Skip to main content

Advertisement

Table 4 Accuracy of machine learning predictions classifying sequences folding to the least designable conformations among random binary sequences for a) hexagonal and b) triangular shapes.a

From: Use of machine learning algorithms to classify binary protein sequences as highly-designable or poorly-designable

  J48 Naïve Bayes SMO
a) Sequences folding to the bottom 10% of designable structures vs. random binary sequences of length 19 for the hexagon 57.5% correct 55.6% correct 57.9% correct
  AUC 0.58 AUC 0.59 AUC 0.58
  Sens: 0.62 Sens: 0.55 Sens: 0.61
  Spec: 0.56 Spec: 0.55 Spec: 0.57
b) Sequences folding to the bottom 10% of designable structures vs. random binary sequences of length 21 for the triangle 50.1% correct 52.3% correct 56.0% correct
  AUC 0.50 AUC 0.53 AUC 0.56
  Sens: 0.54 Sens: 0.67 Sens: 0.59
  Spec: 0.53 Spec: 0.54 Spec: 0.58
  1. a Values of prediction accuracy and area under the curve (AUC), sensitivity (Sens) and specificity (Spec) for each method are given.