-
Notifications
You must be signed in to change notification settings - Fork 0
/
habitat.Rmd
417 lines (339 loc) · 13.3 KB
/
habitat.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
---
title: "Structure by habitat type"
output:
html_document:
df_print: paged
---
Load libraries:
```{r, echo=FALSE}
library(ape)
library(paran)
library(splits)
library(ggplot2)
library(dplyr)
```
Bar plots of all OTU abundance by habitat type
```{r}
# read data
samples_otus<-read.delim("samples_OTUs.txt") %>%
dplyr::arrange(., OTU) %>% # order by otu
mutate(., OTU=as.factor(OTU)) # otu as character not number
levels(samples_otus$OTU)<-unique(samples_otus$OTU) # add levels so that it plots nice (cant use integer because there is not otu 9)
# plot
ggplot(samples_otus, aes(x=OTU, fill=vegetation_type)) +
geom_bar() + theme_bw() +
scale_fill_manual(values=c("green4", "orange"),
name="Vegetation type") +
theme(legend.title=element_text(size=13),
legend.text=element_text(size=12),
axis.title.x = element_text(size=13),
axis.title.y = element_text(size=13),
axis.text.x = element_text(size=12),
axis.text.y = element_text(size=12)) +
scale_x_discrete(breaks=seq(0,40,5))
```
Bar plot by family:
```{r}
ggplot(samples_otus, aes(x=OTU, fill=vegetation_type)) +
geom_bar() + theme_bw() +
facet_wrap(. ~ family, scales="free_x") +
scale_fill_manual(values=c("green4", "orange"),
name="Habitat") +
theme(legend.title=element_text(size=13),
legend.text=element_text(size=12),
axis.title.x = element_text(size=13),
axis.title.y = element_text(size=13),
axis.text.x = element_text(size=10),
axis.text.y = element_text(size=12),
strip.text = element_text(size=12)) +
scale_x_discrete(breaks=c(1:11, seq(12,37,3), 39:45))
```
Now plot nice trees.
Modify the plot function from splits (add a 2 so R don't get confused) | Se modifica la función de graficar del paquete splits (se agrega un 2 para que R no se confunda)
```{r}
plotCluster2 <- function(tr, lthresh, show.tip.label = FALSE, # tip labels to FALSE
show.node.label = FALSE, cex = 0.5, edge.width) {
numnod <- tr$Nnode
numtip <- length(tr$tip.label)
cdat <- array(1, 2 * numnod)
ndat <- array("", numnod)
bt <- -branching.times(tr)
nest.nodes <- function(tr, x, p = 0) {
numtip <- length(tr$tip.label)
nods <- array(NA, 0)
desc <- as.integer(tr$edge[, 2][tr$edge[, 1] == x])
if (desc[1] > numtip) {
nods <- c(nods, desc[1], nest.nodes(tr, desc[1]))
}
if (desc[2] > numtip) {
nods <- c(nods, desc[2], nest.nodes(tr, desc[2]))
}
if (length(nods) > 0) {
return(nods)
}
else {
return(NULL)
}
}
threshold.group <- function(mrcas) {
parent <- tr$edge[, 1]
child <- tr$edge[, 2]
thresh.group <- list()
thresh.time <- c()
mrcas <- mrcas + numtip
k <- 1
while (TRUE) {
times <- bt[mrcas - numtip]
thresh1.time <- min(times)
thresh1.node <- mrcas[which.min(times)]
mrcas <- mrcas[-which.min(times)]
if (length(mrcas) == 0) {
thresh.time <- c(thresh.time, thresh1.time)
thresh.group[[k]] <- thresh1.node
break
}
member <- thresh1.node
del <- c()
for (i in 1:length(mrcas)) {
par.nod <- parent[child == mrcas[i]]
t.par <- bt[par.nod - numtip]
if (t.par < thresh1.time) {
member <- c(member, mrcas[i])
del <- c(del, i)
}
}
thresh.time <- c(thresh.time, thresh1.time)
thresh.group[[k]] <- member
k <- k + 1
if (length(del) != 0) {
mrcas <- mrcas[-del]
}
if (length(mrcas) == 0) {
break
}
}
return(thresh.group)
}
group <- threshold.group(lthresh)
colors <- rainbow(length(group))
k <- 1
for (g in group) {
n.col.type <- rep(0, numnod)
for (j in 1:length(g)) {
n.col.type[g[j] - numtip] <- 2
n.col.type[nest.nodes(tr, g[j]) - numtip] <- 1
}
cdat[match(tr$edge[, 1], which((n.col.type == 1) |
(n.col.type == 2)) + numtip) > 0] <-
colors[k]
k <- k + 1
}
plot(tr, edge.color = cdat, use.edge.length = 1, show.node.label =
show.node.label,
show.tip.label = show.tip.label, no.margin = FALSE,
cex = cex, edge.width=edge.width)
}
```
Use the trees resulted from the GMYC analysis (see "otus_delimitation.Rmd"). First, get population names and habitat from sequences names. B corresponds to forest and Z to alpine grasslands. | Se usan los árboles que resultaron del análisis GMYC (explicado en "otus_delimitation.Rmd"). Primero, se obtienen los nombres de las poblaciones y el tipo de vegetación de los nombres de las secuencias. B corresponde a bosques, y Z a pastizal alpino.
