print $1}')
           if [[ " ${sep=' ' expected_fastqc_html_hashes} " != *" $hash "* ]]; then
             fail=true
           fi

From b2965330cd4dcd8122cf83bfdea088cca4a174da Mon Sep 17 00:00:00 2001
From: Christopher Kachulis <ckachuli@broadinstitute.org>
Date: Wed, 15 May 2019 17:50:27 -0400
Subject: [PATCH 11/15] tests should now pass...

---
 test/optimus/pr/ValidateOptimus.wdl                   | 11 -----------
 test/optimus/pr/test_inputs.json                      |  3 ---
 test/optimus/pr/test_optimus_PR.wdl                   |  5 +----
 .../pr/ValidateSmartSeq2SingleCell.wdl                | 10 +---------
 test/smartseq2_single_sample/pr/test_inputs.json      |  3 +--
 .../pr/test_smartseq2_single_sample_PR.wdl            |  3 ---
 6 files changed, 3 insertions(+), 32 deletions(-)

diff --git a/test/optimus/pr/ValidateOptimus.wdl b/test/optimus/pr/ValidateOptimus.wdl
index 2545a2eea..79b757b15 100644
--- a/test/optimus/pr/ValidateOptimus.wdl
+++ b/test/optimus/pr/ValidateOptimus.wdl
@@ -4,8 +4,6 @@ task ValidateOptimus {
       File gene_metrics
       File cell_metrics
       Array[File] fastqc_htmls
-      Array[File] fastqc_zips
-
       Int required_disk = ceil((size(bam, "G") + size(matrix, "G")) * 1.1)
 
       String expected_bam_hash
@@ -13,7 +11,6 @@ task ValidateOptimus {
       String expected_gene_metric_hash
       String expected_cell_metric_hash
       Array[String] expected_fastqc_html_hashes
-      Array[String] expected_fastqc_zip_hashes
 
   command <<<
 
@@ -63,14 +60,6 @@ task ValidateOptimus {
       fi
     done
 
-    for zipfile in ${sep=' ' fastqc_zips}; do
-      hash=$(md5sum $zipfile | awk '{print $1}')
-      if [[ " ${sep=' ' expected_fastqc_zip_hashes} " != *" $hash "* ]]; then
-        >&2 echo "fastq_zip_hash ($hash) did not match expected hash (${sep=' ' expected_fastqc_zip_hashes})"
-        fail=true
-      fi
-    done
-
     if [ $fail == "true" ]; then exit 1; fi
 
   >>>
diff --git a/test/optimus/pr/test_inputs.json b/test/optimus/pr/test_inputs.json
index 61a82d7a9..fd8f4569f 100644
--- a/test/optimus/pr/test_inputs.json
+++ b/test/optimus/pr/test_inputs.json
@@ -6,9 +6,6 @@
   "TestOptimusPR.expected_fastqc_html_hashes": ["cb0bbb7d52198c38f2cfa87621c92e31",
     "6697992484d279d15683b5124ab75554",
     "26e07b94eaff3a7ea3dcc9a191bd1194"],
-  "TestOptimusPR.expected_fastqc_zip_hashes": ["5e26169ee4d626328146065e192a966f",
-    "df5188daf7bb40e2915caca6213e3585",
-    "b11a50d4b0945fe6c49a84dbe3181aea"],
   "TestOptimusPR.r1_fastq": [
     "gs://hca-dcp-mint-test-data/10x/demo/fastqs/pbmc8k_S1_L007_R1_001.fastq.gz",
     "gs://hca-dcp-mint-test-data/10x/demo/fastqs/pbmc8k_S1_L007_R1_001.fastq.gz"
diff --git a/test/optimus/pr/test_optimus_PR.wdl b/test/optimus/pr/test_optimus_PR.wdl
index 4c34470a7..a5a34f27e 100644
--- a/test/optimus/pr/test_optimus_PR.wdl
+++ b/test/optimus/pr/test_optimus_PR.wdl
@@ -11,7 +11,6 @@ workflow TestOptimusPR {
   String expected_gene_metric_hash
   String expected_cell_metric_hash
   Array[String] expected_fastqc_html_hashes
-  Array[String] expected_fastqc_zip_hashes
 
