Focused On-demand Library for Probable ATP-dependent RNA helicase DHX34

From a virtual chemical space containing more than 60 billion molecules, we precisely choose certain compounds. Our collaborator, Reaxense, aids in their synthesis and provision.

The library includes a list of the most promising modulators annotated with 38 ADME-Tox and 32 physicochemical and drug-likeness parameters. Also, each compound is presented with its optimal docking poses, affinity scores, and activity scores, providing a comprehensive overview.

We use our state-of-the-art dedicated workflow for designing focused libraries for enzymes.

This approach involves comprehensive molecular simulations of the catalytic and allosteric binding pockets and ensemble virtual screening that accounts for their conformational flexibility. In the case of designing modulators, the structural adjustments caused by reaction intermediates are considered to improve activity and selectivity.

Our library stands out due to several important features:

• The Receptor.AI platform compiles comprehensive data on the target protein, encompassing previous experiments, literature, known ligands, structural details, and more, leading to a higher chance of selecting the most relevant compounds.
• Advanced molecular simulations on the platform help pinpoint potential binding sites, making the compounds in our focused library ideal for finding allosteric inhibitors and targeting cryptic pockets.
• Receptor.AI boasts over 50 tailor-made AI models, rigorously tested and proven in various drug discovery projects and research initiatives. They are crafted for efficacy, dependability, and precision, all of which are key in creating our focused libraries.
• Beyond creating focused libraries, Receptor.AI offers comprehensive services and complete solutions throughout the preclinical drug discovery phase. Our success-based pricing model minimises risk and maximises the mutual benefits of the project's success.