This chapter describes the role of machine learning approaches such as random forests in holistic discovery applications and provides a background for its better understanding. Their suitability for feature selection, data integration, and network modelling are also evaluated through recent examples in the literature. These examples cover a variety of fields, ranging from ecology to metabolomics.
Montoliu, I. (2015). Adopting Multivariate Nonparametric Tools to Determine Genotype-Phenotype Interactions in Health and Disease. In Molecular and Integrative Toxicology (pp. 45–62). Springer Science+Business Media B.V. https://doi.org/10.1007/978-1-4471-6539-2_3