Options for blocked_pca(). More...

#include <blocked_pca.hpp>

Public Attributes
int	number = 25

bool	scale = false

bool	transpose = true

scran_blocks::WeightPolicy	block_weight_policy = scran_blocks::WeightPolicy::VARIABLE

scran_blocks::VariableWeightParameters	variable_block_weight_parameters

bool	components_from_residuals = true

bool	realize_matrix = true

int	num_threads = 1

irlba::Options	irlba_options

Detailed Description

Options for blocked_pca().

Member Data Documentation

◆ block_weight_policy

scran_blocks::WeightPolicy scran_pca::BlockedPcaOptions::block_weight_policy = scran_blocks::WeightPolicy::VARIABLE

Policy to use for weighting batches of different size.

◆ components_from_residuals

bool scran_pca::BlockedPcaOptions::components_from_residuals = true

Compute the principal components from the residuals. If false, only the rotation vector is computed from the residuals, and the original expression values are projected onto the new axes.

◆ irlba_options

irlba::Options scran_pca::BlockedPcaOptions::irlba_options

Further options to pass to irlba::compute().

◆ num_threads

int scran_pca::BlockedPcaOptions::num_threads = 1

Number of threads to use. The parallelization scheme is determined by tatami::parallelize() and irlba::parallelize().

◆ number

int scran_pca::BlockedPcaOptions::number = 25

Number of principal components (PCs) to compute. This should be no greater than the maximum number of PCs, i.e., the smaller dimension of the input matrix, otherwise an error will be thrown. (This error can be avoided by setting irlba::Options::cap_number = true in BlockedPcaOptions::irlba_options, in which case only the maximum number of PCs will be reported in the results.)

◆ realize_matrix

bool scran_pca::BlockedPcaOptions::realize_matrix = true

Whether to realize tatami::Matrix objects into an appropriate in-memory format before PCA. This is typically faster but increases memory usage.

◆ scale

bool scran_pca::BlockedPcaOptions::scale = false

Should genes be scaled to unit variance? Genes with zero variance are ignored.

◆ transpose

bool scran_pca::BlockedPcaOptions::transpose = true

Should the PC matrix be transposed on output? If true, the output matrix is column-major with cells in the columns, which is compatible with downstream libscran steps.

◆ variable_block_weight_parameters

scran_blocks::VariableWeightParameters scran_pca::BlockedPcaOptions::variable_block_weight_parameters

Parameters for the variable block weights. Only used when BlockedPcaOptions::block_weight_policy = scran_blocks::WeightPolicy::VARIABLE.

The documentation for this struct was generated from the following file:

scran_pca/blocked_pca.hpp

Public Attributes