-
Notifications
You must be signed in to change notification settings - Fork 0
/
stemness1.R
1901 lines (1621 loc) · 69.5 KB
/
stemness1.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
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
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
setwd("~/vip39/TCGA/cancer_stemness/")
load("./cancerstem_sub.rds")
.libPaths()
.libPaths(c(
#"~/vip39/R/x86_64-pc-linux-gnu-library/4.2/",
"/refdir/Rlib_4.3",
"~/vip39/R/x86_64-pc-linux-gnu-library/4.0/",
"~/vip39/R/x86_64-pc-linux-gnu-library/4.1/",
"/home/data/t030432/R/x86_64-pc-linux-gnu-library/4.3/"))
###免疫分析
##cibersort immune score
##自定义基因集做GSVA 绘制热图 带p值
options(stringsAsFactors = F)
library(GSVA)
library(GSEABase)
library(msigdbr)
library(clusterProfiler)
library(org.Hs.eg.db)
library(enrichplot)
library(limma)
library(data.table)
pathway <- fread("./Stemness_gene_new.csv",header = T,data.table = F)
pathway <- as.data.frame(pathway)
pathway_list <- lapply(pathway, function(x) {
unique(na.omit(x))
})
pathway_list <- vector("list",length(pathway))
for (i in seq_along(pathway)) {
pathway_list[[i]] <- unique(na.omit(pathway[,i]))
}
names(pathway_list) <- colnames(pathway)
for (i in 1:36) {
pathway_list[[i]] <- pathway_list[[i]][pathway_list[[i]]!=""]
}
setwd("~/TCGA/cancer_stemness/GSVA/")
head(KIRC_mRNA_fpkm)
gsva_matrix_BD <- gsva(as.matrix(KIRC_mRNA_fpkm), pathway_list,method='gsva',
kcdf='Gaussian',abs.ranking=TRUE)
gsva_matrix_japan <- gsva(as.matrix(japan_mRNA_fpkm), pathway_list,method='gsva',
kcdf='Gaussian',abs.ranking=TRUE)
save(gsva_matrix_BD,gsva_matrix_japan,file = "~/TCGA/cancer_stemness/GSVA/TCGA_JAPAN_GSVA.rds")
load("./GSVA/TCGA_JAPAN_GSVA.rds")
#write.csv(gsva_matrix_BD,file = "gsva_matrix_BD.csv")
save(sub,file = "./stemness_sub.rds")
load("./stemness_sub.rds")
####单因素分析预后分析
library(tidyverse,lib.loc = "/home/data/refdir/Rlib")
library(ggplot2)
library(ggstatsplot)
library(survival)
library(stringr)
library(viridis)
library(scales)
library(survminer)
dim(sub)
Coxoutput <- data.frame(OS=sub$EVENT,
OS.time=sub$OS
)
rownames(Coxoutput) <- sub$Sample
Coxoutput2 <- as.data.frame(t(KIRC_mRNA_fpkm[unique(RNA_gene),sub$Sample]))
Coxoutput <- cbind(Coxoutput,Coxoutput2)
realdata <- Coxoutput
realdata[1:3,1:6]
dir.create("COX")
setwd("./COX/")
Coxoutput=data.frame()
for(i in colnames(realdata[,3:ncol(realdata)])){
cox <- coxph(Surv(OS.time, OS) ~ realdata[,i], data = realdata)
coxSummary = summary(cox)
Coxoutput=rbind(Coxoutput,cbind(gene=i,HR=coxSummary$coefficients[,"exp(coef)"],
z=coxSummary$coefficients[,"z"],
pvalue=coxSummary$coefficients[,"Pr(>|z|)"],
lower=coxSummary$conf.int[,3],
upper=coxSummary$conf.int[,4]))
}
for(i in c(2:6)){
Coxoutput[,i] <- as.numeric(as.vector(Coxoutput[,i]))
}
Coxoutput <- arrange(Coxoutput,pvalue) %>% #按照p值排序
filter(pvalue < 0.01)
dim(Coxoutput)
#[1] 121 6
#保存到文件
write.csv(Coxoutput,'cox_output.csv', row.names = F)
Coxoutput <- read.csv("cox_output.csv")
head(Coxoutput)
plotCoxoutput <- filter(Coxoutput,HR <=0.92 | HR>= 1.15) #选择合适的top genes
#采用那篇nature的配色
ggplot(data=plotCoxoutput,aes(x=HR,y=gene,color=pvalue))+
geom_errorbarh(aes(xmax=upper,xmin=lower),color="black",height=0,size=1.2)+
geom_point(aes(x=HR,y=gene),size=3.5,shape=18)+ #画成菱形
geom_vline(xintercept = 1,linetype='dashed',size=1.2)+
scale_x_continuous(breaks = c(0.75,1,1.30))+
coord_trans(x='log2')+
ylab("Gene")+ #标签
xlab("Hazard ratios of RNAmodify_gene in KIRC")+
labs(color="P value",title ="Univariate Cox regression analysis" )+
scale_color_viridis()+ #nature配色
theme_ggstatsplot()+ #好看的主题，同原文一致
theme(panel.grid =element_blank()) #去除网格线
ggsave('plot1.pdf',width = 8,height = 15)
#让误差线跟着变色
ggplot(data=plotCoxoutput,aes(x=HR,y=gene,color=pvalue))+
geom_errorbarh(aes(xmax=upper,xmin=lower,color = pvalue),height=0,size=1.2)+
geom_point(aes(x=HR,y=gene),size=3.5,shape=18)+ #画成菱形
geom_vline(xintercept = 1,linetype='dashed',size=1.2)+
scale_x_continuous(breaks = c(0.75,1,1.30))+
coord_trans(x='log2')+
ylab("Gene")+ #标签
xlab("Hazard ratios of RNAmodify_gene in KIRC")+
labs(color="P value",title ="" )+
scale_color_viridis()+
theme_ggstatsplot()+ #好看的主题，同原文一致
