Table 4 Predictive accuracy, the number of selected features and marker genes of scFSNN and five other classifiers with feature selection procedure on Human datasets
From: scFSNN: a feature selection method based on neural network for single-cell RNA-seq data
Methods | Accuracy | Selected feature | Marker |
|---|---|---|---|
scFSNN | 0.9886 | 624 | 42 |
SurvNet | 0.9837 | 134 | 26 |
SINC | 0.9886 | 1500 | 25 |
ZIPLDA | 0.9732 | 1000 | 8 |
GL | 0.9827 | 2447 | 42 |
SGL | 0.9818 | 2247 | 41 |