GRridge-package: Implements adaptive group-regularized (logistic) ridge...

In markvdwiel/GRridge: Better prediction by use of co-data: Adaptive group-regularized ridge regression

Description

This package implements adaptive group-regularized (logistic) ridge regression by use of co-data. It uses co-data to improve predictions of binary and continuous response from high-dimension (e.g. genomics) data. Here, co-data is auxiliary information on variables (e.g. genes), such as annotation or p-values from other studies. The package includes convenience functions to convert such co-data to the correct input format. In additiion, in includes functions for evaluating the predictive performance.

Details

Package:	GRridge
Type:	Package
Version:	1.7.3
Date:	2018-11-29
License:	GPL

Main functions in the GRridge package are:

auc: Computes Area-under-the-ROC-curve
CreatePartition: Creates a partition (groups) of variables
dataFarkas: Large data set plus external information
dataSimlin: Small simulated data set with linear response
dataVerlaat: Methylation data plus external information
dataWurdinger: RNAseq data plus external information
simlinsmall: Simulated data for linear regression
grridge: Group-regularized (logistic, survival) ridge regression
grridgeCV: Cross-validated predictions for a grridge (logistic, survival) regression.
matchGeneSets: Creates a grouping of variables (genes) from gene sets
mergeGroups: Merge groups in a partition
PartitionsSelection: Co-data selection in a Group-regularized ridge regression model
predict.grridge: Predictions for new samples from a grridge object
roc: Computes an ROC-curve for probabilistic classifiers

Author(s)

Mark A. van de Wiel ([e-mail]), Putri Novianti ([e-mail])

References

Mark van de Wiel, Tonje Lien, Wina Verlaat, Wessel van Wieringen, Saskia Wilting. (2016). Better prediction by use of co-data: adaptive group-regularized ridge regression. Statistics in Medicine, 35(3), 368-81.

Novianti PW, Snoek B, Wilting SM, van de Wiel MA (2017). Better diagnostic signatures from RNAseq data through use of auxiliary co-data. Bioinformatics, 33, 1572-1574.

See Also

GRridge depends on: penalized. Examples: grridge

markvdwiel/GRridge documentation built on May 21, 2019, 12:25 p.m.