```{r, fig.width=12, fig.height=7}
Ttree<-read.nexus("trees/CurculionidaeTtree")
# run gmyc
Tgmyc<-gmyc(Ttree, method="single", interval=c(0,10),quiet=F)
# change tips
x<-Tgmyc
nomtips<-substr((x$tr)$tip.label, 1,2)
nomtips #Population
samtips<-substr((x$tr)$tip.label, 3,3)
samtips #habitat
#Definir color por tipo de vegetación (samtips)
samtips<-as.factor(samtips)
levels(samtips)<-c("green4", "orange")
samtips
# plot tree according to habitat type
plotCluster2(x$tree, x$MRCA[[which.max(x$likelihood)]], edge.width=2)
tiplabels(pch=15, col=as.vector(samtips), adj=0, offset=0.51, cex=1.5)
tiplabels(text=nomtips, frame="none", col="black", cex=1, adj=0, offset = 0.018)
# add OTU names
edgelabels(text=c("OTU 5", "OTU 4", "OTU 3", "OTU 2", "OTU 7", "OTU 6", "OTU 1"), edge=c(54, 51, 24, 15, 14, 13, 4), frame="none", adj = c(0.5, -0.25), cex=.7, date= .09)
# plot Time vs likelihood
plot(x$threshold.time, x$likelihood,type = "l", xlab = "Time", ylab = "Likelihood", cex.lab=1.5, cex.axis=1.5)
# plot time vs number of entityes and threshold time: -0.03913536
plot(x$threshold.time, x$entity, type="s" , xlab = "Time", ylab = "N", cex.lab=1.5, cex.axis=1.5)
abline(v=-0.03913536, col="red")
```
### Full figures for all Families:
Curculionidae
```{r, echo= FALSE, fig.width=12, fig.height=11}
Ttree<-read.nexus("trees/CurculionidaeTtree")
# run gmyc
Tgmyc<-gmyc(Ttree, method="single", interval=c(0,10),quiet=F)
# change tips
x<-Tgmyc
nomtips<-substr((x$tr)$tip.label, 1,2)
nomtips #Population
samtips<-substr((x$tr)$tip.label, 3,3)
samtips #habitat
#Definir color por tipo de vegetación (samtips)
samtips<-as.factor(samtips)
levels(samtips)<-c("green4", "orange")
samtips
## PLOT
layout(matrix(c(1,1,2,3), 2, 2, byrow = TRUE),
heights=c(2,1))
# plot tree according to habitat type
par(mar=c(0, 4, 2.5, 4))
plotCluster2(x$tree, x$MRCA[[which.max(x$likelihood)]], edge.width=2)
tiplabels(pch=15, col=as.vector(samtips), adj=0, offset=0.51, cex=1.5)
tiplabels(text=nomtips, frame="none", col="black", cex=1, adj=0, offset = 0.018)
title(main="Curculionidae (Coleoptera) \na)",adj=0, cex.main=1.5)
# add OTU names
edgelabels(text=c("OTU 5", "OTU 4", "OTU 3", "OTU 2", "OTU 7", "OTU 6", "OTU 1"), edge=c(54, 51, 24, 15, 14, 13, 4), frame="none", adj = c(0.5, -0.25), cex=.7, date= .09)
# plot Time vs likelihood
par(mar=c(4, 4, 2, 4))
plot(x$threshold.time, x$likelihood,type = "l", xlab = "Time", ylab = "Likelihood", cex.lab=1.5, cex.axis=1.5, lwd=2)
title(main="b)",adj=0, cex.main=1.5)
# plot time vs number of entityes and threshold time
par(mar=c(4, 4, 2, 4))
plot(x$threshold.time, x$entity, type="s" , xlab = "Time", ylab = "N", cex.lab=1.5, cex.axis=1.5, lwd=2)
abline(v=-0.03913536, col="red", lwd=2)
title(main="c)",adj=0, cex.main=1.5)
```
Carabideae
```{r, echo=FALSE, results= "hide", fig.width=12, fig.height=12}
Ttree<-read.nexus("trees/CarabidaeTtree")
# run gmyc
Tgmyc<-gmyc(Ttree, method="single", interval=c(0,10),quiet=F)
# change tips
x<-Tgmyc
nomtips<-substr((x$tr)$tip.label, 1,2)
nomtips #Population
