Table 3 Performance comparison between MSpectraAI and the classic approach utilizing MaxQuant + DNN mode on diverse datasets
Method | PXD007232 [25] | PXD008012 [26] | PXD007705 [27] | PXD005698 [28] | PXD002213 [29] | PXD009602 [30] | |
|---|---|---|---|---|---|---|---|
Accuracy | Classic | 0.70 | 0.52 | 0.969 | 0.625 | 0.794 | – |
MSpectraAI | 0.90 | 0.74 | 1.00 | 1.00 | 1.00 | 1.00 | |
Sensitivity | Classic | 0.75 | 0.551 | 1.00 | 0.615 | 0.765 | – |
MSpectraAI | 1.00 | 0.727 | 1.00 | 1.00 | 1.00 | 1.00 | |
Precision | Classic | 0.60 | 0.593 | 0.938 | 0.667 | 0.813 | – |
MSpectraAI | 0.833 | 0.696 | 1.00 | 1.00 | 1.00 | 1.00 | |
F1 | Classic | 0.667 | 0.571 | 0.968 | 0.64 | 0.788 | – |
MSpectraAI | 0.909 | 0.711 | 1.00 | 1.00 | 1.00 | 1.00 |