Introduction to R / sma / Bioconductor

Statistics for Microarray Data Analysis

The Fields Institute for Research in

Mathematical Sciences

May 25, 2002

Web sites + References

• http://www.R-project.org/

An introduction to RW.N.Venables, D.M.Smith and the R Development

Core Team

• http://lib.stat.cmu.edu/R/CRAN/• http://www.bioconductor.org/

Need to read files such as “swirl1.spot” or “samples.swirl” into the R programs. Functions:

read.tablescan

Save your workspace in RUsing the function

save.imageYou will only see

name.RData or.RData

In your directory

Download ?

Download SetupR.exe from http://cran.r-project.org/,

A few basics

• Working Directory- getwd()- setwd() or click on File and then click on Change Dir,

use Browse to determine your working directory.

• Workspace- save(a, b, file=“my.RData”) : save objects a and b into

the workpace “my.RData”- save.image(“my.RData”) : click on File and then click

on Save Workspace- load(“my.RData”) : click on File and then click on

Load Workspace

• Help- help.start()- help(): e.g. help(plot)

Search paths + packagessearch()> search()[1] ".GlobalEnv" "package:ctest" "Autoloads" "package:base"

library(cluster)search()> library(cluster)Loading required package: mva > search()[1] ".GlobalEnv" "package:mva" "package:cluster" "package:ctest" [5] "Autoloads" "package:base"

ls() : list objects in the GlovalEnvls(3) : list objects in search position number 3, in the above example, it is

package:cluster

R Base packages:basectestmvatcltk

etc…

Contributed packages:ellipseclustersma

GeneSOMhdarray

affyGeneClust

bioconductoretc …

mypackage

Submit to CRAN

An introduction to R

based on the documents produced by

W.N.Venables, D.M.Smith and the R Development Core Team

Vectors and assignment

R operates on named data structures. The simplest such structure is the numeric vector, which is a single entity consisting of an ordered collection of numbers.

To set up a vector named x, say, consisting of five numbers, namely 10.4, 5.6, 3.1, 6.4 and 21.7, use the R command x <- c(10.4, 5.6, 3.1, 6.4, 21.7) orassign(“x”, c(10.4, 5.6, 3.1, 6.4, 21.7))

This is an assignment statement using the function c()

This is a numeric vector> is.numeric(x)[1] TRUE

Character

numeric

vector

logical

X <- c(1:5, 6, 9,3, 10)

X <- c(“a”, “b”, “c3”, “4”)

X <- c(1, 1, 0, TRUE, FALSE)

Other types of objects

matrices or more generally arrays are multi-dimensional generalizations of vectors.

lists provide a convenient way to return the results of a statistical computation.

data frames are matrix-like structures, in which the columns can be of different types. Think of data frames as `data matrices' with one row per observational unit but with (possibly) both numerical and categorical variables.

functions are themselves objects in R which can be stored in the project's workspace. This provides a simple and

convenient way to extend R.

Introduction to Bioconductor(taken from http://www.bioconductor.org)

The packages in the initial release include tools which facilitate:

- annotation (AnnBuilder, annotate)

- data management and organization through the use of the S4 class structure (Biobase, marrayClasses)

- identification of differentially expressed genes and clustering (edd, genefilter, geneplotter, multtest, ROC)

- analysis of Affymetrix expression array data (affy)

- diagnostic plots and normalization for cDNA array data (marrayInput, marrayNorm, marrayPlots)

- storage and retrieval of large datasets (rhdf5).

Character numericlogical

Slots

Most packages rely on the class/method mechanism provided by John Chambers’ R methods package, whichallows object-oriented programming in R

Class

marrayInfo

maLabelscharacter

maInfodata.frame

maNotescharacter

This class can be used to store either the gene names Information or samples information

marrayLayout

maNscnumeric

maNsrnumeric

maNgcnumeric

maNgrnumeric

maNspotsnumeric

maSublogical

maPlatefactor

maControlsfactor

maSpotRownumeric

maSpotColnumeric

maGridRownumeric

maGridColnumeric

maPrintTipnumeric

Methods for quantities that are not slots of marrayLayout

marrayRaw

Methods for quantities that are not slots of marrayRaw

maLayoutmarrayLayout

maGnamesmarrayInfo

maTargetsmarrayInfo

maNotescharacter

maRfmatrix

maRbmatrix

maGf matrix

maGbmatrix

maWmatrix

maLRmatrix

maLG matrix

maMmatrix

maAmatrix

marrayNorm

maLayoutmarrayLayout

maGnamesmarrayInfo

maTargetsmarrayInfo

maNotescharacter

maNormCallcall

maAmatrix

maMmatrix

maMloc matrix

maMscalematrix

maWmatrix

Swirl data

Data (Spot Files)• swirl.1.spot• swirl.2.spot• swirl.3.spot• swirl.4.spot

Target information files• SwirlSample.txt

Gene List• fish.gal

Layout:Grid size: 4 by 4Spot matrix: 22 by 24