Vignette of the a4Classif package

In a4Classif: Automated Affymetrix Array Analysis Classification Package

Introduction

This document explains the functionalities available in the a4Classif package.

This package contains for classification of Affymetrix microarray data, stored in an ExpressionSet. This package integrates within the Automated Affymetrix Array Analysis suite of packages.

    library(a4Classif)
    library(ALL)

To demonstrate the functionalities of the package, the ALL dataset is used. The genes are annotated thanks to the addGeneInfo utility function of the a4Preproc package.

data(ALL, package = "ALL")
ALL <- addGeneInfo(ALL)
ALL$BTtype <- as.factor(substr(ALL$BT,0,1))

Classify microarray data

Lasso regression

resultLasso <- lassoClass(object = ALL, groups = "BTtype")
plot(resultLasso, 
    label = TRUE, 
    main = "Lasso coefficients in relation to degree of penalization."
)
topTable(resultLasso, n = 15)

PAM regression

resultPam <- pamClass(object = ALL, groups = "BTtype")
plot(resultPam, 
    main = "Pam misclassification error versus number of genes."
)

topTable(resultPam, n = 15)

confusionMatrix(resultPam)

Random forest

# select only a subset of the data for computation time reason
ALLSubset <- ALL[sample.int(n = nrow(ALL), size = 100, replace = TRUE), ]

resultRf <- rfClass(object = ALLSubset, groups = "BTtype")
plot(resultRf)
topTable(resultRf, n = 15)

ROC curve

ROCcurve(gene = "ABL1", object = ALL, groups = "BTtype")

Appendix

Session information

print(sessionInfo())

a4Classif documentation built on Nov. 8, 2020, 6:55 p.m.