-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathviewingdata.Rmd
560 lines (349 loc) · 37.1 KB
/
viewingdata.Rmd
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
---
title: "GettingDFs"
author: "Shay Iyer"
date: "`r Sys.Date()`"
output: html_document
editor_options:
chunk_output_type: console
---
```{r setup, include=FALSE}
library(tidyverse)
candidates <- c("BAZ2B", "CDH5", "CD44", "CELF1", "FOXP1", "NRP1", "NRP2", "PECAM1", "SRSF1", "VASH1", "YAP1")
```
# USING EC AS ANNOTATION REFERENCE
```{r load mapping datasets baz2b}
baz2b.se <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/BAZ2B/se_map.csv") %>% filter(gene_name == "BAZ2B") %>% mutate(type = "se")
baz2b.mxe <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/BAZ2B/mxe_map.csv") %>% filter(gene_name == "BAZ2B") %>% mutate(type = "mxe")
baz2b.a3ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/BAZ2B/a3ss_map.csv") %>% filter(gene_name == "BAZ2B") %>% mutate(type = "a3ss")
baz2b.a5ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/BAZ2B/a5ss_map.csv") %>% filter(gene_name == "BAZ2B") %>% mutate(type = "a5ss")
baz2b.all.ec <- rbind(baz2b.se, baz2b.mxe, baz2b.a3ss, baz2b.a5ss)
rm(baz2b.se, baz2b.mxe, baz2b.a3ss, baz2b.a5ss)
```
```{r load mapping datasets cdh5}
cdh5.se <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/CDH5/se_map.csv") %>% filter(gene_name == "CDH5") %>% mutate(type = "se")
cdh5.mxe <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/CDH5/mxe_map.csv") %>% filter(gene_name == "CDH5") %>% mutate(type = "mxe")
cdh5.a3ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/CDH5/a3ss_map.csv") %>% filter(gene_name == "CDH5") %>% mutate(type = "a3ss")
cdh5.a5ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/CDH5/a5ss_map.csv") %>% filter(gene_name == "CDH5") %>% mutate(type = "a5ss")
cdh5.all.ec <- rbind(cdh5.se, cdh5.mxe, cdh5.a3ss, cdh5.a5ss)
rm(cdh5.se, cdh5.mxe, cdh5.a3ss, cdh5.a5ss)
```
```{r load mapping datasets cd44}
cd44.se <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/CD44/se_map.csv") %>% filter(gene_name == "CD44") %>% mutate(type = "se")
cd44.mxe <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/CD44/mxe_map.csv") %>% filter(gene_name == "CD44") %>% mutate(type = "mxe")
cd44.a3ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/CD44/a3ss_map.csv") %>% filter(gene_name == "CD44") %>% mutate(type = "a3ss")
cd44.a5ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/CD44/a5ss_map.csv") %>% filter(gene_name == "CD44") %>% mutate(type = "a5ss")
cd44.all.ec <- rbind(cd44.se, cd44.mxe, cd44.a3ss, cd44.a5ss)
rm(cd44.se, cd44.mxe, cd44.a3ss, cd44.a5ss)
```
```{r load mapping datasets celf1}
celf1.se <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/CELF1/se_map.csv") %>% filter(gene_name == "CELF1") %>% mutate(type = "se")
celf1.mxe <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/CELF1/mxe_map.csv") %>% filter(gene_name == "CELF1") %>% mutate(type = "mxe")
celf1.a3ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/CELF1/a3ss_map.csv") %>% filter(gene_name == "CELF1") %>% mutate(type = "a3ss")
celf1.a5ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/CELF1/a5ss_map.csv") %>% filter(gene_name == "CELF1") %>% mutate(type = "a5ss")
celf1.all.ec <- rbind(celf1.se, celf1.mxe, celf1.a3ss, celf1.a5ss)
rm(celf1.se, celf1.mxe, celf1.a3ss, celf1.a5ss)
```
```{r load mapping datasets foxp1}
foxp1.se <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/FOXP1/se_map.csv") %>% filter(gene_name == "FOXP1") %>% mutate(type = "se")
foxp1.mxe <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/FOXP1/mxe_map.csv") %>% filter(gene_name == "FOXP1") %>% mutate(type = "mxe")
foxp1.a3ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/FOXP1/a3ss_map.csv") %>% filter(gene_name == "FOXP1") %>% mutate(type = "a3ss")
foxp1.a5ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/FOXP1/a5ss_map.csv") %>% filter(gene_name == "FOXP1") %>% mutate(type = "a5ss")
foxp1.all.ec <- rbind(foxp1.se, foxp1.mxe, foxp1.a3ss, foxp1.a5ss)
rm(foxp1.se, foxp1.mxe, foxp1.a3ss, foxp1.a5ss)
```
```{r load mapping datasets nrp1}
nrp1.se <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/NRP1/se_map.csv") %>% filter(gene_name == "NRP1") %>% mutate(type = "se")
