Enhancing the biological insight from limited proteolysis-coupled mass spectrometry
Nagel, L.; Grossbach, J.; Cappelletti, V.; Doerig, C.; Picotti, P.; Beyer, A.
Show abstract
Limited proteolysis combined with mass spectrometry (LiP-MS) facilitates probing structural changes on a proteome-wide scale in situ. Distinguishing the different signal contributions, such as changes in protein abundance, from protein abundance changes remains challenging. We propose a two-step approach, first removing unwanted variations from the LiP signal that are not caused by protein structural effects and subsequently inferring the effects of variables of interest on the remaining signal. Using LiP-MS data from three species we demonstrate that our framework provides a uniquely powerful approach for deconvolving LiP-MS signals and inferring protein structural changes.
Matching journals
The top 2 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Imputation of label-free quantitative mass spectrometry-based proteomics data using self-supervised deep learning 96%
- Sequence-to-sequence translation from mass spectra to peptides with a transformer model 96%
- AlphaPeptDeep: A modular deep learning framework to predict peptide properties for proteomics 96%
Similar papers in this journal
- Turnover and replication analysis by isotope labeling (TRAIL) reveals the influence of tissue context on protein and organelle lifetimes 96%
- Protein Complexes in cells by AI-assisted structural proteomics 95%
- Limited proteolysis-coupled mass spectrometry captures proteome-wide protein structural alterations and biomolecular condensation in living cells 95%
Similar papers in this journal
- To fly, or not to fly, that is the question: A deep learning model for peptide detectability prediction in mass spectrometry 95%
- Pairwise Attention: Leveraging Mass Differences to Enhance De Novo Sequencing of Mass Spectra 95%
- Proteoform Identification by Combining RNA-Seq and Top-down Mass Spectrometry 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.