Alex Rives
@alexrives
AI for scientific discovery. Broad and MIT. Chief scientist at @EvoscaleAI and founder and scientific director of the ESM project previously @Meta.
We're thrilled to present ESM3 in @ScienceMagazine. 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…
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: scim.ag/4jhJ9Wa
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! 🔀 📜: biorxiv.org/content/10.110… 💻: github.com/programmablebi……
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
What if we could universally recombine, insert, delete, or invert any two pieces of DNA? In back-to-back @Nature papers, we report the discovery of bridge RNAs and 3 atomic structures of the first natural RNA-guided recombinase - a new mechanism for programmable genome design
Researchers have developed a deep learning protein language model, ESM3, that enables programmable protein design. Learn more in this week's issue of Science: scim.ag/4b5IlQu
Whoa! When a large language of life model generates a protein equivalent to ~500 million years of evolution. @ScienceMagazine science.org/doi/10.1126/sc… @THayes427 @proteinrosh @EvoscaleAI @arcinstitute @UCBerkeley
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…
We're thrilled to present ESM3 in @ScienceMagazine. 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…
Sign up for Forge, our new API for biological intelligence, now in public beta: forge.evolutionaryscale.ai
We trained a model to co-generate protein sequence and structure by working in the ESMFold latent space, which encodes both. PLAID only requires sequences for training but generates all-atom structures! Really proud of @amyxlu's effort leading this project end-to-end!
1/🧬 Excited to share PLAID, our new approach for co-generating sequence and all-atom protein structures by sampling from the latent space of ESMFold. This requires only sequences during training, which unlocks more data and annotations: bit.ly/plaid-proteins 🧵
1/🧬 Excited to share PLAID, our new approach for co-generating sequence and all-atom protein structures by sampling from the latent space of ESMFold. This requires only sequences during training, which unlocks more data and annotations: bit.ly/plaid-proteins 🧵
This is what we've been waiting for. The best drug targets out there don't have structure, and won't anytime soon. The key to unlocking these targets will be understanding protein function directly from sequence. Next step, designing molecules directly from sequence 🚀
Introducing ESM Cambrian. Unsupervised learning can invert biology at scale to reveal the hidden structure of the natural world. We’ve scaled up compute and data to train a new generation of protein language models. ESM C defines a new state of the art for protein…
Evolutionary Scale · ESM Cambrian: Revealing the mysteries of proteins with unsupervised learning evolutionaryscale.ai/blog/esm-cambr…
Thank you for making ESM C (truly) open source!
Introducing ESM Cambrian. Unsupervised learning can invert biology at scale to reveal the hidden structure of the natural world. We’ve scaled up compute and data to train a new generation of protein language models. ESM C defines a new state of the art for protein…
New and improved OSS tools for practitioners using protein language models!
Introducing ESM Cambrian. Unsupervised learning can invert biology at scale to reveal the hidden structure of the natural world. We’ve scaled up compute and data to train a new generation of protein language models. ESM C defines a new state of the art for protein…
Today @EvoscaleAI scaled up compute + data + trained next gen of protein language models ESM C 300M + 600M w/open weights ESM C 6B on EvolutionaryScale Forge (academic) + AWS Sagemaker (commercial) Unsupervised learning inverts bio at scale + reveals secrets of natural world!
Introducing ESM Cambrian. Unsupervised learning can invert biology at scale to reveal the hidden structure of the natural world. We’ve scaled up compute and data to train a new generation of protein language models. ESM C defines a new state of the art for protein…