bio-polyploid-tools 0.1.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (92) hide show
  1. checksums.yaml +7 -0
  2. data/Gemfile +16 -0
  3. data/Gemfile.lock +67 -0
  4. data/README +21 -0
  5. data/Rakefile +61 -0
  6. data/VERSION +1 -0
  7. data/bin/bfr.rb +133 -0
  8. data/bin/count_variations.rb +36 -0
  9. data/bin/filter_blat_by_target_coverage.rb +15 -0
  10. data/bin/find_best_blat_hit.rb +32 -0
  11. data/bin/hexaploid_primers.rb +168 -0
  12. data/bin/homokaryot_primers.rb +155 -0
  13. data/bin/map_markers_to_contigs.rb +66 -0
  14. data/bin/markers_in_region.rb +42 -0
  15. data/bin/polymarker.rb +219 -0
  16. data/bin/snps_between_bams.rb +106 -0
  17. data/bio-polyploid-tools.gemspec +139 -0
  18. data/conf/defaults.rb +1 -0
  19. data/conf/primer3_config/dangle.dh +128 -0
  20. data/conf/primer3_config/dangle.ds +128 -0
  21. data/conf/primer3_config/interpretations/dangle_i.dh +131 -0
  22. data/conf/primer3_config/interpretations/dangle_i.ds +131 -0
  23. data/conf/primer3_config/interpretations/loops_i.dh +34 -0
  24. data/conf/primer3_config/interpretations/loops_i.ds +31 -0
  25. data/conf/primer3_config/interpretations/stack_i.dh +257 -0
  26. data/conf/primer3_config/interpretations/stack_i.ds +256 -0
  27. data/conf/primer3_config/interpretations/stackmm_i_mm.dh +257 -0
  28. data/conf/primer3_config/interpretations/stackmm_i_mm.ds +256 -0
  29. data/conf/primer3_config/interpretations/tetraloop_i.dh +79 -0
  30. data/conf/primer3_config/interpretations/tetraloop_i.ds +81 -0
  31. data/conf/primer3_config/interpretations/triloop_i.dh +21 -0
  32. data/conf/primer3_config/interpretations/triloop_i.ds +18 -0
  33. data/conf/primer3_config/interpretations/tstack2_i.dh +256 -0
  34. data/conf/primer3_config/interpretations/tstack2_i.ds +256 -0
  35. data/conf/primer3_config/interpretations/tstack_i.dh +256 -0
  36. data/conf/primer3_config/interpretations/tstack_i.ds +256 -0
  37. data/conf/primer3_config/interpretations/tstack_tm_inf_i.dh +256 -0
  38. data/conf/primer3_config/interpretations/tstack_tm_inf_i.ds +256 -0
  39. data/conf/primer3_config/loops.dh +30 -0
  40. data/conf/primer3_config/loops.ds +30 -0
  41. data/conf/primer3_config/stack.dh +256 -0
  42. data/conf/primer3_config/stack.ds +256 -0
  43. data/conf/primer3_config/stackmm.dh +256 -0
  44. data/conf/primer3_config/stackmm.ds +256 -0
