make strandedness optional

tools/samtools.wdl

@@ -550,7 +550,7 @@ task merge {
         Array[File] bams
         String prefix
         File? new_header
-        String region = ""
+        String? region
         Boolean attach_rg = true
         Boolean name_sorted = false
         Boolean combine_rg = true
@@ -585,7 +585,7 @@ task merge {
             --threads "$n_cores" \
             ~{"-h \"" + new_header + "\""} \
             ~{if name_sorted then "-n" else ""} \
-            ~{if (region != "") then "-R \"" + region + "\"" else ""} \
+            ~{"-R \"" + region + "\""} \
             ~{if attach_rg then "-r" else ""} \
             ~{if combine_rg then "-c" else ""} \
             ~{if combine_pg then "-p" else ""} \

workflows/rnaseq/rnaseq-core.wdl

@@ -132,7 +132,7 @@ workflow rnaseq_core {
         Array[File] read_one_fastqs_gz
         Array[File] read_two_fastqs_gz
         Array[String] read_groups
-        String strandedness
+        String? strandedness
         Boolean enable_read_trimming
         Boolean mark_duplicates
         Boolean cleanse_xenograft
@@ -162,15 +162,15 @@ workflow rnaseq_core {
         Int chim_score_drop_max = 30
     }
 
-    Map[String, String] htseq_strandedness_mapping = {
+    Map[String?, String] htseq_strandedness_mapping = {
         "Stranded-Reverse": "reverse",
         "Stranded-Forward": "yes",
         "Unstranded": "no",
         "Inconclusive": "undefined",  # THIS WILL ERRROR (intentional)
-        "": "undefined",
+        None: "undefined",
     }
 
-    String provided_strandedness = strandedness
+    String? provided_strandedness = strandedness
 
     scatter (fq in read_one_fastqs_gz) {
         String read_one_names = basename(fq)
@@ -253,7 +253,7 @@ workflow rnaseq_core {
     }
 
     String htseq_strandedness = (
-        if (provided_strandedness != "")
+        if defined(provided_strandedness)
         then htseq_strandedness_mapping[provided_strandedness]
         else htseq_strandedness_mapping[ngsderive_strandedness.strandedness_string]
     )
@@ -263,11 +263,10 @@ workflow rnaseq_core {
         gtf,
         strandedness = htseq_strandedness,
         prefix = basename(alignment_post.processed_bam, "bam")
-            + (
-                if provided_strandedness == ""
-                then ngsderive_strandedness.strandedness_string
-                else provided_strandedness
-            ),
+            + select_first([
+                provided_strandedness,
+                ngsderive_strandedness.strandedness_string
+            ]),
         pos_sorted = true,
     }
 

workflows/rnaseq/rnaseq-standard-fastq.wdl

@@ -36,6 +36,15 @@ workflow rnaseq_standard_fastq {
             warning: "See `data_structures/read_group.wdl` for more information and help formatting your input JSON.",
         }
         contaminant_db: "A compressed reference database corresponding to the aligner chosen with `xenocp_aligner` for the contaminant genome"
+        strandedness: {
+            description: "Strandedness protocol of the RNA-Seq experiment. If unspecified, strandedness will be inferred by `ngsderive`.",
+            choices: [
+                "",
+                "Stranded-Reverse",
+                "Stranded-Forward",
+                "Unstranded",
+            ],
+        }
         prefix: {
             description: "Prefix for output files",
             help: "See `../../README.md` for more information on the default prefix evaluation.",
@@ -49,15 +58,6 @@ workflow rnaseq_standard_fastq {
                 "star",
             ],
         }
-        strandedness: {
-            description: "Strandedness protocol of the RNA-Seq experiment. If unspecified, strandedness will be inferred by `ngsderive`.",
-            choices: [
-                "",
-                "Stranded-Reverse",
-                "Stranded-Forward",
-                "Unstranded",
-            ],
-        }
         enable_read_trimming: "Enable read trimming with `fastp`?"
         mark_duplicates: "Add SAM flag to computationally determined duplicate reads?"
         cleanse_xenograft: "Use XenoCP to unmap reads from contaminant genome?"
@@ -73,13 +73,13 @@ workflow rnaseq_standard_fastq {
         Array[File] read_two_fastqs_gz
         Array[ReadGroup] read_groups
         File? contaminant_db
+        String? strandedness
         String prefix = sub(
             basename(read_one_fastqs_gz[0]),
             "(([_.][rR](?:ead)?[12])((?:[_.-][^_.-]*?)*?))?\\.(fastq|fq)(\\.gz)?$",
             ""  # Once replacing with capturing groups is supported, replace with group 3
         )
         String xenocp_aligner = "star"
-        String strandedness = ""
         Boolean enable_read_trimming = false
         Boolean mark_duplicates = false
         Boolean cleanse_xenograft = false

workflows/rnaseq/rnaseq-standard.wdl

@@ -31,15 +31,6 @@ workflow rnaseq_standard {
         gtf: "Gzipped GTF feature file"
         star_db: "Database of reference files for the STAR aligner. Can be generated by `star-db-build.wdl`"
         contaminant_db: "A compressed reference database corresponding to the aligner chosen with `xenocp_aligner` for the contaminant genome"
-        prefix: "Prefix for output files"
-        xenocp_aligner: {
-            description: "Aligner to use to map reads to the host genome for detecting contamination",
-            choices: [
-                "bwa aln",
-                "bwa mem",
-                "star",
-            ],
-        }
         strandedness: {
             description: "Strandedness protocol of the RNA-Seq experiment. If unspecified, strandedness will be inferred by `ngsderive`.",
             choices: [
@@ -49,6 +40,15 @@ workflow rnaseq_standard {
                 "Unstranded",
             ],
         }
+        prefix: "Prefix for output files"
+        xenocp_aligner: {
+            description: "Aligner to use to map reads to the host genome for detecting contamination",
+            choices: [
+                "bwa aln",
+                "bwa mem",
+                "star",
+            ],
+        }
         enable_read_trimming: "Enable read trimming with `fastp`?"
         mark_duplicates: "Add SAM flag to computationally determined duplicate reads?"
         cleanse_xenograft: "Use XenoCP to unmap reads from contaminant genome?"
@@ -62,9 +62,9 @@ workflow rnaseq_standard {
         File gtf
         File star_db
         File? contaminant_db
+        String? strandedness
         String prefix = basename(bam, ".bam")
         String xenocp_aligner = "star"
-        String strandedness = ""
         Boolean enable_read_trimming = false
         Boolean mark_duplicates = false
         Boolean cleanse_xenograft = false
@@ -147,7 +147,6 @@ task parse_input {
         strand: {
             description: "Provided strandedness protocol of the RNA-Seq experiment",
             choices: [
-                "",
                 "Stranded-Reverse",
                 "Stranded-Forward",
                 "Unstranded",
@@ -158,7 +157,7 @@ task parse_input {
     }
 
     input {
-        String strand
+        String? strand
         Boolean cleanse_xenograft
         Boolean contaminant_db
     }