guess_the_plot.Rmd

title: "Comparing data presentations"
author: "Dominik Brilhaus"
date: "2022-08-16"
output: html_document
knitr::opts_chunk$set(echo = TRUE)

if(!"scales" %in% row.names(installed.packages())){install.packages("scales")}
library(tidyverse)

if(!"scales" %in% row.names(installed.packages())){install.packages("scales")}
library(scales)


load("../runs/kallisto_combined/mothertableV3.Rdata")

# View(dfr)
gene_set <- c("AT1G29930", "AT4G23230", "AT1G01120", "AT1G06410", "AT2G25510")

dir.create("../runs/guess_the_plots/", showWarnings = F, recursive = T)


plot_tpm <- subset(dfr, locus %in% gene_set,
                   select = c("locus", grep("_tpm", colnames(dfr), value = T)), drop = T)

plot_tpm <- pivot_longer(plot_tpm, cols = 2:ncol(plot_tpm))
plot_tpm$condition <- gsub("._tpm", "", plot_tpm$name)

p_tpm_point <- ggplot(plot_tpm, aes(x = locus, y = value)) +
  geom_point(aes(col = condition), position = position_dodge(width = 0.5)) +
  theme_classic() + scale_color_brewer(palette = "Dark2") +
  labs(y = "Transcript level [tpm]")

print(p_tpm_point)

pdf(file = "../runs/guess_the_plots/p_tpm_point.pdf", width = 6, height = 6)
print(p_tpm_point)
print(p_tpm_point + labs(y = "") + theme(legend.position = "none"))
dev.off()

plot_tpm_mean <- subset(dfr, locus %in% gene_set,
                   select = c("locus", grep("mean_", colnames(dfr), value = T)), drop = T)

plot_tpm_mean <- pivot_longer(plot_tpm_mean, cols = 2:ncol(plot_tpm_mean))
plot_tpm_mean$condition <- gsub("mean_", "", plot_tpm_mean$name)

p_mean_bar <- ggplot(plot_tpm_mean, aes(x = locus, y = value)) +
  geom_col(aes(fill = condition), position = position_dodge()) +
  theme_classic() + scale_fill_brewer(palette = "Dark2") +
  labs(y = "Transcript level [tpm]") +
  scale_y_continuous(expand = expansion(mult = c(0, .1)))

print(p_mean_bar)

pdf(file = "../runs/guess_the_plots/p_mean_bar.pdf", width = 6, height = 6)
print(p_mean_bar)
print(p_mean_bar + labs(y = "") + theme(legend.position = "none"))
dev.off()


p_mean_bar_log10 <- p_mean_bar +  scale_y_log10(breaks = trans_breaks("log10", function(x) 10^x),
              labels = trans_format("log10", math_format(10^.x)),
              expand = expansion(mult = c(0, .1)))

print(p_mean_bar_log10) + annotation_logticks(sides = "l")

pdf(file = "../runs/guess_the_plots/p_mean_bar_log10.pdf", width = 6, height = 6)
print(p_mean_bar_log10) + annotation_logticks(sides = "l")
print(p_mean_bar_log10 + labs(y = "") + theme(axis.ticks.y = element_blank(), axis.text.y = element_blank()))
dev.off()


p_mean_bar_facet <- p_mean_bar + facet_wrap(~locus, scales = "free") +
  theme(aspect.ratio = 1) +
  theme(axis.text.x = element_blank(),
        axis.ticks.x = element_blank(),
        axis.title.x = element_blank())

print(p_mean_bar_facet)

pdf(file = "../runs/guess_the_plots/p_mean_bar_facet.pdf", width = 6, height = 6)
print(p_mean_bar_facet)
dev.off()


p_mean_heat <-  ggplot(plot_tpm_mean, aes(x = condition, y = locus, fill = value)) +
  geom_point(alpha = 1, size = 12, shape = 22) +
  scale_x_discrete(position = "top") +
  theme_classic() +
  theme(aspect.ratio = length(gene_set), axis.title = element_blank(),
        axis.text.x.top = element_text(angle = 45, hjust = 0),
        axis.line = element_blank(),
        axis.ticks = element_blank()) +
  labs(fill = "Transcript level [tpm]")

p_mean_heat + scale_fill_gradient2(low = "white", high = "#C21F3A")

pdf(file = "../runs/guess_the_plots/p_mean_heat.pdf", width = 6, height = 5)
print(p_mean_heat + scale_fill_gradient2(low = "white", high = "#C21F3A"))
print(p_mean_heat + scale_fill_gradient2(low = "white", high = "#C21F3A") +
        theme(legend.position = "none", axis.text.x.top = element_blank()))
dev.off()


p_mean_heat_log10 <- p_mean_heat + scale_fill_gradient2(low = "white", high = "#C21F3A", trans='log10') +
  labs(fill = "log10(Transcript level [tpm])")


pdf(file = "../runs/guess_the_plots/p_mean_heat_log10.pdf", width = 6, height = 5)
print(p_mean_heat_log10)
print(p_mean_heat_log10 + theme(legend.position = "none"))
dev.off()


plot_logfc <- subset(dfr, locus %in% gene_set,
                   select = c("locus", "log2FC"), drop = T)

p_logfc_bar <- ggplot(plot_logfc, aes(x = locus, y = log2FC)) +
  geom_col(width = 0.5) +
  theme_classic() +
  theme(aspect.ratio = length(gene_set)*0.7, axis.text.x = element_text(angle = 45, hjust = 1)) +
  geom_hline(yintercept = 0) +
  labs(y = "log2-FC (treatment/mock)")


print(p_logfc_bar)

pdf(file = "../runs/guess_the_plots/p_logfc_bar.pdf", width = 6, height = 6)
print(p_logfc_bar)
print(p_logfc_bar + labs(y = ""))
dev.off()


p_logfc_heat <- ggplot(plot_logfc, aes(x = 1, y = locus, fill = log2FC)) +
  scale_fill_gradient2(low = "#377D98", high = "#C21F3A", midpoint = 0) +
  geom_point(alpha = 1, size = 12, shape = 22) +
  theme_classic() +
  theme(aspect.ratio = length(gene_set), axis.title = element_blank(),
        axis.text.x = element_blank(),
        axis.line.x = element_blank(),
        axis.ticks.x = element_blank()) +
  labs(fill = "log2-FC (treatment/mock)")


print(p_logfc_heat)

pdf(file = "../runs/guess_the_plots/p_logfc_heat.pdf", width = 6, height = 5)
print(p_logfc_heat)
print(p_logfc_heat + theme(legend.position = "none"))
dev.off()