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 +1,131 @@
1
+ /* Enthalpy of dangling end */
2
+ /* 3' dangling */
3
+ AA_A 0
4
+ AC_A 0
5
+ AG_A 0
6
+ AT_A 0
7
+ AA_C 0
8
+ AC_C 0
9
+ AG_C 0
10
+ AT_C 0
11
+ AA_G 0
12
+ AC_G 0
13
+ AG_G 0
14
+ AT_G 0
15
+ AA_T 5
16
+ AC_T -47
17
+ AG_T 41
18
+ AT_T 38
19
+ CA_A 0
20
+ CC_A 0
21
+ CG_A 0
22
+ CT_A 0
23
+ CA_C 0
24
+ CC_C 0
25
+ CG_C 0
26
+ CT_C 0
27
+ CA_G 59
28
+ CC_G 26
29
+ CG_G 32
30
+ CT_G 52
31
+ CA_T 0
32
+ CC_T 0
33
+ CG_T 0
34
+ CT_T 0
35
+ GA_A 0
36
+ GC_A 0
37
+ GG_A 0
38
+ GT_A 0
39
+ GA_C 21
40
+ GC_C 2
41
+ GG_C 39
42
+ GT_C 44
43
+ GA_G 0
44
+ GC_G 0
45
+ GG_G 0
46
+ GT_G 0
47
+ GA_T 0
48
+ GC_T 0
49
+ GG_T 0
50
+ GT_T 0
51
+ TA_A 7
52
+ TC_A -44
53
+ TG_A 16
54
+ TT_A -29
55
+ TA_C 0
56
+ TC_C 0
57
+ TG_C 0
58
+ TT_C 0
59
+ TA_G 0
60
+ TC_G 0
61
+ TG_G 0
62
+ TT_G 0
63
+ TA_T 0
64
+ TC_T 0
65
+ TG_T 0
66
+ TT_T 0
67
+ /* 5' dangling */
68
+ A_AA 0
69
+ A_AC 0
70
+ A_AG 0
71
+ A_AT 0
72
+ A_CA 0
73
+ A_CC 0
74
+ A_CG 0
75
+ A_CT 0
76
+ A_GA 0
77
+ A_GC 0
78
+ A_GG 0
79
+ A_GT 0
80
+ A_TA 29
81
+ A_TC 41
82
+ A_TG 42
83
+ A_TT 2
84
+ C_AA 0
85
+ C_AC 0
86
+ C_AG 0
87
+ C_AT 0
88
+ C_CA 0
89
+ C_CC 0
90
+ C_CG 0
91
+ C_CT 0
92
+ C_GA 37
93
+ C_GC 40
94
+ C_GG 39
95
+ C_GT 49
96
+ C_TA 0
97
+ C_TC 0
98
+ C_TG 0
99
+ C_TT 0
100
+ G_AA 0
101
+ G_AC 0
102
+ G_AG 0
103
+ G_AT 0
104
+ G_CA 63
105
+ G_CC 44
106
+ G_CG 51
107
+ G_CT 40
108
+ G_GA 0
109
+ G_GC 0
110
+ G_GG 0
111
+ G_GT 0
112
+ G_TA 0
113
+ G_TC 0
114
+ G_TG 0
115
+ G_TT 0
116
+ T_AA -2
117
+ T_AC -6
118
+ T_AG 11
119
+ T_AT 69
120
+ T_CA 0
121
+ T_CC 0
122
+ T_CG 0
123
+ T_CT 0
124
+ T_GA 0
125
+ T_GC 0
126
+ T_GG 0
127
+ T_GT 0
128
+ T_TA 0
129
+ T_TC 0
130
+ T_TG 0
131
+ T_TT 0
@@ -0,0 +1,131 @@
1
+ /* Entropy of dangling end */
2
+ /* 3' dangling */
3
+ AA_A 0
4
+ AC_A 0
5
+ AG_A 0
6
+ AT_A 0
7
+ AA_C 0
8
+ AC_C 0
9
+ AG_C 0
10
+ AT_C 0
11
+ AA_G 0
12
+ AC_G 0
13
+ AG_G 0
14
+ AT_G 0
15
+ AA_T 11
16
+ AC_T -142
17
+ AG_T 131
18
+ AT_T 126
19
+ CA_A 0
20
+ CC_A 0
21
+ CG_A 0
22
+ CT_A 0
23
+ CA_C 0
24
+ CC_C 0
25
+ CG_C 0
26
+ CT_C 0
27
+ CA_G 165
28
+ CC_G 74
29
+ CG_G 104
30
+ CT_G 150
31
+ CA_T 0
32
