Stack Overflow
Stack Overflow

Questions tagged [limma]

limma is a bioconductor package used for linear models in differential expression or methylation analyses

limma is a package for the analysis of expression or methylation data, especially the use of linear models for analysing designed experiments and the assessment of differential expression.

52 questions
7
votes
1 answer

In R, how do I define model contrasts for comparing two conditions relative to a common control?

I've been using the makeContrasts function in the Limma package to create contrasts, and I understand how to make simple contrasts, for example comparing each Treatment to a control independently or comparing two treatments: makeContrasts(A_vs_Ctrl…
Jay
  • 442
  • 1
  • 5
  • 13
4
votes
1 answer

I need a good Limma tutorial that uses R

I'm trying to get started using some statistical analysis with the limma package that runs out of R. Any one know a good tutorial?
illbill
  • 403
  • 1
  • 6
  • 6
4
votes
1 answer

Meaning of coef in limma

tl;dr why isn't fit <- eBayes(fit); topTable(fit, coef=4) the same as fit <- contrasts.fit(fit, c(-1,0,0,1)); fit <- eBayes(fit); topTable(fit) (column 1 of the design beeing the intercept)? Example from the limma usersguide Strain <-…
jkd
  • 1,327
  • 14
  • 29
4
votes
1 answer

Issues with limma for analysis of microarray gene expression data - possibly related to design matrix

I am fairly new to R, and have recently started using it to analyse some microarray data. The overall aim of the analysis is to take DC2 and compare the WT vs KO groups in this population. But I have come across some problems with the limma…
Jack
  • 43
  • 5
3
votes
1 answer

Comparing three groups of paired data with limma. How to make the paired design

So I am using r, with the packages Bioconductor (oligo), (limma) to analyze some microarray data. I am having trouble in the paired analysis. So this is my phenotype data ph@data ph@data index filename group WT1 WT WT1 …
Ander Daniel
  • 51
  • 4
2
votes
1 answer

Display elements, instead of just counts, within each circle of a Venn diagram?

For example, set A={a,b,c} and set B={b,c,d} and the intersection of sets A and B should be {b,c}. But how can I display {b,c} instead of the count 2 in a Venn diagram? I tried venn in the limma package and Venn in the Vennerable package but neither…
gipelttil
  • 41
  • 3
2
votes
1 answer

Turn string into the contents of a function in R for pipeline

I have am using the makeContrasts function as part of a pipeline (with limma). I have several studies, which are entered into the pipeline one after the other. For two of which, the makeContrasts functions looks like this: aarts_1_cm =…
James
  • 69
  • 6
2
votes
0 answers

Limma's vennDiagram doesn't plot the values

The basic vennDiagram plot works very well. But I'm trying to show the percentage instead of amount like this vennDiagram(vennCounts( df)/5000*100, circle.col = 1:4) It works with 2 and 3 sets: But with 4 and 5 sets the percentages aren't…
Péter P
  • 21
  • 3
2
votes
1 answer

Package Limma -contrast matrix differential expression

I am using limma to analyse differential gene expressions. For modeling you need a design and contrast matrix. I just want to know whether anyone has experience with it. Suppose that expressions are from wild type (WT) and mutants (M) and these are…
stefan
  • 171
  • 2
  • 6
2
votes
1 answer

Test for no change in Limma

I'm looking for a way to identify genes that are significantly stable across conditions. In other words, the opposite of standard DE analysis. Standard DE splits genes in two categories: significantly changing on one side, everything else, "the…
Matteo
  • 265
  • 5
  • 16
2
votes
1 answer

Remove box frame from vennDiagram plot with limma

There is no option with vennDiagram() in the limma package to remove the box frame from the Venn diagram. So can anyone tell me how I can adjust the source code to fix that? I also want to remove the number in the corner. I appreciate it.
Moneeb Irshad Bajwa
  • 65
  • 7
2
votes
0 answers

Bioinformatics: How do a contrast Limma with 3 groups (case/control, age and gender)

I'm a student and I have doubts about how use Limma to contrast the differential gene expression evaluating my three variables: disease (case/control), gender(male/female) and age. My data is like this: (three columns with the gender, age and the…
Miyuki
  • 21
  • 1
1
vote
1 answer

Multi-group differential gene expression for time-series treatment data

This is an example dataset: df = data.frame(genes = c("A", "B", "C", "D", "E"), KO_0min_Rep1 = c(0, 1, 2, 6, 6), KO_0min_Rep2 = c(0, 3, 2, 3, 6), KO_60min_Rep1 = c(0, 0.3, 2, 9.1, 6), …
ip2018
  • 655
  • 1
  • 7
  • 14
1
vote
0 answers

LIMMA: design matrices and procedures

Hy to everyone. I am new with LIMMA package in R studio and I'm encountering trouble in the following procedure: I want to discover DEGs between two classes (SD and CR). I have a gene expression matrix of >26k genes and a info table with 79…
fpisto
  • 35
  • 3
1
vote
1 answer

Negative values after Limma's batch effect correction

I have several RNA-seq data sets. Using a deconvolution approach, I conducted a cell type enrichment analysis for each one of them and then combined the results into one dataframe, yielding 1000+ samples in columns and 38 cell types in rows. The…
Programming Noob
  • 1,232
  • 3
  • 14
1
2 3 4