Merge pull request #55 from broadinstitute/dp-docs

rename spikein tasks and workflows to align_and_count
broadinstitute · Apr 30, 2020 · a160870 · a160870
2 parents e8ce43b + 0afec3d
commit a160870
Show file tree

Hide file tree

Showing 5 changed files with 38 additions and 37 deletions.
diff --git a/pipes/WDL/tasks/tasks_reports.wdl b/pipes/WDL/tasks/tasks_reports.wdl
@@ -143,10 +143,10 @@ task fastqc {
   }
 }
 
-task spikein_report {
+task align_and_count {
   input {
     File    reads_bam
-    File    spikein_db
+    File    ref_db
     Int?    minScoreToFilter = 60
     Int?    topNHits = 3
 
@@ -155,6 +155,7 @@ task spikein_report {
   }
 
   String  reads_basename=basename(reads_bam, ".bam")
+  String  ref_basename=basename(ref_db, ".fasta")
 
   command {
     set -ex -o pipefail
@@ -164,33 +165,33 @@ task spikein_report {
     ln -s ${reads_bam} ${reads_basename}.bam
     read_utils.py bwamem_idxstats \
       ${reads_basename}.bam \
-      ${spikein_db} \
-      --outStats ${reads_basename}.spike_count.txt.unsorted \
+      ${ref_db} \
+      --outStats ${reads_basename}.count.${ref_basename}.txt.unsorted \
       --minScoreToFilter=${minScoreToFilter} \
       --loglevel=DEBUG
 
-      sort -b -r -n -k3 ${reads_basename}.spike_count.txt.unsorted > ${reads_basename}.spike_count.txt
-      head -n ${topNHits} ${reads_basename}.spike_count.txt > ${reads_basename}.spike_count.top_${topNHits}_hits.txt
+      sort -b -r -n -k3 ${reads_basename}.count.${ref_basename}.txt.unsorted > ${reads_basename}.count.${ref_basename}.txt
+      head -n ${topNHits} ${reads_basename}.count.${ref_basename}.txt > ${reads_basename}.count.${ref_basename}.top_${topNHits}_hits.txt
   }
 
   output {
-    File   report           = "${reads_basename}.spike_count.txt"
-    File   report_top_hits  = "${reads_basename}.spike_count.top_${topNHits}_hits.txt"
+    File   report           = "${reads_basename}.count.${ref_basename}.txt"
+    File   report_top_hits  = "${reads_basename}.count.${ref_basename}.top_${topNHits}_hits.txt"
     String viralngs_version = read_string("VERSION")
   }
 
   runtime {
     memory: select_first([machine_mem_gb, 7]) + " GB"
-    cpu: 2
+    cpu: 4
     docker: "${docker}"
     disks: "local-disk 375 LOCAL"
     dx_instance_type: "mem1_ssd1_v2_x4"
   }
 }
 
-task spikein_summary {
+task align_and_count_summary {
   input {
-    Array[File]+  spikein_count_txt
+    Array[File]+  counts_txt
 
     Int?          machine_mem_gb
     String?       docker="quay.io/broadinstitute/viral-core"
@@ -200,15 +201,15 @@ task spikein_summary {
     set -ex -o pipefail
 
     mkdir spike_summaries
-    cp ${sep=' ' spikein_count_txt} spike_summaries/
+    cp ${sep=' ' counts_txt} spike_summaries/
 
     reports.py --version | tee VERSION
-    reports.py aggregate_spike_count spike_summaries/ spikein_summary.tsv \
+    reports.py aggregate_spike_count spike_summaries/ count_summary.tsv \
       --loglevel=DEBUG
   }
 
   output {
-    File   spikein_summary  = "spikein_summary.tsv"
+    File   count_summary    = "count_summary.tsv"
     String viralngs_version = read_string("VERSION")
   }
 
