|
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.). |
||||
| TF data |
PPI Data |
NonPF Data |
||
|
|
||||
| total # features |
GM |
1327 |
1188 |
1780 |
| BM |
803 |
760 |
1306 |
|
| # features per sentence |
GM |
9.70 |
14.44 |
11.43 |
| BM |
12.87 |
17.73 |
9.78 |
|
Yang et al. BMC Bioinformatics 2008 9(Suppl 3):S11 doi:10.1186/1471-2105-9-S3-S11 |
||||