"Evaluating Representation Learning on the Protein Structure Universe" Arian Jamasb Alex Morehead @ ICML (何聪) Zuobai Zhang Chaitanya K. Joshi Kieran Didi Simon Mathis Charlie Harris Jian Tang Pietro Lio' Tom Blundell openreview.net/pdf?id=sTYuRVr…

🚨We are super excited to be hosting Bruno Correia Bruno Correia at the Computer Lab Wednesday next week to talk about AI and protein design !!!🚀 talks.cam.ac.uk/talk/index/210… Title: Exploring novel (bio)molecular spaces by design – a dialogue between representation and generation.

Super excited for the visit of Bruno Correia to Cambridge!

Check out our new paper Nature Chemistry where we use microfluidics to identify a mini enzyme from a de novo designed library giving a plausible scenario for emergence of enzymatic function at #OriginOfLife by #DirectedEvolution! nature.com/articles/s4155…

The headline for AlphaFold3 is no equivariance. But there’s so much more to the methods that is challenging and thought provoking.

Looking forward to this one!

Excited to share a new update to gRNAde code! github.com/chaitjo/geomet… You can now forward-fold designed RNAs in 2D and 3D (RhoFold) to measure structural self-consistency metrics + cool visualisations! Hope we develop our own version of 'designability' in the RNA world ;)

An update to the gRNAde preprint adds some new baselines + a more extensive ablation study on RNA inverse folding models w/ 3D self-consistency metrics: arxiv.org/abs/2305.14749 + new coauthors Alex Morehead @ ICML (何聪) Rishabh Anand 🧬 thanks for all the help in 3D evals

1/4 Can we unleash the power of continuous Riemannian Flow Matching on discrete generation? We introduce “Statistical Flow Matching (SFM)”, a novel FM framework on the manifold of probability measures inspired by information geometry. arxiv.org/abs/2405.16441 Kudos to@ccr_cheng

Biotite has been my go to for a while now- can highly recommend!

New blog post alert! 🚨 I write about AlphaFold3, how it works, where it works well ✅ (and where we think it might not ❌) and what it means to the TechBio landscape more broadly (if you decide to believe me). 🧬 (1/7) 🧵 open.substack.com/pub/harrisbio/…

I wrote a post with owl on "things to keep in mind while reading BioML papers." Check it out and check out owl's writing on The Website!

I really enjoyed reading this -- thank you Nathan C. Frey and owl . Thoughtful takes as always!