@@ -217,7 +218,7 @@ task spikein_summary {
     cpu: 2
     docker: "${docker}"
     disks: "local-disk 50 SSD"
-    dx_instance_type: "mem1_ssd1_v2_x4"
+    dx_instance_type: "mem1_ssd1_v2_x2"
   }
 }
 

diff --git a/pipes/WDL/workflows/align_and_count.wdl b/pipes/WDL/workflows/align_and_count.wdl
@@ -0,0 +1,12 @@
+version 1.0
+
+import "../tasks/tasks_reports.wdl" as reports
+
+workflow align_and_count_report {
+    call reports.align_and_count
+    output {
+        File report               = align_and_count.report
+        File report_top_hits      = align_and_count.report_top_hits
+        String viral_core_version = align_and_count.viralngs_version
+    }
+}
diff --git a/pipes/WDL/workflows/demux_metag.wdl b/pipes/WDL/workflows/demux_metag.wdl
@@ -20,10 +20,10 @@ workflow demux_metag {
     call demux.illumina_demux as illumina_demux
 
     scatter(raw_reads in illumina_demux.raw_reads_unaligned_bams) {
-        call reports.spikein_report as spikein {
+        call reports.align_and_count as spikein {
             input:
                 reads_bam = raw_reads,
-                spikein_db = spikein_db
+                ref_db = spikein_db
         }
         call taxon_filter.deplete_taxa as deplete {
             input:
@@ -62,9 +62,9 @@ workflow demux_metag {
             reads_unmapped_bam = illumina_demux.raw_reads_unaligned_bams
     }
 
-    call reports.spikein_summary as spike_summary {
+    call reports.align_and_count_summary as spike_summary {
         input:
-            spikein_count_txt = spikein.report
+            counts_txt = spikein.report
     }
 
     call reports.aggregate_metagenomics_reports as metag_summary_report {
@@ -87,7 +87,7 @@ workflow demux_metag {
 
         File        multiqc_report_raw     = multiqc_raw.multiqc_report
         File        multiqc_report_cleaned = multiqc_cleaned.multiqc_report
-        File        spikein_counts         = spike_summary.spikein_summary
+        File        spikein_counts         = spike_summary.count_summary
         File        metagenomics_krona     = krakenuniq.krona_report_merged_html
         File        metagenomics_summary   = metag_summary_report.krakenuniq_aggregate_taxlevel_summary
 

diff --git a/pipes/WDL/workflows/demux_plus.wdl b/pipes/WDL/workflows/demux_plus.wdl
@@ -19,10 +19,10 @@ workflow demux_plus {
     call demux.illumina_demux as illumina_demux
 
     scatter(raw_reads in illumina_demux.raw_reads_unaligned_bams) {
-        call reports.spikein_report as spikein {
+        call reports.align_and_count as spikein {
             input:
                 reads_bam = raw_reads,
-                spikein_db = spikein_db
+                ref_db = spikein_db
         }
         call taxon_filter.deplete_taxa as deplete {
             input:
@@ -57,9 +57,9 @@ workflow demux_plus {
             reads_unmapped_bam = illumina_demux.raw_reads_unaligned_bams
     }
 
-    call reports.spikein_summary as spike_summary {
+    call reports.align_and_count_summary as spike_summary {
         input:
-            spikein_count_txt = spikein.report
+            counts_txt = spikein.report
     }
 
     call reports.aggregate_metagenomics_reports as metag_summary_report {
@@ -82,7 +82,7 @@ workflow demux_plus {
 
         File        multiqc_report_raw     = multiqc_raw.multiqc_report
         File        multiqc_report_cleaned = multiqc_cleaned.multiqc_report
-        File        spikein_counts         = spike_summary.spikein_summary
+        File        spikein_counts         = spike_summary.count_summary
         File        metagenomics_krona     = krakenuniq.krona_report_merged_html
         File        metagenomics_summary   = metag_summary_report.krakenuniq_aggregate_taxlevel_summary
 

diff --git a/pipes/WDL/workflows/spikein.wdl b/pipes/WDL/workflows/spikein.wdl