FeatureSelectionState

FeatureSelectionState

Feature selection is performed by modelling the per-gene variance and finding highly variable genes. This wraps the modelGeneVariances function from scran.js.

Methods not documented here are not part of the stable API and should not be used by applications.

Classes

FeatureSelectionState

Methods

compute(parameters)

Description:

  • This method should not be called directly by users, but is instead invoked by runAnalysis.

Source:
Parameters:
Name Type Description
parameters object

Parameter object, equivalent to the feature_selection property of the parameters of runAnalysis.

Properties
Name Type Description
span number

Value between 0 and 1 specifying the span for the LOWESS smoother.
Returns:

The object is updated with the new results.

fetchParameters() → {object}

Source:
Returns:

Object containing the parameters.

Type
object

fetchResults() → {external:ModelGeneVarResults}

Source:
Returns:

Variance modelling results, available after running compute.

Type
external:ModelGeneVarResults

fetchSortedResiduals() → {Float64Array}

Source:
Returns:

Array of length equal to the number of genes, containing the sorted residuals after fitting a mean-dependent trend to the variances. Available after running compute.

Type
Float64Array