theme(panel.grid =element_blank()) #去除网格线
ggsave('plot2.pdf',width = 8,height = 15)
#自己DIY主题和颜色
ggplot(data=plotCoxoutput,aes(x=HR,y=gene,color=pvalue))+
geom_errorbarh(aes(xmax=upper,xmin=lower),color='black',height=0,size=1.2)+
geom_point(aes(x=HR,y=gene),size=3.5,shape=18)+ #画成菱形
geom_vline(xintercept = 1,linetype='dashed',size=1.2)+
scale_x_continuous(breaks = c(0.75,1,1.30))+
coord_trans(x='log2')+
ylab("Gene")+ #标签
xlab("Hazard ratios of RNAmodify_gene in KIRC")+
labs(color="P value",title ="" )+
scale_color_gradient2(low = muted("skyblue"),mid ="white",high =muted('pink'),midpoint = 0.025)+ #樱花色
theme_bw(base_size = 12)+ #字体大小，格式
theme(panel.grid =element_blank(), #去除网格线，开始DIY主题
axis.text.x = element_text(face="bold", color="black", size=9), #各个字体大小
axis.text.y = element_text(face="bold", color="black", size=9),
axis.title.x = element_text(face="bold", color="black", size=11),
axis.title.y = element_text(face="bold",color="black", size=11),
legend.text= element_text(face="bold", color="black", size=9),
legend.title = element_text(face="bold", color="black", size=11),
panel.border = element_rect(colour = 'black',size=1.4)) #边框粗细
ggsave('plot3.pdf',width = 8,height = 15)
save(RNA_gene,file = "~/TCGA/shuainao_model/senescencegene.rds")
##
##直接分型研究
library(ConsensusClusterPlus)
##提取出T1到T3
##这里面只取出sub生存大于30天的
expr <- as.data.frame(gsva_matrix_BD)
dim(expr)
expr <- expr[,sub$Sample]
#shuailaogene_need <- Coxoutput$gene
#save(shuailaogene_need,file = "~/TCGA/shuainao_model/shuailaogene.rds")
#[1] Coxoutput
setwd("../")
dir.create('ConsensusCluster/')
results = ConsensusClusterPlus(as.matrix(expr),
maxK=9,
reps=100,
pItem=0.8,
pFeature=1,
title='ConsensusCluster/',
clusterAlg="km",
distance="euclidean",
seed=123456,
plot="png")
Kvec = 2:9
x1 = 0.1; x2 = 0.9
PAC = rep(NA,length(Kvec))
names(PAC) = paste("K=",Kvec,sep="")
for(i in Kvec){
M = results[[i]]$consensusMatrix
Fn = ecdf(M[lower.tri(M)])
PAC[i-1] = Fn(x2) - Fn(x1)
}
optK = Kvec[which.min(PAC)]
optK
#[1] 2
PAC <- as.data.frame(PAC)
PAC$K <- 2:9
library(ggplot2)
ggplot(PAC,aes(factor(K),PAC,group=1))+
geom_line()+
theme_bw()+theme(panel.grid = element_blank())+
geom_point(size=4,shape=21,color='darkred',fill='skyblue')+
ylab('Proportion of ambiguous clustering')+
xlab('Cluster number K')
library(export)
library(eoffice)
eoffice::topptx(file='ConsensusCluster/PAC.pptx',width=4.5,height=4.5)
topptx(file='ConsensusCluster/PAC.pptx',width=4.5,height=4.5)
eoffice::tofigure(file='ConsensusCluster/PAC.pdf')
ggsave(filename = "ConsensusCluster/PAC.pdf",width = 5,height = 5)
icl <- calcICL(results,title = 'ConsensusCluster/',plot = 'png')
clusterNum=2
cluster=results[[clusterNum]][["consensusClass"]]
sub <- data.frame(Sample=names(cluster),Cluster=cluster)
sub$Cluster <- paste0('C',sub$Cluster)
table(sub$Cluster)
# C1 C2
# 231 285
head(sub)
rownames(sub) <- sub$Sample
sub$EVENT <- as.vector(allclin[rownames(sub),"OS"])
sub$OS <- as.vector(allclin[rownames(sub),"OS.time"])
sub <- sub[sub$OS>30,]
library(survival)
library(survminer)
library(monocle)
library(DDRTree)
library(ggsci)
class(sub)
meta <- sub[,1:4]
head(sub)
colnames(meta) <- c("ID","cluster","event","time")
meta <- meta[,-1]
meta$time <- meta$time/365
head(meta)
sfit <- survfit(Surv(time, event)~cluster, data=meta)
ggsurvplot(sfit, conf.int=F, pval=TRUE)
sfit <- survfit(Surv(OS,EVENT) ~ Cluster,data = sub)
ggsurvplot(sfit, conf.int=F, pval=TRUE)
sfit <- survfit(Surv(OS,EVENT)~Cluster,data = sub)
sfit <- survfit(Surv(OS.time,EVENT)~Cluster,data = sub)
sub$PFI <- allclin[rownames(sub),"PFI"]
sub$PFI.time <- allclin[rownames(sub),"PFI.time"]
sfit <- survfit(Surv(PFI.time, PFI)~Cluster, data=sub)
mytheme <- theme_survminer(font.legend = c(14,"plain", "black"),
font.x = c(14,"plain", "black"),
font.y = c(14,"plain", "black"))
ggsurvplot(sfit,
data = meta,
palette= c(pal_nejm()(2),'grey60'),
conf.int=FALSE,size=1.3,
pval=T,pval.method = T,
legend.labs=c("C1","C2"),
legend.title="cluster",
xlab="Time (years)",
ylab='Overall survival',
risk.table=TRUE,
#break.time.by = 2,
#risk.table.title="Number at risk",
risk.table.height=.3,