nrp1.mxe <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/NRP1/mxe_map.csv") %>% filter(gene_name == "NRP1") %>% mutate(type = "mxe")
nrp1.a3ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/NRP1/a3ss_map.csv") %>% filter(gene_name == "NRP1") %>% mutate(type = "a3ss")
nrp1.a5ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/NRP1/a5ss_map.csv") %>% filter(gene_name == "NRP1") %>% mutate(type = "a5ss")
nrp1.all.ec <- rbind(nrp1.se, nrp1.mxe, nrp1.a3ss, nrp1.a5ss)
rm(nrp1.se, nrp1.mxe, nrp1.a3ss, nrp1.a5ss)
```
```{r load mapping datasets nrp2}
nrp2.se <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/NRP2/se_map.csv") %>% filter(gene_name == "NRP2") %>% mutate(type = "se")
nrp2.mxe <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/NRP2/mxe_map.csv") %>% filter(gene_name == "NRP2") %>% mutate(type = "mxe")
nrp2.a3ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/NRP2/a3ss_map.csv") %>% filter(gene_name == "NRP2") %>% mutate(type = "a3ss")
nrp2.a5ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/NRP2/a5ss_map.csv") %>% filter(gene_name == "NRP2") %>% mutate(type = "a5ss")
nrp2.all.ec <- rbind(nrp2.se, nrp2.mxe, nrp2.a3ss, nrp2.a5ss)
rm(nrp2.se, nrp2.mxe, nrp2.a3ss, nrp2.a5ss)
```
```{r load mapping datasets pecam1}
pecam1.se <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/PECAM1/se_map.csv") %>% filter(gene_name == "PECAM1") %>% mutate(type = "se")
pecam1.mxe <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/PECAM1/mxe_map.csv") %>% filter(gene_name == "PECAM1") %>% mutate(type = "mxe")
pecam1.a3ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/PECAM1/a3ss_map.csv") %>% filter(gene_name == "PECAM1") %>% mutate(type = "a3ss")
pecam1.a5ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/PECAM1/a5ss_map.csv") %>% filter(gene_name == "PECAM1") %>% mutate(type = "a5ss")
pecam1.all.ec <- rbind(pecam1.se, pecam1.mxe, pecam1.a3ss, pecam1.a5ss)
rm(pecam1.se, pecam1.mxe, pecam1.a3ss, pecam1.a5ss)
```
```{r load mapping datasets vash1}
vash1.se <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/VASH1/se_map.csv") %>% filter(gene_name == "VASH1") %>% mutate(type = "se")
vash1.mxe <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/VASH1/mxe_map.csv") %>% filter(gene_name == "VASH1") %>% mutate(type = "mxe")
vash1.a3ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/VASH1/a3ss_map.csv") %>% filter(gene_name == "VASH1") %>% mutate(type = "a3ss")
vash1.a5ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/VASH1/a5ss_map.csv") %>% filter(gene_name == "VASH1") %>% mutate(type = "a5ss")
vash1.all.ec <- rbind(vash1.se, vash1.mxe, vash1.a3ss, vash1.a5ss)
rm(vash1.se, vash1.mxe, vash1.a3ss, vash1.a5ss)
```
```{r load mapping datasets srsf1}
srsf1.se <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/SRSF1/se_map.csv") %>% filter(gene_name == "SRSF1") %>% mutate(type = "se")
srsf1.mxe <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/SRSF1/mxe_map.csv") %>% filter(gene_name == "SRSF1") %>% mutate(type = "mxe")
srsf1.a3ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/SRSF1/a3ss_map.csv") %>% filter(gene_name == "SRSF1") %>% mutate(type = "a3ss")
srsf1.a5ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/SRSF1/a5ss_map.csv") %>% filter(gene_name == "SRSF1") %>% mutate(type = "a5ss")
srsf1.all.ec <- rbind(srsf1.se, srsf1.mxe, srsf1.a3ss, srsf1.a5ss)
rm(srsf1.se, srsf1.mxe, srsf1.a3ss, srsf1.a5ss)
```
```{r load mapping datasets yap1}
yap1.se <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/YAP1/se_map.csv") %>% filter(gene_name == "YAP1") %>% mutate(type = "se")
yap1.mxe <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/YAP1/mxe_map.csv") %>% filter(gene_name == "YAP1") %>% mutate(type = "mxe")
yap1.a3ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/YAP1/a3ss_map.csv") %>% filter(gene_name == "YAP1") %>% mutate(type = "a3ss")
yap1.a5ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/EC-annot/YAP1/a5ss_map.csv") %>% filter(gene_name == "YAP1") %>% mutate(type = "a5ss")
yap1.all.ec <- rbind(yap1.se, yap1.mxe, yap1.a3ss, yap1.a5ss)
rm(yap1.se, yap1.mxe, yap1.a3ss, yap1.a5ss)
```
# USING WTC11 AS ANNOTATION REFERENCE
```{r load mapping datasets baz2b}