  45. data/conf/primer3_config/tetraloop.dh +77 -0
  46. data/conf/primer3_config/tetraloop.ds +77 -0
  47. data/conf/primer3_config/triloop.dh +16 -0
  48. data/conf/primer3_config/triloop.ds +16 -0
  49. data/conf/primer3_config/tstack.dh +256 -0
  50. data/conf/primer3_config/tstack2.dh +256 -0
  51. data/conf/primer3_config/tstack2.ds +256 -0
  52. data/conf/primer3_config/tstack_tm_inf.ds +256 -0
  53. data/lib/bio/BFRTools.rb +698 -0
  54. data/lib/bio/BIOExtensions.rb +186 -0
  55. data/lib/bio/PolyploidTools/ChromosomeArm.rb +52 -0
  56. data/lib/bio/PolyploidTools/ExonContainer.rb +194 -0
  57. data/lib/bio/PolyploidTools/Marker.rb +175 -0
  58. data/lib/bio/PolyploidTools/PrimerRegion.rb +22 -0
  59. data/lib/bio/PolyploidTools/SNP.rb +681 -0
  60. data/lib/bio/PolyploidTools/SNPSequence.rb +56 -0
  61. data/lib/bio/SAMToolsExtensions.rb +284 -0
  62. data/lib/bio/db/exonerate.rb +272 -0
  63. data/lib/bio/db/fastadb.rb +164 -0
  64. data/lib/bio/db/primer3.rb +673 -0
  65. data/lib/bioruby-polyploid-tools.rb +25 -0
  66. data/test/data/BS00068396_51.fa +2 -0
  67. data/test/data/BS00068396_51_contigs.aln +1412 -0
  68. data/test/data/BS00068396_51_contigs.dnd +7 -0
  69. data/test/data/BS00068396_51_contigs.fa +8 -0
  70. data/test/data/BS00068396_51_exonerate.tab +6 -0
  71. data/test/data/BS00068396_51_genes.txt +14 -0
  72. data/test/data/LIB1716.bam +0 -0
  73. data/test/data/LIB1716.bam.bai +0 -0
  74. data/test/data/LIB1719.bam +0 -0
  75. data/test/data/LIB1719.bam.bai +0 -0
  76. data/test/data/LIB1721.bam +0 -0
  77. data/test/data/LIB1721.bam.bai +0 -0
  78. data/test/data/LIB1722.bam +0 -0
  79. data/test/data/LIB1722.bam.bai +0 -0
  80. data/test/data/S22380157.fa +16 -0
  81. data/test/data/S22380157.fa.fai +1 -0
  82. data/test/data/Test3Aspecific.csv +1 -0
  83. data/test/data/Test3Aspecific_contigs.fa +6 -0
  84. data/test/data/patological_cases5D.csv +1 -0
  85. data/test/data/short_primer_design_test.csv +10 -0
  86. data/test/data/test_primer3_error.csv +4 -0
  87. data/test/data/test_primer3_error_contigs.fa +10 -0
  88. data/test/test_bfr.rb +51 -0
  89. data/test/test_exon_container.rb +17 -0
  90. data/test/test_exonearate.rb +53 -0
  91. data/test/test_snp_parsing.rb +40 -0
  92. metadata +201 -0
@@ -0,0 +1,256 @@
1
+ AA_AA inf
2
+ AA_AC inf
3
+ AA_AG inf
4
+ AA_AT 12.9