risk.table.y.text = FALSE,
ggtheme = mytheme)
ggsave(filename = "OS_twogroup.pdf",height = 6,width = 6)
ggsurvplot(sfit,
data = meta,
palette= c(pal_nejm()(2),'grey60'),
conf.int=FALSE,size=1.3,
pval=T,pval.method = T,
legend.labs=c("C1","C2"),
legend.title="cluster",
xlab="Time (days)",
#ylab='Overall survival',
ylab='Progression Free Survival',
risk.table=TRUE,
#break.time.by = 2,
#risk.table.title="Number at risk",
risk.table.height=.3,
risk.table.y.text = FALSE,
ggtheme = mytheme)
###PFI
meta$PFI <- allclin[rownames(meta),"PFI"]
meta$PFI.time <- allclin[rownames(meta),"PFI.time"]/365
sfit <- survfit(Surv(PFI.time, PFI)~cluster, data=meta)
ggsurvplot(sfit,
palette= c(pal_nejm()(2),'grey60'),
conf.int=FALSE,size=1.3,
pval=T,pval.method = T,
legend.labs=c("C1","C2"),
legend.title="cluster",
xlab="Time (years)",
ylab='Progression Free Survival',
risk.table=TRUE,
#break.time.by = 2,
#risk.table.title="Number at risk",
risk.table.height=.3,
risk.table.y.text = FALSE,
ggtheme = mytheme)
ggsave(filename = "PFI_twogroup.pdf",height = 6,width = 6)
T1_meta <- meta%>%
filter(pstage=="T1")
sfit <- survfit(Surv(PFI.time, PFI)~cluster, data=T1_meta)
sfit <- survfit(Surv(time, event)~cluster, data=T1_meta)
ggsurvplot(sfit,
palette= c(pal_nejm()(2),'grey60'),
conf.int=FALSE,size=1.3,
pval=T,pval.method = T,
legend.labs=c("C1","C2"),
legend.title="cluster",
xlab="Time (years)",
ylab='Progression Free Survival',
risk.table=TRUE,
break.time.by = 2,
risk.table.title="Number at risk",
risk.table.height=.3,
risk.table.y.text = FALSE,
ggtheme = mytheme)
T2_meta <- meta%>%
filter(pstage=="T2")
sfit <- survfit(Surv(PFI.time, PFI)~cluster, data=T2_meta)
sfit <- survfit(Surv(time, event)~cluster, data=T2_meta)
ggsurvplot(sfit,
palette= c(pal_nejm()(2),'grey60'),
conf.int=FALSE,size=1.3,
pval=T,pval.method = T,
legend.labs=c("C1","C2"),
legend.title="cluster",
xlab="Time (years)",
ylab='Progression Free Survival',
risk.table=TRUE,
break.time.by = 2,
risk.table.title="Number at risk",
risk.table.height=.3,
risk.table.y.text = FALSE,
ggtheme = mytheme)
T3_meta <- meta%>%
filter(pstage=="T3")
sfit <- survfit(Surv(PFI.time, PFI)~cluster, data=T3_meta)
sfit <- survfit(Surv(time, event)~cluster, data=T3_meta)
ggsurvplot(sfit,
palette= c(pal_nejm()(2),'grey60'),
conf.int=FALSE,size=1.3,
pval=T,pval.method = T,
legend.labs=c("C1","C2"),
legend.title="cluster",
xlab="Time (years)",
ylab='Progression Free Survival',
risk.table=TRUE,
break.time.by = 2,
risk.table.title="Number at risk",
risk.table.height=.3,
risk.table.y.text = FALSE,
ggtheme = mytheme)
T4_meta <- meta%>%
filter(pstage=="T4")
sfit <- survfit(Surv(PFI.time, PFI)~cluster, data=T4_meta)
sfit <- survfit(Surv(time, event)~cluster, data=T4_meta)
ggsurvplot(sfit,
palette= c(pal_nejm()(2),'grey60'),
conf.int=FALSE,size=1.3,
pval=T,pval.method = T,
legend.labs=c("C1","C2"),
legend.title="cluster",
xlab="Time (years)",
ylab='Progression Free Survival',
risk.table=TRUE,
break.time.by = 2,
risk.table.title="Number at risk",
risk.table.height=.3,
risk.table.y.text = FALSE,
ggtheme = mytheme)
####绘制热图####
#加上正常组织三组绘图
dir.create("./complexheatmap")
setwd("/home/data/vip39/TCGA/cancer_stemness/complexheatmap/")
library(ComplexHeatmap)
library(stringr)
library(pheatmap)
library(gplots)
library(grid)
library(scico)
library(circlize)
Sys.setenv(LANGUAGE = "en") #显示英文报错信息
options(stringsAsFactors = FALSE) #禁止chr转成factor
###准备两个数据 mygene_data 和 Subtype 分组信息
normal_id <- colnames(gsva_matrix_BD)[str_sub(colnames(gsva_matrix_BD),14,15)=="11"]
c(normal_id,sub$Sample)
Subtype <- data.frame(Subtype=c(rep("N",length(normal_id)),sub$Cluster),
id=c(normal_id,rownames(sub)))
rownames(Subtype) <- Subtype$id
Subtype <- Subtype[-2]
mygene_data <- gsva_matrix_BD[,rownames(Subtype)]
#Subtype <- Subtype[com_sam,,drop = F]
head(Subtype)
table(Subtype$Subtype)
# C1 C2 N
# 231 285 72
## 用前面的自定义函数计算组间统计差异
comprTab <- cross_subtype_compr(expr = mygene_data, # 或log2(mygene_data + 1)，如果用参数检验，请注意对数转化；若非参均可
subt = Subtype,
#two_sam_compr_method = "wilcox", # 两组"t.test", "wilcox"
multi_sam_compr_method = "kruskal", # 多组"anova", "kruskal"
res.path = ".")
