计算机技术与发展2025，Vol.35Issue(9)：200-206,7.DOI:10.20165/j.cnki.ISSN1673-629X.2025.0092
深度学习在肽段测序任务中的应用与进展
Application and Progress of Deep Learning in Peptide Sequencing Tasks
摘要
Abstract
Tandem mass spectrometry(MS/MS)has become the primary technology for proteomic data analysis and a crucial tool for large-scale protein identification due to its high sensitivity and reliability.De novo peptide sequencing technology directly interprets mass spectrometry data without relying on existing protein databases,thereby overcoming the limitations of traditional database-dependent methods in processing large-scale,highly complex mass spectrometry data,such as slow processing speeds and limited flexibility.In recent years,deep learning techniques have provided more efficient and innovative approaches for de novo peptide sequencing by leveraging their powerful capabilities in data processing and feature extraction.We comprehensively investigate the application of deep learning models-including convolutional neural networks(CNNs),encoder-decoder architectures,and transformer architectures-in peptide sequencing tasks,and introduce commonly used datasets,evaluation metrics,and specific model architectures,with a focus on how these models learn complex features from mass spectrometry data and effectively address challenges such as noise interference,data sparsity,and long-range dependencies in peptide sequence prediction.The implementation of these models has significantly improved the accuracy and efficiency of de novo peptide sequencing,offering robust technical support and novel research perspectives for proteomic studies.Furthermore,we explore the potential applications of these approaches in biomedical research,providing innovative technical solutions to advance future developments in proteomics and precision medicine.关键词
肽段从头测序/深度学习/蛋白质组学/串联质谱技术/生物信息学Key words
de novo peptide sequencing/deep learning/proteomics/tandem mass spectrometry/bioinformatics分类
信息技术与安全科学引用本文复制引用
柳楠,张航,邱宁宁..深度学习在肽段测序任务中的应用与进展[J].计算机技术与发展,2025,35(9):200-206,7.基金项目
国家自然科学基金青年项目(61902221) （61902221）
山东省研究生教育教学改革研究项目(SDYJG21173) （SDYJG21173）
