R ggplot2: boxes with wilcoxon significance levels and faces. Show only significant comparisons with asterisks

Question

Following this question and for the sake of completeness, I changed the accepted answer and set up the final plot, but I still encounter some important problems.

To summarize, I am making boxplots reflecting the significance of Kruskal-Wallis and comparative comparisons with Wilcoxon.

I want to replace the p numbers with asterisks and show only significant comparisons, reducing the vertical distance to the maximum.

Basically, I want to do this , but with the added face problem, which will ruin everything.

So far I have been working on a very decent MWE, but it still shows problems ...

library(reshape2)
library(ggplot2)
library(gridExtra)
library(tidyverse)
library(data.table)
library(ggsignif)
library(RColorBrewer)

data(iris)
iris$treatment <- rep(c("A","B"), length(iris$Species)/2)
mydf <- melt(iris, measure.vars=names(iris)[1:4])
mydf$treatment <- as.factor(mydf$treatment)
mydf$variable <- factor(mydf$variable, levels=sort(levels(mydf$variable)))
mydf$both <- factor(paste(mydf$treatment, mydf$variable), levels=(unique(paste(mydf$treatment, mydf$variable))))

# Change data to reduce number of statistically significant differences
set.seed(2)
mydf <- mydf %>% mutate(value=rnorm(nrow(mydf)))
##

##FIRST TEST BOTH

#Kruskal-Wallis
addkw <- as.data.frame(mydf %>% group_by(Species) %>%
                       summarize(p.value = kruskal.test(value ~ both)$p.value))
#addkw$p.adjust <- p.adjust(addkw$p.value, "BH")
a <- combn(levels(mydf$both), 2, simplify = FALSE)
#new p.values
pv.final <- data.frame()
for (gr in unique(mydf$Species)){
    for (i in 1:length(a)){
        tis <- a[[i]] #variable pair to test
        as <- subset(mydf, Species==gr & both %in% tis)
        pv <- wilcox.test(value ~ both, data=as)$p.value
        ddd <- data.table(as)
        asm <- as.data.frame(ddd[, list(value=mean(value)), by=list(both=both)])
        asm2 <- dcast(asm, .~both, value.var="value")[,-1]
        pf <- data.frame(group1=paste(tis[1], gr), group2=paste(tis[2], gr), mean.group1=asm2[,1], mean.group2=asm2[,2], FC.1over2=asm2[,1]/asm2[,2], p.value=pv)
        pv.final <- rbind(pv.final, pf)
    }
}
#pv.final$p.adjust <- p.adjust(pv.final$p.value, method="BH")
pv.final$map.signif <- ifelse(pv.final$p.value > 0.05, "", ifelse(pv.final$p.value > 0.01,"*", "**"))

cols <- colorRampPalette(brewer.pal(length(unique(mydf$Species)), "Set1"))
myPal <- cols(length(unique(mydf$Species)))

#Function to get a list of plots to use as "facets" with grid.arrange
plot.list=function(mydf, pv.final, addkw, a, myPal){
    mylist <- list()
    i <- 0
    for (sp in unique(mydf$Species)){
        i <- i+1
        mydf0 <- subset(mydf, Species==sp)
        addkw0 <- subset(addkw, Species==sp)
        pv.final0 <- pv.final[grep(sp, pv.final$group1), ]
        num.signif <- sum(pv.final0$p.value <= 0.05)
        P <- ggplot(mydf0,aes(x=both, y=value)) +
            geom_boxplot(aes(fill=Species)) +
            stat_summary(fun.y=mean, geom="point", shape=5, size=4) +
            facet_grid(~Species, scales="free", space="free_x") +
            scale_fill_manual(values=myPal[i]) + #WHY IS COLOR IGNORED?
            geom_text(data=addkw0, hjust=0, size=4.5, aes(x=0, y=round(max(mydf0$value, na.rm=TRUE)+0.5), label=paste0("KW p=",p.value))) +
            geom_signif(test="wilcox.test", comparisons = a[which(pv.final0$p.value<=0.05)],#I can use "a"here
              map_signif_level = F,            
              vjust=0,
              textsize=4,
              size=0.5,
              step_increase = 0.05)
        if (i==1){
            P <- P + theme(legend.position="none",
                  axis.text.x=element_text(size=20, angle=90, hjust=1),
                  axis.text.y=element_text(size=20),
                  axis.title=element_blank(),
                  strip.text.x=element_text(size=20,face="bold"),
                  strip.text.y=element_text(size=20,face="bold"))
        } else{
            P <- P + theme(legend.position="none",
                  axis.text.x=element_text(size=20, angle=90, hjust=1),
                  axis.text.y=element_blank(),
                  axis.ticks.y=element_blank(),
                  axis.title=element_blank(),
                  strip.text.x=element_text(size=20,face="bold"),
                  strip.text.y=element_text(size=20,face="bold"))
        }
        #WHY USING THE CODE BELOW TO CHANGE NUMBERS TO ASTERISKS I GET ERRORS?
        #P2 <- ggplot_build(P)
        #P2$data[[3]]$annotation <- rep(subset(pv.final0, p.value<=0.05)$map.signif, each=3)
        #P <- plot(ggplot_gtable(P2))
        mylist[[sp]] <- list(num.signif, P)
    }
    return(mylist)
}
p.list <- plot.list(mydf, pv.final, addkw, a, myPal)
y.rng <- range(mydf$value)
# Get the highest number of significant p-values across all three "facets"
height.factor <- 0.3
max.signif <- max(sapply(p.list, function(x) x[[1]]))
# Lay out the three plots as facets (one for each Species), but adjust so that y-range is same for each facet. Top of y-range is adjusted using max_signif.
png(filename="test.png", height=800, width=1200)
grid.arrange(grobs=lapply(p.list, function(x) x[[2]] +
             scale_y_continuous(limits=c(y.rng[1], y.rng[2] + height.factor*max.signif))), 
             ncol=length(unique(mydf$Species)), top="Random title", left="Value") #HOW TO CHANGE THE SIZE OF THE TITLE AND THE Y AXIS TEXT?
             #HOW TO ADD A COMMON LEGEND?
dev.off()

