1 Import and prepare for ggplot2

The data was manually curated to fix redundancy errors and mismatches and turned into long-format using Excel

defo.long <- read.csv("protomes.ggplot/final.proteome.defo.csv")
diel.long <- read.csv("protomes.ggplot/final.proteome.diel.csv")
prot.long <- rbind(defo.long,diel.long)

print(paste(nrow(defo.long),"proteins were detected in the DEFO proteome"))
## [1] "1790 proteins were detected in the DEFO proteome"
print(paste(nrow(diel.long),"proteins were detected in the DIEL proteome"))
## [1] "793 proteins were detected in the DIEL proteome"
datatable(prot.long)

# Preparing a mini-table for only the mec genes

mec.mini <- prot.long[prot.long$Class == "Mec",]
write.csv(mec.mini,"mec.proteome.table.csv",row.names = F)

datatable(mec.mini)

2 Plotting

library(ggplot2)
library(scales)
library(plyr)

df = prot.long
df = df[complete.cases(df),]
df$Class <- factor(df$Class, levels=c("other","Mec"))
df <- df[order(df$Class),]

theme_set(theme_minimal())
plot.qpcr <- ggplot(df, aes(x=Genome, y=Average)) +
  geom_jitter(size = 1, aes(color = Class, shape=Class ), 
              position = position_jitter(width=c(0.1,.2),seed=23),
              alpha = 0.6) +
  scale_color_manual(values=c("#c7c7c7","#ff0000" )) +
  stat_boxplot(geom ="errorbar", width = 0.25) + 
  geom_boxplot(outlier.alpha = 0, alpha = .1, width = 0.5) +
  stat_summary(fun.y=mean, colour="black", geom="point", 
               shape=21, fill = "white", size=2,show_guide = FALSE) +
  labs(y="Relative abundance", 
       x="Genome") + guides(color = guide_legend(override.aes = list(size=5))) + 
  labs(color='remove') +
  ylim(0,45) 
ggsave(file="protomes.ggplot/prot.dodge.box.svg", plot=plot.qpcr, width=10, height=8)
plot(plot.qpcr)

These tables are imported into Adobe Illustrator for clean-up and annotation