baz2b.se <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/BAZ2B/se_map.csv") %>% filter(gene_name == "BAZ2B") %>% mutate(type = "se")
baz2b.mxe <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/BAZ2B/mxe_map.csv") %>% filter(gene_name == "BAZ2B") %>% mutate(type = "mxe")
baz2b.a3ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/BAZ2B/a3ss_map.csv") %>% filter(gene_name == "BAZ2B") %>% mutate(type = "a3ss")
baz2b.a5ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/BAZ2B/a5ss_map.csv") %>% filter(gene_name == "BAZ2B") %>% mutate(type = "a5ss")
baz2b.all.wtc11 <- rbind(baz2b.se, baz2b.mxe, baz2b.a3ss, baz2b.a5ss)
rm(baz2b.se, baz2b.mxe, baz2b.a3ss, baz2b.a5ss)
```
```{r load mapping datasets cdh5}
cdh5.se <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/CDH5/se_map.csv") %>% filter(gene_name == "CDH5") %>% mutate(type = "se")
cdh5.mxe <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/CDH5/mxe_map.csv") %>% filter(gene_name == "CDH5") %>% mutate(type = "mxe")
cdh5.a3ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/CDH5/a3ss_map.csv") %>% filter(gene_name == "CDH5") %>% mutate(type = "a3ss")
cdh5.a5ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/CDH5/a5ss_map.csv") %>% filter(gene_name == "CDH5") %>% mutate(type = "a5ss")
cdh5.all.wtc11 <- rbind(cdh5.se, cdh5.mxe, cdh5.a3ss, cdh5.a5ss)
rm(cdh5.se, cdh5.mxe, cdh5.a3ss, cdh5.a5ss)
```
```{r load mapping datasets cd44}
cd44.se <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/CD44/se_map.csv") %>% filter(gene_name == "CD44") %>% mutate(type = "se")
cd44.mxe <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/CD44/mxe_map.csv") %>% filter(gene_name == "CD44") %>% mutate(type = "mxe")
cd44.a3ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/CD44/a3ss_map.csv") %>% filter(gene_name == "CD44") %>% mutate(type = "a3ss")
cd44.a5ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/CD44/a5ss_map.csv") %>% filter(gene_name == "CD44") %>% mutate(type = "a5ss")
cd44.all.wtc11 <- rbind(cd44.se, cd44.mxe, cd44.a3ss, cd44.a5ss)
rm(cd44.se, cd44.mxe, cd44.a3ss, cd44.a5ss)
```
```{r load mapping datasets celf1}
celf1.se <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/CELF1/se_map.csv") %>% filter(gene_name == "CELF1") %>% mutate(type = "se")
celf1.mxe <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/CELF1/mxe_map.csv") %>% filter(gene_name == "CELF1") %>% mutate(type = "mxe")
celf1.a3ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/CELF1/a3ss_map.csv") %>% filter(gene_name == "CELF1") %>% mutate(type = "a3ss")
celf1.a5ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/CELF1/a5ss_map.csv") %>% filter(gene_name == "CELF1") %>% mutate(type = "a5ss")
celf1.all.wtc11 <- rbind(celf1.se, celf1.mxe, celf1.a3ss, celf1.a5ss)
rm(celf1.se, celf1.mxe, celf1.a3ss, celf1.a5ss)
```
```{r load mapping datasets foxp1}
foxp1.se <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/FOXP1/se_map.csv") %>% filter(gene_name == "FOXP1") %>% mutate(type = "se")
foxp1.mxe <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/FOXP1/mxe_map.csv") %>% filter(gene_name == "FOXP1") %>% mutate(type = "mxe")
foxp1.a3ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/FOXP1/a3ss_map.csv") %>% filter(gene_name == "FOXP1") %>% mutate(type = "a3ss")
foxp1.a5ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/FOXP1/a5ss_map.csv") %>% filter(gene_name == "FOXP1") %>% mutate(type = "a5ss")
foxp1.all.wtc11 <- rbind(foxp1.se, foxp1.mxe, foxp1.a3ss, foxp1.a5ss)
rm(foxp1.se, foxp1.mxe, foxp1.a3ss, foxp1.a5ss)
```
```{r load mapping datasets nrp1}
nrp1.se <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/NRP1/se_map.csv") %>% filter(gene_name == "NRP1") %>% mutate(type = "se")
nrp1.mxe <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/NRP1/mxe_map.csv") %>% filter(gene_name == "NRP1") %>% mutate(type = "mxe")
nrp1.a3ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/NRP1/a3ss_map.csv") %>% filter(gene_name == "NRP1") %>% mutate(type = "a3ss")
nrp1.a5ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/NRP1/a5ss_map.csv") %>% filter(gene_name == "NRP1") %>% mutate(type = "a5ss")
nrp1.all.wtc11 <- rbind(nrp1.se, nrp1.mxe, nrp1.a3ss, nrp1.a5ss)
rm(nrp1.se, nrp1.mxe, nrp1.a3ss, nrp1.a5ss)
```
```{r load mapping datasets nrp2}