He creates the following chart:

, , :

1 - -

2 - , ,

():

, :

1 -

2 -

... :

3 -

4 - -

5 - ( ) y

, , , , "CNb" "pv.final".

; "", ""... 6 "" ( ), ...

MWE:

##NOW TEST MEASURE, TO GET VERTICAL AND HORIZONTAL FACETS

addkw <- as.data.frame(mydf %>% group_by(treatment, Species) %>%
                       summarize(p.value = kruskal.test(value ~ variable)$p.value))
#addkw$p.adjust <- p.adjust(addkw$p.value, "BH")
a <- combn(levels(mydf$variable), 2, simplify = FALSE)
#new p.values
pv.final <- data.frame()
for (tr in levels(mydf$treatment)){
    for (gr in levels(mydf$Species)){
        for (i in 1:length(a)){
            tis <- a[[i]] #variable pair to test
            as <- subset(mydf, treatment==tr & Species==gr & variable %in% tis)
            pv <- wilcox.test(value ~ variable, data=as)$p.value
            ddd <- data.table(as)
            asm <- as.data.frame(ddd[, list(value=mean(value, na.rm=T)), by=list(variable=variable)])
            asm2 <- dcast(asm, .~variable, value.var="value")[,-1]
            pf <- data.frame(group1=paste(tis[1], gr, tr), group2=paste(tis[2], gr, tr), mean.group1=asm2[,1], mean.group2=asm2[,2], FC.1over2=asm2[,1]/asm2[,2], p.value=pv)
            pv.final <- rbind(pv.final, pf)
        }
    }
}
#pv.final$p.adjust <- p.adjust(pv.final$p.value, method="BH")
# set signif level
pv.final$map.signif <- ifelse(pv.final$p.value > 0.05, "", ifelse(pv.final$p.value > 0.01,"*", "**"))
plot.list2=function(mydf, pv.final, addkw, a, myPal){
    mylist <- list()
    i <- 0
    for (sp in unique(mydf$Species)){
    for (tr in unique(mydf$treatment)){
        i <- i+1
        mydf0 <- subset(mydf, Species==sp & treatment==tr)
        addkw0 <- subset(addkw, Species==sp & treatment==tr)
        pv.final0 <- pv.final[grep(paste(sp,tr), pv.final$group1), ]
        num.signif <- sum(pv.final0$p.value <= 0.05)
        P <- ggplot(mydf0,aes(x=variable, y=value)) +
            geom_boxplot(aes(fill=Species)) +
            stat_summary(fun.y=mean, geom="point", shape=5, size=4) +
            facet_grid(treatment~Species, scales="free", space="free_x") +
            scale_fill_manual(values=myPal[i]) + #WHY IS COLOR IGNORED?
            geom_text(data=addkw0, hjust=0, size=4.5, aes(x=0, y=round(max(mydf0$value, na.rm=TRUE)+0.5), label=paste0("KW p=",p.value))) +
            geom_signif(test="wilcox.test", comparisons = a[which(pv.final0$p.value<=0.05)],#I can use "a"here
              map_signif_level = F,            
              vjust=0,
              textsize=4,
              size=0.5,
              step_increase = 0.05)
        if (i==1){
            P <- P + theme(legend.position="none",
                  axis.text.x=element_blank(),
                  axis.text.y=element_text(size=20),
                  axis.title=element_blank(),
                  axis.ticks.x=element_blank(),
                  strip.text.x=element_text(size=20,face="bold"),
                  strip.text.y=element_text(size=20,face="bold"))
        }
        if (i==4){
            P <- P + theme(legend.position="none",
                  axis.text.x=element_text(size=20, angle=90, hjust=1),
                  axis.text.y=element_text(size=20),
                  axis.title=element_blank(),
                  strip.text.x=element_text(size=20,face="bold"),
                  strip.text.y=element_text(size=20,face="bold"))
        }
        if ((i==2)|(i==3)){
            P <- P + theme(legend.position="none",
                  axis.text.x=element_blank(),
                  axis.text.y=element_blank(),
                  axis.title=element_blank(),
                  axis.ticks.x=element_blank(),
                  axis.ticks.y=element_blank(),
                  strip.text.x=element_text(size=20,face="bold"),
                  strip.text.y=element_text(size=20,face="bold"))
        }
        if ((i==5)|(i==6)){
            P <- P + theme(legend.position="none",
                  axis.text.x=element_text(size=20, angle=90, hjust=1),
                  axis.text.y=element_blank(),
                  #axis.ticks.y=element_blank(), #WHY SPECIFYING THIS GIVES ERROR?
                  axis.title=element_blank(),
                  axis.ticks.y=element_blank(),
                  strip.text.x=element_text(size=20,face="bold"),
                  strip.text.y=element_text(size=20,face="bold"))
        }
        #WHY USING THE CODE BELOW TO CHANGE NUMBERS TO ASTERISKS I GET ERRORS?
        #P2 <- ggplot_build(P)
        #P2$data[[3]]$annotation <- rep(subset(pv.final0, p.value<=0.05)$map.signif, each=3)
        #P <- plot(ggplot_gtable(P2))
        sptr <- paste(sp,tr)
        mylist[[sptr]] <- list(num.signif, P)
    }
    }
    return(mylist)
}
p.list2 <- plot.list2(mydf, pv.final, addkw, a, myPal)
y.rng <- range(mydf$value)
# Get the highest number of significant p-values across all three "facets"
height.factor <- 0.5
max.signif <- max(sapply(p.list2, function(x) x[[1]]))
# Lay out the three plots as facets (one for each Species), but adjust so that y-range is same for each facet. Top of y-range is adjusted using max_signif.
png(filename="test2.png", height=800, width=1200)
grid.arrange(grobs=lapply(p.list2, function(x) x[[2]] +
             scale_y_continuous(limits=c(y.rng[1], y.rng[2] + height.factor*max.signif))), 
             ncol=length(unique(mydf$Species)), top="Random title", left="Value") #HOW TO CHANGE THE SIZE OF THE TITLE AND THE Y AXIS TEXT?
             #HOW TO ADD A COMMON LEGEND?
dev.off()

