Drug and Biomarker Discovery

---

Documentation for package ‘oncoPredict’ version 0.2

• DESCRIPTION file.
• User guides, package vignettes and other documentation.

Help Pages

calcPhenotype	This function predicts a phenotype (drug sensitivity score) when provided with microarray or bulk RNAseq gene expression data of different platforms. The imputations are performed using ridge regression, training on a gene expression matrix where phenotype is already known. This function integrates training and testing datasets via a user-defined procedure, and power transforming the known phenotype.
completeMatrix	This function performs an iterative matrix completion algorithm to predict drug response for pre-clinical data when there are missing ('NA') values.
doVariableSelection	This function performs variable selection on gene expression matrices. It can, for instance, remove genes with low variation.
glds	This function determines drug-gene associations for pre-clinical data.
homogenizeData	This function takes two gene expression matrices (like trainExprMat and testExprMat) and returns homogenized versions of the matrices by employing the homogenization method specified. By default, the Combat method from the sva library is used. In both matrices, genes are row names and samples are column names. It will deal with duplicated gene names, as it subsets and orders the matrices correctly.
idwas	This function will test every drug against every CNV or somatic mutation for your cancer type.
map_cnv	This function maps cnv data to genes. The output of this function is a .RData file called map.RData; this file contains theCnvQuantVecList_mat (rows are genes, and columns are samples) and tumorSamps (indicates which samples are primary tumor samples, 01A).
summarizeGenesByMean	This function takes a gene expression matrix and if duplicate genes are measured, summarizes them by their means.