Skip to main content

Advertisement

Table 5 Performance of different prediction models on independent test set

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

Subset Modela Recall (%) Precision (%) Accuracy (%) F1-score (%) MCC
Single-heme STR 76.05 28.72 77.06 41.69 0.366
  STRRFP 72.10 31.44 80.03 43.78 0.382
  SEQ 58.86 39.35 85.78 47.17 0.404
  STR+SEQ 52.28 52.75 89.80 52.51 0.468
  STRRFP+SEQ 50.54 55.78 90.34 53.03 0.477
Multi-heme STR 87.07 51.48 69.66 64.70 0.454
  STRRFP 86.56 52.60 70.80 65.43 0.466
  SEQ 63.14 59.85 74.70 61.45 0.427
  STR+SEQ 58.55 69.53 78.57 63.57 0.489
  STRRFP+SEQ 58.25 70.18 78.76 63.66 0.493
All STR 80.13 34.93 75.83 48.65 0.412
  STRRFP 77.45 37.72 78.50 50.73 0.431
  SEQ 60.44 45.36 83.94 51.83 0.431
  STR+SEQ 54.60 58.34 87.94 56.41 0.495
  STRRFP+SEQ 53.39 60.82 88.42 56.87 0.504
  1. aSTR, RFP and SEQ denote structure-based classifier, reducing false positives and sequence-based classifier respectively.