FIGURE 1.

Comparison of effective raw data set dimensions and sizes in the categorized studies. Each point represents a data set that was used for optimizing and testing at least one predictive model. In multi-omics, a data set includes measurements from multiple omics sources. Each data set is plotted at the position that corresponds to its effective raw dimension and size. Please refer to the main text for explanations on the meaning of effective raw feature and sample counts (Section 2.1). Note that the graph shows only a selection of all ML-ready data sets from all studies. Supplementary Figure S1 provides references to the shown data points.