PD-2559andPD-2558: UMI filtering and cell barcode correction

pipelines/skylab/multiome/Multiome.changelog.md

@@ -1,15 +1,20 @@
+# 3.4.3
+2024-04-24 (Date of Last Commit)
+
+* Updated the input parameters for STARsolo in STARsoloFastq task. These include the parameters: soloCBmatchWLtype, soloUMIdedup and soloUMIfiltering
+* Added "Uniform" as the default string for STARsolo multimapping parameters
 
 # 3.4.2
-20240403 (Date of Last Commit)
+2024-04-03 (Date of Last Commit)
 * Modified adaptor trimming in Paired-tag WDL; this does not impact Multiome
 
 # 3.4.1
-20240326 (Date of Last Commit)
+2024-03-26 (Date of Last Commit)
 
 * Updated the median umi per cell metric for STARsolo library-level metrics
 
 # 3.4.0 
-20240315 (Date of Last Commit)
+2024-03-15 (Date of Last Commit)
 
 * Added cell metrics to the library-level metrics
 

pipelines/skylab/multiome/Multiome.wdl

@@ -7,7 +7,7 @@ import "https://raw.githubusercontent.com/broadinstitute/CellBender/v0.3.0/wdl/c
 
 workflow Multiome {
 
-    String pipeline_version = "3.4.2"
+    String pipeline_version = "3.4.3"
 
     input {
         String input_id

pipelines/skylab/optimus/Optimus.changelog.md

@@ -1,11 +1,16 @@
+# 6.6.2
+2024-04-24 (Date of Last Commit)
+
+* Updated the input parameters for STARsolo in STARsoloFastq task. These include the parameters: soloCBmatchWLtype, soloUMIdedup and soloUMIfiltering
+* Added "Uniform" as the default string for STARsolo multimapping parameters
 
 # 6.6.1
-20240326 (Date of Last Commit)
+2024-03-26 (Date of Last Commit)
 
 * Updated the median umi per cell metric for STARsolo library-level metrics
 
 # 6.6.0
-20240315 (Date of Last Commit)
+2024-03-15 (Date of Last Commit)
 
 * Added cell metrics to the library-level metrics
 

pipelines/skylab/optimus/Optimus.wdl

@@ -30,7 +30,7 @@ workflow Optimus {
     File tar_star_reference
     File annotations_gtf
     File? mt_genes
-    String? soloMultiMappers
+    String? soloMultiMappers = "Uniform"
 
     # Chemistry options include: 2 or 3
     Int tenx_chemistry_version
@@ -65,7 +65,7 @@ workflow Optimus {
   # version of this pipeline
 
 
-  String pipeline_version = "6.6.1"
+  String pipeline_version = "6.6.2"
 
 
   # this is used to scatter matched [r1_fastq, r2_fastq, i1_fastq] arrays

pipelines/skylab/paired_tag/PairedTag.changelog.md

@@ -1,3 +1,9 @@
+# 0.5.1
+2024-04-12 (Date of Last Commit)
+
+* Updated the input parameters for STARsolo in STARsoloFastq task. These include the parameters: soloCBmatchWLtype, soloUMIdedup and soloUMIfiltering
+* Added "Uniform" as the default string for STARsolo multimapping parameters
+
 # 0.5.0
 20240403 (Date of Last Commit)
 

pipelines/skylab/paired_tag/PairedTag.wdl

@@ -5,7 +5,7 @@ import "../../../pipelines/skylab/optimus/Optimus.wdl" as optimus
 import "../../../tasks/skylab/H5adUtils.wdl" as H5adUtils
 import "../../../tasks/skylab/PairedTagUtils.wdl" as Demultiplexing
 workflow PairedTag {
-    String pipeline_version = "0.5.0"
+    String pipeline_version = "0.5.1"
 
     input {
         String input_id

pipelines/skylab/slideseq/SlideSeq.changelog.md

@@ -1,10 +1,15 @@
+# 3.1.5
+2024-04-12 (Date of Last Commit)
+
+* Updated the input parameters for STARsolo in STARsoloFastq task. These include the parameters: soloCBmatchWLtype, soloUMIdedup and soloUMIfiltering
+
 # 3.1.4
-20240326 (Date of Last Commit)
+2024-03-26 (Date of Last Commit)
 
