Merge branch 'main' into im-metagenomics-workflow

.github/ISSUE_TEMPLATE/bug-report.md

@@ -0,0 +1,38 @@
+---
+name: Bug Report
+about: Tell us about a bug
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+:bug:
+
+### :pencil: Describe the Issue
+
+<!-- Please describe what the issue you are facing and any necessary context. -->
+
+### :repeat: How to Reproduce
+
+- Was this run on the Terra platform?
+  - Terra on GCP or Azure?
+- Or were the workflows run locally using `miniwdl` or `cromwell`?
+  - **What was the exact command was used to launch the workflow?**
+- If possible, we may ask you to share your Terra workspace with us. Usually READER access is sufficient, but we may ask for WRITER access if we need to make changes to the workspace to reproduce the issue.
+
+<!-- Please describe the steps needed to reproduce the observed behavior. -->
+
+### :fishing_pole_and_fish: Expected Behavior
+
+<!-- Please describe what you expected to happen. -->
+
+### :floppy_disk: Version Information
+
+<!-- What workflow (if applicable) did this issue occur on?
+What version of the workflow (if applicable) was being used? -->
+
+### :information_source: Additional Information
+
+<!-- Please describe any additional information we should know in order to address the issue. 
+If applicable, please add screenshots to help explain your problem.-->

.github/ISSUE_TEMPLATE/feature-request.md

@@ -0,0 +1,26 @@
+---
+name: Feature Request
+about: Tell us about what you need
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+:cool:
+
+### :pushpin: Explain the Request
+
+<!--Please describe what you would like us to add.-->
+
+### :books: Context
+
+<!--Please describe the context about your request.-->
+
+### :chart_with_upwards_trend: Desired Behavior
+
+<!--Please provide a clear and concise description of what you want to happen.-->
+
+### :information_source: Additional Information
+
+<!--Please add any other information or screenshots about your request here.-->

tasks/gene_typing/task_plasmidfinder.wdl

@@ -4,10 +4,10 @@ task plasmidfinder {
   input {
     File assembly
     String samplename
-    Int cpu = 8
-    Int memory = 16
+    Int cpu = 2
+    Int memory = 8
     String docker = "us-docker.pkg.dev/general-theiagen/staphb/plasmidfinder:2.1.6"
-    Int disk_size = 100
+    Int disk_size = 50
     String? database
     String? database_path
     String? method_path
@@ -41,15 +41,15 @@ task plasmidfinder {
   if [ ! -f results_tab.tsv ]; then
     PF="No plasmids detected in database"
   else
-    PF="$(tail -n +2 results_tab.tsv | cut -f 2 | sort | uniq -u | paste -s -d, - )"
+    PF="$(tail -n +2 results_tab.tsv | uniq | cut -f 2 | sort | paste -s -d, - )"
       if [ "$PF" == "" ]; then
         PF="No plasmids detected in database"
       fi  
   fi
-  echo $PF | tee PLASMIDS
+  echo "$PF" | tee PLASMIDS
 
-  mv results_tab.tsv ~{samplename}_results.tsv
-  mv Hit_in_genome_seq.fsa ~{samplename}_seqs.fsa
+  mv -v results_tab.tsv ~{samplename}_results.tsv
+  mv -v Hit_in_genome_seq.fsa ~{samplename}_seqs.fsa
 
   >>>
   output {

tasks/taxon_id/task_kraken2.wdl

@@ -111,6 +111,15 @@ task kraken2_standalone {
     percentage_human=$(grep "Homo sapiens" ~{samplename}.report.txt | cut -f 1)
     if [ -z "$percentage_human" ] ; then percentage_human="0" ; fi
     echo $percentage_human | tee PERCENT_HUMAN
+
+    # rename classified and unclassified read files if SE
+    if [ -e "~{samplename}.classified#.fastq.gz" ]; then
+      mv "~{samplename}.classified#.fastq.gz" ~{samplename}.classified_1.fastq.gz
+    fi
+    if [ -e "~{samplename}.unclassified#.fastq.gz" ]; then
+      mv "~{samplename}.unclassified#.fastq.gz" ~{samplename}.unclassified_1.fastq.gz
+    fi
+
   >>>
   output {
     String kraken2_version = read_string("VERSION")
@@ -119,10 +128,10 @@ task kraken2_standalone {
     File kraken2_report = "~{samplename}.report.txt"
     File kraken2_classified_report = "~{samplename}.classifiedreads.txt.gz"
     File kraken2_unclassified_read1 = "~{samplename}.unclassified_1.fastq.gz"
-    File kraken2_unclassified_read2 = "~{samplename}.unclassified_2.fastq.gz"
+    File? kraken2_unclassified_read2 = "~{samplename}.unclassified_2.fastq.gz"
     File kraken2_classified_read1 = "~{samplename}.classified_1.fastq.gz"
-    File kraken2_classified_read2 = "~{samplename}.classified_2.fastq.gz"
     Float kraken2_percent_human = read_float("PERCENT_HUMAN")
+    File? kraken2_classified_read2 = "~{samplename}.classified_2.fastq.gz"
   }
   runtime {
       docker: "~{docker}"

