get_feature_genes: Extract feature genes

In cole-trapnell-lab/garnett: Automated cell type classification

Extract feature genes

Description

Extract the genes chosen as features in cell type classification from a trained garnett_classifier

Usage

get_feature_genes(classifier, node = "root", convert_ids = FALSE,
  db = NULL)

Arguments

classifier	Trained garnett_classifier - output from train_cell_classifier.
node	Character. The name of the parent node of the multinomial classifier you would like to view features for. If top level, use "root".
convert_ids	Logical. Should classifier IDs be converted to SYMBOL?
db	Bioconductor AnnotationDb-class package for converting gene IDs. For example, for humans use org.Hs.eg.db. See available packages at Bioconductor. If convert_ids = FALSE, db can be NULL.

Value

A data.frame of coefficient values for each gene with non-zero coefficients in the classifier.

Examples

library(org.Hs.eg.db)
data(test_classifier)
featuresdf <- get_feature_genes(test_classifier, db=org.Hs.eg.db)
featuresdf2 <- get_feature_genes(test_classifier,
                                 convert_ids = FALSE,
                                 node = "T cells")

cole-trapnell-lab/garnett documentation built on Jan. 6, 2025, 2:18 p.m.