Skip to main content

Table 4 Performance of different prediction models on main dataset

From: HemeBIND: a novel method for heme binding residue prediction by combining structural and sequence information

Modela Recall (%) Precision (%) Accuracy (%) F1-score (%) MCC FP TN FN TP
STR 79.08 34.07 76.49 47.56 0.407 7824 24888 1061 4018
STRRFP 76.05 37.14 79.24 49.76 0.427 6629 26083 1215 3864
SEQ 63.29 45.64 84.88 52.97 0.451 3852 28860 1865 3214
STR+SEQ 55.87 57.48 88.44 56.55 0.500 2128 30584 2241 2838
STRRFP+SEQ 54.08 60.74 89.03 57.07 0.510 1814 30898 2332 2747
  1. aSTR, RFP and SEQ denote structure-based classifier, reducing false positives and sequence-based classifier respectively.