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

The novel nature of SARS-CoV-2 calls for the development of efficient de novodrug design approaches. In this study, we propose an end-to-end framework,named CogMol (Controlled Generation of Molecules), for designing new drug-likesmall molecules targeting novel viral proteins with high affinity andoff-target selectivity. CogMol combines adaptive pre-training of a molecularSMILES Variational Autoencoder (VAE) and an efficient multi-attributecontrolled sampling scheme that uses guidance from attribute predictors trainedon latent features. To generate novel and optimal drug-like molecules forunseen viral targets, CogMol leverages a protein-molecule binding affinitypredictor that is trained using SMILES VAE embeddings and protein sequenceembeddings learned unsupervised from a large corpus. CogMol framework isapplied to three SARS-CoV-2 target proteins: main protease, receptor-bindingdomain of the spike protein, and non-structural protein 9 replicase. Thegenerated candidates are novel at both molecular and chemical scaffold levelswhen compared to the training data. CogMol also includes insilico screening forassessing toxicity of parent molecules and their metabolites with a multi-tasktoxicity classifier, synthetic feasibility with a chemical retrosynthesispredictor, and target structure binding with docking simulations. Dockingreveals favorable binding of generated molecules to the target proteinstructure, where 87-95 % of high affinity molecules showed docking free energy< -6 kcal/mol. When compared to approved drugs, the majority of designedcompounds show low parent molecule and metabolite toxicity and high syntheticfeasibility. In summary, CogMol handles multi-constraint design ofsynthesizable, low-toxic, drug-like molecules with high target specificity andselectivity, and does not need target-dependent fine-tuning of the framework ortarget structure information.

CogMol: Target-Specific and Selective Drug Design for COVID-19 Using Deep Generative Models