Biohub, a Mark Zuckerberg- and Priscilla Chan-funded institute, releases “a world model of protein biology” to researchers for prediction, design, and discovery
Biohub, the Mark Zuckerberg and Priscilla Chan-funded institute, on Wednesday released what it says amounts to “a world model of protein biology.”
Axios Ina Fried
Related Coverage
- Zuckerberg's philanthropic venture unveils AI world model for drug discovery Reuters · Jaspreet Singh
- Biohub releases a world model of protein biology Biohub
- Mark Zuckerberg's philanthropic venture unveils AI world model for drug discovery Reuters
- Biohub unveils AI world model for drug discovery, enhancing protein design Crypto Briefing
- 🔬ESMFold2: The Bitter Lesson is Coming for Proteins - Alex Rives, BioHub Latent.Space · RJ Honicky
- Today Biohub is sharing a major scientific advance: our first world model for protein biology. This system can help scientists discover and design proteins that will hopefully lead to new medical therapies. @zuck · Mark Zuckerberg
- This release consists of two AI models and an atlas: ESMC, our state-of-the-art language model that represents proteins; ESMFold2, designed to transform ESMC's sequence representations into atomically resolved 3D structures; and ESM Atlas, a dataset and tool that makes these representations navigable across 6.8 billion protein sequences. … @zuck · Mark Zuckerberg
- Move over, AlphaFold: open source model predicts shape of 1 billion proteins Nature
Discussion
-
@alexrives
Alex Rives
on x
We designed miniproteins and antibodies for five targets that are important in cancer and immunology. We found binders with nanomolar affinities for all, and sometimes picomolar affinities, testing just 84 designs per target and modality. Scaling compute at inference time [image]
-
@alexrives
Alex Rives
on x
ESMFold2 is blazing fast and has state of the art accuracy across benchmarks for structure prediction, especially for the challenging problem of predicting protein interactions, including the interaction of antibodies with their targets. [image]
-
@alexrives
Alex Rives
on x
Today we're announcing ESMFold2, an open scientific engine to power prediction, design, and discovery across protein biology. The new model delivers state of the art performance on protein interactions, especially antibodies, a critical modality for therapeutics. We have [image]
-
@shanaokelley
Shana Kelley
on x
A powerful example of how open science and AI can expand what's possible in biology. @Biohub is uniquely positioned to bring together interdisciplinary science, engineering, and computation at the scale needed to drive breakthroughs like this.
-
Priscilla Chan
Priscilla Chan
on linkedin
Medicine works best when it can address the specific biology driving disease in an individual patient. …