Latent Space interviews Biohub’s Alex Rives about ESMFold2 and the broader ESM protein modeling stack. The discussion centers on datasets versus inductive bias, and whether protein biology is entering its own Bitter Lesson era. The key implication is that large-scale evolutionary sequence data and open models may become foundations for structure prediction, interaction modeling, and programmable biology.
This article, published on the Hugging Face blog, introduces a breakthrough from the OpenMed team: they successfully trained an mRNA language model spanning 25…
The "Virtual Cell" is one of the ultimate goals at the intersection of systems biology and artificial intelligence, aiming to fully simulate the physiological…