-
Notifications
You must be signed in to change notification settings - Fork 0
/
MCP_counter.Rmd
345 lines (271 loc) · 11.1 KB
/
MCP_counter.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
---
title: "MCP_counter analysis with default parameters"
author: "Rajesh Pal"
date: '2022-08-31'
output: html_document
---
```{r echo=FALSE, message=FALSE}
library(dplyr)
library(MCPcounter)
library(readr)
library(ComplexHeatmap)
library(circlize)
library(dendextend)
library(reshape2)
library(ggplot2)
library(ggsignif)
library(viridis)
library(hrbrthemes)
#library(ggpubr)
```
<br>
**The following script has been adapted from webMCP-counter R shiny app. The app currently has the following drawbacks: frequent crashes when you upload large files, and you cannot download high quality images following analysis. **
**The whole script has been written in easy to understand language. I know some of the things could have been written in a loop, or it could have been modified here and there, however i am lazy, so, feel free to do whatever you like! **
**For the analysis please use normalized data. Following analysis assumes that you have normalized counts matrix from DESEQ's (estimatesizefactors) output. Please do not use TPM, for GOD's sake!! **
<br>
**Provide the input directory of normalized matrix.** This code block reads the tibble data frame, converts it into dataframe and sets the first column in to row names.
```{r message = FALSE}
setwd("/omics/odcf/analysis/hipo/hipo_021/RP_all_RNAseq/rnaseq/")
normalized_matrix = read_csv("positive_matrix.csv")
normalized_matrix = as.data.frame(normalized_matrix)
rownames(normalized_matrix) <- normalized_matrix[, 1]
normalized_matrix <- normalized_matrix[,-1]
```
**Initiating MCP counter.**
This code block transposes the dataframe, scale it, followed by clustering.
```{r}
clusterColorCode <- c("#e41a1c","#377eb8","#4daf4a","#984ea3","#ff7f00","#ffff33","#a65628","#f781bf","#999999","#8dd3c7")
names(clusterColorCode) <- paste("Cluster",1:10)
estimates <- t(data.frame(MCPcounter.estimate(normalized_matrix,featuresType = "HUGO_symbols"),check.names = FALSE))
est.norm <- t(apply(t(estimates),1,scale))
colnames(est.norm) <- row.names(estimates)
est.norm[is.na(est.norm[,1]),] <- 0
dend.mcp <- hclust(dist(est.norm,method = "euclidian"))
dend.samples <- hclust(dist(t(est.norm),method = "euclidian"))
```
<br>
**Just modify the num_of_clusters value to visualize more clusters on the heatmap or overall analysis. **
```{r}
##############
num_of_clusters = 3
#############
dend.samples <- color_branches(dend.samples,k=num_of_clusters,col = clusterColorCode[1:num_of_clusters])
```
**Heatmap**
```{r}
###adjust col-size here
size = 5
##############################
Heatmap(as.matrix(est.norm), col = colorRamp2(c(-4,-2, 0, 2,4),c("#2166ac","#92c5de","#f7f7f7","#f4a582","#b2182b")),
cluster_rows = dend.mcp, cluster_columns = dend.samples, show_column_names = TRUE, show_row_names = TRUE, name = "Row Z-score", column_names_gp = grid::gpar(fontsize = size))
```
<br>
**Extracting the clusters for for making boxplots/violin plots and significance analysis between the clusters.**
```{r}
clusters <- paste("Cluster",match(get_leaves_attr(dend.samples,"edgePar"),clusterColorCode))
clusters_n <- paste(clusters,"\n(n=",table(clusters)[clusters],")",sep="")
names(clusters_n) <- labels(dend.samples)
clusters_n <- clusters_n[rownames(estimates)]
melt_df <- function(df,var_to_group){
df.m <- melt(df,id = var_to_group,varnames = c("variable","value"))
colnames(df.m)[1] <- "groups"
df.m$value <- as.numeric(as.character(df.m$value))
return(df.m)
}
# get boxplots
estimates_df <- data.frame(estimates,check.names = F)
estimates_df$clusters <- clusters_n
melted_est <- melt_df(estimates_df,var_to_group = 'clusters')
```
**Initiating violin plots with significance test between all the groups. At present it performs t-test, Need to modify the code if you want to perform any other test.
