seqtrimnext 2.0.29

Sign up to get free protection for your applications and to get access to all the features.
Files changed (115) hide show
  1. data/History.txt +3 -0
  2. data/Manifest.txt +114 -0
  3. data/PostInstall.txt +7 -0
  4. data/README.rdoc +159 -0
  5. data/Rakefile +38 -0
  6. data/bin/create_graphs.rb +46 -0
  7. data/bin/extract_seqs.rb +45 -0
  8. data/bin/extract_seqs_from_fasta.rb +56 -0
  9. data/bin/extract_seqs_from_fastq.rb +45 -0
  10. data/bin/fasta2fastq.rb +38 -0
  11. data/bin/fastq2fasta.rb +35 -0
  12. data/bin/gen_qual.rb +46 -0
  13. data/bin/get_seq.rb +46 -0
  14. data/bin/group_by_range.rb +17 -0
  15. data/bin/join_ilumina_paired.rb +130 -0
  16. data/bin/parse_amplicons.rb +95 -0
  17. data/bin/parse_json_results.rb +66 -0
  18. data/bin/parse_params.rb +82 -0
  19. data/bin/resume_clusters.rb +48 -0
  20. data/bin/resume_rejected.sh +9 -0
  21. data/bin/reverse_paired.rb +49 -0
  22. data/bin/seqtrimnext +368 -0
  23. data/bin/split_fastq.rb +42 -0
  24. data/bin/split_ilumina_paired.rb +65 -0
  25. data/bin/split_paired.rb +70 -0
  26. data/lib/seqtrimnext/actions/action_ab_adapter.rb +32 -0
  27. data/lib/seqtrimnext/actions/action_ab_far_adapter.rb +32 -0
  28. data/lib/seqtrimnext/actions/action_ab_left_adapter.rb +32 -0
  29. data/lib/seqtrimnext/actions/action_empty_insert.rb +22 -0
  30. data/lib/seqtrimnext/actions/action_ignore_repeated.rb +24 -0
  31. data/lib/seqtrimnext/actions/action_indetermination.rb +30 -0
  32. data/lib/seqtrimnext/actions/action_induced_low_complexity.rb +29 -0
  33. data/lib/seqtrimnext/actions/action_insert.rb +32 -0
  34. data/lib/seqtrimnext/actions/action_is_contaminated.rb +30 -0
  35. data/lib/seqtrimnext/actions/action_key.rb +30 -0
  36. data/lib/seqtrimnext/actions/action_left_adapter.rb +32 -0
  37. data/lib/seqtrimnext/actions/action_left_primer.rb +17 -0
  38. data/lib/seqtrimnext/actions/action_linker.rb +30 -0
  39. data/lib/seqtrimnext/actions/action_low_complexity.rb +30 -0
  40. data/lib/seqtrimnext/actions/action_low_high_size.rb +31 -0
  41. data/lib/seqtrimnext/actions/action_low_quality.rb +33 -0
  42. data/lib/seqtrimnext/actions/action_mid.rb +30 -0
  43. data/lib/seqtrimnext/actions/action_multiple_linker.rb +29 -0
  44. data/lib/seqtrimnext/actions/action_paired_reads.rb +28 -0
  45. data/lib/seqtrimnext/actions/action_poly_a.rb +29 -0
  46. data/lib/seqtrimnext/actions/action_poly_t.rb +29 -0
  47. data/lib/seqtrimnext/actions/action_rem_adit_artifacts.rb +32 -0
  48. data/lib/seqtrimnext/actions/action_right_adapter.rb +29 -0
  49. data/lib/seqtrimnext/actions/action_right_primer.rb +25 -0
  50. data/lib/seqtrimnext/actions/action_short_insert.rb +32 -0
  51. data/lib/seqtrimnext/actions/action_unexpected_poly_t.rb +29 -0
  52. data/lib/seqtrimnext/actions/action_unexpected_vector.rb +31 -0
  53. data/lib/seqtrimnext/actions/action_vectors.rb +31 -0
  54. data/lib/seqtrimnext/actions/seqtrim_action.rb +136 -0
