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

In the last few years, de novo molecular design using machine learning hasmade great technical progress but its practical deployment has not been assuccessful. This is mostly owing to the cost and technical difficulty ofsynthesizing such computationally designed molecules. To overcome suchbarriers, various methods for synthetic route design using deep neural networkshave been studied intensively in recent years. However, little progress hasbeen made in designing molecules and their synthetic routes simultaneously.Here, we formulate the problem of simultaneously designing molecules with thedesired set of properties and their synthetic routes within the framework ofBayesian inference. The design variables consist of a set of reactants in areaction network and its network topology. The design space is extremely largebecause it consists of all combinations of purchasable reactants, often in theorder of millions or more. In addition, the designed reaction networks canadopt any topology beyond simple multistep linear reaction routes. To solvethis hard combinatorial problem, we present a powerful sequential Monte Carloalgorithm that recursively designs a synthetic reaction network by sequentiallybuilding up single-step reactions. In a case study of designing drug-likemolecules based on commercially available compounds, compared with heuristiccombinatorial search methods, the proposed method shows overwhelmingperformance in terms of computational efficiency and coverage and novelty withrespect to existing compounds.

Bayesian Sequential Stacking Algorithm for Concurrently Designing Molecules and Synthetic Reaction Networks