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

Deep generative models have recently achieved superior performance in 3Dmolecule generation. Most of them first generate atoms and then add chemicalbonds based on the generated atoms in a post-processing manner. However, theremight be no corresponding bond solution for the temporally generated atoms astheir locations are generated without considering potential bonds. We definethis problem as the atom-bond inconsistency problem and claim it is the mainreason for current approaches to generating unrealistic 3D molecules. Toovercome this problem, we propose a new diffusion model called MolDiff whichcan generate atoms and bonds simultaneously while still maintaining theirconsistency by explicitly modeling the dependence between their relationships.We evaluated the generation ability of our proposed model and the quality ofthe generated molecules using criteria related to both geometry and chemicalproperties. The empirical studies showed that our model outperforms previousapproaches, achieving a three-fold improvement in success rate and generatingmolecules with significantly better quality.

MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generation