Skip to main content

Table 9 Comparison of our predictors with other models via 10-fold cross-validation for H. sapiens

From: Comparative analysis and prediction of nucleosome positioning using integrative feature representation and machine learning algorithms

Method

Feature

ACC

Sn

Sp

MCC

AUC

DLNN-5 [24]

 

0.8537

0.8834

0.8229

 ~ 

 ~ 

ZCMM [23]

 

0.7772

0.7487

0.8151

0.5600

0.8610

SVM

FCGR

0.8758

0.8966

0.8552

0.7528

0.9288

FCGR + DAC

0.8749

0.8856

0.8644

0.7507

0.9314

FCGR + TAC

0.8752

0.8878

0.8626

0.7513

0.9306

FCGR + DACC

0.8537

0.8531

0.8544

0.7079

0.9208

FCGR + TACC

0.8415

0.8319

0.8509

0.6837

0.9113

FCGR + PCPseDNC

0.8727

0.8896

0.8561

0.7463

0.9284

FCGR + PCPseTNC

0.8719

0.8878

0.8561

0.7444

0.9281

All features

0.8137

0.7518

0.8748

0.6322

0.8996

ELM

FCGR

0.8428

0.8636

0.8222

0.6866

0.9075

FCGR + DAC

0.8461

0.8724

0.8200

0.6936

0.9128

FCGR + TAC

0.8469

0.8698

0.8244

0.6952

0.9129

FCGR + DACC

0.8458

0.8763

0.8157

0.6936

0.9095

FCGR + TACC

0.8439

0.8808

0.8074

0.6902

0.9072

FCGR + PCPseDNC

0.8454

0.8645

0.8265

0.6918

0.9107

FCGR + PCPseTNC

0.8437

0.8627

0.8248

0.6882

0.9069

All features

0.8447

0.8843

0.8057

0.6923

0.9118

XGBoost

FCGR

0.8585

0.89309

0.8244

0.71934

0.9197

FCGR + DAC

0.8537

0.8667

0.8409

0.708

0.9172

FCGR + TAC

0.8859

0.9045

0.8674

0.7725

0.9491

FCGR + DACC

0.8423

0.86583

0.8191

0.68588

0.9127

FCGR + TACC

0.8395

0.8667

0.8126

0.6805

0.905

FCGR + PCPseDNC

0.8559

0.88913

0.823

0.71396

0.9207

FCGR + PCPseTNC

0.8498

0.8645

0.8352

0.7003

0.9155

All features

0.8472

0.87374

0.8209

0.69581

0.917

MLP

FCGR

0.8565

0.8768

0.8365

0.7144

0.9186

CNN

FCGR

0.8585

0.8746

0.8426

0.7185

0.9214

  1. The table shows the optimal results of each classifier, and the specific parameters are shown in the previous tables
  2. Best values are in bold