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

Many protein design applications, such as binder or enzyme design, requirescaffolding a structural motif with high precision. Generative modellingparadigms based on denoising diffusion processes emerged as a leading candidateto address this motif scaffolding problem and have shown early experimentalsuccess in some cases. In the diffusion paradigm, motif scaffolding is treatedas a conditional generation task, and several conditional generation protocolswere proposed or imported from the Computer Vision literature. However, most ofthese protocols are motivated heuristically, e.g. via analogies to Langevindynamics, and lack a unifying framework, obscuring connections between thedifferent approaches. In this work, we unify conditional training andconditional sampling procedures under one common framework based on themathematically well-understood Doob's h-transform. This new perspective allowsus to draw connections between existing methods and propose a new variation onexisting conditional training protocols. We illustrate the effectiveness ofthis new protocol in both, image outpainting and motif scaffolding and findthat it outperforms standard methods.

A framework for conditional diffusion modelling with applications in motif scaffolding for protein design