 * Updated the median umi per cell metric for STARsolo library-level metrics
 
 # 3.1.3
-20240315 (Date of Last Commit)
+2024-03-15 (Date of Last Commit)
 
 * Added cell metrics to the library-level metrics CSV; this does not impact the slide-seq pipeline
 

pipelines/skylab/slideseq/SlideSeq.wdl

@@ -23,7 +23,7 @@ import "../../../tasks/skylab/MergeSortBam.wdl" as Merge
 
 workflow SlideSeq {
 
-    String pipeline_version = "3.1.4"
+    String pipeline_version = "3.1.5"
 
     input {
         Array[File] r1_fastq

pipelines/skylab/smartseq2_single_nucleus_multisample/MultiSampleSmartSeq2SingleNucleus.changelog.md

@@ -1,10 +1,15 @@
+# 1.3.4
+2024-04-12 (Date of Last Commit)
+
+* Updated the input parameters for STARsolo in STARsoloFastq task. These include the parameters: soloCBmatchWLtype, soloUMIdedup and soloUMIfiltering
+
 # 1.3.3
-20240326 (Date of Last Commit)
+2024-03-26 (Date of Last Commit)
 
 * Updated the median umi per cell metric for STARsolo library-level metrics
 
 # 1.3.2
-20240315 (Date of Last Commit)
+2024-03-15 (Date of Last Commit)
 
 * Added cell metrics to the library-level metrics CSV; this does not impact the Single-nucleus Multi Sample Smartseq pipeline
 

pipelines/skylab/smartseq2_single_nucleus_multisample/MultiSampleSmartSeq2SingleNucleus.wdl

@@ -40,7 +40,7 @@ workflow MultiSampleSmartSeq2SingleNucleus {
       String? input_id_metadata_field
   }
   # Version of this pipeline
-  String pipeline_version = "1.3.3"
+  String pipeline_version = "1.3.4"
 
   if (false) {
      String? none = "None"

