MSIseq (version 1.0.0)

MSIseq.train: Build Microsatellite Instability Classification Model with Training Dataset

Description

This function generate a detector for MSI status based on the mutation information in the mutationNum parameter.

Usage

MSIseq.train(mutationNum, classification, cancerType = NULL)

Arguments

mutationNum

A data frame output from Compute.input.variables, which containing 9 variables: T.sns, S.sns, T.ind, S.ind, T, S, Ratio.sns, Ratio.ind, Ratio.

classification

A data frame with two columns: Tumor_Sample_Barcode (tumor ID) and the corresponding MSI_status. Check NGStrainclass for detail.

cancerType

A data frame with two columns: Tumor_Sample_Barcode (tumor ID) and the corresponding cancer_type. Check NGStraintype for detail.

Value

A Weka_classifier object: a decision tree model built with the 'RWeka' function J48()

Details

This function builds and evaluates a decision tree model from mutationNum.

References

Kurt Hornik, Christian Buchta, Achim Zeileis (2009) Open-Source Machine Learning: R Meets Weka. Computational Statistics, 24(2), 225-232.

See Also

MSIseq.classify, Compute.input.variables

Examples

## load sample data (train.mutationNum, NGStraintype, 
## NGStrainclass)

data(train.mutationNum)
data(NGStrainclass)
data(NGStraintype)

## create NGSclassifier with traindata
## note that this is a built-in classifier, which can be directly used 
## if you do not have your own training data to create a classifier

NGSclassifier<-MSIseq.train(mutationNum = train.mutationNum, 
  classification=NGStrainclass, cancerType=NGStraintype)