Class: Merger

Inherits:
Object
  • Object
show all
Defined in:
lib/nugen_barcode_splitter/merger.rb

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(fwd, rev, outdir, number, barcodes) ⇒ Merger

Returns a new instance of Merger.



4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
 
# File 'lib/nugen_barcode_splitter/merger.rb', line 4

def initialize(fwd,rev,outdir,number,barcodes)
  # get sampleID
  @sample_ids = []
  i = 0
  File.open(barcodes).each do |line|
    next if line.include?("#")
    line = line.split(" ")
    @sample_ids[i] = line[0]
    i += 1
  end
  @fwd = fwd
  @rev = rev
  @outdir = outdir
  @number = number
end

Instance Attribute Details

#sample_ids ⇒ Object

Returns the value of attribute sample_ids.



20
21
22
 
# File 'lib/nugen_barcode_splitter/merger.rb', line 20

def sample_ids
  @sample_ids
end

Instance Method Details

#merge ⇒ Object

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



49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
 
# File 'lib/nugen_barcode_splitter/merger.rb', line 49

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')
  rev_out_unmatched = File.open(@outdir+"/R2_#{@number}.unmatched.updated.fq",'w')

  @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

  fwd_file.each do |fwd_line|
    statistics[-1] += 1
    rev_line = rev_file.readline()
    rev_name = rev_line.split(" ")
    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()
        name_compare_fwd = compare_line_fwd.split(" ")
        if fwd_name[0] == name_compare_fwd[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
            fwd_file.readline()
            compare_line_fwd = fwd_splitted_files[i].readline()
            fwd_out_files[i].write(compare_line_fwd.gsub(/^[A-Z]{4}/,"NNNN")) if k == 1
            fwd_out_files[i].write(compare_line_fwd) if k == 2
            fwd_out_files[i].write(compare_line_fwd.gsub(/^[\S]{4}/,"@@@@")) if k == 3
            rev_out_files[i].write(rev_file.readline())
          end
          fwd_file.lineno = fwd_file.lineno - 1
          rev_file.lineno = rev_file.lineno - 1
        else
          fwd_splitted_files[i].pos = fwd_splitted_files[i].pos - compare_line_fwd.length()
        end
      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)
      rev_out_unmatched.write(rev_line)
      for k in 1..3
        rev_out_unmatched.write(rev_file.readline())
        fwd_out_unmatched.write(fwd_file.readline())
      end
    end
  end
  stats = ""
  @sample_ids.each_with_index do |id,i|
    stats += id +"\t" + statistics[i].to_s + "\n"
  end
  stats += "unmatched\t" + statistics[-2].to_s + "\n"
  stats += "total\t" + statistics[-1].to_s + "\n"
end