Skip to contents

Cluster samples by taxa abundances (k-means).

Source: R/clustering.r
taxa_clusters.Rd

Runs stats::kmeans() on the samples x taxa abundance matrix, with nstart = 10 random starts so that the partition is stable, and with the random number generator seeded by seed so that it is reproducible.

Usage

taxa_clusters(biom, rank = ".otu", k = 5, seed = 0, ...)

Arguments

biom

An rbiom object, or any value accepted by as_rbiom().

rank

Which taxa rank to use. E.g. "Phylum", "Genus", ".otu", etc. An integer can also be given, where 1 is the highest rank, 2 is the second highest, -1 is the lowest rank, -2 is the second lowest, and 0 is the OTU "rank". Run biom$ranks to see all options for a given rbiom object. Default: .otu.

k

Number of clusters. Default: 5L

seed

Random seed for the k-means starting centers. Default: 0

...

Passed on to stats::kmeans().

Value

A numeric factor assigning samples to clusters.

See also

Other taxa_abundance: sample_sums(), taxa_boxplot(), taxa_corrplot(), taxa_da(), taxa_forest(), taxa_heatmap(), taxa_stacked(), taxa_stats(), taxa_sums(), taxa_table()

Other clustering: bdiv_clusters()

Examples

    library(rbiom)

    biom <- rarefy(hmp50)
    biom$metadata$otu_cluster <- taxa_clusters(biom)

    pull(biom, 'otu_cluster')[1:10]
#> HMP01 HMP02 HMP03 HMP04 HMP05 HMP06 HMP07 HMP08 HMP09 HMP10 
#>     3     3     2     2     3     2     3     2     2     4 
#> Levels: 1 2 3 4 5

    bdiv_ord_plot(biom, layers = "p", stat.by = "otu_cluster")