Skip to main content

Table 3 Comparison of the overall success rate between different vector representation methods on Dataset 1 and Dataset 2

From: Accurate classification of membrane protein types based on sequence and evolutionary information using deep learning

Method

Dataset 1

Dataset 2

 

Validation set

Testing set

Validation set

Testing set

One hot encoding

80.78%

87.77%

78.21%

82.63%

Random method

74.77%

80.87%

71.22%

81.94%

Our method

85.54%

91.58%

83.25%

89.18%

  1. Note: Best performing method in bold.