:

, , - .

, . , , ! !!

Answer 1

. , , . tidyverse. , . kruskal wallis, ggsignif. p.values ​​ geom_signif. , .

1-

2-

... :

3-

4- - ,

5- ( ) y

library(tidyverse)
library(ggsignif)

# 1. your data
set.seed(2)
df <- as.tbl(iris) %>% 
  mutate(treatment=rep(c("A","B"), length(iris$Species)/2)) %>% 
  gather(key, value, -Species, -treatment) %>% 
  mutate(value=rnorm(n())) %>% 
  mutate(key=factor(key, levels=unique(key))) %>% 
  mutate(both=interaction(treatment, key, sep = " "))

# 2. Kruskal test
KW <- df %>% 
  group_by(Species) %>%
  summarise(p=round(kruskal.test(value ~ both)$p.value,2),
            y=min(value),
            x=1) %>% 
  mutate(y=min(y))

# 3. Plot  
P <- df %>% 
ggplot(aes(x=both, y=value)) + 
  geom_boxplot(aes(fill=Species)) + 
  facet_grid(~Species) +
  ylim(-3,7)+
  theme(axis.text.x = element_text(angle=45, hjust=1)) +
  geom_signif(comparisons = combn(levels(df$both),2,simplify = F),
              map_signif_level = T) +
  stat_summary(fun.y=mean, geom="point", shape=5, size=4) +
  xlab("") +
  geom_text(data=KW,aes(x, y=y, label=paste0("KW p=",p)),hjust=0) +
  ggtitle("Plot") + ylab("This is my own y-lab")

