The ESM3 model can reason across three fundamental biological properties of proteins: sequence, structure and function. This allows scientists to generate new proteins with a high degree of control. The smallest model has been open-sourced, while the medium and large versions are available for commercial use. The company hopes the technology will be used to solve major global problems and benefit human health and society, with potential applications in pharmaceutical companies for the development of novel medicines.
Key takeaways:
- EvolutionaryScale, an AI research lab, has launched ESM3, a generative language model that can design novel proteins. The model was able to generate a novel green fluorescent protein (esmGFP), which would have taken hundreds of millions of years to evolve naturally.
- The startup has raised $142 million in a seed round of funding, led by Nat Friedman, Daniel Gross and Lux Capital. AWS and Nvidia’s venture capital arm also participated in the round.
- ESM3 can jointly reason across three fundamental biological properties of proteins: sequence, structure and function. It can generate new proteins with an unprecedented degree of control.
- ESM3 is available in three sizes, small, medium and large. The smallest one, with 1.4B parameters, has been open-sourced with weights and code on GitHub under a non-commercial license. The medium and large versions are available for commercial use.