Today CZI is announcing an unprecedented new scientific initiative to build the future of AI-powered biology. I am joining CZI to lead this initiative as Head of Science, and the EvolutionaryScale team is joining forces with Biohub. This is the first large scale scientific

This is incredibly exciting news for the BioAI community! @czi is making an amazing impact in advancing virtual biology, and this new initiative will massively boost BioAI. Congratulations to Alex Rives and the rest of the Biohub team! Onward to making the world a better place!

I am beyond excited that @EvoscaleAI will be joining @Biohub! This brings together our strengths in AI research with frontier bio capabilities.

Congrats to EvolutionaryScale! I remember being so impressed by what this team was building at our @bitsinbio panel last year with @ebetica and Roshan Rao. Can’t wait to see what they do next with @czi !

Our amazing team at @EvoscaleAI are joining forces with CZI to train some big models at @ChanZuckerberg ! I'm really excited to be on this journey. I'm extra excited to open source some models again for the scientific community. We're cooking some good stuff :)

About 2.5 years ago we started EvolutionaryScale as an AI research company for biology. We got one of the first 1,000+ H100 GPU clusters in the world, built a world class team, and trained frontier AI models - shipped ESM3 and ESM Cambrian for proteins, and way beyond that we’ve

Excited to be joining forces with the Biohubs to train some of the largest models at the intersection of AI and biology. We have several new models in the works — and I’m especially thrilled to be open sourcing them for the scientific community!

😮

Looking forward to working with you and CZI!

I’m very excited for Alex and his team. This is a big boon for science.

Congrats to @alexrives @salcandido @TomSercu and the @EvoscaleAI team, and to CZI/Biohub for their new effort in AI x biology Proud to have worked with EvolutionaryScale from the beginning, co-leading the first two funding rounds and collaborating on their ESM3 breakthrough

Designing DNA-binding proteins shouldn’t require structures. ❌🧬 With DPAC, we align protein and DNA language models via contrastive learning -- then use simulated annealing to design new binders straight from sequence! 🔀 📜: https://t.co/H0M4qgUlgK 💻: https://t.co/Gtf395bRPy

In a medical milestone, a customized base editor was developed, characterized in human and mouse cells, tested in mice, studied for safety in non-human primates, cleared by @US_FDA for clinical trial use, manufactured as a complex with an LNP, and dosed into a baby with a severe,

Genomes encode biological complexity, which is determined by combinations of DNA mutations across millions of bases In new @arcinstitute work, we report the discovery and engineering of the first programmable DNA recombinases capable of megabase-scale human genome rearrangement

Researchers have developed a deep learning protein language model, ESM3, that enables programmable protein design. Learn more in this week's issue of Science: https://t.co/PndjVQWjT5

An #AI model created to design proteins simulates 500 million years of protein evolution in developing a previously unknown bright fluorescent protein. Learn more in a new Science study: https://t.co/klcE9wFRco

Whoa! When a large language of life model generates a protein equivalent to ~500 million years of evolution. @ScienceMagazine https://t.co/p6GWxC15Zm @THayes427 @proteinrosh @EvoscaleAI @arcinstitute @UCBerkeley

ESM3 generating a fluorescent protein!

We’re also announcing an ESM3 compute grant pilot program for applications at the scientific frontier. ESM3 can enable creative applications of protein engineering from drug design, to green chemistry, and materials science. Please apply on Forge if your research could benefit

ESM3 generating a fluorescent protein!