A study published in Science details the generative design of bacteriophages using genome language models. This research represents an important milestone for synthetic genomics, as it shows AI generating entire functional genomes that work in a laboratory setting.
Professor Patrick Cai, Chair of Synthetic Genomics at the University of Manchester, stated that this suggests genome language models are beginning to learn design principles encoded by evolution, opening the door to AI-assisted genome writing. The next challenge is to scale these approaches to larger and more complex genomes, ensuring rigorous experimental validation.
Jordi García Ojalvo, Professor of Systems Biology at Pompeu Fabra University of Barcelona, highlighted that the breakthrough demonstrates a complete functional genome can be designed from scratch using generative AI. However, the process currently has low efficiency, with only 16 viable phages obtained from thousands of generated genomes.
Marc Güell, coordinator of the Translational Synthetic Biology research group at Pompeu Fabra University, described the study as a significant turning point, allowing biology to be designed on a computer for the first time. This moves away from relying exclusively on bioprospecting, with potential applications for tackling major challenges, including antibiotic therapies.
Dr Simon Jackson, Phage Therapy Research Group lead at Waikato University, noted that the work is an impressive proof of principle, combining AI-based genome design software with laboratory hardware. He added that the potential implications for phage therapy are exciting, as suitable phages can be difficult to find in nature.