From: Single-cell classification using graph convolutional networks
Training dataset | BaronHuman + Muraro + Segerstolpe | Xin + Muraro + Segerstolpe | Xin + BaronHuman + Segerstolpe | Xin + BaronHuman + Muraro |
---|---|---|---|---|
Testing dataset | Xin | BaronHuman | Muraro | Segerstolpe |
sigGCN | 0.993 | 0.976 | 0.957 | 0.989 |
FC | 0.976 | 0.965 | 0.945 | 0.990 |
scID | 0.991 | 0.98 | 0.976 | 0.994 |
scPred | 0.923 | 0.231 | 0.912 | 0.725 |
CasTLe | 0.974 | 0.916 | 0.966 | 0.988 |
SingleR | 0.988 | 0.974 | 0.969 | 0.994 |
scmapcluster | 0.133 | 0.001 | 0.001 | 0 |
scmapcell | 0.415 | 0.232 | 0.353 | 0.241 |
ACTINN | 0.982 | 0.977 | 0.957 | 0.989 |
RF | 0.946 | 0.914 | 0.957 | 0.903 |
SVM-linear | 0.986 | 0.972 | 0.952 | 0.986 |
SVM-rbf | 0.963 | 0.97 | 0.958 | 0.952 |
KNN | 0.766 | 0.74 | 0.504 | 0.602 |