肽段的理论串联质谱图预测方法研究进展

Trends on Methods for Prediction of Tandem Mass Spectra of Peptides

基于串联质谱技术的蛋白质组学已经成为生命科学领域的重要工具,其中肽段的理论串联质谱图(通常也被称为二级谱图)预测问题在近年来广受关注.大量高质量质谱数据的积累和计算技术的发展为此问题的解决提供了有效途径.肽段的理论二级谱图预测的方法可以分为两大类,一类是基于物理模型的方法,即基于移动质子模型的方法,例如MassAnalyzer、MS-Simulator;另一类是基于机器学习的方法,包括集成学习相关算法和基于神经网络的方法,例如PeptideART、MS2PIP、MS2PBPI和p Deep等.本文对这两大类方法进行了整理和综述,并简要指出了目前理论谱图预测方法存在的一些不足,展望了未来的发展方向.

Tandem mass spectrometry(MS/MS)-based proteomics has become one of the most important tools in bioscience, and researchers now pay much attention to the prediction of MS/MS spectra for protein identification and quantification. With the accumulation of massive high-quality spectrum data and the development of computing technology, quite a few new methods were emerged to solve this problem. These methods can be divided into two catagories:mobile proton model-based methods, such as MassAnalyzer and MS-Simulator;and machine learning-based methods, including traditional machine learning and deep learning, such as PeptideART,MS2PIP, MS2PBPI and pDeep. In this paper, we investigated a wide variety of corresponding methods, and briefly pointed out the deficiencies of existing software tools, and suggested the future work.