cvSelectParams: Fold-Specific Selection of Contrastive and Penalization...
In PhilBoileau/scPCA: Sparse Contrastive Principal Component Analysis

cvSelectParams

R Documentation

Fold-Specific Selection of Contrastive and Penalization Parameters

Description

A wrapper function for fitting various internal functions to select the optimal setting of the contrastive and penalization parameters via cross-validation. For internal use only.

Usage

cvSelectParams(
  fold,
  target,
  background,
  center,
  scale,
  n_eigen,
  alg = alg,
  contrasts,
  penalties,
  clust_method,
  n_centers,
  max_iter,
  linkage_method,
  n_medoids,
  parallel,
  clusters,
  eigdecomp_tol,
  eigdecomp_iter,
  scaled_matrix
)

Arguments

`fold`	Object specifying cross-validation folds as generated by a call to `make_folds`.
`target`	The target (experimental) data set, in a standard format such as a `data.frame` or `matrix`.
`background`	The background data set, in a standard format such as a `data.frame` or `matrix`. Note that the number of features must match the number of features in the target data.
`center`	A `logical` indicating whether the target and background data sets should be centered to mean zero.
`scale`	A `logical` indicating whether the target and background data sets should be scaled to unit variance.
`n_eigen`	A `numeric` indicating the number of eigenvectors (or sparse contrastive components) to be computed. The default is to compute two such eigenvectors.
`alg`	A `character` indicating the SPCA algorithm used to sparsify the contrastive loadings. Currently supports `iterative` for the \insertCitezou2006sparse;textualscPCA implementation, `var_proj` for the non-randomized \insertCiteerichson2018sparse;textualscPCA solution, and `rand_var_proj` for the randomized \insertCiteerichson2018sparse;textualscPCA result.
`contrasts`	A `numeric` vector of the contrastive parameters. Each element must be a unique non-negative real number. The default is to use 40 logarithmically spaced values between 0.1 and 1000.
`penalties`	A `numeric` vector of the L1 penalty terms on the loadings. The default is to use 20 equidistant values between 0.05 and 1.
`clust_method`	A `character` specifying the clustering method to use for choosing the optimal contrastive parameter. Currently, this is limited to either k-means, partitioning around medoids (PAM), and hierarchical clustering. The default is k-means clustering.
`n_centers`	A `numeric` giving the number of centers to use in the clustering algorithm. If set to 1, cPCA, as first proposed by Abid et al., is performed, regardless of what the `penalties` argument is set to.
`max_iter`	A `numeric` giving the maximum number of iterations to be used in k-means clustering, defaulting to 10.
`linkage_method`	A `character` specifying the agglomerative linkage method to be used if `clust_method = "hclust"`. The options are `ward.D2`, `single`, `complete`, `average`, `mcquitty`, `median`, and `centroid`. The default is `complete`.
`n_medoids`	A `numeric` indicating the number of medoids to consider if `n_centers` is set to 1. The default is 8 such medoids.
`parallel`	A `logical` indicating whether to invoke parallel processing via the BiocParallel infrastructure. The default is `FALSE` for sequential evaluation.
`clusters`	A `numeric` vector of cluster labels for observations in the `target` data. Defaults to `NULL`, but is otherwise used to identify the optimal set of hyperparameters when fitting the scPCA and the automated version of cPCA.
`eigdecomp_tol`	A `numeric` providing the level of precision used by eigendecompositon calculations. Defaults to `1e-10`.
`eigdecomp_iter`	A `numeric` indicating the maximum number of interations performed by eigendecompositon calculations. Defaults to `1000`.
`scaled_matrix`	A `logical` indicating whether to output a `ScaledMatrix` object. The centering and scaling procedure is delayed until later, permitting more efficient matrix multiplication and row or column sums downstream. However, this comes at the at the cost of numerical precision.

Value

Output structure matching either that of fitCPCA or fitGrid (or their parallelized variants, namely either bpFitCPCA and link{bpFitGrid}, respectively).