摘要
In order to identify continuous B-cell epitopes effectively and to increase the success rate of experimental identification, the modified Back Propagation artificial neural network (BP neural network) was used to predict the continuous B-cell epitopes, and finally the predictive model for the B-cells epitopes was established. Comparing with the other predictive models, the prediction performance of this model is more excellent (AUC = 0.723). For the purpose of verifying the performance of the model, the prediction to the SWISS PROT NUMBER: P08677 was carried on, and the satisfying results were obtained.
In order to identify continuous B-cell epitopes effectively and to increase the success rate of experimental identification, the modified Back Propagation artificial neural network (BP neural network) was used to predict the continuous B-cell epitopes, and finally the predictive model for the B-cells epitopes was established. Comparing with the other predictive models, the prediction performance of this model is more excellent (AUC = 0.723). For the purpose of verifying the performance of the model, the prediction to the SWISS PROT NUMBER: P08677 was carried on, and the satisfying results were obtained.
作者
Yajie Cao
Jinglin Liu
Tao Liu
Dejiang Liu
Yunfei Wu
Yajie Cao;Jinglin Liu;Tao Liu;Dejiang Liu;Yunfei Wu(College of Science, Jiamusi University, Jiamusi, China;College of Science, Hebei Polytechnic University, Tangshan, China;Department of Computer Science, University of Georgia, Georgia, USA;College of Science, Northeast Forestry University, Harbin, China)
