Mercurial > repos > ucsb-phylogenetics > osiris_phylogenetics
comparison orthologs/ucsb_hamster/lib/wisecfg/human.gf @ 0:5b9a38ec4a39 draft default tip
First commit of old repositories
author | osiris_phylogenetics <ucsb_phylogenetics@lifesci.ucsb.edu> |
---|---|
date | Tue, 11 Mar 2014 12:19:13 -0700 |
parents | |
children |
comparison
equal
deleted
inserted
replaced
-1:000000000000 | 0:5b9a38ec4a39 |
---|---|
1 # Splice sites and intron regions information for GeneWise-21 | |
2 # Wed Jan 1 13:42:23 IST 1997 | |
3 # Created by Mor Amitai (mor@compugen.co.il) | |
4 # dataset : hum1 and hum2 from embl48 | |
5 # Consensi are read from top down. The value, for a sequence, | |
6 # is the number in the line of the first consensus that | |
7 # matches the sequence. | |
8 # Note: the set of sequences that are represented by a consensus | |
9 # are all the sequences that match this consensus and none of the | |
10 # previous consensi | |
11 # | |
12 # the numbers in types 5SS, 3SS, CDS, and the emissions are the number of | |
13 # occurrences of each sequence in the database. | |
14 # In case of a consensus this is the number of occurrences of sequences | |
15 # that are represented by the consensus in the database divided by the | |
16 # number of sequences that are represented by the consensus. | |
17 # *stay_prob is the probability of the transition from the state to itself. | |
18 # No_Spacer_Prob is the probability of transition from Pyrimidine directly | |
19 # to 3SS (no spacer). | |
20 type 5SS | |
21 center 3 | |
22 phase all | |
23 begin consensus | |
24 C-GGTGAGTG 15.75 | |
25 --GGTGAGTG 8.83333 | |
26 CAGGTGAG-- 7.6 | |
27 AAGGTGAG-- 6.86667 | |
28 CAGGTAAG-- 4.3125 | |
29 GAGGTGAG-- 4.26667 | |
30 AAGGTAAG-- 4.1875 | |
31 --GGTGAGT- 1.71795 | |
32 ---GTGAGTG 1.66667 | |
33 --GGTGAG-C 1.51282 | |
34 -A-GTAAGT- 1.41071 | |
35 -AGGTG-GT- 1.39583 | |
36 -TGGTAAG-- 1.39062 | |
37 CAGGTA-G-- 1.35417 | |
38 AAGGTA-G-- 1.04167 | |
39 -GGGTAAG-- 1 | |
40 --GGTGAG-- 0.91453 | |
41 -C-GTAAGT- 0.828125 | |
42 ---GTGAGT- 0.729167 | |
43 -AGGTAA--- 0.578704 | |
44 -AGGTG-G-- 0.506944 | |
45 CAGGTA---- 0.381944 | |
46 --GGTA-GT- 0.339286 | |
47 -AGGTGA--- 0.265625 | |
48 --GGTCAG-- 0.207031 | |
49 ---GTAAG-- 0.155556 | |
50 -AGGTA---- 0.134921 | |
51 -AGGT--G-- 0.111607 | |
52 --GGT--G-- 0.0369898 | |
53 -AGGT----- 0.0250947 | |
54 --GGTA---- 0.0234375 | |
55 --AGT--G-- 0.0132415 | |
56 ---GT----- 0.00148067 | |
57 end consensus | |
58 type 5SS | |
59 center 3 | |
60 phase 0 | |
61 begin consensus | |
62 A-GGTGAGTG 8.25 | |
63 C-GGTGAGTG 7.75 | |
64 AAGGTGAG-- 3.86667 | |
65 CAGGTGAG-- 3.46667 | |
66 AAGGTAAG-- 2.5 | |
67 GAGGTGAG-- 2.4375 | |
68 --GGTGAGT- 1.19565 | |
69 -AGGTAAG-- 1.02083 | |
