BioEmu now published in @ScienceMagazine !! What is BioEmu? Check out this video: piped.video/LStKhWcL0VE?si=tQQX…

RT @ralphruthe: 🦜 !B

Today we announced the Claude-led discovery of a molecular machine that we suspect could represent a new gene editing mechanism. Its precise function, biotechnological utility (if any), or level of significance is not yet clear, but at minimum it is work I would have been proud to do as a PhD student. The work was done mostly, though not entirely, by Claude: our life sciences team suggested a broad area of research, Claude read through the literature and a bunch of genome data and discovered something interesting, then Claude proposed experiments to verify the discovery and our team carried them out. It’s easy to dismiss this as a one-off or curiosity, but we’ve repeatedly seen a pattern where AI performance in new intellectual domains goes from weak to superhuman in a matter of a few years. In 2023 models struggled to do math at the level of an average high-school student. In 2024 they started to do well on math competitions for the best high-schoolers in the country, in 2025 they started to solve minor open problems, in early 2026 more significant open problems, and in late 2026 they are beginning to solve the top few open problems in all of mathematics. We believe AI for biology is on a similar exponential trend. The main difference between biology and mathematics, of course, is that math can be done purely theoretically, while biology requires experimentation. Some have used this to draw the conclusion that AI’s utility in biology will be limited. We think this is wrong. As we’ve demonstrated today, humans can collaborate with AI to perform the experiments, validate key results in a few weeks and, if necessary, work with the AI to iterate on what they find. Eventually it may even be possible for Claude itself to safely perform the experiments by autonomously controlling lab equipment, with appropriate safeguards in place, but we aren’t doing that today (our lab is also a BSL1/BSL2 facility that doesn't handle materials dangerous to humans). More broadly, biomedical advancement has many stages — from fundamental biology discoveries, to translational research, to drug discovery, clinical trials, and finally the actual delivery of medicines and health care to patients. We are also interested in these later stages, but even simply accelerating the first stage of fundamental biological discoveries has the potential to speed up and broaden the entire pipeline. Improving our understanding of biology and sharpening biologists’ tools can drive forward all of the later stages, for example by identifying new drug targets, finding new therapeutic modalities, allowing for more precise measurement, and speeding up the experimental loop which itself further accelerates our understanding of biology. This will not in itself speed up clinical trial times, but if it succeeds it could greatly increase the number of promising candidates that go into the pipeline — an increase in throughput even though latency remains. In Machines of Loving Grace, I wrote about AI’s potential to “cure most diseases in 5-10 years” — a goal that sounds impossible, but one I believe is just barely possible if AI is applied to every stage of the pipeline. The first step is showing that AI can first help with, and then drive, biological discoveries. Claude’s discovery is the latest in a line of related prior work that goes back decades, beginning with systems like CRISPR, and continuing with discoveries like the bridge recombinase and VIPR in the past few years. Recently, there has been heightened interest in systems based on reverse transcriptase (RT) enzymes, the enzyme underlying the system Claude identified. And most recently, a Stanford team working independently described a novel RT system with an associated non-coding array that is in some ways similar to the one Claude found, though they are distinct systems that evolved independently from each other. I believe that we’re at the very beginning of finding such systems and developing them into powerful tools for biotechnology. I’m proud of the resources Anthropic has invested in accelerating the public benefits of AI through the life sciences, and we’re aiming both to grow our life sciences team and to work with other scientists to extend this approach to a broad range of problems. If you have a proposal for a research collaboration or are interested in joining our life sciences team, please reach out.

RT @ralphruthe: Über den muss man kurz nachdenken. !B

🤣🤣🤣🤣🤣🤣🤣🤣🤣🤣🤣🤣

Synthesis is a major bottleneck in drug discovery. AI synthesis planning can help propose better routes and make generative molecular design tractable. With our retroChimera model we have been pushing the boundaries of these models further - out in @Nature today. 1/2

Excited to see this out: An ab initio foundation model of wavefunctions that accurately describes chemical bond breaking. Based on deep Quantum Monte Carlo. @MSFTResearch @AdamEFoster @SherryLixueC @PBerntSzab1 @jonkhler @n_gao96 Zeno S, Jan H. nature.com/articles/s41467-0…

First (x,y,t) Pymgy of the year! With @CecClementi in Amed, Bali!

