All articles tagged with #genome design
Researchers used AI to design complete bacteriophage genomes, selecting 302 designs and confirming 16 that kill E. coli in the lab; this marks the first time a complete viral genome was designed by AI and could accelerate phage therapy and drug development, but raises urgent biosafety and biosecurity concerns that require safeguards.
Evo 2 is a large, open biological foundation model trained on 9 trillion base pairs across all life, with a 1‑million‑token context, available in 7B and 40B sizes. It predicts mutational effects on DNA, RNA and proteins without task-specific fine-tuning, can generate genome-scale sequences and chromatin-accessibility designs, and supports exon–intron annotation and variant-effect prediction across diverse species. The model and data (OpenGenome2) are fully open-source, with training/inference code and tools (Evo Designer, Evo Mech Interp), plus safety safeguards such as virus-data exclusions to mitigate misuse.
AI models like Evo2 can design DNA, RNA, and protein sequences and have produced M. genitalium–inspired genomes, mitochondria genomes, and a yeast chromosome, but researchers caution that writing fully functional genomes for living cells—and validating them at scale—still requires major advances before synthetic life becomes a reality.