AIoptamer: Artificial Intelligence-Driven Aptamer Optimization Pipeline for Targeted Therapeutics in Healthcare

Area of Science:

• Biochemistry
• Computational Biology
• Drug Discovery

Background:

• Aptamers are crucial for drug discovery, diagnostics, and biosensing due to their high specificity and affinity.
• Traditional aptamer selection methods like SELEX are laborious, time-consuming, and resource-intensive.

Purpose of the Study:

• To develop a novel, AI-driven pipeline (AIoptamer) for accelerated aptamer discovery and optimization.
• To integrate artificial intelligence with computational methods to overcome limitations of conventional aptamer selection.

Main Methods:

• AIoptamer generates aptamer variants from known complexes and screens them using AI models for binding affinity.
• Top candidates undergo structural modeling (CHIMERA_NA) and binding affinity prediction (PredPRBA, PDA-Pred).
• Refinement via molecular dynamics (MD) simulations assesses structural stability and interaction strength.

Main Results:

• The AIoptamer pipeline demonstrates effectiveness for both RNA and DNA aptamer optimization.
• The method significantly reduces reliance on experimental trial-and-error approaches.
• The pipeline offers a generalized and robust framework for rational aptamer design.

Conclusions:

• AIoptamer provides a faster, scalable, and more efficient approach to aptamer optimization.
• This AI-driven strategy advances rational aptamer design for various applications.
• The integrated computational approach enhances the discovery and development of aptamer-based technologies.