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

Recently, utilizing reinforcement learning (RL) to generate molecules withdesired properties has been highlighted as a promising strategy for drugdesign. A molecular docking program - a physical simulation that estimatesprotein-small molecule binding affinity - can be an ideal reward scoringfunction for RL, as it is a straightforward proxy of the therapeutic potential.Still, two imminent challenges exist for this task. First, the models oftenfail to generate chemically realistic and pharmacochemically acceptablemolecules. Second, the docking score optimization is a difficult explorationproblem that involves many local optima and less smooth surfaces with respectto molecular structure. To tackle these challenges, we propose a novel RLframework that generates pharmacochemically acceptable molecules with largedocking scores. Our method - Fragment-based generative RL with ExplorativeExperience replay for Drug design (FREED) - constrains the generated moleculesto a realistic and qualified chemical space and effectively explores the spaceto find drugs by coupling our fragment-based generation method and a novelerror-prioritized experience replay (PER). We also show that our model performswell on both de novo and scaffold-based schemes. Our model produces moleculesof higher quality compared to existing methods while achieving state-of-the-artperformance on two of three targets in terms of the docking scores of thegenerated molecules. We further show with ablation studies that our method,predictive error-PER (FREED(PE)), significantly improves the model performance.

Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation