Beyond SELEX: AI-driven aptamers from sequence to structure to function.

Abstract

Conventional aptamer discovery by systematic evolution of ligands by exponential enrichment (SELEX) is often constrained by limited library capacity, PCR bias, and multi-round screening. The recent convergence of artificial intelligence with aptamer development is driving a paradigm shift from empirical screening toward rational, data-driven design. This Review presents a timely and comprehensive overview of AI integration across the entire aptamer development pipeline, with a particular emphasis on advances reported in 2024-2026. We begin by discussing bioinformatics databases and computational tools for high-throughput SELEX data analysis. We then review state-of-the-art strategies for secondary and tertiary structure prediction, including recent breakthroughs such as AlphaFold 3, RoseTTAFoldNA, and diffusion-based approaches. We also cover machine learning methods for aptamer-target interaction prediction, molecular docking, dynamics simulations, and free energy calculations. A major focus is placed on very recent AI-driven generative design, including diffusion models (AptaDiff), language model-based frameworks (InstructNA, GRAPE-LM), and reinforcement learning approaches (AiDTA) for de novo aptamer generation and optimization. Emerging applications of AI-designed aptamers in precision diagnostics, targeted therapy, and biosensing are also surveyed. Finally, we discuss current challenges and outline future directions toward closed-loop, interpretable AI frameworks for translational aptamer development. By synthesizing the latest computational and experimental advances, this Review aims to serve as a timely resource for researchers seeking to leverage AI for next-generation aptamer discovery.