# 用全部基因来画
n.show_top_gene <- nrow(mygene_data)
# 按分组排序
subt.order <- Subtype[order(Subtype$Subtype),,drop = F]
indata <- mygene_data[comprTab$gene[1:n.show_top_gene],rownames(subt.order)]
# 数据标准化和边界设置
plotdata <- t(scale(t(indata)))
plotdata[plotdata > 2] <- 2
plotdata[plotdata < -2] <- -2
# 调整行名
blank <- " " # 行名和p值之间的间隔
p.value <- comprTab$adjusted.p.value[1:n.show_top_gene]
sig.label <- ifelse(p.value < 0.001,"****",
ifelse(p.value < 0.005,"***",
ifelse(p.value < 0.01,"**",
ifelse(p.value < 0.05,"*",""))))
p.label <- formatC(p.value, # 将p值变成保留两位小数的科学计数法
format = "e",
digits = 2)
add.label <- str_pad(paste0(rownames(plotdata),sig.label), # 固定行名宽度并再右侧补齐" "
max(nchar(paste0(rownames(plotdata),sig.label))),
side = "right")
annCol <- subt.order # 获得排序后的亚型注释信息，这里只有一个变量需要注释
colnames(annCol)[1] <- paste(str_pad(colnames(annCol)[1], # 注释列名补上"P-value"，宽度和刚才一致
max(nchar(paste0(rownames(plotdata),sig.label))),
side = "right"),
"P-value",
sep = blank)
annColors <- list(c( "C1"="#1F78B4FF", "C2"="#E31A1CFF","N"="#33A02CFF")) # 如果有多个变量要注释颜色请补充c()
names(annColors) <- colnames(annCol)[1] # 如果有多个变量要注释颜色请补充每张list的name
# 绘制热图
pheatmap(cellheight = 15, cellwidth = 1,
mat = plotdata, # 输入数据
scale = "none", # 不标准化因为数据已经被标准化
annotation_col = annCol, # 列注释信息
annotation_colors = annColors, # 列注释对应的颜色
cluster_cols = F, # 列不聚类
cluster_rows = F, # 行不聚类
show_colnames = F, # 不显示列名
show_rownames = T, # 显示基因名
annotation_legend = F, # 不显示图例
#labels_row = paste(add.label, p.label, sep=blank), # 自定义样本名义blank作间隔
#fontfamily = "mono", # 关键，使用fixed font而不是proportional font
gaps_col = c(231,516), # 根据自己的数据设置空白间隔的位置
filename = "heatmapPvalue.pdf")
dev.off()
dev.new()
library(paletteer)
pheatmap(cellheight = 15, cellwidth = 1,
mat = plotdata, # 输入数据
scale = "none", # 不标准化因为数据已经被标准化
annotation_col = annCol, # 列注释信息
annotation_colors = annColors, # 列注释对应的颜色
cluster_cols = F, # 列不聚类
cluster_rows = F, # 行不聚类
show_colnames = F, # 不显示列名
show_rownames = T, # 显示基因名
annotation_legend = F, # 不显示图例
gaps_col = c(231,516),
color = paletteer_c("scico::berlin", n = 100),
labels_row = paste(add.label, p.label, sep=blank), # 自定义样本名义blank作间隔
#fontfamily = "Times New Roman"
#filename = "heatmapPvalue.pdf",
height = 5,
width = 15)
pheatmap(cellheight = 10, cellwidth = 1,
mat = plotdata, # 输入数据
scale = "none", # 不标准化因为数据已经被标准化
annotation_col = annCol, # 列注释信息
annotation_colors = annColors, # 列注释对应的颜色
cluster_cols = F, # 列不聚类
cluster_rows = F, # 行不聚类
show_colnames = F, # 不显示列名
show_rownames = T, # 显示基因名
annotation_legend = F, # 不显示图例
gaps_col = c(231,516),
color = paletteer_c("scico::berlin", n = 100),
labels_row = paste(add.label, p.label, sep=blank),
)
table(Subtype$Subtype)
###差异分析####
setwd("/home/data/vip39/TCGA/cancer_stemness/")
colnames(KIRC_mRNA_count) <- str_sub(colnames(KIRC_mRNA_count),1,15)
exp <-KIRC_mRNA_count[,sub$Sample]
group_list <- sub$Cluster
#C1预后差,放后面
group_list = factor(group_list,levels = c("C2","C1"))
library(DESeq2)
colData <- data.frame(row.names =colnames(exp),
condition=group_list)
exp <- round(exp)
range(exp)
exp = exp[apply(exp, 1, function(x) sum(x > 1) > 5), ]
if(!file.exists(paste0("CS2_CS1","dd.Rdata"))){
dds <- DESeqDataSetFromMatrix(
countData = exp,
