nugen_barcode_splitter 0.0.17 → 0.0.18

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (4) hide show
  1. data/bin/nugen_barcode_splitter +7 -7
  2. data/lib/nugen_barcode_splitter/merger.rb +46 -44
  3. data/test/test_mutations_caller_pipeline.rb +11 -6
  4. metadata +1 -1
data/bin/nugen_barcode_splitter CHANGED
@@ -147,13 +147,13 @@ Dir.glob(options[:project_dir]+"/*").each do |p|
147
147
  status = system('bash', '-c', cmd)
148
148
  raise "Calling the template for fwd did not succeed!" if !status
149
149
  end
150
- cmd = nugen_temp.fill(lane,number,outdir, barcodes, rev, false)
151
- if options[:debug]
152
- STDERR.puts cmd if options[:debug]
153
- else
154
- status = system('bash', '-c', cmd)
155
- raise "Calling the template for rev did not succeed!" if !status
156
- end
150
+ #cmd = nugen_temp.fill(lane,number,outdir, barcodes, rev, false)
151
+ #if options[:debug]
152
+ # STDERR.puts cmd if options[:debug]
153
+ #else
154
+ # status = system('bash', '-c', cmd)
155
+ # raise "Calling the template for rev did not succeed!" if !status
156
+ #end
157
157
  # Merging
158
158
  merger = Merger.new(fwd,rev,outdir,number,barcodes)
159
159
  stats = merger.merge()
data/lib/nugen_barcode_splitter/merger.rb CHANGED
@@ -3,8 +3,6 @@ require "zlib"
3
3
  class Merger
4
4
  def initialize(fwd,rev,outdir,number,barcodes)
5
5
  # get sampleID
6
- @values_fwd = []
7
- @values_rev = []
8
6
  @sample_ids = []
9
7
  i = 0
10
8
  File.open(barcodes).each do |line|
@@ -19,7 +17,7 @@ class Merger
19
17
  @number = number
20
18
  end
21
19
 
22
- attr_accessor :sample_ids, :values_fwd, :values_rev
20
+ attr_accessor :sample_ids
23
21
 
24
22
  #def prepare_hash()
25
23
  # @sample_ids.each_with_index do |sample_id, i|
@@ -61,7 +59,7 @@ class Merger
61
59
 
62
60
  @sample_ids.each_with_index do |sample_id, i|
63
61
  fwd_splitted_files[i] = File.open(@outdir+"/R1_#{@number}.#{sample_id}.fq")
64
- rev_splitted_files[i] = File.open(@outdir+"/R2_#{@number}.#{sample_id}.fq")
62
+ #rev_splitted_files[i] = File.open(@outdir+"/R2_#{@number}.#{sample_id}.fq")
65
63
  #OUTFILES????
66
64
  fwd_out_files[i] = File.open(@outdir+"/R1_#{@number}.#{sample_id}.updated.fq",'w')
67
65
  rev_out_files[i] = File.open(@outdir+"/R2_#{@number}.#{sample_id}.updated.fq",'w')
@@ -74,11 +72,12 @@ class Merger
74
72
  fwd_name = fwd_line.split(" ")
75
73
  marker = true
76
74
 
75
+
77
76
  @sample_ids.each_with_index do |sample_id, i|
78
- if !fwd_splitted_files[i].eof?
77
+ if !fwd_splitted_files[i].eof? && marker
79
78
  compare_line_fwd = fwd_splitted_files[i].readline()
80
79
  name_compare_fwd = compare_line_fwd.split(" ")
81
- if fwd_name[0] == name_compare_fwd[0] && marker
80
+ if fwd_name[0] == name_compare_fwd[0]
82
81
  marker = false
83
82
  statistics[i] += 1
84
83
  fwd_out_files[i].write(fwd_line)
@@ -94,49 +93,52 @@ class Merger
94
93
  fwd_file.lineno = fwd_file.lineno - 1
95
94
  rev_file.lineno = rev_file.lineno - 1
96
95
  else
97
- #puts compare_line_fwd
98
96
  fwd_splitted_files[i].pos = fwd_splitted_files[i].pos - compare_line_fwd.length()
99
97
  end
100
98
  end
101
-
102
- if !marker && !rev_splitted_files[i].eof?
103
- compare_line_rev = rev_splitted_files[i].readline()
104
- name_compare_rev = compare_line_rev.split(" ")
105
- if name_compare_rev[0] == name_compare_fwd[0]
106
- for k in 1..3
107
- compare_line_rev = rev_splitted_files[i].readline()
108
- end
109
- else
110
- #puts compare_line_rev
111
- rev_splitted_files[i].pos = rev_splitted_files[i].pos - compare_line_rev.length()
112
- end
113
- end
114
- break if !marker
115
- if !rev_splitted_files[i].eof?
116
- compare_line_rev = rev_splitted_files[i].readline()
117
- name_compare_rev = compare_line_rev.split(" ")
118
- if rev_name[0] == name_compare_rev[0] && marker
119
- marker = false
120
- statistics[i] += 1
121
- fwd_out_files[i].write(fwd_line)
122
- rev_out_files[i].write(rev_line)
123
- for k in 1..3
124
- rev_file.readline()
125
- compare_line_rev = rev_splitted_files[i].readline()
126
- rev_out_files[i].write(compare_line_rev.gsub(/[A-Z]{4}$/,"NNNN")) if k == 1
127
- rev_out_files[i].write(compare_line_rev) if k == 2
128
- rev_out_files[i].write(compare_line_rev.gsub(/[\S]{4}$/,"@@@@")) if k == 3
129
- fwd_out_files[i].write(fwd_file.readline())
130
- end
131
- fwd_file.lineno = fwd_file.lineno - 1
132
- rev_file.lineno = rev_file.lineno - 1
133
- else
134
- rev_splitted_files[i].pos = rev_splitted_files[i].pos - compare_line_rev.length()
135
- end
136
- end
137
- break if !marker
138
99
  end
139
100
 
