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

Proteins power a vast array of functional processes in living cells. Thecapability to create new proteins with designed structures and functions wouldthus enable the engineering of cellular behavior and development ofprotein-based therapeutics and materials. Structure-based protein design aimsto find structures that are designable (can be realized by a protein sequence),novel (have dissimilar geometry from natural proteins), and diverse (span awide range of geometries). While advances in protein structure prediction havemade it possible to predict structures of novel protein sequences, thecombinatorially large space of sequences and structures limits the practicalityof search-based methods. Generative models provide a compelling alternative, byimplicitly learning the low-dimensional structure of complex datadistributions. Here, we leverage recent advances in denoising diffusionprobabilistic models and equivariant neural networks to develop Genie, agenerative model of protein structures that performs discrete-time diffusionusing a cloud of oriented reference frames in 3D space. Through in silicoevaluations, we demonstrate that Genie generates protein backbones that aremore designable, novel, and diverse than existing models. This indicates thatGenie is capturing key aspects of the distribution of protein structure spaceand facilitates protein design with high success rates. Code for generating newproteins and training new versions of Genie is available athttps://github.com/aqlaboratory/genie.

Generating Novel, Designable, and Diverse Protein Structures by Equivariantly Diffusing Oriented Residue Clouds