colData = colData,
design = ~ condition)
dds <- DESeq(dds)
save(dds,file = paste0("CS1_CS2","_dd.Rdata"))
}
load(paste0("CS1_CS2","_dd.Rdata"))
# 两两比较
res <- results(dds, contrast = c("condition",rev(levels(group_list))))
resOrdered <- res[order(res$pvalue),] # 按照P值排序
DEG <- as.data.frame(resOrdered)
head(DEG)
table(is.na(DEG))
#添加change列标记基因上调下调
logFC_cutoff <- with(DEG,mean(abs(log2FoldChange)) + 2*sd(abs(log2FoldChange)) )
logFC_cutoff <- 2
DEG$change = as.factor(
ifelse(DEG$pvalue < 0.05 & abs(DEG$log2FoldChange) > logFC_cutoff,
ifelse(DEG$log2FoldChange > logFC_cutoff ,'UP','DOWN'),'NOT')
)
head(DEG)
table(DEG$change)
# DOWN NOT UP
# 110 18295 763
library(EnhancedVolcano,lib.loc = "/home/data/vip39/R/x86_64-pc-linux-gnu-library/4.0/")
EnhancedVolcano(res,
lab = rownames(res),
x = 'log2FoldChange',
y = 'pvalue',
title = 'CS1 versus CS2',
pCutoff = 0.05,
FCcutoff = logFC_cutoff,
pointSize = 2.0,
labSize = 3.0,
col=c('#b5b5b5','#b5b5b5','#4D4398','#F18D00'),#调整颜色
colAlpha=0.6)
##火山图美化
EnhancedVolcano(res,
x='log2FoldChange',
y='pvalue',
#lab=data$id,
title = 'CS2 versus CS1',
pCutoff=10e-1/20,#y轴阈值线(水平)
FCcutoff=1.5,#x轴阈值线（垂直）
pointSize=3,#散点大小
labSize=4,#标签大小
xlim=c(-6, 6),#限制X轴范围
ylim=c(0,300),#限制Y轴范围
col=c('#b5b5b5','#b5b5b5','#4D4398','#F18D00'),#调整颜色
colAlpha=0.6,#调整透明度
#selectLab=c(downvals,upvals),#使用selectLab参数选定所关注的标签
xlab=bquote(~Log[2]~'fold change'))#将内容传递给xlab
####↓新加入↓####
#labCol='black',#标签颜色
#labFace='bold',#标签字体
#boxedLabels=TRUE,#是否在框中绘制标签
#drawConnectors=TRUE,#是否通过连线将标签连接到对应的点上
#widthConnectors=0.8,#连线的宽度
#endsConnectors="last",#连线绘制箭头的方向，可选first、both、last
#colConnectors='black')#连线的颜色
topptx(file="CS2_CS1_EnhancedVolcano.pptx")
######富集分析#####
library(clusterProfiler)
library(AnnotationHub)
library(AnnotationDbi)
#BiocManager::install("GOplot")
library(GOplot)
library(ggplot2,lib.loc = "/home/data/vip39/R/x86_64-pc-linux-gnu-library/4.0/")
colnames(DEG)
library(ReactomePA,lib.loc = "/home/data/vip39/R/x86_64-pc-linux-gnu-library/4.0/")
library(tidyverse)
library(data.table)
library(org.Hs.eg.db)
library(org.Mm.eg.db)
library(clusterProfiler)
library(biomaRt)
library(enrichplot)
library(ggsci)
library(paletteer)
DEG$SYMBOL <- rownames(DEG)
DEG2 <-DEG%>%
arrange(log2FoldChange)
top150down <- DEG2$SYMBOL[1:150]
top150up <- DEG2$SYMBOL[(nrow(DEG2)-149):nrow(DEG2)]
#write.table(top150up,"up_CS2_map.txt",col.names = F,row.names = F,sep = "\t",quote = F)
#write.table(top150down,"down_CS2_map.txt",col.names = F,row.names = F,sep = "\t",quote = F)
genelist_input <- DEG[,c(2,8)]
genename <- as.character(genelist_input[,2])
class(genename)
gene_map<-bitr(genelist_input$SYMBOL, #转换的列是df数据框中的SYMBOL列
fromType = "SYMBOL",#需要转换ID类型
toType = "ENTREZID",#转换成的ID类型
OrgDb = "org.Hs.eg.db")#对应的物种，小鼠的是org.Mm.eg.db
gene_map <- select(org.Hs.eg.db, keys=genename, keytype="SYMBOL", columns=c("ENTREZID"))
#gene_map <- select(org.Hs.eg.db, keys=genelist_input[,2], keytype="SYMBOL", columns=c("ENTREZID"))
head(gene_map)
colnames(gene_map)[1]<-"Gene"
colnames(genelist_input) <- c("logFC","Gene")
class(genelist_input$Gene)
aaa<-inner_join(gene_map,genelist_input,by = "Gene")
head(aaa)
aaa<-aaa[,-1]
aaa<-na.omit(aaa)
aaa$logFC<-sort(aaa$logFC,decreasing = T)