5
+ AA_CA inf
6
+ AA_CC inf
7
+ AA_CG inf
8
+ AA_CT 20.2
9
+ AA_GA inf
10
+ AA_GC inf
11
+ AA_GG inf
12
+ AA_GT 7.4
13
+ AA_TA 1.7
14
+ AA_TC 4.6
15
+ AA_TG -2.3
16
+ AA_TT inf
17
+ AC_AA inf
18
+ AC_AC inf
19
+ AC_AG -9.8
20
+ AC_AT inf
21
+ AC_CA inf
22
+ AC_CC inf
23
+ AC_CG -3.8
24
+ AC_CT inf
25
+ AC_GA inf
26
+ AC_GC inf
27
+ AC_GG 3.2
28
+ AC_GT inf
29
+ AC_TA 14.6
30
+ AC_TC -4.4
31
+ AC_TG inf
32
+ AC_TT 0.2
33
+ AG_AA inf
34
+ AG_AC -4.2
35
+ AG_AG inf
36
+ AG_AT inf
37
+ AG_CA inf
38
+ AG_CC 0.6
39
+ AG_CG inf
40
+ AG_CT inf
41
+ AG_GA inf
42
+ AG_GC -13.2
43
+ AG_GG inf
44
+ AG_GT inf
45
+ AG_TA -2.3
46
+ AG_TC inf
47
+ AG_TG -9.5
48
+ AG_TT 0.9
49
+ AT_AA 1.7
50
+ AT_AC inf
51
+ AT_AG inf
52
+ AT_AT inf
53
+ AT_CA 14.6
54
+ AT_CC inf
55
+ AT_CG inf
56
+ AT_CT inf
57
+ AT_GA -2.3
58
+ AT_GC inf
59
+ AT_GG inf
60
+ AT_GT inf
61
+ AT_TA inf
62
+ AT_TC -6.2
63
+ AT_TG -8.3
64
+ AT_TT -10.8
65
+ CA_AA inf
66
+ CA_AC inf
67
+ CA_AG inf
68
+ CA_AT 8.0
69
+ CA_CA inf
70
+ CA_CC inf
71
+ CA_CG inf
72
+ CA_CT 16.4
73
+ CA_GA -4.2
74
+ CA_GC 3.7
75
+ CA_GG -2.3
76
+ CA_GT inf
77
+ CA_TA inf
78
+ CA_TC inf
79
+ CA_TG inf
80
+ CA_TT 0.7
81
+ CC_AA inf
82
+ CC_AC inf
83
+ CC_AG 14.2
84
+ CC_AT inf
85
+ CC_CA inf
86
+ CC_CC inf
87
+ CC_CG 8.9
88
+ CC_CT inf
89
+ CC_GA -0.6
90
+ CC_GC -7.2
91
+ CC_GG -19.9
92
+ CC_GT -4.5
93
+ CC_TA inf
94
+ CC_TC inf
95
+ CC_TG 13.5
96
+ CC_TT inf
97
+ CG_AA inf
98
+ CG_AC 3.7
99
+ CG_AG inf
100
+ CG_AT inf
101
+ CG_CA inf
102
+ CG_CC -7.2
103
+ CG_CG inf
104
+ CG_CT inf
105
+ CG_GA -13.2
106
+ CG_GC inf
107
+ CG_GG -15.3
108
+ CG_GT -11.7
109
+ CG_TA inf
110
+ CG_TC -6.1
111
+ CG_TG inf
112
+ CG_TT inf
113
+ CT_AA 4.6
114
+ CT_AC inf
115
+ CT_AG inf
116
+ CT_AT inf
117
+ CT_CA -4.4
118
+ CT_CC inf
119
+ CT_CG inf
120
+ CT_CT inf
121
+ CT_GA inf
122
+ CT_GC -6.1
123
+ CT_GG -8.0
124
+ CT_GT -15.8
125
+ CT_TA -6.2
126
+ CT_TC inf
127
+ CT_TG inf
128
+ CT_TT inf
129
+ GA_AA inf
130
+ GA_AC inf
131
+ GA_AG inf
132
+ GA_AT 0.7
133
+ GA_CA -9.8
134
+ GA_CC 14.2
135
+ GA_CG -1.0
136
+ GA_CT inf
137
+ GA_GA inf
138
+ GA_GC inf
139
+ GA_GG inf
140
+ GA_GT 3.6
141
+ GA_TA inf
142
+ GA_TC inf
143
+ GA_TG inf
144
+ GA_TT -5.3
145
+ GC_AA inf
146
+ GC_AC inf
147
+ GC_AG -1.0
148
+ GC_AT inf
149
+ GC_CA -3.8
150
+ GC_CC 8.9
151
+ GC_CG inf
152
+ GC_CT 5.4
153
+ GC_GA inf
154
+ GC_GC inf
155