   # Optimus inputs
   Array[File] r1_fastq
@@ -43,13 +42,11 @@ workflow TestOptimusPR {
       gene_metrics = target.gene_metrics,
       cell_metrics = target.cell_metrics,
       fastqc_htmls = flatten(target.fastqc_htmls),
-      fastqc_zips = flatten(target.fastqc_zips),
       expected_bam_hash = expected_bam_hash,
       expected_matrix_hash = expected_matrix_hash,
       expected_cell_metric_hash = expected_cell_metric_hash,
       expected_gene_metric_hash = expected_gene_metric_hash,
-      expected_fastqc_html_hashes = expected_fastqc_html_hashes,
-      expected_fastqc_zip_hashes = expected_fastqc_zip_hashes
+      expected_fastqc_html_hashes = expected_fastqc_html_hashes
   }
 
 }
diff --git a/test/smartseq2_single_sample/pr/ValidateSmartSeq2SingleCell.wdl b/test/smartseq2_single_sample/pr/ValidateSmartSeq2SingleCell.wdl
index 85a22c0bf..6e8e8a92a 100644
--- a/test/smartseq2_single_sample/pr/ValidateSmartSeq2SingleCell.wdl
+++ b/test/smartseq2_single_sample/pr/ValidateSmartSeq2SingleCell.wdl
@@ -5,9 +5,7 @@ task ValidateSmartSeq2SingleCell {
       File target_metrics
       String expected_metrics_hash
 
-      Array[File] fastqc_zips
       Array[File] fastqc_htmls
-      Array[String] expected_fastqc_zip_hashes
       Array[String] expected_fastqc_html_hashes
 
   command <<<
@@ -36,17 +34,11 @@ task ValidateSmartSeq2SingleCell {
     for htmlfile in ${sep=' ' fastqc_htmls}; do
           hash=$(md5sum $htmlfile | awk '{print $1}')
           if [[ " ${sep=' ' expected_fastqc_html_hashes} " != *" $hash "* ]]; then
+            >&2 echo "fastq_html_hash ($hash) did not match expected hash (${sep=' ' expected_fastqc_html_hashes})"
             fail=true
           fi
         done
 
-    for zipfile in ${sep=' ' fastqc_zips}; do
-      hash=$(md5sum $zipfile | awk '{print $1}')
-      if [[ " ${sep=' ' expected_fastqc_zip_hashes} " != *" $hash "* ]]; then
-        fail=true
-      fi
-    done
-
     if [ $fail == "true" ]; then exit 1; fi
 
   >>>
diff --git a/test/smartseq2_single_sample/pr/test_inputs.json b/test/smartseq2_single_sample/pr/test_inputs.json
index d689cf26b..d29d475a5 100644
--- a/test/smartseq2_single_sample/pr/test_inputs.json
+++ b/test/smartseq2_single_sample/pr/test_inputs.json
@@ -15,6 +15,5 @@
   "TestSmartSeq2SingleCellPR.output_name":"SRR1294925",
   "TestSmartSeq2SingleCellPR.expected_counts_hash": "135a3fbb959583db17713dc8b9d7fe33",
   "TestSmartSeq2SingleCellPR.expected_metrics_hash": "99bd9903ac8dc77eb1c047ffa8eb42ed",
-  "TestSmartSeq2SingleCellPR.expected_fastqc_zip_hashes": ["2080c23507ce431aab4491f8aecfff39","7ad3130042307ca8db85e228e1a30f77"],
-  "TestSmartSeq2SingleCellPR.expected_fastqc_html_hashes": ["7e126084d99342c7dd78e7b80429d9f3","26934543205d10a70488ba7920557e42"]
+  "TestSmartSeq2SingleCellPR.expected_fastqc_html_hashes": ["21aac025893e0488d6dac0cd206ac2a9","d0d16bee2e05441acd8189d8e29849e7"]
 }
diff --git a/test/smartseq2_single_sample/pr/test_smartseq2_single_sample_PR.wdl b/test/smartseq2_single_sample/pr/test_smartseq2_single_sample_PR.wdl
index bf00ce994..06ddf8b6b 100644
--- a/test/smartseq2_single_sample/pr/test_smartseq2_single_sample_PR.wdl
+++ b/test/smartseq2_single_sample/pr/test_smartseq2_single_sample_PR.wdl
@@ -23,7 +23,6 @@ workflow TestSmartSeq2SingleCellPR {
   String output_name
   File fastq1
   File fastq2
-  Array[String] expected_fastqc_zip_hashes
   Array[String] expected_fastqc_html_hashes
 
