-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathclusterProfiler With BP, MF and CC-withFCcolor.R
362 lines (277 loc) · 12.7 KB
/
clusterProfiler With BP, MF and CC-withFCcolor.R
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
#http://yulab-smu.top/clusterProfiler-book/index.html
#Import your dataset
#Col1 name as "ID" (Genes ID in Entrez form). Use transgeneID or Biomart for conversion
#Col2 "LogFC"(LogFoldChange)
if (!requireNamespace("BiocManager", quietly = TRUE))
install.packages("BiocManager")
BiocManager::install("clusterProfiler")
BiocManager::install("org.Hs.eg.db")
BiocManager::install("ReactomePA")
BiocManager::install("DOSE")
BiocManager::install("enrichplot")
BiocManager::install("ggnewscale")
install.packages("rlang")
#Access libraries
library(DOSE)
library(viridis)
library(ggnewscale)
library(enrichplot)
library(ReactomePA)
library(clusterProfiler)
library(dplyr)
library(ggplot2)
#COLOR PALLETES WEBSITE: http://www.sthda.com/english/wiki/ggplot2-colors-how-to-change-colors-automatically-and-manually
## assume that 1st column is ID
## 2nd column is fold change
d <- geneList
geneList <- d[,2]
names(geneList) <- as.character(d[,1])
genevector <- names(geneList)
nomes <- d$ID
valores <- d$LogFC
names(valores) <- nomes
geneList <- sort(geneList, decreasing = TRUE)
edo <- enrichPathway(genevector)
edo <- pairwise_termsim(edo, method = "JC", semData = NULL, showCategory = 200)
edo2 <- gsePathway(geneList, pvalueCutoff = 0.2)
egoBP <- enrichGO(genevector, ont="BP", OrgDb = "org.Hs.eg.db")
egoBP <- pairwise_termsim(egoBP, method = "JC", semData = NULL, showCategory = 200)
egoBP2 <- gseGO(geneList, ont="BP", OrgDb = "org.Hs.eg.db")
egoCC <- enrichGO(genevector, ont="CC", OrgDb = "org.Hs.eg.db")
egoCC <- pairwise_termsim(egoCC, method = "JC", semData = NULL, showCategory = 200)
egoCC2 <- gseGO(geneList, ont="CC", OrgDb = "org.Hs.eg.db")
egoMF <- enrichGO(genevector, ont="MF", OrgDb = "org.Hs.eg.db")
egoMF <- pairwise_termsim(egoMF, method = "JC", semData = NULL, showCategory = 200)
egoMF2 <- gseGO(geneList, ont="MF", OrgDb = "org.Hs.eg.db")
edox <- setReadable(edo, 'org.Hs.eg.db', 'ENTREZID')
egoxCC <- setReadable(egoCC, 'org.Hs.eg.db', 'ENTREZID')
egoxBP <- setReadable(egoBP, 'org.Hs.eg.db', 'ENTREZID')
egoxMF <- setReadable(egoMF, 'org.Hs.eg.db', 'ENTREZID')
###############################################################
## PLOTS (ORA, Pahtways)
#Dot plot of enriched terms.
dotplot(edo, showCategory=15) + ggtitle("dotplot for ORA") + scale_color_viridis()
# to change the color scheme replace scale_color_viridis() for (gradient as: low midle and high): scale_color_gradientn(colours = c("#89DC8C","#34A593", "#0B1199"))
# Bar plot of enriched terms.
edo@result <- edo@result %>% arrange(desc(Count))
col_fun = RColorBrewer::brewer.pal(n =9, name = "RdYlBu")
barplot(edo, showCategory=15, fill="p.adjust")+
ggtitle("barplot for ORA")+
scale_fill_viridis()
edo@result <- edo@result %>% arrange(desc(p.adjust))
#Ridgeline plot - Histogram
ridgeplot(edo2, fill="pvalue")+
#fill= "p.adjust" if necessary
xlab("logFC")
#Network plot of enriched terms.
