Alex Rives (@alexrives) 's Twitter Profile
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.

ID: 29474101

calendar_today07-04-2009 15:47:19

322 Tweet

10,10K Followers

892 Following

Josh Wolfe (@wolfejosh) 's Twitter Profile Photo

Today EvolutionaryScale 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!

Elad Gil (@eladgil) 's Twitter Profile Photo

Evolutionary Scale · ESM Cambrian: Revealing the mysteries of proteins with unsupervised learning evolutionaryscale.ai/blog/esm-cambr…

Amy Lu (@amyxlu) 's Twitter Profile Photo

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
🧵
Alex Federation (@afederation) 's Twitter Profile Photo

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 🚀

Kevin K. Yang 楊凱筌 (@kevinkaichuang) 's Twitter Profile Photo

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 Amy Lu's effort leading this project end-to-end!

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 <a href="/amyxlu/">Amy Lu</a>'s effort leading this project end-to-end!
Alex Rives (@alexrives) 's Twitter Profile Photo

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

Science Magazine (@sciencemagazine) 's Twitter Profile Photo

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

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
Science Magazine (@sciencemagazine) 's Twitter Profile Photo

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

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
Patrick Hsu (@pdhsu) 's Twitter Profile Photo

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

David R. Liu (@davidrliu) 's Twitter Profile Photo

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 U.S. FDA for clinical trial use, manufactured as a complex with an LNP, and dosed into a baby with a severe,

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 <a href="/US_FDA/">U.S. FDA</a> for clinical trial use, manufactured as a complex with an LNP, and dosed into a baby with a severe,
Pranam Chatterjee (@pranamanam) 's Twitter Profile Photo

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…

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…