geneList = aaa[,2]
names(geneList) = as.character(aaa[,1])
geneList
#GSEA分析——GO
Go_gseresult <- gseGO(geneList, OrgDb = "org.Hs.eg.db", keyType = "ENTREZID", ont="all", minGSSize = 10, maxGSSize = 500, pvalueCutoff=1)
#GSEA分析——KEGG
KEGG_gseresult <- gseKEGG(geneList, nPerm = 1000, minGSSize = 10, maxGSSize = 1000, pvalueCutoff=0.5)
#GSEA分析——Reactome
Go_Reactomeresult <- gsePathway(geneList, nPerm = 1000, minGSSize = 10, maxGSSize = 1000, pvalueCutoff=1)
#波浪图
ridgeplot(KEGG_gseresult,10) #输出前十个结果
ridgeplot(Go_gseresult,10) #输出前十个结果
gseaplot2(Go_Reactomeresult, geneSetID = 1:3, pvalue_table = TRUE,
color = c("#E495A5", "#86B875", "#7DB0DD"), ES_geom = "dot")
gseaplot2(Go_Reactomeresult, geneSetID = 1:5, pvalue_table = TRUE,
color = paletteer_c("scico::berlin", n = 5), ES_geom = "dot")
topptx(filename = "GSEA_up.pptx")
# go <- enrichGO(gene = geneList, OrgDb = "org.Hs.eg.db", ont="all")
# barplot(go, split="ONTOLOGY")+ facet_grid(ONTOLOGY~., scale="free")
gseaplot2(Go_Reactomeresult, geneSetID = c("R-HSA-381753","R-HSA-418555","R-HSA-1461957",
"R-HSA-8851680","R-HSA-176974"), pvalue_table = TRUE,
color = paletteer_c("scico::berlin", n = 5), ES_geom = "dot")
####
gsym.id <- DEG[,c("SYMBOL","log2FoldChange","change")]
head(gsym.id)
gsym.id <- gsym.id[gsym.id$change!="NOT",]
gsym <- bitr(gsym.id$SYMBOL, #基因名
fromType = "SYMBOL", #从gene symbol
toType = "ENTREZID", #提取ENTREZ ID
OrgDb = "org.Hs.eg.db") #相应物种的包，人是org.Hs.eg.db
head(gsym)
gsym.id <- inner_join(gsym.id,gsym,by="SYMBOL")
head(gsym.id)
dim(gsym.id)
id.fc <- gsym.id[,c(2,4)]
#save(id.fc,file="very_easy_input_H.Rdata")
ego <- enrichGO(gene = id.fc$ENTREZID,
#小鼠用这行
OrgDb = org.Hs.eg.db,
#人类用这行
#OrgDb = org.Hs.eg.db,
#非模式生物用这行，例如玉米
#OrgDb = maize.db,
ont = "BP", #或MF或CC
pAdjustMethod = "BH",
#pvalueCutoff = 0.001,
qvalueCutoff = 0.05)
dim(ego)
#write.csv(ego,"enrichGO_output.csv",quote = F)
#把ENTREZ ID转为gene symbol
egox <- setReadable(ego, 'org.Hs.eg.db', #物种
'ENTREZID')
#把基因倍数信息转成画图所需的格式
geneList <- id.fc$log2FoldChange
names(geneList) <- id.fc$ENTREZID
#画⭕️图
#BiocManager::install("ggnewscale")
library(ggnewscale,lib.loc = "/home/data/vip39/R/x86_64-pc-linux-gnu-library/4.0/")
cnetplot(egox,
foldChange = geneList,
#foldChange = NULL, #不展示倍数
circular = TRUE,
#node_label = FALSE, #如果太多，就不要显示基因名了
showCategory = 5, #显示富集的term数量，默认5
colorEdge = TRUE)
#保存到pdf文件
#ggsave("clusterProfiler_circle.pdf", width = 8, height = 5)
#不画成⭕️，process分开，效果更好呢
cnetplot(egox,
foldChange = geneList,
#foldChange = NULL, #不展示倍数
#circular = TRUE,
#node_label = FALSE, #不显示基因名
showCategory = 4, #显示的富集term数量，默认5
colorEdge = TRUE)
#ggsave("clusterProfiler_not_circle.pdf", width = 8, height = 5)
#读入富集分析结果
#ego <- read.csv("enrichGO_output.csv", header = T)
ego[1,]
go <- data.frame(Category = "BP",
ID = ego$ID,
Term = ego$Description,
Genes = gsub("/", ", ", ego$geneID),
adj_pval = ego$p.adjust)
#基因变化倍数
head(id.fc)
genelist <- data.frame(ID = id.fc$ENTREZID, logFC = id.fc$log2FoldChange)
#把富集分析和倍数整合在一起
library(GOplot,lib.loc = "/home/data/vip39/R/x86_64-pc-linux-gnu-library/4.0/")
circ <- circle_dat(go, genelist)
head(circ)
#根据ENTREZ ID提取gene symbol
id.gsym <- bitr(circ$genes, #基因名
fromType = "ENTREZID", #从ENTREZ ID