p1 <- cnetplot(edox, foldChange=valores)
p2 <- cnetplot(edox, foldChange=valores, circular = TRUE, colorEdge = TRUE, showCategory = 15) + scale_color_viridis()
cowplot::plot_grid(p2, ncol=1, rel_widths=c(1, 1))
#Labelling nodes by selected subset
p3 <- cnetplot(edox, node_label="none")
p4 <- cnetplot(edox, node_label="gene")
p5 <- cnetplot(edox, node_label="category")
p6 <- cnetplot(edox, node_label="all")
cnetplot(edox, foldChange=valores)+scale_color_viridis(option = "plasma")
cowplot::plot_grid(p6, ncol=1) + xlab("logFC")
#Heatmap plot of enriched terms
p7 <- heatplot(edox)
p8 <- heatplot(edox, foldChange=valores)+ scale_color_viridis()
cowplot::plot_grid(p8, ncol=1)
#Plot for results obtained from hypergeometric test and gene set enrichment analysis.
p9 <- emapplot(edo)
p10 <- emapplot(edo, cex_category=1.5)
p11 <- emapplot(edo,layout="circle")
p12 <- emapplot(edo, cex_category=1.5,layout="circle", showCategory = 15, cex_line = 0.4)+ scale_color_viridis()
cowplot::plot_grid(p12, ncol=1)
#Network using specific pathways
View(edox@result)
#choose your pathways
goid <- c("R-HSA-162909", "R-HSA-162906", "R-HSA-1169410", "R-HSA-877300")
edox@result <- edox@result[goid, ]
cnetplot(edox, foldChange=valores, circular = TRUE, colorEdge = TRUE, showCategory = 6) + scale_color_viridis()
#After running this, you should run the enrichment again
edo <- enrichPathway(genevector)
edo <- pairwise_termsim(edo, method = "JC", semData = NULL, showCategory = 200)
edox <- setReadable(edo, 'org.Hs.eg.db', 'ENTREZID')
###############################################################
## PLOTS (BP)
#Dot plot of enriched terms.
dotplot(egoBP, showCategory=20) + ggtitle("dotplot for BP")+ scale_color_viridis()
View(egoBP)
# Bar plot of enriched terms.
egoBP@result <- egoBP@result %>% arrange(desc(Count))
barplot(egoBP, showCategory=13, color="p.adjust")+
ggtitle("barplot for BP")+
scale_fill_gradient(low="peachpuff", high="indianred3")
egoBP@result <- egoBP@result %>% arrange(desc(p.adjust))
#Ridgeline plot - Histogram
ridgeplot(egoBP2, fill="pvalue")+
#fill= "p.adjust" if necessary
xlab("logFC")
#Network plot of enriched terms.
p1 <- cnetplot(egoxBP, foldChange=valores)
p2 <- cnetplot(egoxBP, foldChange=valores, circular = TRUE, colorEdge = TRUE, showCategory = 5)+ scale_color_viridis()
cowplot::plot_grid(p2, ncol=1, rel_widths=c(1, 1))
#Labelling nodes by selected subset
p3 <- cnetplot(egoxBP, node_label="none")
p4 <- cnetplot(egoxBP, node_label="gene")
p5 <- cnetplot(egoxBP, node_label="category")
p6 <- cnetplot(egoxBP, node_label="all")
cowplot::plot_grid(p6, ncol=1)
#Heatmap plot of enriched terms
p7 <- heatplot(egoxBP)
p8 <- heatplot(egoxBP, foldChange=valores)+ scale_color_viridis()
cowplot::plot_grid(p8, ncol=1)
#Plot for results obtained from hypergeometric test and gene set enrichment analysis.
