Figure 2.

Overview of the ML approaches in the integration of multi-omics data. Multi-omics data could be integrated using both statistical and ML methods, where statistical approaches are used as a preprocessing step. ML approaches are classified into supervised and unsupervised algorithms, which could be utilized in the integration of omics to reduce the data dimensionality for building novel networks and pathways. SVM: support vector machine; KNN: K-nearest neighbor; HDBSCAN: hierarchical density-based spatial clustering of applications with noise.