TP - True Positives
FP - False Positives
FN - False Negatives

GoldStandard - CAFA1 dataset
Size: 529 sequences

Precision = TP/(TP+FP)
Recall = TP/(TP+FN)
F1 score = 2*(precision*recall)/(precision+recall)


### Sifter v2.0:
    TP: 68        12.9%
    FP: 146       27.6%
    FN: 315       59.5%

    Precision: 0.317757009346
    Recall: 0.177545691906
    F1 score: 0.227805695142



### Sifter-T:
    TP: 228       43.1%
    FP: 278       52.6%
    FN: 23         4.3%

    Precision: 0.450592885375
    Recall: 0.908366533865
    F1 score: 0.602377807133