一种基于深度学习的苦味肽精准预测方法  

An accurate identification method of bitter peptides based on deep learning

作　　者：杨学冬 韩丽君 王榕 王宏伟 王晓 YANG Xuedong;HAN Lijun;WANG Rong;WANG Hongwei;WANG Xiao(College of Computer and Communication Engineering,Zhengzhou University of Light Industry,Zhengzhou 450001,China;College of Food and Bioengineering,Zhengzhou University of Light Industry,Zhengzhou 450001,China;Henan Key Laboratory of Food Safety Data Intelligence,Zhengzhou 450001,China)

机构地区：[1]郑州轻工业大学计算机与通信工程学院,河南郑州450001 [2]郑州轻工业大学食品与生物工程学院,河南郑州450001 [3]河南省食品安全数据智能重点实验室,河南郑州450001

出　　处：《轻工学报》2023年第3期11-16,共6页Journal of Light Industry

基　　金：国家自然科学基金青年科学基金项目(32101976);河南省科技攻关项目(232102210020);河南省高等学校青年骨干教师培养项目(2019GGJS132);河南省高等学校重点科研项目(22A520013,23B520004)。

摘　　要：鉴于湿实验方法已无法满足快速鉴别苦味肽的需求,提出一种新颖的融合了传统手工特征和预训练深度特征的预测方法Bitter-Fus。该方法首先使用预训练蛋白质序列语言模型自动地从多肽序列中提取深度学习特征,然后将该特征输入长短期记忆(LSTM)网络中进行降维处理以保留与多肽序列最相关的深度特征,最后将降维后的深度特征与传统氨基酸组成(AAC)方法提取的手工特征融合并输入前馈神经网络中构建预测模型。验证实验结果表明:预测方法Bitter-Fus在10折交叉验证测试中获得了0.902的准确性和0.805的马修斯相关系数,在独立数据集测试中准确性和马修斯相关系数分别达到0.930和0.862,明显优于当前最先进的苦味肽预测方法BERT4Bitter和iBitter-SCM。Given that wet experimental methods were no longer adequate for the rapid identification of bitter peptides,this paper presented Bitter-Fus,a novel predictive deep learning method incorporating traditional manual features and pre-trained deep features.Firstly,the method automatically extracted deep learning features from peptide sequences using a pre-trained protein sequence language model,then fed the deep learning features into a long short-term memory(LSTM)network for dimensionality reduction to retain the most relevant features.Finally,the reduced-dimensional deep features were fused with the manual features composed of traditional amino acids composition(AAC)method and passed into the feedforward neural network to construct a prediction model.The validation experimental results showed that the prediction method Bitter-Fus obtained an accuracy precision value of 0.902 and a Mathews correlation coefficient value of 0.805 in a 10-fold cross-validation,and an accuracy precision value of 0.930 and a Mathews correlation coefficient value of 0.862 in the independent dataset test,which significantly outperformed the current state-of-the-art bitter peptide prediction methods BERT4Bitter and iBitter-SCM.

关 键 词：苦味肽 深度学习 特征提取 特征融合 

分 类 号：TS201.2[轻工技术与工程—食品科学] TP399[轻工技术与工程—食品科学与工程]