nugen_barcode_splitter 0.0.17 → 0.0.18

data/bin/nugen_barcode_splitter

@@ -147,13 +147,13 @@ 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
+    #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()

data/lib/nugen_barcode_splitter/merger.rb

@@ -3,8 +3,6 @@ require "zlib"
 class Merger
   def initialize(fwd,rev,outdir,number,barcodes)
     # get sampleID
-    @values_fwd = []
-    @values_rev = []
     @sample_ids = []
     i = 0
     File.open(barcodes).each do |line|
@@ -19,7 +17,7 @@ class Merger
     @number = number
   end
 
-  attr_accessor :sample_ids, :values_fwd, :values_rev
+  attr_accessor :sample_ids
 
   #def prepare_hash()
   #  @sample_ids.each_with_index do |sample_id, i|
@@ -61,7 +59,7 @@ 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")
+      #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')
@@ -74,11 +72,12 @@ class Merger
       fwd_name = fwd_line.split(" ")
       marker = true
 
+
       @sample_ids.each_with_index do |sample_id, i|
-        if !fwd_splitted_files[i].eof?
+        if !fwd_splitted_files[i].eof? && marker
           compare_line_fwd = fwd_splitted_files[i].readline()
           name_compare_fwd = compare_line_fwd.split(" ")
-          if fwd_name[0] == name_compare_fwd[0] && marker
+          if fwd_name[0] == name_compare_fwd[0]
             marker = false
             statistics[i] += 1
             fwd_out_files[i].write(fwd_line)
@@ -94,49 +93,52 @@ class Merger
             fwd_file.lineno = fwd_file.lineno - 1
             rev_file.lineno = rev_file.lineno - 1
           else
-            #puts compare_line_fwd
             fwd_splitted_files[i].pos = fwd_splitted_files[i].pos - compare_line_fwd.length()
           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?
-          compare_line_rev = rev_splitted_files[i].readline()
-          name_compare_rev = compare_line_rev.split(" ")
-          if rev_name[0] == name_compare_rev[0] && marker
-            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 && !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)

data/test/test_mutations_caller_pipeline.rb

@@ -11,7 +11,7 @@ class NugenBarcodeSplitterTest < Test::Unit::TestCase
     assert template.to_s.include?("fastq-multx")
     assert template.to_s.include?("<%= @read %>")
     temp = template.fill("Lane_3", "33", "~/Lane3/", "bc", "fwd", true)
-    assert_equal(temp.to_s, "fastq-multx   bc \\\n  <(gunzip -c fwd) \\\n  -o ~/Lane3//R1_33.%.fq  \\\n  >> ~/Lane3//nugen_demultiplexing.log\n")
+    assert_equal(temp.to_s, "gunzip -c fwd | fastq-multx \\\n  --bcfile bc  --bol \\\n  --prefix ~/Lane3//R1_33. \\\n  --suffix \".fq\"\n")
   end
 
   def test_fastq
@@ -54,12 +54,17 @@ 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"])
+    #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")
     stats = merger.merge()
-    assert_equal([28, 18, 26, 21, 7],stats)
     #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: 0.0.17
+  version: 0.0.18
   prerelease: 
 platform: ruby
 authors: