load("F:/Bioinfor_project/Breast/AS_research/AS/result/hubgene.Rdata")
mydata<-data
head(data)## ID group CCL14 HBA1 CCL16 TUBB3 PAM50 Os_time
## 1 TCGA.A1.A0SK.01 TNBC 3.372704 0.000000 0.000000 5.936486 Basal 967
## 2 TCGA.A1.A0SP.01 TNBC 4.970021 3.394930 0.000000 6.001432 Basal 584
## 3 TCGA.A2.A04U.01 TNBC 4.766927 0.000000 0.000000 5.043662 Basal 2654
## 4 TCGA.A2.A0CM.01 TNBC 4.192953 3.738738 2.842951 5.127705 Basal 754
## 5 TCGA.A2.A0D0.01 TNBC 0.000000 0.000000 0.000000 5.653455 Basal 2048
## 6 TCGA.A2.A0D2.01 TNBC 5.338654 0.000000 4.069236 6.043691 Basal 1027
## OS_event RFS_time RFS_event age ER PR gender HER2
## 1 1 NA NA 54 Negative Negative FEMALE Negative
## 2 0 NA NA 40 Negative Negative FEMALE Negative
## 3 0 NA NA 47 Negative Negative FEMALE Negative
## 4 1 NA NA 40 Negative Negative FEMALE Negative
## 5 0 2048 0 60 Negative Negative FEMALE Negative
## 6 0 1027 0 45 Negative Negative FEMALE Negative
## Margin_status Node M_stage N_stage T_stage Pathologic stage
## 1 Positive 0 M0 N0 T2 Stage_IIA
## 2 Negative 0 M0 N0 T2 Stage_IIA
## 3 Negative 0 M0 N0 T2 Stage_IIA
## 4 Negative 0 M0 N0 T2 Stage_IIA
## 5 Negative 0 M0 N0 T2 Stage_IIA
## 6 Negative 0 M0 N0 T2 Stage_IIArequire(table1)## Loading required package: table1## Warning: package 'table1' was built under R version 3.6.1##
## Attaching package: 'table1'## The following objects are masked from 'package:base':
##
## units, units<-## 分组变量
mydata$CCL16<-factor(ifelse((mydata$CCL16)>median(mydata$CCL16),"high","low"),labels=c("CCL16 high","CCL16 low"))
## 分类变量标签调整
mydata$gender<-factor(mydata$gender,levels=c("FEMALE","MALE"),labels =c("female","male"))
##改变变量标签
## 更换标签的函数
label(mydata$age)<-"Age"
label(mydata$gender)<-"Gender"
label(mydata$T_stage)<-"T stage"
label(mydata$N_stage)<-"N stage"
label(mydata$M_stage)<-"M stage"
label(mydata$group)<-"Group"
##给连续变量指定单位
units(mydata$age)<-"years"
## 默认版
table1(~gender+age+group+T_stage+N_stage+M_stage|CCL16,data = mydata,overall = "Total")| CCL16 high (n=114) |
CCL16 low (n=114) |
Total (n=228) |
|
|---|---|---|---|
| Gender | |||
| female | 113 (99.1%) | 114 (100%) | 227 (99.6%) |
| male | 1 (0.9%) | 0 (0%) | 1 (0.4%) |
| Age (years) | |||
| Mean (SD) | 57.2 (14.4) | 54.8 (12.1) | 56.0 (13.3) |
| Median [Min, Max] | 56.0 [30.0, 90.0] | 54.0 [29.0, 90.0] | 55.0 [29.0, 90.0] |
| Group | |||
| Normal | 103 (90.4%) | 10 (8.8%) | 113 (49.6%) |
| TNBC | 11 (9.6%) | 104 (91.2%) | 115 (50.4%) |
| T stage | |||
| T1 | 29 (25.4%) | 26 (22.8%) | 55 (24.1%) |
| T2 | 65 (57.0%) | 73 (64.0%) | 138 (60.5%) |
| T3 | 11 (9.6%) | 13 (11.4%) | 24 (10.5%) |
| T4 | 9 (7.9%) | 2 (1.8%) | 11 (4.8%) |
| TX | 0 (0%) | 0 (0%) | 0 (0%) |
| N stage | |||
| N0 | 50 (43.9%) | 69 (60.5%) | 119 (52.2%) |
| N1 | 45 (39.5%) | 29 (25.4%) | 74 (32.5%) |
| N2 | 13 (11.4%) | 11 (9.6%) | 24 (10.5%) |
| N3 | 3 (2.6%) | 5 (4.4%) | 8 (3.5%) |
| NX | 3 (2.6%) | 0 (0%) | 3 (1.3%) |
| M stage | |||
| M0 | 103 (90.4%) | 99 (86.8%) | 202 (88.6%) |
| M1 | 2 (1.8%) | 2 (1.8%) | 4 (1.8%) |
| MX | 9 (7.9%) | 13 (11.4%) | 22 (9.6%) |
require(dplyr)## Loading required package: dplyr## Warning: package 'dplyr' was built under R version 3.6.1##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionload("F:/Bioinfor_project/Breast/AS_research/AS/result/hubgene.Rdata")
