BioDSL 1.0.0

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 (197) hide show
  1. checksums.yaml +7 -0
  2. data/.gitignore +10 -0
  3. data/BioDSL.gemspec +64 -0
  4. data/LICENSE +339 -0
  5. data/README.md +205 -0
  6. data/Rakefile +94 -0
  7. data/examples/fastq_to_fasta.rb +8 -0
  8. data/lib/BioDSL/cary.rb +242 -0
  9. data/lib/BioDSL/command.rb +133 -0
  10. data/lib/BioDSL/commands/add_key.rb +110 -0
  11. data/lib/BioDSL/commands/align_seq_mothur.rb +194 -0
  12. data/lib/BioDSL/commands/analyze_residue_distribution.rb +222 -0
  13. data/lib/BioDSL/commands/assemble_pairs.rb +336 -0
  14. data/lib/BioDSL/commands/assemble_seq_idba.rb +230 -0
  15. data/lib/BioDSL/commands/assemble_seq_ray.rb +345 -0
  16. data/lib/BioDSL/commands/assemble_seq_spades.rb +252 -0
  17. data/lib/BioDSL/commands/classify_seq.rb +217 -0
  18. data/lib/BioDSL/commands/classify_seq_mothur.rb +226 -0
  19. data/lib/BioDSL/commands/clip_primer.rb +318 -0
  20. data/lib/BioDSL/commands/cluster_otus.rb +181 -0
  21. data/lib/BioDSL/commands/collapse_otus.rb +170 -0
  22. data/lib/BioDSL/commands/collect_otus.rb +150 -0
  23. data/lib/BioDSL/commands/complement_seq.rb +117 -0
  24. data/lib/BioDSL/commands/count.rb +135 -0
  25. data/lib/BioDSL/commands/count_values.rb +149 -0
  26. data/lib/BioDSL/commands/degap_seq.rb +253 -0
  27. data/lib/BioDSL/commands/dereplicate_seq.rb +168 -0
  28. data/lib/BioDSL/commands/dump.rb +157 -0
  29. data/lib/BioDSL/commands/filter_rrna.rb +239 -0
  30. data/lib/BioDSL/commands/genecall.rb +237 -0
  31. data/lib/BioDSL/commands/grab.rb +535 -0
  32. data/lib/BioDSL/commands/index_taxonomy.rb +226 -0
  33. data/lib/BioDSL/commands/mask_seq.rb +175 -0
  34. data/lib/BioDSL/commands/mean_scores.rb +168 -0
  35. data/lib/BioDSL/commands/merge_pair_seq.rb +175 -0
  36. data/lib/BioDSL/commands/merge_table.rb +225 -0
  37. data/lib/BioDSL/commands/merge_values.rb +113 -0
  38. data/lib/BioDSL/commands/plot_heatmap.rb +233 -0
  39. data/lib/BioDSL/commands/plot_histogram.rb +306 -0
  40. data/lib/BioDSL/commands/plot_matches.rb +282 -0
  41. data/lib/BioDSL/commands/plot_residue_distribution.rb +278 -0
  42. data/lib/BioDSL/commands/plot_scores.rb +285 -0
  43. data/lib/BioDSL/commands/random.rb +153 -0
  44. data/lib/BioDSL/commands/read_fasta.rb +222 -0
  45. data/lib/BioDSL/commands/read_fastq.rb +414 -0
  46. data/lib/BioDSL/commands/read_table.rb +329 -0
  47. data/lib/BioDSL/commands/reverse_seq.rb +113 -0
  48. data/lib/BioDSL/commands/slice_align.rb +400 -0
  49. data/lib/BioDSL/commands/slice_seq.rb +151 -0
  50. data/lib/BioDSL/commands/sort.rb +223 -0
  51. data/lib/BioDSL/commands/split_pair_seq.rb +220 -0
  52. data/lib/BioDSL/commands/split_values.rb +165 -0
  53. data/lib/BioDSL/commands/trim_primer.rb +314 -0
  54. data/lib/BioDSL/commands/trim_seq.rb +192 -0
  55. data/lib/BioDSL/commands/uchime_ref.rb +170 -0
  56. data/lib/BioDSL/commands/uclust.rb +286 -0
  57. data/lib/BioDSL/commands/unique_values.rb +145 -0
  58. data/lib/BioDSL/commands/usearch_global.rb +171 -0
  59. data/lib/BioDSL/commands/usearch_local.rb +171 -0
  60. data/lib/BioDSL/commands/write_fasta.rb +207 -0
  61. data/lib/BioDSL/commands/write_fastq.rb +191 -0
  62. data/lib/BioDSL/commands/write_table.rb +419 -0
  63. data/lib/BioDSL/commands/write_tree.rb +167 -0