+ GC_GG -15.8
156
+ GC_GT inf
157
+ GC_TA inf
158
+ GC_TC inf
159
+ GC_TG -12.3
160
+ GC_TT inf
161
+ GG_AA inf
162
+ GG_AC -2.3
163
+ GG_AG inf
164
+ GG_AT inf
165
+ GG_CA 3.2
166
+ GG_CC -19.9
167
+ GG_CG -15.8
168
+ GG_CT 10.4
169
+ GG_GA inf
170
+ GG_GC -15.3
171
+ GG_GG inf
172
+ GG_GT inf
173
+ GG_TA inf
174
+ GG_TC 80
175
+ GG_TG inf
176
+ GG_TT 16.3
177
+ GT_AA 23
178
+ GT_AC inf
179
+ GT_AG inf
180
+ GT_AT inf
181
+ GT_CA inf
182
+ GT_CC 13.5
183
+ GT_CG -12.3
184
+ GT_CT -8.4
185
+ GT_GA -9.5
186
+ GT_GC inf
187
+ GT_GG inf
188
+ GT_GT inf
189
+ GT_TA -8.3
190
+ GT_TC inf
191
+ GT_TG 9.5
192
+ GT_TT inf
193
+ TA_AA 12.9
194
+ TA_AC 8.0
195
+ TA_AG 0.7
196
+ TA_AT inf
197
+ TA_CA inf
198
+ TA_CC inf
199
+ TA_CG inf
200
+ TA_CT 0.7
201
+ TA_GA inf
202
+ TA_GC inf
203
+ TA_GG inf
204
+ TA_GT -1.7
205
+ TA_TA inf
206
+ TA_TC inf
207
+ TA_TG inf
208
+ TA_TT -1.5
209
+ TC_AA 20.2
210
+ TC_AC 16.4
211
+ TC_AG inf
212
+ TC_AT 0.7
213
+ TC_CA inf
214
+ TC_CC inf
215
+ TC_CG 5.4
216
+ TC_CT inf
217
+ TC_GA inf
218
+ TC_GC inf
219
+ TC_GG 10.4
220
+ TC_GT inf
221
+ TC_TA inf
222
+ TC_TC inf
223
+ TC_TG -8.4
224
+ TC_TT inf
225
+ TG_AA 7.4
226
+ TG_AC inf
227
+ TG_AG 3.6
228
+ TG_AT -1.7
229
+ TG_CA inf
230
+ TG_CC -4.5
231
+ TG_CG inf
232
+ TG_CT inf
233
+ TG_GA inf
234
+ TG_GC -11.7
235
+ TG_GG inf
236
+ TG_GT -6.2
237
+ TG_TA inf
238
+ TG_TC -15.8
239
+ TG_TG inf
240
+ TG_TT inf
241
+ TT_AA inf
242
+ TT_AC -7
243
+ TT_AG -5.3
244
+ TT_AT -1.5
245
+ TT_CA 0.2
246
+ TT_CC inf
247
+ TT_CG inf
248
+ TT_CT inf
249
+ TT_GA 0.9
250
+ TT_GC inf
251
+ TT_GG 16.3
252
+ TT_GT inf
253
+ TT_TA -10.8
254
+ TT_TC inf
255
+ TT_TG inf
256
+ TT_TT inf
@@ -0,0 +1,79 @@
1
+ /* tetraloop bonuses for GNRA and GNAB kcal/mol*(-10) */
2
+
3
+ AAAAAT -5
4
+ AAAACT -7
5
+ AAACAT -10
6
+ ACTTGT 0
7
+ AGAAAT 11
8
+ AGAGAT 11
9
+ AGATAT 15
10
+ AGCAAT 16
11
+ AGCGAT 11
12
+ AGCTTT -2
13
+ AGGAAT 11
14
+ AGGGAT 11
15
+ AGGGGT -5
16
+ AGTAAT 16
17
+ AGTGAT 11
18
+ AGTTCT -8
19
+ ATTCGT 2
20
+ ATTTGT 0
21
+ ATTTTT 5
22
+ CAAAAG -5
23
+ CAAACG -7
24
+ CAACAG -10
25
+ CAACCG 0
26
+ CCTTGG 0
27
+ CGAAAG 11
28
+ CGAGAG 11
29
+ CGATAG 15
30
+ CGCAAG 16
31
+ CGCGAG 11
32
+ CGCTTG -2
33
+ CGGAAG 11
34
+ CGGGAG 10
35
+ CGGGGG -5
36
+ CGTAAG 16
37
+ CGTGAG 11
38
+ CGTTCG -8
39
+ CTTCGG 2
40
+ CTTTGG 0
41
+ CTTTTG 5
42
+ GAAAAC -5
43
+ GAAACC -7
44
+ GAACAC -10
45
