Anthropic just used Claude to accelerate 30+ open-source biology models, including our own ESMFold2. Our researchers contributed to speed up the kernels and dramatically decrease the memory requirements, enabling much larger protein folds.

I’ve given Claude Opus various published papers (and my own unpublished ones) and asked it to review them. (Don’t panic—I’m not uploading confidential manuscripts.) The reviews it produces are excellent. It finds statistical errors, internal contradictions, and conceptual confusions that human reviewers miss; it provides useful suggestions; it has a good sense of what counts as significant and novel and what doesn’t; and it’s generous in its appreciation for what the authors get right. And it doesn’t suffer from the strong “myside bias” humans have; it doesn’t recommend rejection because the author didn’t cite it enough; it doesn’t insult the authors; and it doesn’t agree to write a review and then never send anything in. As a journal editor, I’m not sure what to do with this. If I gave up on human reviewers and used GPT-5.6 Sol and Claude Opus instead, my bosses would fire me, probably rightfully so. The only constructive thing I can recommend is that, before submitting something to a journal, researchers and scholars use this tremendously valuable resource. (Just don’t tell the models that it’s your paper, because they do suffer from sycophancy.)

🧵 We ran the largest head-to-head benchmark of protein binder design methods in the wet lab. Project page: research.nvidia.com/labs/gen… 1 million designs. 127 targets. RFdiffusion, BindCraft, BoltzGen, and Proteina-Complexa — all tested side by side.👇

Nature research paper: Nanobody-based recombinant antivenom for cobra, mamba and rinkhals bites go.nature.com/47TmCuf

New Huang lab publication!! The first demonstration of nanopore discrimination of all proteinogenic amino acid enantiomers, suggesting nanopore sequencing of D- or DL-peptide? onlinelibrary.wiley.com/doi/…

Excited to share #AlphaGenome, a start of our AlphaGenome named journey to decipher the regulatory genome! The model matches or exceeds top-performing external models on 24 out of 26 variant evaluations, across a wide range of biological modalities.1/6

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

Boltz-2 was released recently. It is an Open Source protein-ligand co-folding model, which means it can predict the structure of a protein along with the ligand. It has various applications from drug discovery to protein design. I thought why not make a OSS web app for it.

Excited to see our work published in @ScienceAdvances! We present RBPseg, a method for structural prediction of #phage receptor-binding proteins. We applied it to diverse tail fibers and validated the predicted structures using #cryoEM. Read here: science.org/doi/10.1126/scia…

Exited to share our preprint on the structure of a Salmonella contractile injection system 🥳 Wonderful work by first author @Rooshanie Ejaz and @CloudyKielkopf, @freddie__martin, @HangryHobbit, @RebrovaEva, great collab with @Salmo_Lab @UCPH_CPR #cryoem shorturl.at/QHLpm

New pre-print - 🥳🥳🥳 biorxiv.org/content/10.1101/…

There is also a Colab notebook for EvoBindRare now! Try it and let us know what you think: colab.research.google.com/gi…

You want to start tomography? Solve structures inside cells? Reach Nyquist😳? We have a website for you! tomoguide.github.io You'll find a tutorial on how to reconstruct tomograms, pick particles and do subtomo averaging, using different software! Hope it will be useful !

I'm happy to see our collaboration with @phagebioUCPH @LNdsted out on npj viruses! I had a fun time modelling T-even #phages adhesin proteins. Verifying that we can use #AF2 bias to select true binders was even cooler. Congrats to Veronika Lutz and all nature.com/articles/s44298-0…

12 lessons students learn in the Sinclair Lab: Lesson 1. Write the way you speak

New Huang lab publication. A comprehensive review of nanopore environmental analysis. And, it is open access, which should be convinient for most readers. pubs.acs.org/doi/10.1021/jac…

New paper alert 🚨 We've solved the complete structure of a C. difficile-infecting phage using cryo-EM, in both extended and contracted conformations - published today in Life Science Alliance

A recent news/views article about our nanopore rare earth element sensing work published at Nature Nanotechnology. Thanks Andrew Laszlo for your comments, really supportive and inspiring 😊😊. There are plenty of room for nanopore beyond sequencing. nature.com/articles/s41565-0…

Please spread the word! We have an opening in the Atkinson lab for a post-doc with a focus on molecular mechanisms of microbial immune systems. Can be a fully computational or experimental or hybrid project. Read more & apply here: lu.varbi.com/en/what:job/job… #phage #Bioinformatics

💛LoVis4u - a visualisation tool for comparative genomics and sequencing coverage profiles is now published! See our paper in NAR GB: doi.org/10.1093/nargab/lqaf0…