nrp2.se <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/NRP2/se_map.csv") %>% filter(gene_name == "NRP2") %>% mutate(type = "se")
nrp2.mxe <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/NRP2/mxe_map.csv") %>% filter(gene_name == "NRP2") %>% mutate(type = "mxe")
nrp2.a3ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/NRP2/a3ss_map.csv") %>% filter(gene_name == "NRP2") %>% mutate(type = "a3ss")
nrp2.a5ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/NRP2/a5ss_map.csv") %>% filter(gene_name == "NRP2") %>% mutate(type = "a5ss")
nrp2.all.wtc11 <- rbind(nrp2.se, nrp2.mxe, nrp2.a3ss, nrp2.a5ss)
rm(nrp2.se, nrp2.mxe, nrp2.a3ss, nrp2.a5ss)
```
```{r load mapping datasets pecam1}
pecam1.se <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/PECAM1/se_map.csv") %>% filter(gene_name == "PECAM1") %>% mutate(type = "se")
pecam1.mxe <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/PECAM1/mxe_map.csv") %>% filter(gene_name == "PECAM1") %>% mutate(type = "mxe")
pecam1.a3ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/PECAM1/a3ss_map.csv") %>% filter(gene_name == "PECAM1") %>% mutate(type = "a3ss")
pecam1.a5ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/PECAM1/a5ss_map.csv") %>% filter(gene_name == "PECAM1") %>% mutate(type = "a5ss")
pecam1.all.wtc11 <- rbind(pecam1.se, pecam1.mxe, pecam1.a3ss, pecam1.a5ss)
rm(pecam1.se, pecam1.mxe, pecam1.a3ss, pecam1.a5ss)
```
```{r load mapping datasets vash1}
vash1.se <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/VASH1/se_map.csv") %>% filter(gene_name == "VASH1") %>% mutate(type = "se")
vash1.mxe <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/VASH1/mxe_map.csv") %>% filter(gene_name == "VASH1") %>% mutate(type = "mxe")
vash1.a3ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/VASH1/a3ss_map.csv") %>% filter(gene_name == "VASH1") %>% mutate(type = "a3ss")
vash1.a5ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/VASH1/a5ss_map.csv") %>% filter(gene_name == "VASH1") %>% mutate(type = "a5ss")
vash1.all.wtc11 <- rbind(vash1.se, vash1.mxe, vash1.a3ss, vash1.a5ss)
rm(vash1.se, vash1.mxe, vash1.a3ss, vash1.a5ss)
```
```{r load mapping datasets srsf1}
srsf1.se <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/SRSF1/se_map.csv") %>% filter(gene_name == "SRSF1") %>% mutate(type = "se")
srsf1.mxe <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/SRSF1/mxe_map.csv") %>% filter(gene_name == "SRSF1") %>% mutate(type = "mxe")
srsf1.a3ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/SRSF1/a3ss_map.csv") %>% filter(gene_name == "SRSF1") %>% mutate(type = "a3ss")
srsf1.a5ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/SRSF1/a5ss_map.csv") %>% filter(gene_name == "SRSF1") %>% mutate(type = "a5ss")
srsf1.all.wtc11 <- rbind(srsf1.se, srsf1.mxe, srsf1.a3ss, srsf1.a5ss)
rm(srsf1.se, srsf1.mxe, srsf1.a3ss, srsf1.a5ss)
```
```{r load mapping datasets yap1}
yap1.se <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/YAP1/se_map.csv") %>% filter(gene_name == "YAP1") %>% mutate(type = "se")
yap1.mxe <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/YAP1/mxe_map.csv") %>% filter(gene_name == "YAP1") %>% mutate(type = "mxe")
yap1.a3ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/YAP1/a3ss_map.csv") %>% filter(gene_name == "YAP1") %>% mutate(type = "a3ss")
yap1.a5ss <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/WTC11-1-annot/YAP1/a5ss_map.csv") %>% filter(gene_name == "YAP1") %>% mutate(type = "a5ss")
yap1.all.wtc11 <- rbind(yap1.se, yap1.mxe, yap1.a3ss, yap1.a5ss)
rm(yap1.se, yap1.mxe, yap1.a3ss, yap1.a5ss)
```
# ALL ELSE
```{r making allmaps: all maps for candidate genes}
# how many splicing events for the genes of interest?
allmaps <- rbind(baz2b.all.ec, cdh5.all.ec, celf1.all.ec, foxp1.all.ec, nrp1.all.ec, nrp2.all.ec, srsf1.all.ec, yap1.all.ec, cd44.all.ec, pecam1.all.ec, vash1.all.ec, baz2b.all.wtc11, cdh5.all.wtc11, celf1.all.wtc11, foxp1.all.wtc11, nrp1.all.wtc11, nrp2.all.wtc11, srsf1.all.wtc11, yap1.all.wtc11, cd44.all.wtc11, pecam1.all.wtc11, vash1.all.wtc11) %>% filter(gene_name %in% candidates)
