Table 3 Performance of different window sizes on the human dataset. Boldface values indicate the best performance for each metric.

From: A deep learning framework for lysine 2-hydroxyisobutyrylation site prediction using evolutionary feature representation

Window size

10-fold cross-validation set

Independent test set

ACC

SN

PR

F1

MCC

ACC

SN

PR

F1

MCC

47

0.799

0.853

0.769

0.809

0.601

0.809

0.890

0.769

0.825

0.625

45

0.798

0.843

0.773

0.806

0.598

0.800

0.862

0.770

0.814

0.604

43

0.818

0.860

0.794

0.825

0.640

0.823

0.894

0.786

0.837

0.653

41

0.800

0.848

0.774

0.809

0.604

0.808

0.859

0.783

0.819

0.619

39

0.798

0.846

0.771

0.807

0.598

0.814

0.852

0.795

0.823

0.629

37

0.789

0.851

0.757

0.801

0.583

0.807

0.854

0.783

0.817

0.615

35

0.767

0.802

0.749

0.774

0.535

0.789

0.858

0.758

0.805

0.583

Back to article page