p9 <- emapplot(egoBP)
p10 <- emapplot(egoBP, cex_category=1.5)
p11 <- emapplot(egoBP,layout="kk")
p12 <- emapplot(egoBP, cex_category=1.5,layout="kk")+ scale_color_viridis()
cowplot::plot_grid(p12, ncol=1)
#Network using specific pathways.Change according the refs below
View(egoxBP@result)
#choose your pathways. change according the refs below
goidBP <- c("GO:0006260","GO:0140014","GO:0071103","GO:0007059", "GO:0000075", "GO:0000082","GO:0000070","GO:0006302","GO:0006310")
egoxBP@result <- egoxBP@result[goidBP, ]
cnetplot(egoxBP, foldChange=valores, circular = TRUE, colorEdge = TRUE)+ scale_color_viridis()
emapplot(egoxBP, cex_category=1.5,layout="kk")+ scale_color_viridis()
cnetplot(egoxBP, foldChange=valores, colorEdge = TRUE)+ scale_color_viridis()
barplot(egoxBP, showCategory=15, color="p.adjust")+
ggtitle("barplot for BP")+
scale_color_viridis()
dotplot(egoxBP, showCategory=20) + ggtitle("dotplot for BP")+ scale_color_viridis()
#Ridgeline plot - Histogram
ridgeplot(egoBP2, fill="pvalue")+
#fill= "p.adjust" if necessary
xlab("logFC")
heatplot(egoxBP, foldChange=valores)+ scale_color_viridis()
#After running this, you should run the enrichment again
egoBP <- enrichGO(genevector, ont="BP", OrgDb = "org.Hs.eg.db")
egoBP <- pairwise_termsim(egoBP, method = "JC", semData = NULL, showCategory = 200)
egoxBP <- setReadable(egoBP, 'org.Hs.eg.db', 'ENTREZID')
###########################################################
## PLOTS (CC)
#Dot plot of enriched terms.
dotplot(egoCC, showCategory=20) + ggtitle("dotplot for CC") + scale_color_viridis()
# Bar plot of enriched terms.
egoCC@result <- egoCC@result %>% arrange(desc(Count))
barplot(egoCC, showCategory=15, color="p.adjust")+
ggtitle("barplot for CC")+
scale_color_viridis()
egoCC@result <- egoCC@result %>% arrange(desc(p.adjust))
#Ridgeline plot - Histogram
ridgeplot(egoCC2, fill="pvalue")+
#fill= "p.adjust" if necessary
xlab("logFC")
#Network plot of enriched terms.
p1 <- cnetplot(egoxCC, foldChange=valores)
p2 <- cnetplot(egoxCC, foldChange=valores, circular = TRUE, colorEdge = TRUE, showCategory = 5) + scale_color_viridis()
cowplot::plot_grid(p2, ncol=1, rel_widths=c(1, 1))
#Labelling nodes by selected subset
p3 <- cnetplot(egoxCC, node_label="none")
p4 <- cnetplot(egoxCC, node_label="gene")
p5 <- cnetplot(egoxCC, node_label="category")
p6 <- cnetplot(egoxCC, node_label="all")
cowplot::plot_grid(p6, ncol=1)
#Heatmap plot of enriched terms
p7 <- heatplot(egoxCC)
p8 <- heatplot(egoxCC, foldChange=valores)+ scale_color_viridis()
cowplot::plot_grid(p8, ncol=1)
#Plot for results obtained from hypergeometric test and gene set enrichment analysis.
p9 <- emapplot(egoCC)
p10 <- emapplot(egoCC, cex_category=1.5)
p11 <- emapplot(egoCC,layout="kk")
p12 <- emapplot(egoCC, cex_category=1.5,layout="kk") + scale_color_viridis()
cowplot::plot_grid(p12, ncol=1)
#Network using specific pathways
View(egoxCC@result)
#choose your pathways
goidCC <- c("GO:1990204", "GO:0098563", "GO:0030665", "GO:0044815", "GO:0031985")
egoxCC@result <- egoxCC@result[goidCC, ]
cnetplot(egoxCC, foldChange=valores, circular = TRUE, colorEdge = TRUE) + scale_color_viridis()
#After running this, you should run the enrichment again
egoCC <- enrichGO(genevector, ont="CC", OrgDb = "org.Hs.eg.db")
egoCC <- pairwise_termsim(egoCC, method = "JC", semData = NULL, showCategory = 200)
egoxCC <- setReadable(egoCC, 'org.Hs.eg.db', 'ENTREZID')
###############################################################
## PLOTS (MF)
#Dot plot of enriched terms.
