X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=bp_scripts%2FQA_454_report.rb;h=905bfc33fef791be3e6cffde9c4388210dcaa1f8;hb=5de6112b70b59420b245ce636a8b2e3c90acbe00;hp=362c728289c406fea726167ee470a25578ec7650;hpb=af576f0bbbb660f3943d72e7b67fe1d77c76f706;p=biopieces.git

diff --git a/bp_scripts/QA_454_report.rb b/bp_scripts/QA_454_report.rb
index 362c728..905bfc3 100755
--- a/bp_scripts/QA_454_report.rb
+++ b/bp_scripts/QA_454_report.rb
@@ -45,8 +45,7 @@ class Report
 
     def initialize(sff_file, tmpdir)
       @sff_file  = sff_file
-      @out1_file = File.join(tmpdir, "out1.txt")
-      @out2_file = File.join(tmpdir, "out2.txt")
+      @anal_file = File.join(tmpdir, "out1.txt")
       @count     = 0
       @min       = 0
       @max       = 0
@@ -58,7 +57,6 @@ class Report
 
       bp_seq_analyze
       parse_analyze_vals
-      parse_mean_vals
     end
 
     private
@@ -68,38 +66,24 @@ class Report
       system(
         "read_sff -i #{@sff_file} |
          progress_meter |
-         analyze_vals -k SEQ -o #{@out1_file} |
          analyze_seq |
-         mean_vals -k 'GC%,HARD_MASK%,SOFT_MASK%' -o #{@out2_file} -x"
+         analyze_vals -k SEQ,GC%,HARD_MASK%,SOFT_MASK% -x |
+         write_tab -o #{@anal_file} -x"
        )
       STDERR.puts "done.\n"
     end
 
     def parse_analyze_vals
-      File.open(@out1_file, "r") do |ios|
+      File.open(@anal_file, "r") do |ios|
         while not ios.eof?
-          line = ios.readline.chomp
-
-          case line
-          when /COUNT\s+(\d+)/; then @count = $1
-          when /MIN\s+(\d+)/;   then @min   = $1
-          when /MAX\s+(\d+)/;   then @max   = $1
-          when /MEAN\s+(\d+)/;  then @mean  = $1
-          when /SUM\s+(\d+)/;   then @bases = $1
-          end
-        end
-      end
-    end
-
-    def parse_mean_vals
-      File.open(@out2_file, "r") do |ios|
-        while not ios.eof?
-          line = ios.readline.chomp
-
-          case line
-          when /GC%_MEAN: (.+)/;        then @gc   = $1
-          when /HARD_MASK%_MEAN: (.+)/; then @hard = $1
-          when /SOFT_MASK%_MEAN: (.+)/; then @soft = $1
+          line   = ios.readline.chomp
+          fields = line.split("\t")
+
+          case fields.first
+          when "SEQ"        then @count, @min, @max, @bases, @mean = fields[2 .. 6]
+          when "GC%"        then @gc   = fields[6]
+          when "HARD_MASK%" then @hard = fields[6]
+          when "SOFT_MASK%" then @soft = fields[6]
           end
         end
       end
@@ -107,7 +91,7 @@ class Report
   end
 
   class PlotData
-    attr_reader :lendist_unclipped, :lendist_clipped, :scores_unclipped, :scores_clipped, :mean_scores, :nucleotide_dist
+    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
@@ -117,15 +101,17 @@ class Report
       @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)
-      @nucleotide_dist   = png2base64(@plot6)
+      @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
@@ -141,8 +127,10 @@ class Report
          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} |
+         extract_seq -l 500 |
+         plot_nucleotide_distribution -c -t png -o #{@plot6} |
          extract_seq -l 50 |
-         plot_nucleotide_distribution -t png -o #{@plot6} -x"
+         plot_nucleotide_distribution -t png -o #{@plot7} -x"
       )
       STDERR.puts "done.\n"
     end
@@ -306,7 +294,9 @@ template = %{
       </table>
       <h2>Residue frequency analysis</h2>
       <p>Plot of nucleotide distribution in percent of the first 50 bases:</p>
-      <p><img alt="plot_nucleotide_distribution" src="<%= @plots.nucleotide_dist %>" width="600" /></p>
+      <p><img alt="plot_nucleotide_distribution" src="<%= @plots.nucleotide_dist50 %>" width="600" /></p>
+      <p>Plot of nucleotide distribution in percent of the first 500 bases:</p>
+      <p><img alt="plot_nucleotide_distribution" src="<%= @plots.nucleotide_dist500 %>" width="600" /></p>
     </body>
   </html>
 }.gsub(/^\s+/, '')