samtips<-substr((x$tr)$tip.label, 3,3)
samtips #habitat
#Definir color por tipo de vegetación (samtips)
samtips<-as.factor(samtips)
levels(samtips)<-c("green4", "orange")
samtips
## PLOT
layout(matrix(c(1,1,2,3), 2, 2, byrow = TRUE),
heights=c(3,1.2))
# plot tree according to habitat type
par(mar=c(0, 4, 2.5, 4))
plotCluster2(x$tree, x$MRCA[[which.max(x$likelihood)]], edge.width=2)
tiplabels(pch=15, col=as.vector(samtips), adj=0, offset=0.51, cex=1.5)
tiplabels(text=nomtips, frame="none", col="black", cex=1, adj=0, offset = 0.018)
title("Carabidae (Coleoptera) \na)",adj=0, cex.main=1.5)
# add OTU names
edgelabels(text=c("OTU 11", "OTU 10"), edge=c(38,1), frame="none", adj = c(0.5, -0.25), cex=.8, date= .2)
# plot Time vs likelihood
par(mar=c(4, 4, 2, 4))
plot(x$threshold.time, x$likelihood,type = "l", xlab = "Time", ylab = "Likelihood", cex.lab=1.5, cex.axis=1.5, lwd=2)
title(main="b)",adj=0, cex.main=1.5)
# plot time vs number of entityes and threshold time
par(mar=c(4, 4, 2, 4))
plot(x$threshold.time, x$entity, type="s" , xlab = "Time", ylab = "N", cex.lab=1.5, cex.axis=1.5, lwd=2, ylim=c(1,20))
abline(v=-0.05120494, col="red", lwd=2)
title(main="c)",adj=0, cex.main=1.5)
```
Linyphiidae.
This family has many OTUs, check OTU names were assigned correctly
```{r, results= "hide", fig.width=13, fig.height=32}
Ttree<-read.nexus("trees/LinyphiidaeTtree")
# run gmyc
Tgmyc<-gmyc(Ttree, method="single", interval=c(0,10),quiet=F)
x<-Tgmyc
samtips<-substr((x$tr)$tip.label, 3,3)
samtips #habitat
#Definir color por tipo de vegetación (samtips)
samtips<-as.factor(samtips)
levels(samtips)<-c("green4", "orange")
samtips
# get which CROP OTU is each tip
nomtips<-(x$tr)$tip.label
nomtips<-as.data.frame(nomtips)
otu_tips<-inner_join(nomtips, samples_otus, by=c("nomtips"="sample_id"))
####
# plot tree according to habitat type and otus name
par(mar=c(0, 4, 2.5, 4))
plotCluster2(x$tree, x$MRCA[[which.max(x$likelihood)]], edge.width=2)
tiplabels(pch=15, col=as.vector(samtips), adj=0, offset=0.51, cex=1.5)
tiplabels(text=otu_tips$OTU, frame="none", col="black", cex=.50, adj=0, offset = 0.006)
tiplabels(text=(x$tr)$tip.label, frame="none", col="black", cex=.4, adj=0, offset= 0.016)
title("Linyphiidae (Aranae) \na)",adj=0, cex.main=1.5)
# add OTU names
edgelabels(text=c("OTU 31", "OTU 28", "OTU 27", "OTU 34", "OTU 26", "OTU 38", "OTU 25", "OTU 24", "OTU 23", "OTU 29", "OTU 22", "OTU 21", "OTU 20", "OTU 19", "OTU 18", "OTU 33", "OTU 18", "OTU 35", "OTU 17", "OTU 16", "OTU 32", "OTU 15", "OTU 14", "OTU 13", "OTU 36", "OTU 30", "OTU 37", "OTU 12"),
edge=c(256, 245, 236, 235, 220, 215, 203, 196, 192, 190, 187, 180, 159, 150, 130, 129, 122, 118, 103, 100, 98, 62, 37, 15, 13, 9, 8, 2),
frame="none", adj = c(0.5, -0.25), cex=.6)
```
Now nice plot:
```{r, echo=FALSE, results= "hide", fig.width=12, fig.height=32}
Ttree<-read.nexus("trees/LinyphiidaeTtree")
# run gmyc
Tgmyc<-gmyc(Ttree, method="single", interval=c(0,10),quiet=F)
# change tips
x<-Tgmyc
nomtips<-substr((x$tr)$tip.label, 1,2)
nomtips #Population
samtips<-substr((x$tr)$tip.label, 3,3)
