X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=bp_scripts%2FQA_Illumina_report.rb;h=cc6269f1d79280aaf06ba76a20a40d6af204bffb;hb=5de6112b70b59420b245ce636a8b2e3c90acbe00;hp=c7061a527ab2ad3f28402f2c813fd0ef89397eda;hpb=2c9aea983d8a632d93316c073031c797747514e5;p=biopieces.git
diff --git a/bp_scripts/QA_Illumina_report.rb b/bp_scripts/QA_Illumina_report.rb
index c7061a5..cc6269f 100755
--- a/bp_scripts/QA_Illumina_report.rb
+++ b/bp_scripts/QA_Illumina_report.rb
@@ -23,13 +23,28 @@ require 'tmpdir'
require 'base64'
require 'erb'
+class Numeric
+ def commify
+ self.to_s.gsub(/(^[-+]?\d+?(?=(?>(?:\d{3})+)(?!\d))|\G\d{3}(?=\d))/, '\1,')
+ end
+end
+
def parse_analysis(file)
data = {}
File.open(file, 'r') do |ios|
ios.each do |line|
- key, val = line.chomp.split(' ')
- data[key] = val.to_i;
+ key, val = line.chomp.split(': ')
+ begin Integer(val)
+ val = val.to_i.commify
+ rescue
+ begin Float(val)
+ val = val.to_f.commify
+ rescue
+ end
+ end
+
+ data[key] = val
end
end
@@ -54,28 +69,33 @@ end
tmpdir = Dir.mktmpdir
seq_file = ARGV.shift
-analyze_vals_file = File.join(tmpdir, 'analyze_vals.txt')
-analyze_vals_trim_file = File.join(tmpdir, 'analyze_vals_trim.txt')
-lendist_file = File.join(tmpdir, 'lendist.png')
-scores_file = File.join(tmpdir, 'scores.png')
-nucdist_file = File.join(tmpdir, 'nucdist.png')
-lendist_bin_file = File.join(tmpdir, 'lendist_bin.png')
-scores_bin_file = File.join(tmpdir, 'scores_bin.png')
+analyze_vals_file = File.join(tmpdir, 'analyze_vals.txt')
+analyze_vals_trim_file = File.join(tmpdir, 'analyze_vals_trim_noadapt.txt')
+analyze_vals_trim_noadapt_file = File.join(tmpdir, 'analyze_vals_trim.txt')
+lendist_file = File.join(tmpdir, 'lendist.png')
+scores_file = File.join(tmpdir, 'scores.png')
+nucdist_file = File.join(tmpdir, 'nucdist.png')
+lendist_bin_file = File.join(tmpdir, 'lendist_bin.png')
+scores_bin_file = File.join(tmpdir, 'scores_bin.png')
STDERR.puts "Analyzing sequences ... "
system(
- "read_fastq -i #{seq_file} |
+ "read_fastq -e base_33 -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 -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} |
- bin_vals -k SEQ_LEN -b 50 |
- plot_distribution -T '50 bases bin sequence length distribution' -X 'Sequence length' -k SEQ_LEN_BIN -t png -o #{lendist_bin_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 |
bin_vals -k SCORES_MEAN -b 5 |
plot_distribution -k SCORES_MEAN_BIN -T '5 bin mean score distribution' -X 'Mean scores' -t png -o #{scores_bin_file} -x"
@@ -85,6 +105,7 @@ STDERR.puts "done.\n"
analysis1 = parse_analysis(analyze_vals_file)
analysis2 = parse_analysis(analyze_vals_trim_file)
+analysis3 = parse_analysis(analyze_vals_trim_noadapt_file)
template = %{
@@ -97,16 +118,16 @@ template = %{
File: <%= seq_file %>
Sequence composition
- | Before trimming | After trimming |
- | Number of sequences | <%= analysis1['COUNT'] %> | <%= analysis2['COUNT'] %> |
- | Number of bases | <%= analysis1['SUM'] %> | <%= analysis2['SUM'] %> |
- | Min sequence length | <%= analysis1['MIN'] %> | <%= analysis2['MIN'] %> |
- | Max sequence length | <%= analysis1['MAX'] %> | <%= analysis2['MAX'] %> |
- | Max sequence length | <%= analysis1['MEAN'] %> | <%= analysis2['MEAN'] %> |
+ | Before trimming | After trimming | After adaptor removal |
+ | Number of sequences | <%= analysis1['COUNT'] %> | <%= analysis2['COUNT'] %> | <%= analysis3['COUNT'] %> |
+ | Number of bases | <%= analysis1['SUM'] %> | <%= analysis2['SUM'] %> | <%= analysis3['SUM'] %> |
+ | Min sequence length | <%= analysis1['MIN'] %> | <%= analysis2['MIN'] %> | <%= analysis3['MIN'] %> |
+ | Max sequence length | <%= analysis1['MAX'] %> | <%= analysis2['MAX'] %> | <%= analysis3['MAX'] %> |
+ | Mean sequence length | <%= analysis1['MEAN'] %> | <%= analysis2['MEAN'] %> | <%= analysis3['MEAN'] %> |
Sequence trimming was performed by removing from the ends all residues until 3 consecutive
residues with quality score larger than or equal to 25.
- All plots are after sequence trimming.
+ All plots are after sequence trimming and adaptor removal.
Sequence length distribution
 %>)
 %>)