-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy path.Rhistory
512 lines (512 loc) · 25.8 KB
/
.Rhistory
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
size=3,
colour='gray40')
ggplot(mdat, aes(x=age, y=index_epi)) +
geom_point(size=1,
aes(shape = menopause)) +
geom_smooth(method=lm, size=0.50, colour = "gray40") +
geom_abline(slope=1, linetype="dashed", colour = "gray40") +
xlab("Chronological age (years)") + ylab("WID epithelial clock") +
xlim(c(30,80)) + ylim(c(30,80)) +
annotate(geom='text',
x=70, y=34,
label=paste('correlation: ',cor,'\n (p=',pval,')','\n', 'error: ', err, sep=''),
size=3,
colour='gray40')
ggplot(mdat, aes(x=age, y=index_epi)) +
geom_point(size=1,
aes(shape = menopause)) +
geom_smooth(method=lm, size=0.50, colour = "gray40") +
geom_abline(slope=1, linetype="dashed", colour = "gray40") +
xlab("Chronological age (years)") + ylab("WID epithelial clock") +
xlim(c(30,80)) + ylim(c(30,80)) +
annotate(geom='text',
x=70, y=34,
label=paste('correlation: ',cor,'\n (p=',pval,')','\n', 'error: ', err, sep=''),
size=3,
colour='gray40')
load("~/Dropbox/index-dev/master-dataset/1-output/mdat.Rdata")
ind <- mdat$experiment_name=='3C_VALIDATION_DATA' & mdat$type=='Control'
mdat <- mdat[na.omit(ind),]
fit <- lm(index_general_age ~ age + ic, mdat[mdat$menopause=='Pre',])
mdat$index_general_age_adj <- mdat$index_general_age - predict(fit, mdat)
fit <- lm(index_epithelial_age ~ age + ic, mdat[mdat$menopause=='Pre',])
mdat$index_epithelial_age_adj <- mdat$index_epithelial_age - predict(fit, mdat)
fit <- lm(index_immune_age ~ age +ic , mdat[mdat$menopause=='Pre',])
mdat$index_immune_age_adj <- mdat$index_immune_age - predict(fit, mdat)
pdat <- data.frame(time = c(mdat$index_general_age_adj,
mdat$index_epithelial_age_adj,
mdat$index_immune_age_adj),
clock = c(rep('General\nclock',nrow(mdat)),
rep('Epithelial\nclock',nrow(mdat)),
rep('Immune\nclock',nrow(mdat))),
menopause = rep(mdat$menopause,3))
pdat$clock <- factor(pdat$clock, levels=c('General\nclock',
'Epithelial\nclock',
'Immune\nclock'))
pdat$menopause <- factor(pdat$menopause, levels=c('Pre','Post'))
ggplot(pdat) +
geom_boxplot(aes(x=clock,y=time,fill=menopause)) +
theme_minimal() +
scale_fill_manual(name = "Menopausal status",
labels = c("Pre", "Post"),
values=c("tomato", "deepskyblue3")) +
ylab("Residuals (after\nadjustment for age and ic in\npre-menopausal controls)") +
xlab("") +
theme(legend.position = 'top') +
annotate("text", y=-22, x=1, label = paste("(",as.numeric(table(pdat$menopause[pdat$clock == "General\nclock"]))[1],",",as.numeric(table(pdat$menopause[pdat$clock == "General\nclock"]))[2],")",sep=""), size=3, color="gray40") +
annotate("text", y=-22, x=2, label = paste("(",as.numeric(table(pdat$menopause[pdat$clock == "Epithelial\nclock"]))[1],",",as.numeric(table(pdat$menopause[pdat$clock == "Epithelial\nclock"]))[2],")",sep=""), size=3, color="gray40") +
annotate("text", y=-22, x=3, label = paste("(",as.numeric(table(pdat$menopause[pdat$clock == "Immune\nclock"]))[1],",",as.numeric(table(pdat$menopause[pdat$clock == "Immune\nclock"]))[2],")",sep=""), size=3, color="gray40")
pdat
wilcox.test(pdat[pdat$clock=="Epithelial\nclock" & pdat$menopause=="Pre",]$time,
pdat[pdat$clock=="Epithelial\nclock" & pdat$menopause=="Post",]$time)
epi <- wilcox.test(pdat[pdat$clock=="Epithelial\nclock" & pdat$menopause=="Pre",]$time,