+ CC_T 0
33
+ CG_T 0
34
+ CT_T 0
35
+ GA_A 0
36
+ GC_A 0
37
+ GG_A 0
38
+ GT_A 0
39
+ GA_C 39
40
+ GC_C 1
41
+ GG_C 112
42
+ GT_C 131
43
+ GA_G 0
44
+ GC_G 0
45
+ GG_G 0
46
+ GT_G 0
47
+ GA_T 0
48
+ GC_T 0
49
+ GG_T 0
50
+ GT_T 0
51
+ TA_A 8
52
+ TC_A -149
53
+ TG_A 36
54
+ TT_A -104
55
+ TA_C 0
56
+ TC_C 0
57
+ TG_C 0
58
+ TT_C 0
59
+ TA_G 0
60
+ TC_G 0
61
+ TG_G 0
62
+ TT_G 0
63
+ TA_T 0
64
+ TC_T 0
65
+ TG_T 0
66
+ TT_T 0
67
+ /* 5' dangling */
68
+ A_AA 0
69
+ A_AC 0
70
+ A_AG 0
71
+ A_AT 0
72
+ A_CA 0
73
+ A_CC 0
74
+ A_CG 0
75
+ A_CT 0
76
+ A_GA 0
77
+ A_GC 0
78
+ A_GG 0
79
+ A_GT 0
80
+ A_TA 76
81
+ A_TC 130
82
+ A_TG 150
83
+ A_TT 5
84
+ C_AA 0
85
+ C_AC 0
86
+ C_AG 0
87
+ C_AT 0
88
+ C_CA 0
89
+ C_CC 0
90
+ C_CG 0
91
+ C_CT 0
92
+ C_GA 100
93
+ C_GC 119
94
+ C_GG 109
95
+ C_GT 138
96
+ C_TA 0
97
+ C_TC 0
98
+ C_TG 0
99
+ C_TT 0
100
+ G_AA 0
101
+ G_AC 0
102
+ G_AG 0
103
+ G_AT 0
104
+ G_CA 171
105
+ G_CC 126
106
+ G_CG 140
107
+ G_CT 109
108
+ G_GA 0
109
+ G_GC 0
110
+ G_GG 0
111
+ G_GT 0
112
+ G_TA 0
113
+ G_TC 0
114
+ G_TG 0
115
+ G_TT 0
116
+ T_AA -23
117
+ T_AC -33
118
+ T_AG 16
119
+ T_AT 200
120
+ T_CA 0
121
+ T_CC 0
122
+ T_CG 0
123
+ T_CT 0
124
+ T_GA 0
125
+ T_GC 0
126
+ T_GG 0
127
+ T_GT 0
128
+ T_TA 0
129
+ T_TC 0
130
+ T_TG 0
131
+ T_TT 0
@@ -0,0 +1,34 @@
1
+ DESTABILIZING ENTHALPIES BY SIZE OF LOOP (INTERPOLATE WHERE NEEDED)
2
+ hp3 ave calc no tmm;hp4 ave calc with tmm; ave all bulges
3
+ SIZE INTERNAL BULGE HAIRPIN
4
+ -------------------------------------------------------
5
+ 1 . 0.0 .
6
+ 2 0.0 0.0 .
7
+ 3 0.0 0.0 0.0
8
+ 4 0.0 0.0 0.0
9
+ 5 0.0 0.0 0.0
10
+ 6 0.0 0.0 0.0
11
+ 7 0.0 0.0 0.0
12
+ 8 0.0 0.0 0.0
13
+ 9 0.0 0.0 0.0
14
+ 10 0.0 0.0 0.0
15
+ 11 0.0 0.0 0.0
16
+ 12 0.0 0.0 0.0
17
+ 13 0.0 0.0 0.0
18
+ 14 0.0 0.0 0.0
19
+ 15 0.0 0.0 0.0
20
+ 16 0.0 0.0 0.0
21
+ 17 0.0 0.0 0.0
22
+ 18 0.0 0.0 0.0
23
+ 19 0.0 0.0 0.0
24
+ 20 0.0 0.0 0.0
25
+ 21 0.0 0.0 0.0
26
+ 22 0.0 0.0 0.0
27
+ 23 0.0 0.0 0.0
28
+ 24 0.0 0.0 0.0
29
+ 25 0.0 0.0 0.0
30
+ 26 0.0 0.0 0.0
31
+ 27 0.0 0.0 0.0
32
+ 28 0.0 0.0 0.0
33
+ 29 0.0 0.0 0.0
34
+ 30 0.0 0.0 0.0
@@ -0,0 +1,31 @@
1
+ SIZE INTERNAL BULGE HAIRPIN
2
+ 1 . -128.9 .
