Prediction of glycopeptide fragment mass spectra by deep learning
Abstract Deep learning has achieved a notable success in mass spectrometry-based proteomics and is now emerging in glycoproteomics. While various deep learning models can predict fragment mass spectra of peptides with good accuracy, they cannot cope with the non-linear glycan structure in an intact...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-03-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-024-46771-1 |
| _version_ | 1797247129486360576 |
|---|---|
| author | Yi Yang Qun Fang |
| author_facet | Yi Yang Qun Fang |
| author_sort | Yi Yang |
| collection | DOAJ |
| description | Abstract Deep learning has achieved a notable success in mass spectrometry-based proteomics and is now emerging in glycoproteomics. While various deep learning models can predict fragment mass spectra of peptides with good accuracy, they cannot cope with the non-linear glycan structure in an intact glycopeptide. Herein, we present DeepGlyco, a deep learning-based approach for the prediction of fragment spectra of intact glycopeptides. Our model adopts tree-structured long-short term memory networks to process the glycan moiety and a graph neural network architecture to incorporate potential fragmentation pathways of a specific glycan structure. This feature is beneficial to model explainability and differentiation ability of glycan structural isomers. We further demonstrate that predicted spectral libraries can be used for data-independent acquisition glycoproteomics as a supplement for library completeness. We expect that this work will provide a valuable deep learning resource for glycoproteomics. |
| first_indexed | 2024-04-24T19:53:47Z |
| format | Article |
| id | doaj.art-5f8bd09fc326422aa0ab84569387ded2 |
| institution | Directory Open Access Journal |
| issn | 2041-1723 |
| language | English |
| last_indexed | 2024-04-24T19:53:47Z |
| publishDate | 2024-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj.art-5f8bd09fc326422aa0ab84569387ded22024-03-24T12:27:05ZengNature PortfolioNature Communications2041-17232024-03-0115111210.1038/s41467-024-46771-1Prediction of glycopeptide fragment mass spectra by deep learningYi Yang0Qun Fang1ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang UniversityZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang UniversityAbstract Deep learning has achieved a notable success in mass spectrometry-based proteomics and is now emerging in glycoproteomics. While various deep learning models can predict fragment mass spectra of peptides with good accuracy, they cannot cope with the non-linear glycan structure in an intact glycopeptide. Herein, we present DeepGlyco, a deep learning-based approach for the prediction of fragment spectra of intact glycopeptides. Our model adopts tree-structured long-short term memory networks to process the glycan moiety and a graph neural network architecture to incorporate potential fragmentation pathways of a specific glycan structure. This feature is beneficial to model explainability and differentiation ability of glycan structural isomers. We further demonstrate that predicted spectral libraries can be used for data-independent acquisition glycoproteomics as a supplement for library completeness. We expect that this work will provide a valuable deep learning resource for glycoproteomics.https://doi.org/10.1038/s41467-024-46771-1 |
| spellingShingle | Yi Yang Qun Fang Prediction of glycopeptide fragment mass spectra by deep learning Nature Communications |
| title | Prediction of glycopeptide fragment mass spectra by deep learning |
| title_full | Prediction of glycopeptide fragment mass spectra by deep learning |
| title_fullStr | Prediction of glycopeptide fragment mass spectra by deep learning |
| title_full_unstemmed | Prediction of glycopeptide fragment mass spectra by deep learning |
| title_short | Prediction of glycopeptide fragment mass spectra by deep learning |
| title_sort | prediction of glycopeptide fragment mass spectra by deep learning |
| url | https://doi.org/10.1038/s41467-024-46771-1 |
| work_keys_str_mv | AT yiyang predictionofglycopeptidefragmentmassspectrabydeeplearning AT qunfang predictionofglycopeptidefragmentmassspectrabydeeplearning |