testPosteriors {RIVER} | R Documentation |
testPosteriors
computes posterior probabilities of FR (functionality
of regulatory variant) given G (genomic annotations) and E (outlier
status) with estimate of beta (parameters between FR and G) and
theta (parameters between FR and E).
testPosteriors(Feat, Out, emModel)
Feat |
Genomic features (G) |
Out |
Binary values of outlier status (E). |
emModel |
Estimated parameters including beta and theta via EM and selected lambdas |
test posterior probabilities of FR given new outlier status (E) and genomic features (G), P(FR | G, E, beta, theta), and probable status of FR.
Yungil Kim, ipw012@gmail.com
getFuncRvFeat
and getFuncRvPosteriors
dataInput <- getData(filename=system.file("extdata", "simulation_RIVER.gz", package = "RIVER"), ZscoreThrd=1.5) Feat <- scale(t(Biobase::exprs(dataInput))) # genomic features (G) Out <- as.vector(as.numeric(unlist(dataInput$Outlier))-1) # outlier status (E) theta.init <- matrix(c(.99, .01, .3, .7), nrow=2) costs <- c(100, 10, 1, .1, .01, 1e-3, 1e-4) logisticAllCV <- glmnet::cv.glmnet(Feat, Out, lambda=costs, family="binomial", alpha = 0, nfolds=10) emModelAll <- integratedEM(Feat, Out, logisticAllCV$lambda.min, logisticAllCV$glmnet.fit, pseudoc=50, theta.init, costs, verbose=FALSE) trainedpost <- testPosteriors(Feat, Out, emModel=emModelAll)