Table I. Comparison of different prediction approaches with F1 score

The average true positive of the random network is calculated from 10 randomized networks. Precision represents predicted PPIs with experimental evidence/all predicted PPIs, and recall represents predicted PPIs with experimental evidence/all experimentally determined PPIs.

MethodPredicted PPIs with Experimental EvidenceAll Predicted PPIsAll Experimentally Determined PPIsPrecisionRecallF1 Score
Random network348316,74721,2820.0010.0160.002
AtPID38624,41821,2820.0160.0180.017
AtPIN44990,04321,2820.0050.0210.008
PAIR1,995145,35521,2820.0140.0940.024
AraPPINet6,040316,74721,2820.0190.2840.036