Skip to main content

Table 2 Performance of our models and the compared models on the CESSM dataset

From: GO2Vec: transforming GO terms and proteins to vector representations via graph embeddings

Metric

Model

BP

CC

MF

ECC

Resnik

0.4258

0.3444

0.4842

 

Lin

0.4217

0.3391

0.5162

 

Jang&Conrath

0.4114

0.2520

0.5189

 

simGIC

0.3888

0.3503

0.5875

 

simUI

0.3818

0.3527

0.5783

 

w2vGO

0.4204

0.3516

0.4905

 

GO2Vec_mhd_go

0.4476

0.3650

0.6715

 

GO2Vec_cos_goa

0.4251

0.3507

0.6472

 

GO2Vec_mhd_goa

0.4508

0.3618

0.6792

Pfam

Resnik

0.4507

0.4676

0.5221

 

Lin

0.3811

0.4562

0.5149

 

Jang&Conrath

0.2741

0.3321

0.4503

 

simGIC

0.4383

0.4682

0.5825

 

simUI

0.4253

0.4873

0.5504

 

w2vGO

0.4569

0.4735

0.5436

 

GO2Vec_mhd_go

0.5041

0.4902

0.4537

 

GO2Vec_cos_goa

0.4916

0.4727

0.4315

 

GO2Vec_mhd_goa

0.5118

0.4975

0.4453

  1. The best result in each metric is highlighted in boldface