rm(baz2b.all.ec, cdh5.all.ec, celf1.all.ec, foxp1.all.ec, nrp1.all.ec, nrp2.all.ec, srsf1.all.ec, yap1.all.ec, cd44.all.ec, pecam1.all.ec, vash1.all.ec, baz2b.all.wtc11, cdh5.all.wtc11, celf1.all.wtc11, foxp1.all.wtc11, nrp1.all.wtc11, nrp2.all.wtc11, srsf1.all.wtc11, yap1.all.wtc11, cd44.all.wtc11, pecam1.all.wtc11, vash1.all.wtc11)
allmaps <- allmaps %>% unique()
```
```{r run everthing above to load all map datasets}
print("helloworld")
```
# Aggregate data
```{r making allsplicing: all splice events for candidate genes}
SE <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/SE.csv") %>% filter(geneSymbol %in% candidates)
MXE <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/MXE.csv") %>% filter(geneSymbol %in% candidates)
A3SS <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/A3SS.csv") %>% filter(geneSymbol %in% candidates)
A5SS <- read.csv("/Volumes/sheynkman/projects/shay_thesis/output/candidate_mapping/A5SS.csv") %>% filter(geneSymbol %in% candidates)
SE <- SE %>% select(c(GeneID, geneSymbol, chr, strand, PValue, FDR, IncLevel1, IncLevel2, IncLevelDifference, incID, excID)) %>% mutate("type" = "se")
MXE <- MXE %>% select(c(GeneID, geneSymbol, chr, strand, PValue, FDR, IncLevel1, IncLevel2, IncLevelDifference, incID, excID)) %>% mutate("type" = "mxe")
A3SS <- A3SS %>% select(c(GeneID, geneSymbol, chr, strand, PValue, FDR, IncLevel1, IncLevel2, IncLevelDifference, incID, excID)) %>% mutate("type" = "a3ss")
A5SS <- A5SS %>% select(c(GeneID, geneSymbol, chr, strand, PValue, FDR, IncLevel1, IncLevel2, IncLevelDifference, incID, excID)) %>% mutate("type" = "a5ss")
allsplicing <- rbind(SE, MXE, A3SS, A5SS)
# allsplicing <- allsplicing %>%
# pivot_longer(
# cols = c(incID, excID),
# names_to = "incOrExc",
# values_to = "transcript_id"
# ) %>% select(-incOrExc)
rm(SE, MXE, A3SS, A5SS)
```
```{r loading annot.*: annotation files for candidates}
# nodelistcolumns <- c(GeneID, geneSymbol, chr, strand, PValue, FDR, IncLevel1, IncLevel2, IncLevelDifference, type, transcript_id)
ec.annot.baz2b <- rtracklayer::import("/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/01_annotation/EC-BAZ2B.gtf") %>% as.data.frame()
ec.annot.cd44 <- rtracklayer::import("/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/01_annotation/EC-CD44.gtf") %>% as.data.frame()
ec.annot.cdh5 <- rtracklayer::import("/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/01_annotation/EC-CDH5.gtf") %>% as.data.frame()
ec.annot.celf1 <- rtracklayer::import("/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/01_annotation/EC-CELF1.gtf") %>% as.data.frame()
ec.annot.foxp1 <- rtracklayer::import("/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/01_annotation/EC-FOXP1.gtf") %>% as.data.frame()
ec.annot.nrp1 <- rtracklayer::import("/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/01_annotation/EC-NRP1.gtf") %>% as.data.frame()
ec.annot.nrp2 <- rtracklayer::import("/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/01_annotation/EC-NRP2.gtf") %>% as.data.frame()
ec.annot.pecam1 <- rtracklayer::import("/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/01_annotation/EC-PECAM1.gtf") %>% as.data.frame()
ec.annot.srsf1 <- rtracklayer::import("/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/01_annotation/EC-SRSF1.gtf") %>% as.data.frame()
ec.annot.vash1 <- rtracklayer::import("/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/01_annotation/EC-VASH1.gtf") %>% as.data.frame()
ec.annot.yap1 <- rtracklayer::import("/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/01_annotation/EC-YAP1.gtf") %>% as.data.frame()
wtc11.annot.baz2b <- rtracklayer::import("/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/01_annotation/WTC11-1-BAZ2B.gtf") %>% as.data.frame()
wtc11.annot.cd44 <- rtracklayer::import("/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/01_annotation/WTC11-1-CD44.gtf") %>% as.data.frame()
wtc11.annot.cdh5 <- rtracklayer::import("/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/01_annotation/WTC11-1-CDH5.gtf") %>% as.data.frame()
wtc11.annot.celf1 <- rtracklayer::import("/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/01_annotation/WTC11-1-CELF1.gtf") %>% as.data.frame()
wtc11.annot.foxp1 <- rtracklayer::import("/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/01_annotation/WTC11-1-FOXP1.gtf") %>% as.data.frame()
