citrus.extractModelFeatures: Report model features at pre-specified thresholds.

In ParkerICI/kumquat: Identification of stratifying subpopulations in Flow Cytometry Data (based on the Citrus package)

Description

Report model features at pre-specific thresholds. For predictive models, reports non-zero model features at specified regularization thresholds. For FDR-constrained models, reports features below specified false discovery rates.

Usage

citrus.extractModelFeatures(cvMinima, finalModel, finalFeatures)

Arguments

cvMinima	List of regularization indicies at which to extract model features, produced by citrus.getCVMinima.
finalModel	Predictive model from which to extract non-zero features.
finalFeatures	Features used to construct finalModel.

Value

List of significant features and clusters at specified thresholds.

Author(s)

Robert Bruggner

ParkerICI/kumquat documentation built on Dec. 18, 2021, 6:40 a.m.