Predicting new protein conformations from molecular dynamics simulation conformational landscapes and machine learning
Johannissen, Linus O.; email: firstname.lastname@example.org
Hay, Sam; orcid: 0000-0003-3274-0938; email: email@example.com
MetadataShow full item record
AbstractAbstract: Molecular dynamics (MD) simulations are a popular method of studying protein structure and function, but are unable to reliably sample all relevant conformational space in reasonable computational timescales. A range of enhanced sampling methods are available that can improve conformational sampling, but these do not offer a complete solution. We present here a proof‐of‐principle method of combining MD simulation with machine learning to explore protein conformational space. An autoencoder is used to map snapshots from MD simulations onto a user‐defined conformational landscape defined by principal components analysis or specific structural features, and we show that we can predict, with useful accuracy, conformations that are not present in the training data. This method offers a new approach to the prediction of new low energy/physically realistic structures of conformationally dynamic proteins and allows an alternative approach to enhanced sampling of MD simulations.
CitationProteins: Structure, Function, and Bioinformatics, volume 89, issue 8, page 915-921
PublisherJohn Wiley & Sons, Inc.
DescriptionFrom Wiley via Jisc Publications Router
History: received 2020-08-05, rev-recd 2021-01-21, accepted 2021-02-23, pub-electronic 2021-03-03, pub-print 2021-08
Article version: VoR
Publication status: Published
Funder: Biotechnology and Biological Sciences Research Council; Id: http://dx.doi.org/10.13039/501100000268; Grant(s): BB/M017702/1