Integrative Molecular Scaffold Generation of PI3K/mTOR Inhibitors Using DeepSARM and Ligand-Based Virtual Screening...

Area of Science:

• Medicinal Chemistry
• Computational Chemistry
• Drug Discovery

Background:

• Designing novel core scaffolds is crucial for medicinal chemistry, especially for generating chemical novelty.
• Alternative chemotypes are often required during lead generation.

Purpose of the Study:

• To apply artificial intelligence (AI)-based structure generation to create novel scaffold series.
• To augment medicinal chemistry capabilities using the DeepSARM methodology.
• To identify simplified, novel scaffolds for drug development.

Main Methods:

• Utilized the DeepSARM methodology for AI-based structure generation.
• Employed ligand-based virtual screening to identify candidate compounds.
• Selected and optimized a top-ranked virtual hit for experimental validation.
• Performed chemical synthesis and in vitro evaluation.

Main Results:

• Generated novel scaffold series using DeepSARM.
• Identified several candidate compounds with simplified scaffolds.
• Optimized a virtual hit (compound 6) into a tool compound (6A).
• Synthesized and validated a novel non-tricyclic scaffold.

Conclusions:

• The DeepSARM AI methodology can successfully generate novel molecular scaffolds.
• Simplified scaffolds can be identified and validated for medicinal chemistry applications.
• This AI-driven approach offers a powerful tool for discovering alternative chemotypes and enhancing chemical novelty.