Scholarlink

The advancements in technology and computation are progressively enhancing the sensitivity and accuracy of mass spectrometry-based immunopeptidomics. In our previous study, we developed a machine learning filter by incorporating retention time as well as predicted physicochemical properties of peptides to eliminate false positives in identifications by Mascot-based traditional shotgun proteomic workflow. The present study provides a step-by-step guide on emphasizing how to prepare and organize the data, as well as applying the machine learning model to analyze the users’ own experimental data.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Novel Machine Learning Post-processing Filter for Mass Spectrometry-Based Proteogenomics Leveraging Retention Time Deviation and Peptide Physicochemical Properties

  • 实验方案

  • 发表日期：

    2026年

查看全文
  • Feifei Wei,
  • Tetsuro Sasada

摘要

The advancements in technology and computation are progressively enhancing the sensitivity and accuracy of mass spectrometry-based immunopeptidomics. In our previous study, we developed a machine learning filter by incorporating retention time as well as predicted physicochemical properties of peptides to eliminate false positives in identifications by Mascot-based traditional shotgun proteomic workflow. The present study provides a step-by-step guide on emphasizing how to prepare and organize the data, as well as applying the machine learning model to analyze the users’ own experimental data.