基于深度学习和蛋白质语言模型的抗菌肽预测模型研究

1. 18新利直播计算机科学与技术学院, 河南郑州 450001;
2. 河南省食品安全数据智能重点实验室, 河南郑州 450001;
3. 18新利直播食品与生物工程学院, 河南郑州 450001;
4. 18新利直播电子信息学院, 河南郑州 450001

作者简介:王晓(1982-),男,河南省卫辉市人,18新利直播副教授,博士,主要研究方向为人工智能、生物信息学和食品信息学。E-mail:wangxiao@zzuli.edu.cn;

基金项目:国家自然科学基金青年科学基金项目(32101976,61906175)
河南省科技攻关项目(232102210020,20210221014)
河南省高等学校重点科研项目(22A520013,23B520004)
中图分类号:TS201.2;TP399

Research on antimicrobial peptide prediction model based on deep learning and protein language model

1. College of Computer Science and Technology, Zhengzhou University of Light Industry, Zhengzhou 450001, China;
2. Henan Key Laboratory of Data Intelligence for Food Safety, Zhengzhou 450001, China;
3. College of Food and Bioengineering, Zhengzhou University of Light Industry, Zhengzhou 450001, China;
4. College of Electronic Information, Zhengzhou University of Light Industry, Zhengzhou 450001, China
Received Date:2023-10-19
Accepted Date:2024-01-25

