A function for estimating the number of clusters using various method Methods available are: Discriminant, Distance (Gap, Silhouette, Slope, Jump, and Within Cluster Distance,) and Instability
Usage
estimateNumCluster(data, method = c("Discriminant", "Distance"), kSeq = 2:20)Arguments
- data
the SOM object generated by generatePrototypes(), or an object of class SingleCellExperiment or SpatialExperiment.
- method
one of Discriminant, Distance, Stability. By default, everything is run
- kSeq
a sequence of the number of clusters to try. Default is 2:20 clusters
Value
A list containing the cluster estimations if a dataframe or matrix is provided
A SingleCellExperiment with a cluster estimate in it's metadata if a SingleCellExperiment or SpatialExperiment object is provided
Author
Elijah WIllie ewil3501@uni.sydney.edu.au
Examples
data("risom_dat")
risomMarkers <- c(
"CD45", "SMA", "CK7", "CK5", "VIM", "CD31", "PanKRT", "ECAD"
)
res <- runFuseSOM(risom_dat, markers = risomMarkers, numClusters = 23)
#> You have provided a dataset of class data.frame
#> Everything looks good. Now running the FuseSOM algorithm
#> Now Generating the Self Organizing Map Grid
#> Optimal Grid Size is: 5
#> Now Running the Self Organizing Map Model
#> Now Clustering the Prototypes
#> Now Mapping Clusters to the Original Data
#> The Prototypes have been Clustered and Mapped Successfully
#> The FuseSOM algorithm has completed successfully
res.est.k <- estimateNumCluster(res$model, kSeq = 2:25)
#> Now Computing the Number of Clusters using Discriminant Analysis
#> Now Computing The Number Of Clusters Using Distance Analysis