Table 1 Comparison of clustering performance and computing time for JOINT and published imputation algorithms on real scRNA-Seq datasets
From: JOINT for large-scale single-cell RNA-sequencing analysis via soft-clustering and parallel computing
Performance Scores | Raw | Saver | scImpute | JOINT |
Baron Dataset | ||||
Adjusted Rand Index | 0.64 | 0.63 | 0.43 | 0.95 |
Jaccard Index | 0.55 | 0.53 | 0.34 | 0.92 |
Adjusted Mutual Info | 0.79 | 0.76 | 0.64 | 0.89 |
Zeisel Dataset | ||||
Adjusted Rand Index | 0.67 | 0.69 | 0.45 | 0.67 |
Jaccard Index | 0.57 | 0.59 | 0.35 | 0.57 |
Adjusted Mutual Info | 0.63 | 0.63 | 0.56 | 0.65 |
Computing Time (s) | Saver | scImpute | JOINT | |
Baron Dataset | 4777 | 1010 | 528 | |
Zeisel Dataset | 18036 | 3440 | 836 | |