Magdoll patch 11 (#39)

* Update examples.md added toy dataset (post segmentation) and 10x barcode list to be downloaded. fixed groupdedup command to use sorted BAM input * Update examples.md * Update examples.md update examples readme
PacificBiosciences · Aug 30, 2022 · 765a10f · 765a10f
1 parent b9067b7
commit 765a10f
Showing 1 changed file with 13 additions and 9 deletions.
diff --git a/docs/umi/examples.md b/docs/umi/examples.md
@@ -10,31 +10,35 @@ nav_order: 4
 This is an example of an end-to-end cmd-line-only workflow:
 
     # Download HiFi reads
-    $ wget https://downloads.pacbcloud.com/public/dataset/ISMB_workshop/singlecell/ccs.bam
+    $ wget https://downloads.pacbcloud.com/public/dataset/IsoSeq_sandbox/2022_pbmc_singlecell_mini/ccs.bam
+    $ wget https://downloads.pacbcloud.com/public/dataset/IsoSeq_sandbox/2022_pbmc_singlecell_mini/ccs.bam.pbi
 
-    # Download primers
+    # Download cDNA primers
     $ wget https://downloads.pacbcloud.com/public/dataset/ISMB_workshop/singlecell/primers.fasta
+
+    # Download cell barcode include list
+    $ wget https://downloads.pacbcloud.com/public/dataset/IsoSeq_sandbox/10x_barcodes/3M-february-2018-REVERSE-COMPLEMENTED.txt.gz
 
     # Check lima version to be >= 2.6.0
     $ lima --version
-    lima 2.6.0 (commit v2.6.0)
+    lima 2.6.0
 
-    # Check isoseq3 version to be >= 3.7.0
+    # Check isoseq3 version to be >= 3.8.0
     $ isoseq3 --version
-    isoseq3 3.7.0 (commit v3.7.0)
+    isoseq3 3.8.0 
 
     # cDNA primer removal and read orientation
-    $ lima --isoseq ccs.bam primers.fasta output.bam
+    $ lima --per-read --isoseq ccs.bam primers.fasta output.bam
 
     # Clip UMI and cell barcode
-    $ isoseq3 tag output.5p--3p.bam flt.bam --design T-8U-12B
+    $ isoseq3 tag output.5p--3p.bam flt.bam --design T-12U-16B
 
     # Remove poly(A) tails and concatemer
     $ isoseq3 refine flt.bam primers.fasta fltnc.bam --require-polya
 
     # Correct single cell barcodes based on an include list
-    $ isoseq3 correct --barcodes include.txt fltnc.bam corrected.bam
+    $ isoseq3 correct -B 3M-february-2018-REVERSE-COMPLEMENTED.txt.gz fltnc.bam corrected.bam
 
     # Deduplicate reads based on UMIs
     $ samtools sort -t CB corrected.bam -o corrected.sorted.bam
-    $ isoseq3 groupdedup corrected.bam dedup.bam --log-level INFO
+    $ isoseq3 groupdedup corrected.sorted.bam dedup.bam