wtc11.annot.nrp1 <- rtracklayer::import("/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/01_annotation/WTC11-1-NRP1.gtf") %>% as.data.frame()
wtc11.annot.nrp2 <- rtracklayer::import("/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/01_annotation/WTC11-1-NRP2.gtf") %>% as.data.frame()
wtc11.annot.pecam1 <- rtracklayer::import("/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/01_annotation/WTC11-1-PECAM1.gtf") %>% as.data.frame()
wtc11.annot.srsf1 <- rtracklayer::import("/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/01_annotation/WTC11-1-SRSF1.gtf") %>% as.data.frame()
wtc11.annot.vash1 <- rtracklayer::import("/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/01_annotation/WTC11-1-VASH1.gtf") %>% as.data.frame()
wtc11.annot.yap1 <- rtracklayer::import("/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/01_annotation/WTC11-1-YAP1.gtf") %>% as.data.frame()
```
```{r optional cleaning all ec.annot.* to resemble structure of allsplicing, no genID (see block below)}
ec.annot.baz2b <- ec.annot.baz2b %>% select(gene_id, gene_name, seqnames, strand, transcript_id) %>% rename( "GeneID" = gene_id, "geneSymbol" = gene_name, "chr" = seqnames, "transcript_id" = transcript_id
) %>% add_column( "PValue" = NA, "FDR" = NA, "IncLevel1" = NA, "IncLevel2" = NA, "IncLevelDifference" = NA, "type" = "isoform")
ec.annot.cd44 <- ec.annot.cd44 %>% select(gene_id, gene_name, seqnames, strand, transcript_id) %>% rename( "GeneID" = gene_id, "geneSymbol" = gene_name, "chr" = seqnames, "transcript_id" = transcript_id
) %>% add_column( "PValue" = NA, "FDR" = NA, "IncLevel1" = NA, "IncLevel2" = NA, "IncLevelDifference" = NA, "type" = "isoform")
ec.annot.cdh5 <- ec.annot.cdh5 %>% select(gene_id, gene_name, seqnames, strand, transcript_id) %>% rename( "GeneID" = gene_id, "geneSymbol" = gene_name, "chr" = seqnames, "transcript_id" = transcript_id
) %>% add_column( "PValue" = NA, "FDR" = NA, "IncLevel1" = NA, "IncLevel2" = NA, "IncLevelDifference" = NA, "type" = "isoform")
ec.annot.celf1 <- ec.annot.celf1 %>% select(gene_id, gene_name, seqnames, strand, transcript_id) %>% rename( "GeneID" = gene_id, "geneSymbol" = gene_name, "chr" = seqnames, "transcript_id" = transcript_id
) %>% add_column( "PValue" = NA, "FDR" = NA, "IncLevel1" = NA, "IncLevel2" = NA, "IncLevelDifference" = NA, "type" = "isoform")
ec.annot.foxp1 <- ec.annot.foxp1 %>% select(gene_id, gene_name, seqnames, strand, transcript_id) %>% rename( "GeneID" = gene_id, "geneSymbol" = gene_name, "chr" = seqnames, "transcript_id" = transcript_id
) %>% add_column( "PValue" = NA, "FDR" = NA, "IncLevel1" = NA, "IncLevel2" = NA, "IncLevelDifference" = NA, "type" = "isoform")
ec.annot.nrp1 <- ec.annot.nrp1 %>% select(gene_id, gene_name, seqnames, strand, transcript_id) %>% rename( "GeneID" = gene_id, "geneSymbol" = gene_name, "chr" = seqnames, "transcript_id" = transcript_id
) %>% add_column( "PValue" = NA, "FDR" = NA, "IncLevel1" = NA, "IncLevel2" = NA, "IncLevelDifference" = NA, "type" = "isoform")
ec.annot.nrp2 <- ec.annot.nrp2 %>% select(gene_id, gene_name, seqnames, strand, transcript_id) %>% rename( "GeneID" = gene_id, "geneSymbol" = gene_name, "chr" = seqnames, "transcript_id" = transcript_id
) %>% add_column( "PValue" = NA, "FDR" = NA, "IncLevel1" = NA, "IncLevel2" = NA, "IncLevelDifference" = NA, "type" = "isoform")
ec.annot.pecam1 <- ec.annot.pecam1 %>% select(gene_id, gene_name, seqnames, strand, transcript_id) %>% rename( "GeneID" = gene_id, "geneSymbol" = gene_name, "chr" = seqnames, "transcript_id" = transcript_id
) %>% add_column( "PValue" = NA, "FDR" = NA, "IncLevel1" = NA, "IncLevel2" = NA, "IncLevelDifference" = NA, "type" = "isoform")
ec.annot.srsf1 <- ec.annot.srsf1 %>% select(gene_id, gene_name, seqnames, strand, transcript_id) %>% rename( "GeneID" = gene_id, "geneSymbol" = gene_name, "chr" = seqnames, "transcript_id" = transcript_id
) %>% add_column( "PValue" = NA, "FDR" = NA, "IncLevel1" = NA, "IncLevel2" = NA, "IncLevelDifference" = NA, "type" = "isoform")
ec.annot.vash1 <- ec.annot.vash1 %>% select(gene_id, gene_name, seqnames, strand, transcript_id) %>% rename( "GeneID" = gene_id, "geneSymbol" = gene_name, "chr" = seqnames, "transcript_id" = transcript_id
) %>% add_column( "PValue" = NA, "FDR" = NA, "IncLevel1" = NA, "IncLevel2" = NA, "IncLevelDifference" = NA, "type" = "isoform")