   call target_wdl.SmartSeq2SingleCell as target_workflow {
@@ -51,8 +50,6 @@ workflow TestSmartSeq2SingleCellPR {
      target_metrics = target_workflow.insert_size_metrics,
      expected_metrics_hash = expected_metrics_hash,
      fastqc_htmls = target_workflow.fastqc_htmls,
-     fastqc_zips = target_workflow.fastqc_zips,
-     expected_fastqc_zip_hashes = expected_fastqc_zip_hashes,
      expected_fastqc_html_hashes = expected_fastqc_html_hashes
   }
 

From abb02f0d6278845435b616952e755fbe23827c15 Mon Sep 17 00:00:00 2001
From: Christopher Kachulis <ckachuli@broadinstitute.org>
Date: Thu, 16 May 2019 10:27:11 -0400
Subject: [PATCH 12/15] Phil comments

---
 pipelines/optimus/Optimus.wdl                 |  4 ++--
 test/optimus/pr/ValidateOptimus.wdl           |  7 +++++++
 test/optimus/pr/test_inputs.json              |  1 +
 test/optimus/pr/test_optimus_PR.wdl           |  7 +++++--
 .../pr/ValidateSmartSeq2SingleCell.wdl        | 20 +++++++++++++------
 .../pr/test_smartseq2_single_sample_PR.wdl    |  5 ++++-
 6 files changed, 33 insertions(+), 11 deletions(-)

diff --git a/pipelines/optimus/Optimus.wdl b/pipelines/optimus/Optimus.wdl
index 8490bedb7..c79aafcd5 100644
--- a/pipelines/optimus/Optimus.wdl
+++ b/pipelines/optimus/Optimus.wdl
@@ -245,7 +245,7 @@ workflow Optimus {
       Array[File]? zarr_output_files = OptimusZarrConversion.zarr_output_files
 
       # fastqc
-      Array[Array[File]] fastqc_htmls = fastqc_output_htmls
-      Array[Array[File]] fastqc_zips = fastqc_output_zips
+      Array[File] fastqc_htmls = flatten(fastqc_output_htmls)
+      Array[File] fastqc_zips = flatten(fastqc_output_zips)
   }
 }
diff --git a/test/optimus/pr/ValidateOptimus.wdl b/test/optimus/pr/ValidateOptimus.wdl
index 79b757b15..0762a8130 100644
--- a/test/optimus/pr/ValidateOptimus.wdl
+++ b/test/optimus/pr/ValidateOptimus.wdl
@@ -4,12 +4,14 @@ task ValidateOptimus {
       File gene_metrics
       File cell_metrics
       Array[File] fastqc_htmls
+      Int n_fastqc_zips
       Int required_disk = ceil((size(bam, "G") + size(matrix, "G")) * 1.1)
 
       String expected_bam_hash
       String expected_matrix_hash
       String expected_gene_metric_hash
       String expected_cell_metric_hash
+      Int expected_n_fastqc_zips
       Array[String] expected_fastqc_html_hashes
 
   command <<<
@@ -60,6 +62,11 @@ task ValidateOptimus {
       fi
     done
 
+    if [ ${expected_n_fastqc_zips} != ${n_fastqc_zips} ]; then
+      >&2 echo "number of fastqc zip (${n_fastqc_zips}) did not match expected number (${expected_n_fastqc_zips})"
+      fail=true
+    fi
+
     if [ $fail == "true" ]; then exit 1; fi
 
