ICE_cv_entire: ICE cross-validation for entire circRNA matrix

In bioinformatist/ICE: ICE: Impute CircRNA Expression

Description

Convinient wrapper for ICE_cv that performs cross-validation analysis for assessing imputation accuracies for all circRNAs using the training datasets

Usage

ICE_cv_entire(
  train.pcg,
  train.circ,
  method = "KNN",
  cor.method = "spearman",
  ncores = 16,
  ...
)

Arguments

train.pcg	training protein coding dataset. a numeric matrix with with row names indicating samples, and column names indicating protein coding gene IDs.
train.circ	training circRNA expression dataset. a numeric matrix with row names indicating samples, and column names indicating circRNA IDs.
method	method for imputation, either "RF" for random forests, "KNN" for K-nearest neighbor or "SVM" for support vector machines.
cor.method	a character string indicating which correlation coefficient is to be used for the correlation test. Default is "spearman", could also be "pearson".
...	optional parameters that can be passed on to the machine-learning method: RF (randomForest), KNN (knn.reg) or SVM(svm)

Value

a matrix containing Spearman's correlation coefficient, P-value and RMSE from the cross-validation analysis of the complete circRNA training dataset

Examples

ICE_cv_entire(train.pcg = GA.pcg, train.circ = GA.mir, method = "KNN")
ICE_cv_entire(train.pcg = GA.pcg, train.circ = GA.mir, method = "SVM")

bioinformatist/ICE documentation built on July 5, 2020, 12:20 a.m.