R Notebook

This is an R Markdown Notebook. When you execute code within the notebook, the results appear beneath the code.

Try executing this chunk by clicking the Run button within the chunk or by placing your cursor inside it and pressing Ctrl+Shift+Enter.

getwd()

## [1] "C:/Users/Julkowska Lab/Desktop/R codes by Maryam/20240820_satistics_DUF247_eLife_revision"

list.files(pattern=".csv")

## [1] "calculateWC-DUF247-5-soil-grown.csv"  
## [2] "calculateWC-DUF247-5-soil-grownV2.csv"
## [3] "DUF150-expression-in-col-only.csv"    
## [4] "DUF247-expression-in-col-only.csv"

all_data <- read.csv("calculateWC-DUF247-5-soil-grownV2.csv")
all_data

colnames(all_data) <- gsub("ï..", "", colnames(all_data))
all_data

all_data$All.ID<-paste(all_data$Genotype,all_data$Condition,sep="_")
all_data

library(ggplot2)
library(ggpubr)
library(multcompView)

## Warning: package 'multcompView' was built under R version 4.3.2

aov(WC.percentage ~ All.ID, data = all_data)

## Call:
##    aov(formula = WC.percentage ~ All.ID, data = all_data)
## 
## Terms:
##                   All.ID Residuals
## Sum of Squares   16.3441  311.1758
## Deg. of Freedom        5        44
## 
## Residual standard error: 2.659357
## Estimated effects may be unbalanced

Output <- TukeyHSD(aov(WC.percentage ~ All.ID, data = all_data))
Output

##   Tukey multiple comparisons of means
##     95% family-wise confidence level
## 
## Fit: aov(formula = WC.percentage ~ All.ID, data = all_data)
## 
## $All.ID
##                                        diff       lwr      upr     p adj
## col_EarlyStress-col_ctrl         0.61019925 -3.350812 4.571211 0.9972785
## col_LateStress-col_ctrl         -0.16708234 -4.128094 3.793929 0.9999953
## duf_ctrl-col_ctrl                1.16984650 -2.587899 4.927592 0.9372679
## duf_EarlyStress-col_ctrl        -0.48483586 -4.445847 3.476175 0.9990965
## duf_LateStress-col_ctrl         -0.04071832 -4.001730 3.920293 1.0000000
## col_LateStress-col_EarlyStress  -0.77728159 -4.738293 3.183730 0.9915644
## duf_ctrl-col_EarlyStress         0.55964725 -3.198098 4.317392 0.9976824
## duf_EarlyStress-col_EarlyStress -1.09503511 -5.056046 2.865976 0.9615704
## duf_LateStress-col_EarlyStress  -0.65091757 -4.611929 3.310094 0.9963064
## duf_ctrl-col_LateStress          1.33692884 -2.420816 5.094674 0.8944080
## duf_EarlyStress-col_LateStress  -0.31775352 -4.278765 3.643258 0.9998856
## duf_LateStress-col_LateStress    0.12636402 -3.834647 4.087375 0.9999988
## duf_EarlyStress-duf_ctrl        -1.65468235 -5.412428 2.103063 0.7770360
## duf_LateStress-duf_ctrl         -1.21056482 -4.968310 2.547180 0.9280756
## duf_LateStress-duf_EarlyStress   0.44411754 -3.516894 4.405129 0.9994097

P7 = Output$All.ID[,'p adj']
stat.test<- multcompLetters(P7)
stat.test

## $Letters
## col_EarlyStress  col_LateStress        duf_ctrl duf_EarlyStress  duf_LateStress 
##             "a"             "a"             "a"             "a"             "a" 
##        col_ctrl 
##             "a" 
## 
## $LetterMatrix
##                    a
## col_EarlyStress TRUE
## col_LateStress  TRUE
## duf_ctrl        TRUE
## duf_EarlyStress TRUE
## duf_LateStress  TRUE
## col_ctrl        TRUE

test <- as.data.frame(stat.test$Letters)
test$group1 <- rownames(test)
test$group2 <- rownames(test)
colnames(test)[1] <- "Tukey"
test

test$info <- strsplit(test$group1, "_")
test$info[[1]][2]

## [1] "EarlyStress"

test$info[[1]][3]

## [1] NA

test$Genotype <- "none"
test$Condition<- "none"
test

for(i in 1:nrow(test)){
  test$Genotype[i] <- test$info[[i]][1]
  test$Condition[i] <- test$info[[i]][2]
  
}

test2 <- test[,c(5:6,1)]
test2$group1 <- test2$Genotype
test2$group2 <- test2$Genotype

all_data

all_data$Condition <- factor(all_data$Condition, levels = c("ctrl", "EarlyStress", "LateStress"))

WC_soil_plants <- ggplot(data = all_data, mapping = aes(x = Genotype, y = WC.percentage, colour = Genotype)) 
WC_soil_plants <- WC_soil_plants + geom_boxplot(alpha=0.2) + geom_jitter(width=0.1,alpha=0.2)
WC_soil_plants <- WC_soil_plants + facet_grid(~Condition, scales = "free_y")
WC_soil_plants <- WC_soil_plants + stat_summary(fun=mean, geom="point", shape=95, size=6, color="black", fill="black")
WC_soil_plants <- WC_soil_plants + scale_color_manual(values = c("blue","red"))
WC_soil_plants <- WC_soil_plants + ylab("Plant Water Content %") + xlab("")+stat_pvalue_manual(test2, label = "Tukey", y.position = 1)
WC_soil_plants <- WC_soil_plants + theme(axis.text.x = element_text(angle=90, hjust=0.9, vjust=0.5))
WC_soil_plants <- WC_soil_plants + rremove("legend")
WC_soil_plants

library(cowplot)

## 
## Attaching package: 'cowplot'

## The following object is masked from 'package:ggpubr':
## 
##     get_legend

pdf("Plants-WC-soil-grown.pdf", height = 5, width = 12)
plot_grid(WC_soil_plants, ncol=2,
          align = "hv", labels=c("AUTO"), 
          label_size = 24)
dev.off()

## png 
##   2