EvolutionaryScale

We have been working in science for nearly a decade, and we’ve seen incredible traction. We’ve funded research to fill critical gaps in basic science, created our own scientific research labs and built the world’s largest single-cell dataset. While each of these efforts has driven discoveries on its own, we believe that bringing them together will unlock the promise of AI-powered biology and drive even greater breakthroughs. That’s where Biohub comes in. Mark and I are committing the vast majority of our philanthropic resources to Biohub — our first of its kind initiative combining frontier AI and frontier biology. As part of this next chapter, we’re thrilled to welcome Alex Rives as our Head of Science, and the EvolutionaryScale team to help us lead this new era of AI-powered biology. Their expertise in building advanced AI models for proteins and genomes will help unlock discoveries that once felt out of reach. We’re building something that doesn’t exist anywhere else—AI-powered tools, datasets, and experimental biology working together to: ✨ Simulate virtual cells and a virtual immune system 💡 Generate new biological insights faster than ever 🚀 Accelerate discoveries that design treatments to change lives Almost 10 years ago, Mark and I announced our mission to help scientists cure or prevent all disease within our children’s lifetime. With Biohub, we’re getting there faster than we ever thought possible.

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 effort to combine frontier AI and frontier biology. I feel an incredible sense of optimism in this moment. There is a path to build predictive models of life that can fundamentally accelerate science, and unlock a new understanding of disease. https://lnkd.in/eF62iqC6

We’re thrilled to share that our team is joining Biohub — a community of world-class scientists and engineers building tools to accelerate biomedical discovery. Together, we’ll explore how AI-powered models of biology can help scientists understand and design at the cellular level — from mapping how cells work to predicting how they respond to change. This collaboration represents an exciting step toward harnessing frontier AI and frontier biology to advance human health.

We're sponsoring the use of ESM3 and EMSC to help researchers engineer improved PETase enzymes in the The Align Foundation 2025 Protein Engineering Tournament. Get started using ESMC to predict protein function and ESM3 to generate new enzymes here:  https://lnkd.in/efwED4t4

🌌 To help our understanding of how life evolves at the molecular level, scientists at EvolutionaryScale and the Arc Institute used #AI to create a protein modeled on 500M years of evolutionary change. ➡️ https://nvda.ws/3Q0jHXK ✨

ESM3: An open frontier language model for biology, accompanied by a paper in Science. Evolutionary Scale is a startup company that started out as a research project at FAIR (and some co-founders did their PhD at NYU). Amazing possibilities in protein design opened by ESM3: proteins that fluoresce, that digest plastics,...

ESM3: An open frontier language model for biology, accompanied by a paper in Science. Evolutionary Scale is a startup company that started out as a research project at FAIR (and some co-founders did their PhD at NYU). Amazing possibilities in protein design opened by ESM3: proteins that fluoresce, that digest plastics,...

We're thrilled to present ESM3 in Science Magazine. ESM3 is a generative language model that reasons over the three fundamental properties of proteins: sequence, structure, and function. Today we're making ESM3 available free to researchers worldwide via the public beta of an API for biological intelligence. Trained with over a trillion teraflops of compute, this is the first time a model of this scale has been trained for biology, pushing the frontier of AI for biological discovery and engineering. ESM3 learns to represent the immense complexity of protein biology, learning from billions of natural proteins. From this training it developed the capability to design proteins, responding to complex prompts combining atomic level details and high level instructions to generate new proteins. ESM3 can explore protein space far beyond natural evolution. We prompted ESM3 to generate a fluorescent protein at a far distance from any known fluorescent proteins, searching an unknown region of protein space, to discover a new fluorescent protein. We estimate this is equivalent to simulating five hundred million years of evolution. Read the paper: https://lnkd.in/eWdKRdCt Our blog post: https://lnkd.in/eqFR7BE8 Sign up for Forge, our new API for biological intelligence, now in public beta: https://lnkd.in/eSDkkNqd

🎁 I have an early holiday gift to my protein folding people! I've created a new plugin for PyMOL (called PyMOLfold) that allows you to fold protein sequences right in the GUI. Simply select your model of choice (such as EvolutionaryScale's ESM3 models, etc.) and paste in your amino acid sequence. Then, the folded protein will be loaded directly into your PyMOL session in a few seconds. Get PyMOLfold here: https://lnkd.in/eeTXkjqH (Also, I'm looking for developers/testers to help integrate more models into the tool. So, please fork my open-source code and add in your own functionality.) #proteinfolding #esm3 #pymol #boltz1 #chai1 #ai #genomics #bioinformatics #computationalbiology #aidrugdesign 🐖