Skip to main content

Table 2 Comparison with published results, in 10-fold cross-validation, of SVM methods using the D&D dataset

From: Exploring general-purpose protein features for distinguishing enzymes and non-enzymes within the twilight zone

Kernel

Accuracy* (%)

Reference

Run time

Computer

PUK

82.0 ± 0.3

ProtDCal 3D model

53 m 2 s

Intel Core i5–3210 M 2.5 GHz with 8 GB of RAM

GraphK ShinglingWL

81.54 ± 1.54

[62]

3 h 1 m 7 s

Apple MacPro with 3.0GHz Intel 8-Core with 16GB RAM

GraphK WLmod

80.31

[63]

25 m 0 s

NA

Radial

80.17 ± 1.24

[33]

NA

NA

GraphK WL

79.78 ± 0.36

[64]

11 m 0 s

Apple MacPro with 3.0GHz Intel 8-Core with 16GB RAM

GraphK WL

79.00 ± 0.2

[65]

6 m 42 s

3.4GHz Intel core i7 processors

PUK

78.8 ± 0.2

ProtDCal 1D model

3 m 42 s

Intel Core i5–3210 M 2.5 GHz with 8 GB of RAM

GraphK WL

78.29

[66]

2 h 12 m 57 s

MAC OS × 10.5 with two 2.66GHz Dual Core Intel Xeon processors, with 4GB 667MHz DDR2 memory

PUK

77.58

[68]

21 m 51 s

2.5 GHz Intel 2-Core processor (i.e. i5–3210 m)

GraphK LWL

76.60 ± 0.6

[69]

11 m 00s

16 cores machine (Intel Xeon CPU E5–2665@2.40GHZ and 96GB of RAM)

GraphK SP

75,87

[70]

1 h 40 m 57 s

NA

GraphK PRW

75.40 ± 0.6

[71]

NA

NA

  1. The runtimes reported for our models comprise both the time for computing the features and times related to the building and assessing the models using Weka 3.7.11
  2. NA Not-available
  3. *For each of the listed references, the tabulated accuracy corresponds to the best performance in the D&D dataset as shown in the article
  4. Runtime and computational resource were also displayed for the methods included in the comparison
  5. All the referenced methods constitute 3D classifiers given that they use 3D–graphs to represent the protein structure