mydata<-data
## 数据清洗
mydata<-mydata %>%
filter(group=="TNBC") #%>%
#filter(M_stage!="MX") %>%
#filter(N_stage!="NX") %>%
#filter(T_stage!="TX")
dim(mydata)## [1] 115 22head(mydata)## # A tibble: 6 x 22
## ID group CCL14 HBA1 CCL16 TUBB3 PAM50 Os_time OS_event RFS_time
## <chr> <chr> <dbl> <dbl> <dbl> <dbl> <fct> <int> <int> <int>
## 1 TCGA~ TNBC 3.37 0 0 5.94 Basal 967 1 NA
## 2 TCGA~ TNBC 4.97 3.39 0 6.00 Basal 584 0 NA
## 3 TCGA~ TNBC 4.77 0 0 5.04 Basal 2654 0 NA
## 4 TCGA~ TNBC 4.19 3.74 2.84 5.13 Basal 754 1 NA
## 5 TCGA~ TNBC 0 0 0 5.65 Basal 2048 0 2048
## 6 TCGA~ TNBC 5.34 0 4.07 6.04 Basal 1027 0 1027
## # ... with 12 more variables: RFS_event <int>, age <int>, ER <fct>,
## # PR <fct>, gender <fct>, HER2 <fct>, Margin_status <fct>, Node <int>,
## # M_stage <fct>, N_stage <fct>, T_stage <fct>, `Pathologic stage` <fct>## 数据清洗调整标签
##
mydata<-within(mydata,{
T_stage<-factor(T_stage,levels=c("T1","T2","T3","T4","TX"),labels = c("T1/T2","T1/T2","T3/T4","T3/T4","TX"))
N_stage<-factor(N_stage,levels=c("N0","N1","N2","N3","NX"),labels = c("N0/N1","N0/N1","N2/N3","N2/N3","NX"))
M_stage<-factor(M_stage,levels=c("M0","M1","MX"), labels = c("M0","M1","MX"))
age<- factor(ifelse(age>=median(age),">=55","<55"),labels = c(">=55","<55"))
gender<-factor(gender,levels=c("FEMALE","MALE"),labels = c("female","male"))
})
## 分组变量
mydata$CCL16<-factor(ifelse((mydata$CCL16)>median(mydata$CCL16),"high","low"),labels=c("CCL16 high","CCL16 low"))
## 左侧标签名调整
labels <- list(
variables=list(gender="Gender",
age="Age (years)",
#group="Group",
T_stage="T stage",
N_stage="N stage",
M_stage="M stage"),
groups=list("", "Expression"))
## 设置短横线亚组
strata <- c(list(Total=mydata), split(mydata, mydata$CCL16))
## 渲染风格
my.render.cont <- function(x) {
with(stats.apply.rounding(stats.default(x), digits=2), c("",
"Mean (SD)"=sprintf("%s (± %s)", MEAN, SD)))
}
my.render.cat <- function(x) {
c("", sapply(stats.default(x), function(y) with(y,
sprintf("%d (%0.0f %%)", FREQ, PCT))))
}
##
## 绘制三线表
table1(strata, labels, groupspan=c(1, 2),
render.continuous=my.render.cont, render.categorical=my.render.cat,
topclass="Rtable1-zebra")Expression |
|||
|---|---|---|---|
| Total (n=115) |
CCL16 high (n=57) |
CCL16 low (n=58) |
|
| Gender | |||
| female | 115 (100 %) | 57 (100 %) | 58 (100 %) |
| male | 0 (0 %) | 0 (0 %) | 0 (0 %) |
| Age (years) | |||
| >=55 | 57 (50 %) | 30 (53 %) | 27 (47 %) |
| <55 | 58 (50 %) | 27 (47 %) | 31 (53 %) |
| T stage | |||
| T1/T2 | 99 (86 %) | 47 (82 %) | 52 (90 %) |
| T3/T4 | 16 (14 %) | 10 (18 %) | 6 (10 %) |
| TX | 0 (0 %) | 0 (0 %) | 0 (0 %) |
| N stage | |||
| N0/N1 | 99 (86 %) | 48 (84 %) | 51 (88 %) |
| N2/N3 | 16 (14 %) | 9 (16 %) | 7 (12 %) |
| NX | 0 (0 %) | 0 (0 %) | 0 (0 %) |
| M stage | |||
| M0 | 98 (85 %) | 48 (84 %) | 50 (86 %) |
| M1 | 2 (2 %) | 2 (4 %) | 0 (0 %) |
| MX | 15 (13 %) | 7 (12 %) | 8 (14 %) |
## 然后复制到word中即可require(dplyr)
load("F:/Bioinfor_project/Breast/AS_research/AS/result/hubgene.Rdata")
mydata<-data
## 数据清洗
mydata<-mydata %>%
filter(group=="TNBC") %>%
filter(M_stage!="MX") %>%
filter(N_stage!="NX") %>%
