[BioC] MLInterfaces

Stephen Henderson s.henderson at ucl.ac.uk
Tue Mar 7 11:17:18 CET 2006


Hi
I don't know much about the Genespring software but you may want to
compare the various SVM control parameters. Or have you already done
this? 
The important ones are usually 

kernel, degree, gamma, and  cost 
you can see these parameters in the function typing

>svmB

with no call

I think that the MLInterfaces method is a wrapper (i.e. a consistent
interface) for the svm function in package "e1071". The documentation
for this package is fairly sparse as you are expected to look at the
originating methods for details. so try:

>library(e1071)
>?svm

to see specific details of these parameters

Stephen Henderson
Wolfson Inst. for Biomedical Research
Cruciform Bldg., Gower Street
University College London
United Kingdom, WC1E 6BT
+44 (0)207 679 6827


-----Original Message-----
From: bioconductor-bounces at stat.math.ethz.ch
[mailto:bioconductor-bounces at stat.math.ethz.ch] On Behalf Of
Qi.Zhang at astrazeneca.com
Sent: 06 March 2006 22:35
To: bioconductor at stat.math.ethz.ch
Subject: [BioC] MLInterfaces

Hi,  I am trying to use svmB in MLInterfaces for my analysis, and
results
look very different from what I got using svm in GeneSpring.  Does
anyone
here have experience with MLInterfaces, especially svmB?  how the
implementation of svm in MLInterfaces (or R) differ from that in
GeneSpring?
Thanks a lot.

_______________________________________________
Bioconductor mailing list
Bioconductor at stat.math.ethz.ch
https://stat.ethz.ch/mailman/listinfo/bioconductor

**********************************************************************
This email and any files transmitted with it are confidentia...{{dropped}}



More information about the Bioconductor mailing list