pdat[pdat$clock=="Epithelial\nclock" & pdat$menopause=="Post",]$time)
epi$p.value
epi <- wilcox.test(pdat[pdat$clock=="General\nclock" & pdat$menopause=="Pre",]$time,
pdat[pdat$clock=="General\nclock" & pdat$menopause=="Post",]$time)
epi
general <- wilcox.test(pdat[pdat$clock=="General\nclock" & pdat$menopause=="Pre",]$time,
pdat[pdat$clock=="General\nclock" & pdat$menopause=="Post",]$time)
general
immune <- wilcox.test(pdat[pdat$clock=="Immune\nclock" & pdat$menopause=="Pre",]$time,
pdat[pdat$clock=="Immune\nclock" & pdat$menopause=="Post",]$time)
immune
ggplot(pdat) +
geom_boxplot(aes(x=clock,y=time,fill=menopause)) +
theme_minimal() +
scale_fill_manual(name = "Menopausal status",
labels = c("Pre", "Post"),
values=c("tomato", "deepskyblue3")) +
ylab("Residuals (after\nadjustment for age and ic in\npre-menopausal controls)") +
xlab("") +
theme(legend.position = 'top') +
annotate("text", y=-22, x=1, label = paste("(",as.numeric(table(pdat$menopause[pdat$clock == "General\nclock"]))[1],",",as.numeric(table(pdat$menopause[pdat$clock == "General\nclock"]))[2],")",sep=""), size=3, color="gray40") +
annotate("text", y=-22, x=2, label = paste("(",as.numeric(table(pdat$menopause[pdat$clock == "Epithelial\nclock"]))[1],",",as.numeric(table(pdat$menopause[pdat$clock == "Epithelial\nclock"]))[2],")",sep=""), size=3, color="gray40") +
annotate("text", y=-22, x=3, label = paste("(",as.numeric(table(pdat$menopause[pdat$clock == "Immune\nclock"]))[1],",",as.numeric(table(pdat$menopause[pdat$clock == "Immune\nclock"]))[2],")",sep=""), size=3, color="gray40") +
annotate("text", label = c("**", "*"),
x = c(1, 2), y = 22, size = 3, colour = "gray40") +
annotate("segment",
x = c(0.8, 1.8), xend = c(1.2, 2.2),
y = 21, yend = 21, size= 0.5, colour = "gray40")
ggplot(pdat) +
geom_boxplot(aes(x=clock,y=time,fill=menopause)) +
theme_minimal() +
scale_fill_manual(name = "Menopausal status",
labels = c("Pre", "Post"),
values=c("tomato", "deepskyblue3")) +
ylab("Residuals (after\nadjustment for age and ic in\npre-menopausal controls)") +
xlab("") +
theme(legend.position = 'top') +
annotate("text", y=-22, x=1, label = paste("(",as.numeric(table(pdat$menopause[pdat$clock == "General\nclock"]))[1],",",as.numeric(table(pdat$menopause[pdat$clock == "General\nclock"]))[2],")",sep=""), size=3, color="gray40") +
annotate("text", y=-22, x=2, label = paste("(",as.numeric(table(pdat$menopause[pdat$clock == "Epithelial\nclock"]))[1],",",as.numeric(table(pdat$menopause[pdat$clock == "Epithelial\nclock"]))[2],")",sep=""), size=3, color="gray40") +
annotate("text", y=-22, x=3, label = paste("(",as.numeric(table(pdat$menopause[pdat$clock == "Immune\nclock"]))[1],",",as.numeric(table(pdat$menopause[pdat$clock == "Immune\nclock"]))[2],")",sep=""), size=3, color="gray40") +
annotate("text", label = c("*", "**"),
x = c(1, 2), y = 22, size = 3, colour = "gray40") +
annotate("segment",
x = c(0.8, 1.8), xend = c(1.2, 2.2),
y = 21, yend = 21, size= 0.5, colour = "gray40")
ggplot(pdat) +
geom_boxplot(aes(x=clock,y=time,fill=menopause)) +
theme_minimal() +
scale_fill_manual(name = "Menopausal status",
labels = c("Pre", "Post"),
values=c("tomato", "deepskyblue3")) +
ylab("Residuals (after\nadjustment for age and ic in\npre-menopausal controls)") +
xlab("") +
