An Improved Method for Predicting Linear B-cell Epitope Using Deep Maxout Networks.

Yao Lian; Ze Chi Huang; Meng GE; Xian Ming Pan

Return

An Improved Method for Predicting Linear B-cell Epitope Using Deep Maxout Networks.

Author: Yao LIAN ¹ ; Ze Chi HUANG ² ; Meng GE ³ ; Xian Ming PAN ¹
Author Information

1. The Key Laboratory of Bioinformatics, Ministry of Education, School of Life Sciences, Tsinghua University, Beijing 100084, China.
2. Key Laboratory of Protein and Peptide Pharmaceutical, Institute of Biophysics, Chinese Academy of Sciences, Beijing 100101, China.
3. CAS Key Laboratory of Genome Sciences and Information, Beijing Institute of Genomics, Chinese Academy of Sciences, Beijing 100101, China.
Publication Type:Letter
MeSH: Amino Acid Sequence; Computational Biology; methods; Epitopes, B-Lymphocyte; chemistry; immunology; ROC Curve
From: Biomedical and Environmental Sciences 2015;28(6):460-463
CountryChina
Language:English
Abstract: To establish a relation between an protein amino acid sequence and its tendencies to generate antibody response, and to investigate an improved in silico method for linear B-cell epitope (LBE) prediction. We present a sequence-based LBE predictor developed using deep maxout network (DMN) with dropout training techniques. A graphics processing unit (GPU) was used to reduce the training time of the model. A 10-fold cross-validation test on a large, non-redundant and experimentally verified dataset (Lbtope_Fixed_ non_redundant) was performed to evaluate the performance. DMN-LBE achieved an accuracy of 68.33% and an area under the receiver operating characteristic curve (AUC) of 0.743, outperforming other prediction methods in the field. A web server, DMN-LBE, of the improved prediction model has been provided for public free use. We anticipate that DMN-LBE will be beneficial to vaccine development, antibody production, disease diagnosis, and therapy.