Hello to everyone,
I have a question regarding normalization in microarray data. I would like to normalize my training set using rma. After normalizing my training set, I would like to use the training set parameters(mean,sd) to normalize my test set. Is there any function to normalize my test using training set parameters. Or just use the formula like (test-mean(train))/sd(train). It would be really helpful if you solve my problem. Thanks in advance
2 answers
see if this package in R helps you out: www.bioconductor.org/packages/release/bioc/html/RefPlus.html
from the vignette, copy/pasted:
The RMA+ algorithm calculates the microarray intensities using a pre-stored RMA model trained on a reference microarray set (can be standard reference microarrays, microarrays from an independent study, or an incomplete set of microarrays in a study)
You may want to consider fRMA (frozen RMA) as a general solution:
https://www.bioconductor.org/packages/release/bioc/html/frma.html
Log in to answer this question.
-
Microarray analysis using Limma
written by mrashad
-
Remove batch effects on the train set to avoid information leakage
written by AlexStar •
-
Batch effect correction & normalization after training/test split for gene expression data
written by mmitra •
-
limma voom normalization of train and test set
written by asalimih •
-
Neural Networks hyperparameter tuning
written by ldaveyl •
-
DESeq2 - Between sample normalization of train/test subsets
written by ml_researcher •
-
how to normalize microarray expression set
written by Michel Edwar
-
variance stabilization and normalization
written by ash •
-
R use models from survival analysis and do prediction
written by hdy
-
Classifier Optimization In Weka!
written by kandoigaurav
