plot_dimred {MOFA2} | R Documentation |
Plot dimensionality reduction based on MOFA factors
plot_dimred( object, method = c("UMAP", "TSNE"), groups = "all", show_missing = TRUE, color_by = NULL, shape_by = NULL, color_name = NULL, shape_name = NULL, label = FALSE, dot_size = 1.5, stroke = NULL, alpha_missing = 1, legend = TRUE, rasterize = FALSE, return_data = FALSE, ... )
object |
a trained |
method |
string indicating which method has been used for non-linear dimensionality reduction (either 'umap' or 'tsne') |
groups |
character vector with the groups names, or numeric vector with the indices of the groups of samples to use, or "all" to use samples from all groups. |
show_missing |
logical indicating whether to include samples for which |
color_by |
specifies groups or values used to color the samples. This can be either: (1) a character giving the name of a feature present in the training data. (2) a character giving the same of a column present in the sample metadata. (3) a vector of the same length as the number of samples specifying discrete groups or continuous numeric values. |
shape_by |
specifies groups or values used to shape the samples. This can be either: (1) a character giving the name of a feature present in the training data, (2) a character giving the same of a column present in the sample metadata. (3) a vector of the same length as the number of samples specifying discrete groups. |
color_name |
name for color legend. |
shape_name |
name for shape legend. |
label |
logical indicating whether to label the medians of the clusters. Only if color_by is specified |
dot_size |
numeric indicating dot size. |
stroke |
numeric indicating the stroke size (the black border around the dots, default is NULL, infered automatically). |
alpha_missing |
numeric indicating dot transparency of missing data. |
legend |
logical indicating whether to add legend. |
rasterize |
logical indicating whether to rasterize plot using |
return_data |
logical indicating whether to return the long data frame to plot instead of plotting |
... |
This function plots dimensionality reduction projections that are stored in the dim_red
slot.
Typically this contains UMAP or t-SNE projections computed using run_tsne
or run_umap
, respectively.
Returns a ggplot2
object or a long data.frame (if return_data is TRUE)
# Using an existing trained model on simulated data file <- system.file("extdata", "model.hdf5", package = "MOFA2") model <- load_model(file) # Run UMAP model <- run_umap(model) # Plot UMAP plot_dimred(model, method = "UMAP") # Plot UMAP, colour by Factor 1 values plot_dimred(model, method = "UMAP", color_by = "Factor1") # Plot UMAP, colour by the values of a specific feature plot_dimred(model, method = "UMAP", color_by = "feature_0_view_0")