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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Coarse-grained molecular models of proteins permit access to length and timescales unattainable by all-atom models and the simulation of processes thatoccur on long-time scales such as aggregation and folding. The reducedresolution realizes computational accelerations but an atomistic representationcan be vital for a complete understanding of mechanistic details. Backmappingis the process of restoring all-atom resolution to coarse-grained molecularmodels. In this work, we report DiAMoNDBack (Diffusion-denoising AutoregressiveModel for Non-Deterministic Backmapping) as an autoregressive denoisingdiffusion probability model to restore all-atom details to coarse-grainedprotein representations retaining only C{\alpha} coordinates. Theautoregressive generation process proceeds from the protein N-terminus toC-terminus in a residue-by-residue fashion conditioned on the C{\alpha} traceand previously backmapped backbone and side chain atoms within the localneighborhood. The local and autoregressive nature of our model makes ittransferable between proteins. The stochastic nature of the denoising diffusionprocess means that the model generates a realistic ensemble of backbone andside chain all-atom configurations consistent with the coarse-grained C{\alpha}trace. We train DiAMoNDBack over 65k+ structures from Protein Data Bank (PDB)and validate it in applications to a hold-out PDB test set,intrinsically-disordered protein structures from the Protein Ensemble Database(PED), molecular dynamics simulations of fast-folding mini-proteins from DEShaw Research, and coarse-grained simulation data. We achieve state-of-the-artreconstruction performance in terms of correct bond formation, avoidance ofside chain clashes, and diversity of the generated side chain configurationalstates. We make DiAMoNDBack model publicly available as a free and open sourcePython package.

DiAMoNDBack: Diffusion-denoising Autoregressive Model for Non-Deterministic Backmapping of C{\alpha} Protein Traces