tasks/utilities/task_kmc.wdl

@@ -44,7 +44,7 @@ task kmc {
     tail -n8 LOG > ~{samplename}_kmer_stats.txt
   >>>
   output {
-    String est_genome_size = read_string("UNIQUE_COUNTED") 
+    Int est_genome_size = read_int("UNIQUE_COUNTED") 
     File kmer_stats = "~{samplename}_kmer_stats.txt"
     String kmc_version = read_string("VERSION")
   }

tests/workflows/theiaprok/test_wf_theiaprok_illumina_pe.yml

@@ -264,7 +264,7 @@
     - path: miniwdl_run/call-merlin_magic/workflow.log
       contains: ["wdl", "theiaprok_illumina_pe", "merlin", "done"]
     - path: miniwdl_run/call-plasmidfinder/command
-      md5sum: 61f7be9cfd36e3a48585e7f64cbcfe35
+      md5sum: 3b70033058bf91c04337e38bfd038b5a
     - path: miniwdl_run/call-plasmidfinder/inputs.json
     - path: miniwdl_run/call-plasmidfinder/outputs.json
     - path: miniwdl_run/call-plasmidfinder/stderr.txt
@@ -556,7 +556,7 @@
     - path: miniwdl_run/wdl/tasks/gene_typing/task_bakta.wdl
       md5sum: 0bed8fb60786095843a67b1ad03051dc
     - path: miniwdl_run/wdl/tasks/gene_typing/task_plasmidfinder.wdl
-      md5sum: 6ca295b4dcdbe95dd86516ba0a4073f8
+      md5sum: 8730e07b1c7ab9d2434a7838ddb1fc72
     - path: miniwdl_run/wdl/tasks/gene_typing/task_prokka.wdl
       md5sum: 8e8423b99d5cd3e92bb89b3c3211d432
     - path: miniwdl_run/wdl/tasks/gene_typing/task_resfinder.wdl

tests/workflows/theiaprok/test_wf_theiaprok_illumina_se.yml

@@ -261,7 +261,7 @@
     - path: miniwdl_run/call-merlin_magic/workflow.log
       contains: ["wdl", "theiaprok_illumina_se", "merlin", "done"]
     - path: miniwdl_run/call-plasmidfinder/command
-      md5sum: 61f7be9cfd36e3a48585e7f64cbcfe35
+      md5sum: 3b70033058bf91c04337e38bfd038b5a
     - path: miniwdl_run/call-plasmidfinder/inputs.json
     - path: miniwdl_run/call-plasmidfinder/outputs.json
     - path: miniwdl_run/call-plasmidfinder/stderr.txt
@@ -526,7 +526,7 @@
     - path: miniwdl_run/wdl/tasks/gene_typing/task_bakta.wdl
       md5sum: 0bed8fb60786095843a67b1ad03051dc
     - path: miniwdl_run/wdl/tasks/gene_typing/task_plasmidfinder.wdl
-      md5sum: 6ca295b4dcdbe95dd86516ba0a4073f8
+      md5sum: 8730e07b1c7ab9d2434a7838ddb1fc72
     - path: miniwdl_run/wdl/tasks/gene_typing/task_prokka.wdl
       md5sum: 8e8423b99d5cd3e92bb89b3c3211d432
     - path: miniwdl_run/wdl/tasks/gene_typing/task_resfinder.wdl

workflows/theiaprok/wf_theiaprok_ont.wdl

@@ -489,7 +489,7 @@ workflow theiaprok_ont {
     String? nanoplot_version = nanoplot_raw.nanoplot_version
     String? nanoplot_docker = nanoplot_raw.nanoplot_docker
     # Read QC - kmc outputs
-    String? kmc_est_genome_size = read_qc_trim.est_genome_size
+    Int? kmc_est_genome_size = read_qc_trim.est_genome_size
     File? kmc_kmer_stats = read_qc_trim.kmc_kmer_stats
     String? kmc_version = read_qc_trim.kmc_version
     # Read QC - rasusa outputs

workflows/utilities/wf_read_QC_trim_ont.wdl

@@ -84,7 +84,7 @@ workflow read_QC_trim_ont {
   }
   output { 
     # kmc outputs
-    String est_genome_size = kmc.est_genome_size
+    Int est_genome_size = kmc.est_genome_size
     File kmc_kmer_stats = kmc.kmer_stats
     String kmc_version = kmc.kmc_version