Mapping HDX-MS Data to Protein Conformations through Training Ensemble-Based Models
Journal of the American Society for Mass Spectrometry · 2023
DOI: 10.1021/jasms.3c00145 ↗At a glance
Journal article in Journal of the American Society for Mass Spectrometry, 2023. Written by Ramin E Salmas and 2 co-authors. Institution: Department of Chemistry, Britannia House, King's College London, London SE1 1DB, U.K. Major MEDLINE topics: Hydrogen Deuterium Exchange-Mass Spectrometry, Artificial Intelligence. Cited 8 times so far (Crossref); 37 references. The full text is freely available (open access, CC BY 4.0). Funded by: Biotechnology and Biological Sciences Research Council.
Abstract (original language)
An original approach that adopts machine learning inference to predict protein structural information using hydrogen-deuterium exchange mass spectrometry (HDX-MS) is described. The method exploits an in-house optimization program that increases the resolution of HDX-MS data from peptides to amino acids. A system is trained using Gradient Tree Boosting as a type of machine learning ensemble technique to assign a protein secondary structure. Using limited training data we generate a discriminative model that uses optimized HDX-MS data to predict protein secondary structure with an accuracy of 75%. This research could form the basis for new methods exploiting artificial intelligence to model protein conformations by HDX-MS.
Subjects
MeSH terms (MEDLINE)
Substances
Authors and institutions
- Department of Chemistry, Britannia House, King's College London, London SE1 1DB, U.K.
ORCID profiles: Ramin E Salmas, Antoni J Borysik
Funding
- Biotechnology and Biological Sciences Research Council
Cite
APA
Salmas, R. E., Harris, M. J., & Borysik, A. J. (2023). Mapping HDX-MS Data to Protein Conformations through Training Ensemble-Based Models. Journal of the American Society for Mass Spectrometry. https://doi.org/10.1021/jasms.3c00145
Vancouver
Salmas RE, Harris MJ, Borysik AJ. Mapping HDX-MS Data to Protein Conformations through Training Ensemble-Based Models. Journal of the American Society for Mass Spectrometry. 2023. doi:10.1021/jasms.3c00145
BibTeX
@article{Salmas2023,
author = {Salmas, Ramin E and Harris, Matthew J and Borysik, Antoni J},
title = {Mapping HDX-MS Data to Protein Conformations through Training Ensemble-Based Models},
journal = {Journal of the American Society for Mass Spectrometry},
year = {2023},
doi = {10.1021/jasms.3c00145}
}
EUVIMED