Table 2 Summarized results of RSKC applied to the three cases considering the genes selected by JGL (\(\lambda _1\)= 0.095 and\(\lambda _2\)= 0.01), for\(\alpha\)= 0.1 and L1 = 2. The clusters were evaluated by Silhouette and Calinski-Harabasz scores. ARI was computed to quantify the agreement between clusters and the glioma types, considering the most relevant parameters combination
From: Disclosing transcriptomics network-based signatures of glioma heterogeneity using sparse methods
Case | K | Silhouette | Calinski-Harabasz | ARI |
|---|---|---|---|---|
(A) LGG vs. GBM | 2 | 0.70 | 640.95 | 0.54 |
3 | 0.62 | 786.37 | – | |
(B) Astrocytoma vs. Oligodendroglioma | 2 | 0.58 | 513.29 | 0.15 |
3 | 0.59 | 526.92 | – | |
(C) Astrocytoma vs. Oligodendroglioma vs. GBM | 2 | 0.73 | 843.31 | 0.49 |
3 | 0.61 | 753.07 | 0.21 |