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

Shape-based virtual screening is widely employed in ligand-based drug designto search chemical libraries for molecules with similar 3D shapes yet novel 2Dchemical structures compared to known ligands. 3D deep generative models havethe potential to automate this exploration of shape-conditioned 3D chemicalspace; however, no existing models can reliably generate valid drug-likemolecules in conformations that adopt a specific shape such as a known bindingpose. We introduce a new multimodal 3D generative model that enablesshape-conditioned 3D molecular design by equivariantly encoding molecular shapeand variationally encoding chemical identity. We ensure local geometric andchemical validity of generated molecules by using autoregressive fragment-basedgeneration with heuristic bonding geometries, allowing the model to prioritizethe scoring of rotatable bonds to best align the growing conformationalstructure to the target shape. We evaluate our 3D generative model in tasksrelevant to drug design including shape-conditioned generation of chemicallydiverse molecular structures and shape-constrained molecular propertyoptimization, demonstrating its utility over virtual screening of enumeratedlibraries.

Equivariant Shape-Conditioned Generation of 3D Molecules for Ligand-Based Drug Design