基于注意力的双向 LSTM 方法预测 TCR 和表位的结合,IEEE/ACM Transactions on Computational Biology and Bioinformatics

link之家

链接快照平台

输入网页链接，自动生成快照
标签化管理网页链接

相关文章推荐

呐喊的竹笋 · openwrt routeros ...· 1 月前 ·

欢乐的柳树 · 八十中学11月4日走进幸福村学区人工智能嘉年 ...· 8 月前 ·

小眼睛的椅子 · 哥布林洞窟 - 百度· 1 年前 ·

任性的便当 · 一次性看完爽文漫画《末世凡人》，感受世界末日 ...· 1 年前 ·

愉快的电池 · 纯电、插混、增程、混动有什么区别，到底谁更好 ...· 1 年前 ·

T细胞表位预测一直是免疫信息学和生物信息学领域的长期挑战。研究T细胞受体(TCR)与肽-主要组织相容性复合物(p-MHC)复合物的特异性识别，有助于我们更好地理解免疫机制，对开发疫苗和靶向药物也有重要贡献。同时，需要更先进的方法来区分 TCR 与不同表位的结合。在本文中，我们介绍了一种由双向长短期记忆网络 (BiLSTM)、注意力和卷积神经网络 (CNN) 组成的混合模型，可以识别 TCR 与表位的结合。BiLSTM可以更完整地提取序列中的氨基酸正向和反向信息，注意力机制可以关注复杂序列中某些位置的氨基酸以捕获最重要的特征，然后使用CNN进一步提取显着特征以预测TCR-表位的结合。在 McPAS 数据集中，原始 TCR 表位结合的 AUC 值（ROC 曲线下的面积）为 0.974，特异性 TCR 表位结合为 0.887。该模型取得了比其他现有模型（TCRGP、ERGO、NetTCR）更好的预测结果，并通过一些实验来分析我们模型的优势。该算法可在该模型取得了比其他现有模型（TCRGP、ERGO、NetTCR）更好的预测结果，并通过一些实验来分析我们模型的优势。该算法可在该模型取得了比其他现有模型（TCRGP、ERGO、NetTCR）更好的预测结果，并通过一些实验来分析我们模型的优势。该算法可在 https://github.com/bijingshu/BiAttCNN.git The T-cell epitope prediction has always been a long-term challenge in immunoinformatics and bioinformatics. Studying the specific recognition between T-cell receptor (TCR) and peptide-major histocompatibility complex (p-MHC) complexes can help us better understand the immune mechanism, it’s also make a signification contribution in developing vaccines and targeted drugs. Meanwhile, more advanced methods are needed for distinguishing TCRs binding from different epitopes. In this paper, we introduce a hybrid model composed of bidirectional long short-term memory networks (BiLSTM), attention and convolutional neural networks (CNN) that can identified the binding of TCRs to epitopes. The BiLSTM can more completely extract amino acid forward and backward information in the sequence, and attention mechanism can focus on amino acids at certain positions from complex sequences to capture the most important feature, then CNN was used to further extract salient features to predict the binding of TCR-epitope. In McPAS dataset, the AUC value (the area under ROC curve) of naive TCR-epitope binding is 0.974 and specific TCR-epitope binding is 0.887. The model has achieved better prediction results than other existing models (TCRGP, ERGO, NetTCR), and some experiments are used to analyze the advantages of our model. The algorithm is available at https://github.com/bijingshu/BiAttCNN.git