A Sequence-based Antibody Paratope Prediction Model Through Combing Local-Global Information and Partner Features

Antibodies are proteins which play a vital role in the immune system by recognizing and neutralizing antigens. The region on the antibody binding to an antigen, known as paratope, mediates antibody-antigen interaction with high affinity and specificity. And the accurate prediction of those regions from antibody sequence contributes to the design of therapeutic antibodies and remains challenging. However, the experimental methods are time-consuming and expensive. In this article, we propose a sequence-based method for antibody paratope prediction by combing local and global information of antibody sequence and partner features from partner antigen sequence. Convolution Neural Networks(CNNs) and a sliding window approach on antibody sequence are used to extract local information. Attention-based Bidirectional Long Short-Term Memory (Att-BLSTM) on antibody sequence are used to extract global information. Also, the partner antigen is vital for paratope prediction, and we employ Att-BLSTM on the partner antigen sequence as well. The outputs of CNNs and Att-BLSTM networks are combined to predict antibody paratope by fully-connected networks. The experiments show that our proposed method achieves superior performance over the state-of-the-art sequenced-based antibody paratope prediction methods on benchmark datasets.