In previous versions of R and bioconductor, I was able to make an initial call to lme(), then use update() inside a loop. I can still do that if I don't load any bioconductor packages. For example, library(nlme) ge <- xx[1,] age <- c(0,0,1,1,0,0,1,1,0,0,1,1) gen <- c(0,1,0,1,0,1,0,1,0,1,0,1) fdr <- c(0,0,0,0,1,1,1,1,3,3,3,3) dat <- data.frame(age, gen, fdr, ge) ge.lme <- lme(fixed=ge~age+gen+age*gen, data=dat, random=~ 1| fdr) update(ge.lme) works fine. If I then load affy and try update() again, I get an error: library(affy) update(ge.lme) Error in update(ge.lme) : No direct or inherited method for function "update" for this call I am using windows 2000 and the following packages: base 1.9.0 utils 1.9.0 graphics 1.9.0 stats 1.9.0 methods 1.9.0 nlme 3.1-48 Biobase 1.4.14 affy 1.4.30 xtable 1.2-1 Would anyone have an idea of what is happening? Thanks, Dick ********************************************************************** ********* Richard P. Beyer, Ph.D. University of Washington Tel.:(206) 616 7378 Env. & Occ. Health Sci. , Box 354695 Fax: (206) 685 4696 4225 Roosevelt Way NE, # 100 Seattle, WA 98105-6099 http://depts.washington.edu/ceeh/ServiceCores/FC5/FC5.html

> Would anyone have an idea of what is happening? I do. There's a bug... Thanks for reporting. If you copy/paste the following line into your R session, it should solve the problem: setMethod("update", "ANY", update.default) (note the affy pack must be loaded) I'll patch the affy pack with that fix ASAP. Thanks again, L.