Table 3 Independent test results of SCM models using different optimal propensity scores of g-gap dipeptides.

From: A novel sequence-based predictor for identifying and characterizing thermophilic proteins using estimated propensity scores of dipeptides

g-gap

R

Cutoff

ACC

Sn

Sp

MCC

AUC

0

0.650

418

0.865

0.849

0.881

0.731

0.925

1

0.592

420

0.844

0.846

0.841

0.687

0.912

2

0.634

414

0.863

0.868

0.857

0.725

0.918

3

0.653

412

0.860

0.836

0.884

0.721

0.908

4

0.602

417

0.852

0.863

0.841

0.704

0.909

5

0.601

416

0.852

0.854

0.849

0.704

0.915

6

0.601

407

0.867

0.863

0.871

0.733

0.914

7

0.664

415

0.853

0.860

0.846

0.706

0.909

8

0.668

415

0.840

0.822

0.857

0.680

0.910

9

0.585

425

0.837

0.849

0.825

0.674

0.897

Mean

416

0.625

0.853

0.851

0.855

0.706

0.912

SD

0.032

4.77

0.011

0.014

0.019

0.021

0.007