R: Impute/predict methylation files

impute_met_files {Melissa}

R Documentation

Impute/predict methylation files

Description

Make predictions of missing methylation states, i.e. perfrom imputation using Melissa. Each file in the directory will be used as input and a new file will be created in outdir with an additional column containing the predicted met state (value between 0 and 1). Note that predictions will be made only on annotation regions that were used for training Melissa. Check impute_test_met, if you want to make predictions only on test data.

Usage

impute_met_files(
  met_dir,
  outdir = NULL,
  obj,
  anno_region,
  basis = NULL,
  is_predictive = TRUE,
  no_cores = NULL
)

Arguments

`met_dir`	Directory of methylation files, each file corresponds to a single cell. It should contain three columns <chr> <pos> <met_state> (similar to the input required by `create_melissa_data_obj`), where `met_state` can be any value that denotes missing CpG information, e.g. -1. Note that files can contain also CpGs for which we have coverage information, and we can check the predictions made by Melissa, hence the value can also be 0 (unmet) or (1) met. Predictions made by Melissa, will not change the <met_state> column. Melissa will just add an additional column named <predicted>.
`outdir`	Directory to store the output files for each cell with exactly the same name. If NULL, then a directory called 'imputed' inside 'met_dir' will be created by default.
`obj`	Output of Melissa inference object.
`anno_region`	Annotation region object. This will be the outpuf of `create_melissa_data_obj` function, e..g melissa_data$anno_region. This is required to select those regions that were used to train Melissa.
`basis`	Basis object, if NULL we perform imputation using Melissa, otherwise using BPRMeth (then `obj` should be BPRMeth output).
`is_predictive`	Logical, use predictive distribution for imputation, or choose the cluster label with the highest responsibility.
`no_cores`	Number of cores to be used for parallel processing of data.

Value

A new directory outdir containing files (cells) with predicted / imputed methylation states per CpG location.

Author(s)

C.A.Kapourani C.A.Kapourani@ed.ac.uk

Examples

## Not run: 
# Met directory
met_dir <- "name_of_met_dir"
# Annotation file name
anno_file <- "name_of_anno_file"
# Create data object
melissa_data <- create_melissa_data_obj(met_dir, anno_file)
# Run Melissa
melissa_obj <- melissa(X = melissa_data$met, K = 2)
# Annotation object
anno_region <- melissa_data$anno_region

# Peform imputation
impute_met_dir <- "name_of_met_dir_for_imputing_cells"
out <- impute_met_files(met_dir = impute_met_dir, obj = melissa_obj,
                        anno_region = anno_region)

## End(Not run)

[Package Melissa version 1.4.1 Index]