70 -A-GTGAGT- 0.916667 | |
71 -AGGT--GTG 0.785714 | |
72 AAGGT-GG-- 0.716667 | |
73 -C-GTGAGT- 0.666667 | |
74 ---GTAAGTG 0.566667 | |
75 --GGTGAG-- 0.423077 | |
76 --GGTAAG-- 0.355556 | |
77 CAGGT--G-- 0.3 | |
78 ---GTAAGT- 0.284722 | |
79 -AGGTAA--- 0.265625 | |
80 --GGTA-GT- 0.196429 | |
81 -AGGTAC--- 0.157895 | |
82 AAGGTG---- 0.13964 | |
83 -AGGTG---- 0.048048 | |
84 -AGGT----- 0.0181818 | |
85 --GGT--G-- 0.0129717 | |
86 ---GTA---- 0.00291667 | |
87 ---GT----- 0.000915751 | |
88 end consensus | |
89 type 5SS | |
90 center 3 | |
91 phase 1 | |
92 begin consensus | |
93 --GGTGAGTG 4.375 | |
94 CAGGTGAG-- 2.8 | |
95 AAGGTGAG-- 2.26667 | |
96 -AGGTAAG-- 1.01562 | |
97 -TGGTAAG-- 0.8125 | |
98 -TGGTGAG-- 0.7 | |
99 G-GGTGAG-- 0.755556 | |
100 CAGGT-GG-- 0.546875 | |
101 --GGTGAG-- 0.428571 | |
102 ---GTGAGTG 0.625 | |
103 ---GTAAGT- 0.223214 | |
104 AAGGT--G-- 0.200893 | |
105 -AGGTAA--- 0.1875 | |
106 --GGTA-G-G 0.175 | |
107 CAGGT----- 0.0733945 | |
108 ---GTGAG-- 0.0527778 | |
109 --GGT--GT- 0.0512129 | |
110 A-GGTA---- 0.046398 | |
111 -AGGT----- 0.0137104 | |
112 ---G-AAG-- 0.00972447 | |
113 ---GT----- 0.00111909 | |
114 end consensus | |
115 type 5SS | |
116 center 3 | |
117 phase 2 | |
118 begin consensus | |
119 -AGGTGAG-- 0.703125 | |
120 C--GTGAGT- 0.516667 | |
121 -AGGTAAG-- 0.5 | |
122 ---GTAAGT- 0.241667 | |
123 --GGTGAG-- 0.227778 | |
124 CAGGTA---- 0.133333 | |
125 ---GTGAG-- 0.0569444 | |
126 -AGGT--G-- 0.0483491 | |
127 ---GTAAG-- 0.0444444 | |
128 --GGTA---- 0.00896991 | |
129 ---GT----- 0.000797367 | |
130 end consensus | |
131 type 3SS | |
132 center 3 | |
133 phase all | |
134 begin consensus | |
135 CAGGTG 143 | |
136 CAGGGT 120 | |
137 CAGGGC 88 | |
138 CAGGGA 82 | |
139 CAGGCT 77 | |
140 CAGGAG 73 | |
141 CAGGGG 66 | |
142 CAGGTA 60 | |
143 CAGGCC 58 | |
144 CAGGAA 54 | |
145 CAGATC 50 | |
146 CAGCTG 50 | |
147 CAGG-C 43.5 | |
148 CAGG-T 38.5 | |
149 CAGA-C 35.6667 | |
150 CAGAT- 29.3333 | |
151 CAGA-A 27.3333 | |
152 CAG-TC 25.5 | |
153 TAGG-G 21.75 | |
154 CAG-CA 21.6667 | |
155 TAGGA- 21.3333 | |
156 TAGGG- 20.6667 | |
157 CAGA-G 19.3333 | |
158 CAGTG- 18.75 | |
159 CAGA-- 18 | |
160 TAGG-- 13.8333 | |
161 CAG-C- 11.8571 | |
162 CAG-T- 10.4 | |
163 CAG-A- 7.375 | |
164 TAGA-- 6.0625 | |
165 TAGC-- 3.3125 | |
166 AAGG-- 3.125 | |
167 -AGT-- 1.08333 | |
168 -AG--- 0.714286 | |
169 end consensus | |
170 type 3SS | |
171 center 3 | |
172 phase 0 | |
173 begin consensus | |
174 CAGGGT 88 | |
175 CAGGTG 64 | |
176 CAGGAG 43 | |
177 CAGGG- 40.3333 | |
178 CAGATC 32 | |
179 CAGG-C 25 | |
180 CAGG-A 19 | |
181 CAGG-T 17.3333 | |
182 CAGA-C 14.6667 | |
183 CAG-TG 13 | |
184 CAGAA- 13 | |
185 CAGA-T 11.3333 | |
186 CAGC-C 10.25 | |
187 TAGG-- 9.8125 | |
188 CAG--A 4.09091 | |