3
+ 2 . -93.5 .
4
+ 3 -103.1 -99.9 -112.8
5
+ 4 -116 -103.1 -112.8
6
+ 5 -128.9 -106.4 -106.4
7
+ 6 -141.8 -112.8 -128.9
8
+ 7 -148.3 -119.2 -135.4
9
+ 8 -154.7 -125.7 -138.6
10
+ 9 -157.9 -132.1 -145
11
+ 10 -157.9 -138.6 -148.3
12
+ 11 -162.6 -143.2 -152.9
13
+ 12 -167.6 -145 -161.2
14
+ 13 -171.5 -148.9 -165
15
+ 14 -174.1 -154.7 -164.4
16
+ 15 -177.4 -158.1 -167.7
17
+ 16 -180.5 -161.2 -170.8
18
+ 17 -183.4 -164.1 -173.8
19
+ 18 -187 -167.6 -177.3
20
+ 19 -189.6 -170.2 -179.9
21
+ 20 -190.2 -170.8 -183.7
22
+ 21 -192.5 -173.2 -186.1
23
+ 22 -194.8 -175.5 -188.4
24
+ 23 -197 -177.6 -190.5
25
+ 24 -199 -179.7 -192.6
26
+ 25 -203.1 -180.5 -196.6
27
+ 26 -205 -182.4 -198.5
28
+ 27 -206.8 -184.2 -200.4
29
+ 28 -208.6 -186 -202.1
30
+ 29 -210.3 -187.7 -203.8
31
+ 30 -212.8 -190.2 -203.1
@@ -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 inf
10
+ AA_GA inf
11
+ AA_GC inf
12
+ AA_GG inf
13
+ AA_GT inf
14
+ AA_TA inf
15
+ AA_TC inf
16
+ AA_TG inf
17
+ AA_TT -7900
18
+ AC_AA inf
19
+ AC_AC inf
20
+ AC_AG inf
21
+ AC_AT inf
22
+ AC_CA inf
23
+ AC_CC inf
24
+ AC_CG inf
25
+ AC_CT inf
26
+ AC_GA inf
27
+ AC_GC inf
28
+ AC_GG inf
29
+ AC_GT inf
30
+ AC_TA inf
31
+ AC_TC inf
32
+ AC_TG -8400
33
+ AC_TT inf
34
+ AG_AA inf
35
+ AG_AC inf
36
+ AG_AG inf
37
+ AG_AT inf
38
+ AG_CA inf
39
+ AG_CC inf
40
+ AG_CG inf
41
+ AG_CT inf
42
+ AG_GA inf
43
+ AG_GC inf
44
+ AG_GG inf
45
+ AG_GT inf
46
+ AG_TA inf
47
+ AG_TC -7800
48
+ AG_TG inf
49
+ AG_TT inf
50
+ AT_AA inf
51
+ AT_AC inf
52
+ AT_AG inf
53
+ AT_AT inf
54
+ AT_CA inf
55
+ AT_CC inf
56
+ AT_CG inf
57
+ AT_CT inf
58
+ AT_GA inf
59
+ AT_GC inf
60
+ AT_GG inf
61
+ AT_GT inf
62
+ AT_TA -7200
63
+ AT_TC inf
64
+ AT_TG inf
65
+ AT_TT inf
66
+ CA_AA inf
67
+ CA_AC inf
68
+ CA_AG inf
69
+ CA_AT inf
70
+ CA_CA inf
71
+ CA_CC inf
72
+ CA_CG inf
73
+ CA_CT inf
74
+ CA_GA inf
75
+ CA_GC inf
76
+ CA_GG inf
77
+ CA_GT -8500
78
+ CA_TA inf
79
+ CA_TC inf
80
+ CA_TG inf
81
+ CA_TT inf
82
+ CC_AA inf
83
+ CC_AC inf
84
+ CC_AG -52
85
+ CC_AT inf
86
+ CC_CA inf
87
+ CC_CC inf
88
+ CC_CG -36
89
+ CC_CT inf
90
+ CC_GA inf
91
+ CC_GC inf
92
+ CC_GG -8000
93
+ CC_GT inf
94
+ CC_TA inf
95
+ CC_TC inf
96
+ CC_TG inf
97
+ CC_TT inf
98
+ CG_AA inf
99
+ CG_AC inf
100
+ CG_AG inf
101
+ CG_AT inf
102
+ CG_CA inf
103
+ CG_CC inf
104
+ CG_CG inf
105
+ CG_CT inf
106
+ CG_GA inf
107
+ CG_GC -10600
108
