imputeByModule: Impute missing data separately in each module

In WGCNA: Weighted Correlation Network Analysis

Impute missing data separately in each module

Description

Use impute.knn to ipmpute missing data, separately in each module.

Usage

imputeByModule(
  data, 
  labels, 
  excludeUnassigned = FALSE, 
  unassignedLabel = if (is.numeric(labels)) 0 else "grey", 
  scale = TRUE, 
  ...)

Arguments

data	Data to be imputed, with variables (genes) in columns and observations (samples) in rows.
labels	Module labels. A vector with one entry for each column in data.
excludeUnassigned	Logical: should unassigned variables (genes) be excluded from the imputation?
unassignedLabel	The value in labels that represents unassigned variables.
scale	Logical: should data be scaled to mean 0 and variance 1 before imputation?
...	Other arguments to impute.knn.

Value

The input data with missing values imputed.

Note

This function is potentially faster but could give different imputed values than applying impute.knn directly to (scaled) data.

Author(s)

Peter Langfelder

See Also

impute.knn that does the actual imputation.

WGCNA documentation built on Sept. 18, 2024, 5:08 p.m.