Skip to contents

Cluster spatial transcriptomics data

Usage

smooth_lrc(input, lambda, k, n_clust, epsilon = 0.001, maxiter = 1000)

Arguments

input

SummarizedExperiment object containing counts assay and row/col coordinates.

lambda

positive numeric; penalization parameter.

k

integer; indicates desired rank of singular value decomposition.

n_clust

integer; number of clusters.

epsilon

positive numeric; convergence criterion.

maxiter

positive integer; maximum desired iterations

Value

SummarizedExperiment object with u, v and cluster labels.

Examples


sce <- example_sce()
lambda <- 5
k <- 10
n_clust <- 5
epsilon <- 1e-3
maxiter <- 5
smooth_lrc(sce, lambda, k, n_clust, epsilon, maxiter)
#> [1] "Initializing components..."
#> [1] "Running smoothLRC..."
#> iteration: 1 | convergence: 0.100351 | 0.0337224 | 1
#> iteration: 2 | convergence: 0.0846095 | 0.0324173 | 0.00435998
#> iteration: 3 | convergence: 0.07633 | 0.0325976 | 0.00409897
#> iteration: 4 | convergence: 0.0713086 | 0.0329443 | 0.00396169
#> iteration: 5 | convergence: 0.0697088 | 0.0331661 | 0.00394547
#> [1] "Clustering right singular vectors..."
#> fitting ...
#> 
  |                                                                            
  |                                                                      |   0%
  |                                                                            
  |===================================                                   |  50%
  |                                                                            
  |======================================================================| 100%
#> [1] "Done!"
#> class: SummarizedExperiment 
#> dim: 1000 100 
#> metadata(2): smooth_u smooth_v
#> assays(2): counts logcounts
#> rownames(1000): Feature 1 Feature 2 ... Feature 999 Feature 1000
#> rowData names(0):
#> colnames(100): Pixel 1 Pixel 2 ... Pixel 99 Pixel 100
#> colData names(3): row col smooth_cluster