[BioC] Multiple regression, how to do fit all/stepwise/backward methods

[andrea.grilli at ior.it]

Hi to all,
I want to perform multiple regression analysis, to see if expression  
of some miRs could influence growth agar (as number of cells) in a  
group of cell lines.

I've imported log2 expression data from previous array analysis for  
miRs, and I log2 transformed number of cells. I can calculate linear  
regression with lm, and I used same procedure for multiple regression,  
as follow:

matrix <- read.table("expression_file.txt", header = TRUE, sep = "\t")
attach(matrix)
miRs = cbind(miR-1, miR-2, miR-3, miR-4, miR-x)
agar_log = cbind(log2_n_colonies)
model = lm(agar_log ~ miRs)
summary(model)

Do you know if lm can also perform the so-called (i) fit all (ii)  
stepwise regression or (iii) backward regression methods to calculate  
most significant model? Do you know if others packages can do it?

I'm pretty new to Bioconductor and I didn't find how to do this analysis.
Thanks in advance,
Andrea


Dr. Andrea Grilli
andrea.grilli at ior.it
phone 051/63.66.756

Laboratory of Experimental Oncology
Rizzoli Orthopaedic Institute
Codivilla Putti Research Center
via di Barbiano 1/10
40136 - Bologna - Italy