
Step: t-SNE
step_tsne.RdPerform t-SNE analysis using glystats::gly_tsne() and
plot a t-SNE plot using glyvis::plot_tsne().
Note that the result of t-SNE largely depends on the perplexity parameter.
Usually it's a trial-and-error process to find the best value iteratively.
If you are not satisfied with the result,
manually call glyvis::plot_tsne() with different perplexity values
to find the best one.
Arguments
- on
Name of the experiment to run t-SNE on. Can be "exp", "sig_exp", "trait_exp", "sig_trait_exp", "motif_exp", "sig_motif_exp".
- dims
Number of output dimensions. Default is 2.
- perplexity
Perplexity parameter for t-SNE. Default is 30.
- plot_width
Width of the plot in inches. Default is 5.
- plot_height
Height of the plot in inches. Default is 5.
- ...
Additional arguments passed to
Rtsne::Rtsne().
Details
Data required:
exp(ifon = "exp"): The experiment to perform t-SNE ontrait_exp(ifon = "trait_exp"): The trait experiment to perform t-SNE onmotif_exp(ifon = "motif_exp"): The motif experiment to perform t-SNE on
Data generated (with suffixes):
tsne: The t-SNE result
Plots generated (with suffixes):
tsne: The t-SNE plot
AI Prompt
This section is for AI in inquire_blueprint() only.
Include this step only when the user explicitly asks for t-SNE.