theme(legend.position = 'top') +
annotate("text", y=-22, x=1, label = paste("(",as.numeric(table(pdat$menopause[pdat$clock == "General\nclock"]))[1],",",as.numeric(table(pdat$menopause[pdat$clock == "General\nclock"]))[2],")",sep=""), size=3, color="gray40") +
annotate("text", y=-22, x=2, label = paste("(",as.numeric(table(pdat$menopause[pdat$clock == "Epithelial\nclock"]))[1],",",as.numeric(table(pdat$menopause[pdat$clock == "Epithelial\nclock"]))[2],")",sep=""), size=3, color="gray40") +
annotate("text", y=-22, x=3, label = paste("(",as.numeric(table(pdat$menopause[pdat$clock == "Immune\nclock"]))[1],",",as.numeric(table(pdat$menopause[pdat$clock == "Immune\nclock"]))[2],")",sep=""), size=3, color="gray40") +
annotate("text", label = c("*", "**"),
x = c(1, 2), y = 22, size = 3, colour = "gray40") +
annotate("segment",
x = c(0.8, 1.8), xend = c(1.2, 2.2),
y = 21, yend = 21, size= 0.5, colour = "gray40") +
annotate("segment",
x = c(0.8, 1.2, 1.8, 2.2), xend = c(0.8, 1.2, 1.8, 2.2),
y = 20, yend = 21, size= 0.5, colour = "gray40")
pdat$clock <- factor(pdat$clock, levels=c('General\nclock',
'Epithelial\nclock',
'Immune\nclock'))
pdat$menopause <- factor(pdat$menopause, levels=c('Pre','Post'))
t1 <- wilcox.test(pdat[pdat$clock=="Epithelial\nclock" & pdat$menopause=="Pre",]$time,
pdat[pdat$clock=="Epithelial\nclock" & pdat$menopause=="Post",]$time)
t1 <- wilcox.test(pdat[pdat$clock=="General\nclock" & pdat$menopause=="Pre",]$time,
pdat[pdat$clock=="General\nclock" & pdat$menopause=="Post",]$time)
t3 <- wilcox.test(pdat[pdat$clock=="Immune\nclock" & pdat$menopause=="Pre",]$time,
pdat[pdat$clock=="Immune\nclock" & pdat$menopause=="Post",]$time)
ggplot(pdat) +
geom_boxplot(aes(x=clock,y=time,fill=menopause)) +
theme_minimal() +
scale_fill_manual(name = "Menopausal status",
labels = c("Pre", "Post"),
values=c("tomato", "deepskyblue3")) +
ylab("Residuals (after\nadjustment for age and ic in\npre-menopausal controls)") +
xlab("") +
theme(legend.position = 'top') +
annotate("text", y=-22, x=1, label = paste("(",as.numeric(table(pdat$menopause[pdat$clock == "General\nclock"]))[1],",",as.numeric(table(pdat$menopause[pdat$clock == "General\nclock"]))[2],")",sep=""), size=3, color="gray40") +
annotate("text", y=-22, x=2, label = paste("(",as.numeric(table(pdat$menopause[pdat$clock == "Epithelial\nclock"]))[1],",",as.numeric(table(pdat$menopause[pdat$clock == "Epithelial\nclock"]))[2],")",sep=""), size=3, color="gray40") +
annotate("text", y=-22, x=3, label = paste("(",as.numeric(table(pdat$menopause[pdat$clock == "Immune\nclock"]))[1],",",as.numeric(table(pdat$menopause[pdat$clock == "Immune\nclock"]))[2],")",sep=""), size=3, color="gray40") +
annotate("text", label = c("*", "**"),
x = c(1, 2), y = 22, size = 3, colour = "gray40") +
annotate("segment",
x = c(0.8, 1.8), xend = c(1.2, 2.2),
y = 21, yend = 21, size= 0.5, colour = "gray40") +
annotate("segment",
x = c(0.8, 1.2, 1.8, 2.2), xend = c(0.8, 1.2, 1.8, 2.2),
y = 20, yend = 21, size= 0.5, colour = "gray40")
load("~/Dropbox/index-dev/master-dataset/1-output/mdat.Rdata")
# create mdat for validation set 1
ind <- (mdat$dataset_name == "3C_external_validation") |
(mdat$dataset_name == "3C_training" & (mdat$type == "Breast" | mdat$type == "Endometrial" | mdat$type == "Ovarian")) |