  55. data/lib/seqtrimnext/classes/action_manager.rb +47 -0
  56. data/lib/seqtrimnext/classes/em_classes/seqtrim_work_manager.rb +335 -0
  57. data/lib/seqtrimnext/classes/em_classes/seqtrim_worker.rb +290 -0
  58. data/lib/seqtrimnext/classes/extract_stats.rb +255 -0
  59. data/lib/seqtrimnext/classes/gnu_plot_graph.rb +140 -0
  60. data/lib/seqtrimnext/classes/graph_stats.rb +74 -0
  61. data/lib/seqtrimnext/classes/install_database.rb +43 -0
  62. data/lib/seqtrimnext/classes/install_requirements.rb +123 -0
  63. data/lib/seqtrimnext/classes/list_db.rb +49 -0
  64. data/lib/seqtrimnext/classes/make_blast_db.rb +113 -0
  65. data/lib/seqtrimnext/classes/one_blast.rb +41 -0
  66. data/lib/seqtrimnext/classes/params.rb +387 -0
  67. data/lib/seqtrimnext/classes/piro.rb +78 -0
  68. data/lib/seqtrimnext/classes/plugin_manager.rb +153 -0
  69. data/lib/seqtrimnext/classes/scan_for_restr_site.rb +138 -0
  70. data/lib/seqtrimnext/classes/scbi_stats.rb +68 -0
  71. data/lib/seqtrimnext/classes/seqtrim.rb +317 -0
  72. data/lib/seqtrimnext/classes/sequence.rb +55 -0
  73. data/lib/seqtrimnext/classes/sequence_group.rb +72 -0
  74. data/lib/seqtrimnext/classes/sequence_with_action.rb +503 -0
  75. data/lib/seqtrimnext/plugins/plugin.rb +267 -0
  76. data/lib/seqtrimnext/plugins/plugin_ab_adapters.rb +189 -0
  77. data/lib/seqtrimnext/plugins/plugin_adapters.rb +165 -0
  78. data/lib/seqtrimnext/plugins/plugin_amplicons.rb +221 -0
  79. data/lib/seqtrimnext/plugins/plugin_contaminants.rb +209 -0
  80. data/lib/seqtrimnext/plugins/plugin_extract_inserts.rb +438 -0
  81. data/lib/seqtrimnext/plugins/plugin_find_poly_at.rb +393 -0
  82. data/lib/seqtrimnext/plugins/plugin_ignore_repeated.rb +101 -0
  83. data/lib/seqtrimnext/plugins/plugin_indeterminations.rb +199 -0
  84. data/lib/seqtrimnext/plugins/plugin_key.rb +70 -0
  85. data/lib/seqtrimnext/plugins/plugin_linker.rb +232 -0
  86. data/lib/seqtrimnext/plugins/plugin_low_complexity.rb +98 -0
  87. data/lib/seqtrimnext/plugins/plugin_low_high_size.rb +74 -0
  88. data/lib/seqtrimnext/plugins/plugin_low_quality.rb +394 -0
  89. data/lib/seqtrimnext/plugins/plugin_mids.rb +231 -0
  90. data/lib/seqtrimnext/plugins/plugin_rem_adit_artifacts.rb +246 -0
  91. data/lib/seqtrimnext/plugins/plugin_short_insert.rb +244 -0
  92. data/lib/seqtrimnext/plugins/plugin_vectors.rb +191 -0
  93. data/lib/seqtrimnext/templates/amplicons.txt +16 -0
  94. data/lib/seqtrimnext/templates/genomics_454.txt +5 -0
  95. data/lib/seqtrimnext/templates/genomics_454_with_paired.txt +5 -0
  96. data/lib/seqtrimnext/templates/low_quality.txt +5 -0
  97. data/lib/seqtrimnext/templates/low_quality_and_low_complexity.txt +5 -0
  98. data/lib/seqtrimnext/templates/transcriptomics_454.txt +8 -0
  99. data/lib/seqtrimnext/templates/transcriptomics_plants.txt +8 -0
  100. data/lib/seqtrimnext/utils/extract_samples.rb +52 -0
  101. data/lib/seqtrimnext/utils/fasta2xml.rb +69 -0