filter(T_stage!="TX")
dim(mydata)## [1] 100 22head(mydata)## # A tibble: 6 x 22
## ID group CCL14 HBA1 CCL16 TUBB3 PAM50 Os_time OS_event RFS_time
## <chr> <chr> <dbl> <dbl> <dbl> <dbl> <fct> <int> <int> <int>
## 1 TCGA~ TNBC 3.37 0 0 5.94 Basal 967 1 NA
## 2 TCGA~ TNBC 4.97 3.39 0 6.00 Basal 584 0 NA
## 3 TCGA~ TNBC 4.77 0 0 5.04 Basal 2654 0 NA
## 4 TCGA~ TNBC 4.19 3.74 2.84 5.13 Basal 754 1 NA
## 5 TCGA~ TNBC 0 0 0 5.65 Basal 2048 0 2048
## 6 TCGA~ TNBC 5.34 0 4.07 6.04 Basal 1027 0 1027
## # ... with 12 more variables: RFS_event <int>, age <int>, ER <fct>,
## # PR <fct>, gender <fct>, HER2 <fct>, Margin_status <fct>, Node <int>,
## # M_stage <fct>, N_stage <fct>, T_stage <fct>, `Pathologic stage` <fct>## 数据清洗调整标签
##
mydata<-within(mydata,{
T_stage<-factor(T_stage,levels=c("T1","T2","T3","T4"),labels = c("T1/T2","T1/T2","T3/T4","T3/T4"))
N_stage<-factor(N_stage,levels=c("N0","N1","N2","N3"),labels = c("N0/N1","N0/N1","N2/N3","N2/N3"))
M_stage<-factor(M_stage,levels=c("M0","M1"), labels = c("M0","M1"))
age<- factor(ifelse(age>=median(age),">=55","<55"),labels = c(">=55","<55"))
gender<-factor(gender,levels=c("FEMALE","MALE"),labels = c("female","male"))
})
## 需要重新构建分组变量
mydata$CCL16<-factor(ifelse((mydata$CCL16)>median(mydata$CCL16),"high","low"),
levels = c("high","low","P-value"),
labels=c("CCL16 high","CCL16 low","P-value"))
## 左侧标签名调整
labels <- list(
variables=list(gender="Gender",
age="Age (years)",
#group="Group",
T_stage="T stage",
N_stage="N stage",
M_stage="M stage"),
groups=list("", "Expression",""))## 标题栏短横线
## 设置短横线亚组
strata <- c(list(Total=mydata), split(mydata, mydata$CCL16))
### 共有三处变量需要修改
rndr <- function(x, name, ...) {
if (length(x) == 0) {
y <- mydata[[name]]##修改mydata
s <- rep("", length(render.default(x=y, name=name, ...)))
if (is.numeric(y)) {
p <- t.test(y ~ mydata$CCL16)$p.value##修改mydata
} else {
p <- chisq.test(table(y, droplevels(mydata$CCL16)))$p.value###修改mydata
}
s[2] <- sub("<", "<", format.pval(p, digits=3, eps=0.001))
s
} else {
render.default(x=x, name=name, ...)
}
}
rndr.strat <- function(label, n, ...) {
ifelse(n==0, label, render.strat.default(label, n, ...))
}
############
## 绘制三线表
table1(strata, labels, groupspan=c(1,2,1),droplevels = F,
render=rndr, render.strat=rndr.strat,
topclass="Rtable1-zebra") ## Warning in chisq.test(table(y, droplevels(mydata$CCL16))): Chi-squared
## approximation may be incorrect
## Warning in chisq.test(table(y, droplevels(mydata$CCL16))): Chi-squared
## approximation may be incorrectExpression |
||||
|---|---|---|---|---|
| Total (n=100) |
CCL16 high (n=50) |
CCL16 low (n=50) |
P-value | |
| Gender | ||||
| female | 100 (100%) | 50 (100%) | 50 (100%) | NA |
| male | 0 (0%) | 0 (0%) | 0 (0%) | |
| Age (years) | ||||
| >=55 | 49 (49.0%) | 27 (54.0%) | 22 (44.0%) | 0.424 |
| <55 | 51 (51.0%) | 23 (46.0%) | 28 (56.0%) | |
| T stage | ||||
| T1/T2 | 90 (90.0%) | 42 (84.0%) | 48 (96.0%) | 0.0956 |
| T3/T4 | 10 (10.0%) | 8 (16.0%) | 2 (4.0%) | |
| N stage | ||||
| N0/N1 | 87 (87.0%) | 41 (82.0%) | 46 (92.0%) | 0.234 |
| N2/N3 | 13 (13.0%) | 9 (18.0%) | 4 (8.0%) | |
| M stage | ||||
| M0 | 98 (98.0%) | 48 (96.0%) | 50 (100%) | 0.475 |
| M1 | 2 (2.0%) | 2 (4.0%) | 0 (0%) | |