189 CAGT-- 4.45455 | |
190 TAG-T- 3.33333 | |
191 TAG--- 1.36111 | |
192 -AGG-- 1.06061 | |
193 -AG--- 0.342857 | |
194 end consensus | |
195 type 3SS | |
196 center 3 | |
197 phase 1 | |
198 begin consensus | |
199 CAGGTG 71 | |
200 CAGGCT 36 | |
201 CAGGG- 24.75 | |
202 CAG-CC 17.5 | |
203 CAG-TG 16.6667 | |
204 CAGAG- 15.75 | |
205 CAGG-- 14.5556 | |
206 CAGA-A 13.3333 | |
207 CAGTG- 10.75 | |
208 CAG-TC 10.3333 | |
209 TAGG-G 9.5 | |
210 CAGA-- 6.16667 | |
211 TAGG-- 5 | |
212 CAGC-- 3.69231 | |
213 TAG--- 1.66667 | |
214 -AG--- 0.328467 | |
215 end consensus | |
216 type 3SS | |
217 center 3 | |
218 phase 2 | |
219 begin consensus | |
220 CAGG-A 19.25 | |
221 CAGG-T 14.75 | |
222 CAG-G- 4.57143 | |
223 CAG--T 4.66667 | |
224 TAGG-- 3 | |
225 CAG--- 2.87879 | |
226 TAG--- 0.645833 | |
227 AAG--- 0.25 | |
228 end consensus | |
229 type CDS | |
230 phase all | |
231 begin consensus | |
232 AAA 5290.000000 | |
233 AAC 4795.000000 | |
234 AAG 8178.000000 | |
235 AAT 3305.000000 | |
236 ACA 6240.000000 | |
237 ACC 7728.000000 | |
238 ACG 3347.000000 | |
239 ACT 4930.000000 | |
240 AGA 8491.000000 | |
241 AGC 8639.000000 | |
242 AGG 8997.000000 | |
243 AGT 4417.000000 | |
244 ATA 1975.000000 | |
245 ATC 4973.000000 | |
246 ATG 6474.000000 | |
247 ATT 3083.000000 | |
248 CAA 7057.000000 | |
249 CAC 6815.000000 | |
250 CAG 11041.000000 | |
251 CAT 5779.000000 | |
252 CCA 10537.000000 | |
253 CCC 10307.000000 | |
254 CCG 5621.000000 | |
255 CCT 10134.000000 | |
256 CGA 3377.000000 | |
257 CGC 5146.000000 | |
258 CGG 5375.000000 | |
259 CGT 2765.000000 | |
260 CTA 3502.000000 | |
261 CTC 7465.000000 | |
262 CTG 13780.000000 | |
263 CTT 5453.000000 | |
264 GAA 7461.000000 | |
265 GAC 6937.000000 | |
266 GAG 9975.000000 | |
267 GAT 4949.000000 | |
268 GCA 7747.000000 | |
269 GCC 10890.000000 | |
270 GCG 4828.000000 | |
271 GCT 9371.000000 | |
272 GGA 10143.000000 | |
273 GGC 10400.000000 | |
274 GGG 8869.000000 | |
275 GGT 5567.000000 | |
276 GTA 2143.000000 | |
277 GTC 4593.000000 | |
278 GTG 8189.000000 | |
279 GTT 3021.000000 | |
280 TAA 1775.000000 | |
281 TAC 3687.000000 | |
282 TAG 1333.000000 | |
283 TAT 2477.000000 | |
284 TCA 6180.000000 | |
285 TCC 7668.000000 | |
286 TCG 2875.000000 | |
287 TCT 5767.000000 | |
288 TGA 7315.000000 | |
289 TGC 8625.000000 | |
290 TGG 11718.000000 | |
291 TGT 5197.000000 | |
292 TTA 1664.000000 | |
293 TTC 5462.000000 | |
294 TTG 4420.000000 | |
295 TTT 3453.000000 | |
296 end consensus | |
297 type CDS | |
298 phase 0 | |
299 begin consensus | |
300 AAA 2167.000000 | |
301 AAC 2839.000000 | |
302 AAG 4830.000000 | |
303 AAT 1616.000000 | |
304 ACA 1543.000000 | |
305 ACC 3187.000000 | |
306 ACG 983.000000 | |
307 ACT 1484.000000 | |
308 AGA 995.000000 | |