toType = "SYMBOL", #提取gene symbol
OrgDb = "org.Hs.eg.db") #相应物种的包
#把circ里的ENTREZ ID换成gene symbol
rownames(id.gsym) <- id.gsym$ENTREZID
circ.gsym <- circ
circ.gsym$genes <- id.gsym[circ$genes,]$SYMBOL
head(circ.gsym)
#参数设置
n = 5 #圈图需要选定term，这里画前面5个
chord <- chord_dat(circ, genelist, go$Term[1:n])
head(chord)
#根据ENTREZ ID提取gene symbol
id.gsym <- bitr(row.names(chord), #基因名
fromType = "ENTREZID", #从ENTREZ ID
toType = "SYMBOL", #提取gene symbol
OrgDb = "org.Hs.eg.db") #相应物种的包
#把chord的列名ENTREZ ID换成gene symbol
rownames(id.gsym) <- id.gsym$ENTREZID
head(id.gsym)
chord.gsym <- chord
row.names(chord.gsym) <- id.gsym[row.names(chord),]$SYMBOL
head(chord.gsym)
GOChord(chord.gsym,
space = 0.02, #基因方块间隙
gene.order = 'logFC',
lfc.col = c('darkgoldenrod1', 'black', 'cyan1'), #自定义变化倍数的颜色
gene.space = 0.25, #基因名跟⭕️的相对距离
gene.size = 3, #基因名字体大小
border.size = 0.1, #中间曲线的黑色边的粗细
process.label = 8) #term字体大小
ggsave("GOChordBP.pdf", width = 12, height = 14)
ggsave("GOChordCC.pdf", width = 12, height = 14)
ggsave("GOChordMF.pdf", width = 12, height = 14)
graph2ppt(file="GOChord_CS2_CS1.pptx")
#定义足够多的颜色，后面从这里选颜色
mycol <- c("#223D6C","#D20A13","#FFD121","#088247","#58CDD9","#7A142C","#5D90BA","#431A3D","#91612D","#6E568C","#E0367A","#D8D155","#64495D","#7CC767")
GOCluster(circ.gsym, go$Term[1:n],
#clust.by = 'logFC', #用变化倍数聚类
clust.by = 'term', #用富集的term聚类
lfc.col = c('darkgoldenrod1', 'black', 'cyan1'), #自定义变化倍数的颜色
lfc.space = 0.1, #倍数跟树间的空隙大小
lfc.width = 1, #变化倍数的⭕️宽度
term.col = mycol[1:n], #自定义term的颜色
term.space = 0.2, #倍数跟term间的空隙大小
term.width = 0.8) #富集term的⭕️宽度
ggsave("GOCluster.pdf", width = 12, height = 14)
graph2ppt(file="GOCluster_CS2_CS1_BP.pptx")
topptx(filename = "GOCluster_CS2_CS1_BP.pptx")
if(!require(paletteer))install.packages("paletteer")
if(!require(scico))install.packages('scico')
if(!require(nord))install.packages('nord')
library(paletteer)
##CC
ego_CC <- enrichGO(gene = id.fc$ENTREZID,
#小鼠用这行
OrgDb = org.Hs.eg.db,
#人类用这行
#OrgDb = org.Hs.eg.db,
#非模式生物用这行，例如玉米
#OrgDb = maize.db,
ont = "CC", #或MF或CC
pAdjustMethod = "BH",
#pvalueCutoff = 0.001,
qvalueCutoff = 0.05)
dim(ego_CC)
#write.csv(ego_CC,"enrichGOCC_output.csv",quote = F)
ego_CC[1,]
goCC <- data.frame(Category = "CC",
ID = ego_CC$ID,
Term = ego_CC$Description,
Genes = gsub("/", ", ", ego_CC$geneID),
adj_pval = ego_CC$p.adjust)
#基因变化倍数
head(id.fc)
genelist <- data.frame(ID = id.fc$ENTREZID, logFC = id.fc$log2FoldChange)
#把富集分析和倍数整合在一起
circ <- circle_dat(goCC, genelist)
head(circ)
#根据ENTREZ ID提取gene symbol
id.gsym <- bitr(circ$genes, #基因名
fromType = "ENTREZID", #从ENTREZ ID
toType = "SYMBOL", #提取gene symbol
OrgDb = "org.Hs.eg.db") #相应物种的包
#把circ里的ENTREZ ID换成gene symbol
rownames(id.gsym) <- id.gsym$ENTREZID
circ.gsym <- circ
circ.gsym$genes <- id.gsym[circ$genes,]$SYMBOL
head(circ.gsym)
#参数设置
n = 5 #圈图需要选定term，这里画前面5个
chord <- chord_dat(circ, genelist, goCC$Term[1:n])
head(chord)
#根据ENTREZ ID提取gene symbol
id.gsym <- bitr(row.names(chord), #基因名
fromType = "ENTREZID", #从ENTREZ ID
toType = "SYMBOL", #提取gene symbol
OrgDb = "org.Hs.eg.db") #相应物种的包
#把chord的列名ENTREZ ID换成gene symbol
rownames(id.gsym) <- id.gsym$ENTREZID
head(id.gsym)
chord.gsym <- chord
row.names(chord.gsym) <- id.gsym[row.names(chord),]$SYMBOL
