WIP: This is magic! I'm walking around a bacteria cell in #AppleVisionPro!!! It's an atomistic cell model (you can see atoms when I get close to something). I just got this prototype working in CellWalk's renderer. #science #biology #scicomm #education #gamedev #apple

new blogpost on the Adaptyv binder design competition blog.booleanbiotech.com/adaptyv-binder…

Just putting some papers on the timeline:) Looking forward to seeing if we are now in the fourth phase (with deep-learning adding even more designs per year). Also nice to put some numbers onto things people have long suspected (like overrepresentation of alpha helices).

figuring out if anyone has done something before is always such a pain...

We’re excited to introduce @ChaiDiscovery and release Chai-1, a foundation model for molecular structure prediction that performs at the state-of-the-art across a variety of drug discovery tasks We're releasing inference code, weights & a web interface: chaidiscovery.com/blog/introduct…

Published today in nature, we describe an approach for single-molecule protein reading on Oxford Nanopore arrays. By utilizing ClpX unfoldase to ratchet proteins through a CsgG nanopore, we achieved single-amino-acid sensitivity. nature.com/articles/s4158…

Introducing PaperQA2, the first AI agent that conducts entire scientific literature reviews on its own. PaperQA2 is also the first agent to beat PhD and Postdoc-level biology researchers on multiple literature research tasks, as measured both by accuracy on objective benchmarks

We used PaperQA2 to extract claims from papers and then see if they're contradicted anywhere in literature. This task is time consuming for humans, but we were able to use this for hundreds of papers to look for trends in disagreement in fields, decades, and journals.

We had a lot to announce, but want to highlight we're building a PaperQA2-version of Wikipedia covering the human proteome. The 240 articles that were graded by experts as better than existing Wikipedia are already viewable - we're generating the rest over the next few weeks!

OpenAI o1 solves a complex logic puzzle.

Great AI meets Bio event in Boston with Michael Koeris george church and Alex Rives 🧬🧬🧬🔥🔥🔥

Have you ever wanted to design protein binders with ease? Today we present 𝑩𝒊𝒏𝒅𝑪𝒓𝒂𝒇𝒕, a user-friendly and open-source pipeline that allows to anyone to create protein binders de novo with high experimental success rates. Bruno Correia Sergey Ovchinnikov biorxiv.org/content/10.110…

Exciting new work from Qian Cong's group on predicting human protein interactome. Leveraging new eukaryotic genomes, new RoseTTAFold2 trained on +/- pairs of PPI and large distilled dataset of domain-domain interactions! 🤩 biorxiv.org/content/10.110…

What does gLM2 learn in non-protein-coding sequences?🧬 Using the Categorical Jacobian and the latest gLM2, we detect incredible regulatory signals in the non-protein coding regions -- all without any supervision!🪄 a quick 🧵

New paper with Bowen :) "Generative Modeling of Molecular Dynamics Trajectories" arxiv.org/abs/2409.17808… A "video diffusion" model but for MD trajectories. Different conditioning solves different tasks. E.g. condition on first and last frame => transition path sampling 1/4

i love this plot

Super excited about ESMC and the quality of the protein representations! Can't wait to see what people build on top of it

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

So excited to be part of this work and programming biology! 🤖🧬🧫

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