Making a design matrix when the control has a different number of replicates?
1
0
Entering edit mode
5.8 years ago

Hello,

How do you go about making a design matrix when the control has 8 replicates and the rest have 9. Is it possible or do I have to throw out the one extra from the rest. Thank you!

limma hugene20st • 915 views
ADD COMMENT
1
Entering edit mode

In most cases you can have 8 replicates vs 9. But what is your goal here ?

ADD REPLY
0
Entering edit mode

The goal is to find DEGs between the time points. So a pairwise comparison between all time points.

ADD REPLY
1
Entering edit mode
5.8 years ago

Yes you can:

model.matrix(~0 + Treatments, data = data.frame(Treatments = factor(c(rep("Control", times = 8), rep("Treated", times = 9)))))‚Äč
ADD COMMENT
0
Entering edit mode

thanks for that helped!

ADD REPLY
0
Entering edit mode

if I want to compare cancer v/s normal samples, what is the code for design matrix then? Also, there are different numbers of cancer and normal sample. I have no sample replicates.

ADD REPLY
0
Entering edit mode

That's a whole different kettle of fish. Depends on your experimental design, if your tumour/normal samples are paired, what type of data you have, etc, etc, etc. The design matrix itself is essentially a description of your experimental design. I think you need to do some more reading, or consult with some bioinformatics support at your institution.

ADD REPLY
0
Entering edit mode

My samples are not paired. I have no one to consult that's why I am here. If you want then I would like to explain my work.

ADD REPLY
0
Entering edit mode

Then create a new post if it's a new topic to discuss

ADD REPLY

Login before adding your answer.

Traffic: 2113 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