  64. data/lib/BioDSL/commands.rb +31 -0
  65. data/lib/BioDSL/config.rb +55 -0
  66. data/lib/BioDSL/csv.rb +307 -0
  67. data/lib/BioDSL/debug.rb +42 -0
  68. data/lib/BioDSL/fasta.rb +133 -0
  69. data/lib/BioDSL/fastq.rb +77 -0
  70. data/lib/BioDSL/filesys.rb +137 -0
  71. data/lib/BioDSL/fork.rb +145 -0
  72. data/lib/BioDSL/hamming.rb +128 -0
  73. data/lib/BioDSL/helpers/aux_helper.rb +44 -0
  74. data/lib/BioDSL/helpers/email_helper.rb +66 -0
  75. data/lib/BioDSL/helpers/history_helper.rb +40 -0
  76. data/lib/BioDSL/helpers/log_helper.rb +55 -0
  77. data/lib/BioDSL/helpers/options_helper.rb +405 -0
  78. data/lib/BioDSL/helpers/status_helper.rb +132 -0
  79. data/lib/BioDSL/helpers.rb +35 -0
  80. data/lib/BioDSL/html_report.rb +200 -0
  81. data/lib/BioDSL/math.rb +55 -0
  82. data/lib/BioDSL/mummer.rb +216 -0
  83. data/lib/BioDSL/pipeline.rb +354 -0
  84. data/lib/BioDSL/seq/ambiguity.rb +66 -0
  85. data/lib/BioDSL/seq/assemble.rb +240 -0
  86. data/lib/BioDSL/seq/backtrack.rb +252 -0
  87. data/lib/BioDSL/seq/digest.rb +99 -0
  88. data/lib/BioDSL/seq/dynamic.rb +263 -0
  89. data/lib/BioDSL/seq/homopolymer.rb +59 -0
  90. data/lib/BioDSL/seq/kmer.rb +293 -0
  91. data/lib/BioDSL/seq/levenshtein.rb +113 -0
  92. data/lib/BioDSL/seq/translate.rb +109 -0
  93. data/lib/BioDSL/seq/trim.rb +188 -0
  94. data/lib/BioDSL/seq.rb +742 -0
  95. data/lib/BioDSL/serializer.rb +98 -0
  96. data/lib/BioDSL/stream.rb +113 -0
  97. data/lib/BioDSL/taxonomy.rb +691 -0
  98. data/lib/BioDSL/test.rb +42 -0
  99. data/lib/BioDSL/tmp_dir.rb +68 -0
  100. data/lib/BioDSL/usearch.rb +301 -0
  101. data/lib/BioDSL/verbose.rb +42 -0
  102. data/lib/BioDSL/version.rb +31 -0
  103. data/lib/BioDSL.rb +81 -0
  104. data/test/BioDSL/commands/test_add_key.rb +105 -0
  105. data/test/BioDSL/commands/test_align_seq_mothur.rb +99 -0
  106. data/test/BioDSL/commands/test_analyze_residue_distribution.rb +134 -0
  107. data/test/BioDSL/commands/test_assemble_pairs.rb +459 -0
  108. data/test/BioDSL/commands/test_assemble_seq_idba.rb +50 -0
  109. data/test/BioDSL/commands/test_assemble_seq_ray.rb +51 -0
  110. data/test/BioDSL/commands/test_assemble_seq_spades.rb +50 -0
  111. data/test/BioDSL/commands/test_classify_seq.rb +50 -0
  112. data/test/BioDSL/commands/test_classify_seq_mothur.rb +59 -0
  113. data/test/BioDSL/commands/test_clip_primer.rb +377 -0
  114. data/test/BioDSL/commands/test_cluster_otus.rb +128 -0
  115. data/test/BioDSL/commands/test_collapse_otus.rb +81 -0
  116. data/test/BioDSL/commands/test_collect_otus.rb +82 -0
  117. data/test/BioDSL/commands/test_complement_seq.rb +78 -0
  118. data/test/BioDSL/commands/test_count.rb +103 -0
  119. data/test/BioDSL/commands/test_count_values.rb +85 -0
  120. data/test/BioDSL/commands/test_degap_seq.rb +96 -0
  121. data/test/BioDSL/commands/test_dereplicate_seq.rb +92 -0
  122. data/test/BioDSL/commands/test_dump.rb +109 -0
  123. data/test/BioDSL/commands/test_filter_rrna.rb +128 -0
  124. data/test/BioDSL/commands/test_genecall.rb +50 -0
  125. data/test/BioDSL/commands/test_grab.rb +398 -0
  126. data/test/BioDSL/commands/test_index_taxonomy.rb +62 -0
  127. data/test/BioDSL/commands/test_mask_seq.rb +98 -0
  128. data/test/BioDSL/commands/test_mean_scores.rb +111 -0