BTW, the worst code block begins!!
Please don't judge me, and i wont judge you!**
```{r}
melted_est%>%
filter(variable == "NK cells") %>%
select(groups,value) %>%
#left_join(sample_size) %>%
mutate(myaxis = groups) %>%
{ggplot(.,aes(myaxis, value, fill= groups)) +
geom_violin(width=1.4) + # ggbeeswarm::geom_beeswarm()+
geom_boxplot(width=0.1, color="grey", alpha=0.2) +
scale_fill_viridis(discrete = TRUE) +
theme_ipsum() +
theme(
legend.position="none",
plot.title = element_text(size=11)
) +
ggtitle("NK-cells") +
xlab("") + ylab("MCP score") +
ggsignif::geom_signif(comparisons = combn(sort(unique(.$groups)),2, simplify = F),
step_increase = 0.1,test='t.test')}
```
```{r, echo=FALSE, message=FALSE}
melted_est%>%
filter(variable == "T cells") %>%
select(groups,value) %>%
#left_join(sample_size) %>%
mutate(myaxis = groups) %>%
{ggplot(.,aes(myaxis, value, fill= groups)) +
geom_violin(width=1.4) + # ggbeeswarm::geom_beeswarm()+
geom_boxplot(width=0.1, color="grey", alpha=0.2) +
scale_fill_viridis(discrete = TRUE) +
theme_ipsum() +
theme(
legend.position="none",
plot.title = element_text(size=11)
) +
ggtitle("T-cells") +
xlab("") + ylab("MCP score") +
ggsignif::geom_signif(comparisons = combn(sort(unique(.$groups)),2, simplify = F),
step_increase = 0.1,test='t.test')}
melted_est%>%
filter(variable == "CD8 T cells") %>%
select(groups,value) %>%
#left_join(sample_size) %>%
mutate(myaxis = groups) %>%
{ggplot(.,aes(myaxis, value, fill= groups)) +
geom_violin(width=1.4) + # ggbeeswarm::geom_beeswarm()+
geom_boxplot(width=0.1, color="grey", alpha=0.2) +
scale_fill_viridis(discrete = TRUE) +
theme_ipsum() +
theme(
legend.position="none",
plot.title = element_text(size=11)
) +
ggtitle("CD8 T cells") +
xlab("") + ylab("MCP score") +
ggsignif::geom_signif(comparisons = combn(sort(unique(.$groups)),2, simplify = F),
step_increase = 0.1,test='t.test')}
melted_est%>%
filter(variable == "Cytotoxic lymphocytes") %>%
select(groups,value) %>%
#left_join(sample_size) %>%
mutate(myaxis = groups) %>%
{ggplot(.,aes(myaxis, value, fill= groups)) +
geom_violin(width=1.4) + # ggbeeswarm::geom_beeswarm()+
geom_boxplot(width=0.1, color="grey", alpha=0.2) +
scale_fill_viridis(discrete = TRUE) +
theme_ipsum() +
theme(
legend.position="none",
plot.title = element_text(size=11)
) +
ggtitle("Cytotoxic lymphocytes") +
xlab("") + ylab("MCP score") +
ggsignif::geom_signif(comparisons = combn(sort(unique(.$groups)),2, simplify = F),
step_increase = 0.1,test='t.test')}
melted_est%>%
filter(variable == "B lineage") %>%
select(groups,value) %>%
#left_join(sample_size) %>%
mutate(myaxis = groups) %>%
{ggplot(.,aes(myaxis, value, fill= groups)) +
geom_violin(width=1.4) + # ggbeeswarm::geom_beeswarm()+
geom_boxplot(width=0.1, color="grey", alpha=0.2) +
scale_fill_viridis(discrete = TRUE) +
theme_ipsum() +
theme(
legend.position="none",
plot.title = element_text(size=11)
) +
ggtitle("B lineage") +
xlab("") + ylab("MCP score") +
ggsignif::geom_signif(comparisons = combn(sort(unique(.$groups)),2, simplify = F),
step_increase = 0.1,test='t.test')}
melted_est%>%
filter(variable == "Monocytic lineage") %>%
select(groups,value) %>%
#left_join(sample_size) %>%
