The application of AI-driven Drug Discovery technology for molecular optimization of nuclear receptor ligands

Authors: Bachorz RA
Conference: Ninth Joint Sheffield Conference on Chemoinformatics
Software: ADMET Predictor®
Division: Simulations Plus


Nuclear receptors (NRs) are a superfamily of transcription factors whose activity is regulated upon the binding of a specific ligand. In this work, we utilized the new AI-driven Drug Design (AIDD) module within the ADMET Predictor® suite to derive novel and promising RORyT agonists with suitable predicted ADMET and PK properties. The AIDD module uses chemically intelligent SMIRKS transformations to generate new molecules based on seed compounds. The generation process is channeled towards molecules of desired properties within a multicriteria optimization loop. The objectives, including potency and selectivity at the chosen target, synthetic feasibility, and ADMET/pharmacokinetic (PK) properties are considered simultaneously. Thus, the properties of optimized molecules are on a Pareto front and are excellent candidates for experimental verification.

By Rafał A. Bachorz

Ninth Joint Sheffield Conference on Chemoinformatics, – University of Sheffield, UK