(mdat$dataset_name == "3C_internal_validation" & (mdat$type == "Breast" | mdat$type == "Endometrial" | mdat$type == "Ovarian"))
mdat <- mdat[ind,]
mdat <- mdat[!is.na(mdat$type),]
mdat <- droplevels(mdat)
cont <- mdat %>% filter(type == "Control")
pval <- signif(cor.test(cont$index_general_age, cont$pgct_age)$p.value,digits=2)
cor <- signif(cor(cont$index_general_age, cont$pgct_age, use = 'complete.obs'),digits=2)
cont <- mdat %>% filter(type == "Control")
cont$index_general_age
cont$pgct_age
load("~/Dropbox/index-dev/master-dataset/1-output/mdat.Rdata")
mdat$pcg
# create mdat for validation set 1
ind <- (mdat$dataset_name == "3C_external_validation") |
(mdat$dataset_name == "3C_training" & (mdat$type == "Breast" | mdat$type == "Endometrial" | mdat$type == "Ovarian")) |
(mdat$dataset_name == "3C_internal_validation" & (mdat$type == "Breast" | mdat$type == "Endometrial" | mdat$type == "Ovarian"))
mdat <- mdat[ind,]
mdat <- mdat[!is.na(mdat$type),]
mdat <- droplevels(mdat)
cont <- mdat %>% filter(type == "Control")
pval <- signif(cor.test(cont$index_general_age, cont$pgctage)$p.value,digits=2)
cont$index_general_age
cont$pgctage
cont$pcgtage
load("~/Dropbox/index-dev/master-dataset/1-output/mdat.Rdata")
# create mdat for validation set 1
ind <- (mdat$dataset_name == "3C_external_validation") |
(mdat$dataset_name == "3C_training" & (mdat$type == "Breast" | mdat$type == "Endometrial" | mdat$type == "Ovarian")) |
(mdat$dataset_name == "3C_internal_validation" & (mdat$type == "Breast" | mdat$type == "Endometrial" | mdat$type == "Ovarian"))
mdat <- mdat[ind,]
mdat <- mdat[!is.na(mdat$type),]
mdat <- droplevels(mdat)
cont <- mdat %>% filter(type == "Control")
pval <- signif(cor.test(cont$index_general_age, cont$pgctage)$p.value,digits=2)
pval <- signif(cor.test(cont$index_general_age, cont$pcgtage)$p.value,digits=2)
cor <- signif(cor(cont$index_general_age, cont$pcgtage, use = 'complete.obs'),digits=2)
ggplot(cont, aes(x=index_general_age, y=pgctage)) + geom_point(size=0.75) +
geom_smooth(method=lm, size=0.5, col="gray40") + xlab("WID general clock") + ylab('pcgtAge') +
annotate(geom='text',
x=70, y=0.026,
label=paste('correlation: ',cor,'\n(p=',pval,')',sep=''),
size=3,
colour='gray40') + ylim(c(0.02,0.138))
library(ggplot2)
library(dplyr)
library(viridis)
library(tidyverse)
library(patchwork)
knitr::opts_chunk$set(cache = FALSE)
knitr::opts_chunk$set(echo=FALSE)
theme_set(
theme_minimal() +
theme(legend.position = "top")
)
dir_list <- dir('~/Dropbox/index-dev/age-index/1-doc/3-plots')
for(d in dir_list){
source(paste('~/Dropbox/index-dev/age-index/1-doc/3-plots/',d,sep=""))
}
load("~/Dropbox/index-dev/master-dataset/1-output/mdat.Rdata")
ind <- mdat$experiment_name=='3C_VALIDATION_DATA' & mdat$type=='Control'
mdat <- mdat[na.omit(ind),]
fit <- lm(index_general_age ~ age + ic, mdat[mdat$menopause=='Pre',])
mdat$index_general_age_adj <- mdat$index_general_age - predict(fit, mdat)
fit <- lm(index_epithelial_age ~ age + ic, mdat[mdat$menopause=='Pre',])
mdat$index_epithelial_age_adj <- mdat$index_epithelial_age - predict(fit, mdat)
fit <- lm(index_immune_age ~ age +ic , mdat[mdat$menopause=='Pre',])
mdat$index_immune_age_adj <- mdat$index_immune_age - predict(fit, mdat)
pdat <- data.frame(time = c(mdat$index_general_age_adj,
mdat$index_epithelial_age_adj,
mdat$index_immune_age_adj),
clock = c(rep('General\nclock',nrow(mdat)),
