Skip to main content

Table 1 Accuracy of three different machine learning prediction algorithms – J48 Decision Tree, Naïve Bayes and SVM with SMO training – using binary H/P sequences.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 top 10% and the bottom 10% of designable conformations for the hexagon

96.8% correct

95.8% correct

98.3% correct

 

AUC .97

AUC 0.99

AUC 0.98

 

Sens: 1.0

Sens: 1.0

Sens: 0.997

 

Spec: 0.94

Spec: 0.92

Spec: 0.97

b) Sequences folding to the top 10% and the bottom 10% of designable conformations for the triangle

92.7% correct

82.4% correct

95.0% correct

 

AUC 0.93

AUC 0.92

AUC 0.95

 

Sens: 0.93

Sens: 0.76

Sens: 0.92

 

Spec: 0.92

Spec: 0.86

Spec: 0.97

  1. a We compare random subsets of sequences corresponding to the top 10% and the bottom 10% of designable structures for the a) hexagon, and b) triangle. Prediction accuracy and area under the curve (AUC), sensitivity (Sens) and specificity (Spec) for each method are given.