# 4. remove not significant values and add step increase
P_new <- ggplot_build(P)
P_new$data[[2]] <- P_new$data[[2]] %>% 
  filter(annotation != "NS.") %>% 
  group_by(PANEL) %>%
  mutate(index=(as.numeric(group[drop=T])-1)*0.5) %>% 
  mutate(y=y+index,
         yend=yend+index) %>% 
  select(-index) %>% 
  as.data.frame()
# the final plot  
plot(ggplot_gtable(P_new))

,

# --------------------
# 5. Kruskal
KW <- df %>% 
  group_by(Species, treatment) %>%
  summarise(p=round(kruskal.test(value ~ both)$p.value,2),
            y=min(value),
            x=1) %>% 
  ungroup() %>% 
  mutate(y=min(y))


# 6. Plot with two facets  
P <- df %>% 
  ggplot(aes(x=key, y=value)) + 
  geom_boxplot(aes(fill=Species)) + 
  facet_grid(treatment~Species) +
  ylim(-5,7)+
  theme(axis.text.x = element_text(angle=45, hjust=1)) +
  geom_signif(comparisons = combn(levels(df$key),2,simplify = F),
              map_signif_level = T) +
  stat_summary(fun.y=mean, geom="point", shape=5, size=4) +
  xlab("") +
  geom_text(data=KW,aes(x, y=y, label=paste0("KW p=",p)),hjust=0) +
  ggtitle("Plot") + ylab("This is my own y-lab")

# 7. remove not significant values and add step increase
P_new <- ggplot_build(P)
P_new$data[[2]] <- P_new$data[[2]] %>% 
  filter(annotation != "NS.") %>% 
  group_by(PANEL) %>%
  mutate(index=(as.numeric(group[drop=T])-1)*0.5) %>% 
  mutate(y=y+index,
         yend=yend+index) %>% 
  select(-index) %>% 
  as.data.frame()
# the final plot  
plot(ggplot_gtable(P_new))

.

p.adjust, geom_signif().

wilcox.test.BH.adjusted <- function(x,y,n){
  tmp <- wilcox.test(x,y)
  tmp$p.value <- p.adjust(tmp$p.value, n = n,method = "BH")
  tmp
}  

geom_signif(comparisons = combn(levels(df$both),2,simplify = F),
          map_signif_level = T, test = "wilcox.test.BH.adjusted", 
          test.args = list(n=8))

, , . n . 8. .

Answer 2

ggplots , 1 . ggplot , . print. Re point 2, , . plot.list:

plot.list=function(mydf, pv.final, addkw, a, myPal){
    mylist <- list()
    i <- 0
    for (sp in unique(mydf$Species)){
        i <- i+1
        mydf0 <- subset(mydf, Species==sp)
        addkw0 <- subset(addkw, Species==sp)
        pv.final0 <- pv.final[grep(sp, pv.final$group1), ]
        num.signif <- sum(pv.final0$p.value <= 0.05)
        P <- ggplot(mydf0,aes(x=both, y=value)) +
            geom_boxplot(aes(fill=Species)) +
            stat_summary(fun.y=mean, geom="point", shape=5, size=4) +
            facet_grid(~Species, scales="free", space="free_x") +
            scale_fill_manual(values=myPal[i]) +
            geom_text(data=addkw0, hjust=0, size=4.5, aes(x=0, y=round(max(mydf0$value, na.rm=TRUE)+0.5), label=paste0("KW p=",p.value))) +
            geom_signif(test="wilcox.test", comparisons = a[which(pv.final0$p.value<=0.05)],#I can use "a"here
                        map_signif_level = F,            
                        vjust=0,
                        textsize=4,
                        size=0.5,
                        step_increase = 0.05)
        if (i==1){
            P <- P + theme(legend.position="none",
                           axis.text.x=element_text(size=20, angle=90, hjust=1),
                           axis.text.y=element_text(size=20),
                           axis.title=element_blank(),
                           strip.text.x=element_text(size=20,face="bold"),
                           strip.text.y=element_text(size=20,face="bold"))
        } else{
            P <- P + theme(legend.position="none",
                           axis.text.x=element_text(size=20, angle=90, hjust=1),
                           axis.text.y=element_blank(),
                           axis.ticks.y=element_blank(),
                           axis.title=element_blank(),
                           strip.text.x=element_text(size=20,face="bold"),
                           strip.text.y=element_text(size=20,face="bold"))
        }
        P2 <- ggplot_build(P)
        P2$data[[4]]$annotation <- rep(subset(pv.final0, p.value<=0.05)$map.signif, each=3)
        P <- ggplot_gtable(P2)
        mylist[[sp]] <- list(num.signif, P)
    }
    return(mylist)
}

, ggplot, ggplot_build/ggplot_gtable, . , plot.list. ,

grid.arrange(grobs=lapply(p.list, function(x) x[[2]]), 
             ncol=length(unique(mydf$Species)), top="Random title", left="Value")

, , , .