Cardiac and TOP2 Genes - Log2CPM Boxplots

📌 Log2CPM Boxplots for Cardiac and TOP2 Genes

This analysis generates boxplots for cardiac genes and TOP2 genes across different treatments and timepoints.

📌 Load Required Libraries

library(ggplot2)

Warning: package 'ggplot2' was built under R version 4.3.3

library(dplyr)

Warning: package 'dplyr' was built under R version 4.3.2

library(tidyr)

Warning: package 'tidyr' was built under R version 4.3.3

📌 Read Log2CPM Data

# Load feature count matrix
boxplot1 <- read.csv("data/Feature_count_Matrix_Log2CPM_filtered.csv") %>% as.data.frame()

# Ensure column names are cleaned
colnames(boxplot1) <- trimws(gsub("^X", "", colnames(boxplot1)))  

📌 Define Genes of Interest

# Define the genes of interest
top2_genes <- c("TOP2A", "TOP2B")
cardiac_genes <- c("ACTN2", "CALR", "MYBPC3", "MYH6", "MYH7", 
                   "MYL2", "RYR2", "SCN5A", "TNNI3", "TNNT2", "TTN")
dna_damage_genes <- c("TP53")  # Using correct gene symbol TP53

📌 Read and Process DEGs Data

# Load Toptables
deg_files <- list.files("data/DEGs", pattern = "Toptable_.*\\.csv", full.names = TRUE)
deg_list <- lapply(deg_files, read.csv)
names(deg_list) <- gsub("data/DEGs/Toptable_|\\.csv", "", deg_files)  

# Function to check significance based on **Entrez_ID in the correct sample**
is_significant <- function(gene, drug, conc, timepoint) {
  condition <- paste(drug, conc, timepoint, sep = "_")
  if (!condition %in% names(deg_list)) return(FALSE)
  
  toptable <- deg_list[[condition]]
  gene_entrez <- boxplot1$ENTREZID[boxplot1$SYMBOL == gene]
  
  if (length(gene_entrez) == 0) return(FALSE)
  
  return(any(gene_entrez %in% toptable$Entrez_ID[toptable$adj.P.Val < 0.05]))
}

📌 Process Data for Plotting

process_gene_data <- function(gene) {
  # Filter log2CPM data for the gene
  gene_data <- boxplot1 %>% filter(SYMBOL == gene)
  
  # Reshape data
  long_data <- gene_data %>%
    pivot_longer(cols = -c(ENTREZID, SYMBOL, GENENAME), names_to = "Sample", values_to = "log2CPM") %>%
    mutate(
      Indv = case_when(
        grepl("75.1", Sample) ~ "1",
        grepl("78.1", Sample) ~ "2",
        grepl("87.1", Sample) ~ "3",
        grepl("17.3", Sample) ~ "4",
        grepl("84.1", Sample) ~ "5",
        grepl("90.1", Sample) ~ "6",
        TRUE ~ NA_character_
      ),
      Drug = case_when(
        grepl("CX.5461", Sample) ~ "CX",
        grepl("DOX", Sample) ~ "DOX",
        grepl("VEH", Sample) ~ "VEH",
        TRUE ~ NA_character_
      ),
      Conc. = case_when(
        grepl("_0.1_", Sample) ~ "0.1",
        grepl("_0.5_", Sample) ~ "0.5",
        TRUE ~ NA_character_
      ),
      Timepoint = case_when(
        grepl("_3$", Sample) ~ "3",
        grepl("_24$", Sample) ~ "24",
        grepl("_48$", Sample) ~ "48",
        TRUE ~ NA_character_
      ),
      Condition = paste(Drug, Conc., Timepoint, sep = "_")
    )

  # **Ensure Condition is Ordered Correctly**
  long_data$Condition <- factor(
    long_data$Condition, 
    levels = c(
      "CX_0.1_3", "CX_0.1_24", "CX_0.1_48", "CX_0.5_3", "CX_0.5_24", "CX_0.5_48",
      "DOX_0.1_3", "DOX_0.1_24", "DOX_0.1_48", "DOX_0.5_3", "DOX_0.5_24", "DOX_0.5_48",
      "VEH_0.1_3", "VEH_0.1_24", "VEH_0.1_48", "VEH_0.5_3", "VEH_0.5_24", "VEH_0.5_48"
    )
  )
  
  # Identify significant conditions **per Drug, Conc, and Timepoint**
  significance_labels <- long_data %>%
    distinct(Drug, Conc., Timepoint, Condition) %>%
    rowwise() %>%
    mutate(
      max_log2CPM = max(long_data$log2CPM[long_data$Condition == Condition], na.rm = TRUE),
      Significance = ifelse(is_significant(gene, Drug, Conc., Timepoint), "*", "")
    ) %>%
    filter(Significance != "") %>% ungroup()
  
  list(long_data = long_data, significance_labels = significance_labels)
}

📌Generate Boxplots for Cardiac Genes

for (gene in cardiac_genes) {
  data_info <- process_gene_data(gene)
  p <- ggplot(data_info$long_data, aes(x = Condition, y = log2CPM, fill = Drug)) +
    geom_boxplot(outlier.shape = NA) +
    scale_fill_manual(values = c("CX" = "#0000FF", "DOX" = "#e6d800", "VEH" = "#FF00FF")) +
    geom_point(aes(color = Indv), size = 2, alpha = 0.5, position = position_jitter(width = -1, height = 0)) +
    geom_text(data = data_info$significance_labels, aes(x = Condition, y = max_log2CPM + 0.5, label = Significance),
              inherit.aes = FALSE, size = 6, color = "black") +
    ggtitle(paste("Log2CPM Expression of", gene)) +
    labs(x = "Treatment", y = "log2CPM") +
    theme_bw() +
    theme(plot.title = element_text(size = rel(2), hjust = 0.5),
          axis.title = element_text(size = 15, color = "black"),
          axis.text.x = element_text(size = 10, color = "black", angle = 90, hjust = 1))
  
