Horizontal integration of multi omic data is combining and integrating independent studies measured on the same P predictors (e.g. genes).

mixOmics/MINT suggest such method with a binary dependent variable, though I look for a continuous one (regression).

Any suggestions?

Dror.

I'm not totally clear on what your goal is, but it sounds possibly you want to do regression on a continuous dependent variable. If that's the case, you might check out:

• mlR: https://mlr-org.github.io/mlr-tutorial/devel/html/create_learner/index.html#regression
• caret: https://www.machinelearningplus.com/machine-learning/caret-package/
• glmnet: https://cran.r-project.org/web/packages/glmnet/index.html
• penalized: https://cran.r-project.org/web/packages/penalized/
• hardly seems worth mentioning in the same block of these more substantial packages, but my old pensim package mainly provides a nested cross-validation wrapper around the penalized package: https://cran.r-project.org/web/packages/pensim/index.html (I myself now would more likely use mlR or caret, which are more flexible but do require more configuration).

MultiAssayExperiment's intersectColumns(), intersectRows(), assays(), wideFormat(), longFormat(), and subsetting methods should allow you to get to the formats and data required by any of these packages pretty efficiently.