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 0
2
+ AA_AC 0
3
+ AA_AG 0
4
+ AA_AT -2500
5
+ AA_CA 0
6
+ AA_CC 0
7
+ AA_CG 0
8
+ AA_CT -2700
9
+ AA_GA 0
10
+ AA_GC 0
11
+ AA_GG 0
12
+ AA_GT -2400
13
+ AA_TA -3100
14
+ AA_TC -1600
15
+ AA_TG -1900
16
+ AA_TT -5000
17
+ AC_AA 0
18
+ AC_AC 0
19
+ AC_AG -8000
20
+ AC_AT 0
21
+ AC_CA 0
22
+ AC_CC 0
23
+ AC_CG -3200
24
+ AC_CT 0
25
+ AC_GA 0
26
+ AC_GC 0
27
+ AC_GG -4600
28
+ AC_GT 0
29
+ AC_TA -1800
30
+ AC_TC -100
31
+ AC_TG -6000
32
+ AC_TT -900
33
+ AG_AA 0
34
+ AG_AC -4300
35
+ AG_AG 0
36
+ AG_AT 0
37
+ AG_CA 0
38
+ AG_CC -2700
39
+ AG_CG 0
40
+ AG_CT 0
41
+ AG_GA 0
42
+ AG_GC -6000
43
+ AG_GG 0
44
+ AG_GT 0
45
+ AG_TA -2500
46
+ AG_TC -6000
47
+ AG_TG -1100
48
+ AG_TT -3200
49
+ AT_AA -3100
50
+ AT_AC 0
51
+ AT_AG 0
52
+ AT_AT 0
53
+ AT_CA -1800
54
+ AT_CC 0
55
+ AT_CG 0
56
+ AT_CT 0
57
+ AT_GA -2500
58
+ AT_GC 0
59
+ AT_GG 0
60
+ AT_GT 0
61
+ AT_TA -5000
62
+ AT_TC -2300
63
+ AT_TG -3500
64
+ AT_TT -2400
65
+ CA_AA 0
66
+ CA_AC 0
67
+ CA_AG 0
68
+ CA_AT -2300
69
+ CA_CA 0
70
+ CA_CC 0
71
+ CA_CG 0
72
+ CA_CT -700
73
+ CA_GA -4300
74
+ CA_GC -2600
75
+ CA_GG -3900
76
+ CA_GT -6000
77
+ CA_TA 0
78
+ CA_TC 0
79
+ CA_TG 0
80
+ CA_TT -700
81
+ CC_AA 0
82
+ CC_AC 0
83
+ CC_AG -5000
84
+ CC_AT 0
85
+ CC_CA 0
86
+ CC_CC 0
87
+ CC_CG -3900
88
+ CC_CT 0
89
+ CC_GA -2700
90
+ CC_GC -2100
91
+ CC_GG -7000
92
+ CC_GT -3200
93
+ CC_TA 0
94
+ CC_TC 0
95
+ CC_TG -3000
96
+ CC_TT 0
97
+ CG_AA 0
98
+ CG_AC -2600
99
+ CG_AG 0
100
+ CG_AT 0
101
+ CG_CA 0
102
+ CG_CC -2100
103
+ CG_CG 0
104
+ CG_CT 0
105
+ CG_GA -6000
106
+ CG_GC -7000
107
+ CG_GG -3800
108
+ CG_GT -3800
109
+ CG_TA 0
110
+ CG_TC -3900
111
+ CG_TG 0
112
+ CG_TT 0
113
+ CT_AA -1600
114
+ CT_AC 0
115
+ CT_AG 0
116
+ CT_AT 0
117
+ CT_CA -100
118
+ CT_CC 0
119
+ CT_CG 0
120
+ CT_CT 0
121
+ CT_GA -6000
122
+ CT_GC -3900
123
+ CT_GG -6600
124
+ CT_GT -6100
125
+ CT_TA -2300
126
+ CT_TC 0
127
+ CT_TG 0
128
+ CT_TT 0
129
+ GA_AA 0
130
+ GA_AC 0
131
+ GA_AG 0
132
+ GA_AT -2000
133
