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 diffusion models are a promising avenue for 3D de novomolecular design in materials science and drug discovery. However, theirutility is still limited by suboptimal performance on large molecularstructures and limited training data. To address this gap, we explore thedesign space of E(3)-equivariant diffusion models, focusing on previouslyunexplored areas. Our extensive comparative analysis evaluates the interplaybetween continuous and discrete state spaces. From this investigation, wepresent the EQGAT-diff model, which consistently outperforms established modelsfor the QM9 and GEOM-Drugs datasets. Significantly, EQGAT-diff takes continuousatom positions, while chemical elements and bond types are categorical and usestime-dependent loss weighting, substantially increasing training convergence,the quality of generated samples, and inference time. We also showcase thatincluding chemically motivated additional features like hybridization states inthe diffusion process enhances the validity of generated molecules. To furtherstrengthen the applicability of diffusion models to limited training data, weinvestigate the transferability of EQGAT-diff trained on the large PubChem3Ddataset with implicit hydrogen atoms to target different data distributions.Fine-tuning EQGAT-diff for just a few iterations shows an efficientdistribution shift, further improving performance throughout data sets.Finally, we test our model on the Crossdocked data set for structure-based denovo ligand generation, underlining the importance of our findings showingstate-of-the-art performance on Vina docking scores.

Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generation