  102. data/lib/seqtrimnext/utils/global_match.rb +65 -0
  103. data/lib/seqtrimnext/utils/hash_stats.rb +29 -0
  104. data/lib/seqtrimnext/utils/json_utils.rb +50 -0
  105. data/lib/seqtrimnext/utils/load_fasta_names_in_hash.rb +37 -0
  106. data/lib/seqtrimnext/utils/load_qual_in_hash.rb +37 -0
  107. data/lib/seqtrimnext/utils/recover_mid.rb +95 -0
  108. data/lib/seqtrimnext/utils/string_utils.rb +56 -0
  109. data/lib/seqtrimnext.rb +37 -0
  110. data/script/console +10 -0
  111. data/script/destroy +14 -0
  112. data/script/generate +14 -0
  113. data/test/test_helper.rb +3 -0
  114. data/test/test_seqtrimnext.rb +11 -0
  115. metadata +318 -0
metadata ADDED
@@ -0,0 +1,318 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: seqtrimnext
3
+ version: !ruby/object:Gem::Version
4
+ prerelease:
5
+ version: 2.0.29
6
+ platform: ruby
7
+ authors:
8
+ - Dario Guerrero & Almudena Bocinos
9
+ autorequire:
10
+ bindir: bin
11
+ cert_chain: []
12
+
13
+ date: 2011-06-14 00:00:00 Z
14
+ dependencies:
15
+ - !ruby/object:Gem::Dependency
16
+ name: narray
17
+ prerelease: false
18
+ requirement: &id001 !ruby/object:Gem::Requirement
19
+ none: false
20
+ requirements:
21
+ - - ">="
22
+ - !ruby/object:Gem::Version
23
+ version: "0"
24
+ type: :runtime
25
+ version_requirements: *id001
26
+ - !ruby/object:Gem::Dependency
27
+ name: gnuplot
28
+ prerelease: false
29
+ requirement: &id002 !ruby/object:Gem::Requirement
30
+ none: false
31
+ requirements:
32
+ - - ">="
33
+ - !ruby/object:Gem::Version
34
+ version: "0"
35
+ type: :runtime
36
+ version_requirements: *id002
37
+ - !ruby/object:Gem::Dependency
38
+ name: term-ansicolor
39
+ prerelease: false
40
+ requirement: &id003 !ruby/object:Gem::Requirement
41
+ none: false
42
+ requirements:
43
+ - - ">="
44
+ - !ruby/object:Gem::Version
45
+ version: "0"
46
+ type: :runtime
47
+ version_requirements: *id003
48
+ - !ruby/object:Gem::Dependency
49
+ name: xml-simple
50
+ prerelease: false
51
+ requirement: &id004 !ruby/object:Gem::Requirement
52
+ none: false
53
+ requirements:
54
+ - - ">="
55
+ - !ruby/object:Gem::Version
56
+ version: "0"
57
+ type: :runtime
58
+ version_requirements: *id004
59
+ - !ruby/object:Gem::Dependency
60
+ name: scbi_blast
61
+ prerelease: false
62
+ requirement: &id005 !ruby/object:Gem::Requirement
63
+ none: false
64
+ requirements:
65
+ - - ">="
66
+ - !ruby/object:Gem::Version
67
+ version: "0"
68
+ type: :runtime
69
+ version_requirements: *id005
70
+ - !ruby/object:Gem::Dependency
71
+ name: scbi_mapreduce
72
+ prerelease: false
73
+ requirement: &id006 !ruby/object:Gem::Requirement
74
+ none: false
75
+ requirements:
76
+ - - ">="
77
+ - !ruby/object:Gem::Version
78
+ version: "0"
79
+ type: :runtime
80
+ version_requirements: *id006
81
+ - !ruby/object:Gem::Dependency
82
+ name: scbi_fasta
83
+ prerelease: false
84
+ requirement: &id007 !ruby/object:Gem::Requirement
85
+ none: false
86
+ requirements:
87
+ - - ">="
88
+ - !ruby/object:Gem::Version
89
+ version: "0"
