I recently joined The Pauling Principle podcast to discuss our research on RNA design, hot takes on architecture research in BioML, origins of life, and being in a wet lab! Feels pretty surreal that I'm interesting enough to be on a podcast (?) www.youtube.com/watch?v=ftrQ...

New blog 💙: I reflect on why I worked on what I worked on... I think a PhD is a very special time. You get to challenge yourself, push your boundaries, and grow. My thoughts go against the current AI/academia narrative online, so I hope you find it interesting. chaitjo.substack.com/p/phd-thesis...

Happy new year! A step change in RNA structure prediction, powered by top Kaggle-ers in a collaboration lead by Stanford University and NVIDIA Happy to have played a small part in the new RNAPro model, significantly outperforming AlphaFold 3 as well as VFold (CASP winners)

Merry Christmas!🎄🌟 Sharing something interesting: Friso van de Stadt created a pretty neat explainer video for our gRNAde paper and "AlphaGo moment for RNA design" blogpost! www.youtube.com/watch?v=wDeZ...

I wrote some personal reflections about being physically embedded in a world-leading molecular biology lab @mrclmb.bsky.social, learning to communicate with experimentalists, back-breaking wet lab work, scientific rigour, and skin in the game! 💌: chaitjo.substack.com/p/an-ai-rese...

Excited to release the fully open-source code for gRNAde - our wet-lab validated, generative AI framework for 3D RNA inverse design 🚀⭐️ I pride myself on open-science & this is probably the most intense release I've done!

Happy to have contributed to and now finally share LeMat-GenBench, a new open benchmark + leaderboard for generative crystalline materials models! ⚛️✨ It provides standardised metrics for validity, stability, & much more. Already includes results for 12 models! 🔗 Paper: arxiv.org/abs/2512.04562 1/4

Thank you to everyone who made the inaugural Virtual Cell Challenge a success. Over 5,000 participants from 114 countries competed to build AI models that predict cellular responses to genetic perturbations. Today we're announcing the winners and reflecting on what we learned.

I think the term ‘Virtual cell’ will have the same trajectory as ‘AGI’ or ‘Foundation models’: Initially opposed by rigorous scientists, while the Bay Area and Demis Hassabis are the only ones comfortable using it → becoming a mainstream term in academia soon, in few years (Overton window)

An AI researcher interested in biochemistry modeling successfully improved his RNA language model through participation in the Eterna pseudoknot design competition. Congratulations, Chaitanya! 🧬🧪 #RNAsky The polymerase ribozyme results are pretty cool too. 😎

Enumerating possible pseudoknots that a sequence can form with nearest-neighbor models is an NP-hard problem. Even evaluating these structures is challenging, let alone designing them. So it’s great to see data-based models starting to crack the RNA structural design problem! 🧬🧪

Introducing gRNAde: our own little "AlphaGo Moment" for RNA design! 🧬🚀 📝: tinyurl.com/gRNAde-paper Unlike proteins, RNA design has long relied on "wisdom of the crowd" (human experts) or the slow crawl of directed evolution — gRNAde changes that! 🧵👇

Wow thank you, Jamie, for sharing! 🤗

To make future progress it’s worth revisiting the past. From Olke Uhlenbeck, “Keeping RNA Happy” pmc.ncbi.nlm.nih.gov/articles/PMC...

🚀🧬 Beyond Structure-based Biomolecule Design Its an important moment for structure-based biomolecule design: models starting to work and action shifting from academia to industry. So what are the next scientific problems academia could be thinking about? chaitjo.substack.com/p/beyond-str...

Why do 'frontier' labs train the best models? I think its because training deep learning models is less like science/engineering, and more like cooking. It takes some time to develop the intuitions around learning dynamics of big models.

The results are in: top codes in Stanford #RNA 3D Folding @kaggle.com competition are competitive with CASP16-leading humans Vfold, beat AlphaFold 3. Top team’s trick was template-based modeling, not #DeepLearning. Congrats: john, odat, Eigen, + all 1706 participants! www.kaggle.com/competitions...

