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
- RL Training Collapses at Step 8: Dev Implements LoRA to Fix GPU Sync — mervenoyann · 2026-08-07
- Noether: Open-Source Tool to Automatically Prove Math Properties of JAX Code in Lean — jonkhler · 2026-08-07
- Decoding Perceived Speech from MEG Using CLIP-style Architecture — Ilia Semenkov · 2026-08-07
- MiroFish: A Universal Swarm Intelligence Engine for Predicting Anything — 666ghj · 2026-08-07
- Breaking Centralized AI Limits: Swarm Intelligence in Multi-Agent Systems — _N-iX_ · 2026-08-07
- Research: DPO and RL Training Cause Negative Parallelism in Models — sethlazar · 2026-08-07