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

Predicting the binding structure of a small molecule ligand to a protein -- atask known as molecular docking -- is critical to drug design. Recent deeplearning methods that treat docking as a regression problem have decreasedruntime compared to traditional search-based methods but have yet to offersubstantial improvements in accuracy. We instead frame molecular docking as agenerative modeling problem and develop DiffDock, a diffusion generative modelover the non-Euclidean manifold of ligand poses. To do so, we map this manifoldto the product space of the degrees of freedom (translational, rotational, andtorsional) involved in docking and develop an efficient diffusion process onthis space. Empirically, DiffDock obtains a 38% top-1 success rate (RMSD<2A) onPDBBind, significantly outperforming the previous state-of-the-art oftraditional docking (23%) and deep learning (20%) methods. Moreover, whileprevious methods are not able to dock on computationally folded structures(maximum accuracy 10.4%), DiffDock maintains significantly higher precision(21.7%). Finally, DiffDock has fast inference times and provides confidenceestimates with high selective accuracy.

DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking