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

Virtual, make-on-demand chemical libraries have transformed early-stage drugdiscovery by unlocking vast, synthetically accessible regions of chemicalspace. Recent years have witnessed rapid growth in these libraries frommillions to trillions of compounds, hiding undiscovered, potent hits for avariety of therapeutic targets. However, they are quickly approaching a sizebeyond that which permits explicit enumeration, presenting new challenges forvirtual screening. To overcome these challenges, we propose the CombinatorialSynthesis Library Variational Auto-Encoder (CSLVAE). The proposed generativemodel represents such libraries as a differentiable, hierarchically-organizeddatabase. Given a compound from the library, the molecular encoder constructs aquery for retrieval, which is utilized by the molecular decoder to reconstructthe compound by first decoding its chemical reaction and subsequently decodingits reactants. Our design minimizes autoregression in the decoder, facilitatingthe generation of large, valid molecular graphs. Our method performs fast andparallel batch inference for ultra-large synthesis libraries, enabling a numberof important applications in early-stage drug discovery. Compounds proposed byour method are guaranteed to be in the library, and thus synthetically andcost-effectively accessible. Importantly, CSLVAE can encode out-of-librarycompounds and search for in-library analogues. In experiments, we demonstratethe capabilities of the proposed method in the navigation of massivecombinatorial synthesis libraries.

An efficient graph generative model for navigating ultra-large combinatorial synthesis libraries