309 AGC 2722.000000 | |
310 AGG 1326.000000 | |
311 AGT 1093.000000 | |
312 ATA 585.000000 | |
313 ATC 3281.000000 | |
314 ATG 2538.000000 | |
315 ATT 1584.000000 | |
316 CAA 1141.000000 | |
317 CAC 1981.000000 | |
318 CAG 4796.000000 | |
319 CAT 1016.000000 | |
320 CCA 2021.000000 | |
321 CCC 3183.000000 | |
322 CCG 1104.000000 | |
323 CCT 2289.000000 | |
324 CGA 770.000000 | |
325 CGC 2011.000000 | |
326 CGG 1762.000000 | |
327 CGT 687.000000 | |
328 CTA 745.000000 | |
329 CTC 2964.000000 | |
330 CTG 6980.000000 | |
331 CTT 1200.000000 | |
332 GAA 2729.000000 | |
333 GAC 3946.000000 | |
334 GAG 6121.000000 | |
335 GAT 2318.000000 | |
336 GCA 1767.000000 | |
337 GCC 4902.000000 | |
338 GCG 1288.000000 | |
339 GCT 2556.000000 | |
340 GGA 2322.000000 | |
341 GGC 4338.000000 | |
342 GGG 2688.000000 | |
343 GGT 1903.000000 | |
344 GTA 690.000000 | |
345 GTC 2172.000000 | |
346 GTG 4546.000000 | |
347 GTT 1020.000000 | |
348 TAA 0.000000 | |
349 TAC 2405.000000 | |
350 TAG 0.000000 | |
351 TAT 1323.000000 | |
352 TCA 990.000000 | |
353 TCC 2579.000000 | |
354 TCG 684.000000 | |
355 TCT 1522.000000 | |
356 TGA 0.000000 | |
357 TGC 1747.000000 | |
358 TGG 1766.000000 | |
359 TGT 931.000000 | |
360 TTA 397.000000 | |
361 TTC 3156.000000 | |
362 TTG 1313.000000 | |
363 TTT 1697.000000 | |
364 end consensus | |
365 type CDS | |
366 phase 1 | |
367 begin consensus | |
368 AAA 1534.000000 | |
369 AAC 1140.000000 | |
370 AAG 2597.000000 | |
371 AAT 767.000000 | |
372 ACA 3632.000000 | |
373 ACC 3429.000000 | |
374 ACG 1849.000000 | |
375 ACT 2262.000000 | |
376 AGA 4427.000000 | |
377 AGC 4014.000000 | |
378 AGG 5377.000000 | |
379 AGT 1927.000000 | |
380 ATA 953.000000 | |
381 ATC 1055.000000 | |
382 ATG 3488.000000 | |
383 ATT 777.000000 | |
384 CAA 998.000000 | |
385 CAC 1332.000000 | |
386 CAG 3260.000000 | |
387 CAT 731.000000 | |
388 CCA 4701.000000 | |
389 CCC 3908.000000 | |
390 CCG 2252.000000 | |
391 CCT 2992.000000 | |
392 CGA 471.000000 | |
393 CGC 1361.000000 | |
394 CGG 1785.000000 | |
395 CGT 443.000000 | |
396 CTA 825.000000 | |
397 CTC 1766.000000 | |
398 CTG 4378.000000 | |
399 CTT 882.000000 | |
400 GAA 924.000000 | |
401 GAC 843.000000 | |
402 GAG 1897.000000 | |
403 GAT 424.000000 | |
404 GCA 3140.000000 | |
405 GCC 3275.000000 | |
406 GCG 1806.000000 | |
407 GCT 2595.000000 | |
408 GGA 1911.000000 | |
409 GGC 2034.000000 | |
410 GGG 2835.000000 | |
411 GGT 762.000000 | |
412 GTA 577.000000 | |
413 GTC 968.000000 | |
414 GTG 2506.000000 | |
415 GTT 563.000000 | |
416 TAA 622.000000 | |
417 TAC 561.000000 | |
418 TAG 912.000000 | |
419 TAT 322.000000 | |
420 TCA 3963.000000 | |
421 TCC 3535.000000 | |
422 TCG 1466.000000 | |
423 TCT 2607.000000 | |
424 TGA 3311.000000 | |
