Generative AI Designs Complete, Viable Bacteriophage Genomes
bravo_abad · x · 2026-08-07
Researchers have successfully used genome language models Evo 1 and Evo 2 to generate complete bacteriophage genomes designed to infect specific bacterial hosts.
- Model Training: The models were pretrained on millions of genomes and fine-tuned on 15,000 Microviridae sequences.
- Generation Pipeline: Generation alone was not enough. The useful system combined a foundation model with task-specific fine-tuning, prompt design, predictive computational filters, and experimental validation.
- Results: From nearly 300 synthesized AI-designed genomes, 16 produced viable phages. This demonstrates the huge potential of generative AI at the macro-genome level.
More from Research
- Simplex Diffusion Models paper talk by EPFL/DeepMind's Justin Deschenaux on Oct 19 — ArnaudDoucet1 · 2026-10-16
- Meituan LongCat team's Data World synthesizes data environments to train data agents — meituan-longcat · 2026-10-16
- FDE-Gym benchmark shows huge gap on real AI delivery tasks: top model scores 0.563 — DeepLethe · 2026-10-16
- ForcingBooster halves computation of autoregressive video diffusion with patch-wise denoising — VAST-AI · 2026-10-16
- Baidu open-sources FlashMask: up to 1.55x faster than FlashAttention-4 for long-context training — BaiduResearch · 2026-10-16
- SemEval-2027 Task 9 opens: multimodal news framing analysis across 4 languages — preslav_nakov · 2026-10-16