Researchers have launched Evo 2, an advanced open-source genomic model capable of analyzing complex biological data across all three domains of life: bacteria, archaea, and eukaryotes.
Trained on trillions of DNA bases, Evo 2 is designed to process large-scale genomes, including human DNA. The model excels at identifying critical biological elements, such as protein-coding regions and the specific mutations that impact them.
Key Highlights:
- Scale: Trained on a massive dataset covering the entire tree of life.
- Capabilities: Identifies protein-coding sequences and functional mutations.
- Accessibility: The project is fully open-source and available on GitHub.
- Source: Developed by the Arc Institute (repository:
ArcInstitute/evo2).
This breakthrough provides scientists with a powerful tool to predict how genetic variations influence biological functions, accelerating research in genetics and drug discovery.
