No more blacklist

.github/workflows/ci.yml

@@ -13,8 +13,8 @@ jobs:
           conda env create --quiet -n testenv -f environment.yml
       - name: Download test dataset
         run: |
-          wget -nv https://export.uppmax.uu.se/snic2020-6-3/minute-testdata/minute-testdata-0.4.tar.gz
-          tar xf minute-testdata-0.4.tar.gz
+          wget -nv https://export.uppmax.uu.se/snic2020-6-3/minute-testdata/minute-testdata-0.5.tar.gz
+          tar xf minute-testdata-0.5.tar.gz
       - name: Run pipeline
         run: |
           source $CONDA/etc/profile.d/conda.sh

Snakefile

@@ -242,7 +242,7 @@ rule remove_exclude_regions:
         bam="restricted/{library}.bam"
     input:
         bam="dedup/{library}.bam",
-        bed=config["blacklist_bed"]
+        bed=config["exclude_regions"],
     shell:
         "bedtools"
         " intersect"

config.yaml

@@ -6,7 +6,7 @@
 reference_fasta: "ref/mm9.fasta.gz"
 
 # Path to a BED file listing the regions to be excluded
-blacklist_bed: "dummy_blacklist.bed"
+exclude_regions: "exclude.bed"
 
 # Length of the 5' UMI
 umi_length: 6

minute-testdata/Snakefile

@@ -18,12 +18,12 @@ rule all:
         "inp_R2.fastq.gz",
         "ref.fa",
         "ref.chrom.sizes",
-        "blacklist.bed",
+        "exclude.bed",
 
 
-rule blacklist:
+rule exclude_regions:
     output:
-        bed="blacklist.bed"
+        bed="exclude.bed"
     run:
         with open(output.bed, "w") as f:
             print("mini", 3_100_000, 3_150_000, sep="\t", file=f)

minute-testdata/config.yaml

@@ -6,16 +6,22 @@
 reference_fasta: "ref.fa.gz"
 
 # Path to a BED file listing the regions to be excluded
-blacklist_bed: "blacklist.bed"
-
-# Chromosome lengths file (.chrom.sizes or .genome)
-chrom_sizes: "ref.chrom.sizes"
-
-# Effective genome size
-genome_size: 3700000
+exclude_regions: "exclude.bed"
 
 # Length of the 5' UMI
 umi_length: 6
 
 # Fragment length (insert size)
 fragment_size: 150
+
+
+#
+# Optional settings
+#
+# These usually don’t need to be changed
+#
+
+# The base name of the Bowtie2 index. This is normally found automatically
+# in the same folder as the reference_fasta.
+#
+# - bowtie_index_name: "ref/mm9"