Skip to main content

Table 4 Prediction performance comparison of our MHC-CNN with other networks

From: In silico design of MHC class I high binding affinity peptides through motifs activation map

Model

SRCC

AUC

NetMHCpan [52]

0.071

0.546

sNebula [53]

0.06

0.539

HLA-CNN [10]

0.178

0.56

MHC-CNN

0.117

0.576

  1. All the training dataset is HLA-A*0201 while the testing dataset is IEDB 1029824 HLA-A*0201 segmented from HLA-A*0201. MHC-CNN denotes our best performance network architecture: 2CNN+multi GAPs. The bold face denotes the best performance of the column
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us