101
+ # if !marker && !rev_splitted_files[i].eof?
102
+ # compare_line_rev = rev_splitted_files[i].readline()
103
+ # name_compare_rev = compare_line_rev.split(" ")
104
+ # if name_compare_rev[0] == name_compare_fwd[0]
105
+ # for k in 1..3
106
+ # compare_line_rev = rev_splitted_files[i].readline()
107
+ # end
108
+ # else
109
+ # #puts compare_line_rev
110
+ # rev_splitted_files[i].pos = rev_splitted_files[i].pos - compare_line_rev.length()
111
+ # end
112
+ # end
113
+ # break if !marker
114
+ # if !rev_splitted_files[i].eof? && marker
115
+ # compare_line_rev = rev_splitted_files[i].readline()
116
+ # name_compare_rev = compare_line_rev.split(" ")
117
+ # puts "REV: " + compare_line_rev if i == 2
118
+ # #puts name_compare_rev[0]
119
+ # if rev_name[0] == name_compare_rev[0]
120
+ # marker = false
121
+ # statistics[i] += 1
122
+ # fwd_out_files[i].write(fwd_line)
123
+ # rev_out_files[i].write(rev_line)
124
+ # for k in 1..3
125
+ # rev_file.readline()
126
+ # compare_line_rev = rev_splitted_files[i].readline()
127
+ # rev_out_files[i].write(compare_line_rev.gsub(/[A-Z]{4}$/,"NNNN")) if k == 1
128
+ # rev_out_files[i].write(compare_line_rev) if k == 2
129
+ # rev_out_files[i].write(compare_line_rev.gsub(/[\S]{4}$/,"@@@@")) if k == 3
130
+ # fwd_out_files[i].write(fwd_file.readline())
131
+ # end
132
+ # fwd_file.lineno = fwd_file.lineno - 1
133
+ # rev_file.lineno = rev_file.lineno - 1
134
+ # else
135
+ # rev_splitted_files[i].pos = rev_splitted_files[i].pos - compare_line_rev.length()
136
+ # end
137
+ # end
138
+ # break if !marker
139
+ #end
140
+
141
+
140
142
  if marker
141
143
  statistics[-2] += 1
142
144
  fwd_out_unmatched.write(fwd_line)
data/test/test_mutations_caller_pipeline.rb CHANGED
@@ -11,7 +11,7 @@ class NugenBarcodeSplitterTest < Test::Unit::TestCase
11
11
  assert template.to_s.include?("fastq-multx")
12
12
  assert template.to_s.include?("<%= @read %>")
13
13
  temp = template.fill("Lane_3", "33", "~/Lane3/", "bc", "fwd", true)
14
- assert_equal(temp.to_s, "fastq-multx bc \\\n <(gunzip -c fwd) \\\n -o ~/Lane3//R1_33.%.fq \\\n >> ~/Lane3//nugen_demultiplexing.log\n")
14
+ assert_equal(temp.to_s, "gunzip -c fwd | fastq-multx \\\n --bcfile bc --bol \\\n --prefix ~/Lane3//R1_33. \\\n --suffix \".fq\"\n")
15
15
  end
16
16
 
17
17
  def test_fastq
@@ -54,12 +54,17 @@ class NugenBarcodeSplitterTest < Test::Unit::TestCase
54
54
  end
55
55
 
56
56
  def test_merger
57
- merger = Merger.new("test/fixtures/Sample_Lane5/k.gz",
58
- "test/fixtures/Sample_Lane5/l.gz",
59
- "test/fixtures/Sample_Lane5", "001", "test/fixtures/barcode_5.txt")
60
- assert_equal(merger.sample_ids, ["RX3", "RX4", "RX3X2", "RX4X2"])
57
+ #merger = Merger.new("test/fixtures/Sample_Lane5/k.gz",
58
+ # "test/fixtures/Sample_Lane5/l.gz",
59
+ # "test/fixtures/Sample_Lane5", "001", "test/fixtures/barcode_5.txt")
60
+ #assert_equal(merger.sample_ids, ["RX3", "RX4", "RX3X2", "RX4X2"])
61
+ #stats = merger.merge()
62
+ #assert_equal("RX3\t18\nRX4\t7\nRX3X2\t16\nRX4X2\t8\nunmatched\t1\ntotal\t50\n",stats)
63
+ merger = Merger.new("test/fixtures/Sample_Lane8/Lane8_NoIndex_L008_R1_019.fastq.gz",
64
+ "test/fixtures/Sample_Lane8/Lane8_NoIndex_L008_R2_019.fastq.gz",
65
+ "test/fixtures/Sample_Lane8", "019", "test/fixtures/barcode_8.txt")
61
66
  stats = merger.merge()
62
- assert_equal([28, 18, 26, 21, 7],stats)
63
67
  #assert.equal(merger.values_fwd[1].value_at(),{"sfggf"=>"dffg"})
68
+ assert_equal("RX9\t22464\nRX10\t28699\nRX9X2\t26434\nRX10X2\t22994\nunmatched\t15445\ntotal\t116036\n",stats)
64
69
  end
65
70
  end
metadata CHANGED
@@ -1,7 +1,7 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: nugen_barcode_splitter
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.0.17
4
+ version: 0.0.18
5
5
  prerelease:
6
6
  platform: ruby
7
7
  authors: