prs.train.cv: Polygenic risk score (given only allele frequencies);...
In ssa: Simultaneous Signal Analysis

Description Usage Arguments Value Examples

Uses CV to select how many SNPs to include. SNPs are ordered by the magnitude of their estimated (ang possibly weighted) allelic log-odds ratio. The discriminant function is

∑_j\hat{β}_jI≤ft(≤ft\vert\frac{\hat{β}_j}{w_j}\right\vert>λ\right)X_j,

where X_j is the additively coded genotype of SNP j.

1	prs.train.cv(X0, X1, K = 3, w = 1, nlambda = 100, verbose = FALSE)

`X0, X1`	n x p vectors of control and case genotypes, additively coded; IMPORTANT: coding must be relative to the same allele in both cases and controls
`K`	number of folds for CV
`w`	p x 1 weight vector
`nlambda`	number of thresholds to tune over
`verbose`	if TRUE, report current fold of CV

`pi0`	minor allele frequencies in controls of kept SNPs
`pi1`	minor allele frequencies in cases of kept SNPs
`w`	weight vector for kept SNPs
`lambda`	lambda cutoff
`P`	proportion of cases

p <- 1000; ## number of snps
I <- rep(0,p); I[1:10] <- 1; ## which snps are causal
set.seed(1); pi0 <- runif(p,0.1,0.5); ## control minor allele frequencies
set.seed(1); ors <- runif(sum(I),-1,1); ## odds ratios
pi1 <- pi0;
pi1[I==1] <- expit(ors+logit(pi0[I==1]));
n0 <- 100; ## number of controls
X0 <- t(replicate(n0,rbinom(p,2,pi0))); ## controls
n1 <- 50; ## number of cases
X1 <- t(replicate(n1,rbinom(p,2,pi1))); ## cases
prs.train.cv(X0,X1,K=3,w=1,nlambda=100,verbose=TRUE);