gibran hemani explodecomputer

https://www.bris.ac.uk/integrative-epidemiology/intranet/training/

Causal methods

Introduction

In an epidemiological context, whether stated explicitly or not, we typically are referring to a counterfactual condition. A counterfactual condition is where we suppose that the outcome would not have happened in an alternate reality where all things were identical except for the exposure.

For example, if an individual had body mass index = 23 instead of body mass index = 27, but all else was identical, what would the impact be on their bone mineral density?

	#===================================#
	# GWAS Practical #
	# iBSC Genomic Medicine #
	# Lavinia Paternoster #
	# 08/11/2018 #
	#===================================#


	# Run the GWAS without PCs but using the cleaned genetic data

	# Get the list of arguments passed to R
	args <- commandArgs(T)

	# Get the first argument, make it numeric because by default it is read as a string
	job_id <- as.numeric(args[1])

	# Print the argument
	message("job number ", job_id)

	n <- 5
	a <- combn(c(1:(2*n)), 2)
	b <- combn(1:ncol(a), n)
	l <- list()
	m <- list()
	j <- 1
	for(i in 1:ncol(b))
	{
	x <- a[, b[,i]]
	if(!any(duplicated(c(x))))

	# How does adjusted r-square do with overfitting?

	rm(list=ls())
	set.seed(101)

	library(ggplot2)
	library(tidyr)

	y <- rnorm(1000)
	x <- matrix(rnorm(1000 * 1000), 1000, 1000)

	dat_3a$rsq.exposure <- with(dat_3a, 2 * beta.exposure^2 * eaf.exposure * (1-eaf.exposure))
	dat_3a$rsq.outcome <- with(dat_3a, 2 * beta.outcome^2 * eaf.outcome * (1-eaf.outcome))
	dat_3a$steiger_dir <- dat_3a$rsq.exposure > dat_3a$rsq.outcome

	dat_3b$rsq.exposure <- with(dat_3b, 2 * beta.exposure^2 * eaf.exposure * (1-eaf.exposure))
	dat_3b$rsq.outcome <- with(dat_3b, 2 * beta.outcome^2 * eaf.outcome * (1-eaf.outcome))
	dat_3b$steiger_dir <- dat_3b$rsq.exposure > dat_3b$rsq.outcome

	---
	title: Calculating HWE
	---

	Choose a set of parameters. For each allele frequency and sample size, run 100 simulations

	```{r}
	library(tidyr)
	library(ggplot2)
	library(dplyr)

	library(devtools)
	install_github("explodecomputer/simulateGP")
	library(simulateGP)
	library(ggplot2)

	param <- rbind(
	expand.grid(
	ncase=100,
	ncontrol=100,
	prev=0.001,

	randomness <- function(x)
	{
	a <- (sum(x[-1] != x[-length(x)]) / (length(x)-1) - 0.5) * 2
	return(round(a, 2))
	}
	make_dat <- function()
	{
	dat <- read.table("~/Desktop/ascii.txt", he=F, sep="\t", stringsAsFactors = FALSE, quote="", comment="")
	names(dat) <- c("dec", "hex", "binary", "al")
	dat$binary <- gsub("0", ".", dat$binary)

	library(dplyr)
	library(MeSH.db)
	k <- keys(MeSH.db, keytype = "MESHID")

	select(MeSH.db, keys = k[1:10], columns = c("MESHID", "MESHTERM"), keytype = "MESHID")

	LEU <- select(MeSH.db, keys = "Leukemia", columns = c("MESHID", "MESHTERM", "CATEGORY", "SYNONYM"), keytype = "MESHTERM")


	library("MeSH.AOR.db")