   >>>
diff --git a/test/optimus/pr/test_inputs.json b/test/optimus/pr/test_inputs.json
index fd8f4569f..d70337c03 100644
--- a/test/optimus/pr/test_inputs.json
+++ b/test/optimus/pr/test_inputs.json
@@ -6,6 +6,7 @@
   "TestOptimusPR.expected_fastqc_html_hashes": ["cb0bbb7d52198c38f2cfa87621c92e31",
     "6697992484d279d15683b5124ab75554",
     "26e07b94eaff3a7ea3dcc9a191bd1194"],
+  "TestOptimusPR.expected_n_fastqc_zips": 6,
   "TestOptimusPR.r1_fastq": [
     "gs://hca-dcp-mint-test-data/10x/demo/fastqs/pbmc8k_S1_L007_R1_001.fastq.gz",
     "gs://hca-dcp-mint-test-data/10x/demo/fastqs/pbmc8k_S1_L007_R1_001.fastq.gz"
diff --git a/test/optimus/pr/test_optimus_PR.wdl b/test/optimus/pr/test_optimus_PR.wdl
index a5a34f27e..dc09444f9 100644
--- a/test/optimus/pr/test_optimus_PR.wdl
+++ b/test/optimus/pr/test_optimus_PR.wdl
@@ -11,6 +11,7 @@ workflow TestOptimusPR {
   String expected_gene_metric_hash
   String expected_cell_metric_hash
   Array[String] expected_fastqc_html_hashes
+  Int expected_n_fastqc_zips
 
   # Optimus inputs
   Array[File] r1_fastq
@@ -41,12 +42,14 @@ workflow TestOptimusPR {
       matrix = target.matrix,
       gene_metrics = target.gene_metrics,
       cell_metrics = target.cell_metrics,
-      fastqc_htmls = flatten(target.fastqc_htmls),
+      fastqc_htmls = target.fastqc_htmls,
+      n_fastq_zips = length(target.fastqc_zips),
       expected_bam_hash = expected_bam_hash,
       expected_matrix_hash = expected_matrix_hash,
       expected_cell_metric_hash = expected_cell_metric_hash,
       expected_gene_metric_hash = expected_gene_metric_hash,
-      expected_fastqc_html_hashes = expected_fastqc_html_hashes
+      expected_fastqc_html_hashes = expected_fastqc_html_hashes,
+      expected_n_fastqc_zips = expected_n_fastqc_zips
   }
 
 }
diff --git a/test/smartseq2_single_sample/pr/ValidateSmartSeq2SingleCell.wdl b/test/smartseq2_single_sample/pr/ValidateSmartSeq2SingleCell.wdl
index 6e8e8a92a..4974aa12d 100644
--- a/test/smartseq2_single_sample/pr/ValidateSmartSeq2SingleCell.wdl
+++ b/test/smartseq2_single_sample/pr/ValidateSmartSeq2SingleCell.wdl
@@ -8,6 +8,9 @@ task ValidateSmartSeq2SingleCell {
       Array[File] fastqc_htmls
       Array[String] expected_fastqc_html_hashes
 
