SmartCADD: AI-QM Empowered Drug Discovery Platform with Explainability.

Area of Science:

• Pharmaceutical Science
• Computational Chemistry
• Biotechnology

Background:

• Artificial intelligence (AI) adoption in pharma/biotech is growing but faces challenges like model opacity, implementation complexity, and data scarcity.
• These challenges hinder the integration of AI into scientific research and drug discovery workflows.
• Existing tools often lack integration, requiring separate use of diverse computational methods.

Purpose of the Study:

• To introduce SmartCADD, an open-source virtual screening platform designed to overcome AI integration challenges in drug discovery.
• To provide a user-friendly Python framework combining deep learning, CADD, and quantum mechanics.
• To streamline the creation of comprehensive virtual screening workflows.

Main Methods:

• Development of SmartCADD, an integrated platform using Python.
• Incorporation of deep learning, computer-aided drug design (CADD), and quantum mechanics.
• Integration of ADMET property prediction, pharmacophore modeling, molecular docking, and explainable AI.

Main Results:

• SmartCADD successfully integrates diverse computational techniques into a unified workflow.
• The platform demonstrates efficacy in identifying potential lead compounds, as shown in an HIV inhibition case study.
• Explainable AI mechanisms are incorporated to address model opaqueness.

Conclusions:

• SmartCADD democratizes access to advanced AI and quantum mechanics tools for pharmaceutical research.
• The platform enhances efficiency and innovation in drug discovery and development.
• SmartCADD represents a significant advancement in computational drug design.