English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

All-atom and coarse-grained molecular dynamics are two widely usedcomputational tools to study the conformational states of proteins. Yet, thesetwo simulation methods suffer from the fact that without access tosupercomputing resources, the time and length scales at which these statesbecome detectable are difficult to achieve. One alternative to such methods isbased on encoding the atomistic trajectory of molecular dynamics as a shorthandversion devoid of physical particles, and then learning to propagate theencoded trajectory through the use of artificial intelligence. Here we showthat a simple textual representation of the frames of molecular dynamicstrajectories as vectors of Ramachandran basin classes retains most of thestructural information of the full atomistic representation of a protein ineach frame, and can be used to generate equivalent atom-less trajectoriessuitable to train different types of generative neural networks. In turn, thetrained generative models can be used to extend indefinitely the atom-lessdynamics or to sample the conformational space of proteins from theirrepresentation in the models latent space. We define intuitively thismethodology as molecular dynamics without molecules, and show that it enablesto cover physically relevant states of proteins that are difficult to accesswith traditional molecular dynamics.

Molecular dynamics without molecules: searching the conformational space of proteins with generative neural networks