+      Int expected_n_fastqc_zips
+      Int n_fastqc_zips
+
   command <<<
 
     # catch intermittent failures
@@ -32,12 +35,17 @@ task ValidateSmartSeq2SingleCell {
     fi
 
     for htmlfile in ${sep=' ' fastqc_htmls}; do
-          hash=$(md5sum $htmlfile | awk '{print $1}')
-          if [[ " ${sep=' ' expected_fastqc_html_hashes} " != *" $hash "* ]]; then
-            >&2 echo "fastq_html_hash ($hash) did not match expected hash (${sep=' ' expected_fastqc_html_hashes})"
-            fail=true
-          fi
-        done
+      hash=$(md5sum $htmlfile | awk '{print $1}')
+      if [[ " ${sep=' ' expected_fastqc_html_hashes} " != *" $hash "* ]]; then
+        >&2 echo "fastq_html_hash ($hash) did not match expected hash (${sep=' ' expected_fastqc_html_hashes})"
+        fail=true
+      fi
+    done
+
+    if [ ${expected_n_fastqc_zips} != ${n_fastqc_zips} ]; then
+      >&2 echo "number of fastqc zip (${n_fastqc_zips}) did not match expected number (${expected_n_fastqc_zips})"
+      fail=true
+    fi
 
     if [ $fail == "true" ]; then exit 1; fi
 
diff --git a/test/smartseq2_single_sample/pr/test_smartseq2_single_sample_PR.wdl b/test/smartseq2_single_sample/pr/test_smartseq2_single_sample_PR.wdl
index 06ddf8b6b..5fdc9d960 100644
--- a/test/smartseq2_single_sample/pr/test_smartseq2_single_sample_PR.wdl
+++ b/test/smartseq2_single_sample/pr/test_smartseq2_single_sample_PR.wdl
@@ -24,6 +24,7 @@ workflow TestSmartSeq2SingleCellPR {
   File fastq1
   File fastq2
   Array[String] expected_fastqc_html_hashes
+  Int expected_n_fastqc_zips
 
   call target_wdl.SmartSeq2SingleCell as target_workflow {
     input:
@@ -50,7 +51,9 @@ workflow TestSmartSeq2SingleCellPR {
      target_metrics = target_workflow.insert_size_metrics,
      expected_metrics_hash = expected_metrics_hash,
      fastqc_htmls = target_workflow.fastqc_htmls,
-     expected_fastqc_html_hashes = expected_fastqc_html_hashes
+     expected_fastqc_html_hashes = expected_fastqc_html_hashes,
+     n_fastqc_zips = length(target_workflow.fastqc_zips),
+     expected_n_fastqc_zips = expected_n_fastqc_zips
   }
 
 }

From 2b843082303387adff1f7bbd6b654ac99c277dba Mon Sep 17 00:00:00 2001
From: Christopher Kachulis <ckachuli@broadinstitute.org>
Date: Thu, 16 May 2019 10:38:27 -0400
Subject: [PATCH 13/15] tests

---
 test/optimus/pr/test_optimus_PR.wdl              | 2 +-
 test/smartseq2_single_sample/pr/test_inputs.json | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/test/optimus/pr/test_optimus_PR.wdl b/test/optimus/pr/test_optimus_PR.wdl
index dc09444f9..4a8873b4e 100644
--- a/test/optimus/pr/test_optimus_PR.wdl
+++ b/test/optimus/pr/test_optimus_PR.wdl
@@ -43,7 +43,7 @@ workflow TestOptimusPR {
       gene_metrics = target.gene_metrics,
       cell_metrics = target.cell_metrics,
       fastqc_htmls = target.fastqc_htmls,
-      n_fastq_zips = length(target.fastqc_zips),
+      n_fastqc_zips = length(target.fastqc_zips),
       expected_bam_hash = expected_bam_hash,
       expected_matrix_hash = expected_matrix_hash,
       expected_cell_metric_hash = expected_cell_metric_hash,
diff --git a/test/smartseq2_single_sample/pr/test_inputs.json b/test/smartseq2_single_sample/pr/test_inputs.json
index d29d475a5..7b17303f6 100644
--- a/test/smartseq2_single_sample/pr/test_inputs.json
+++ b/test/smartseq2_single_sample/pr/test_inputs.json
@@ -15,5 +15,6 @@
   "TestSmartSeq2SingleCellPR.output_name":"SRR1294925",
   "TestSmartSeq2SingleCellPR.expected_counts_hash": "135a3fbb959583db17713dc8b9d7fe33",
   "TestSmartSeq2SingleCellPR.expected_metrics_hash": "99bd9903ac8dc77eb1c047ffa8eb42ed",
-  "TestSmartSeq2SingleCellPR.expected_fastqc_html_hashes": ["21aac025893e0488d6dac0cd206ac2a9","d0d16bee2e05441acd8189d8e29849e7"]
+  "TestSmartSeq2SingleCellPR.expected_fastqc_html_hashes": ["21aac025893e0488d6dac0cd206ac2a9","d0d16bee2e05441acd8189d8e29849e7"],
+  "TestSmartSeq2SingleCellPR.n_fastqc_zips": 2
 }

