SC Connecticut News

Researchers from Yale School of Medicine, the Jackson Laboratory, and the Broad Institute have developed a new AI method to design regulatory DNA elements. These elements, known as cis-regulatory elements (CREs), control how genes are expressed in cells. The AI platform, called Computational Optimization of DNA Activity (CODA), creates synthetic DNA that can switch on genes only in specific cell types.

Steven Reilly, PhD, assistant professor of genetics at YSM and one of the study's senior authors, stated: “This project essentially asks the question: ‘Can we learn to read and write the code of these regulatory elements?’”

The researchers published their findings in Nature on October 23. They hope this development will enhance gene therapy by targeting specific diseased cells without affecting healthy ones. This approach aims to address issues seen in early experimental gene therapies that failed due to off-target effects.

Pardis Sabeti, MD, DPhil, co-senior author and core institute member at the Broad Institute and Harvard professor, commented on the potential of these technologies: "By applying machine learning and molecular biology to the logic of when and where CREs work...we can leverage that knowledge using generative AI."

Ryan Tewhey, PhD from the Jackson Laboratory noted: “Combining computational models with large-scale experimental approaches is a powerful strategy.” The scientists used data from over 775,000 regulatory elements across different cell types for training CODA.

Rodrigo Castro, PhD from Jackson Laboratory observed: “We were impressed by how effectively CODA-designed sequences achieved cell-type specificity.”

Sager Gosai, PhD from Sabeti's lab at Broad Institute remarked on natural CREs' limitations compared to this new method: "Natural CREs...represent a tiny fraction of possible genetic elements."

The research was funded by Howard Hughes Medical Institute and several US National Institutes of Health grants.