TCGA_PRAD_AgeRace

library(tidyverse)
library(ggplot2)
library(plotly)


###################################################
###       ## TCGA exploritory BRCA PRAD ##      ###
###################################################


# Specify which TCGA study to analyze
study = "PRAD"
setwd("/home/mwells11/ASex_Chr_Lab/PRAD/")
filepath <- "/home/mwells11/ASex_Chr_Lab/PRAD/"


counts_fname <- paste("TCGA", study, "TPM.tsv", sep = "-")
meta_fname <- paste("TCGA", study, "METADATA.tsv", sep = "-")

counts_path <- paste(filepath, counts_fname, sep = "")
meta_path <- paste(filepath, meta_fname, sep = "")

#################################################################

library(GenomicDataCommons)
library(tidyverse)
library(TCGAutils)

#hello
#pull out case ids, project id must match or r will crash 
# - project ID "TCGA-PRAC" for example


################
### METADATA ###
################

case_ids2 <- cases() %>%
  GenomicDataCommons::filter(~ project.project_id == "TCGA-PRAD") %>%
  ids()
clindat2 <- gdc_clinical(case_ids2)
# Pull out clinical data of interest into lists
# CLINICAL DATA LISTS WERE FOUND BY LOOKING AT GDC WEBSITE AND SEEING WHAT CLINICAL DATA ENTAILED,

meta_df_clin <- clindat2
class(meta_df_clin)
meta_df_clin <- as.data.frame(meta_df_clin)

write_tsv(
  meta_df_clin,
  "/home/mwells11/ASex_Chr_Lab/PRAD/TCGA_PRAD_CLINDATA.tsv",
  na = "NA",
  append = FALSE,
  col_names = TRUE,
  quote = "none",
  eol = "\n",
  num_threads = readr_threads(),
  progress = show_progress()
)

mf_list_1 <- clindat2[["demographic"]][["gender"]]
status_list_1 <- clindat2[["demographic"]][["vital_status"]]
surv_times_1  <- clindat2[["demographic"]][["days_to_death"]]
follow_list_1 <- clindat2[["diagnoses"]][["days_to_last_follow_up"]]
age_list_1 <- clindat2[["demographic"]][["age_at_index"]]
race_list_1 <- clindat2[["demographic"]][["race"]]
tissue_list_1 <- clindat[["diagnoses"]][["tissue_or_organ_of_origin"]]


################################################################################
##  checking rows and vectors

lengths <- sapply(list(case_ids2, mf_list_1, status_list_1, surv_times_1, follow_list_1, age_list_1, race_list_1, tissue_list_1), length)
lengths
max_length <- max(lengths)
################################################################################

max_length <- max(lengths)

# Create a list of vectors
vector_list <- list(
  case_ids2,
  mf_list_1,
  status_list_1,
  surv_times_1,
  follow_list_1,
  age_list_1,
  race_list_1,
  tissue_list_1
)

# Loop through the list and adjust vector lengths
adjusted_vectors <- lapply(vector_list, function(vec) {
  if (length(vec) < max_length) {
    # Pad with NA to match the maximum length
    return(c(vec, rep(NA, max_length - length(vec))))
  } else {
    # If length is already equal to max_length, no adjustment needed
    return(vec)
  }
})

# Create a data frame from adjusted vectors
meta_df2 <- data.frame(do.call(cbind, adjusted_vectors))
#This code checks each vector's length and pads it with NA values if needed to match the max_length. 

#Adjust the code based on your specific vectors and requirements.







