Generic imputation return function

Source: R/scMethrix_transforms.R

Generic imputation return function

impute_regions(
  scm = NULL,
  assay = "score",
  new_assay = "impute",
  regions = NULL,
  n_chunks = 1,
  n_threads = 1,
  overlap_type = c("within", "start", "end", "any", "equal"),
  type = c("kNN", "iPCA", "RF"),
  verbose = TRUE,
  k = 10,
  n_pc = 2,
  ...
)

Arguments

scm

scMethrix; the single cell methylation experiment
assay

string; name of an existing assay. Default = "score"
new_assay

string; name for transformed assay. Default = "new_assay"
regions

Granges; the regions to impute. Default is by chromosome.
n_chunks

integer; Number of chunks to split the scMethrix object in case it is very large. Default = 1
n_threads

integer; Maximum number of parallel instances. Default = 1
overlap_type

defines the type of the overlap of the CpG sites with the target region. Default value is within. For detailed description, see the findOverlaps function of the IRanges package.
type

string/closure; the imputation to perform "kNN","iPCA",or "RF". Otherwise, a closure can be specified that returns the imputed matrix. Default = "kNN"
verbose

boolean; Flag for outputting function status messages. Default = TRUE
k

Number of neighbors to be used in the imputation (default=10)
n_pc

the range of principal components to check when using iPCA. Caution: this can be very time-intensive
...

further arguments passed to or from other methods

Value

list; two scMethrix objects names 'training' and 'test'

Details

Uses the specified imputation operation to evaluation an scMethrix object.

References

Hastie T, Tibshirani R, Narasimhan B, Chu G (2021). impute: impute: Imputation for microarray data. R package version 1.66.0.

Stekhoven, D. J., & Bühlmann, P. (2012). MissForest—non-parametric missing value imputation for mixed-type data. Bioinformatics, 28(1), 112-118.

Bro, R., Kjeldahl, K. Smilde, A. K. and Kiers, H. A. L. (2008) Cross-validation of component models: A critical look at current methods. Analytical and Bioanalytical Chemistry, 5, 1241-1251.

Josse, J. and Husson, F. (2011). Selecting the number of components in PCA using cross-validation approximations. Computational Statistics and Data Analysis. 56 (6), pp. 1869-1879.

Examples

data('scMethrix_data')
impute_regions(scMethrix_data)

#> Starting imputation...
#> Imputed in 0.04s
#> An object of class scMethrix
#>    n_CpGs: 286
#>    n_samples: 4
#>    assays: score, counts, impute
#>    reduced dims: 
#>    is_h5: FALSE
#>    Reference: hg19
#>    Physical size: 56.7 Kb