Extracting Residue Solvent Exposure from Covalent Labeling Data with Machine Learning: A Hybrid Approach for Protein Structure Prediction
Journal of the American Society for Mass Spectrometry · 2025
DOI: 10.1021/jasms.5c00053 ↗At a glance
Journal article in Journal of the American Society for Mass Spectrometry, 2025. Written by Elijah H Day and 1 co-authors. Institution: Department of Chemistry and Biochemistry, Ohio State University, Columbus, Ohio 43210, United States. Major MEDLINE topics: Machine Learning, Proteins, Protein Footprinting. Cited 6 times so far (Crossref); 104 references.
Abstract (original language)
Hydroxyl radical protein footprinting (HRPF) coupled with mass spectrometry yields information about residue solvent exposure and protein topology. However, data from these experiments are sparse and require computational interpretation to generate useful structural insight. We previously implemented a Rosetta algorithm that uses experimental HRPF data to improve protein structure prediction. Modern structure prediction methods, such as AlphaFold2 (AF2), use machine learning (ML) to generate their predictions. Implementation of an HRPF-guided version of AF2 is challenging due to the substantial amount of training data required and the inherently abstract nature of ML networks. Thus, here we present a hybrid method that uses a light gradient boosting machine to predict residue solvent accessibility from experimental HRPF data. These predictions were subsequently used to improve Rosetta structure prediction. Our hybrid approach identified models with atomic-level detail for all four proteins in our benchmark set. These results illustrate that it is possible to successfully use ML in combination with HRPF data to accurately predict protein structures.
Subjects
MeSH terms (MEDLINE)
Substances
Authors and institutions
- Department of Chemistry and Biochemistry, Ohio State University, Columbus, Ohio 43210, United States.
ORCID profiles: Elijah H Day, Steffen Lindert
Cite
APA
Day, E. H., & Lindert, S. (2025). Extracting Residue Solvent Exposure from Covalent Labeling Data with Machine Learning: A Hybrid Approach for Protein Structure Prediction. Journal of the American Society for Mass Spectrometry. https://doi.org/10.1021/jasms.5c00053
Vancouver
Day EH, Lindert S. Extracting Residue Solvent Exposure from Covalent Labeling Data with Machine Learning: A Hybrid Approach for Protein Structure Prediction. Journal of the American Society for Mass Spectrometry. 2025. doi:10.1021/jasms.5c00053
BibTeX
@article{Day2025,
author = {Day, Elijah H and Lindert, Steffen},
title = {Extracting Residue Solvent Exposure from Covalent Labeling Data with Machine Learning: A Hybrid Approach for Protein Structure Prediction},
journal = {Journal of the American Society for Mass Spectrometry},
year = {2025},
doi = {10.1021/jasms.5c00053}
}
EUVIMED