nugen_barcode_splitter 0.0.18 → 1.0.0

data/bin/nugen_barcode_splitter

@@ -5,7 +5,7 @@ require "nugen_barcode_splitter"
 require "fileutils"
 
 usage =<<EOF
-      V E R S I O N - 0 . 0 . 17 - BETA
+      V E R S I O N - 1 . 0 . 0
       #{$0} [options] -p project_dir -o out_dir -c sample_sheet_nugen
 _____________________________________________________________________________
 
@@ -33,7 +33,7 @@ options = {
   :bel_only? => "",
   :mismatches => "",
   :keep_barcode => "",
-  :fastq_multx => "fastq_multx",
+  :fastx => "fastq_multx",
   :debug => false,
   :lane_number => ""
 }
@@ -79,8 +79,8 @@ optparse = OptionParser.new do |opts|
     options[:lane_number] = i if i
   end
 
-  opts.on("-x", "--fastq_multx DIR", String) do |i|
-    options[:fastq_multx] = i if i
+  opts.on("-x", "--fastx_barcode_splitter.pl DIR", String) do |i|
+    options[:fastx] = i if i
   end
 
   opts.on("-d", "--debug", "Debug mode!") do |i|
@@ -117,7 +117,7 @@ sample_sheet.create_barcode_txt("#{options[:out_dir]}/barcode")
 
 # Prepare template
 multx_opts = "#{options[:keep_barcode]} #{options[:eol_only]} #{options[:bol_only]} #{options[:mismatches]}"
-nugen_temp = NugenTemplate.new(options[:fastq_multx],multx_opts)
+nugen_temp = NugenTemplate.new(options[:fastx],multx_opts)
 
 Dir.glob(options[:project_dir]+"/*").each do |p|
   next unless File.directory? p
@@ -147,24 +147,18 @@ Dir.glob(options[:project_dir]+"/*").each do |p|
       status = system('bash', '-c', cmd)
       raise "Calling the template for fwd did not succeed!" if !status
     end
-    #cmd = nugen_temp.fill(lane,number,outdir, barcodes, rev, false)
-    #if options[:debug]
-    #  STDERR.puts cmd if options[:debug]
-    #else
-    #  status = system('bash', '-c', cmd)
-    #  raise "Calling the template for rev did not succeed!" if !status
-    #end
+
     # Merging
     merger = Merger.new(fwd,rev,outdir,number,barcodes)
     stats = merger.merge()
-    stats_file = File.open("#{outdir}/nugen_demultiplexing.log", 'a')
+    stats_file = File.open("#{outdir}/nugen_demultiplexing_Lane#{lane}.log", 'a')
     stats_file.write(stats)
     stats_file.close()
   end
 
   # Add the trimmed bases
   Dir.glob(outdir+"/*").each do |f|
-    if f =~ /nugen_demultiplexing.log/
+    if f =~ /nugen_demultiplexing/
       sample_sheet.lanes
       statistics = Statistics.new(f)
       stats_out = outdir + "/statistics"
@@ -189,6 +183,13 @@ Dir.glob(options[:project_dir]+"/*").each do |p|
       status = system(cmd)
       raise "Was not able to rename and move file #{f}!" if status!=true
     end
+    cmd = "gzip #{sample_dir}/#{name}"
+    if options[:debug]
+      STDERR.puts cmd if options[:debug]
+    else
+      status = system(cmd)
+      raise "Was not able to gzip file #{f}"
+    end
   end
 