CLC number:TS201.2;TP399

摘要:针对目前已有抗菌肽(Antimicrobial Peptides,AMPs)预测模型的准确度( ACC)仍有待提高的问题,提出一种新的基于深度学习和蛋白质语言模型的抗菌肽预测模型DeepGlap,该模型分别采用两个蛋白质语言模型对抗菌肽序列进行特征提取,将提取的特征向量融合后输入由多层双向长短记忆网络(mBi-LSTM)、一维卷积神经网络(1D-CNN)和注意力机制组成的深度学习网络中,并进行性能评估与优化。结果表明:该模型的 ACC、皮尔逊相关系数( MCC)和曲线下的面积( AUC) 分别为0.739、0.489和0.81,优于已有抗菌肽预测模型的预测效果。
- 抗菌肽/
- 预测模型/
- 食源性病原体/
- 蛋白质语言模型/
- 深度学习网络
Abstract:In response to the need for improving prediction accuracy ( ACC) in existing models for Antimicrobial Peptides (AMPs), a novel AMP prediction model called DeepGlap was proposed. This model utilized two protein language models for feature extraction from AMP sequences, followed by fusion of feature vectors. These fused vectors were then input into a deep learning network composed of multiple layers of bidirectional long short-term memory networks (mBi-LSTM), one-dimensional convolutional neural networks (1D-CNN), and attention mechanisms. The model underwent performance evaluation and optimization. Results indicated that the model achieved ACC,the Pearson correlation coefficient ( MCC), and the area urder the curve ( AUC) values of 0.739, 0.489, and 0.81, respectively, demonstrating superior predictive performance compared to existing AMP prediction models.
- antimicrobial peptide/
- prediction model/
- foodborne pathogen/
- protein language model/
- deep learning network
1. [1]
  WHITE D G,ZHAO S H,SIMJEE S,et al.Antimicrobial resistance of foodborne pathogens[J].Microbes and Infection,2002,4(4):405-412.
2. [2]
  KUMAR P,KIZHAKKEDATHU J N,STRAUS S K.Antimicrobial peptides:Diversity,mechanism of action and strategies to improve the activity and biocompatibilityin vivo[J].Biomolecules,2018,8(1):4.
3. [3]
  ZHANG R N,WU D,GAO Y T.Progress on the design and optimization of antimicrobial peptides[J].Journal of Biomedical Engineering,2022,39(6):1247-1253.
4. [4]
  JOSEPH S,KARNIK S,NILAWE P,et al.ClassAMP:A prediction tool for classification of antimicrobial peptides[J].IEEE-ACM Transactions on Computational Biology and Bioinformatics,2012,9(5):1535-1538.
5. [5]
  SHARMA R,SHRIVASTAVA S,SINGH S K,et al.AniAMPpred:Artificial intelligence guided discovery of novel antimicrobial peptides in animal kingdom[J].Briefings in Bioinformatics,2021,22(6):bbab242.
6. [6]
  KAVOUSI K,BAGHERI M,BEHROUZI S,et al.IAMPE:NMR-assisted computational prediction of antimicrobial peptides[J].Journal of Chemical Information and Modeling,2020,60(10):4691-4701.
7. [7]
  CHUNG C R,KUO T R,WU L C,et al.Characterization and identification of antimicrobial peptides with different functional activities[J].Briefings in Bioinformatics,2020,21(3):1098-1114.
8. [8]
  XU J,LI F Y,LI C,et al.iAMPCN:A deep-learning approach for identifying antimicrobial peptides and their functional activities[J].Briefings in Bioinformatics,2023,24(4):bbad240.
9. [9]
  YAN K,LYU H W,GUO Y C,et al.sAMPpred-GAT:Prediction of antimicrobial peptide by graph attention network and predicted peptide structure[J].Bioinformatics,2023,39(1):btac715.
10. [10]
  FERRUZ N,HCKER B.Controllable protein design with language models[J].Nature Machine Intelligence,2022,4(6):521-532.
11. [11]
  WANG G S,LI X,WANG Z.APD3:The antimicrobial peptide database as a tool for research and education[J].Nucleic Acids Research,2016,44:D1087-D1093.
12. [12]
  ZHAO X W,WU H Y,LU H R,et al.LAMP:A database linking antimicrobial peptides[J].PLoS ONE,2013,8(6):e66557.
13. [13]
  THOMAS S,KARNIK S,BARAI R S,et al.CAMP:A useful resource for research on antimicrobial peptides[J].Nucleic Acids Research,2010,38:D774-D780.
14. [14]
  GOGOLADZE G,GRIGOLAVA M,VISHNEPOLSKY B,et al.DBAASP:Database of antimicrobial activity and structure of peptides[J].FEMS Microbiology Letters,2014,357(1):63-68.
15. [15]
  KANG X Y,DONG F Y,SHI C,et al.DRAMP 2.0,an updated data repository of antimicrobial peptides[J].Scientific Data,2019,6:148.
16. [16]
  JHONG J H,CHI Y H,LI W C,et al.dbAMP:An integrated resource for exploring antimicrobial peptides with functional activities and physicochemical properties on transcriptome and proteome data[J].Nucleic Acids Research,2019,47:D285-D297.
17. [17]
  FU L M,NIU B F,ZHU Z W,et al.CD-HIT:Accelerated for clustering the next-generation sequencing data[J].Bioinformatics,2012,28(23):3150-3152.
18. [18]
  ZHANG Y,LIN J Y,ZHAO L M,et al.A novel antibacterial peptide recognition algorithm based on BERT[J].Briefings in Bioinformatics,2021,22(6):bbab200.
19. [19]
  XU J,LI F Y,LEIER A,et al.Comprehensive assessment of machine learning-based methods for predicting antimicrobial peptides[J].Briefings in Bioinformatics,2021,22(5):bbab083.
20. [20]
  ALLEY E C,KHIMULYA G,BISWAS S,et al.Unified rational protein engineering with sequence-based deep representation learning[J].Nature Methods,2019,16(12):1315-1322.
21. [21]
  BRANDES N,OFER D,PELEG Y,et al.ProteinBERT:A universal deep-learning model of protein sequence and function[J].Bioinformatics,2022,38(8):2102-2110.
22. [22]
  HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780.
23. [23]
  YU Z X,HUANG F,ZHAO X H,et al.Predicting drug-disease associations through layer attention graph convolutional network[J].Briefings in Bioinformatics,2021,22(4):bbaa243.
1. [1]
  王晓,杨鹏鹏,王榕,李辉. 基于伪氨基酸组成和多标记最近邻算法的抗菌肽功能类型预测. 轻工学报, 2015, 30(5-6): 85-87.doi: 10.3969/j.issn.2095-476X.2015.5/6.017
2. [2]
  王金圳. 聚丙烯纤维混凝土强度冻融损失率灰色关联分析. 轻工学报, 2013, 28(6): 73-76.doi: 10.3969/j.issn.2095-476X.2013.06.017
3. [3]
  方刚. 基于统计语言模型及动态规划算法的蛋白质表达载体的优化设计. 轻工学报, 2016, 31(4): 88-94.doi: 10.3969/j.issn.2096-1553.2016.4.013
4. [4]
  杨学冬,韩丽君,王榕,王宏伟,王晓. 一种基于深度学习的苦味肽精准预测方法. 轻工学报, 2023, 38(3): 11-16.doi: 10.12187/2023.03.002
5. [5]
  陈建明,张盼盼. 灰色BP神经网络模型在电力系统短路电流峰值预测中的应用. 轻工学报, 2018, 33(4): 79-85.doi: 10.3969/j.issn.2096-1553.2018.04.011
6. [6]
  袁培,刘键,付云飞,郝亚萍,许旺龙,吕彦力. 立式冷藏陈列柜食品温度预测计算模型. 轻工学报, 2016, 31(6): 69-73.doi: 10.3969/j.issn.2096-1553.2016.6.010
7. [7]
  蒋亚平,郭俊亮. 基于马尔柯夫过程的交叉路口车流量预测模型研究. 轻工学报, 2012, 27(6): 21-23,31.doi: 10.3969/j.issn.2095-476X.2012.06.006
8. [8]
  吕恒志,张涛,章凯旋,何帅彪,金楠. 三相四开关容错变换器调制模型预测控制策略. 轻工学报, 2019, 34(4): 87-95.doi: 10.3969/j.issn.2096-1553.2019.04.013
9. [9]
  吕彦力,孟志强,曹秀琴,马秋阳,吴学红,张文慧. 立式冷藏陈列柜内食品传热模型研究及温度预测. 轻工学报, 2012, 27(5): 59-62.doi: 10.3969/j.issn.2095-476X.2012.05.014
10. [10]
  王宁宁. 最优加权融合SO₂转化率预测模型. 轻工学报, 2015, 30(3-4): 138-141.doi: 10.3969/j.issn.2095-476X.2015.3/4.030
11. [11]
  谷国玲,戴秀英,刘杰. 基于改进GM(1,1)模型的猪肉价格预测研究. 轻工学报, 2015, 30(2): 105-108.doi: 10.3969/j.issn.2095-476X.2015.02.023
12. [12]
  孙轶峰,侯智文,王文辉,王志国,杨光露,金楠. 卷烟车间有源电力滤波器模型预测控制策略. 轻工学报, 2021, 36(6): 77-85,90.doi: 10.12187/2021.06.009
13. [13]
  尚姝钰,陈豪,姜素霞,吕恒志,陶涛,崔光照. 基于模型预测控制的有源电力滤波器开关损耗优化设计. 轻工学报, 2017, 32(2): 103-108.doi: 10.3969/j.issn.2096-1553.2017.2.016
14. [14]
  王晓,李辉,翟云清. 基于集成学习和基因本体标注库的细胞凋亡蛋白亚细胞位置预测. 轻工学报, 2016, 31(4): 95-101.doi: 10.3969/j.issn.2096-1553.2016.4.014
15. [15]
  杨开广,张丽华,张玉奎. 蛋白质分离和鉴定的新技术新方法研究进展. 轻工学报, 2012, 27(5): 1-7,12.doi: 10.3969/j.issn.2095-476X.2012.05.001
16. [16]
  吴慈,梁玉,梁振,张丽华,张玉奎. 整体材料的研制及其在蛋白质组色谱分离中的应用. 轻工学报, 2016, 31(4): 1-14.doi: 10.3969/j.issn.2096-1553.2016.4.001
17. [17]
  赵建国,李玉,杨德健,朱昌蔼,李刚强. 双酚A废水处理对污泥急性毒性和蛋白质表达的影响. 轻工学报, 2018, 33(6): 19-26.doi: 10.3969/j.issn.2096-1553.2018.06.003
18. [18]
  楚鹏飞,倪众,卢晨曦,杨涵颖,于曼曼,刘玉欣. 低温长时间热加工对海参体壁蛋白质消化吸收特性的影响. 轻工学报, 2023, 38(4): 37-45.doi: 10.12187/2023.04.005
19. [19]
  刘足江,刘云. 环形无线网络呼叫接入控制模型研究. 轻工学报, 2012, 27(6): 97-100.doi: 10.3969/j.issn.2095-476X.2012.06.026
20. [20]
  刘穗君,杨林超,张萍,邱宗鹤. 基于模糊神经网络的智能混丝掺配PID控制模型研究. 轻工学报, 2015, 30(3-4): 39-43.doi: 10.3969/j.issn.2095-476X.2015.3/4.009