################################################################################
################################################################################

meta_df2 <- data.frame(cbind(case_ids2, mf_list_1, status_list_1,
                             surv_times_1, follow_list_1, age_list_1,
                             race_list_1, tissue_list_1))


write_tsv(
  meta_df2,
  "/home/mwells11/ASex_Chr_Lab/PRAD/TCGA_PRAD_METADATA.tsv",
  na = "NA",
  append = FALSE,
  col_names = TRUE,
  quote = "none",
  eol = "\n",
  num_threads = readr_threads(),
  progress = show_progress()
)


################################################################################
##                      WRITE PLOTS BASED ON AGE AND RACE                     ##
################################################################################


library(ggplot2)
setwd("/home/mwells11/ASex_Chr_Lab/PRAD/")
filepath <- "/home/mwells11/ASex_Chr_Lab/PRAD/"



##  age_list_1 for age, mf_list_1 = reported sex
ggplot(, aes(x = Age)) +
  geom_histogram(binwidth = 5, fill = "blue", color = "black") +
  labs(title = "Age Distribution of Cancer Cells", x = "Age", y = "Count")




library(ggplot2)

#histogram of age and race

# Read the metadata file
metadata <- read_tsv("/home/mwells11/ASex_Chr_Lab/PRAD/TCGA_PRAD_METADATA.tsv")

# Create a ggplot
ggplot(metadata, aes(x = age_list_1, fill = race_list_1)) +
  geom_histogram(binwidth = 5, position = "dodge", color = "black") +
  labs(title = "Age Distribution by Race", x = "Age", y = "Count", fill = "Race") +
  theme_minimal()
########################################################################################################################################
##                 USE THIS ONE          violin plot of age and race               USE THIS ONE                                       ##
########################################################################################################################################

# Read the metadata file
metadata <- read_tsv("/home/mwells11/ASex_Chr_Lab/PRAD/TCGA_PRAD_METADATA.tsv")

# Create a ggplot with violin plots
ggplot(metadata, aes(x = race_list_1, y = age_list_1, fill = race_list_1)) +
  geom_violin(trim = FALSE) +
  labs(title = "Age Distribution by Race", x = "Race", y = "Age", fill = "Race") +
  theme_minimal()

#VIOlin scatter plot of age and race

# Read the metadata file
metadata <- read_tsv("/home/mwells11/ASex_Chr_Lab/PRAD/TCGA_PRAD_METADATA.tsv")

# Create a ggplot with violin and scatter plot
ggplot(metadata, aes(x = race_list_1, y = age_list_1)) +
  geom_violin(trim = FALSE, fill = "lightblue") +
  geom_jitter(aes(color = race_list_1), width = 0.3, alpha = 0.5) +
  labs(title = "Age Distribution by Race", x = "Race", y = "Age", color = "Race") +
  theme_minimal()

#makes the datapoints black
ggplot(metadata, aes(x = race_list_1, y = age_list_1)) +
  geom_violin(trim = FALSE, fill = "lightblue") +
  geom_jitter(color = "black", width = 0.3, alpha = 0.5) +  # Set color to black
  labs(title = "Age Distribution by Race in Males with Prostate Cancer Diagnosis", x = "Race", y = "Age", color = "Race") +
  theme_minimal()
############## USING CLINDSATA #####################



# Read the clinical data file
clinical_data <- read_tsv("/home/mwells11/ASex_Chr_Lab/PRAD/TCGA_PRAD_CLINDATA.tsv")

############### Create a violin plot of age, race, and main primary site ################
ggplot(clinical_data, aes(x = diagnoses.age_at_diagnosis, y = age_list_1, fill = race_list_1)) +
  geom_violin(trim = FALSE) +
  labs(title = "Clinical Data: Age, Race, and Main Primary Site",
       x = "age_at_diagnosis",
       y = "Age",
       fill = "Race") +
  theme_minimal()



################### Create a histogram of age ########################
ggplot(clinical_data, aes(x = age_list_1)) +
  geom_histogram(binwidth = 5, fill = "skyblue", color = "black") +
  labs(title = "Histogram of Age",
       x = "Age",
       y = "Count") +
  theme_minimal()
# Create a histogram of age at diagnosis
ggplot(clinical_data, aes(x = diagnoses.age_at_diagnosis)) +
  geom_histogram(binwidth = 5, fill = "skyblue", color = "black") +
  labs(title = "Histogram of Age at Diagnosis",
       x = "Age at Diagnosis",
       y = "Count") +
  theme_minimal()