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 inf
5
+ AA_CA inf
6
+ AA_CC inf
7
+ AA_CG inf
8
+ AA_CT inf
9
+ AA_GA inf
10
+ AA_GC inf
11
+ AA_GG inf
12
+ AA_GT inf
13
+ AA_TA inf
14
+ AA_TC inf
15
+ AA_TG inf
16
+ AA_TT -22.2
17
+ AC_AA inf
18
+ AC_AC inf
19
+ AC_AG inf
20
+ AC_AT inf
21
+ AC_CA inf
22
+ AC_CC inf
23
+ AC_CG inf
24
+ AC_CT inf
25
+ AC_GA inf
26
+ AC_GC inf
27
+ AC_GG inf
28
+ AC_GT inf
29
+ AC_TA inf
30
+ AC_TC inf
31
+ AC_TG -22.4
32
+ AC_TT inf
33
+ AG_AA inf
34
+ AG_AC inf
35
+ AG_AG inf
36
+ AG_AT inf
37
+ AG_CA inf
38
+ AG_CC inf
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 inf
46
+ AG_TC -21.0
47
+ AG_TG inf
48
+ AG_TT inf
49
+ AT_AA inf
50
+ AT_AC inf
51
+ AT_AG inf
52
+ AT_AT inf
53
+ AT_CA inf
54
+ AT_CC inf
55
+ AT_CG inf
56
+ AT_CT inf
57
+ AT_GA inf
58
+ AT_GC inf
59
+ AT_GG inf
60
+ AT_GT inf
61
+ AT_TA -20.4
62
+ AT_TC inf
63
+ AT_TG inf
64
+ AT_TT inf
65
+ CA_AA inf
66
+ CA_AC inf
67
+ CA_AG inf
68
+ CA_AT inf
69
+ CA_CA inf
70
+ CA_CC inf
71
+ CA_CG inf
72
+ CA_CT inf
73
+ CA_GA inf
74
+ CA_GC inf
75
+ CA_GG inf
76
+ CA_GT -22.7
77
+ CA_TA inf
78
+ CA_TC inf
79
+ CA_TG inf
80
+ CA_TT inf
81
+ CC_AA inf
82
+ CC_AC inf
83
+ CC_AG inf
84
+ CC_AT inf
85
+ CC_CA inf
86
+ CC_CC inf
87
+ CC_CG inf
88
+ CC_CT inf
89
+ CC_GA inf
90
+ CC_GC inf
91
+ CC_GG -19.9
92
+ CC_GT inf
93
+ CC_TA inf
94
+ CC_TC inf
95
+ CC_TG inf
96
+ CC_TT inf
97
+ CG_AA inf
98
+ CG_AC inf
99
+ CG_AG inf
100
+ CG_AT inf
101
+ CG_CA inf
102
+ CG_CC inf
103
+ CG_CG inf
104
+ CG_CT inf
105
+ CG_GA inf
106
+ CG_GC -27.2
107
+ CG_GG inf
108
+ CG_GT inf
109
+ CG_TA inf
110
+ CG_TC inf
111
+ CG_TG inf
112
+ CG_TT inf
113
+ CT_AA inf
114
+ CT_AC inf
115
+ CT_AG inf
116
+ CT_AT inf
117
+ CT_CA inf
118
+ CT_CC inf
119
+ CT_CG inf
120
+ CT_CT inf
121
+ CT_GA -21.0
122
+ CT_GC inf
123
+ CT_GG inf
124
+ CT_GT -15.8
125
+ CT_TA inf
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 inf
133
+ GA_CA inf
134
+ GA_CC inf
135
+ GA_CG inf
136
+ GA_CT -22.2
137
+ GA_GA inf
138
+ GA_GC inf
139
+ GA_GG inf
140
+ GA_GT inf
141
+ GA_TA inf
142
+ GA_TC inf
143
+ GA_TG inf
144
+ GA_TT inf
145
+ GC_AA inf
146
+ GC_AC inf
147
+ GC_AG inf
148
+ GC_AT inf
149
+ GC_CA inf
150
+ GC_CC inf
151
+ GC_CG -24.4
152
+ GC_CT inf
153
+ GC_GA inf
154
+ GC_GC inf
155
+ GC_GG inf
156
+ GC_GT inf
157
+ GC_TA inf
158
+ GC_TC inf
159
+ GC_TG inf
160
+ GC_TT inf
161
+ GG_AA inf
162
+ GG_AC inf
163
+ GG_AG inf
164
+ GG_AT inf
165
+ GG_CA inf
166
+ GG_CC -19.9
167
+ GG_CG -15.8
168
+ GG_CT inf
169
+ GG_GA inf
170
+ GG_GC inf
171
+ GG_GG inf
172
+ GG_GT inf
173
+ GG_TA inf
174
+ GG_TC inf
175
+ GG_TG inf
176
+ GG_TT inf
177
+ GT_AA inf
178
+ GT_AC inf
179
+ GT_AG inf
180
+ GT_AT inf
181