点击查看大图

计量

PDF下载量:19
文章访问数:1406
引证文献数:0

通讯作者:陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

基于深度学习和蛋白质语言模型的抗菌肽预测模型研究

作者简介:王晓(1982-),男,河南省卫辉市人,18新利直播副教授,博士,主要研究方向为人工智能、生物信息学和食品信息学。E-mail:wangxiao@zzuli.edu.cn;

Research on antimicrobial peptide prediction model based on deep learning and protein language model

计量

通讯作者:陈斌, bchen63@163.com

基于深度学习和蛋白质语言模型的抗菌肽预测模型研究

作者简介:王晓(1982-),男,河南省卫辉市人,18新利直播副教授,博士,主要研究方向为人工智能、生物信息学和食品信息学。E-mail:wangxiao@zzuli.edu.cn

English Abstract

Research on antimicrobial peptide prediction model based on deep learning and protein language model

目录

基于深度学习和蛋白质语言模型的抗菌肽预测模型研究

作者简介:王晓(1982-),男,河南省卫辉市人,18新利直播 副教授,博士,主要研究方向为人工智能、生物信息学和食品信息学。E-mail:wangxiao@zzuli.edu.cn;

Research on antimicrobial peptide prediction model based on deep learning and protein language model

计量

文章相关

通讯作者:陈斌, bchen63@163.com

基于深度学习和蛋白质语言模型的抗菌肽预测模型研究

作者简介:王晓(1982-),男,河南省卫辉市人,18新利直播 副教授,博士,主要研究方向为人工智能、生物信息学和食品信息学。E-mail:wangxiao@zzuli.edu.cn

English Abstract

Research on antimicrobial peptide prediction model based on deep learning and protein language model

目录

作者简介:王晓(1982-),男,河南省卫辉市人,18新利直播副教授,博士,主要研究方向为人工智能、生物信息学和食品信息学。E-mail:wangxiao@zzuli.edu.cn;

作者简介:王晓(1982-),男,河南省卫辉市人,18新利直播副教授,博士,主要研究方向为人工智能、生物信息学和食品信息学。E-mail:wangxiao@zzuli.edu.cn