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

Generative models for structure-based molecular design hold significantpromise for drug discovery, with the potential to speed up the hit-to-leaddevelopment cycle, while improving the quality of drug candidates and reducingcosts. Data sparsity and bias are, however, two main roadblocks to thedevelopment of 3D-aware models. Here we propose a first-in-kind trainingprotocol based on multi-level contrastive learning for improved bias controland data efficiency. The framework leverages the large data resources availablefor 2D generative modelling with datasets of ligand-protein complexes. Theresult are hierarchical generative models that are topologically unbiased,explainable and customizable. We show how, by deconvolving the generativeposterior into chemical, topological and structural context factors, we notonly avoid common pitfalls in the design and evaluation of generative models,but furthermore gain detailed insight into the generative process itself. Thisimproved transparency significantly aids method development, besides allowingfine-grained control over novelty vs familiarity.

3D pride without 2D prejudice: Bias-controlled multi-level generative models for structure-based ligand design