Seurat (version 2.1.0)

ValidateClusters: Cluster Validation

Description

Methods for validating the legitimacy of clusters using classification. SVMs are used as the basis for the classification. Merging is done based on the connectivity from an SNN graph.

Usage

ValidateClusters(object, pc.use = NULL, top.genes = 30,
  min.connectivity = 0.01, acc.cutoff = 0.9, verbose = TRUE)

Arguments

object

Seurat object

pc.use

Which PCs to use to define genes in model construction

top.genes

Use the top X genes for each PC in model construction

min.connectivity

Threshold of connectedness for comparison of two clusters

acc.cutoff

Accuracy cutoff for classifier

verbose

Controls whether to display progress and merging results

Value

Returns a Seurat object, object@ident has been updated with new cluster info

Examples

# NOT RUN {
pbmc_small
# May throw warnings when cluster sizes are particularly small
# }
# NOT RUN {
pbmc_small <- FindClusters(object = pbmc_small, reduction.type = "pca",
                           dims.use = 1:10, resolution = 1.1, save.SNN = TRUE)
pbmc_small <- ValidateClusters(pbmc_small, pc.use = 1:10)
# }
# NOT RUN {
# }