optSNE-class | R Documentation |
A opt-SNE object that holds pertinent opt-SNE advanced analysis run information. This class should never be called explicitly. If a user would like to create a new Cytobank opt-SNE object, utilize the dimensionality_reduction.new function, or any other opt-SNE endpoints that return opt-SNE objects documented in the 'Details' section.
A Dimensionality Reduction advanced analysis object
perplexity
numeric representing a rough guess for the number of close neighbors any given cellular event will have, learn more about Dimensionality Reduction perplexity
auto_learning_rate
logical representing whether or not to set auto learning rate
clustering_channels
list the channels selected for the Dimensionality Reduction analysis, this can be either a list of short channel IDs (integer) OR long channel names (character)
desired_events_per_file
numeric representing the number of desired events per file
desired_total_events
numeric representing the number of desired total events per file
early_exaggeration
numeric representing how tight natural clusters in the original space are in the embedded space and how much space will be between them
event_sampling_method
character representing the name of event sampling method will be used, learn more about Event Sampling for Dimensionality Reduction analysis
fcsfile_ids
list representing the fcs file ids
gateset_id
numeric representing the selected gate id
learning_rate
numeric representing the learning rate,learn more about opt-SNE learning rate.
max_iterations
numeric representing the maximum number of iterations to perform– typically opt-SNE will automatically stop before this number is reached
normalize_scales
logical representing whether or not to normalize scales
random_seed
numeric representing the seed, Dimensionality Reduction picks a random seed each run, but if users want reproducible data, setting the same seed will allow them to do this
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.