90
+ type: :runtime
91
+ version_requirements: *id007
92
+ - !ruby/object:Gem::Dependency
93
+ name: scbi_fastq
94
+ prerelease: false
95
+ requirement: &id008 !ruby/object:Gem::Requirement
96
+ none: false
97
+ requirements:
98
+ - - ">="
99
+ - !ruby/object:Gem::Version
100
+ version: "0"
101
+ type: :runtime
102
+ version_requirements: *id008
103
+ - !ruby/object:Gem::Dependency
104
+ name: scbi_plot
105
+ prerelease: false
106
+ requirement: &id009 !ruby/object:Gem::Requirement
107
+ none: false
108
+ requirements:
109
+ - - ">="
110
+ - !ruby/object:Gem::Version
111
+ version: "0"
112
+ type: :runtime
113
+ version_requirements: *id009
114
+ - !ruby/object:Gem::Dependency
115
+ name: scbi_math
116
+ prerelease: false
117
+ requirement: &id010 !ruby/object:Gem::Requirement
118
+ none: false
119
+ requirements:
120
+ - - ">="
121
+ - !ruby/object:Gem::Version
122
+ version: "0"
123
+ type: :runtime
124
+ version_requirements: *id010
125
+ - !ruby/object:Gem::Dependency
126
+ name: hoe
127
+ prerelease: false
128
+ requirement: &id011 !ruby/object:Gem::Requirement
129
+ none: false
130
+ requirements:
131
+ - - ">="
132
+ - !ruby/object:Gem::Version
133
+ version: 2.8.0
134
+ type: :development
135
+ version_requirements: *id011
136
+ description: SeqtrimNEXT is a customizable and distributed pre-processing software for NGS (Next Generation Sequencing) biological data. It makes use of scbi_mapreduce gem to be able to run in parallel and distributed environments. It is specially suited for Roche 454 (normal and paired-end) & Ilumina datasets, although it could be easyly adapted to any other situation.
137
+ email:
138
+ - dariogf@gmail.com & alkoke@gmail.com
139
+ executables:
140
+ - create_graphs.rb
141
+ - extract_seqs.rb
142
+ - extract_seqs_from_fasta.rb
143
+ - extract_seqs_from_fastq.rb
144
+ - fasta2fastq.rb
145
+ - fastq2fasta.rb
146
+ - gen_qual.rb
147
+ - get_seq.rb
148
+ - group_by_range.rb
149
+ - join_ilumina_paired.rb
150
+ - parse_amplicons.rb
151
+ - parse_json_results.rb
152
+ - parse_params.rb
153
+ - resume_clusters.rb
154
+ - resume_rejected.sh
155
+ - reverse_paired.rb
156
+ - seqtrimnext
157
+ - split_fastq.rb
158
+ - split_ilumina_paired.rb
159
+ - split_paired.rb
160
+ extensions: []
161
+
162
+ extra_rdoc_files:
163
+ - lib/seqtrimnext/templates/amplicons.txt
164
+ - lib/seqtrimnext/templates/genomics_454.txt
165
+ - lib/seqtrimnext/templates/genomics_454_with_paired.txt
166
+ - lib/seqtrimnext/templates/low_quality.txt
167
+ - lib/seqtrimnext/templates/low_quality_and_low_complexity.txt
168
+ - lib/seqtrimnext/templates/transcriptomics_454.txt
169
+ - lib/seqtrimnext/templates/transcriptomics_plants.txt
170
+ - History.txt
171
+ - Manifest.txt
172
+ - PostInstall.txt
173
+ files:
174
+ - bin/create_graphs.rb
175
+ - bin/extract_seqs.rb
176
+ - bin/extract_seqs_from_fasta.rb
177
+ - bin/extract_seqs_from_fastq.rb
178
+ - bin/fasta2fastq.rb
179
+ - bin/fastq2fasta.rb
180
