Computer-aided drug discovery: historical foundations, practical AI tools, and emerging ethical considerations

Area of Science:

• Pharmacology and Medicinal Chemistry
• Computational Biology
• Artificial Intelligence in Drug Discovery

Background:

• Computer-aided drug discovery (CADD) has evolved over four decades, significantly contributing to approved therapeutics.
• Recent advancements in Artificial Intelligence (AI) and Machine Learning (ML) offer enhanced predictive capabilities and workflow integration.
• CADD is now an integral part of drug discovery, from hit identification to candidate refinement in academia and industry.

Purpose of the Study:

• To provide a historical overview of CADD and its impact on drug discovery.
• To highlight contemporary, non-specialist-friendly AI and ML tools for drug discovery.
• To offer medicinal chemists practical resources for open-source computational workflows.

Main Methods:

• Review of historical CADD methodologies and approved drugs/candidates.
• Curated selection and analysis of contemporary AI/ML tools.
• Compilation and analysis of cloud-based virtual screening platforms and ADMET prediction tools.

Main Results:

• Identification of numerous approved drugs and clinical candidates developed using computational methods.
• A curated list of accessible AI/ML tools for drug discovery practitioners.
• A consolidated guide to open-source virtual screening and ADMET prediction workflows.

Conclusions:

• AI and ML tools are increasingly vital for efficient drug discovery.
• Accessible computational resources empower medicinal chemists.
• Responsible adoption of AI in drug discovery requires addressing ethical considerations like data bias and environmental impact.