Table 3 Performance comparison of DeEPsnap with different types of features. S: sequence features; N: network embedding features; G: gene ontology features; C: protein complex features; D: protein domain features.
From: A deep ensemble framework for human essential gene prediction by integrating multi-omics data
Features | AUROC | AUPRC | MCC | F1 | Accuracy |
|---|---|---|---|---|---|
S+N+G+C+D | 0.9616 \({\pm }\) 0.0059 | 0.9383 \({\pm }\) 0.0083 | 0.7592 \({\pm }\) 0.0186 | 0.8062 \({\pm }\) 0.0149 | 0.9236 \({\pm }\) 0.0059 |
S+N+G+C | 0.9548 \({\pm }\) 0.0070 | 0.9302 \({\pm }\) 0.0085 | 0.7403 \({\pm }\) 0.0169 | 0.7915 \({\pm }\) 0.0135 | 0.9166 \({\pm }\) 0.0053 |
S+N+G+D | 0.9582 \({\pm }\) 0.0082 | 0.9319 \({\pm }\) 0.0119 | 0.7509 \({\pm }\) 0.0326 | 0.8000 \({\pm }\) 0.0260 | 0.9190 \({\pm }\) 0.0106 |
S+N+C+D | 0.9587 \({\pm }\) 0.0082 | 0.9330 \({\pm }\) 0.0139 | 0.7402 \({\pm }\) 0.0361 | 0.7913 \({\pm }\) 0.0287 | 0.9161 \({\pm }\) 0.0120 |
S+G+C+D | 0.9590 \({\pm }\) 0.0077 | 0.9343 \({\pm }\) 0.0103 | 0.7352 \({\pm }\) 0.0234 | 0.7873 \({\pm }\) 0.0185 | 0.9117 \({\pm }\) 0.0086 |
N+G+C+D | 0.9354 \({\pm }\) 0.0083 | 0.9019 \({\pm }\) 0.0094 | 0.6863 \({\pm }\) 0.0228 | 0.7477 \({\pm }\) 0.0183 | 0.9003 \({\pm }\) 0.0075 |