+ GA_CA -8000
134
+ GA_CC -5000
135
+ GA_CG -4300
136
+ GA_CT -6000
137
+ GA_GA 0
138
+ GA_GC 0
139
+ GA_GG 0
140
+ GA_GT -1100
141
+ GA_TA 0
142
+ GA_TC 0
143
+ GA_TG 0
144
+ GA_TT -3600
145
+ GC_AA 0
146
+ GC_AC 0
147
+ GC_AG -4300
148
+ GC_AT 0
149
+ GC_CA -3200
150
+ GC_CC -3900
151
+ GC_CG -7000
152
+ GC_CT -4900
153
+ GC_GA 0
154
+ GC_GC 0
155
+ GC_GG -700
156
+ GC_GT 0
157
+ GC_TA 0
158
+ GC_TC 0
159
+ GC_TG -5900
160
+ GC_TT 0
161
+ GG_AA 0
162
+ GG_AC -3900
163
+ GG_AG 0
164
+ GG_AT 0
165
+ GG_CA -4600
166
+ GG_CC -7000
167
+ GG_CG -700
168
+ GG_CT -5700
169
+ GG_GA 0
170
+ GG_GC -3800
171
+ GG_GG 0
172
+ GG_GT 0
173
+ GG_TA 0
174
+ GG_TC -6600
175
+ GG_TG 0
176
+ GG_TT 0
177
+ GT_AA -1900
178
+ GT_AC 0
179
+ GT_AG 0
180
+ GT_AT 0
181
+ GT_CA -6000
182
+ GT_CC -3000
183
+ GT_CG -5900
184
+ GT_CT -7400
185
+ GT_GA -1100
186
+ GT_GC 0
187
+ GT_GG 0
188
+ GT_GT 0
189
+ GT_TA -3500
190
+ GT_TC 0
191
+ GT_TG 0
192
+ GT_TT 0
193
+ TA_AA -2500
194
+ TA_AC -2300
195
+ TA_AG -2000
196
+ TA_AT -5000
197
+ TA_CA 0
198
+ TA_CC 0
199
+ TA_CG 0
200
+ TA_CT -2500
201
+ TA_GA 0
202
+ TA_GC 0
203
+ TA_GG 0
204
+ TA_GT -3900
205
+ TA_TA 0
206
+ TA_TC 0
207
+ TA_TG 0
208
+ TA_TT -3200
209
+ TC_AA -2700
210
+ TC_AC -700
211
+ TC_AG -6000
212
+ TC_AT -2500
213
+ TC_CA 0
214
+ TC_CC 0
215
+ TC_CG -4900
216
+ TC_CT 0
217
+ TC_GA 0
218
+ TC_GC 0
219
+ TC_GG -5700
220
+ TC_GT 0
221
+ TC_TA 0
222
+ TC_TC 0
223
+ TC_TG -7400
224
+ TC_TT 0
225
+ TG_AA -2400
226
+ TG_AC -6000
227
+ TG_AG -1100
228
+ TG_AT -3900
229
+ TG_CA 0
230
+ TG_CC -3200
231
+ TG_CG 0
232
+ TG_CT 0
233
+ TG_GA 0
234
+ TG_GC -3800
235
+ TG_GG 0
236
+ TG_GT 0
237
+ TG_TA 0
238
+ TG_TC -6100
239
+ TG_TG 0
240
+ TG_TT 0
241
+ TT_AA -5000
242
+ TT_AC -700
243
+ TT_AG -3600
244
+ TT_AT -3200
245
+ TT_CA -900
246
+ TT_CC 0
247
+ TT_CG 0
248
+ TT_CT 0
249
+ TT_GA -3200
250
+ TT_GC 0
251
+ TT_GG 0
252
+ TT_GT 0
253
+ TT_TA -2400
254
+ TT_TC 0
255
+ TT_TG 0
256
+ TT_TT 0
@@ -0,0 +1,256 @@
1
+ AA_AA inf
2
+ AA_AC inf
3
+ AA_AG inf
4
+ AA_AT -6.3
5
