DESeq2: Variable Importance

Question

[gt]

Is there a way to obtain the relative importance of a variable in the DESeq2 model? I know you can run a likelihood ratio test with a reduced model that does not include the factor to see if it is significant or not. But is there something similar to when you have a multiple linear regression model and calculate the proportion of R-squared associated with each variable?

[Kevin Blighe]

User has posted on Bioconductor: https://support.bioconductor.org/p/9137718/#9137718

Answer 1

[Kevin Blighe]

You must mean the terms of the design formula? There are different ways to define 'importance', including beta coefficient, Gini coefficient, or even PCA-based methods. You may post this on Bioconductor support, where the DESeq2 maintainer will probably reply: https://support.bioconductor.org/

[gt]

Yes I do mean the design formula factors. Sorry I was not clear. I have found this package online: https://www.bioconductor.org/packages/release/bioc/vignettes/variancePartition/inst/doc/variancePartition.pdf and wondering if this is something common that people use in conjunction with Deseq2?