packages <- c(
    "tidyverse",
    "printr",
    "ggthemes",
    "readr",
    "miR34AasRNAproject",
    "grid",
    "gtable"
)
purrr::walk(packages, library, character.only = TRUE)
rm(packages)



Note: in cases where less than 3 samples are in any group, r-estimates and p-values are not reported.

data <- getData("Supplementary Figure 1a")

#normalize expression values
data <- mutate(
    data,
    RP3 = log2(RP3 / max(RP3)),
    miR34a = log2(miR34a / max(miR34a))  
  )

#add BRCA subtypes
data <- data %>%
  mutate(PAM50 = if_else(is.na(PAM50), "", PAM50)) %>%
  mutate(cancer_PAM50 = gsub("BRCA", "BRCA ", paste(cancer, PAM50, sep = "")))

#sort 
data <- arrange(data, cancer_PAM50, TP53, RP3)

#remove infinite data
data <- filter(data, !is.infinite(RP3) & !is.infinite(miR34a))

#diploid only
data <- filter(data, abs(RP3_cna) < 0.1)

#rename TP53
data <- mutate(data, TP53 = if_else(TP53 == 1, "TP53mut", "TP53wt"))

#diploid only correlation analysis
#calculate correlation for all samples per cancer type
all <- data %>% 
  filter(RP3_cna < 0.1) %>%
  group_by(cancer_PAM50) %>%
  summarize(
    n = n(),
    `all p` = cor.test(RP3, miR34a, method = "spearman")$p.value,
    `all rho` = cor.test(RP3, miR34a, method = "spearman")$estimate
  ) %>%
  mutate(
    `all p` = format(`all p`, scientific = TRUE, digits = 3),
    `all rho` = format(`all rho`, scientific = FALSE, digits = 2)
  )

#calculate correlation for p53 wt and mut samples per cancer type
p53 <- data %>%
  group_by(cancer_PAM50, TP53) %>%
  filter(n() > 3) %>%
  summarize(
    n = n(),
    p = cor.test(RP3, miR34a, method = "spearman")$p.value,
    rho = cor.test(RP3, miR34a, method = "spearman")$estimate
  ) %>%
  ungroup() %>%
  mutate(
    p = format(p, scientific = TRUE, digits = 3),
    rho = format(rho, scientific = FALSE, digits = 1)
  ) %>%
  gather(metric, value, -(cancer_PAM50:TP53)) %>%
  unite(temp, TP53, metric, sep = " ") %>%
  spread(temp, value)

table <- full_join(all, p53, by = "cancer_PAM50") %>%
  rename(cancer = cancer_PAM50, `all n` = n) %>%
  select(
    cancer, `all n`, `all rho`, `all p`, `TP53wt n`, 
    `TP53wt rho`, `TP53wt p`, `TP53mut n`, `TP53mut rho`, `TP53mut p`
  )

table

#add abbreviation definitions
def <- tibble(
  fullName = c(
    "Adrenocortical carcinoma", "Bladder Urothelial Carcinoma", "Breast invasive carcinoma", 
    "Breast invasive carcinoma", "Breast invasive carcinoma", "Breast invasive carcinoma",
    "Cervical squamous cell carcinoma and\nendocervical adenocarcinoma", "Head and Neck squamous cell carcinoma", "Kidney Chromophobe",
    "Kidney renal clear cell carcinoma", "Kidney renal papillary cell carcinoma", "Brain Lower Grade Glioma",
    "Liver hepatocellular carcinoma", "Lung adenocarcinoma", "Lung squamous cell carcinoma",
    "Ovarian serous cystadenocarcinoma", "Prostate adenocarcinoma", "Skin Cutaneous Melanoma",
    "Stomach adenocarcinoma", "Thyroid carcinoma"
  ),
  cancer = c(
    "ACC", "BLCA", "BRCA Basal", 
    "BRCA Her2", "BRCA LumA", "BRCA LumB",
    "CESC", "HNSC", "KICH",
    "KIRC", "KIRP", "LGG",
    "LIHC", "LUAD", "LUSC",
    "OV", "PRAD", "SKCM", 
    "STAD", "THCA"
  )
)

table <- def %>%
  full_join(table, by = "cancer") %>%
  mutate(finalName = case_when(
    fullName == "Breast invasive carcinoma" ~ paste(fullName, gsub("BRCA", "(BRCA)", cancer), sep = " "),
    TRUE ~ paste(fullName, "(", cancer, ")", sep = " ")
  )) %>%
  select(-fullName, -cancer) %>%
  rename(cancer = finalName) %>%
  select(cancer, `all n`, `all rho`, `all p`, `TP53wt n`, `TP53wt rho`, `TP53wt p`, `TP53mut n`, `TP53mut rho`, `TP53mut p`)

#save figure
# path <- file.path("~/GitHub/miR34a_asRNA_project/inst", fileMap(type = "pdf")["Figure 1-Supplement 1a"][[1]])
# pdf(file = path, width = 13, height = 6.1)
# gridExtra::grid.table(table, rows = NULL)
# invisible(dev.off())
R-squared and p-values from the correlation analysis investigating the correlation between miR34a and miR34a asRNA expression in p53 wild type (wt) and mutated (mut) samples within TCGA cancer types. Bladder Urothelial Carcinoma (BLCA), Breast invasive carcinoma (BRCA), Head and Neck squamous cell carcinoma (HNSC), Lower Grade Glioma (LGG), Liver hepatocellular carcinoma (LIHC), Lung adenocarcinoma (LUAD), Lung squamous cell carcinoma (LUSC), Ovarian serous cystadenocarcinoma (OV), Prostate adenocarcinoma (PRAD), Skin Cutaneous Melanoma (SKCM), Stomach adenocarcinoma (STAD).





sessionInfo()


GranderLab/miR34a_asRNA_project documentation built on May 26, 2019, 7:26 a.m.