Skip to main content

Table 12 Comparison of the overall success rate with eight state-of-the-art methods

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

Method

Overall success rate

 

Dataset 1

Dataset 2

AAC based on Covariance [9]

37.2%

—

PsePSSM based on ensemble method [9]

91.6%

78.3%

Physicochemical properties based on ensemble method [13]

91.0%

—

Fusion representation based on SVM [16]

92.6%

88.2%

PsePSSM based on LLDA and ensemble method [22]

88.7%

—

PsePSSM and DC based on GPP and KNN [20]

90.2%

—

PsePSSM based on PCA and KNN [22]

80.66%

—

Previous work [19]

93.49%

—

This paper

95.68%

92.98%

  1. Note: Best performing method in bold.