rep('Epithelial\nclock',nrow(mdat)),
rep('Immune\nclock',nrow(mdat))),
menopause = rep(mdat$menopause,3))
pdat$clock <- factor(pdat$clock, levels=c('General\nclock',
'Epithelial\nclock',
'Immune\nclock'))
pdat$menopause <- factor(pdat$menopause, levels=c('Pre','Post'))
t1 <- wilcox.test(pdat[pdat$clock=="Epithelial\nclock" & pdat$menopause=="Pre",]$time,
pdat[pdat$clock=="Epithelial\nclock" & pdat$menopause=="Post",]$time)
t1 <- wilcox.test(pdat[pdat$clock=="General\nclock" & pdat$menopause=="Pre",]$time,
pdat[pdat$clock=="General\nclock" & pdat$menopause=="Post",]$time)
t3 <- wilcox.test(pdat[pdat$clock=="Immune\nclock" & pdat$menopause=="Pre",]$time,
pdat[pdat$clock=="Immune\nclock" & pdat$menopause=="Post",]$time)
ggplot(pdat) +
geom_boxplot(aes(x=clock,y=time,fill=menopause)) +
theme_minimal() +
scale_fill_manual(name = "Menopausal status",
labels = c("Pre", "Post"),
values=c("tomato", "deepskyblue3")) +
ylab("Residuals (after\nadjustment for age and ic in\npre-menopausal controls)") +
xlab("") +
theme(legend.position = 'top') +
annotate("text", y=-22, x=1, label = paste("(",as.numeric(table(pdat$menopause[pdat$clock == "General\nclock"]))[1],",",as.numeric(table(pdat$menopause[pdat$clock == "General\nclock"]))[2],")",sep=""), size=3, color="gray40") +
annotate("text", y=-22, x=2, label = paste("(",as.numeric(table(pdat$menopause[pdat$clock == "Epithelial\nclock"]))[1],",",as.numeric(table(pdat$menopause[pdat$clock == "Epithelial\nclock"]))[2],")",sep=""), size=3, color="gray40") +
annotate("text", y=-22, x=3, label = paste("(",as.numeric(table(pdat$menopause[pdat$clock == "Immune\nclock"]))[1],",",as.numeric(table(pdat$menopause[pdat$clock == "Immune\nclock"]))[2],")",sep=""), size=3, color="gray40") +
annotate("text", label = c("*", "**"),
x = c(1, 2), y = 22, size = 3, colour = "gray40") +
annotate("segment",
x = c(0.8, 1.8), xend = c(1.2, 2.2),
y = 21, yend = 21, size= 0.5, colour = "gray40") +
annotate("segment",
x = c(0.8, 1.2, 1.8, 2.2), xend = c(0.8, 1.2, 1.8, 2.2),
y = 20, yend = 21, size= 0.5, colour = "gray40")
t1
t2
t3
ggplot(pdat) +
geom_boxplot(aes(x=clock,y=time,fill=menopause)) +
theme_minimal() +
scale_fill_manual(name = "Menopausal status",
labels = c("Pre", "Post"),
values=c("tomato", "deepskyblue3")) +
ylab("Residuals (after\nadjustment for age and ic in\npre-menopausal controls)") +
xlab("") +
theme(legend.position = 'top') +
annotate("text", y=-22, x=1, label = paste("(",as.numeric(table(pdat$menopause[pdat$clock == "General\nclock"]))[1],",",as.numeric(table(pdat$menopause[pdat$clock == "General\nclock"]))[2],")",sep=""), size=3, color="gray40") +
annotate("text", y=-22, x=2, label = paste("(",as.numeric(table(pdat$menopause[pdat$clock == "Epithelial\nclock"]))[1],",",as.numeric(table(pdat$menopause[pdat$clock == "Epithelial\nclock"]))[2],")",sep=""), size=3, color="gray40") +
annotate("text", y=-22, x=3, label = paste("(",as.numeric(table(pdat$menopause[pdat$clock == "Immune\nclock"]))[1],",",as.numeric(table(pdat$menopause[pdat$clock == "Immune\nclock"]))[2],")",sep=""), size=3, color="gray40") +
annotate("text", label = c("*", "**"),
x = c(1, 2), y = 22, size = 3, colour = "gray40") +
annotate("segment",
x = c(0.8, 1.8), xend = c(1.2, 2.2),
y = 21, yend = 21, size= 0.5, colour = "gray40") +
annotate("segment",
