Fig. 3
From: A benchmark study of deep learning-based multi-omics data fusion methods for cancer
JI, C-index, silhouette score, and Davies Bouldin score of the ten unsupervised methods for clustering on simulated multi-omics datasets. An external index JI (a) and three internal indices C-index, silhouette score and Davies Bouldin score (b, c, d) were calculated based on the clustering on the simulated data. The cluster number is set to 5, 10, and 15. SS and RS represent two conditions, i.e., all clusters have the same size and the clusters have variable random sizes. The k-means clustering was run over 1000 times. The results of a are presented as mean values of JIs