+ AA_CA inf
6
+ AA_CC inf
7
+ AA_CG inf
8
+ AA_CT -7.0
9
+ AA_GA inf
10
+ AA_GC inf
11
+ AA_GG inf
12
+ AA_GT -5.8
13
+ AA_TA -7.8
14
+ AA_TC -4.0
15
+ AA_TG -4.4
16
+ AA_TT -13.2
17
+ AC_AA inf
18
+ AC_AC inf
19
+ AC_AG -22.5
20
+ AC_AT inf
21
+ AC_CA inf
22
+ AC_CC inf
23
+ AC_CG -7.1
24
+ AC_CT inf
25
+ AC_GA inf
26
+ AC_GC inf
27
+ AC_GG -11.4
28
+ AC_GT inf
29
+ AC_TA -3.8
30
+ AC_TC -0.5
31
+ AC_TG -16.1
32
+ AC_TT -1.7
33
+ AG_AA inf
34
+ AG_AC -10.7
35
+ AG_AG inf
36
+ AG_AT inf
37
+ AG_CA inf
38
+ AG_CC -6.0
39
+ AG_CG inf
40
+ AG_CT inf
41
+ AG_GA inf
42
+ AG_GC -15.5
43
+ AG_GG inf
44
+ AG_GT inf
45
+ AG_TA -5.9
46
+ AG_TC -16.1
47
+ AG_TG -2.1
48
+ AG_TT -8.7
49
+ AT_AA -7.8
50
+ AT_AC inf
51
+ AT_AG inf
52
+ AT_AT inf
53
+ AT_CA -3.8
54
+ AT_CC inf
55
+ AT_CG inf
56
+ AT_CT inf
57
+ AT_GA -5.9
58
+ AT_GC inf
59
+ AT_GG inf
60
+ AT_GT inf
61
+ AT_TA -13.6
62
+ AT_TC -6.3
63
+ AT_TG -9.4
64
+ AT_TT -6.5
65
+ CA_AA inf
66
+ CA_AC inf
67
+ CA_AG inf
68
+ CA_AT -5.9
69
+ CA_CA inf
70
+ CA_CC inf
71
+ CA_CG inf
72
+ CA_CT -1.3
73
+ CA_GA -10.7
74
+ CA_GC -5.9
75
+ CA_GG -9.6
76
+ CA_GT -16.1
77
+ CA_TA inf
78
+ CA_TC inf
79
+ CA_TG inf
80
+ CA_TT -1.2
81
+ CC_AA inf
82
+ CC_AC inf
83
+ CC_AG -13.8
84
+ CC_AT inf
85
+ CC_CA inf
86
+ CC_CC inf
87
+ CC_CG -10.6
88
+ CC_CT inf
89
+ CC_GA -6.0
90
+ CC_GC -5.1
91
+ CC_GG -19.3
92
+ CC_GT -8.0
93
+ CC_TA inf
94
+ CC_TC inf
95
+ CC_TG -7.8
96
+ CC_TT inf
97
+ CG_AA inf
98
+ CG_AC -5.9
99
+ CG_AG inf
100
+ CG_AT inf
101
+ CG_CA inf
102
+ CG_CC -5.1
103
+ CG_CG inf
104
+ CG_CT inf
105
+ CG_GA -15.5
106
+ CG_GC -19.3
107
+ CG_GG -9.5
108
+ CG_GT -9.0
109
+ CG_TA inf
110
+ CG_TC -10.6
111
+ CG_TG inf
112
+ CG_TT inf
113
+ CT_AA -4.0
114
+ CT_AC inf
115
+ CT_AG inf
116
+ CT_AT inf
117
+ CT_CA -0.5
118
+ CT_CC inf
119
+ CT_CG inf
120
+ CT_CT inf
121
+ CT_GA -16.1
122
+ CT_GC -10.6
123
+ CT_GG -18.7
124
+ CT_GT -16.9
125
+ CT_TA -6.3
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 -4.7
133
+ GA_CA -22.5
134
+ GA_CC -13.8
135
+ GA_CG -11.1