+ CG_GG inf
109
+ CG_GT inf
110
+ CG_TA inf
111
+ CG_TC inf
112
+ CG_TG inf
113
+ CG_TT inf
114
+ CT_AA inf
115
+ CT_AC inf
116
+ CT_AG inf
117
+ CT_AT inf
118
+ CT_CA inf
119
+ CT_CC inf
120
+ CT_CG inf
121
+ CT_CT inf
122
+ CT_GA -7800
123
+ CT_GC inf
124
+ CT_GG inf
125
+ CT_GT inf
126
+ CT_TA inf
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 inf
134
+ GA_CA inf
135
+ GA_CC inf
136
+ GA_CG inf
137
+ GA_CT -8200
138
+ GA_GA inf
139
+ GA_GC inf
140
+ GA_GG inf
141
+ GA_GT inf
142
+ GA_TA inf
143
+ GA_TC inf
144
+ GA_TG inf
145
+ GA_TT inf
146
+ GC_AA inf
147
+ GC_AC inf
148
+ GC_AG inf
149
+ GC_AT inf
150
+ GC_CA inf
151
+ GC_CC inf
152
+ GC_CG -9800
153
+ GC_CT inf
154
+ GC_GA inf
155
+ GC_GC inf
156
+ GC_GG inf
157
+ GC_GT inf
158
+ GC_TA inf
159
+ GC_TC inf
160
+ GC_TG inf
161
+ GC_TT inf
162
+ GG_AA inf
163
+ GG_AC inf
164
+ GG_AG inf
165
+ GG_AT inf
166
+ GG_CA inf
167
+ GG_CC -8000
168
+ GG_CG inf
169
+ GG_CT inf
170
+ GG_GA inf
171
+ GG_GC inf
172
+ GG_GG inf
173
+ GG_GT inf
174
+ GG_TA inf
175
+ GG_TC inf
176
+ GG_TG inf
177
+ GG_TT inf
178
+ GT_AA inf
179
+ GT_AC inf
180
+ GT_AG inf
181
+ GT_AT inf
182
+ GT_CA -8400
183
+ GT_CC inf
184
+ GT_CG inf
185
+ GT_CT inf
186
+ GT_GA inf
187
+ GT_GC inf
188
+ GT_GG inf
189
+ GT_GT inf
190
+ GT_TA inf
191
+ GT_TC inf
192
+ GT_TG inf
193
+ GT_TT inf
194
+ TA_AA inf
195
+ TA_AC inf
196
+ TA_AG inf
197
+ TA_AT -7200
198
+ TA_CA inf
199
+ TA_CC inf
200
+ TA_CG inf
201
+ TA_CT inf
202
+ TA_GA inf
203
+ TA_GC inf
204
+ TA_GG inf
205
+ TA_GT inf
206
+ TA_TA inf
207
+ TA_TC inf
208
+ TA_TG inf
209
+ TA_TT inf
210
+ TC_AA inf
211
+ TC_AC inf
212
+ TC_AG -8200
213
+ TC_AT inf
214
+ TC_CA inf
215
+ TC_CC inf
216
+ TC_CG inf
217
+ TC_CT inf
218
+ TC_GA inf
219
+ TC_GC inf
220
+ TC_GG inf
221
+ TC_GT inf
222
+ TC_TA inf
223
+ TC_TC inf
224
+ TC_TG inf
225
+ TC_TT inf
226
+ TG_AA inf
227
+ TG_AC -8500
228
+ TG_AG inf
229
+ TG_AT inf
230
+ TG_CA inf
231
+ TG_CC inf
232
+ TG_CG inf
233
+ TG_CT inf
234
+ TG_GA inf
235
+ TG_GC inf
236
+ TG_GG inf
237
+ TG_GT inf
238
+ TG_TA inf
239
+ TG_TC inf
240
+ TG_TG inf
241
+ TG_TT inf
242
+ TT_AA -7900
243
+ TT_AC inf
244
+ TT_AG inf
245
+ TT_AT inf
246
+ TT_CA inf
247
+ TT_CC inf
248
+ TT_CG inf
249
+ TT_CT inf
250
+ TT_GA inf
251
+ TT_GC inf
252
+ TT_GG inf
253
+ TT_GT inf
254
+ TT_TA inf
255
+ TT_TC inf
256
+ TT_TG inf
257
+ TT_TT inf