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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Longer timelines and lower success rates of drug candidates limit theproductivity of clinical trials in the pharmaceutical industry. Promising denovo drug design techniques help solve this by exploring a broader chemicalspace, efficiently generating new molecules, and providing improved therapies.However, optimizing for molecular characteristics found in approved oral drugsremains a challenge, limiting de novo usage. In this work, we propose NovoMol,a novel de novo method using recurrent neural networks to mass-generate drugmolecules with high oral bioavailability, increasing clinical trial timeefficiency. Molecules were optimized for desirable traits and ranked using thequantitative estimate of drug-likeness (QED). Generated molecules meeting QED'soral bioavailability threshold were used to retrain the neural network, and,after five training cycles, 76% of generated molecules passed this strictthreshold and 96% passed the traditionally used Lipinski's Rule of Five. Thetrained model was then used to generate specific drug candidates for thecancer-related PDGFR{\alpha} receptor and 44% of generated candidates hadbetter binding affinity than the current state-of-the-art drug, Imatinib (witha receptor binding affinity of -9.4 kcal/mol), and the best-generated candidateat -12.9 kcal/mol. NovoMol provides a time/cost-efficient AI-based de novomethod offering promising drug candidates for clinical trials.

NovoMol: Recurrent Neural Network for Orally Bioavailable Drug Design and Validation on PDGFR{\alpha} Receptor