classifySamples: Dichotimize a training expression set and fit a logistic...

In SiYangming/pRRophetic: Predict clinical chemotherapeutic response from before-treatment tumor gene expression levels.

Dichotimize a training expression set and fit a logistic ridge regression model which is applied to the test expression matirx.

Description

Dichotimize a training expression set and fit a logistic ridge regression model which is applied to the test expression matirx. This function will return a set of probabilities.

Usage

classifySamples(trainingExprData, trainingPtype, testExprData,
  batchCorrect = "eb", minNumSamples = 10, selection = -1,
  printOutput = TRUE, numGenesSelected = 1000, numSens = 15,
  numRes = 55)

Arguments

trainingExprData	- Gene expression matrix for samples for which we the phenotype is already known.
trainingPtype	The known phenotype, a vector in the same order as the columns of "trainingExprData" or with the same names as colnames of "trainingExprData".
testExprData	Gene expression matrix for samples on which we wish to predict a phenotype. Gene names as rows, samples names as columns.
batchCorrect	The type of batch correction to be used. Options are "eb", "none", .....
minNumSamples	The minimum number of test samples, print an error if the number of columns of "testExprData" is below this threshold. A large number of test samples may be necessary to correct for batch effects.
selection	How should duplicate gene ids be handled. Default is -1 which asks the user. 1 to summarize by their or 2 to disguard all duplicates.
printOutput	Set to FALSE to supress output
numGenesSelected	Specifies how genes are selected for "variableSelectionMethod". Options are "tTests", "pearson" and "spearman".
numSens	The number of sensitive cell lines to be fit in the logistic regression model.
numRes	The number of resistant cell lines fit in the logistic regression model.

SiYangming/pRRophetic documentation built on July 13, 2022, 10:36 p.m.