Biological AI Foundation Models are Here

Welcome Renaissance Creator,

Today, we move beyond the world of bits and into the world of atoms.

While most of our discussion here, and in the AI space in general, has been focused on new foundation models that aid us in the creation of software or software based applications, it turns out those same tools can cross over into seemingly any domain. Including our own biology.

Enter Evo, a long-context biological foundation model that generalizes across the fundamental languages of biology: DNA, RNA, and proteins.

Strap in, this is a crazy one.

The One Big Thing

What is the one big thing?

Together AI, in collaboration with the Arc Institute, has unveiled Evo, a foundational model that could very well redefine our understanding and manipulation of life's most elemental codes.

It's a foundation model that deciphers the complex languages of DNA, RNA, and proteins, capable of predictions and designs across molecular to genome scales, handling over 650k tokens. The StripedHyena architecture, upon which Evo is built, emerges as a notable departure from the widely adopted Transformer models, heralding efficiency and precision in processing biological data. This isn't just an incremental improvement; it's a recalibration of what's possible in the domain of computational biology.

One of the most compelling aspects of Evo is its dual capabilities in prediction and generative design. The model's utility in predicting gene essentiality—a task traditionally mired in laborious experimental protocols—heralds a new era where computational models can forecast the viability of genes with unprecedented speed and accuracy. Moreover, Evo’s foray into the generative design of CRISPR systems underscores its potential to revolutionize genetic engineering.

The potential applications of Evo span from drug discovery and agriculture to sustainability and beyond. The model represents not just a step but a giant leap towards a future where understanding and engineering life at the genetic level could become as commonplace as editing a document on a computer.

This is a beginning of a new world where the synergy between AI and biology can lead to unprecedented discoveries and innovations. Evo’s open-source nature means that it's not just the creation of Together AI and the Arc Institute; it's a canvas for the global community to contribute to, improve, and redefine what's possible in the life sciences.

Inspiration / Gallery / Artisan Board

Playground 2.5 outputs look cool

Magnific outputs and tutorial:

More Sora demoes…these keep getting crazier

Tools

Must have tools for every Renaissance creator to add to their toolkit:

Deep Tech

The newest and coolest in the research world that you need to know about:

Closing Thought

Work With Us!

The AI Renaissance is coming and we are building the best community of the people making it happen.

Contact us to sponsor your product or brand and reach the exact audience for your needs across our newsletter and podcast network.