HELP VIP SCORE analysis

Analysis
1

Hello,
I have a question regarding variable selection in my omics data. I have 1700 variables, and I want to select the most relevant ones for future use. I also wanted to work with the mixOmics package for VIP scores. I applied this code to extract the VIP scores, but I’m not sure if what I’m doing is correct.

I would like to know how to extract relevant variables. What criteria should I use to determine their importance? Should the VIP score be > 1 in both components?

code:
library(mixOmics)
plsda_model ← mixOmics::plsda(X,as.factor(Y), ncomp = 2)
vip_scores ← vip(plsda_model)
print(vip_scores)

Thankyou sm

2

hi @Oumaaa12

Note that we only respond on Friday every week or 2 weeks so nothing can be treated as urgent here.

This is a copy paste from our book, which states (Chapter 10): This criterion is used in SIMCA-P software (Umetri, 1996) and considers a VIP > 1 as important in explaining Y .

Kim-Anh