From e794f71b7ea989a4c980fbb9e69296eef1c91f72 Mon Sep 17 00:00:00 2001
From: Christopher Kachulis <ckachuli@broadinstitute.org>
Date: Thu, 16 May 2019 11:42:14 -0400
Subject: [PATCH 14/15] tests

---
 test/smartseq2_single_sample/pr/test_inputs.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/test/smartseq2_single_sample/pr/test_inputs.json b/test/smartseq2_single_sample/pr/test_inputs.json
index 7b17303f6..2dc99faed 100644
--- a/test/smartseq2_single_sample/pr/test_inputs.json
+++ b/test/smartseq2_single_sample/pr/test_inputs.json
@@ -16,5 +16,5 @@
   "TestSmartSeq2SingleCellPR.expected_counts_hash": "135a3fbb959583db17713dc8b9d7fe33",
   "TestSmartSeq2SingleCellPR.expected_metrics_hash": "99bd9903ac8dc77eb1c047ffa8eb42ed",
   "TestSmartSeq2SingleCellPR.expected_fastqc_html_hashes": ["21aac025893e0488d6dac0cd206ac2a9","d0d16bee2e05441acd8189d8e29849e7"],
-  "TestSmartSeq2SingleCellPR.n_fastqc_zips": 2
+  "TestSmartSeq2SingleCellPR.expected_n_fastqc_zips": 2
 }

From c139eef5af64059bc6bbc26a02439c70e9d39d6d Mon Sep 17 00:00:00 2001
From: Christopher Kachulis <ckachuli@broadinstitute.org>
Date: Thu, 16 May 2019 15:07:47 -0400
Subject: [PATCH 15/15] fixing tests

---
 test/optimus/pr/ValidateOptimus.wdl           | 20 ++++++++++++-------
 test/optimus/pr/test_inputs.json              |  6 +++---
 test/optimus/pr/test_optimus_PR.wdl           |  4 ++--
 .../pr/ValidateSmartSeq2SingleCell.wdl        | 20 ++++++++++++-------
 .../pr/test_inputs.json                       |  3 ++-
 .../pr/test_smartseq2_single_sample_PR.wdl    |  4 ++--
 6 files changed, 35 insertions(+), 22 deletions(-)

diff --git a/test/optimus/pr/ValidateOptimus.wdl b/test/optimus/pr/ValidateOptimus.wdl
index 0762a8130..c8e0e7c6b 100644
--- a/test/optimus/pr/ValidateOptimus.wdl
+++ b/test/optimus/pr/ValidateOptimus.wdl
@@ -12,7 +12,7 @@ task ValidateOptimus {
       String expected_gene_metric_hash
       String expected_cell_metric_hash
       Int expected_n_fastqc_zips
-      Array[String] expected_fastqc_html_hashes
+      Array[String] expected_fastqc_html_strings
 
   command <<<
 
@@ -54,12 +54,18 @@ task ValidateOptimus {
       fail=true
     fi
 
-    for htmlfile in ${sep=' ' fastqc_htmls}; do
-      hash=$(md5sum $htmlfile | awk '{print $1}')
-      if [[ " ${sep=' ' expected_fastqc_html_hashes} " != *" $hash "* ]]; then
-        >&2 echo "fastq_html_hash ($hash) did not match expected hash (${sep=' ' expected_fastqc_html_hashes})"
-        fail=true
-      fi
+    #search for expected strings in fastqc html
+    for string in "${sep='" "' expected_fastqc_html_strings}"; do
+        fail_html=true
+        for htmlfile in ${sep=' ' fastqc_htmls}; do
+          if grep "$string" $htmlfile; then
+            fail_html=false
+          fi
+        done
+        if [ $fail_html == "true" ]; then
+          >&2 echo "expected string ($string) not found in fastqc html files"
+          fail=true
+        fi
     done
 
