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

De novo molecular design has facilitated the exploration of large chemicalspace to accelerate drug discovery. Structure-based de novo method can overcomethe data scarcity of active ligands by incorporating drug-target interactioninto deep generative architectures. However, these strategies are bottleneckedby the small fraction of experimentally determined protein or complexstructures. In addition, the cost of molecular generation is computationallyexpensive due to 3D representations of both molecule and protein. Here, wedemonstrate a widely used and fast protein sequence-based reinforcementlearning (RL) model for drug discovery. In the generative model, one of thereward components, a binding affinity predictor, is based on 1D proteinsequence and molecular SMILES. As a proof of concept, the RL model was utilizedto design molecules for four targets. The generated compounds showedbioactivities by the validation of both QSAR and molecular docking withexperimental 3D binding pockets. We also found that the performance ofgenerated molecules depends on the selection of data source training for thebinding predictor. Furthermore, drug design for a kinase without anyexperimental structure, CDK20, was studied by our model. With only 1D proteinsequence as input, the generated novel compounds showed favorable bindingaffinity based on the AlphaFold predicted structure.

Widely Used and Fast De Novo Drug Design by a Protein Sequence-Based Reinforcement Learning Model