Standardization of gene expression and methylation dataset to the same scale

Question

[ymukhiddin]

I am trying to build a classification model using logistic regression with regularization based on a combined methylation and gene expression datasets. Data I am considering now is for COAD cancer from TCGA. I am going to combine selected CpG sites and gene expressions as one dataset. But, I am not sure what is the best/appropriate approach to make methylation betas and expression intensities have the same scale.

Thanks in advance for the answers.

Answer 1

[Sean Davis]

I'd consider converting the methylation beta values to M-values and then standardizing (possibly using robust estimators such as median and IQR).

[ymukhiddin]

Thank you. I forgot about M-vales. What do you think, if I combine M-values with gene expressions and then standardize sample-wise, for example in such a way: (feature_val - median)/IQR, would it be ok?