a question on creating model.matrix using limma
1
2
Entering edit mode
@srinivas-iyyer-939
Last seen 7.3 years ago
Dear Dr. Smith and group, apologies for simple question. I have data with simple plan. There are 8 samples (4 normal and 4 tumor). These tissue samples are from different patients. No replicate experiments were done. I wish to see genes differentially expressed between Tumors and normals. In such cases how can I create model.matrix Following is taken from Limma manual: design <- model.matrix(~ -1 + factor(c(1,1,1,2,2,3,3,3))) my question: 1. what is '~ -1' is for? 2. Will this work for my study structure. That means I have only two types of RNA 1. tumor and 2. Normal. design <- model.matrix(~ -1 + factor(c(1,1,1,1,2,2,2,2))). Thanks sri
limma limma • 4.8k views
ADD COMMENT
0
Entering edit mode
@james-w-macdonald-5106
Last seen 1 day ago
United States
Hi Srinivas, Srinivas Iyyer wrote: > Dear Dr. Smith and group, > > apologies for simple question. > > I have data with simple plan. There are 8 samples (4 > normal and 4 tumor). These tissue samples are from > different patients. No replicate experiments were > done. > I wish to see genes differentially expressed between > Tumors and normals. > > In such cases how can I create model.matrix > > > Following is taken from Limma manual: > > design <- model.matrix(~ -1 + > factor(c(1,1,1,2,2,3,3,3))) > > > my question: > 1. what is '~ -1' is for? The default for model.matrix() is to fit a model that has an intercept (or in the case of ANOVA, a baseline level). If you specify the model with either ~ -1 or ~ 0, then you are saying that you don't want an intercept. > 2. Will this work for my study structure. That means > I have only two types of RNA 1. tumor and 2. Normal. > design <- model.matrix(~ -1 + > factor(c(1,1,1,1,2,2,2,2))). This will work, but you will also need to fit a contrast between tumor and normal, so you will need something like this: design <- model.matrix(~-1 + factor(rep(1:2, each=4))) colnames(design) <- c("tumor","normal") contrast <- makeContrasts(tumor - normal, levels = design) fit <- lmFit(eset, design) fit2 <- contrasts.fit(fit, contrast) fit2 <- eBayes(fit2) topTable(fit2) Alternatively, you can fit an intercept and then will not need to fit a contrast, because it will be implicit in the model. design <- model.matrix(~factor(rep(1:2, each=4))) fit <- lmFit(eset, design) fit2 <- eBayes(fit) topTable(fit2, coef = 2) HTH, Jim > > Thanks > sri > > _______________________________________________ > Bioconductor mailing list > Bioconductor at stat.math.ethz.ch > https://stat.ethz.ch/mailman/listinfo/bioconductor > Search the archives: http://news.gmane.org/gmane.science.biology.informatics.conductor -- James W. MacDonald, M.S. Biostatistician Affymetrix and cDNA Microarray Core University of Michigan Cancer Center 1500 E. Medical Center Drive 7410 CCGC Ann Arbor MI 48109 734-647-5623 ********************************************************** Electronic Mail is not secure, may not be read every day, and should not be used for urgent or sensitive issues.
ADD COMMENT

Login before adding your answer.

Traffic: 376 users visited in the last hour
Help About
FAQ
Access RSS
API
Stats

Use of this site constitutes acceptance of our User Agreement and Privacy Policy.

Powered by the version 2.3.6