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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Machine learning based methods have shown potential for optimizing existingmolecules with more desirable properties, a critical step towards acceleratingnew chemical discovery. Here we propose QMO, a generic query-based moleculeoptimization framework that exploits latent embeddings from a moleculeautoencoder. QMO improves the desired properties of an input molecule based onefficient queries, guided by a set of molecular property predictions andevaluation metrics. We show that QMO outperforms existing methods in thebenchmark tasks of optimizing small organic molecules for drug-likeness andsolubility under similarity constraints. We also demonstrate significantproperty improvement using QMO on two new and challenging tasks that are alsoimportant in real-world discovery problems: (i) optimizing existing potentialSARS-CoV-2 Main Protease inhibitors toward higher binding affinity; and (ii)improving known antimicrobial peptides towards lower toxicity. Results from QMOshow high consistency with external validations, suggesting effective means tofacilitate material optimization problems with design constraints.

Optimizing Molecules using Efficient Queries from Property Evaluations