AI decodes plant DNA 'switches' to better predict gene control

An international research team led by Forschungszentrum Jülich and the IPK Leibniz Institute has developed an artificial intelligence model that predicts where regulatory proteins dock onto plant DNA to switch genes on and off. Trained entirely on the rich genomic data available for the model plant Arabidopsis thaliana, the model transfers successfully to crops such as maize—opening new ways to understand how genetic variation shapes crop performance. The study was recently published in Nature Communications.