Fig. 2

Workflow of the evaluation on simulated multi-omics datasets. a InterSIM CRAN package generated three kinds of omics data that were used as input. b Supervised DL methods are evaluated in the classification tasks. The performance of these methods was based on 4-fold cross-validation and was evaluated by three metrics: accuracy, F1 macro, and F1 weighted score. c Unsupervised DL methods are applied to fuse the simulated multi-omics data to obtain 5-dimensional, 10-dimensional, and 15-dimensional embeddings first. Then k-means algorithm is used to cluster the multi-omics dimensionality reduction results. We employed JI, C-index, silhouette score and Davies Bouldin score as the evaluation indexes of clustering