head(chord.gsym)
#定义足够多的颜色，后面从这里选颜色
mycol <- c("#223D6C","#D20A13","#FFD121","#088247","#58CDD9","#7A142C","#5D90BA","#431A3D","#91612D","#6E568C","#E0367A","#D8D155","#64495D","#7CC767")
GOCluster(circ.gsym, goCC$Term[1:n],
#clust.by = 'logFC', #用变化倍数聚类
clust.by = 'term', #用富集的term聚类
lfc.col = c('darkgoldenrod1', 'black', 'cyan1'), #自定义变化倍数的颜色
lfc.space = 0.1, #倍数跟树间的空隙大小
lfc.width = 1, #变化倍数的⭕️宽度
term.col = paletteer_c("scico::berlin", n = 5), #自定义term的颜色
term.space = 0.2, #倍数跟term间的空隙大小
term.width = 0.8) #富集term的⭕️宽度
ggsave("GOClusterCC.pdf", width = 12, height = 14)
graph2ppt(file="GOCluster_CS2_CS1_CC.pptx")
topptx(filename = "GOCluster_CS2_CS1_CC.pptx")
##MF
ego_MF <- enrichGO(gene = id.fc$ENTREZID,
#小鼠用这行
OrgDb = org.Hs.eg.db,
#人类用这行
#OrgDb = org.Hs.eg.db,
#非模式生物用这行，例如玉米
#OrgDb = maize.db,
ont = "MF", #或MF或MF
pAdjustMethod = "BH",
#pvalueCutoff = 0.001,
qvalueCutoff = 0.05)
dim(ego_MF)
#write.csv(ego_MF,"enrichGOMF_output.csv",quote = F)
ego_MF[1,]
goMF <- data.frame(Category = "MF",
ID = ego_MF$ID,
Term = ego_MF$Description,
Genes = gsub("/", ", ", ego_MF$geneID),
adj_pval = ego_MF$p.adjust)
#基因变化倍数
head(id.fc)
genelist <- data.frame(ID = id.fc$ENTREZID, logFC = id.fc$log2FoldChange)
#把富集分析和倍数整合在一起
circ <- circle_dat(goMF, genelist)
head(circ)
#根据ENTREZ ID提取gene symbol
id.gsym <- bitr(circ$genes, #基因名
fromType = "ENTREZID", #从ENTREZ ID
toType = "SYMBOL", #提取gene symbol
OrgDb = "org.Hs.eg.db") #相应物种的包
#把circ里的ENTREZ ID换成gene symbol
rownames(id.gsym) <- id.gsym$ENTREZID
circ.gsym <- circ
circ.gsym$genes <- id.gsym[circ$genes,]$SYMBOL
head(circ.gsym)
#参数设置
n = 5 #圈图需要选定term，这里画前面5个
chord <- chord_dat(circ, genelist, goMF$Term[1:n])
head(chord)
#根据ENTREZ ID提取gene symbol
id.gsym <- bitr(row.names(chord), #基因名
fromType = "ENTREZID", #从ENTREZ ID
toType = "SYMBOL", #提取gene symbol
OrgDb = "org.Hs.eg.db") #相应物种的包
#把chord的列名ENTREZ ID换成gene symbol
rownames(id.gsym) <- id.gsym$ENTREZID
head(id.gsym)
chord.gsym <- chord
row.names(chord.gsym) <- id.gsym[row.names(chord),]$SYMBOL
head(chord.gsym)
#定义足够多的颜色，后面从这里选颜色
mycol <- c("#223D6C","#D20A13","#FFD121","#088247","#58CDD9","#7A142C","#5D90BA","#431A3D","#91612D","#6E568C","#E0367A","#D8D155","#64495D","#7MF767")
GOCluster(circ.gsym, goMF$Term[1:n],
#clust.by = 'logFC', #用变化倍数聚类
clust.by = 'term', #用富集的term聚类
lfc.col = c('darkgoldenrod1', 'black', 'cyan1'), #自定义变化倍数的颜色
lfc.space = 0.1, #倍数跟树间的空隙大小
lfc.width = 1, #变化倍数的⭕️宽度
term.col = paletteer_d("RColorBrewer::Paired",n=5), #自定义term的颜色
term.space = 0.2, #倍数跟term间的空隙大小
term.width = 0.8) #富集term的⭕️宽度
ggsave("GOClusterMF.pdf", width = 12, height = 14)
graph2ppt(file="GOCluster_C2_C1_MF.pptx")
topptx(filename = "GOCluster_C2_C1_MF.pptx")
####gsva#####
library(msigdbr)
library(dplyr)
library(data.table)
library(GSVA)
library(limma)
library(stringr)
library(ggplot2)
Sys.setenv(LANGUAGE = "en") #显示英文报错信息
options(stringsAsFactors = FALSE) #禁止chr转成factor
# 读入前面生成的通路中的基因列表
(load("~/huitu/FigureYa61GSVA/hallmark.gs.RData")) #保存在当前文件夹
# 读入基因表达矩阵
gsym.expr <- KIRC_mRNA_fpkm
head(gsym.expr)
# 这一句就完成了GSVA分析
gsva_es <- gsva(as.matrix(gsym.expr), gs)
# 预览GSVA分析返回的矩阵
head(gsva_es)
# 把通路的表达量保存到文件
write.csv(gsva_es, "gsva_output.csv", quote = F)