Skip to main content
Fig. 2 | BMC Bioinformatics

Fig. 2

From: DeepNetBim: deep learning model for predicting HLA-epitope interactions based on network analysis by harnessing binding and immunogenicity information

Fig. 2

Improved performance of integrating network metrics in DeepNetBim. a Absolute error for binding affinity prediction and b accuracy rate for immunogenic prediction of the original model (coloured in blue) and the PepOnly model (coloured in white) for the 6 most frequent alleles in the test dataset. c Absolute error for binding affinity prediction and d ROC curve for immunogenic prediction of the original network, shuffle networks (shuffled network edge weights) and random network (reassigned network weights by uniform distribution) in the test dataset

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us