Table 2 Cross-validation 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

0.883

0.878

0.887

0.766

0.926

1

0.592

420

0.872

0.879

0.865

0.744

0.918

2

0.634

414

0.867

0.865

0.868

0.734

0.919

3

0.653

412

0.869

0.864

0.874

0.739

0.916

4

0.602

417

0.865

0.867

0.862

0.730

0.918

5

0.601

416

0.867

0.873

0.861

0.735

0.918

6

0.601

407

0.865

0.862

0.868

0.730

0.913

7

0.664

415

0.862

0.885

0.840

0.726

0.911

8

0.668

415

0.862

0.848

0.875

0.724

0.912

9

0.585

425

0.861

0.885

0.837

0.724

0.909

Mean

0.625

416

0.867

0.871

0.864

0.735

0.916

SD

0.032

4.77

0.006

0.012

0.015

0.013

0.005