In this work we investigated the Pks13-TE domain, which plays a critical role in the viability of the mycobacteria. In this report, we have used a series of AI and Physics-based tools to identify Pks13-TE inhibitors. The Reinvent 4, pKCSM, KDeep, and SwissADME are AI-ML-based tools. AutoDock Vina, PLANTS, MDS, and MM-GBSA are physics-based methods. A combination of these methods yields powerful support in the drug discovery cycle. Known inhibitors of Pks13-TE were collected, curated, and used as input for the AI-based tools, and Mol2Mol molecular optimisation methods generated novel inhibitors. These ligands were filtered based on physics-based methods like molecular docking and molecular dynamics using multiple tools for consensus generation. Rigorous analysis was performed on the selected compounds to reduce the chemical space while retaining the most promising compounds. The molecule interactions, stability of the protein-ligand complexes and the comparable binding energies with the native ligand were essential factors for narrowing the ligands set. The filtered ligands from docking, MDS, and binding energy colocations were further tested for their ADMET properties since they are among the essential criteria for this series of molecules. It was found that ligands Mt1 to Mt6 have excellent predicted pharmacokinetic, pharmacodynamic and toxicity profiles and good synthesisability.
Keywords: Deep neural network; FEL; Generative AI; Graph learning; Physics-based methods; Pks13; Reinforcement learning; Reinvent 4; antiTb drug discovery.
Copyright © 2024 Elsevier Ltd. All rights reserved.