First leaf sheep movie of the year. In Bali with @CecClementi

Klassiker 😅

We use 1B tokens/day at Acellera, including input and cached tokens, so I’m curious how far local models can go. I tested 7 LLM + harness combinations on an IL-23 discovery task. A few surprises, including what one RTX 5090 could produce. Blog and docs: acellera.com/blog/beyond-one…

When we design molecule we often want to target properties which are averages for the Boltzmann ensemble, rather than a single configuration or graph. Yet, current property-guided 3D generative models condition on single conformers. We target this with Boltzmann-Expected Design

Arrived in Bali with @CecClementi

At OpenAI, it's felt like our researchers & engineers have been living in the future with Codex. Today, we're bringing that same experience to life science researchers with the Rosalind Workbench.

We are hiring a postdoc on very large-scale protein modeling and free energy calculation for protein-ligand and membrane protein systems. Join us at @MSFTResearch to develop the next generation of AI models for biomolecular dynamics and function. apply.careers.microsoft.com/…

New paper at @mlforhc (MLHC) 2026: when AI is used to predict treatment outcomes, a common practice is to treat it as binary classification – did a patient have the outcome by N years, or not?

Europe always chooses science and partnership. Japan too. Japan is now officially associated with Horizon Europe. This means Japanese researchers and organisations can take part in the world's largest public research and innovation programme. Let's break new frontiers together.

ELEMENTA is a large scale DFT dataset for UMLIP and “foundation model” training. The coolest thing we found is the sampling on the spin degree of freedom. This has long been neglected but turned out to be so important!

Hello from the Gordon Conference on Computational Chemistry in Barcelona #GCCC @GordonConf @UCSD @Yale

The wait ⏰ is over! Most structure prediction tools give you 1 answer. #RNA just doesn’t work that way - it's the ultimate shapeshifter. Today, we’re launching #RNAccess by Emergente Inc. with access for academic, nonprofit, and commercial researchers. RNAccess is powered by #RNAnneal, our physics-grounded #AI engine for #RNA structure prediction. By combining physics-based simulation with Generative AI, RNAnneal captures the structural flexibility that makes RNA both incredibly challenging—and incredibly powerful. The workflow is simple: 🧬Submit an RNA sequence of up to 100 nucleotides (long RNAs coming soon). ⚡Receive a thermodynamically ranked ensemble of high-accuracy 3D structures. 🔍Explore results through intuitive, interactive visualizations in your browser. 🦠Example: A key functional region of SARS-CoV-2 #RNA pictured below was predicted + visualized accurately in #RNAccess (with no prior knowledge, just physics!) We built #RNAccess to make serious RNA structure prediction more accurate, accessible, and useful for researchers working across all RNA work, from fundamental discovery to applied innovations. No local compute. No pipeline setup. No coding experience needed. Not even a GPU bill - we’ve got that covered 🙇 🎓Academic/non-commercial researchers: Receive a free batch of predictions every month, with pay-as-you-go options when you need more. 🏢Commercial teams: Start with a complimentary prediction, then talk with us about evaluation, confidential use, and larger-scale applications. 📍Try RNAccess: emergente-sci.com 📍Contact: [email protected] Come fold with us 💫 ------------------ It took a village to get this far. Thank you to @NIH-NIGMS, @NSF -Chemistry-CTMC, TEDCO, University of Maryland Institute for Health Computing, Institute for Physical Science and Technology, Montgomery County Government, UMD Chemistry and Biochemistry, @UMDscience, @UMmedschool and many others for financial and other support. Gratitude to leadership Bradley Maron, MD, Adam Porter, @VarshneyAmitabh, Mark T. Gladwin, MD, Martha Jurczak for their continued faith in our team at University of Maryland Institute for Health Computing and in Emergente Inc. - the first startup out of the IHC! And finally, huge thanks to our awesome scientific advisers Robert Copeland, Jonathan Dinman and John (Jay) Schneekloth for their guidance.