 end

data/lib/nugen_barcode_splitter/merger.rb

@@ -19,39 +19,11 @@ class Merger
 
   attr_accessor :sample_ids
 
-  #def prepare_hash()
-  #  @sample_ids.each_with_index do |sample_id, i|
-  #    a = Thread.new {
-  #      filehandler = File.open(@outdir+"/R1_#{@number}.#{sample_id}.fq")
-  #      filehandler.each do |line|
-  #        next unless line.include?("@HWI-")
-  #        line = line.split(" ")
-  #        name = line[0].split(":")[4..-1].join(":")
-  #        @values_fwd[i].store(name,filehandler.pos)
-  #      end
-  #      filehandler.close()
-  #    }
-  #    b = Thread.new {
-  #      filehandler = File.open(@outdir+"/R2_#{@number}.#{sample_id}.fq")
-  #      filehandler.each do |line|
-  #        next unless line.include?("@HWI-")
-  #        line = line.split(" ")
-  #        name = line[0].split(":")[4..-1].join(":")
-  #        @values_rev[i].store(name,filehandler.pos)
-  #      end
-  #      filehandler.close()
-  #    }
-  #    a.join
-  #    b.join
-  #  end
-  #end
-
   def merge()
     statistics = Array.new(@sample_ids.length()+2,0)
     fwd_file = Zlib::GzipReader.open(@fwd)
     rev_file = Zlib::GzipReader.open(@rev)
     fwd_splitted_files = []
-    rev_splitted_files = []
     fwd_out_files = []
     rev_out_files = []
     fwd_out_unmatched = File.open(@outdir+"/R1_#{@number}.unmatched.updated.fq",'w')
@@ -59,8 +31,6 @@ class Merger
 
     @sample_ids.each_with_index do |sample_id, i|
       fwd_splitted_files[i] = File.open(@outdir+"/R1_#{@number}.#{sample_id}.fq")
-      #rev_splitted_files[i] = File.open(@outdir+"/R2_#{@number}.#{sample_id}.fq")
-      #OUTFILES????
       fwd_out_files[i] = File.open(@outdir+"/R1_#{@number}.#{sample_id}.updated.fq",'w')
       rev_out_files[i] = File.open(@outdir+"/R2_#{@number}.#{sample_id}.updated.fq",'w')
     end
@@ -72,7 +42,6 @@ class Merger
       fwd_name = fwd_line.split(" ")
       marker = true
 
-
       @sample_ids.each_with_index do |sample_id, i|
         if !fwd_splitted_files[i].eof? && marker
           compare_line_fwd = fwd_splitted_files[i].readline()
@@ -98,47 +67,6 @@ class Merger
         end
       end
 
-      #  if !marker && !rev_splitted_files[i].eof?
-      #    compare_line_rev = rev_splitted_files[i].readline()
-      #    name_compare_rev = compare_line_rev.split(" ")
-      #    if name_compare_rev[0] == name_compare_fwd[0]
-      #      for k in 1..3
-      #        compare_line_rev = rev_splitted_files[i].readline()
-      #      end
-      #    else
-      #      #puts compare_line_rev
-      #      rev_splitted_files[i].pos = rev_splitted_files[i].pos - compare_line_rev.length()
-      #    end
-      #  end
-      #  break if !marker
-      #  if !rev_splitted_files[i].eof? && marker
-      #    compare_line_rev = rev_splitted_files[i].readline()
-      #    name_compare_rev = compare_line_rev.split(" ")
-      #    puts "REV: " + compare_line_rev if i == 2
-      #    #puts name_compare_rev[0]
-      #    if rev_name[0] == name_compare_rev[0]
-      #      marker = false
-      #      statistics[i] += 1
-      #      fwd_out_files[i].write(fwd_line)
-      #      rev_out_files[i].write(rev_line)
-      #      for k in 1..3
-      #        rev_file.readline()
-      #        compare_line_rev = rev_splitted_files[i].readline()
-      #        rev_out_files[i].write(compare_line_rev.gsub(/[A-Z]{4}$/,"NNNN")) if k == 1
-      #        rev_out_files[i].write(compare_line_rev) if k == 2
-      #        rev_out_files[i].write(compare_line_rev.gsub(/[\S]{4}$/,"@@@@")) if k == 3
-      #        fwd_out_files[i].write(fwd_file.readline())
-      #      end
-      #      fwd_file.lineno = fwd_file.lineno - 1
-      #      rev_file.lineno = rev_file.lineno - 1
-      #    else
-      #      rev_splitted_files[i].pos = rev_splitted_files[i].pos - compare_line_rev.length()
-      #    end
-      #  end
-      #  break if !marker
-      #end
-
-
       if marker
         statistics[-2] += 1
         fwd_out_unmatched.write(fwd_line)
@@ -149,6 +77,10 @@ class Merger
         end
       end
     end
+    stats = make_stats(statistics)
+  end
+
+  def make_stats(statistics)
     stats = ""
     @sample_ids.each_with_index do |id,i|
       stats += id +"\t" + statistics[i].to_s + "\n"
@@ -156,4 +88,8 @@ class Merger
     stats += "unmatched\t" + statistics[-2].to_s + "\n"
     stats += "total\t" + statistics[-1].to_s + "\n"
   end
-end
+end
+
+
+
+

