Skip to main content
. 2017 Jan 6;7:40053. doi: 10.1038/srep40053

Table 1. Statistic evaluations and validation of SVM-Pose.

  SVM-Pose
1PB7 1PB8 1PB9 1PBQ 1Y1M 1Y1Z 1Y20
r2 0.98 0.99 0.97 0.94 0.98 0.98 0.93
ΔMax 0.00 0.09 0.42 0.14 0.49 0.49 0.57
MAE 0.00 0.02 0.19 0.02 0.17 0.37 0.14
s 0.00 0.02 0.12 0.03 0.16 0.18 0.21
RMSE 0.00 0.02 0.22 0.03 0.23 0.41 0.25
Inline graphic 0.89 0.95 0.93 0.91 0.91 0.91 0.90
Inline graphic 0.98 0.99 0.97 0.93 0.97 0.97 0.92
k 1.00 0.99 1.00 0.98 0.99 1.00 0.99
Inline graphic 0.97 0.99 0.97 0.92 0.97 0.97 0.91
Inline graphic 0.96 0.97 0.94 0.90 0.94 0.96 0.86
Inline graphic 0.94 0.97 0.91 0.83 0.93 0.93 0.79
Inline graphic 0.95 0.97 0.92 0.86 0.83 0.94 0.83
Inline graphic 0.02 0.00 0.03 0.07 0.01 0.03 0.07
Eq. (1) x x x x x x x
Eq. (2) x x x x x x x
Eq. (3) x x x x x x x
Eq. (4) x x x x x x x
Eq. (5) x x x x x x x
Eq. (6) x x x x x x x

Statistic evaluations of SVM-Score models, namely correlation coefficient (r2), 10-fold cross-validation correlation coefficient (Inline graphic), maximal absolute residual (ΔMax), mean absolute error (MAE), standard deviation (s), and RMSE as well as validation.