+ - bin/gen_qual.rb
181
+ - bin/get_seq.rb
182
+ - bin/group_by_range.rb
183
+ - bin/join_ilumina_paired.rb
184
+ - bin/parse_amplicons.rb
185
+ - bin/parse_json_results.rb
186
+ - bin/parse_params.rb
187
+ - bin/resume_clusters.rb
188
+ - bin/resume_rejected.sh
189
+ - bin/reverse_paired.rb
190
+ - bin/seqtrimnext
191
+ - bin/split_fastq.rb
192
+ - bin/split_ilumina_paired.rb
193
+ - bin/split_paired.rb
194
+ - lib/seqtrimnext/actions/action_ab_adapter.rb
195
+ - lib/seqtrimnext/actions/action_ab_far_adapter.rb
196
+ - lib/seqtrimnext/actions/action_ab_left_adapter.rb
197
+ - lib/seqtrimnext/actions/action_empty_insert.rb
198
+ - lib/seqtrimnext/actions/action_ignore_repeated.rb
199
+ - lib/seqtrimnext/actions/action_indetermination.rb
200
+ - lib/seqtrimnext/actions/action_induced_low_complexity.rb
201
+ - lib/seqtrimnext/actions/action_insert.rb
202
+ - lib/seqtrimnext/actions/action_is_contaminated.rb
203
+ - lib/seqtrimnext/actions/action_key.rb
204
+ - lib/seqtrimnext/actions/action_left_adapter.rb
205
+ - lib/seqtrimnext/actions/action_left_primer.rb
206
+ - lib/seqtrimnext/actions/action_linker.rb
207
+ - lib/seqtrimnext/actions/action_low_complexity.rb
208
+ - lib/seqtrimnext/actions/action_low_high_size.rb
209
+ - lib/seqtrimnext/actions/action_low_quality.rb
210
+ - lib/seqtrimnext/actions/action_mid.rb
211
+ - lib/seqtrimnext/actions/action_multiple_linker.rb
212
+ - lib/seqtrimnext/actions/action_paired_reads.rb
213
+ - lib/seqtrimnext/actions/action_poly_a.rb
214
+ - lib/seqtrimnext/actions/action_poly_t.rb
215
+ - lib/seqtrimnext/actions/action_rem_adit_artifacts.rb
216
+ - lib/seqtrimnext/actions/action_right_adapter.rb
217
+ - lib/seqtrimnext/actions/action_right_primer.rb
218
+ - lib/seqtrimnext/actions/action_short_insert.rb
219
+ - lib/seqtrimnext/actions/action_unexpected_poly_t.rb
220
+ - lib/seqtrimnext/actions/action_unexpected_vector.rb
221
+ - lib/seqtrimnext/actions/action_vectors.rb
222
+ - lib/seqtrimnext/actions/seqtrim_action.rb
223
+ - lib/seqtrimnext/classes/action_manager.rb
224
+ - lib/seqtrimnext/classes/em_classes/seqtrim_work_manager.rb
225
+ - lib/seqtrimnext/classes/em_classes/seqtrim_worker.rb
226
+ - lib/seqtrimnext/classes/extract_stats.rb
227
+ - lib/seqtrimnext/classes/gnu_plot_graph.rb
228
+ - lib/seqtrimnext/classes/graph_stats.rb
229
+ - lib/seqtrimnext/classes/install_database.rb
230
+ - lib/seqtrimnext/classes/install_requirements.rb
231
+ - lib/seqtrimnext/classes/list_db.rb
232
+ - lib/seqtrimnext/classes/make_blast_db.rb
233
+ - lib/seqtrimnext/classes/one_blast.rb
234
+ - lib/seqtrimnext/classes/params.rb
235
+ - lib/seqtrimnext/classes/piro.rb
236
+ - lib/seqtrimnext/classes/plugin_manager.rb
237
+ - lib/seqtrimnext/classes/scan_for_restr_site.rb
238
+ - lib/seqtrimnext/classes/scbi_stats.rb
239
+ - lib/seqtrimnext/classes/seqtrim.rb
240
+ - lib/seqtrimnext/classes/sequence.rb
241
+ - lib/seqtrimnext/classes/sequence_group.rb
242
+ - lib/seqtrimnext/classes/sequence_with_action.rb
