IntegratedPrediction {IntegratedMRF}

Integrated Prediction of Testing samples from integrated RF or MRF model

Description

Generates Random Forest or Multivariate Random Forest model for each subtype of dataset and predicts testing samples using the generated models. Subsequently, the prediction for different subtypes of dataset are combined using the Combination weights generated from Integrated Model which is based on Bootstrap error estimate

Usage

IntegratedPrediction(finalX, finalY_train, Cell, finalY_train_cell,
  finalY_test_cell, n_tree, m_feature, min_leaf)

Arguments

finalX

List of Matrices where each matrix represent a specific data subtype (such as genomic characterizations for drug sensitivity prediction). Each subtype can have different types of features. For example, if there are three subtypes containing 100, 200 and 250 features respectively, finalX will be a list containing 3 matrices of sizes M x 100, M x 200 and M x 250 where M is the number of Samples.

finalY_train

A M x T matrix of output features for training samples, where M is number of samples and T is the number of output features. The dataset is assumed to contain no missing values. If there are missing values, an imputation method should be applied before using the function. A function 'Imputation' is included within the package.

Cell

It contains a list of samples (the samples can be represented either numerically by indices or by names) for each data subtype. For the example of 3 data subtypes, it will be a list containing 3 arrays where each array contains the sample information for each data subtype.

finalY_train_cell

Cell lines of output features for training samples

finalY_test_cell

Cell lines of output features for testing samples

n_tree

number of trees in the forest, which must be positive integer

m_feature

Number of randomly selected features considered for a split in each regression tree node, which must be positive integer

min_leaf

minimum number of samples in the leaf node, which must be positive integer and less than or equal to M (number of training samples)

Details

Input matrix and output response of training samples have been used to build Random Forest or Multivariate Random Forest model for each subtype of a dataset. These models are used to calculate prediction of testing samples for each subtype separately. Subsequently Combination Weights are used to integrate the predictions from data subtypes.

Combination Weight Generation: For M x N dataset, N number of bootstrap sampling sets are considered. For each bootstrap sampling set and each subtype, a Random Forest (RF) or, Multivariate Random Forest (MRF) model is generated, which is used for calculating the prediction performance for out-of-bag samples. The prediction performance for each dataset subtypes is based on the averaging over different bootstrap training sets. The combination weights (regression coefficients) for each combination of subtypes are generated using least Square Regression from the individual subtype predictions and used to integrate the predictions from data subtypes.

The specific set of combination weights to be used for testing samples will depend on the number of data subtypes available for the testing samples. Note that not all subtype information maybe available for all samples. As an example with three data subtypes, a testing sample with all subtype data available will use the combination weights corresponding to Serial [1 2 3] where as if subtype 3 is not available, the function will use the combination weights corresponding to Serial [1 2].

Value

Final Prediction of testing samples based on provided testing sample names.

Examples

library(IntegratedMRF)
data(Dream_Dataset)
Tree=1
Feature=1
Leaf=10
finalX=Dream_Dataset[[1]]
Cell=Dream_Dataset[[2]]
Y_train_Dream=Dream_Dataset[[3]]
Y_train_cell=Dream_Dataset[[4]]
Y_test=Dream_Dataset[[5]]
Y_test_cell=Dream_Dataset[[6]]
Drug=c(1,2,3)
Y_train_Drug=matrix(Y_train_Dream[,Drug],ncol=length(Drug))
IntegratedPrediction(finalX,Y_train_Drug,Cell,Y_train_cell,Y_test_cell,Tree,Feature,Leaf)