ec.annot.yap1 <- ec.annot.yap1 %>% select(gene_id, gene_name, seqnames, strand, transcript_id) %>% rename( "GeneID" = gene_id, "geneSymbol" = gene_name, "chr" = seqnames, "transcript_id" = transcript_id
) %>% add_column( "PValue" = NA, "FDR" = NA, "IncLevel1" = NA, "IncLevel2" = NA, "IncLevelDifference" = NA, "type" = "isoform")
```
```{r optional cleaning all wtc11.annot.* to resemble structure of allsplicing, no genID (see block below)}
wtc11.annot.baz2b <- wtc11.annot.baz2b %>% select(gene_id, gene_name, seqnames, strand, transcript_id) %>% rename( "GeneID" = gene_id, "geneSymbol" = gene_name, "chr" = seqnames, "transcript_id" = transcript_id
) %>% add_column( "PValue" = NA, "FDR" = NA, "IncLevel1" = NA, "IncLevel2" = NA, "IncLevelDifference" = NA, "type" = "isoform")
wtc11.annot.cd44 <- wtc11.annot.cd44 %>% select(gene_id, gene_name, seqnames, strand, transcript_id) %>% rename( "GeneID" = gene_id, "geneSymbol" = gene_name, "chr" = seqnames, "transcript_id" = transcript_id
) %>% add_column( "PValue" = NA, "FDR" = NA, "IncLevel1" = NA, "IncLevel2" = NA, "IncLevelDifference" = NA, "type" = "isoform")
wtc11.annot.cdh5 <- wtc11.annot.cdh5 %>% select(gene_id, gene_name, seqnames, strand, transcript_id) %>% rename( "GeneID" = gene_id, "geneSymbol" = gene_name, "chr" = seqnames, "transcript_id" = transcript_id
) %>% add_column( "PValue" = NA, "FDR" = NA, "IncLevel1" = NA, "IncLevel2" = NA, "IncLevelDifference" = NA, "type" = "isoform")
wtc11.annot.celf1 <- wtc11.annot.celf1 %>% select(gene_id, gene_name, seqnames, strand, transcript_id) %>% rename( "GeneID" = gene_id, "geneSymbol" = gene_name, "chr" = seqnames, "transcript_id" = transcript_id
) %>% add_column( "PValue" = NA, "FDR" = NA, "IncLevel1" = NA, "IncLevel2" = NA, "IncLevelDifference" = NA, "type" = "isoform")
wtc11.annot.foxp1 <- wtc11.annot.foxp1 %>% select(gene_id, gene_name, seqnames, strand, transcript_id) %>% rename( "GeneID" = gene_id, "geneSymbol" = gene_name, "chr" = seqnames, "transcript_id" = transcript_id
) %>% add_column( "PValue" = NA, "FDR" = NA, "IncLevel1" = NA, "IncLevel2" = NA, "IncLevelDifference" = NA, "type" = "isoform")
wtc11.annot.nrp1 <- wtc11.annot.nrp1 %>% select(gene_id, gene_name, seqnames, strand, transcript_id) %>% rename( "GeneID" = gene_id, "geneSymbol" = gene_name, "chr" = seqnames, "transcript_id" = transcript_id
) %>% add_column( "PValue" = NA, "FDR" = NA, "IncLevel1" = NA, "IncLevel2" = NA, "IncLevelDifference" = NA, "type" = "isoform")
wtc11.annot.nrp2 <- wtc11.annot.nrp2 %>% select(gene_id, gene_name, seqnames, strand, transcript_id) %>% rename( "GeneID" = gene_id, "geneSymbol" = gene_name, "chr" = seqnames, "transcript_id" = transcript_id
) %>% add_column( "PValue" = NA, "FDR" = NA, "IncLevel1" = NA, "IncLevel2" = NA, "IncLevelDifference" = NA, "type" = "isoform")
wtc11.annot.pecam1 <- wtc11.annot.pecam1 %>% select(gene_id, gene_name, seqnames, strand, transcript_id) %>% rename( "GeneID" = gene_id, "geneSymbol" = gene_name, "chr" = seqnames, "transcript_id" = transcript_id
) %>% add_column( "PValue" = NA, "FDR" = NA, "IncLevel1" = NA, "IncLevel2" = NA, "IncLevelDifference" = NA, "type" = "isoform")
wtc11.annot.srsf1 <- wtc11.annot.srsf1 %>% select(gene_id, gene_name, seqnames, strand, transcript_id) %>% rename( "GeneID" = gene_id, "geneSymbol" = gene_name, "chr" = seqnames, "transcript_id" = transcript_id
) %>% add_column( "PValue" = NA, "FDR" = NA, "IncLevel1" = NA, "IncLevel2" = NA, "IncLevelDifference" = NA, "type" = "isoform")
wtc11.annot.vash1 <- wtc11.annot.vash1 %>% select(gene_id, gene_name, seqnames, strand, transcript_id) %>% rename( "GeneID" = gene_id, "geneSymbol" = gene_name, "chr" = seqnames, "transcript_id" = transcript_id
) %>% add_column( "PValue" = NA, "FDR" = NA, "IncLevel1" = NA, "IncLevel2" = NA, "IncLevelDifference" = NA, "type" = "isoform")
wtc11.annot.yap1 <- wtc11.annot.yap1 %>% select(gene_id, gene_name, seqnames, strand, transcript_id) %>% rename( "GeneID" = gene_id, "geneSymbol" = gene_name, "chr" = seqnames, "transcript_id" = transcript_id
) %>% add_column( "PValue" = NA, "FDR" = NA, "IncLevel1" = NA, "IncLevel2" = NA, "IncLevelDifference" = NA, "type" = "isoform")
```
```{r making ec.wtc11.annot}