x = c(0.8, 1.2, 1.8, 2.2), xend = c(0.8, 1.2, 1.8, 2.2),
y = 20, yend = 21, size= 0.5, colour = "gray40")
table(mdat$HRT_current)
table(mdat$HRT_ever)
mdat$type
mdat <- droplevels(mdat)
table(mdat$type, mdat$HRT_ever)
table(mdat$menopause, mdat$HRT_ever)
load("~/Dropbox/index-dev/master-dataset/1-output/mdat.Rdata")
ind <- mdat$experiment_name=='3C_VALIDATION_DATA' & mdat$type=='Control' & mdat$HRT_ever=="No"
mdat <- mdat[na.omit(ind),]
fit <- lm(index_general_age ~ age + ic, mdat[mdat$menopause=='Pre',])
mdat$index_general_age_adj <- mdat$index_general_age - predict(fit, mdat)
fit <- lm(index_epithelial_age ~ age + ic, mdat[mdat$menopause=='Pre',])
mdat$index_epithelial_age_adj <- mdat$index_epithelial_age - predict(fit, mdat)
fit <- lm(index_immune_age ~ age +ic , mdat[mdat$menopause=='Pre',])
mdat$index_immune_age_adj <- mdat$index_immune_age - predict(fit, mdat)
pdat <- data.frame(time = c(mdat$index_general_age_adj,
mdat$index_epithelial_age_adj,
mdat$index_immune_age_adj),
clock = c(rep('General\nclock',nrow(mdat)),
rep('Epithelial\nclock',nrow(mdat)),
rep('Immune\nclock',nrow(mdat))),
menopause = rep(mdat$menopause,3))
pdat$clock <- factor(pdat$clock, levels=c('General\nclock',
'Epithelial\nclock',
'Immune\nclock'))
pdat$menopause <- factor(pdat$menopause, levels=c('Pre','Post'))
t1 <- wilcox.test(pdat[pdat$clock=="Epithelial\nclock" & pdat$menopause=="Pre",]$time,
pdat[pdat$clock=="Epithelial\nclock" & pdat$menopause=="Post",]$time)
t2 <- wilcox.test(pdat[pdat$clock=="General\nclock" & pdat$menopause=="Pre",]$time,
pdat[pdat$clock=="General\nclock" & pdat$menopause=="Post",]$time)
t3 <- wilcox.test(pdat[pdat$clock=="Immune\nclock" & pdat$menopause=="Pre",]$time,
pdat[pdat$clock=="Immune\nclock" & pdat$menopause=="Post",]$time)
t1
t2
t3
ggplot(pdat) +
geom_boxplot(aes(x=clock,y=time,fill=menopause)) +
theme_minimal() +
scale_fill_manual(name = "Menopausal status",
labels = c("Pre", "Post"),
values=c("tomato", "deepskyblue3")) +
ylab("Residuals (after\nadjustment for age and ic in\npre-menopausal controls)") +
xlab("") +
theme(legend.position = 'top') +
annotate("text", y=-22, x=1, label = paste("(",as.numeric(table(pdat$menopause[pdat$clock == "General\nclock"]))[1],",",as.numeric(table(pdat$menopause[pdat$clock == "General\nclock"]))[2],")",sep=""), size=3, color="gray40") +
annotate("text", y=-22, x=2, label = paste("(",as.numeric(table(pdat$menopause[pdat$clock == "Epithelial\nclock"]))[1],",",as.numeric(table(pdat$menopause[pdat$clock == "Epithelial\nclock"]))[2],")",sep=""), size=3, color="gray40") +
annotate("text", y=-22, x=3, label = paste("(",as.numeric(table(pdat$menopause[pdat$clock == "Immune\nclock"]))[1],",",as.numeric(table(pdat$menopause[pdat$clock == "Immune\nclock"]))[2],")",sep=""), size=3, color="gray40") +
annotate("text", label = c("*", "**"),
x = c(1, 2), y = 22, size = 3, colour = "gray40") +
annotate("segment",
x = c(0.8, 1.8), xend = c(1.2, 2.2),
y = 21, yend = 21, size= 0.5, colour = "gray40") +
annotate("segment",
x = c(0.8, 1.2, 1.8, 2.2), xend = c(0.8, 1.2, 1.8, 2.2),
y = 20, yend = 21, size= 0.5, colour = "gray40")
ggplot(pdat) +
geom_boxplot(aes(x=clock,y=time,fill=menopause)) +
theme_minimal() +
scale_fill_manual(name = "Menopausal status",
labels = c("Pre", "Post"),
values=c("tomato", "deepskyblue3")) +