+ GCTTGC 0
46
+ GGAAAC 11
47
+ GGAGAC 11
48
+ GGATAC 16
49
+ GGCAAC 16
50
+ GGCGAC 11
51
+ GGCTTC -2
52
+ GGGAAC 11
53
+ GGGGAC 11
54
+ GGGGGC -5
55
+ GGTAAC 16
56
+ GGTGAC 11
57
+ GGTTCC -8
58
+ GTTCGC 2
59
+ GTTTGC 0
60
+ GTTTTC 5
61
+ TAAAAA -5
62
+ TAAACA -7
63
+ TAACAA -10
64
+ TCTTGA 0
65
+ TGAAAA 11
66
+ TGAGAA 11
67
+ TGATAA 16
68
+ TGCAAA 16
69
+ TGCGAA 11
70
+ TGCTTA -2
71
+ TGGAAA 11
72
+ TGGGAA 11
73
+ TGGGGA -5
74
+ TGTAAA 16
75
+ TGTGAA 11
76
+ TGTTCA -8
77
+ TTTCGA 2
78
+ TTTTGA 0
79
+ TTTTTA 5
@@ -0,0 +1,81 @@
1
+ /*
2
+ VIIDE
3
+ */
4
+
5
+ AAAAAT 6.5
6
+ AAAACT -16.1
7
+ AAACAT -16.1
8
+ ACTTGT -41.9
9
+ AGAAAT -16.1
10
+ AGAGAT -16.1
11
+ AGATAT -16.1
12
+ AGCAAT -16.1
13
+ AGCGAT -16.1
14
+ AGCTTT -16.1
15
+ AGGAAT -16.1
16
+ AGGGAT -16.1
17
+ AGGGGT -6.4
18
+ AGTAAT -16.1
19
+ AGTGAT -16.1
20
+ AGTTCT -16.1
21
+ ATTCGT -16.1
22
+ ATTTGT -16.1
23
+ ATTTTT -16.1
24
+ CAAAAG 12.9
25
+ CAAACG 0
26
+ CAACAG 0
27
+ CAACCG 0
28
+ CCTTGG -25.7
29
+ CGAAAG 0
30
+ CGAGAG 0
31
+ CGATAG 0
32
+ CGCAAG 0
33
+ CGCGAG 0
34
+ CGCTTG 0
35
+ CGGAAG 0
36
+ CGGGAG 0
37
+ CGGGGG 9.7
38
+ CGTAAG 0
39
+ CGTGAG 0
40
+ CGTTCG 0
41
+ CTTCGG 0
42
+ CTTTGG 0
43
+ CTTTTG 0
44
+ GAAAAC 32.3
45
+ GAAACC 0
46
+ GAACAC 0
47
+ GCTTGC -25.7
48
+ GGAAAC 0
49
+ GGAGAC 0
50
+ GGATAC 0
51
+ GGCAAC 0
52
+ GGCGAC 0
53
+ GGCTTC 0
54
+ GGGAAC 0
55
+ GGGGAC 0
56
+ GGGGGC 9.7
57
+ GGTAAC 0
58
+ GGTGAC 0
59
+ GGTTCC 0
60
+ GTTCGC 0
61
+ GTTTGC 0
62
+ GTTTTC 0
63
+ TAAAAA -3.2
64
+ TAAACA -16.1
65
+ TAACAA -16.1
66
+ TCTTGA -41.9
67
+ TGAAAA -16.1
68
+ TGAGAA -16.1
69
+ TGATAA -16.1
70
+ TGCAAA -16.1
71
+ TGCGAA -16.1
72
+ TGCTTA -16.1
73
+ TGGAAA -16.1
74
+ TGGGAA -16.1
75
+ TGGGGA -6.4
76
+ TGTAAA -16.1
77
+ TGTGAA -16.1
78
+ TGTTCA -16.1
79
+ TTTCGA -16.1
80
+ TTTTGA -16.1
81
+ TTTTTA -16.1
@@ -0,0 +1,21 @@
1
+
2
+ /* triloop bonus*/
3
+
4
+ /* Enthalpy Hairpin loop */
5
+
6
+ AGAAT 15
7
+ AGCAT 15
8
+ AGGAT 15
9
+ AGTAT 15
10
+ CGAAG 20
11
+ CGCAG 20
12
+ CGGAG 20
13
+ CGTAG 20
14
+ GGAAC 20
15
+ GGCAC 20
16
+ GGGAC 20
17
+ GGTAC 20
18
+ TGAAA 15
19
+ TGCAA 15
20
+ TGGAA 15
21
+ TGTAA 15
@@ -0,0 +1,18 @@
1
+ /* bonuses for GNA triloops */
2
+
3
+ AGAAT 0
4
+ AGCAT 0
5
+ AGGAT 0
6
+ AGTAT 0
7
+ CGAAG 0
8
+ CGCAG 0
9
+ CGGAG 0
10
+ CGTAG 0
11
+ GGAAC 0
12
+ GGCAC 0
13
+ GGGAC 0
14
+ GGTAC 0
15
+ TGAAA 0
16
+ TGCAA 0
17
+ TGGAA 0
18
+ TGTAA 0