Fragment Mass Spectrum Prediction Facilitates Site Localization of Phosphorylation
- Yi YangYi YangDepartment of Chemistry and Shanghai Stomatological Hospital, Fudan University, Handan Road 220, Shanghai 200000, ChinaMore by Yi Yang
- ,
- Peter Horvatovich*Peter Horvatovich*Email: [email protected]Department of Pharmacy, University of Groningen, Antonius Deusinglaan 1, Groningen 9700 AD, The NetherlandsMore by Peter Horvatovich
- , and
- Liang Qiao*Liang Qiao*Email: [email protected]Department of Chemistry and Shanghai Stomatological Hospital, Fudan University, Handan Road 220, Shanghai 200000, ChinaMore by Liang Qiao
Abstract

Liquid chromatography tandem mass spectrometry (LC–MS/MS) has been the most widely used technology for phosphoproteomics studies. As an alternative to database searching and probability-based phosphorylation site localization approaches, spectral library searching has been proved to be effective in the identification of phosphopeptides. However, incompletion of experimental spectral libraries limits the identification capability. Herein, we utilize MS/MS spectrum prediction coupled with spectral matching for site localization of phosphopeptides. In silico MS/MS spectra are generated from peptide sequences by deep learning/machine learning models trained with nonphosphopeptides. Then, mass shift according to phosphorylation sites, phosphoric acid neutral loss, and a “budding” strategy are adopted to adjust the in silico mass spectra. In silico MS/MS spectra can also be generated in one step for phosphopeptides using models trained with phosphopeptides. The method is benchmarked on data sets of synthetic phosphopeptides and is used to process real biological samples. It is demonstrated to be a method requiring only computational resources that supplements the probability-based approaches for phosphorylation site localization of singly and multiply phosphorylated peptides.
Cited By
This article is cited by 11 publications.
- Yang Zhang, Benjamin Dreyer, Natalia Govorukhina, Alexander M. Heberle, Saša Končarević, Christoph Krisp, Christiane A. Opitz, Pauline Pfänder, Rainer Bischoff, Hartmut Schlüter, Marcel Kwiatkowski, Kathrin Thedieck, Peter L. Horvatovich. Comparative Assessment of Quantification Methods for Tumor Tissue Phosphoproteomics. Analytical Chemistry 2022, 94 (31) , 10893-10906. https://doi.org/10.1021/acs.analchem.2c01036
- Zhen-Lin Chen, Peng-Zhi Mao, Wen-Feng Zeng, Hao Chi, Si-Min He. pDeepXL: MS/MS Spectrum Prediction for Cross-Linked Peptide Pairs by Deep Learning. Journal of Proteome Research 2021, 20 (5) , 2570-2582. https://doi.org/10.1021/acs.jproteome.0c01004
- Jürgen Cox. Prediction of peptide mass spectral libraries with machine learning. Nature Biotechnology 2023, 41 (1) , 33-43. https://doi.org/10.1038/s41587-022-01424-w
- Patrick Bangert, Nandha Kumar Balasubramaniam, Carol E. Parker, Christoph H. Borchers. Pattern Recognition for Mass-Spectrometry-Based Proteomics. 2022https://doi.org/10.5772/intechopen.108422
- Joseph Paul, Timothy D. Veenstra. Separation of Serum and Plasma Proteins for In-Depth Proteomic Analysis. Separations 2022, 9 (4) , 89. https://doi.org/10.3390/separations9040089
- Jiří Urban. A review on recent trends in the phosphoproteomics workflow. From sample preparation to data analysis. Analytica Chimica Acta 2022, 1199 , 338857. https://doi.org/10.1016/j.aca.2021.338857
- Joanna Bons, Jacob Rose, Amy O’Broin, Birgit Schilling. Advanced mass spectrometry-based methods for protein molecular-structural biologists. 2022, 311-326. https://doi.org/10.1016/B978-0-323-90264-9.00020-9
- Yi Yang, Ling Lin, Liang Qiao. Deep learning approaches for data-independent acquisition proteomics. Expert Review of Proteomics 2021, 18 (12) , 1031-1043. https://doi.org/10.1080/14789450.2021.2020654
- Fynn M. Hansen, Maria C. Tanzer, Franziska Brüning, Isabell Bludau, Che Stafford, Brenda A. Schulman, Maria S. Robles, Ozge Karayel, Matthias Mann. Data-independent acquisition method for ubiquitinome analysis reveals regulation of circadian biology. Nature Communications 2021, 12 (1) https://doi.org/10.1038/s41467-020-20509-1
- Ronghui Lou, Weizhen Liu, Rongjie Li, Shanshan Li, Xuming He, Wenqing Shui. DeepPhospho accelerates DIA phosphoproteome profiling through in silico library generation. Nature Communications 2021, 12 (1) https://doi.org/10.1038/s41467-021-26979-1
- Matthias Mann, Chanchal Kumar, Wen-Feng Zeng, Maximilian T. Strauss. Artificial intelligence for proteomics and biomarker discovery. Cell Systems 2021, 12 (8) , 759-770. https://doi.org/10.1016/j.cels.2021.06.006