Table 3 Feature statistics for different datasets (GM = generic model; BM = biological model). Note that the feature list used in the BM model is longer than that of the GM model due to the additional binary biological features (has-protein, has-two-proteins, etc.).
From: Identification of transcription factor contexts in literature using machine learning approaches
| Â | Â | TF data | PPI Data | NonPF Data |
|---|---|---|---|---|
total # features | GM | 1327 | 1188 | 1780 |
| Â | BM | 803 | 760 | 1306 |
# features per sentence | GM | 9.70 | 14.44 | 11.43 |
| Â | BM | 12.87 | 17.73 | 9.78 |