Building a One-Stop Platform Applying Deep Neural Networks to Optimize Signature Peptide Selections for Assay Designs of Mrm-Based Absolute Quantifications in Targeted Proteomics

Project: National Science and Technology CouncilNational Science and Technology Council Academic Grants

Project Details

Abstract

本計畫預期對社會和學術發展的影響包括: (1) 建構一個一站式平台提供標準化流程加速標識胜肽選擇,且使MRM試驗盡可能能達成高敏感度、高準確性以及高再現性的蛋白絕對定量。(2) 本計畫所發展之人工智慧模型,可藉由胜肽的物理化學特徵來解釋標識胜肽的合適性,讓研究人員能夠有所依據且合理地選擇標識胜肽,而所選出的胜肽亦預能夠更敏感與準確地被質譜儀偵測到。(3) 由本計畫所衍生出來的標識胜肽的物理化學特徵的知識,可進一步運用於其他質譜儀數據研究當中,例如,使用質譜儀進行胜肽的從頭測序實驗時,使用質譜訊號直接推論至胜肽序列時,若推論模型能考慮此胜肽物化特徵知識,預期可推論出較為正確之胜肽序列。

Project IDs

Project ID:PC11207-2163
External Project ID:NSTC112-2320-B182-032
StatusFinished
Effective start/end date01/08/2331/07/24

Keywords

  • targeted proteomics
  • multiple reaction monitoring
  • mass spectrometry data analysis
  • absolute protein quantitation
  • signature peptide selection
  • deep learning

Fingerprint

Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.