PO.EN-package: An Elastic-Net Regularized presence-only Model

In PO.EN: An Elastic-Net Regularized Presence-Only Model

Description

This package fits a presence-only model with elastic-net penalty using coordinate descent. This package also provides a feature of tuning the prevalence parameter through a two-dimensional cross-validation. The package can be used in genetics study mainly for predicting regulatory effects of genetic variants given a large number of epigenetic features.

Details

Accept typical presence-only response vector y, a vector consisted of presence and background observations, and design matrix x. Three main functions:

cv.PO.EN	The cross-validation tuning function
PO.EN	The main model-fitting function
PO.EN.predict	The predicting function

Author(s)

Zikun Yang, Chen Wang, Iuliana Ionita-Laza

Maintainer: Zikun Yang <[e-mail]>

References

Zikun Yang, Chen Wang, Iuliana Ionita-Laza. A robust presence-only model to predict regulatory effects of genetic variants at single nucleotide resolution by integrating epigenetic information and massively parallel reporter assays. 2020

Examples

data(example.data) # example training dataset, including training dataset and testing dataset
train_data<-example.data$train.data
y_train=train_data$response;x_train=train_data[,-1]  # response and design matrix of training data
test_data<-example.data$test.data
y_test=test_data$response;x_test=test_data[,-1]  # response and design matrix of testing data
PO.EN.cv<-cv.PO.EN(x_train,y_train,input.pi=seq(0.01,0.4,length.out=4))

PO.EN.beta<-PO.EN(x_train,y_train,lambda=PO.EN.cv$lambda.min,
            true.prob=PO.EN.cv$pi,beta_start=rep(0,ncol(x_train)+1))
predictions<-PO.EN.predict(x_test,PO.EN.beta)
pROC::roc(y_test~predictions)

PO.EN documentation built on Aug. 19, 2020, 9:06 a.m.