136
+ GA_CT -16.1
137
+ GA_GA inf
138
+ GA_GC inf
139
+ GA_GG inf
140
+ GA_GT -2.7
141
+ GA_TA inf
142
+ GA_TC inf
143
+ GA_TG inf
144
+ GA_TT -9.8
145
+ GC_AA inf
146
+ GC_AC inf
147
+ GC_AG -11.1
148
+ GC_AT inf
149
+ GC_CA -7.1
150
+ GC_CC -10.6
151
+ GC_CG -19.3
152
+ GC_CT -13.5
153
+ GC_GA inf
154
+ GC_GC inf
155
+ GC_GG -19.2
156
+ GC_GT inf
157
+ GC_TA inf
158
+ GC_TC inf
159
+ GC_TG -16.1
160
+ GC_TT inf
161
+ GG_AA inf
162
+ GG_AC -9.6
163
+ GG_AG inf
164
+ GG_AT inf
165
+ GG_CA -11.4
166
+ GG_CC -19.3
167
+ GG_CG -19.2
168
+ GG_CT -15.9
169
+ GG_GA inf
170
+ GG_GC -9.5
171
+ GG_GG inf
172
+ GG_GT inf
173
+ GG_TA inf
174
+ GG_TC -18.7
175
+ GG_TG inf
176
+ GG_TT inf
177
+ GT_AA -4.4
178
+ GT_AC inf
179
+ GT_AG inf
180
+ GT_AT inf
181
+ GT_CA -16.1
182
+ GT_CC -7.8
183
+ GT_CG -16.1
184
+ GT_CT -21.2
185
+ GT_GA -2.1
186
+ GT_GC inf
187
+ GT_GG inf
188
+ GT_GT inf
189
+ GT_TA -9.4
190
+ GT_TC inf
191
+ GT_TG inf
192
+ GT_TT inf
193
+ TA_AA -6.3
194
+ TA_AC -5.9
195
+ TA_AG -4.7
196
+ TA_AT -14.2
197
+ TA_CA inf
198
+ TA_CC inf
199
+ TA_CG inf
200
+ TA_CT -6.3
201
+ TA_GA inf
202
+ TA_GC inf
203
+ TA_GG inf
204
+ TA_GT -10.5
205
+ TA_TA inf
206
+ TA_TC inf
207
+ TA_TG inf
208
+ TA_TT -8.9
209
+ TC_AA -7.0
210
+ TC_AC -1.3
211
+ TC_AG -16.1
212
+ TC_AT -6.3
213
+ TC_CA inf
214
+ TC_CC inf
215
+ TC_CG -13.5
216
+ TC_CT inf
217
+ TC_GA inf
218
+ TC_GC inf
219
+ TC_GG -15.9
220
+ TC_GT inf
221
+ TC_TA inf
222
+ TC_TC inf
223
+ TC_TG -21.2
224
+ TC_TT inf
225
+ TG_AA -5.8
226
+ TG_AC -16.1
227
+ TG_AG -2.7
228
+ TG_AT -10.5
229
+ TG_CA inf
230
+ TG_CC -8.0
231
+ TG_CG inf
232
+ TG_CT inf
233
+ TG_GA inf
234
+ TG_GC -9.0
235
+ TG_GG inf
236
+ TG_GT inf
237
+ TG_TA inf
238
+ TG_TC -16.9
239
+ TG_TG inf
240
+ TG_TT inf
241
+ TT_AA -13.5
242
+ TT_AC -1.2
243
+ TT_AG -9.8
244
+ TT_AT -8.9
245
+ TT_CA -1.7
246
+ TT_CC inf
247
+ TT_CG inf
248
+ TT_CT inf
249
+ TT_GA -8.7
250
+ TT_GC inf
251
+ TT_GG inf
252
+ TT_GT inf
253
+ TT_TA -6.5
254
+ TT_TC inf
255
+ TT_TG inf
256
+ TT_TT inf