---

title: “combine data together and calculate the correlation between miRs” output: html_notebook

suppressMessages(library(data.table))
suppressMessages(library(tidyverse))
suppressMessages(library(readxl))
suppressMessages(library(ggpubr))
suppressMessages(library(dplyr))
suppressMessages(library(dtplyr))
suppressMessages(library(purrr))
suppressMessages(library(stringr))
suppressMessages(library(gridExtra))
suppressMessages(library(caret))
suppressMessages(library(plotly))
suppressMessages(library(biomaRt))
suppressMessages(library(systemPipeR))
suppressMessages(library(GenomicFeatures))
suppressMessages(library(BiocParallel))
suppressMessages(library(ConservationtextmineR))
###Import cohort1 and cohort2 csv files
cohort1 <- fread("./data/cohort1.csv")
cohort2 <- fread("./data/cohort2.csv")
cohort1$dataset <- "cohort1"
cohort2$dataset <- "cohort2"
combined <- rbind(cohort1, cohort2)
p <- ggplot(combined, aes(x=log2FC_miRNA1, y=log2FC_miRNA2))+
  geom_point(shape = 21, size = 3, colour = "black", fill = "#08519C")+
  scale_color_manual(values=c("#E31A1C")) +
  geom_point(data = subset(combined, combined$dataset == "cohort2"),
             aes(x=log2FC_miRNA1, y=log2FC_miRNA2), 
             shape = 21, size = 3, colour = "black", fill = "#E31A1C") +
  geom_smooth(method = "lm")+
  ggtitle("correlation")+
  theme_pubr(); p
  
  ##correlation test
  cor.test(combined_comp$log2FC_miRNA1, combined_comp$log2FC_miRNA2, method=c("pearson"))
  
  ##wilcox test
  wilcox.test(combined_comp$log2FC_miRNA1, combined_comp$log2FC_miRNA2, conf.int = TRUE, 
            paired = FALSE, formula = "lhs")