compute_umap: Compute UMAPs.
In mirvie/mirmodels: Models Built by the Informatics Team at Mirvie

Description Usage Arguments Value Examples

Computation is be done using the embed package.

1	compute_umap(df, num_comp = 2, subset = NULL)

`df`	A data frame.
`num_comp`	A positive integer. The number of UMAP components to compute.
`subset`	A character vector. The subset of columns to use for UMAP calculation. Default is all columns. Columns in `df` outside of this subset will be kept in the result.

A data frame with the UMAP components.

if (rlang::is_installed("mirmisc")) {
  ga_data <- get_ga_data(
    log2 = TRUE,
    gene_predicate = ~ median(.) > 0
  )
  genes <- dplyr::intersect(names(ga_data), mirmisc::get_gene_names())
  umap <- compute_umap(ga_data, subset = genes)
  ggplot2::ggplot(
    umap,
    ggplot2::aes(umap_1, umap_2, color = meta_collectionga)
  ) +
    ggplot2::geom_point() +
    ggplot2::scale_color_viridis_c()
}