Merge pull request #91 from theiagen/smw-quasitools-bug-fix-dev

Quasitools Bug Discovery and Destruction
theiagen · Jun 12, 2023 · c5d2f38 · c5d2f38
2 parents 87e8c43 + 5e07a1f
commit c5d2f38
Show file tree

Hide file tree

Showing 3 changed files with 26 additions and 13 deletions.
diff --git a/tasks/quality_control/task_artic_guppyplex.wdl b/tasks/quality_control/task_artic_guppyplex.wdl
@@ -1,10 +1,11 @@
 version 1.0
 
-task read_filtering { # in use
+task read_filtering {
   input {
     File demultiplexed_reads
     String samplename
     String run_prefix = "artic_ncov2019"
+    String docker = "quay.io/staphb/artic-ncov2019:1.3.0-medaka-1.4.3"
     Int min_length = 400
     Int max_length = 700
     Int cpu = 8
@@ -15,18 +16,19 @@ task read_filtering { # in use
     mkdir ~{samplename}
     cp ~{demultiplexed_reads} ~{samplename}/
     echo "DIRNAME: $(dirname)"
-    artic guppyplex --min-length ~{min_length} --max-length ~{max_length} --directory ~{samplename} --prefix ~{run_prefix}
 
+    # run artic guppyplex 
+    artic guppyplex --min-length ~{min_length} --max-length ~{max_length} --directory ~{samplename} --prefix ~{run_prefix}
   >>>
   output {
     File filtered_reads = "~{run_prefix}_~{samplename}.fastq"
   }
   runtime {
-    docker: "quay.io/staphb/artic-ncov2019:1.3.0-medaka-1.4.3"
+    docker: docker
     memory: "16 GB"
     cpu: cpu
     disks:  "local-disk " + disk_size + " SSD"
-    disk: disk_size + " GB" # TES
+    disk: disk_size + " GB"
     preemptible: 0
     maxRetries: 3
   }

diff --git a/tasks/species_typing/task_quasitools.wdl b/tasks/species_typing/task_quasitools.wdl
@@ -4,7 +4,6 @@ task quasitools {
   input {
     File read1
     File? read2
-    File mutation_db = "gs://theiagen-public-files/terra/hivgc-files/mutation_db.tsv"
     String samplename
     String docker = "quay.io/biocontainers/quasitools:0.7.0--pyh864c0ab_1"
   }
@@ -20,34 +19,42 @@ task quasitools {
     fi
     read1_unzip=r1.fastq
 
-    # do the same on read2
-    # unzip file if necessary
-    if ~ [ -z ~{read2} ]; then
+    # do the same on read2 if exists & unzip file if necessary
+    if [[ -e "~{read2}" ]]; then
       if [[ "~{read2}" == *.gz ]]; then
         gunzip -c ~{read2} > r2.fastq
       else
         mv ~{read2} r2.fastq
       fi
       read2_unzip=r2.fastq
     else
-      ont="-rt 5"
+      ont="-rt 5" # set the minimum number of observations in the read data to 5 instead of the default of 1 if ONT data
     fi
 
 
     # Print and save version
     quasitools --version > QUASITOOLS_VERSION && sed -i -e 's/^/quasitools /' QUASITOOLS_VERSION
 
     # Run hydra
+    # -mf : the minimum frequency for observed variant to be included for processing
+    # -sc : reads that have a median/mean quality score less than this cutoff will be filtered out
+    # -lc : reads which fall short of this length will be filtered out
+    # -vq : minimum quality for an amino acid variant to be included
+    # -md : the minimum read depth for observed nucleotide variants to be included
+    # -ma : the minimum allele count for observed variants to be included
+    # -me : indicates that the median score will be used as a cutoff for read filtering
+
+    # the ${ont} needs to be on the same line as a different variable or it will fail
     set -e
     quasitools hydra \
-      -mf 0.05 \
-      "${ont}" \
+      -mf 0.05 ${ont} \
       -sc 7 \
       -lc 50 \
       -vq 7 \
       -md 10 \
       -ma 1 \
-      -me ${read1_unzip} ${read2_unzip} \
+      -me \
+      ${read1_unzip} ${read2_unzip} \
       -o "~{samplename}"
   >>>
   runtime {

diff --git a/workflows/theiacov/wf_theiacov_ont.wdl b/workflows/theiacov/wf_theiacov_ont.wdl
@@ -50,6 +50,9 @@ workflow theiacov_ont {
     # qc check parameters
     File? qc_check_table
   }
+  if (organism == "HIV") { # set HIV specific artic version
+    String run_prefix = "artic_hiv"
+  }
   call screen.check_reads_se as raw_check_reads {
     input:
       read1 = demultiplexed_reads,
@@ -74,7 +77,8 @@ workflow theiacov_ont {
         demultiplexed_reads = ncbi_scrub_se.read1_dehosted,
         samplename = samplename,
         min_length = min_length,
-        max_length = max_length
+        max_length = max_length,
+        run_prefix = run_prefix
     }
     call screen.check_reads_se as clean_check_reads {
       input: