Lk add starsolo barcode metrics

pipelines/skylab/multiome/Multiome.changelog.md

@@ -1,5 +1,7 @@
-# 1.0.1
-2023-07-11 (Date of Last Commit)
+# 1.0.1 
+2023-07-23 (Date of Last Commit)
+
+* Added STARsolo v2.7.10b metric outputs as an optional pipeline output and an output of the STARalign and MergeSTAR tasks
 
 * Updated the CountAlignments task in the FeatureCounts.wdl to use a new docker image. This change does not affect the Multiome pipeline
 

pipelines/skylab/optimus/Optimus.changelog.md

@@ -1,4 +1,9 @@
 
+# 5.8.4
+2023-07-18 (Date of Last Commit)
+
+* Added STARsolo v2.7.10b metric outputs as an optional pipeline output and an output of the STARalign and MergeSTAR tasks
+
 # 5.8.3
 2023-06-23 (Date of Last Commit)
 

pipelines/skylab/optimus/Optimus.wdl

@@ -67,7 +67,7 @@ workflow Optimus {
 
   # version of this pipeline
 
-  String pipeline_version = "5.8.3"
+  String pipeline_version = "5.8.4"
 
   # this is used to scatter matched [r1_fastq, r2_fastq, i1_fastq] arrays
   Array[Int] indices = range(length(r1_fastq))
@@ -173,6 +173,7 @@ workflow Optimus {
       barcodes = STARsoloFastq.barcodes,
       features = STARsoloFastq.features,
       matrix = STARsoloFastq.matrix,
+      cell_reads = STARsoloFastq.cell_reads,
       input_id = input_id
   }
   if (counting_mode == "sc_rna"){
@@ -209,6 +210,7 @@ workflow Optimus {
         barcodes = STARsoloFastq.barcodes_sn_rna,
         features = STARsoloFastq.features_sn_rna,
         matrix = STARsoloFastq.matrix_sn_rna,
+        cell_reads = STARsoloFastq.cell_reads_sn_rna,
         input_id = input_id
     }
     call H5adUtils.SingleNucleusOptimusH5adOutput as OptimusH5adGenerationWithExons{
@@ -245,6 +247,7 @@ workflow Optimus {
     File gene_metrics = GeneMetrics.gene_metrics
     File? cell_calls = RunEmptyDrops.empty_drops_result
     File? picard_metrics = DropseqMetrics.metric_output
+    File? aligner_metrics = MergeStarOutputs.cell_reads_out
     # h5ad
     File h5ad_output_file = final_h5ad_output
   }

pipelines/skylab/slideseq/SlideSeq.changelog.md

@@ -1,3 +1,8 @@
+# 1.0.10
+2023-07-18 (Date of Last Commit)
+
+* Added STARsolo v2.7.10b metric outputs as an optional pipeline output and an output of the STARalign and MergeSTAR tasks. This does not impact the Slideseq pipeline
+
 # 1.0.9
 2023-06-14 (Date of Last Commit)
 

pipelines/skylab/slideseq/SlideSeq.wdl

@@ -23,7 +23,7 @@ import "../../../tasks/skylab/MergeSortBam.wdl" as Merge
 
 workflow SlideSeq {
 
-    String pipeline_version = "1.0.9"
+    String pipeline_version = "1.0.10"
 
     input {
         Array[File] r1_fastq

pipelines/skylab/smartseq2_single_nucleus_multisample/MultiSampleSmartSeq2SingleNucleus.changelog.md

@@ -1,8 +1,10 @@
 # 1.2.25
-2023-07-11 (Date of Last Commit)
+2023-07-18 (Date of Last Commit)
 
+* Added STARsolo v2.7.10b metric outputs as an optional pipeline output and an output of the STARalign and MergeSTAR tasks. This does not impact the snSS2 pipeline
 * Updated the CountAlignments task in the FeatureCounts.wdl to use a new docker image. This change does not affect the MultiSampleSmartSeq2SingleNucleus pipeline
 
+
 # 1.2.24
 2023-06-23 (Date of Last Commit)
 

tasks/skylab/StarAlign.wdl

@@ -318,7 +318,8 @@ task STARsoloFastq {
       --soloUMIdedup 1MM_Directional_UMItools \
       --outSAMtype BAM SortedByCoordinate \
       --outSAMattributes UB UR UY CR CB CY NH GX GN \
-      --soloBarcodeReadLength 0
+      --soloBarcodeReadLength 0 \
+      --soloCellReadStats Standard
     fi
 
     STAR \
@@ -337,36 +338,58 @@ task STARsoloFastq {
       --soloUMIdedup 1MM_Directional_UMItools \
       --outSAMtype BAM SortedByCoordinate \
       --outSAMattributes UB UR UY CR CB CY NH GX GN \
-      --soloBarcodeReadLength 0
+      --soloBarcodeReadLength 0 \
+      --soloCellReadStats Standard
 
     touch barcodes_sn_rna.tsv
     touch features_sn_rna.tsv
     touch matrix_sn_rna.mtx
+    touch CellReads_sn_rna.stats
+    touch Features_sn_rna.stats
+    touch Summary_sn_rna.csv
+    touch UMIperCellSorted_sn_rna.txt
 
