Main_application.Rmd

---
title: "Smilator_omics"
author: "Anastasia&Nasimeh"
date: "6/27/2022"
output: html_document
---
# Simulator code for data generation process of omics data. 





```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)

library(GEOquery) #bioconductor
```


```{r, message=FALSE, cache=FALSE, echo=FALSE,warning=FALSE}
GEO_real_world_data <- "GSE145714" # ID for real world data 
gset <- getGEO(GEO_real_world_data, GSEMatrix =TRUE, getGPL=FALSE, destdir="example_dataset/")
gset <- gset$GSE145714_series_matrix.txt.gz

clinical_data <- pData(gset) # clinico-pathological description
clinical_data <- clinical_data[,c(2,41:44)]
colnames(clinical_data)[c(2:5)] <- c("hiv_status", "gender", "tb_status", "timepoint")
clinical_data <- clinical_data[order(clinical_data$tb_status),]
beta_matrix <- exprs(gset)
rm(gset)

calculate_means(beta_matrix)
```

```{r pressure, echo=FALSE}
#default parameters for the simulator
num_samples <- 500
healthy_proportion <- 0.5
num_mutated_CpGs <- 200
delta_beta <- 0.3

```

```{r pressure, echo=FALSE}
# Function for calculating the mean of CpGs across all samples.
calculate_means <- function (beta_values_matrix) {
means <- as.data.frame(matrixStats::rowMeans2(beta_values_matrix))
names(means) <- "Mean"
return(means)
}
```

```{r pressure, echo=FALSE}
# Function for calculating the standard deviation of CpGs across all samples.
calculate_SD <- function (beta_values_matrix) {
SD <- as.data.frame(matrixStats::rowSds(beta_values_matrix))
names(SD) <- "SD"
return(SD)
}
```