samtips #habitat
#Definir color por tipo de vegetación (samtips)
samtips<-as.factor(samtips)
levels(samtips)<-c("green4", "orange")
samtips
## PLOT
layout(matrix(c(1,1,2,3), 2, 2, byrow = TRUE),
heights=c(6,1))
# plot tree according to habitat type
par(mar=c(0, 4, 2.5, 4))
plotCluster2(x$tree, x$MRCA[[which.max(x$likelihood)]], edge.width=2)
tiplabels(pch=15, col=as.vector(samtips), adj=0, offset=0.51, cex=1.5)
tiplabels(text=nomtips, frame="none", col="black", cex=1, adj=0, offset = 0.018)
title("Linyphiidae (Aranae) \na)",adj=0, cex.main=1.5)
# add OTU names
edgelabels(text=c("OTU 31", "OTU 28", "OTU 27", "OTU 34", "OTU 26", "OTU 38", "OTU 25", "OTU 24", "OTU 23", "OTU 29", "OTU 22", "OTU 21", "OTU 20", "OTU 19", "OTU 18", "OTU 33", "OTU 18", "OTU 35", "OTU 17", "OTU 16", "OTU 32", "OTU 15", "OTU 14", "OTU 13", "OTU 36", "OTU 30", "OTU 37", "OTU 12"),
edge=c(256, 245, 236, 235, 220, 215, 203, 196, 192, 190, 187, 180, 159, 150, 130, 129, 122, 118, 103, 100, 98, 62, 37, 15, 13, 9, 8, 2),
frame="none", adj = c(0.5, -0.25), cex=.6)
# plot Time vs likelihood
par(mar=c(4, 4, 2, 4))
plot(x$threshold.time, x$likelihood,type = "l", xlab = "Time", ylab = "Likelihood", cex.lab=1.5, cex.axis=1.5, lwd=2)
title(main="b)",adj=0, cex.main=1.5)
# plot time vs number of entityes and threshold time
par(mar=c(4, 4, 2, 4))
plot(x$threshold.time, x$entity, type="s" , xlab = "Time", ylab = "N", cex.lab=1.5, cex.axis=1.5, lwd=2)
abline(v=-0.07269869, col="red", lwd=2)
title(main="c)",adj=0, cex.main=1.5)
```
Gnaphosidae
```{r, echo=FALSE, results= "hide", fig.width=12, fig.height=8}
Ttree<-read.nexus("trees/GnaphosidaeTtree")
# run gmyc
Tgmyc<-gmyc(Ttree, method="single", interval=c(0,10),quiet=F)
# change tips
x<-Tgmyc
nomtips<-substr((x$tr)$tip.label, 1,2)
nomtips #Population
samtips<-substr((x$tr)$tip.label, 3,3)
samtips #habitat
#Definir color por tipo de vegetación (samtips)
samtips<-as.factor(samtips)
levels(samtips)<-c("green4", "orange")
samtips
## PLOT
layout(matrix(c(1,1,2,3), 2, 2, byrow = TRUE))
# plot tree according to habitat type
par(mar=c(0, 4, 2.5, 4))
plotCluster2(x$tree, x$MRCA[[which.max(x$likelihood)]], edge.width=2)
tiplabels(pch=15, col=as.vector(samtips), adj=0, offset=0.51, cex=1.5)
tiplabels(text=nomtips, frame="none", col="black", cex=1, adj=0, offset = 0.018)
title("Gnaphosidae (Aranae) \na)",adj=0, cex.main=1.5)
# Plot OTUs name
edgelabels(text=c("OTU 45", "OTU 44", "OTU 43", "OTU 42", "OTU 41", "OTU 40", "OTU 39"), edge=c(38, 35, 32, 26, 23, 10, 3), frame="none", adj = c(0.5, -0.25), cex=.8, date= .1)
# plot Time vs likelihood
par(mar=c(4, 4, 2, 4))
plot(x$threshold.time, x$likelihood,type = "l", xlab = "Time", ylab = "Likelihood", cex.lab=1.5, cex.axis=1.5, lwd=2)
title(main="b)",adj=0, cex.main=1.5)
# plot time vs number of entityes and threshold time
par(mar=c(4, 4, 2, 4))
plot(x$threshold.time, x$entity, type="s" , xlab = "Time", ylab = "N", cex.lab=1.5, cex.axis=1.5, lwd=2)
abline(v=-0.02034695, col="red", lwd=2)
title(main="c)",adj=0, cex.main=1.5)
```