425 TGC 4099.000000 | |
426 TGG 6194.000000 | |
427 TGT 1772.000000 | |
428 TTA 773.000000 | |
429 TTC 1353.000000 | |
430 TTG 2662.000000 | |
431 TTT 713.000000 | |
432 end consensus | |
433 type CDS | |
434 phase 2 | |
435 begin consensus | |
436 AAA 1589.000000 | |
437 AAC 816.000000 | |
438 AAG 751.000000 | |
439 AAT 922.000000 | |
440 ACA 1065.000000 | |
441 ACC 1112.000000 | |
442 ACG 515.000000 | |
443 ACT 1184.000000 | |
444 AGA 3069.000000 | |
445 AGC 1903.000000 | |
446 AGG 2294.000000 | |
447 AGT 1397.000000 | |
448 ATA 437.000000 | |
449 ATC 637.000000 | |
450 ATG 448.000000 | |
451 ATT 722.000000 | |
452 CAA 4918.000000 | |
453 CAC 3502.000000 | |
454 CAG 2985.000000 | |
455 CAT 4032.000000 | |
456 CCA 3815.000000 | |
457 CCC 3216.000000 | |
458 CCG 2265.000000 | |
459 CCT 4853.000000 | |
460 CGA 2136.000000 | |
461 CGC 1774.000000 | |
462 CGG 1828.000000 | |
463 CGT 1635.000000 | |
464 CTA 1932.000000 | |
465 CTC 2735.000000 | |
466 CTG 2422.000000 | |
467 CTT 3371.000000 | |
468 GAA 3808.000000 | |
469 GAC 2148.000000 | |
470 GAG 1957.000000 | |
471 GAT 2207.000000 | |
472 GCA 2840.000000 | |
473 GCC 2713.000000 | |
474 GCG 1734.000000 | |
475 GCT 4220.000000 | |
476 GGA 5910.000000 | |
477 GGC 4028.000000 | |
478 GGG 3346.000000 | |
479 GGT 2902.000000 | |
480 GTA 876.000000 | |
481 GTC 1453.000000 | |
482 GTG 1137.000000 | |
483 GTT 1438.000000 | |
484 TAA 1153.000000 | |
485 TAC 721.000000 | |
486 TAG 421.000000 | |
487 TAT 832.000000 | |
488 TCA 1227.000000 | |
489 TCC 1554.000000 | |
490 TCG 725.000000 | |
491 TCT 1638.000000 | |
492 TGA 4004.000000 | |
493 TGC 2779.000000 | |
494 TGG 3758.000000 | |
495 TGT 2494.000000 | |
496 TTA 494.000000 | |
497 TTC 953.000000 | |
498 TTG 445.000000 | |
499 TTT 1043.000000 | |
500 end consensus | |
501 type Intron_Corr_Term | |
502 phase all | |
503 65.6094 | |
504 type Intron_Corr_Term | |
505 phase 0 | |
506 141.429 | |
507 type Intron_Corr_Term | |
508 phase 1 | |
509 172.738 | |
510 type Intron_Corr_Term | |
511 phase 2 | |
512 371.127 | |
513 type Intron_emission | |
514 begin consensus | |
515 A 399845.000000 | |
516 C 371259.000000 | |
517 G 393779.000000 | |
518 T 425926.000000 | |
519 end consensus | |
520 type Pyrimidine_emission | |
521 begin consensus | |
522 A 2299.000000 | |
523 C 18610.000000 | |
524 G 2345.000000 | |
525 T 17132.000000 | |
526 end consensus | |
527 type Spacer_emission | |
528 begin consensus | |
529 A 3020.000000 | |
530 C 3834.000000 | |
531 G 3644.000000 | |
532 T 4224.000000 | |
533 end consensus | |
534 type Central_Intron_Stay_Prob | |
535 0.99853 | |
536 type Pyrimidine_Stay_Prob | |
537 0.944485 | |
538 type No_Spacer_Prob | |
539 0.331508 | |
540 type Spacer_Stay_Prob | |
541 0.902704 |