日本語
 
Help Privacy Policy ポリシー/免責事項
  詳細検索ブラウズ

アイテム詳細


公開

学術論文

Ad hoc learning of peptide fragmentation from mass spectra enables an interpretable detection of phosphorylated and cross-linked peptides

MPS-Authors
/persons/resource/persons295643

Altenburg,  Tom       
IMPRS for Biology and Computation (Anne-Dominique Gindrat), Dept. of Computational Molecular Biology (Head: Martin Vingron), Max Planck Institute for Molecular Genetics, Max Planck Society;

External Resource
There are no locators available
Fulltext (restricted access)
There are currently no full texts shared for your IP range.
フルテキスト (公開)
付随資料 (公開)
There is no public supplementary material available
引用

Altenburg, T., Giese, S. H., Wang, S., Muth, T., & Renard, B. Y. (2022). Ad hoc learning of peptide fragmentation from mass spectra enables an interpretable detection of phosphorylated and cross-linked peptides. Nature Machine Intelligence, 4, 378-388. doi:10.1038/s42256-022-00467-7.


引用: https://hdl.handle.net/21.11116/0000-000E-56E7-D
要旨
Mass spectrometry-based proteomics provides a holistic snapshot of the entire protein set of living cells on a molecular level. Currently, only a few deep learning approaches exist that involve peptide fragmentation spectra, which represent partial sequence information of proteins. Commonly, these approaches lack the ability to characterize less studied or even unknown patterns in spectra because of their use of explicit domain knowledge. Here, to elevate unrestricted learning from spectra, we introduce ‘ad hoc learning of fragmentation’ (AHLF), a deep learning model that is end-to-end trained on 19.2 million spectra from several phosphoproteomic datasets. AHLF is interpretable, and we show that peak-level feature importance values and pairwise interactions between peaks are in line with corresponding peptide fragments. We demonstrate our approach by detecting post-translational modifications, specifically protein phosphorylation based on only the fragmentation spectrum without a database search. AHLF increases the area under the receiver operating characteristic curve (AUC) by an average of 9.4% on recent phosphoproteomic data compared with the current state of the art on this task. Furthermore, use of AHLF in rescoring search results increases the number of phosphopeptide identifications by a margin of up to 15.1% at a constant false discovery rate. To show the broad applicability of AHLF, we use transfer learning to also detect cross-linked peptides, as used in protein structure analysis, with an AUC of up to 94%.