tasks/skylab/StarAlign.wdl

@@ -252,7 +252,7 @@ task STARsoloFastq {
   }
 
   command <<<
-    set -e
+       set -e
 
     UMILen=10
     CBLen=16
@@ -292,79 +292,43 @@ task STARsoloFastq {
         ## single cell or whole cell
         COUNTING_MODE="Gene"
         echo "Running in ~{counting_mode} mode. The Star parameter --soloFeatures will be set to $COUNTING_MODE"
-        STAR \
-        --soloType Droplet \
-        --soloStrand ~{star_strand_mode} \
-        --runThreadN ~{cpu} \
-        --genomeDir genome_reference \
-        --readFilesIn "~{sep=',' r2_fastq}" "~{sep=',' r1_fastq}" \
-        --readFilesCommand "gunzip -c" \
-        --soloCBwhitelist ~{white_list} \
-        --soloUMIlen $UMILen --soloCBlen $CBLen \
-        --soloFeatures $COUNTING_MODE \
-        --clipAdapterType CellRanger4 \
-        --outFilterScoreMin 30  \
-        --soloCBmatchWLtype 1MM_multi_Nbase_pseudocounts \
-        --soloUMIdedup 1MM_Directional_UMItools \
-        --outSAMtype BAM SortedByCoordinate \
-        --outSAMattributes UB UR UY CR CB CY NH GX GN sF \
-        --soloBarcodeReadLength 0 \
-        --soloCellReadStats Standard \
-        ~{"--soloMultiMappers " + soloMultiMappers}
     elif [[ "~{counting_mode}" == "sn_rna" ]]
     then
         ## single nuclei
         if [[ ~{count_exons} == false ]]
         then
             COUNTING_MODE="GeneFull_Ex50pAS"
             echo "Running in ~{counting_mode} mode. Count_exons is false and the Star parameter --soloFeatures will be set to $COUNTING_MODE"
-            STAR \
-            --soloType Droplet \
-            --soloStrand ~{star_strand_mode} \
-            --runThreadN ~{cpu} \
-            --genomeDir genome_reference \
-            --readFilesIn "~{sep=',' r2_fastq}" "~{sep=',' r1_fastq}" \
-            --readFilesCommand "gunzip -c" \
-            --soloCBwhitelist ~{white_list} \
-            --soloUMIlen $UMILen --soloCBlen $CBLen \
-            --soloFeatures $COUNTING_MODE  \
-            --clipAdapterType CellRanger4 \
-            --outFilterScoreMin 30  \
-            --soloCBmatchWLtype 1MM_multi_Nbase_pseudocounts \
-            --soloUMIdedup 1MM_Directional_UMItools \
-            --outSAMtype BAM SortedByCoordinate \
-            --outSAMattributes UB UR UY CR CB CY NH GX GN sF \
-            --soloBarcodeReadLength 0 \
-            --soloCellReadStats Standard \
-            ~{"--soloMultiMappers " + soloMultiMappers}
         else
             COUNTING_MODE="GeneFull_Ex50pAS Gene"
-            echo "Running in ~{counting_mode} mode. Count_exons is true and the Star parameter --soloFeatures will be set to $COUNTING_MODE"
-            STAR \
-            --soloType Droplet \
-            --soloStrand ~{star_strand_mode} \
-            --runThreadN ~{cpu} \
-            --genomeDir genome_reference \
-            --readFilesIn "~{sep=',' r2_fastq}" "~{sep=',' r1_fastq}" \
-            --readFilesCommand "gunzip -c" \
-            --soloCBwhitelist ~{white_list} \
-            --soloUMIlen $UMILen --soloCBlen $CBLen \
-            --soloFeatures $COUNTING_MODE \
-            --clipAdapterType CellRanger4 \
-            --outFilterScoreMin 30  \
-            --soloCBmatchWLtype 1MM_multi_Nbase_pseudocounts \
-            --soloUMIdedup 1MM_Directional_UMItools \
-            --outSAMtype BAM SortedByCoordinate \
-            --outSAMattributes UB UR UY CR CB CY NH GX GN sF \
-            --soloBarcodeReadLength 0 \
-            --soloCellReadStats Standard \
-            ~{"--soloMultiMappers " + soloMultiMappers}
+            echo "Running in ~{counting_mode} mode. Count_exons is true and the Star parameter --soloFeatures will be set to $COUNTING_MODE"     
         fi
     else
         echo Error: unknown counting mode: "$counting_mode". Should be either sn_rna or sc_rna.
         exit 1;
     fi
 
+    STAR \
+        --soloType Droplet \
+        --soloStrand ~{star_strand_mode} \
+        --runThreadN ~{cpu} \
+        --genomeDir genome_reference \
+        --readFilesIn "~{sep=',' r2_fastq}" "~{sep=',' r1_fastq}" \
+        --readFilesCommand "gunzip -c" \
+        --soloCBwhitelist ~{white_list} \
+        --soloUMIlen $UMILen --soloCBlen $CBLen \
+        --soloFeatures $COUNTING_MODE \
+        --clipAdapterType CellRanger4 \
+        --outFilterScoreMin 30  \
+        --soloCBmatchWLtype 1MM_multi \
+        --soloUMIdedup 1MM_CR \
+        --outSAMtype BAM SortedByCoordinate \
+        --outSAMattributes UB UR UY CR CB CY NH GX GN sF \
+        --soloBarcodeReadLength 0 \
+        --soloCellReadStats Standard \
+        ~{"--soloMultiMappers " + soloMultiMappers} \
+        --soloUMIfiltering MultiGeneUMI_CR
+
     echo "UMI LEN " $UMILen
 
     touch barcodes_sn_rna.tsv