Table 1 Improvement of protein secondary structure prediction with the addition of a "residue-specific" RSA threshold using leave-one-out cross-validation, compared with this improvement using a fixed 16% RSA threshold.
From: Impact of residue accessible surface area on the prediction of protein secondary structures
| Â | Applied Threshold | ||
|---|---|---|---|
| Â | Fixed (16%) | Mean | Median |
A | 0.67 | 3.93 | 2.25 |
C | -5.02 | -0.05 | -0.42 |
D | -1.5 | -1.26 | -0.94 |
E | -2.77 | 1.33 | -3.71 |
F | 0.18 | 5.99 | 7.15 |
G | 0.90 | 5.98 | 5.53 |
H | 0.04 | -4.23 | -4.80 |
I | -19.00 | -16.19 | -16.17 |
K | 9.53 | 9.91 | 11.63 |
L | 0.54 | 4.20 | 2.24 |
M | -6.82 | -7.71 | -8.29 |
N | 1.21 | 1.71 | 1.63 |
P | 1.15 | 1.70 | 1.47 |
Q | -0.61 | -1.49 | -3.38 |
R | 1.84 | 0.87 | 1.15 |
S | 1.29 | 6.44 | 4.85 |
T | 0.20 | 3.12 | 2.53 |
V | -2.57 | -5.80 | -8.33 |
W | -6.18 | -1.66 | -2.22 |
Y | -0.19 | 10.04 | 9.78 |
Total Improvement | 3.46 | 5.79 | 5.13 |