  129. data/test/BioDSL/commands/test_merge_pair_seq.rb +115 -0
  130. data/test/BioDSL/commands/test_merge_table.rb +131 -0
  131. data/test/BioDSL/commands/test_merge_values.rb +83 -0
  132. data/test/BioDSL/commands/test_plot_heatmap.rb +185 -0
  133. data/test/BioDSL/commands/test_plot_histogram.rb +194 -0
  134. data/test/BioDSL/commands/test_plot_matches.rb +157 -0
  135. data/test/BioDSL/commands/test_plot_residue_distribution.rb +309 -0
  136. data/test/BioDSL/commands/test_plot_scores.rb +308 -0
  137. data/test/BioDSL/commands/test_random.rb +88 -0
  138. data/test/BioDSL/commands/test_read_fasta.rb +229 -0
  139. data/test/BioDSL/commands/test_read_fastq.rb +552 -0
  140. data/test/BioDSL/commands/test_read_table.rb +327 -0
  141. data/test/BioDSL/commands/test_reverse_seq.rb +79 -0
  142. data/test/BioDSL/commands/test_slice_align.rb +218 -0
  143. data/test/BioDSL/commands/test_slice_seq.rb +131 -0
  144. data/test/BioDSL/commands/test_sort.rb +128 -0
  145. data/test/BioDSL/commands/test_split_pair_seq.rb +164 -0
  146. data/test/BioDSL/commands/test_split_values.rb +95 -0
  147. data/test/BioDSL/commands/test_trim_primer.rb +329 -0
  148. data/test/BioDSL/commands/test_trim_seq.rb +150 -0
  149. data/test/BioDSL/commands/test_uchime_ref.rb +113 -0
  150. data/test/BioDSL/commands/test_uclust.rb +139 -0
  151. data/test/BioDSL/commands/test_unique_values.rb +98 -0
  152. data/test/BioDSL/commands/test_usearch_global.rb +123 -0
  153. data/test/BioDSL/commands/test_usearch_local.rb +125 -0
  154. data/test/BioDSL/commands/test_write_fasta.rb +159 -0
  155. data/test/BioDSL/commands/test_write_fastq.rb +166 -0
  156. data/test/BioDSL/commands/test_write_table.rb +411 -0
  157. data/test/BioDSL/commands/test_write_tree.rb +122 -0
  158. data/test/BioDSL/helpers/test_options_helper.rb +272 -0
  159. data/test/BioDSL/seq/test_assemble.rb +98 -0
  160. data/test/BioDSL/seq/test_backtrack.rb +176 -0
  161. data/test/BioDSL/seq/test_digest.rb +71 -0
  162. data/test/BioDSL/seq/test_dynamic.rb +133 -0
  163. data/test/BioDSL/seq/test_homopolymer.rb +58 -0
  164. data/test/BioDSL/seq/test_kmer.rb +134 -0
  165. data/test/BioDSL/seq/test_translate.rb +75 -0
  166. data/test/BioDSL/seq/test_trim.rb +101 -0
  167. data/test/BioDSL/test_cary.rb +176 -0
  168. data/test/BioDSL/test_command.rb +45 -0
  169. data/test/BioDSL/test_csv.rb +514 -0
  170. data/test/BioDSL/test_debug.rb +42 -0
  171. data/test/BioDSL/test_fasta.rb +154 -0
  172. data/test/BioDSL/test_fastq.rb +46 -0
  173. data/test/BioDSL/test_filesys.rb +145 -0
  174. data/test/BioDSL/test_fork.rb +85 -0
  175. data/test/BioDSL/test_math.rb +41 -0
  176. data/test/BioDSL/test_mummer.rb +79 -0
  177. data/test/BioDSL/test_pipeline.rb +187 -0
  178. data/test/BioDSL/test_seq.rb +790 -0
  179. data/test/BioDSL/test_serializer.rb +72 -0
  180. data/test/BioDSL/test_stream.rb +55 -0
  181. data/test/BioDSL/test_taxonomy.rb +336 -0
  182. data/test/BioDSL/test_test.rb +42 -0
  183. data/test/BioDSL/test_tmp_dir.rb +58 -0
  184. data/test/BioDSL/test_usearch.rb +33 -0
  185. data/test/BioDSL/test_verbose.rb +42 -0
  186. data/test/helper.rb +82 -0
  187. data/www/command.html.haml +14 -0
  188. data/www/css.html.haml +55 -0
  189. data/www/input_files.html.haml +3 -0
  190. data/www/layout.html.haml +12 -0
  191. data/www/output_files.html.haml +3 -0
