A new study from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) has developed a machine-learning model that can predict the future co-evolution of genes and regulatory elements within genomes. The model, named EVE, uses a technique called neural fields to create a unified, continuous view of how gene regulation changes over time and across species, effectively learning the ‘language’ of the genome. This approach allows researchers to predict mutations that could disrupt regulatory interactions and potentially lead to disease, offering a powerful tool for interpreting non-coding genetic variants whose roles are often unclear. The research demonstrates EVE’s accuracy by predicting known pathogenic mutations in patients with certain blood disorders and provides a new framework for understanding the complex dynamics of gene regulation. For the full details, read the complete article at https://technologyreview.com/2024/07/10/1094825/ai-model-genome-evolution-regulatory-elements/.