X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=bp_scripts%2FQA_454_report.rb;h=8c079f379ba9de4f658a88214e4ed99245d3d55f;hb=48bea5c28b89dc5586d0bddb338ccd6ba23aa1f9;hp=d747fdbbe6199636a8d215558a276cb9c083a96b;hpb=eeacc1bbd2fd8eb3e4b581084b411305d88210d9;p=biopieces.git diff --git a/bp_scripts/QA_454_report.rb b/bp_scripts/QA_454_report.rb index d747fdb..8c079f3 100755 --- a/bp_scripts/QA_454_report.rb +++ b/bp_scripts/QA_454_report.rb @@ -31,7 +31,6 @@ class Report @seq_analysis = SeqAnalyze.new(@sff_file, tmpdir) @plots = PlotData.new(@sff_file, tmpdir) @table_mid_join = MidTable.new(@sff_file, tmpdir) - @table_freq = FreqTable.new(@sff_file, tmpdir) end # Support templating of member data. @@ -108,7 +107,7 @@ class Report end class PlotData - attr_reader :lendist_unclipped, :lendist_clipped, :scores_unclipped, :scores_clipped, :mean_scores + attr_reader :lendist_unclipped, :lendist_clipped, :scores_unclipped, :scores_clipped, :mean_scores, :nucleotide_dist500, :nucleotide_dist50 def initialize(sff_file, tmpdir) @sff_file = sff_file @@ -117,14 +116,18 @@ class Report @plot3 = File.join(tmpdir, "plot3.png") @plot4 = File.join(tmpdir, "plot4.png") @plot5 = File.join(tmpdir, "plot5.png") + @plot6 = File.join(tmpdir, "plot6.png") + @plot7 = File.join(tmpdir, "plot7.png") bp_plot - @lendist_unclipped = png2base64(@plot1) - @lendist_clipped = png2base64(@plot3) - @scores_unclipped = png2base64(@plot2) - @scores_clipped = png2base64(@plot4) - @mean_scores = png2base64(@plot5) + @lendist_unclipped = png2base64(@plot1) + @lendist_clipped = png2base64(@plot3) + @scores_unclipped = png2base64(@plot2) + @scores_clipped = png2base64(@plot4) + @mean_scores = png2base64(@plot5) + @nucleotide_dist500 = png2base64(@plot6) + @nucleotide_dist50 = png2base64(@plot7) end def bp_plot @@ -133,13 +136,17 @@ class Report "read_sff -m -i #{@sff_file} | progress_meter | plot_distribution -k SEQ_LEN -T 'Length Distribution - unclipped' -t png -o #{@plot1} | - plot_scores -T 'Mean Quality Scores - unclipped' -t png -o #{@plot2} | + plot_scores -c -T 'Mean Quality Scores - unclipped' -t png -o #{@plot2} | clip_seq | plot_distribution -k SEQ_LEN -T 'Length Distribution - clipped' -t png -o #{@plot3} | - plot_scores -T 'Mean Quality Scores - clipped' -t png -o #{@plot4} | + plot_scores -c -T 'Mean Quality Scores - clipped' -t png -o #{@plot4} | mean_scores | bin_vals -k SCORES_MEAN -b 5 | - plot_histogram -s num -k SCORES_MEAN_BIN -T 'Mean score bins' -X 'Bins (size 5)' -Y 'Count' -t png -o #{@plot5} -x" + plot_histogram -s num -k SCORES_MEAN_BIN -T 'Mean score bins' -X 'Bins (size 5)' -Y 'Count' -t png -o #{@plot5} | + extract_seq -l 500 | + plot_nucleotide_distribution -c -t png -o #{@plot6} | + extract_seq -l 50 | + plot_nucleotide_distribution -t png -o #{@plot7} -x" ) STDERR.puts "done.\n" end @@ -247,52 +254,6 @@ class Report end end end - - class FreqTable - def initialize(sff_file, tmpdir) - @sff_file = sff_file - @tab_file = File.join(tmpdir, "freq.tab") - - bp_frequency_table - end - - def each - File.open(@tab_file, "r") do |ios| - while not ios.eof? do - fields = ios.readline.chomp.split("\t") - yield FreqRow.new(fields[0], fields[1], fields[2], fields[3], fields[4]) - end - end - end - - private - - def bp_frequency_table - STDERR.puts "Creating residue frequency table ... " - system( - "read_sff -i #{@sff_file} | - progress_meter | - extract_seq -l 50 | - uppercase_seq | - create_weight_matrix -p | - flip_tab | - write_tab -o #{@tab_file} -x" - ) - STDERR.puts "done.\n" - end - - class FreqRow - attr_reader :res_A, :res_C, :res_G, :res_N, :res_T - - def initialize(res_A, res_C, res_G, res_N, res_T) - @res_A = res_A - @res_C = res_C - @res_G = res_G - @res_N = res_N - @res_T = res_T - end - end - end end template = %{ @@ -348,18 +309,10 @@ template = %{ <% end %>

Residue frequency analysis

-

The below table contains the residue frequency (in percent) of the first 50 bases:

- - <% @table_freq.each do |row| %> - - - - - - - - <% end %> -
<%= row.res_A %><%= row.res_T %><%= row.res_C %><%= row.res_G %><%= row.res_N %>
+

Plot of nucleotide distribution in percent of the first 50 bases:

+

plot_nucleotide_distribution

+

Plot of nucleotide distribution in percent of the first 500 bases:

+

plot_nucleotide_distribution

}.gsub(/^\s+/, '')