Description Usage Arguments Value Examples

Performs a fast two-step clustering: first clusters using k-means with a very large k, then uses louvain clustering of the k cluster averages and reports back the cluster labels.

1 2 3 4 5 6 7 8 9 10 11 | ```
fastcluster(
x,
k = NULL,
rdname = "PCA",
nstart = 3,
iter.max = 20,
ndims = NULL,
nfeatures = 1000,
returnType = c("clusters", "preclusters", "metacells", "graph"),
BPPARAM = SerialParam()
)
``` |

`x` |
An object of class SCE |

`k` |
The number of k-means clusters to use in the primary step (should be much higher than the number of expected clusters). Defaults to 1/10th of the number of cells with a maximum of 3000. |

`rdname` |
The name of the dimensionality reduction to use. |

`nstart` |
Number of starts for k-means clustering |

`iter.max` |
Number of iterations for k-means clustering |

`ndims` |
Number of dimensions to use |

`nfeatures` |
Number of features to use (ignored if 'rdname' is given and the corresponding dimensional reduction exists in 'sce') |

`returnType` |
See return. |

`BPPARAM` |
'BiocParallel' BPPARAM for multithreading. |

By default, a vector of cluster labels. If ‘returnType=’preclusters'', returns the k-means pre-clusters. If ‘returnType=’metacells'', returns the metacells aggretated by pre-clusters and the corresponding cell indexes. If ‘returnType=’graph'', returns the graph of (meta-)cells and the corresponding cell indexes.

1 2 | ```
sce <- mockDoubletSCE()
sce$cluster <- fastcluster(sce)
``` |

Embedding an R snippet on your website

Add the following code to your website.

For more information on customizing the embed code, read Embedding Snippets.