ec.wtc11.annot <- rbind(ec.annot.cd44, ec.annot.pecam1, ec.annot.vash1, ec.annot.yap1, ec.annot.srsf1, ec.annot.nrp2, ec.annot.nrp1, ec.annot.foxp1, ec.annot.celf1, ec.annot.cdh5, ec.annot.baz2b, wtc11.annot.baz2b, wtc11.annot.cdh5, wtc11.annot.celf1, wtc11.annot.foxp1, wtc11.annot.nrp1, wtc11.annot.nrp2, wtc11.annot.srsf1, wtc11.annot.yap1, wtc11.annot.cd44, wtc11.annot.pecam1, wtc11.annot.vash1) %>% unique() %>% filter(geneSymbol %in% candidates) %>% drop_na(transcript_id)
rm(ec.annot.cd44, ec.annot.pecam1, ec.annot.vash1, ec.annot.yap1, ec.annot.srsf1, ec.annot.nrp2, ec.annot.nrp1, ec.annot.foxp1, ec.annot.celf1, ec.annot.cdh5, ec.annot.baz2b, wtc11.annot.baz2b, wtc11.annot.cdh5, wtc11.annot.celf1, wtc11.annot.foxp1, wtc11.annot.nrp1, wtc11.annot.nrp2, wtc11.annot.srsf1, wtc11.annot.yap1, wtc11.annot.cd44, wtc11.annot.pecam1, wtc11.annot.vash1)
```
```{r adding general ID to allmaps and allsplicing}
allmaps <- allmaps <- allmaps %>% mutate(
"genID" = str_sub(eventID, end=-5)
)
allsplicing <- allsplicing <- allsplicing %>% mutate(
"genID" = str_sub(incID, end=-5)
)
```
```{r loading full quant files}
ec.quant <- read.csv("/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/02_quantification/EC.tsv", sep = "\t")
wtc11.quant <- read.csv("/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/02_quantification/WTC11-1.tsv", sep = "\t")
ec.quant.total <- sum(ec.quant$rep1ENCSR148IIG)
wtc11.quant.total <- sum(wtc11.quant$rep1ENCSR507JOF)
ec.quant <- ec.quant %>% filter(annot_gene_name %in% candidates) %>% select(-transcript_ID) %>% rename("count_EC" = rep1ENCSR148IIG, "transcript_id" = annot_transcript_id) %>% select(transcript_id, count_EC)
wtc11.quant <- wtc11.quant %>% filter(annot_gene_name %in% candidates) %>% select(-transcript_ID) %>% rename("count_WTC11" = rep1ENCSR507JOF, "transcript_id" = annot_transcript_id) %>% select(transcript_id, count_WTC11)
maq <- left_join(ec.wtc11.annot, ec.quant, by = "transcript_id")
maq <- left_join(maq, wtc11.quant, by = "transcript_id")
maq <- maq %>%
select(-c(PValue, FDR, IncLevel1, IncLevel2, IncLevelDifference)) %>%
replace(is.na(.), 0) %>%
mutate(
TPM_EC = (count_EC/ec.quant.total)*1000000,
TPM_WTC11 = (count_WTC11/wtc11.quant.total)*1000000,
dTPM = TPM_WTC11 - TPM_EC
)
```
# exploratory
```{r writing GTFs as CSV}
ec.path <- "/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/01_annotation/EC-candidates.gtf"
wtc.path <- "/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/01_annotation/WTC11-1-candidates.gtf"
ec.gtf <- rtracklayer::import(ec.path) %>% as.data.frame()
wtc.gtf <- rtracklayer::import(wtc.path) %>% as.data.frame()
write.csv(x = ec.gtf, file = "/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/01_annotation/EC-candidates.csv")
write.csv(x = wtc.gtf, file = wtc.path <- "/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/01_annotation/WTC11-1-candidates.csv")
# test.wtc.csv <- read.csv("/Volumes/sheynkman/projects/shay_thesis/input-data/02_long-read-EC-WTC11-1_input/01_annotation/WTC11-1-candidates.csv") %>% select(-X)
```
```{r merged annots making key}
ec.nov.squish.path <- "/Volumes/sheynkman/projects/shay_thesis/ec-annot-squished.csv"
wtc11.nov.squish.path <- "/Volumes/sheynkman/projects/shay_thesis/wtc11-annot-squished.csv"
ec.nov.squish <- read.csv(ec.nov.squish.path)
wtc11.nov.squish <- read.csv(wtc11.nov.squish.path)
wtc11.annot <- left_join(wtc11.annot, wtc11.nov.squish, by = "transcript_id")
ec.annot.nrp2 <- ec.annot %>% filter(gene_name == "NRP2")
```
```{r checking if ENCLBs match in width etc}
novel.ec.annot <- ec.annot %>% filter(grepl("ENCLB", transcript_id)) %>% filter(gene_name %in% candidates) %>% filter(type == "transcript")
novel.wtc.annot <- wtc11.annot %>% filter(grepl("ENCLB", transcript_id)) %>% filter(gene_name %in% candidates) %>% filter(type == "transcript")
width.list.ec <- novel.ec.annot %>% dplyr::select(gene_name, width, transcript_id) %>% unique()
nwtca.matchwidth <- novel.wtc.annot %>% filter(width %in% width.list.ec$width)
celf1.width.ec <- width.list.ec %>% filter(gene_name == "CELF1")
celf1.width.nwtca <- nwtca.matchwidth %>% filter(gene_name == "CELF1") %>% dplyr::select(gene_name, width, transcript_id)
```
Observation: none of the exon ranges match for the novel transcripts