Table 23

Combining position specific composition (Method 1), thermodynamics (Method 2), N-Gram (Method 11), guide strand structure (Method 4) and Xue features (Method 5) for training RBF-epsilon regression SVM model

train2431

train2431

train2431

test2431

test579

test2431 10 × cross val




t-test

FN2431

R

MSE

R

MSE

R

MSE


0

1523(1523)

0.797

0.015

0.523

0.099

0.760

0.023

1

910(901.3)

0.807

0.014

0.513

0.090

0.760

0.023

2

522(489.5)

0.817

0.013

0.526

0.092

0.746

0.024

3

247(230.8)

0.825

0.013

0.518

0.092

0.726

0.025

4

123(108.7)

0.850

0.011

0.495

0.097

0.710

0.026

5

64(57.1)

0.856

0.011

0.504

0.097

0.709

0.026

6

36(29.7)

0.844

0.012

0.504

0.099

0.695

0.026

7

23(20.6)

0.816

0.013

0.449

0.100

0.675

0.027

8

15(12.8)

0.738

0.018

0.457

0.105

0.618

0.030

9

8(6.9)

0.661

0.022

0.334

0.109

0.606

0.031


Models trained on dataset2431 and testing performed with dataset2431, dataset579 and 10 × cross validation on dataset2431, features removed by increasing stringency of t-test of individual feature to activity from dataset2431.

Feature numbers in parentheses are the average number of features in cross validations.

Entries in bold are column maximums and are simply visual landmarks.

Peek BMC Bioinformatics 2007 8:182   doi:10.1186/1471-2105-8-182

Open Data