pep2peaks:基于序列到序列模型的肽碎片离子强度预测
首发时间:2019-04-11
摘要:在基于串联质谱(MS/MS)的蛋白质组学中,理论质谱的预测对肽序列的鉴定具有重要意义。近年来,一些研究者致力于预测多肽的理论质谱,包括基于动力学模型的方法和基于机器学习的方法,然而这些方法存在某些不足之处。本文提出了基于序列到序列(sequencetosequence,seq2seq)的肽碎片离子强度预测模型pep2peaks,并在多组数据集上验证了pep2peaks的能够达到PCC中值在0.95以上的预测性能,且具有良好的泛化性能和抗干扰能力。pep2peaks同时解决了较长序列肽的预测问题,即pep2peaks可以预测任意长度的肽序列。
关键词: 肽碎片离子 强度预测 seq2seq 蛋白质组学 串联质谱
For information in English, please click here
pep2peaks: Prediction of peptide fragment ion intensity based on sequence-to-sequence model
Abstract:In proteomics based on tandem mass spectrometry (MS/MS), the prediction of theoretical mass spectrometry is of great significance for the identification of peptide sequences.In recent years, some researchers have devoted themselves to the prediction of theoretical mass spectra of polypeptides, including dynamic model-based methods and machine learning-based methods. However, there are some shortcomings in these methods. In this paper, a sequence to sequence (seq2seq) based model for predicting the ionic strength of peptide fragments, pep2peaks, is proposed. The predictive performance of pep2peaks is verified on a number of datasets to be above the 0.95 medianPCC, and it has good generalization performance and anti-interference ability. pep2peaks also solve the problem of predicting long sequence peptide, that is, pep2peaks can predict any length of peptide sequence.
Keywords: Fragment ions Strength prediction seq2seq Proteomics Tandem mass spectrometry
引用
No.****
动态公开评议
共计0人参与
勘误表
pep2peaks:基于序列到序列模型的肽碎片离子强度预测
评论
全部评论0/1000