ChooseMethod: Method choice per gene
In ADImpute: Adaptive Dropout Imputer (ADImpute)

Description Usage Arguments Details Value See Also

ChooseMethod determines the method for dropout imputation based on performance on each gene in training data

1	ChooseMethod(real, masked, imputed, write.to.file = TRUE)

`real`	matrix; original gene expression data, i.e. before masking (genes as rows and samples as columns)
`masked`	matrix, logical indicating which entries were masked (genes as rows and samples as columns)
`imputed`	list; list of matrices with imputation results for all considered methods
`write.to.file`	logical; should the output be written to a file?

The imputed values are compared to the real ones for every masked entry in real. The Mean Squared Error is computed for all masked entries per gene and the method with the best performance is chosen for each gene.

character; best performing method in the training set for each gene

ComputeMSEGenewise

ADImpute documentation built on Nov. 8, 2020, 5:30 p.m.