ylab("Residuals (after\nadjustment for age and ic in\npre-menopausal controls)") +
xlab("") +
theme(legend.position = 'top') +
annotate("text", y=-22, x=1, label = paste("(",as.numeric(table(pdat$menopause[pdat$clock == "General\nclock"]))[1],",",as.numeric(table(pdat$menopause[pdat$clock == "General\nclock"]))[2],")",sep=""), size=3, color="gray40") +
annotate("text", y=-22, x=2, label = paste("(",as.numeric(table(pdat$menopause[pdat$clock == "Epithelial\nclock"]))[1],",",as.numeric(table(pdat$menopause[pdat$clock == "Epithelial\nclock"]))[2],")",sep=""), size=3, color="gray40") +
annotate("text", y=-22, x=3, label = paste("(",as.numeric(table(pdat$menopause[pdat$clock == "Immune\nclock"]))[1],",",as.numeric(table(pdat$menopause[pdat$clock == "Immune\nclock"]))[2],")",sep=""), size=3, color="gray40") +
annotate("text", label = c("", "***"),
x = c(1, 2), y = 25, size = 3, colour = "gray40") +
annotate("segment",
x = c(1.8), xend = c(2.2),
y = 24, yend = 24, size= 0.5, colour = "gray40") +
annotate("segment",
x = c(1.8, 2.2), xend = c(1.8, 2.2),
y = 23, yend = 24, size= 0.5, colour = "gray40")
load("~/Dropbox/index-dev/master-dataset/1-output/mdat.Rdata")
ind <- mdat$experiment_name=='3C_VALIDATION_DATA' & mdat$type=='Control'
mdat <- mdat[na.omit(ind),]
fit <- lm(index_general_age ~ age + ic, mdat[mdat$menopause=='Pre',])
mdat$index_general_age_adj <- mdat$index_general_age - predict(fit, mdat)
fit <- lm(index_epithelial_age ~ age + ic, mdat[mdat$menopause=='Pre',])
mdat$index_epithelial_age_adj <- mdat$index_epithelial_age - predict(fit, mdat)
fit <- lm(index_immune_age ~ age +ic , mdat[mdat$menopause=='Pre',])
mdat$index_immune_age_adj <- mdat$index_immune_age - predict(fit, mdat)
pdat <- data.frame(time = c(mdat$index_general_age_adj,
mdat$index_epithelial_age_adj,
mdat$index_immune_age_adj),
clock = c(rep('General\nclock',nrow(mdat)),
rep('Epithelial\nclock',nrow(mdat)),
rep('Immune\nclock',nrow(mdat))),
menopause = rep(mdat$menopause,3))
pdat$clock <- factor(pdat$clock, levels=c('General\nclock',
'Epithelial\nclock',
'Immune\nclock'))
pdat$menopause <- factor(pdat$menopause, levels=c('Pre','Post'))
t1 <- wilcox.test(pdat[pdat$clock=="Epithelial\nclock" & pdat$menopause=="Pre",]$time,
pdat[pdat$clock=="Epithelial\nclock" & pdat$menopause=="Post",]$time)
t2 <- wilcox.test(pdat[pdat$clock=="General\nclock" & pdat$menopause=="Pre",]$time,
pdat[pdat$clock=="General\nclock" & pdat$menopause=="Post",]$time)
t3 <- wilcox.test(pdat[pdat$clock=="Immune\nclock" & pdat$menopause=="Pre",]$time,
pdat[pdat$clock=="Immune\nclock" & pdat$menopause=="Post",]$time)
t1
pdat
t1 <- t.test(pdat[pdat$clock=="Epithelial\nclock" & pdat$menopause=="Pre",]$time,
pdat[pdat$clock=="Epithelial\nclock" & pdat$menopause=="Post",]$time)
t1
setwd("~/Documents/Work/")
dir.create("WID-BC-index")
setwd("WID-BC-index/")
devtools::create("WID-BC-index")
setwd("~/Documents/Work/")
dir.create("WID.BC")
devtools::create("WID.BC")
here::dr_here()
setwd("/Users/chiara")
dir.create("WID.BC")
devtools::create("WID.BC")
devtools::create("WID.BC")
setwd("/Users/chiara/WID.BC/")
load("~/Dropbox/index-dev/master-dataset/1-output/mdat.Rdata")
library(dplyr)
mdat <- mdat %>%
filter(experiment_name == "3C_DISCOVERY" & dataset_name == "3C_internal_validation" & type %in% c("Control", "Breast")) %>%
droplevels()
mdat <- mdat %>%
