Related Experiment Video
Updated: Oct 14, 2025
11:54
Detection of Protein Ubiquitination Sites by Peptide Enrichment and Mass Spectrometry
Published on: March 23, 2020
9.8K
pValid 2: A deep learning based validation method for peptide identification in shotgun proteomics with increased
Wen-Jing Zhou1, Zhuo-Hong Wei1, Si-Min He1
1Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, China; University of Chinese Academy of Sciences, Beijing, China.
Journal of Proteomics
|November 5, 2021
Summary
pValid 2 is a new computational tool that improves peptide identification accuracy in shotgun proteomics. This method enhances validation by incorporating predicted retention times, leading to fewer false positives and negatives for more reliable protein research.
Area of Science:
- Proteomics and Mass Spectrometry
- Computational Biology and Bioinformatics
Background:
- Tandem mass spectrometry is crucial for shotgun proteomics, but validation of peptide and protein identifications remains a challenge.
- Previous methods like pValid have limitations in scope and performance on complex datasets.
Purpose of the Study:
- To develop a more comprehensive and widely applicable computational validation method for peptide identifications.
- To overcome the limitations of previous validation tools by incorporating new features and improving performance.
Main Methods:
- Developed pValid 2, a novel validation method incorporating a deep learning-based predicted retention time feature (pPredRT).
- Removed features from pValid related to open database search and sub-optimal peptide candidates.
- Implemented validation for identifications from popular search engines like MaxQuant and MS-GF+.
Main Results:
- pValid 2 achieved an average false positive rate of 0.03% and false negative rate of 1.37% on testing datasets.
- Significantly improved detection of incorrect identifications compared to pValid on complex datasets.
- Outperformed three metabolic labeling validation methods and accurately validated open-search datasets.
Conclusions:
- pValid 2 offers a more accurate and versatile computational approach for validating peptide identifications in shotgun proteomics.
- Its improved performance and broad applicability make it a valuable tool for enhancing the reliability of proteomic research.
- pValid 2 has the potential to become a widely adopted standard for validating proteomic data across various search engines.
