Changes from PR review. Remove awk part from sort command and other m…

…inor changes.

environment.yml

@@ -24,4 +24,3 @@ dependencies:
   - freebayes
   - ruamel.yaml
   - ema=0.6.2
-

src/blr/Snakefile

@@ -40,13 +40,11 @@ rule barcode_sort_fastq:
     input:
         fastq = "trimmed.barcoded.{nr}.fastq.gz"
     shell:
-        "pigz -cd {input.fastq} |"
+        "pigz -cd -p 1 {input.fastq} |"
         " paste - - - - |"
-        " awk -F ' ' '{{print $2,$0}}' |"
-        " sort -t ' ' -k1,1  |"
-        " cut -d' ' -f 2- |"
+        " sort -t ' ' -k2 |"
         " tr '\t' '\n' |"
-        " gzip > {output.fastq}"
+        " pigz > {output.fastq}"
 
 
 rule map_reads:

src/blr/blr.yaml

@@ -3,7 +3,7 @@ molecule_tag: MI  # Used to store molecule ID, same as 10x default.
 num_mol_tag: MN # Used to store number of molecules per barcode
 sequence_tag: RX    # Used to store original barcode sequence in bam file. 'RX' is 10x genomic default
 genome_reference:  # Path to indexed reference
-read_mapper: bowtie2  # Choose bwa, bowtie2, minimap2 and ema
+read_mapper: bowtie2  # Choose bwa, bowtie2, minimap2 or ema
 duplicate_marker: sambamba # Choose sambamba or samblaster
 barcode_max_dist: 2 # Max edit distance (Leveshtein distance) allowed to cluster two barcode sequences together
 max_molecules_per_bc: 260 # Max number of molecules allowed for a single barcode (removes if bc has > 260 molecules).

src/blr/rules/trim.smk

@@ -76,7 +76,7 @@ rule extract_DBS:
         " -j {threads}"
         " -m 19"
         " -M 21"
-	" --max-n 0"
+	    " --max-n 0"
         " -o {output.fastq}"
         " {input.fastq}"
         " > {log}"