Violin Plot for TCGA Data

library(ggplot2)
library(dplyr)
library(forcats)
library(hrbrthemes)
library(viridis)
library(tidyr)
library(ggsignif)

setwd("C:/Users/Christopher/OneDrive/A_UC_LabAdmin_Projects/Research_Projects/R21_PRELIMINARY_GBM_PROJECT_COLLABORATION/Data_Materials/ExternalBioinformaticDatasets/timeDB/")

# Load Cell and Clinical Information
lgg_cell <- read.csv(file="CD_TCGA_LGG_2_xCell_full.csv", header=TRUE)
lgg_clinical <- read.csv(file="CD_TCGA_LGG_2_Clinical.csv", header=TRUE)

# Modify matrices
rownames(lgg_cell) <- lgg_cell[,1]
rownames(lgg_clinical) <- lgg_clinical[,1]
lgg_cell <- lgg_cell[,-1]
lgg_clinical <- lgg_clinical[,-1]

# Combine matrices by TCGA sample id
lgg_cell[rownames(lgg_clinical),colnames(lgg_clinical)] <- lgg_clinical


# Create intervals for n_age and pfs
lgg_cell$age_int <- cut_interval(lgg_cell$n_age, n = 2)
lgg_cell$pfs_int <- cut_interval(lgg_cell$pfs, n = 2)


jpeg(file=paste("race-sex.jpeg", sep=""), width = 2000, height = 2000)
lgg_cell %>%
  mutate(day = fct_reorder(c_race, c_gender)) %>%
  mutate(day = factor(c_race, levels=c("Asian", "White", "Black"))) %>%
  drop_na(c("age_int", "c_gender")) %>%
  ggplot(aes(fill=c_gender, y=Monocytes, x=age_int)) +
  geom_violin(position="dodge", alpha=0.5, outlier.colour="transparent") +
  scale_fill_viridis(discrete=T, name="") +
  theme_ipsum()  +
  xlab("") +
  ylab("Tip (%)") +
  geom_signif(
    comparisons = list(c("female, [14,50.5]", "male, [14,50.5]")), # Specify the pairs to compare
    map_signif_level = TRUE, # Show the significance level as stars
    y_position=0.1
  )
dev.off()