Table 2.
Species | Classifiers | AUROC | MCC | ACC | Precision | Recall |
---|---|---|---|---|---|---|
Human | BiLSTMOne-hot | 0.7810 | 0.4409 | 0.7159 | 0.7716 | 0.6095 |
BiLSTMEmbedding | 0.8504 | 0.5602 | 0.7739 | 0.8470 | 0.6661 | |
BiLSTMWord2vec | 0.8510 | 0.5497 | 0.7695 | 0.8361 | 0.6678 | |
EDLm6APred | 0.8660 | 0.5819 | 0.7843 | 0.8617 | 0.6750 | |
Mouse | BiLSTMOne-hot | 0.7838 | 0.4354 | 0.7088 | 0.7901 | 0.5739 |
BiLSTMEmbedding | 0.8390 | 0.5394 | 0.7642 | 0.8296 | 0.6691 | |
BiLSTMWord2vec | 0.8464 | 0.5369 | 0.7604 | 0.8429 | 0.6442 | |
EDLm6APred | 0.8588 | 0.5664 | 0.7754 | 0.8579 | 0.6639 | |
Mix | BiLSTMOne-hot | 0.8055 | 0.4758 | 0.7361 | 0.7687 | 0.6755 |
BiLSTMEmbedding | 0.8459 | 0.5670 | 0.7801 | 0.8313 | 0.7028 | |
BiLSTMWord2vec | 0.8463 | 0.5477 | 0.7707 | 0.8189 | 0.6952 | |
EDLm6APred | 0.8605 | 0.5787 | 0.7862 | 0.8355 | 0.7128 |
The evaluation indexes with EDLm6 APred better than its any single predictor are show in bold