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

MetricModelBPCCMF
ECCResnik0.42580.34440.4842
 Lin0.42170.33910.5162
 Jang&Conrath0.41140.25200.5189
 simGIC0.38880.35030.5875
 simUI0.38180.35270.5783
 w2vGO0.42040.35160.4905
 GO2Vec_mhd_go0.44760.36500.6715
 GO2Vec_cos_goa0.42510.35070.6472
 GO2Vec_mhd_goa0.45080.36180.6792
PfamResnik0.45070.46760.5221
 Lin0.38110.45620.5149
 Jang&Conrath0.27410.33210.4503
 simGIC0.43830.46820.5825
 simUI0.42530.48730.5504
 w2vGO0.45690.47350.5436
 GO2Vec_mhd_go0.50410.49020.4537
 GO2Vec_cos_goa0.49160.47270.4315
 GO2Vec_mhd_goa0.51180.49750.4453
  1. The best result in each metric is highlighted in boldface