dotplot(egoMF, showCategory=20) + ggtitle("dotplot for MF")+ scale_color_viridis()
# Bar plot of enriched terms.
#x - counts
egoMF@result <- egoMF@result %>% arrange(desc(Count))
barplot(egoMF, showCategory=15, color="p.adjust")+
ggtitle("barplot for MF")+
scale_color_viridis()
egoMF@result <- egoMF@result %>% arrange(desc(p.adjust))
#Ridgeline plot - Histogram
ridgeplot(egoMF2, fill="pvalue")+
#fill= "p.adjust" if necessary
xlab("logFC")
#Network plot of enriched terms.
p1 <- cnetplot(egoxMF, foldChange=valores)
p2 <- cnetplot(egoxMF, foldChange=valores, circular = TRUE, colorEdge = TRUE, showCategory = 5)+ scale_color_viridis()
cowplot::plot_grid(p2, ncol=1, rel_widths=c(1, 1))
#Labelling nodes by selected subset
p3 <- cnetplot(egoxMF, node_label="none")
p4 <- cnetplot(egoxMF, node_label="gene")
p5 <- cnetplot(egoxMF, node_label="category")
p6 <- cnetplot(egoxMF, node_label="all")
cowplot::plot_grid(p6, ncol=1)
#Heatmap plot of enriched terms
p7 <- heatplot(egoxMF)
p8 <- heatplot(egoxMF, foldChange=valores)+ scale_color_viridis()
cowplot::plot_grid(p8, ncol=1)
#Plot for results obtained from hypergeometric test and gene set enrichment analysis.
p9 <- emapplot(egoMF)
p10 <- emapplot(egoMF, cex_category=1.5)
p11 <- emapplot(egoMF,layout="kk")
p12 <- emapplot(egoMF, cex_category=1.5,layout="kk")+ scale_color_viridis()
cowplot::plot_grid(p12, ncol=1)
#Network using specific pathways. change according the refs below
View(egoxMF@result)
#choose your pathways
goidMF <- c("GO:0016887", "GO:0003678", "GO:0003777", "GO:0003688", "GO:0003774")
egoxMF@result <- egoxMF@result[goidMF, ]
cnetplot(egoxMF, foldChange=valores, circular = TRUE, colorEdge = TRUE)+ scale_color_viridis()
#After running this, you should run the enrichment again
egoMF <- enrichGO(genevector, ont="MF", OrgDb = "org.Hs.eg.db")
egoMF <- pairwise_termsim(egoMF, method = "JC", semData = NULL, showCategory = 200)
egoxMF <- setReadable(egoMF, 'org.Hs.eg.db', 'ENTREZID')
#######################################################################
#http://yulab-smu.top/clusterProfiler-book/chapter4.html#gsencg-fuction
#Density plots for diseases association with the list of DEGs
#gseDO means GSE Diseases Ontology
y <- gseDO(geneList,
nPerm = 100,
minGSSize = 120,
pvalueCutoff = 1,
verbose = FALSE)
ridgeplot(y, fill= "pvalue")
#gseDGN means GSE Diseases Ontology
dgn <- gseDGN(geneList,
nPerm = 100,
minGSSize = 120,
pvalueCutoff = 1,
verbose = FALSE)
ridgeplot(dgn, fill= "pvalue")
#gseNCG means GS Network of Cancer Gene
ncg <- gseNCG(geneList,
nPerm = 100,
minGSSize = 120,
pvalueCutoff = 1,
verbose = FALSE)
ridgeplot(ncg, fill= "pvalue")
#######################################################################
#Export tables
install.packages("writexl")
library(writexl)
tabelaORA <- edox@result
tabelaCC <- egoxCC@result
tabelaBP <- egoxBP@result
tabelaMF <- egoxMF@result
write_xlsx(tabelaORA, "tabelaORA.xlsx")
write_xlsx(tabelaBP, "tabelaBP-upacute.xlsx")
write_xlsx(tabelaCC, "tabelaCC.xlsx")
write_xlsx(tabelaMF, "tabelaMF.xlsx")