filter(experiment_name == "3C_DISCOVERY" & dataset_name == "3C_internal_validation" & type %in% c("Control", "Breast")) %>%
droplevels() %>%
mutate(WID_BC = index_BC) %>%
select(type, WID_BC)
rownames(mdat) <- ""
rownames(mdat) <- NA
mdat
data <- mdat %>%
filter(experiment_name == "3C_DISCOVERY" & dataset_name == "3C_internal_validation" & type %in% c("Control", "Breast")) %>%
droplevels() %>%
rownames_to_column("") %>%
mutate(WID_BC = index_BC) %>%
select(type, WID_BC)
data <- mdat %>%
filter(experiment_name == "3C_DISCOVERY" & dataset_name == "3C_internal_validation" & type %in% c("Control", "Breast")) %>%
droplevels() %>%
rownames_to_column("basename") %>%
mutate(WID_BC = index_BC) %>%
select(type, WID_BC)
load("~/Dropbox/index-dev/master-dataset/1-output/mdat.Rdata")
data <- mdat %>%
filter(experiment_name == "3C_DISCOVERY" & dataset_name == "3C_internal_validation" & type %in% c("Control", "Breast")) %>%
droplevels() %>%
rownames_to_column("basename") %>%
mutate(WID_BC = index_BC) %>%
select(type, WID_BC)
data
library(usethis)
use_data(data)
mutate(type = factor(type, levels = c("Control", "Breast")) %>%
load("~/Dropbox/index-dev/master-dataset/1-output/mdat.Rdata")
data <- mdat %>%
filter(experiment_name == "3C_DISCOVERY" & dataset_name == "3C_internal_validation" & type %in% c("Control", "Breast")) %>%
mutate(type = factor(type, levels = c("Control", "Breast"))) %>%
droplevels() %>%
rownames_to_column("basename") %>%
mutate(WID_BC = index_BC) %>%
select(type, WID_BC)
load("~/Dropbox/index-dev/master-dataset/1-output/mdat.Rdata")
data <- mdat %>%
filter(experiment_name == "3C_DISCOVERY" & dataset_name == "3C_internal_validation" & type %in% c("Control", "Breast")) %>%
mutate(type = factor(type, levels = c("Control", "Breast"))) %>%
droplevels() %>%
rownames_to_column("basename") %>%
mutate(WID_BC = index_BC) %>%
select(type, WID_BC)
use_data(data)
use_data(data, overwrite = TRUE)
devtools::document()
devtools::document()
library(WID.BC)
data %>%
ggplot(aes(x = type,
y = WID_BC)) +
geom_violin() +
geom_boxplot(width = 0.1)
data %>%
ggplot(aes(x = type,
y = WID_BC)) +
geom_violin() +
geom_boxplot(width = 0.1) +
xlab("")
data %>%
ggplot(aes(x = type,
y = WID_BC)) +
geom_violin() +
geom_boxplot(width = 0.1) +
xlab("") +
ylab("WID-BC-index")
devtools::document()
devtools::install()
devtools::install_github("WID.BC"")
devtools::install_github("WID.BC)
devtools::install_github("WID.BC")
devtools::install_github("WID.BC")
devtools::install_github("chiaraherzog/WID.BC")
load("~/Dropbox/index-dev/master-dataset/1-output/mdat.Rdata")
load("~/Dropbox/data/3c-ext-validation/beta_merged.Rdata")
?WID_BC()
WID.BC::WID_BC(beta_merged)
WID.BC::scaling
WID_BC()
?WID_BC()
x <- WID.BC::WID_BC(beta = beta_merged)
devtools::document()
devtools::install_github("chiaraherzog/WID.BC")
library(WID.BC)
WID_BC(beta_merged)
load("~/Dropbox/index-dev/master-dataset/1-output/mdat.Rdata")
test <- WID_BC(beta_merged)
load("~/Dropbox/index-dev/master-dataset/1-output/mdat.Rdata")
dat <- droplevels(mdat[match(names(test), rownames(mdat)),])
plot(dat$index_BC, test)
devtools::install_github("chiaraherzog/WIDclocks")
library(WIDclocks)
test <- WIDclocks(beta_merged)
test <- WID_clocks(beta_merged)
plot(dat$index_general_age, test$WID_general_clock)
plot(dat$index_epithelial_age, test$WID_epithelial_clock)