| impute_test_met {Melissa} | R Documentation |
Make predictions of missing methylation states, i.e. perfrom
imputation using Melissa. This requires keepin a subset of data as a held
out test set during Melissa inference. If you want to impute a whole
directory containing cells (files) with missing methylation levels, see
impute_met_files.
impute_test_met( obj, test, basis = NULL, is_predictive = TRUE, return_test = FALSE )
obj |
Output of Melissa inference object. |
test |
Test data to evaluate performance. |
basis |
Basis object, if NULL we perform imputation using Melissa, otherwise using BPRMeth. |
is_predictive |
Logical, use predictive distribution for imputation, or choose the cluster label with the highest responsibility. |
return_test |
Whether or not to return a list with the predictions. |
A list containing two vectors, the true methylation state and the predicted/imputed methylation states.
C.A.Kapourani C.A.Kapourani@ed.ac.uk
create_melissa_data_obj, melissa,
filter_regions, eval_imputation_performance,
eval_cluster_performance
# Extract synthetic data
dt <- melissa_synth_dt
# Partition to train and test set
dt <- partition_dataset(dt)
# Create basis object from BPRMeth package
basis_obj <- BPRMeth::create_rbf_object(M = 3)
# Run Melissa
melissa_obj <- melissa(X = dt$met, K = 2, basis = basis_obj, vb_max_iter=10,
vb_init_nstart = 1, is_parallel = FALSE, is_verbose = FALSE)
imputation_obj <- impute_test_met(obj = melissa_obj,
test = dt$met_test)