impute: Impute missing values from a fitted MOFA model

Description Usage Arguments Details Value Examples

View source: R/impute.R

Description

This function uses the latent factors and the loadings inferred in order to impute missing values.

Usage

1
2
impute(object, views = "all", factors = "all", type = c("inRange",
  "response", "link"))

Arguments

object

a MOFAmodel object.

views

character vector with the view names, or numeric vector with view indexes.

factors

character vector with the factor names, or numeric vector with the factor indexes.

type

type of prediction returned, either:

  • response: gives the response vector, the mean for Gaussian and Poisson, and success probabilities for Bernoulli.

  • link: gives the linear predictions.

  • inRange: rounds the fitted values of integer-valued distributions (Poisson and Bernoulli) to the next integer. This is the default option.

Details

Matrix factorization models generate a denoised and condensed low-dimensional representation of the data which capture the main sources of heterogeneity of the data. Such representation can be used to do predictions via the equation Y = WZ.
This method fills the ImputedData slot by replacing the missing values in the training data with the model predictions.
For more details see the Methods section of the MOFA article.

Value

a MOFAmodel object with imputed data in the ImputedData slot

Examples

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
# Load CLL data
filepath <- system.file("extdata", "CLL_model.hdf5", package = "MOFAdata")
MOFA_CLL <- loadModel(filepath)
# impute missing data in all views using all factors
MOFA_CLL <- impute(MOFA_CLL)

# Load scMT data
filepath <- system.file("extdata", "scMT_model.hdf5", package = "MOFAdata")
MOFA_scMT <- loadModel(filepath)
# impute missing data in the RNA view using Factor 1
MOFA_scMT <- impute(MOFA_scMT, views="RNA expression", factors="LF1")

MOFA documentation built on Feb. 11, 2021, 2:01 a.m.