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

Deep generative models have achieved tremendous success in designing noveldrug molecules in recent years. A new thread of works have shown the greatpotential in advancing the specificity and success rate of in silico drugdesign by considering the structure of protein pockets. This setting postsfundamental computational challenges in sampling new chemical compounds thatcould satisfy multiple geometrical constraints imposed by pockets. Previoussampling algorithms either sample in the graph space or only consider the 3Dcoordinates of atoms while ignoring other detailed chemical structures such asbond types and functional groups. To address the challenge, we developPocket2Mol, an E(3)-equivariant generative network composed of two modules: 1)a new graph neural network capturing both spatial and bonding relationshipsbetween atoms of the binding pockets and 2) a new efficient algorithm whichsamples new drug candidates conditioned on the pocket representations from atractable distribution without relying on MCMC. Experimental resultsdemonstrate that molecules sampled from Pocket2Mol achieve significantly betterbinding affinity and other drug properties such as druglikeness and syntheticaccessibility.

Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets