Prediction of Continuous B-cell Epitopes Using Long Short Term Memory Networks
B-cell epitopes play a vital role in the epitope-based vaccine design.The accumulation of epitope sample data makes it possible to predict epitopes using machine learning methods.Compared with the experimental tests, the computational methods are faster and more economic.Several machine learning computational methods have been applied to improve the accuracy of epitope predictions.These methods have been improved several times in the epitope prediction has made some achievements, but there are also deficiencies.The commonly used propensity scale methods for the prediction are physicochemical properties of amino acid sequences.It is difficult to get a good classification result in the network gaining using only the physicochemical properties of the sample sequence.In this study,we have developed a novel method for predicting continuous B-cell epitope.We adopted the Long Short Term Memory network and relevance of amino acids pair feature scale.Long Short Term Memory network can make up for the lack of recurrent artificial neural network algorithm, which is very suitable for epitope prediction.We have been adopted the performance of Long Short Term Memory network and the relevance of amino acids pair feature scale in three aspects, and achieved a certain result.
B-cell epitopes Prediction LSTM Network RAAP Relevance of amino acids pair
Bin Cheng Ling-yun Liu Zhao-hui Qi Hong-guang Yang
Institute of Applied Mathematics, Hebei Academy of Sciences Hebei Authentication Technology Engineer College of Information Science and Technology,Shijiazhuang Tiedao University 17 Northeast, Second In Institute of Applied Mathematics, Hebei Academy of Sciences 46 Youyi South Street,Shijiazhuang, Hebe
国际会议
成都
英文
55-59
2018-03-12（万方平台首次上网日期，不代表论文的发表时间）