data/lib/nugen_barcode_splitter/statistics.rb

@@ -42,8 +42,8 @@ class Statistics
     @barcodes.each_with_index do |code, i|
       str += "#{code}:\t#{@num_reads[i]} \n"
     end
-    #percent = (100 / @total.to_f) * @num_unmatched.to_f
-    #percent = (percent.to_f * 100).round / 100.to_f
+    percent = (100 / @total.to_f) * @num_unmatched.to_f
+    percent = (percent.to_f * 100).round / 100.to_f
     str += "Unmatched:\t#{@num_unmatched}\n"
     str += "Total:\t#{@total}"
     str.to_s

data/test/test_mutations_caller_pipeline.rb

@@ -40,9 +40,7 @@ class NugenBarcodeSplitterTest < Test::Unit::TestCase
     samplesheet = SampleSheet.new("test/fixtures/sample_sheet.csv")
     assert_equal(samplesheet.barcodes[3], "TTAG")
     assert_equal(samplesheet.sample_id[4], "RX3")
-
     samplesheet.create_barcode_txt("test/fixtures/barcode")
-
   end
 
   def test_statistics
@@ -54,17 +52,11 @@ class NugenBarcodeSplitterTest < Test::Unit::TestCase
   end
 
   def test_merger
-    #merger = Merger.new("test/fixtures/Sample_Lane5/k.gz",
-    #  "test/fixtures/Sample_Lane5/l.gz",
-    #  "test/fixtures/Sample_Lane5", "001", "test/fixtures/barcode_5.txt")
-    #assert_equal(merger.sample_ids, ["RX3", "RX4", "RX3X2", "RX4X2"])
-    #stats = merger.merge()
-    #assert_equal("RX3\t18\nRX4\t7\nRX3X2\t16\nRX4X2\t8\nunmatched\t1\ntotal\t50\n",stats)
     merger = Merger.new("test/fixtures/Sample_Lane8/Lane8_NoIndex_L008_R1_019.fastq.gz",
       "test/fixtures/Sample_Lane8/Lane8_NoIndex_L008_R2_019.fastq.gz",
       "test/fixtures/Sample_Lane8", "019", "test/fixtures/barcode_8.txt")
+    assert_equal(["RX9", "RX10", "RX9X2", "RX10X2"], merger.sample_ids)
     stats = merger.merge()
-    #assert.equal(merger.values_fwd[1].value_at(),{"sfggf"=>"dffg"})
     assert_equal("RX9\t22464\nRX10\t28699\nRX9X2\t26434\nRX10X2\t22994\nunmatched\t15445\ntotal\t116036\n",stats)
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: nugen_barcode_splitter
 version: !ruby/object:Gem::Version
-  version: 0.0.18
+  version: 1.0.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,19 +9,17 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-02-22 00:00:00.000000000Z
+date: 2012-02-24 00:00:00.000000000Z
 dependencies: []
 description: ! "This gem is designed to demultiplex reads\n                     produced
   by Illumina with Nugen\n                     (http://www.nugeninc.com/nugen/) barcodes."
 email:
 - katharinaehayer@gmail.com
 executables:
-- base_adder
 - nugen_barcode_splitter
 extensions: []
 extra_rdoc_files: []
 files:
-- bin/base_adder
 - bin/nugen_barcode_splitter
 - lib/nugen_barcode_splitter.rb
 - lib/nugen_barcode_splitter/fastq.rb

data/bin/base_adder

@@ -1,22 +0,0 @@
-#!/usr/bin/env ruby
-require "nugen_barcode_splitter"
-
-usage =<<EOF
-  #{$0} file.fq number_of_bases out.fq
-
-  -_-_-_-_- #{$0} -_-_-_-_-
-
-  Adds N^P bases to the beginning of the
-  fastq file. The Quality is set on the
-  lowest value.
-EOF
-
-file_dir = ARGV[0]
-number_of_bases = ARGV[1].to_i
-out_dir = ARGV[2]
-
-fastq = Fastq.new("#{file_dir}")
-fastq.add(number_of_bases, out_dir)
-fastq.close
-
-