Table 4 The influence of KM, SC, and AG on the ScLSTM model is evaluated on eight data sets using the predicted cluster number
From: ScLSTM: single-cell type detection by siamese recurrent network and hierarchical clustering
Data set | ARI | NMI | ACC | BAS |
|---|---|---|---|---|
Biase | 1 | 1 | 1 | 1 |
Yan | 0.8965 | 0.8997 | 0.9 | 0.9733 |
Goolam | 0.773 | 0.7527 | 0.8548 | 0.9082 |
Camp | 0.8285 | 0.8926 | 0.888 | 0.9472 |
Kolodziejczyk | 1 | 1 | 1 | 1 |
Li | 0.9171 | 0.9358 | 0.934 | 0.9688 |
Usoskin | 0.9865 | 0.9741 | 0.9887 | 0.9916 |
Pollen | 0.9567 | 0.9765 | 0.9601 | 0.9932 |