  print(p)
}

Past versions of Cardiac-1.png

Past versions of Cardiac-2.png

Past versions of Cardiac-3.png

Past versions of Cardiac-4.png

Past versions of Cardiac-5.png

Past versions of Cardiac-6.png

Past versions of Cardiac-7.png

Past versions of Cardiac-8.png

Past versions of Cardiac-9.png

Past versions of Cardiac-10.png

Past versions of Cardiac-11.png

📌Generate Boxplots for TOP2 Genes

for (gene in top2_genes) {
  data_info <- process_gene_data(gene)
  p <- ggplot(data_info$long_data, aes(x = Condition, y = log2CPM, fill = Drug)) +
    geom_boxplot(outlier.shape = NA) +
    scale_fill_manual(values = c("CX" = "#0000FF", "DOX" = "#e6d800", "VEH" = "#FF00FF")) +
    geom_point(aes(color = Indv), size = 2, alpha = 0.5, position = position_jitter(width = -1, height = 0)) +
    geom_text(data = data_info$significance_labels, aes(x = Condition, y = max_log2CPM + 0.5, label = Significance),
              inherit.aes = FALSE, size = 6, color = "black") +
    ggtitle(paste("Log2CPM Expression of", gene)) +
    labs(x = "Treatment", y = "log2CPM") +
    theme_bw() +
    theme(plot.title = element_text(size = rel(2), hjust = 0.5),
          axis.title = element_text(size = 15, color = "black"),
          axis.text.x = element_text(size = 10, color = "black", angle = 90, hjust = 1))
  
  print(p)
}

Past versions of TOP2-1.png

Past versions of TOP2-2.png

📌 Generate Boxplots for DNA Damage Genes

for (gene in dna_damage_genes) {
  data_info <- process_gene_data(gene)
  p <- ggplot(data_info$long_data, aes(x = Condition, y = log2CPM, fill = Drug)) +
    geom_boxplot(outlier.shape = NA) +
    scale_fill_manual(values = c("CX" = "#0000FF", "DOX" = "#e6d800", "VEH" = "#FF00FF")) +
    geom_point(aes(color = Indv), size = 2, alpha = 0.5, position = position_jitter(width = -1, height = 0)) +
    geom_text(data = data_info$significance_labels, aes(x = Condition, y = max_log2CPM + 0.5, label = Significance),
              inherit.aes = FALSE, size = 6, color = "black") +
    ggtitle(paste("Log2CPM Expression of", gene)) +
    labs(x = "Treatment", y = "log2CPM") +
    theme_bw() +
    theme(plot.title = element_text(size = rel(2), hjust = 0.5),
          axis.title = element_text(size = 15, color = "black"),
          axis.text.x = element_text(size = 10, color = "black", angle = 90, hjust = 1))
  
  print(p)
}

Past versions of "DNA Damage-1.png"

Session information

sessionInfo()

R version 4.3.0 (2023-04-21 ucrt)
Platform: x86_64-w64-mingw32/x64 (64-bit)
Running under: Windows 11 x64 (build 22631)

Matrix products: default


locale:
[1] LC_COLLATE=English_United States.utf8 
[2] LC_CTYPE=English_United States.utf8   
[3] LC_MONETARY=English_United States.utf8
[4] LC_NUMERIC=C                          
[5] LC_TIME=English_United States.utf8    

time zone: America/Chicago
tzcode source: internal

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
[1] tidyr_1.3.1     dplyr_1.1.4     ggplot2_3.5.1   workflowr_1.7.1

loaded via a namespace (and not attached):
 [1] gtable_0.3.6      jsonlite_1.8.9    compiler_4.3.0    promises_1.3.0   
 [5] tidyselect_1.2.1  Rcpp_1.0.12       stringr_1.5.1     git2r_0.35.0     
 [9] callr_3.7.6       later_1.3.2       jquerylib_0.1.4   scales_1.3.0     
[13] yaml_2.3.10       fastmap_1.1.1     R6_2.5.1          labeling_0.4.3   
[17] generics_0.1.3    knitr_1.49        tibble_3.2.1      munsell_0.5.1    
[21] rprojroot_2.0.4   bslib_0.8.0       pillar_1.10.1     rlang_1.1.3      
[25] cachem_1.0.8      stringi_1.8.3     httpuv_1.6.15     xfun_0.50        
[29] getPass_0.2-4     fs_1.6.3          sass_0.4.9        cli_3.6.1        
[33] withr_3.0.2       magrittr_2.0.3    ps_1.8.1          digest_0.6.34    
[37] grid_4.3.0        processx_3.8.5    rstudioapi_0.17.1 lifecycle_1.0.4  
[41] vctrs_0.6.5       evaluate_1.0.3    glue_1.7.0        farver_2.1.2     
[45] whisker_0.4.1     colorspace_2.1-0  purrr_1.0.2       rmarkdown_2.29   
[49] httr_1.4.7        tools_4.3.0       pkgconfig_2.0.3   htmltools_0.5.8.1