Giotto clustering — giotto_clust • Kandinsky

Giotto clustering performed by calling the R package Giotto through Kandinsky

giotto_clust(
  data = NULL,
  n_clust = 5,
  ngenes = NULL,
  betas = c(0, 5),
  seed = 347548,
  cores = 1,
  python_path = NULL
)

Arguments

data: Seurat object containing Kandinsky data
n_clust: numeric, number of expected clusters. Can be a single number or a numeric vector if multiple cluster numbers needs to be tested
ngenes: numeric, number of top variable genes to consider for HMRF domain identification Default is 250. If dataset contains less than 250 genes, all genes will be considered.
betas: numeric vector of beta values to use for Giotto HMRF domain identification. Currently only supports two beta values at a time
seed: numeric, random seed.
cores: numeric, number of cores to use for parallelization
python_path: path of python environment with MESA and its dependencies installed

updated Seurat object with 'giotto_clusters' annotation added to metadata slot for each beta value

Giotto must be installed within the same environmnent of Kandinsky