Fork me on GitHub

umap: Uniform Manifold Approximation and ProjectionΒΆ

Docstring:

Usage: qiime diversity umap [OPTIONS]

  Apply Uniform Manifold Approximation and Projection.

Inputs:
  --i-distance-matrix ARTIFACT
    DistanceMatrix       The distance matrix on which UMAP should be
                         computed.                                  [required]
Parameters:
  --p-number-of-dimensions INTEGER
    Range(2, None)       Dimensions to reduce the distance matrix to.
                                                                  [default: 2]
  --p-n-neighbors INTEGER
    Range(1, None)       Provide the balance between local and global
                         structure. Low values prioritize the preservation of
                         local structures. Large values sacrifice local
                         details for a broader global embedding. [default: 15]
  --p-min-dist NUMBER    Controls the cluster size. Low values cause clumpier
    Range(0, None)       clusters. Higher values preserve a broad topological
                         structure. To get less overlapping data points the
                         default value is set to 0.4. For more details visit:
                         https://umap-learn.readthedocs.io/en/latest/parameter
                         s.html                                 [default: 0.4]
  --p-random-state INTEGER
                         Seed used by random number generator.      [optional]
Outputs:
  --o-umap ARTIFACT      The resulting UMAP matrix.
    PCoAResults                                                     [required]
Miscellaneous:
  --output-dir PATH      Output unspecified results to a directory
  --verbose / --quiet    Display verbose output to stdout and/or stderr
                         during execution of this action. Or silence output if
                         execution is successful (silence is golden).
  --example-data PATH    Write example data and exit.
  --citations            Show citations and exit.
  --use-cache DIRECTORY  Specify the cache to be used for the intermediate
                         work of this action. If not provided, the default
                         cache under $TMP/qiime2/ will be used.
                         IMPORTANT FOR HPC USERS: If you are on an HPC system
                         and are using parallel execution it is important to
                         set this to a location that is globally accessible to
                         all nodes in the cluster.
  --help                 Show this message and exit.

Import:

from qiime2.plugins.diversity.methods import umap

Docstring:

Uniform Manifold Approximation and Projection

Apply Uniform Manifold Approximation and Projection.

Parameters
----------
distance_matrix : DistanceMatrix
    The distance matrix on which UMAP should be computed.
number_of_dimensions : Int % Range(2, None), optional
    Dimensions to reduce the distance matrix to.
n_neighbors : Int % Range(1, None), optional
    Provide the balance between local and global structure. Low values
    prioritize the preservation of local structures. Large values sacrifice
    local details for a broader global embedding.
min_dist : Float % Range(0, None), optional
    Controls the cluster size. Low values cause clumpier clusters. Higher
    values preserve a broad topological structure. To get less overlapping
    data points the default value is set to 0.4. For more details visit:
    https://umap-learn.readthedocs.io/en/latest/parameters.html
random_state : Int, optional
    Seed used by random number generator.

Returns
-------
umap : PCoAResults
    The resulting UMAP matrix.