doKmeans

cluster cells using kmeans algorithm

doKmeans(
  gobject,
  feat_type = NULL,
  spat_unit = NULL,
  expression_values = c("normalized", "scaled", "custom"),
  feats_to_use = NULL,
  dim_reduction_to_use = c("cells", "pca", "umap", "tsne"),
  dim_reduction_name = "pca",
  dimensions_to_use = 1:10,
  distance_method = c("original", "pearson", "spearman", "euclidean", "maximum",
    "manhattan", "canberra", "binary", "minkowski"),
  centers = 10,
  iter_max = 100,
  nstart = 1000,
  algorithm = "Hartigan-Wong",
  name = "kmeans",
  return_gobject = TRUE,
  set_seed = TRUE,
  seed_number = 1234
)

Arguments

gobject

giotto object

feat_type

feature type (e.g. "cell")

spat_unit

spatial unit (e.g. "rna", "dna", "protein")

expression_values

expression values to use (e.g. "normalized", "scaled", "custom")

feats_to_use

subset of features to use

dim_reduction_to_use

dimension reduction to use (e.g. "cells", "pca", "umap", "tsne")

dim_reduction_name

dimensions reduction name, default to "pca"

dimensions_to_use

dimensions to use, default = 1:10

distance_method

distance method (e.g. "original", "pearson", "spearman", "euclidean", "maximum", "manhattan", "canberra", "binary", "minkowski")

centers

number of final clusters, default = 10

iter_max

kmeans maximum iterations, default = 100

nstart

kmeans nstart, default = 1000

algorithm

kmeans algorithm, default to "Hartigan-Wong"

name

name for kmeans clustering, default to "kmeans"

return_gobject

boolean: return giotto object (default = TRUE)

set_seed

set seed (default = TRUE)

seed_number

number for seed

Value

giotto object with new clusters appended to cell metadata

Details

Description on how to use Kmeans clustering method.

See also

kmeans

Examples

g <- GiottoData::loadGiottoMini("visium")
#> 1. read Giotto object
#> 2. read Giotto feature information
#> 3. read Giotto spatial information
#> 3.1 read Giotto spatial shape information
#> cell_spatInfo_spatVector.shp
#> cell
#> 
#> 3.2 read Giotto spatial centroid information
#> cell
#> 
#> 3.3 read Giotto spatial overlap information
#> No overlaps were found, overlap loading will be
#>  skipped
#> 
#> 4. read Giotto image information
#> a giotto python environment was found
#> Using python path:
#>  "/Users/yuanlab/Library/r-miniconda/envs/giotto_env/bin/pythonw"

doKmeans(g)
#> An object of class giotto 
#> >Active spat_unit:  cell 
#> >Active feat_type:  rna 
#> [SUBCELLULAR INFO]
#> polygons      : cell 
#> [AGGREGATE INFO]
#> expression -----------------------
#>   [cell][rna] raw normalized scaled
#> spatial locations ----------------
#>   [cell] raw
#> spatial networks -----------------
#>   [cell] Delaunay_network spatial_network
#> spatial enrichments --------------
#>   [cell][rna] cluster_metagene DWLS
#> dim reduction --------------------
#>   [cell][rna] pca custom_pca umap custom_umap tsne
#> nearest neighbor networks --------
#>   [cell][rna] sNN.pca custom_NN
#> attached images ------------------
#> images      : alignment image 
#> 
#> 
#> Use objHistory() to see steps and params used