  192. data/www/overview.html.haml +15 -0
  193. data/www/pipeline.html.haml +4 -0
  194. data/www/png.html.haml +2 -0
  195. data/www/status.html.haml +9 -0
  196. data/www/time.html.haml +11 -0
  197. metadata +503 -0
@@ -0,0 +1,188 @@
1
+ # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
2
+ # #
3
+ # Copyright (C) 2007-2015 Martin Asser Hansen (mail@maasha.dk). #
4
+ # #
5
+ # This program is free software; you can redistribute it and/or #
6
+ # modify it under the terms of the GNU General Public License #
7
+ # as published by the Free Software Foundation; either version 2 #
8
+ # of the License, or (at your option) any later version. #
9
+ # #
10
+ # This program is distributed in the hope that it will be useful, #
11
+ # but WITHOUT ANY WARRANTY; without even the implied warranty of #
12
+ # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the #
13
+ # GNU General Public License for more details. #
14
+ # #
15
+ # You should have received a copy of the GNU General Public License #
16
+ # along with this program; if not, write to the Free Software #
17
+ # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. #
18
+ # #
19
+ # http://www.gnu.org/copyleft/gpl.html #
20
+ # #
21
+ # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
22
+ # #
23
+ # This software is part of BioDSL (www.BioDSL.org). #
24
+ # #
25
+ # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
26
+
27
+ module BioDSL
28
+ # Error class for all exceptions to do with Trim.
29
+ class TrimError < StandardError; end
30
+
31
+ # Module containing methods for end trimming sequences with suboptimal quality
32
+ # scores.
33
+ module Trim
34
+ # Method to progressively trim a Seq object sequence from the right end until
35
+ # a run of min_len residues with quality scores above min_qual is encountered.
36
+ def quality_trim_right(min_qual, min_len = 1)
37
+ check_trim_args(min_qual, min_len)
38
+
39
+ pos = trim_right_pos_c(self.qual, self.length, min_qual, min_len, Seq::SCORE_BASE)
40
+
41
+ self[0 .. pos]
42
+ end
43
+
44
+ # Method to progressively trim a Seq object sequence from the right end until
45
+ # a run of min_len residues with quality scores above min_qual is encountered.
46
+ def quality_trim_right!(min_qual, min_len = 1)
47
+ subseq = quality_trim_right(min_qual, min_len)
48
+ self.seq = subseq.seq
49
+ self.qual = subseq.qual
50
+ self
51
+ end
52
+
53
+ # Method to progressively trim a Seq object sequence from the left end until
54
+ # a run of min_len residues with quality scores above min_qual is encountered.
55
+ def quality_trim_left(min_qual, min_len = 1)
56
+ check_trim_args(min_qual, min_len)
57
+
58
+ pos = trim_left_pos_c(self.qual, self.length, min_qual, min_len, Seq::SCORE_BASE)
59
+
60
+ self[pos .. self.length]
61
+ end
62
+
63
+ # Method to progressively trim a Seq object sequence from the left end until
64
+ # a run of min_len residues with quality scores above min_qual is encountered.
65
+ def quality_trim_left!(min_qual, min_len = 1)
66
+ subseq = quality_trim_left(min_qual, min_len)
67
+ self.seq = subseq.seq
68
+ self.qual = subseq.qual
69
+ self
70
+ end
71
+
72
+ # Method to progressively trim a Seq object sequence from both ends until a
73
+ # run of min_len residues with quality scores above min_qual is encountered.
