Evo2-NIM

As described on AWS Marketplace.

Evo2 potential applications spans from accelerating drug discovery to advancing synthetic biology.

Evo 2 model was trained by Arc Institute. The model training involved a vast dataset of genomes, which enabled Evo 2 to perform a wide range of tasks, from predicting the impact of mutations on protein performance to generating complex molecular systems like CRISPR-Cas complexes. For example, the model demonstrated that it was able to design new versions of the CRISPR genome editor showcased its potential for creating novel biological tools.

Highlighted by the publisher on AWS Marketplace.

Evo2 is a biological foundation model that can integrate information across long genomic sequences while retaining sensitivity to single-nucleotide changes.

Evo2 can perform zero-shot function prediction for genes. Evo also can perform multi-element generation tasks, such as generating synthetic CRISPR-Cas molecular complexes.

Evo 2 can also predict gene essentiality at nucleotide resolution and can generate coding-rich sequences up to at least 1M kb in length. Advances in multi-modal and multi-scale learning with Evo provide a promising path toward improving our understanding and control of biology across multiple levels of complexity.