A joint research team has developed OpenABE, an AI-designed adenine base editor intended to advance the field of gene therapy [1].

This development matters because it leverages artificial intelligence to refine the precision of base editors, which can potentially correct genetic mutations more effectively than previous methods. By optimizing how these tools target and modify DNA, the researchers aim to reduce errors and increase the viability of therapeutic interventions.

The project was led by Daesik Kim, a professor in the Department of Medicine at Sungkyunkwan University [1]. Kim worked alongside Yong-Sub Kim and Jae-Hyun Park to create the Open Adenine Base Editor, or OpenABE [1]. The team represents a collaboration between Sungkyunkwan University, the University of Ulsan College of Medicine, and the Sungkyunkwan University School of Medicine [1].

Base editors are a specialized evolution of CRISPR technology. Instead of cutting through both strands of the DNA double helix, base editors chemically convert one nucleotide into another, a process that allows for the correction of point mutations without causing double-strand breaks.

The researchers introduced OpenABE in July 2026 [1]. The team said they used AI to design the editor to ensure higher efficiency and accuracy in targeting specific adenine bases within the genome [1]. This approach allows the system to be more adaptable to different genetic sequences than traditional, non-AI-designed editors.

By utilizing machine learning to predict the most effective protein structures for editing, the team said they have paved the way for next-generation gene therapy [1]. The research focuses on creating tools that are not only more powerful but also safer for potential human application by minimizing off-target effects.

Open Adenine Base Editor (OpenABE)

The integration of AI into base editing represents a shift from trial-and-error laboratory discovery to predictive engineering. By using OpenABE to target adenine bases with higher precision, scientists can move closer to treating hereditary diseases caused by single-letter mutations while reducing the risk of unintended genomic damage.