74
+ def quality_trim(min_qual, min_len = 1)
75
+ check_trim_args(min_qual, min_len)
76
+
77
+ pos_right = trim_right_pos_c(self.qual, self.length, min_qual, min_len, Seq::SCORE_BASE)
78
+ pos_left = trim_left_pos_c(self.qual, self.length, min_qual, min_len, Seq::SCORE_BASE)
79
+
80
+ pos_left = pos_right if pos_left > pos_right
81
+
82
+ self[pos_left ... pos_right]
83
+ end
84
+
85
+ # Method to progressively trim a Seq object sequence from both ends until a
86
+ # run of min_len residues with quality scores above min_qual is encountered.
87
+ def quality_trim!(min_qual, min_len = 1)
88
+ subseq = quality_trim(min_qual, min_len)
89
+ self.seq = subseq.seq
90
+ self.qual = subseq.qual
91
+ self
92
+ end
93
+
94
+ private
95
+
96
+ # Method to check the arguments for trimming and raise on bad sequence, qualities,
97
+ # and min_qual.
98
+ def check_trim_args(min_qual, min_len)
99
+ raise TrimError, "no sequence" if self.seq.nil?
100
+ raise TrimError, "no quality score" if self.qual.nil?
101
+ unless (Seq::SCORE_MIN .. Seq::SCORE_MAX).include? min_qual
102
+ raise TrimError, "minimum quality value: #{min_qual} out of range #{Seq::SCORE_MIN} .. #{Seq::SCORE_MAX}"
103
+ end
104
+ raise TrimError, "min_len must be larger than zero" if min_len <= 0
105
+ end
106
+
107
+ # Inline C functions for speed below.
108
+ inline do |builder|
109
+ # Method for locating the right trim position and return this.
110
+ builder.c %{
111
+ VALUE trim_right_pos_c(
112
+ VALUE _qual, // quality score string
113
+ VALUE _len, // length of quality score string
114
+ VALUE _min_qual, // minimum quality score
115
+ VALUE _min_len, // minimum quality length
116
+ VALUE _score_base // score base
117
+ )
118
+ {
119
+ char *qual = StringValuePtr(_qual);
120
+ unsigned int len = FIX2UINT(_len);
121
+ unsigned int min_qual = FIX2UINT(_min_qual);
122
+ unsigned int min_len = FIX2UINT(_min_len);
123
+ unsigned int score_base = FIX2UINT(_score_base);
124
+
125
+ unsigned int i = 0;
126
+ unsigned int c = 0;
127
+
128
+ while (i < len)
129
+ {
130
+ c = 0;
131
+
132
+ while ((c < min_len) && ((c + i) < len) && (qual[len - (c + i) - 1] - score_base >= min_qual))
133
+ c++;
134
+
135
+ if (c == min_len)
136
+ return UINT2NUM(len - i);
137
+ else
138
+ i += c;
139
+
140
+ i++;
141
+ }
142
+
143
+ return UINT2NUM(0);
144
+ }
145
+ }
146
+
147
+ # Method for locating the left trim position and return this.
148
+ builder.c %{
149
+ VALUE trim_left_pos_c(
150
+ VALUE _qual, // quality score string
151
+ VALUE _len, // length of quality score string
152
+ VALUE _min_qual, // minimum quality score
153
+ VALUE _min_len, // minimum quality length
154
+ VALUE _score_base // score base
155
+ )
156
+ {
157
+ char *qual = StringValuePtr(_qual);
158
+ unsigned int len = FIX2UINT(_len);
159
+ unsigned int min_qual = FIX2UINT(_min_qual);
160
+ unsigned int min_len = FIX2UINT(_min_len);
161
+ unsigned int score_base = FIX2UINT(_score_base);
162
+
163
+ unsigned int i = 0;
164
+ unsigned int c = 0;
165
+
166
+ while (i < len)
167
+ {
168
+ c = 0;
169
+
170
+ while ((c < min_len) && ((c + i) < len) && (qual[c + i] - score_base >= min_qual))
171
+ c++;
172
+
173
+ if (c == min_len)
174
+ return UINT2NUM(i);
175
+ else
176
+ i += c;
177
+
178
+ i++;
179
+ }
180
+
181
+ return UINT2NUM(i);
182
+ }
183
+ }
184
+ end
185
+ end
186
+ end
187
+
188
+ __END__