Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 2 de 2
Filter
Add more filters










Database
Language
Publication year range
1.
J Phys Chem B ; 125(44): 12166-12176, 2021 11 11.
Article in English | MEDLINE | ID: mdl-34662142

ABSTRACT

The prerequisite of therapeutic drug design and discovery is to identify novel molecules and developing lead candidates with desired biophysical and biochemical properties. Deep generative models have demonstrated their ability to find such molecules by exploring a huge chemical space efficiently. An effective way to generate new molecules with desired target properties is by constraining the critical fucntional groups or the core scaffolds in the generation process. To this end, we developed a domain aware generative framework called 3D-Scaffold that takes 3D coordinates of the desired scaffold as an input and generates 3D coordinates of novel therapeutic candidates as an output while always preserving the desired scaffolds in generated structures. We demonstrated that our framework generates predominantly valid, unique, novel, and experimentally synthesizable molecules that have drug-like properties similar to the molecules in the training set. Using domain specific data sets, we generate covalent and noncovalent antiviral inhibitors targeting viral proteins. To measure the success of our framework in generating therapeutic candidates, generated structures were subjected to high throughput virtual screening via docking simulations, which shows favorable interaction against SARS-CoV-2 main protease (Mpro) and nonstructural protein endoribonuclease (NSP15) targets. Most importantly, our deep learning model performs well with relatively small 3D structural training data and quickly learns to generalize to new scaffolds, highlighting its potential application to other domains for generating target specific candidates.


Subject(s)
COVID-19 , Deep Learning , Pharmaceutical Preparations , Antiviral Agents/pharmacology , Drug Design , Humans , Molecular Docking Simulation , SARS-CoV-2
2.
PLoS One ; 16(4): e0250019, 2021.
Article in English | MEDLINE | ID: mdl-33886614

ABSTRACT

SARS-CoV-2 has caused a global pandemic, and has taken over 1.7 million lives as of mid-December, 2020. Although great progress has been made in the development of effective countermeasures, with several pharmaceutical companies approved or poised to deliver vaccines to market, there is still an unmet need of essential antiviral drugs with therapeutic impact for the treatment of moderate-to-severe COVID-19. Towards this goal, a high-throughput assay was used to screen SARS-CoV-2 nsp15 uracil-dependent endonuclease (endoU) function against 13 thousand compounds from drug and lead repurposing compound libraries. While over 80% of initial hit compounds were pan-assay inhibitory compounds, three hits were confirmed as nsp15 endoU inhibitors in the 1-20 µM range in vitro. Furthermore, Exebryl-1, a ß-amyloid anti-aggregation molecule for Alzheimer's therapy, was shown to have antiviral activity between 10 to 66 µM, in Vero 76, Caco-2, and Calu-3 cells. Although the inhibitory concentrations determined for Exebryl-1 exceed those recommended for therapeutic intervention, our findings show great promise for further optimization of Exebryl-1 as an nsp15 endoU inhibitor and as a SARS-CoV-2 antiviral.


Subject(s)
Antiviral Agents/pharmacology , COVID-19 Drug Treatment , Drug Repositioning , Endoribonucleases/antagonists & inhibitors , SARS-CoV-2/drug effects , Small Molecule Libraries/pharmacology , Viral Nonstructural Proteins/antagonists & inhibitors , Animals , Antiviral Agents/chemistry , COVID-19/virology , Caco-2 Cells , Chlorocebus aethiops , Drug Repositioning/methods , Endoribonucleases/metabolism , High-Throughput Screening Assays/methods , Humans , Molecular Docking Simulation , SARS-CoV-2/metabolism , Small Molecule Libraries/chemistry , Vero Cells , Viral Nonstructural Proteins/metabolism
SELECTION OF CITATIONS
SEARCH DETAIL
...