     if [ ${expected_n_fastqc_zips} != ${n_fastqc_zips} ]; then
diff --git a/test/optimus/pr/test_inputs.json b/test/optimus/pr/test_inputs.json
index d70337c03..7b4b85d17 100644
--- a/test/optimus/pr/test_inputs.json
+++ b/test/optimus/pr/test_inputs.json
@@ -3,9 +3,9 @@
   "TestOptimusPR.expected_matrix_hash": "aec7a79dc7b85a5d621509a3f4fa2192",
   "TestOptimusPR.expected_cell_metric_hash": "45cc8be253445201b02d102d2d096a0c",
   "TestOptimusPR.expected_gene_metric_hash": "d636671dfcff6ec8068987d0f5780334",
-  "TestOptimusPR.expected_fastqc_html_hashes": ["cb0bbb7d52198c38f2cfa87621c92e31",
-    "6697992484d279d15683b5124ab75554",
-    "26e07b94eaff3a7ea3dcc9a191bd1194"],
+  "TestOptimusPR.expected_fastqc_html_strings": ["pbmc8k_S1_L007_I1_001_skip250000_read250000.fastq FastQC Report","Sequence length</td><td>8",
+    "pbmc8k_S1_L007_R1_001_skip250000_read250000.fastq FastQC Report","Sequence length</td><td>26",
+    "pbmc8k_S1_L007_R2_001_skip250000_read250000.fastq FastQC Report","Sequence length</td><td>98"],
   "TestOptimusPR.expected_n_fastqc_zips": 6,
   "TestOptimusPR.r1_fastq": [
     "gs://hca-dcp-mint-test-data/10x/demo/fastqs/pbmc8k_S1_L007_R1_001.fastq.gz",
diff --git a/test/optimus/pr/test_optimus_PR.wdl b/test/optimus/pr/test_optimus_PR.wdl
index 4a8873b4e..794072acc 100644
--- a/test/optimus/pr/test_optimus_PR.wdl
+++ b/test/optimus/pr/test_optimus_PR.wdl
@@ -10,7 +10,7 @@ workflow TestOptimusPR {
   String expected_matrix_hash
   String expected_gene_metric_hash
   String expected_cell_metric_hash
-  Array[String] expected_fastqc_html_hashes
+  Array[String] expected_fastqc_html_strings # a set of strings to search for in the fastqc html outputs
   Int expected_n_fastqc_zips
 
   # Optimus inputs
@@ -48,7 +48,7 @@ workflow TestOptimusPR {
       expected_matrix_hash = expected_matrix_hash,
       expected_cell_metric_hash = expected_cell_metric_hash,
       expected_gene_metric_hash = expected_gene_metric_hash,
-      expected_fastqc_html_hashes = expected_fastqc_html_hashes,
+      expected_fastqc_html_strings = expected_fastqc_html_strings,
       expected_n_fastqc_zips = expected_n_fastqc_zips
   }
 
diff --git a/test/smartseq2_single_sample/pr/ValidateSmartSeq2SingleCell.wdl b/test/smartseq2_single_sample/pr/ValidateSmartSeq2SingleCell.wdl
index 4974aa12d..7268176e1 100644
--- a/test/smartseq2_single_sample/pr/ValidateSmartSeq2SingleCell.wdl
+++ b/test/smartseq2_single_sample/pr/ValidateSmartSeq2SingleCell.wdl
@@ -6,7 +6,7 @@ task ValidateSmartSeq2SingleCell {
       String expected_metrics_hash
 