243
+ - lib/seqtrimnext/plugins/plugin.rb
244
+ - lib/seqtrimnext/plugins/plugin_ab_adapters.rb
245
+ - lib/seqtrimnext/plugins/plugin_adapters.rb
246
+ - lib/seqtrimnext/plugins/plugin_amplicons.rb
247
+ - lib/seqtrimnext/plugins/plugin_contaminants.rb
248
+ - lib/seqtrimnext/plugins/plugin_extract_inserts.rb
249
+ - lib/seqtrimnext/plugins/plugin_find_poly_at.rb
250
+ - lib/seqtrimnext/plugins/plugin_ignore_repeated.rb
251
+ - lib/seqtrimnext/plugins/plugin_indeterminations.rb
252
+ - lib/seqtrimnext/plugins/plugin_key.rb
253
+ - lib/seqtrimnext/plugins/plugin_linker.rb
254
+ - lib/seqtrimnext/plugins/plugin_low_complexity.rb
255
+ - lib/seqtrimnext/plugins/plugin_low_high_size.rb
256
+ - lib/seqtrimnext/plugins/plugin_low_quality.rb
257
+ - lib/seqtrimnext/plugins/plugin_mids.rb
258
+ - lib/seqtrimnext/plugins/plugin_rem_adit_artifacts.rb
259
+ - lib/seqtrimnext/plugins/plugin_short_insert.rb
260
+ - lib/seqtrimnext/plugins/plugin_vectors.rb
261
+ - lib/seqtrimnext/templates/amplicons.txt
262
+ - lib/seqtrimnext/templates/genomics_454.txt
263
+ - lib/seqtrimnext/templates/genomics_454_with_paired.txt
264
+ - lib/seqtrimnext/templates/low_quality.txt
265
+ - lib/seqtrimnext/templates/low_quality_and_low_complexity.txt
266
+ - lib/seqtrimnext/templates/transcriptomics_454.txt
267
+ - lib/seqtrimnext/templates/transcriptomics_plants.txt
268
+ - lib/seqtrimnext/utils/extract_samples.rb
269
+ - lib/seqtrimnext/utils/fasta2xml.rb
270
+ - lib/seqtrimnext/utils/global_match.rb
271
+ - lib/seqtrimnext/utils/hash_stats.rb
272
+ - lib/seqtrimnext/utils/json_utils.rb
273
+ - lib/seqtrimnext/utils/load_fasta_names_in_hash.rb
274
+ - lib/seqtrimnext/utils/load_qual_in_hash.rb
275
+ - lib/seqtrimnext/utils/recover_mid.rb
276
+ - lib/seqtrimnext/utils/string_utils.rb
277
+ - lib/seqtrimnext.rb
278
+ - History.txt
279
+ - Manifest.txt
280
+ - PostInstall.txt
281
+ - Rakefile
282
+ - README.rdoc
283
+ - script/console
284
+ - script/destroy
285
+ - script/generate
286
+ - test/test_helper.rb
287
+ - test/test_seqtrimnext.rb
288
+ homepage: http://www.scbi.uma.es/downloads
289
+ licenses: []
290
+
291
+ post_install_message: PostInstall.txt
292
+ rdoc_options:
293
+ - --main
294
+ - README.rdoc
295
+ require_paths:
296
+ - lib
297
+ required_ruby_version: !ruby/object:Gem::Requirement
298
+ none: false
299
+ requirements:
300
+ - - ">="
301
+ - !ruby/object:Gem::Version
302
+ version: "0"
303
+ required_rubygems_version: !ruby/object:Gem::Requirement
304
+ none: false
305
+ requirements:
306
+ - - ">="
307
+ - !ruby/object:Gem::Version
308
+ version: "0"
309
+ requirements: []
310
+
311
+ rubyforge_project: seqtrimnext
312
+ rubygems_version: 1.7.2
313
+ signing_key:
314
+ specification_version: 3
315
+ summary: SeqtrimNEXT is a customizable and distributed pre-processing software for NGS (Next Generation Sequencing) biological data
316
+ test_files:
317
+ - test/test_helper.rb
318
+ - test/test_seqtrimnext.rb