limma voom normalization of train and test set
Hello,
I am using TCGA RNA-Seq data for a neural net method. I have splitted the data to train and test set. how do i normalize count data of train and test set without data leakage using limma?
My Idea is I might be able to normalize the train set using limma+voom method first and then use the parameters calculated by voom on train set(E and weights) to normalize the test set. however I couldn't realize how?
any help would be greatly appreciated.
• 2,063 views
•
link
written
by
asalimih •
0 answers
No answers yet.
Log in to answer this question.
More posts like this
-
Remove batch effects on the train set to avoid information leakage
written by AlexStar •
-
limma-trend on GTEx inverse normal transform data
written by Alba Mas •
-
TCGAbiolinks methylation data normalization
written by 김 •
-
Neural Networks hyperparameter tuning
written by ldaveyl •
-
RNAseq normalization for new data
written by sosal •
-
problem for 2 different normalization methods in train and test data set
written by modarzi
-
DESeq2 - Between sample normalization of train/test subsets
written by ml_researcher •
-
Multinomial elastic net implementation on microarray dataset , error at lognet and nfold explanation
written by arronar
-
DESeq and Limma+Voom Normalization for Rna-Seq Data Using Ercc Spike-In
written by komal.rathi
-
Re:Normalization in r
written by ash •
I'd normalize them separately. Simply make two matrices, one test and one train, and run the normalization on each of them.
thank you. after I searched more it seems that using
Eandweightsis not correct for this purpose. those parameters are forlmfitand limma itself. Gordon Smyth recommended this:Yes, just run the default normalization as in the manual, so calcNormFactors and then cpm() using the log-transformation. Alternatively something like vst() from DESeq2 might be of interest here.