Small formatting changes, update chagelog

CHANGELOG.md

@@ -48,6 +48,9 @@
     - `samtools/samtools_view`: Views and converts SAM/BAM/CRAM files (PR #48).
     - `samtools/samtools_fastq`: Converts a SAM/BAM/CRAM file to FASTQ (PR #52).
 
+* `umi_tools`:
+    -`umi_tools/umi_tools_extract`: Flexible removal of UMI sequences from fastq reads (PR #71).
+
 * `falco`: A C++ drop-in replacement of FastQC to assess the quality of sequence read data (PR #43).
 
 

src/umi_tools/umi_tools_extract/config.vsh.yaml

@@ -32,7 +32,7 @@ argument_groups:
       description: |
         Whitelist of accepted cell barcodes tab-separated format, where column 1 is the whitelisted
         cell barcodes and column 2 is the list (comma-separated) of other cell barcodes which should 
-        be corrected to the barcode in column 1. If the --error-correct-cell option is not used, this
+        be corrected to the barcode in column 1. If the --error_correct_cell option is not used, this
         column will be ignored.
     - name: --blacklist
       type: file
@@ -71,9 +71,9 @@ argument_groups:
     - name: --ignore_read_pair_suffixes
       type: boolean_true
       description: |
-        Ignore SOH and STX read name suffixes. Note that this options is required if the suffixes are not whitespace
+        Ignore "/1" and "/2" read name suffixes. Note that this options is required if the suffixes are not whitespace
         separated from the rest of the read name
-        
+
   - name: Input
     arguments: 
     - name: --paired

src/umi_tools/umi_tools_extract/script.sh

@@ -16,16 +16,17 @@ test_dir="${metal_executable}/test_data"
 [[ "$par_log2stderr" == "false" ]] && unset par_log2stderr
 
 
+# Check if we have the correct number of input files and patterns for paired-end or single-end reads
+
+# For paired-end rends, check that we have two read files, two patterns
 if [ -n "$par_paired" ]; then
-    # For paired-end rendscheck that we have two read files, two patterns
     if [ -z "$par_input" ] || [ -z "$par_read2_in" ] ||
        [ -z "$par_bc_pattern" ] || [ -z "$par_bc_pattern2" ]; 
         then
         echo "Paired end input requires two read files, two UMI patterns, and two output files"
         exit 1
     fi
-else 
-    # For single-end reads, check that we have only one read file, one pattern
+else # For single-end reads, check that we have only one read file, one pattern
     if [ -n "$par_read2_in" ] || [ -n "$par_bc_pattern2" ]; then
         echo "Single end input requires one read file and one UMI pattern"
         exit 1
@@ -35,6 +36,7 @@ else
     fi
 fi
 
+
 umi_tools extract \
     -I "$par_input" \
     ${par_read2_in:+ --read2-in "$par_read2_in"} \

src/umi_tools/umi_tools_extract/test.sh

@@ -19,7 +19,6 @@ echo ">>> Test 1: Testing for paired-end reads"
     --umi_discard_read 0 \
     --read1_out scrb_seq_fastq.1.umi_extract.fastq.gz \
     --read2_out scrb_seq_fastq.2.umi_extract.fastq.gz \
-    --log log.out \
     --random_seed 1
 
 echo ">> Checking if the correct files are present"
@@ -50,7 +49,6 @@ echo ">>> Test 2: Testing for paired-end reads with umi_discard_reads option"
     --umitools_grouping_method directional \
     --umi_discard_read 2 \
     --read1_out scrb_seq_fastq.1.umi_extract.fastq.gz \
-    --log log.out \
     --random_seed 1
 
 echo ">> Checking if the correct files are present"
@@ -74,7 +72,6 @@ echo ">>> Test 3: Testing for single-end reads"
     --umitools_umi_separator '_' \
     --umitools_grouping_method directional \
     --read1_out slim.umi_extract.fastq.gz \
-    --log log.out \
     --random_seed 1 
 
 echo ">> Checking if the correct files are present"