X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=bp_scripts%2FQA_Illumina_report.rb;h=420294c08662e09d34fa0fa79b16450a3583653a;hb=256548158f770fa6b518a5cc86858655bdb910fe;hp=3139d49127b1e3a796c4e30cc819f3314df94f14;hpb=ee3e2d484f8cc105edc3aef2e12951350877ac43;p=biopieces.git

diff --git a/bp_scripts/QA_Illumina_report.rb b/bp_scripts/QA_Illumina_report.rb
index 3139d49..420294c 100755
--- a/bp_scripts/QA_Illumina_report.rb
+++ b/bp_scripts/QA_Illumina_report.rb
@@ -66,19 +66,19 @@ scores_bin_file                = File.join(tmpdir, 'scores_bin.png')
 STDERR.puts "Analyzing sequences ... "
 
 system(
-  "read_fastq -i #{seq_file} |
+  "read_fastq -e illumina1.8 -i #{seq_file} |
    progress_meter |
    analyze_vals -k SEQ -o #{analyze_vals_file} |
    trim_seq -l 3 -m 25 |
-   grab -e 'SEQ_LEN > 0' |
+   grab -e 'SEQ_LEN > 20' |
    analyze_vals -k SEQ -o #{analyze_vals_trim_file} |
-   find_adaptor -c 12 -l 6 -L 6 -f ACACGACGCTCTTCCGATCT -r AGATCGGAAGAGCACACGTC |
+   find_adaptor -l 6 -L 6 -f ACACGACGCTCTTCCGATCT -r AGATCGGAAGAGCACACGTC |
    clip_adaptor |
    grab -e 'SEQ_LEN > 0' |
    analyze_vals -k SEQ -o #{analyze_vals_trim_noadapt_file} |
    plot_distribution -k SEQ_LEN -T 'Sequence length distribution' -X 'Sequence length' -t png -o #{lendist_file} |
    plot_scores -c -t png -o #{scores_file} |
-   plot_nucleotide_distribution -t png -o #{nucdist_file} |
+   plot_nucleotide_distribution -c -t png -o #{nucdist_file} |
    bin_vals -k SEQ_LEN -b 25 |
    plot_distribution -T '25 bases bin sequence length distribution' -X 'Sequence length' -k SEQ_LEN_BIN -t png -o #{lendist_bin_file} |
    mean_scores |