+ GT_CA -22.4
182
+ GT_CC inf
183
+ GT_CG inf
184
+ GT_CT inf
185
+ GT_GA inf
186
+ GT_GC inf
187
+ GT_GG inf
188
+ GT_GT inf
189
+ GT_TA inf
190
+ GT_TC inf
191
+ GT_TG inf
192
+ GT_TT inf
193
+ TA_AA inf
194
+ TA_AC inf
195
+ TA_AG inf
196
+ TA_AT -21.3
197
+ TA_CA inf
198
+ TA_CC inf
199
+ TA_CG inf
200
+ TA_CT inf
201
+ TA_GA inf
202
+ TA_GC inf
203
+ TA_GG inf
204
+ TA_GT inf
205
+ TA_TA inf
206
+ TA_TC inf
207
+ TA_TG inf
208
+ TA_TT inf
209
+ TC_AA inf
210
+ TC_AC inf
211
+ TC_AG -22.2
212
+ TC_AT inf
213
+ TC_CA inf
214
+ TC_CC inf
215
+ TC_CG inf
216
+ TC_CT inf
217
+ TC_GA inf
218
+ TC_GC inf
219
+ TC_GG inf
220
+ TC_GT inf
221
+ TC_TA inf
222
+ TC_TC inf
223
+ TC_TG inf
224
+ TC_TT inf
225
+ TG_AA inf
226
+ TG_AC -22.7
227
+ TG_AG inf
228
+ TG_AT inf
229
+ TG_CA inf
230
+ TG_CC inf
231
+ TG_CG inf
232
+ TG_CT inf
233
+ TG_GA inf
234
+ TG_GC inf
235
+ TG_GG inf
236
+ TG_GT inf
237
+ TG_TA inf
238
+ TG_TC inf
239
+ TG_TG inf
240
+ TG_TT inf
241
+ TT_AA -22.2
242
+ TT_AC inf
243
+ TT_AG inf
244
+ TT_AT inf
245
+ TT_CA inf
246
+ TT_CC inf
247
+ TT_CG inf
248
+ TT_CT inf
249
+ TT_GA -9
250
+ TT_GC inf
251
+ TT_GG inf
252
+ TT_GT inf
253
+ TT_TA inf
254
+ TT_TC inf
255
+ TT_TG inf
256
+ TT_TT inf
@@ -0,0 +1,257 @@
1
+ /* values in articles are modified as follows: dS *(-10) and dH *(-10) */
2
+ AA_AA inf
3
+ AA_AC inf
4
+ AA_AG inf
5
+ AA_AT inf
6
+ AA_CA inf
7
+ AA_CC inf
8
+ AA_CG inf
9
+ AA_CT 7600
10
+ AA_GA inf
11
+ AA_GC inf
12
+ AA_GG inf
13
+ AA_GT 3000
14
+ AA_TA 1200
15
+ AA_TC 2300
16
+ AA_TG -600
17
+ AA_TT inf
18
+ AC_AA inf
19
+ AC_AC inf
20
+ AC_AG -2900
21
+ AC_AT inf
22
+ AC_CA inf
23
+ AC_CC inf
24
+ AC_CG -700
25
+ AC_CT inf
26
+ AC_GA inf
27
+ AC_GC inf
28
+ AC_GG 500
29
+ AC_GT inf
30
+ AC_TA 5300
31
+ AC_TC 0
32
+ AC_TG -8400
33
+ AC_TT 700
34
+ AG_AA inf
35
+ AG_AC -900
36
+ AG_AG inf
37
+ AG_AT inf
38
+ AG_CA inf
39
+ AG_CC 600
40
+ AG_CG inf
41
+ AG_CT inf
42
+ AG_GA inf
43
+ AG_GC -4000
44
+ AG_GG inf
45
+ AG_GT inf
46
+ AG_TA -700
47
+ AG_TC inf
48
+ AG_TG -3100
49
+ AG_TT -1000
50
+ AT_AA 1200
51
+ AT_AC inf
52
+ AT_AG inf
53
+ AT_AT inf
54
+ AT_CA 5300
55
+ AT_CC inf
56
+ AT_CG inf
57
+ AT_CT inf
58
+ AT_GA -700
59
+ AT_GC inf
60
+ AT_GG inf
61
+ AT_GT inf
62
+ AT_TA -7200
63
+ AT_TC -1200
64
+ AT_TG -2500
65
+ AT_TT -2700
66
+ CA_AA inf
67
+ CA_AC inf
68
+ CA_AG inf
69
+ CA_AT 3400
70
+ CA_CA inf
71
+ CA_CC inf
72
+ CA_CG inf
73
+ CA_CT 6100
74
+ CA_GA -900
75
+ CA_GC 1900
76
+ CA_GG -700
77
+ CA_GT inf
78
+ CA_TA inf
79
+ CA_TC inf
80
+ CA_TG inf
81
+ CA_TT 1000
82
+ CC_AA inf
83
+ CC_AC inf
84
+ CC_AG 5200
85
+ CC_AT inf
86
+ CC_CA inf
87
+ CC_CC inf
88
+ CC_CG 3600
89
+ CC_CT inf
90
+ CC_GA 600
91
+ CC_GC -1500
92
+ CC_GG inf
93
