Seurat (version 2.3.4)

AssessNodes: Assess Internal Nodes

Description

Method for automating assessment of tree splits over all internal nodes, or a provided list of internal nodes. Uses AssessSplit() for calculation of Out of Bag error (proxy for confidence in split).

Usage

AssessNodes(object, node.list, all.below = FALSE, genes.training = NULL)

Arguments

object

Seurat object

node.list

List of internal nodes to assess and return

all.below

If single node provided in node.list, assess all splits below (and including) provided node

genes.training

A vector of genes to use to train the classifier, defaults to rownames(x = object@data) .

Value

Returns the Out of Bag error for a random forest classifiers trained on each internal node split or each split provided in the node list.

Examples

# NOT RUN {
pbmc_small
pbmc_small <- FindClusters(object = pbmc_small, reduction.type = "pca",
                           dims.use = 1:10, resolution = 1.1, save.SNN = TRUE)
pbmc_small <- BuildClusterTree(pbmc_small, reorder.numeric = TRUE, do.reorder = TRUE)
AssessNodes(pbmc_small)
# }
# NOT RUN {
# }

Run the code above in your browser using DataCamp Workspace