Seurat (version 2.1.0)

ValidateSpecificClusters: Specific Cluster Validation

Description

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

Usage

ValidateSpecificClusters(object, cluster1 = NULL, cluster2 = 1,
  pc.use = 2, top.genes = 30, acc.cutoff = 0.9)

Arguments

object

Seurat object

cluster1

First cluster to check classification

cluster2

Second cluster to check with classification

pc.use

Which PCs to use for model construction

top.genes

Use the top X genes for model construction

acc.cutoff

Accuracy cutoff for classifier

Value

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

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 <- ValidateSpecificClusters(pbmc_small, cluster1 = 1,
                                       cluster2 = 2,  pc.use = 1:10)
# }
# NOT RUN {
# }