+ CC_GT -800
94
+ CC_TA inf
95
+ CC_TC inf
96
+ CC_TG 5200
97
+ CC_TT inf
98
+ CG_AA inf
99
+ CG_AC 1900
100
+ CG_AG inf
101
+ CG_AT inf
102
+ CG_CA inf
103
+ CG_CC -1500
104
+ CG_CG inf
105
+ CG_CT inf
106
+ CG_GA -4000
107
+ CG_GC inf
108
+ CG_GG -4900
109
+ CG_GT -4100
110
+ CG_TA inf
111
+ CG_TC -1500
112
+ CG_TG inf
113
+ CG_TT inf
114
+ CT_AA 2300
115
+ CT_AC inf
116
+ CT_AG inf
117
+ CT_AT inf
118
+ CT_CA 0
119
+ CT_CC inf
120
+ CT_CG inf
121
+ CT_CT inf
122
+ CT_GA inf
123
+ CT_GC -1500
124
+ CT_GG -2800
125
+ CT_GT -5000
126
+ CT_TA -1200
127
+ CT_TC inf
128
+ CT_TG inf
129
+ CT_TT inf
130
+ GA_AA inf
131
+ GA_AC inf
132
+ GA_AG inf
133
+ GA_AT 700
134
+ GA_CA -2900
135
+ GA_CC 5200
136
+ GA_CG -600
137
+ GA_CT inf
138
+ GA_GA inf
139
+ GA_GC inf
140
+ GA_GG inf
141
+ GA_GT 1600
142
+ GA_TA inf
143
+ GA_TC inf
144
+ GA_TG inf
145
+ GA_TT -1300
146
+ GC_AA inf
147
+ GC_AC inf
148
+ GC_AG -600
149
+ GC_AT inf
150
+ GC_CA -700
151
+ GC_CC 3600
152
+ GC_CG inf
153
+ GC_CT 2300
154
+ GC_GA inf
155
+ GC_GC inf
156
+ GC_GG -6000
157
+ GC_GT inf
158
+ GC_TA inf
159
+ GC_TC inf
160
+ GC_TG -4400
161
+ GC_TT inf
162
+ GG_AA inf
163
+ GG_AC -700
164
+ GG_AG inf
165
+ GG_AT inf
166
+ GG_CA 500
167
+ GG_CC inf
168
+ GG_CG -6000
169
+ GG_CT 3300
170
+ GG_GA inf
171
+ GG_GC -4900
172
+ GG_GG inf
173
+ GG_GT inf
174
+ GG_TA inf
175
+ GG_TC -2800
176
+ GG_TG inf
177
+ GG_TT 5800
178
+ GT_AA -600
179
+ GT_AC inf
180
+ GT_AG inf
181
+ GT_AT inf
182
+ GT_CA inf
183
+ GT_CC 5200
184
+ GT_CG -4400
185
+ GT_CT -2200
186
+ GT_GA -3100
187
+ GT_GC inf
188
+ GT_GG inf
189
+ GT_GT inf
190
+ GT_TA -2500
191
+ GT_TC inf
192
+ GT_TG 4100
193
+ GT_TT inf
194
+ TA_AA 4700
195
+ TA_AC 3400
196
+ TA_AG 700
197
+ TA_AT inf
198
+ TA_CA inf
199
+ TA_CC inf
200
+ TA_CG inf
201
+ TA_CT 1200
202
+ TA_GA inf
203
+ TA_GC inf
204
+ TA_GG inf
205
+ TA_GT -100
206
+ TA_TA inf
207
+ TA_TC inf
208
+ TA_TG inf
209
+ TA_TT 200
210
+ TC_AA 7600
211
+ TC_AC 6100
212
+ TC_AG inf
213
+ TC_AT 1200
214
+ TC_CA inf
215
+ TC_CC inf
216
+ TC_CG 2300
217
+ TC_CT inf
218
+ TC_GA inf
219
+ TC_GC inf
220
+ TC_GG 3300
221
+ TC_GT inf
222
+ TC_TA inf
223
+ TC_TC inf
224
+ TC_TG -2200
225
+ TC_TT inf
226
+ TG_AA 3000
227
+ TG_AC inf
228
+ TG_AG 1600
229
+ TG_AT -100
230
+ TG_CA inf
231
+ TG_CC -800
232
+ TG_CG inf
233
+ TG_CT inf
234
+ TG_GA inf
235
+ TG_GC -4100
236
+ TG_GG inf
237
+ TG_GT -1400
238
+ TG_TA inf
239
+ TG_TC -5000
240
+ TG_TG inf
241
+ TG_TT inf
242
+ TT_AA inf
243
+ TT_AC 1000
244
+ TT_AG -1300
245
+ TT_AT 200
246
+ TT_CA 700
247
+ TT_CC inf
248
+ TT_CG inf
249
+ TT_CT inf
250
+ TT_GA -100
251
+ TT_GC inf
252
+ TT_GG 5800
253
+ TT_GT inf
254
+ TT_TA -2700
255
+ TT_TC inf
256
+ TT_TG inf
257
+ TT_TT inf