       Array[File] fastqc_htmls
-      Array[String] expected_fastqc_html_hashes
+      Array[String] expected_fastqc_html_strings
 
       Int expected_n_fastqc_zips
       Int n_fastqc_zips
@@ -34,12 +34,18 @@ task ValidateSmartSeq2SingleCell {
       fail=true
     fi
 
-    for htmlfile in ${sep=' ' fastqc_htmls}; do
-      hash=$(md5sum $htmlfile | awk '{print $1}')
-      if [[ " ${sep=' ' expected_fastqc_html_hashes} " != *" $hash "* ]]; then
-        >&2 echo "fastq_html_hash ($hash) did not match expected hash (${sep=' ' expected_fastqc_html_hashes})"
-        fail=true
-      fi
+    #search for expected strings in fastqc html
+    for string in "${sep='" "' expected_fastqc_html_strings}"; do
+        fail_html=true
+        for htmlfile in ${sep=' ' fastqc_htmls}; do
+          if grep "$string" $htmlfile; then
+            fail_html=false
+          fi
+        done
+        if [ $fail_html == "true" ]; then
+          >&2 echo "expected string ($string) not found in fastqc html files"
+          fail=true
+        fi
     done
 
     if [ ${expected_n_fastqc_zips} != ${n_fastqc_zips} ]; then
diff --git a/test/smartseq2_single_sample/pr/test_inputs.json b/test/smartseq2_single_sample/pr/test_inputs.json
index 2dc99faed..176e5bfd6 100644
--- a/test/smartseq2_single_sample/pr/test_inputs.json
+++ b/test/smartseq2_single_sample/pr/test_inputs.json
@@ -15,6 +15,7 @@
   "TestSmartSeq2SingleCellPR.output_name":"SRR1294925",
   "TestSmartSeq2SingleCellPR.expected_counts_hash": "135a3fbb959583db17713dc8b9d7fe33",
   "TestSmartSeq2SingleCellPR.expected_metrics_hash": "99bd9903ac8dc77eb1c047ffa8eb42ed",
-  "TestSmartSeq2SingleCellPR.expected_fastqc_html_hashes": ["21aac025893e0488d6dac0cd206ac2a9","d0d16bee2e05441acd8189d8e29849e7"],
+  "TestSmartSeq2SingleCellPR.expected_fastqc_html_strings": ["SRR1294925_1_skip250000_read250000.fastq FastQC Report","Sequence length</td><td>25",
+    "SRR1294925_2_skip250000_read250000.fastq FastQC Report"],
   "TestSmartSeq2SingleCellPR.expected_n_fastqc_zips": 2
 }
diff --git a/test/smartseq2_single_sample/pr/test_smartseq2_single_sample_PR.wdl b/test/smartseq2_single_sample/pr/test_smartseq2_single_sample_PR.wdl
index 5fdc9d960..5f7dfd09d 100644
--- a/test/smartseq2_single_sample/pr/test_smartseq2_single_sample_PR.wdl
+++ b/test/smartseq2_single_sample/pr/test_smartseq2_single_sample_PR.wdl
@@ -23,7 +23,7 @@ workflow TestSmartSeq2SingleCellPR {
   String output_name
   File fastq1
   File fastq2
-  Array[String] expected_fastqc_html_hashes
+  Array[String] expected_fastqc_html_strings
   Int expected_n_fastqc_zips
 
   call target_wdl.SmartSeq2SingleCell as target_workflow {
@@ -51,7 +51,7 @@ workflow TestSmartSeq2SingleCellPR {
      target_metrics = target_workflow.insert_size_metrics,
      expected_metrics_hash = expected_metrics_hash,
      fastqc_htmls = target_workflow.fastqc_htmls,
-     expected_fastqc_html_hashes = expected_fastqc_html_hashes,
+     expected_fastqc_html_strings = expected_fastqc_html_strings,
      n_fastqc_zips = length(target_workflow.fastqc_zips),
      expected_n_fastqc_zips = expected_n_fastqc_zips
   }