Skip to main content

Table 1 The ROC score of different methods in pathway membership prediction for all ontologies. NN is neural network model, NN 1/0 is neural network model that use binary representation of GO terms as features. The number of layers in neural network are three and the

From: Predicting metabolic pathway membership with deep neural networks by integrating sequential and ontology information

Methods

BP

CC

MF

NN

0.953

0.849

0.895

NN 1/0

0.941

0.847

0.870

cosine

0.931

0.762

0.677

SVM

0.920

0.768†

0.843

RF

0.935†

0.837

0.887

KNN

0.830

0.780

0.806

Resnik

0.829

0.667

0.790

SimGIC

0.902

0.735

0.717

Back to article page

BMC Genomics

ISSN: 1471-2164

Contact us