mutate(myaxis = groups) %>%
{ggplot(.,aes(myaxis, value, fill= groups)) +
geom_violin(width=1.4) + # ggbeeswarm::geom_beeswarm()+
geom_boxplot(width=0.1, color="grey", alpha=0.2) +
scale_fill_viridis(discrete = TRUE) +
theme_ipsum() +
theme(
legend.position="none",
plot.title = element_text(size=11)
) +
ggtitle("Monocytic lineage") +
xlab("") + ylab("MCP score") +
ggsignif::geom_signif(comparisons = combn(sort(unique(.$groups)),2, simplify = F),
step_increase = 0.1,test='t.test')}
melted_est%>%
filter(variable == "Myeloid dendritic cells") %>%
select(groups,value) %>%
#left_join(sample_size) %>%
mutate(myaxis = groups) %>%
{ggplot(.,aes(myaxis, value, fill= groups)) +
geom_violin(width=1.4) + # ggbeeswarm::geom_beeswarm()+
geom_boxplot(width=0.1, color="grey", alpha=0.2) +
scale_fill_viridis(discrete = TRUE) +
theme_ipsum() +
theme(
legend.position="none",
plot.title = element_text(size=11)
) +
ggtitle("Myeloid dendritic cells") +
xlab("") + ylab("MCP score") +
ggsignif::geom_signif(comparisons = combn(sort(unique(.$groups)),2, simplify = F),
step_increase = 0.1,test='t.test')}
melted_est%>%
filter(variable == "Neutrophils") %>%
select(groups,value) %>%
#left_join(sample_size) %>%
mutate(myaxis = groups) %>%
{ggplot(.,aes(myaxis, value, fill= groups)) +
geom_violin(width=1.4) + # ggbeeswarm::geom_beeswarm()+
geom_boxplot(width=0.1, color="grey", alpha=0.2) +
scale_fill_viridis(discrete = TRUE) +
theme_ipsum() +
theme(
legend.position="none",
plot.title = element_text(size=11)
) +
ggtitle("Neutrophils") +
xlab("") + ylab("MCP score") +
ggsignif::geom_signif(comparisons = combn(sort(unique(.$groups)),2, simplify = F),
step_increase = 0.1,test='t.test')}
melted_est%>%
filter(variable == "Endothelial cells") %>%
select(groups,value) %>%
#left_join(sample_size) %>%
mutate(myaxis = groups) %>%
{ggplot(.,aes(myaxis, value, fill= groups)) +
geom_violin(width=1.4) + # ggbeeswarm::geom_beeswarm()+
geom_boxplot(width=0.1, color="grey", alpha=0.2) +
scale_fill_viridis(discrete = TRUE) +
theme_ipsum() +
theme(
legend.position="none",
plot.title = element_text(size=11)
) +
ggtitle("Endothelial cells") +
xlab("") + ylab("MCP score") +
ggsignif::geom_signif(comparisons = combn(sort(unique(.$groups)),2, simplify = F),
step_increase = 0.1,test='t.test')}
melted_est%>%
filter(variable == "Fibroblasts") %>%
select(groups,value) %>%
#left_join(sample_size) %>%
mutate(myaxis = groups) %>%
{ggplot(.,aes(myaxis, value, fill= groups)) +
geom_violin(width=1.4) + # ggbeeswarm::geom_beeswarm()+
geom_boxplot(width=0.1, color="grey", alpha=0.2) +
scale_fill_viridis(discrete = TRUE) +
theme_ipsum() +
theme(
legend.position="none",
plot.title = element_text(size=11)
) +
ggtitle("Fibroblasts") +
xlab("") + ylab("MCP score") +
ggsignif::geom_signif(comparisons = combn(sort(unique(.$groups)),2, simplify = F),
step_increase = 0.1,test='t.test')}
```
In case you wanted simple box plots, here it is! Not that fancy right?
```{r}
boxplot(estimates[,"T cells"]~clusters_n,xlab = "", ylab = "T cells", border = clusterColorCode,outline=FALSE, las=2)
stripchart(estimates[,"T cells"]~clusters_n,vertical = TRUE, add=TRUE, method = "jitter",pch=16, col = clusterColorCode)
```