     if [[ "~{counting_mode}" == "sc_rna" ]]
     then
       mv "Solo.out/Gene/raw/barcodes.tsv" barcodes.tsv
       mv "Solo.out/Gene/raw/features.tsv" features.tsv
       mv "Solo.out/Gene/raw/matrix.mtx"   matrix.mtx
+      mv "Solo.out/Gene/CellReads.stats" CellReads.stats
+      mv "Solo.out/Gene/Features.stats" Features.stats
+      mv "Solo.out/Gene/Summary.csv" Summary.csv
+      mv "Solo.out/Gene/UMIperCellSorted.txt" UMIperCellSorted.txt
     elif [[ "~{counting_mode}" == "sn_rna" ]]
     then
       if ! [[ ~{count_exons} ]]
       then
         mv "Solo.out/GeneFull_Ex50pAS/raw/barcodes.tsv" barcodes.tsv
         mv "Solo.out/GeneFull_Ex50pAS/raw/features.tsv" features.tsv
         mv "Solo.out/GeneFull_Ex50pAS/raw/matrix.mtx"   matrix.mtx
+        mv "Solo.out/GeneFull_Ex50pAS/CellReads.stats" CellReads.stats
+        mv "Solo.out/GeneFull_Ex50pAS/Features.stats" Features.stats
+        mv "Solo.out/GeneFull_Ex50pAS/Summary.csv" Summary.csv
+        mv "Solo.out/GeneFull_Ex50pAS/UMIperCellSorted.txt" UMIperCellSorted.txt
       else
         mv "Solo.out/GeneFull_Ex50pAS/raw/barcodes.tsv" barcodes.tsv
         mv "Solo.out/GeneFull_Ex50pAS/raw/features.tsv" features.tsv
         mv "Solo.out/GeneFull_Ex50pAS/raw/matrix.mtx"   matrix.mtx
+        mv "Solo.out/GeneFull_Ex50pAS/CellReads.stats" CellReads.stats
+        mv "Solo.out/GeneFull_Ex50pAS/Features.stats" Features.stats
+        mv "Solo.out/GeneFull_Ex50pAS/Summary.csv" Summary.csv
+        mv "Solo.out/GeneFull_Ex50pAS/UMIperCellSorted.txt" UMIperCellSorted.txt
         mv "Solo.out/Gene/raw/barcodes.tsv"     barcodes_sn_rna.tsv
         mv "Solo.out/Gene/raw/features.tsv"     features_sn_rna.tsv
         mv "Solo.out/Gene/raw/matrix.mtx"       matrix_sn_rna.mtx
+        mv "Solo.out/Gene/CellReads.stats" CellReads_sn_rna.stats
+        mv "Solo.out/Gene/Features.stats" Features_sn_rna.stats
+        mv "Solo.out/Gene/Summary.csv" Summary_sn_rna.csv
+        mv "Solo.out/Gene/UMIperCellSorted.txt" UMIperCellSorted_sn_rna.txt
       fi
     else
       echo Error: unknown counting mode: "$counting_mode". Should be either sn_rna or sc_rna.
     fi
     mv Aligned.sortedByCoord.out.bam ~{output_bam_basename}.bam
+    #tar -zcvf ~{output_bam_basename}.star_metrics.tar *.stats *.txt *.csv
 
   >>>
 
@@ -389,6 +412,15 @@ task STARsoloFastq {
     File barcodes_sn_rna = "barcodes_sn_rna.tsv"
     File features_sn_rna = "features_sn_rna.tsv"
     File matrix_sn_rna = "matrix_sn_rna.mtx"
+    File cell_reads = "CellReads.stats"
+    File align_features = "Features.stats"
+    File summary = "Summary.csv"
+    File umipercell = "UMIperCellSorted.txt"
+    File cell_reads_sn_rna = "CellReads_sn_rna.stats"
+    File align_features_sn_rna = "Features_sn_rna.stats"
+    File summary_sn_rna = "Summary_sn_rna.csv"
+    File umipercell_sn_rna = "UMIperCellSorted_sn_rna.txt"
+    #File aligner_metrics = "~{output_bam_basename}.star_metrics.tar"
   }
 }
 
@@ -398,6 +430,8 @@ task MergeStarOutput {
     Array[File] barcodes
     Array[File] features
     Array[File] matrix
+    Array[File]? cell_reads
+
     String input_id
 
     #runtime values
@@ -424,6 +458,14 @@ task MergeStarOutput {
     declare -a barcodes_files=(~{sep=' ' barcodes})
     declare -a features_files=(~{sep=' ' features})
     declare -a matrix_files=(~{sep=' ' matrix})
+    declare -a cell_reads_files=(~{sep=' ' cell_reads})
+
+    for cell_read in "${cell_reads_files[@]}"; do
+      if [ -f "$cell_read" ]; then
+        cat "$cell_read" >> "~{input_id}_cell_reads.txt"
+      fi
+    done
+
 
    # create the  compressed raw count matrix with the counts, gene names and the barcodes
     python3 /usr/gitc/create-merged-npz-output.py \
@@ -446,6 +488,7 @@ task MergeStarOutput {
     File row_index = "~{input_id}_sparse_counts_row_index.npy"
     File col_index = "~{input_id}_sparse_counts_col_index.npy"
     File sparse_counts = "~{input_id}_sparse_counts.npz"
+    File? cell_reads_out = "~{input_id}_cell_reads.txt"
   }
 }