1 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.

## Loading required package: a4Core
## Loading required package: a4Preproc
## 
## a4Classif version 1.38.0
## Loading required package: Biobase
## Loading required package: BiocGenerics
## Loading required package: parallel
## 
## Attaching package: 'BiocGenerics'
## The following objects are masked from 'package:parallel':
## 
##     clusterApply, clusterApplyLB, clusterCall, clusterEvalQ,
##     clusterExport, clusterMap, parApply, parCapply, parLapply,
##     parLapplyLB, parRapply, parSapply, parSapplyLB
## The following objects are masked from 'package:stats':
## 
##     IQR, mad, sd, var, xtabs
## The following objects are masked from 'package:base':
## 
##     Filter, Find, Map, Position, Reduce, anyDuplicated, append,
##     as.data.frame, basename, cbind, colnames, dirname, do.call,
##     duplicated, eval, evalq, get, grep, grepl, intersect, is.unsorted,
##     lapply, mapply, match, mget, order, paste, pmax, pmax.int, pmin,
##     pmin.int, rank, rbind, rownames, sapply, setdiff, sort, table,
##     tapply, union, unique, unsplit, which.max, which.min
## Welcome to Bioconductor
## 
##     Vignettes contain introductory material; view with
##     'browseVignettes()'. To cite Bioconductor, see
##     'citation("Biobase")', and for packages 'citation("pkgname")'.

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)
## Loading required package: hgu95av2.db
## Loading required package: AnnotationDbi
## Loading required package: stats4
## Loading required package: IRanges
## Loading required package: S4Vectors
## 
## Attaching package: 'S4Vectors'
## The following object is masked from 'package:base':
## 
##     expand.grid
## Loading required package: org.Hs.eg.db
## 
## 
ALL$BTtype <- as.factor(substr(ALL$BT,0,1))

2 Classify microarray data

2.1 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)
## The lasso selected 16 genes. The top 15 genes are:
## 
##             Gene Coefficient
## 38319_at    CD3D  0.95966733
## 35016_at    CD74 -0.60928095
## 38147_at  SH2D1A  0.49240967
## 35792_at    MGLL  0.46856925
## 37563_at  SRGAP3  0.26648240
## 38917_at  YME1L1  0.25100075
## 40278_at    GGA2 -0.25017550
## 41164_at    IGHM -0.12387272
## 41409_at THEMIS2 -0.10581122
## 38242_at    BLNK -0.10309606
## 35523_at   HPGDS  0.10169706
## 38949_at   PRKCQ  0.07832802
## 33316_at     TOX  0.06963509
## 33839_at   ITPR2  0.05801832
## 40570_at   FOXO1 -0.04858863

2.2 PAM regression

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

topTable(resultPam, n = 15)
## Pam selected  1  genes. The top  15  genes are:
## 
##          GeneSymbol B.score T.score av.rank.in.CV prop.selected.in.CV
## 38319_at       CD3D -0.1693  0.4875             1                   1
confusionMatrix(resultPam)
##     predicted
## true  B  T
##    B 95  0
##    T  1 32

2.3 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)
## Random forest selected 6 genes. The top 15 genes are:
## 
##            GeneSymbol
## 35143_at        CYRIA
## 36062_at         LPXN
## 36885_at          SYK
## 38994_at        SOCS2
## 40151_s_at       PEX5
## 41682_s_at     BCKDHB

2.4 ROC curve

ROCcurve(gene = "ABL1", object = ALL, groups = "BTtype")
## Warning in ROCcurve(gene = "ABL1", object = ALL, groups = "BTtype"): Gene ABL1 corresponds to 6 probesets; only the first probeset ( 1635_at ) has been displayed on the plot.

3 Appendix

3.1 Session information

## R version 4.0.3 (2020-10-10)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 18.04.5 LTS
## 
## Matrix products: default
## BLAS:   /home/biocbuild/bbs-3.12-bioc/R/lib/libRblas.so
## LAPACK: /home/biocbuild/bbs-3.12-bioc/R/lib/libRlapack.so
## 
## locale:
##  [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C               LC_TIME=en_US.UTF-8        LC_COLLATE=C               LC_MONETARY=en_US.UTF-8    LC_MESSAGES=en_US.UTF-8    LC_PAPER=en_US.UTF-8       LC_NAME=C                  LC_ADDRESS=C               LC_TELEPHONE=C             LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       
## 
## attached base packages:
## [1] stats4    parallel  stats     graphics  grDevices utils     datasets  methods   base     
## 
## other attached packages:
##  [1] hgu95av2.db_3.2.3    org.Hs.eg.db_3.12.0  AnnotationDbi_1.52.0 IRanges_2.24.0       S4Vectors_0.28.0     ALL_1.31.0           Biobase_2.50.0       BiocGenerics_0.36.0  a4Classif_1.38.0     a4Preproc_1.38.0     a4Core_1.38.0       
## 
## loaded via a namespace (and not attached):
##  [1] Rcpp_1.0.5          compiler_4.0.3      iterators_1.0.13    tools_4.0.3         bit_4.0.4           digest_0.6.27       memoise_1.1.0       evaluate_0.14       RSQLite_2.2.1       lattice_0.20-41     pkgconfig_2.0.3     rlang_0.4.8         Matrix_1.2-18       foreach_1.5.1       DBI_1.1.0           yaml_2.2.1          xfun_0.18           stringr_1.4.0       knitr_1.30          pamr_1.56.1         cluster_2.1.0       vctrs_0.3.4         bit64_4.0.5         glmnet_4.0-2       
## [25] grid_4.0.3          varSelRF_0.7-8      survival_3.2-7      rmarkdown_2.5       blob_1.2.1          ROCR_1.0-11         magrittr_1.5        codetools_0.2-16    htmltools_0.5.0     splines_4.0.3       randomForest_4.6-14 shape_1.4.5         stringi_1.5.3