🚨To accommodate the addition of EuroMLSB, we have extended the submission deadline to October 1, 2025 11:59pm AoE. Find information on paper guidelines at mlsb.io. Submissions will be made through CMT.

Genome language models can generate new, high-fitness bacteriophages! @samuelhking.bsky.social @claudiadriscoll.bsky.social @david-li.bsky.social @danguo.bsky.social @adititm.bsky.social Garyk Brixi @maxewilkinson.bsky.social @brianhie.bsky.social www.biorxiv.org/content/10.1...

Many of the most complex and useful functions in biology emerge at the scale of whole genomes. Today, we share our preprint “Generative design of novel bacteriophages with genome language models”, where we validate the first, functional AI-generated genomes 🧵

very cool work and a milestone in synthetic biology. how impressive are the new phage genomes? with generative bioML, i'm always looking at how similar the generated sequences are to known sequences. let's take a look

You asked and we listened... @workshopmlsb.bsky.social is excited to be expanding to Copenhagen, DK at @euripsconf.bsky.social 🎉 Two workshops (San Diego & Copenhagen) will run concurrently to support broader attendance. You can indicate your location preference(s) in the submission portal💫

The 3D structure of biomolecules are nature's 'thinking tokens' enroute to the output that we actually truly want to understand: Function. (Slide from Denny Zhou's Stanford talk on LLM Reasoning)

We have restarted our global Nucleic Acid Strcuture webinar series to bring the expiremental and computational communities together to discuss new developments in the field. Join us this Thursday for the next webinar. Sign up to our mailing list here: groups.google.com/g/casp-rna-sig

Scaling laws for BioML and wet lab data will eventually work out in the right setting! After all, language data for LLMs was acquired by the largest wet lab experiment ever conducted: Human civilisation 🤯

(1/7) Training biomolecular foundation models shouldn't be so hard. And open-source structure prediction is important. So today we're releasing two software packages: AtomWorks and RosettaFold3 (RF3) [https://www.biorxiv.org/content/10.1101/2025.08.14.670328v2](www.biorxiv.org/content/10.1...)

📢 Submissions for MLSB 2025 are officially open! We invite researchers to submit their work on the intersection of AI and structural biology. 🗓️ Deadline: September 26, 2025 🔗 More info: cmt3.research.microsoft.com/MLSB2025

RosettaFold 3 is here! 🧬🚀 AtomWorks (the foundational data pipeline powering it) is perhaps the really most exciting part of this release! Congratulations @simonmathis.bsky.social and team!!! ❤️ bioRxiv preprint: www.biorxiv.org/content/10.1...

Really insightful post and responses - this is why I keep coming back to science social media!

🧬 Protein designers: we keep saying we're getting really good at making static, rock-like proteins... Introducing Dynamic MPNN - our first step towards truly multi-state and 'programmable' protein design! Great collaboration led by Alex Abrudan and Sebastian Pujalte!

I am super excited to announce that I will be starting my lab at the Department of Pharmacology of the University of Zurich in Switzerland next year!

Coming up this weekend, Eternacon will feature presentations about fellow #citsci platform @zooniverse.bsky.social and how participants of both Zooniverse and Eterna have created #machinelearning tools for projects. @noirlabastro.bsky.social Register for free at eternagame.org/eternacon/2025

Are we hitting a wall with scaling molecular foundation models? Some thoughts on what I think is one of the most interesting open Qs atm: chaitjo.substack.com/p/transfer-l...

How does a cell know when it’s been damaged? A molecular alarm, set off by mutated RNA and colliding ribosomes, signals danger. @dsamorod.bsky.social reports: www.quantamagazine.org/rna-is-the-c...

We are looking to recruit a tenure track group leader in the field of Chemical/Synthetic Biology (in the broadest sense) to lead a research program within the Division of Protein & Nucleic Acid Chemistry ( www.jobs.ac.uk/job/DNW809/r... ) at the MRC Laboratory of Molecular Biology (LMB).

Highly collaborative efforts that involved 6 lab members and the labs of @yiliangding.bsky.social and @rdaslab.bsky.social. We uncovered a telomerase dimer and its potential role in telomere maintenance.

Unfortunately, the MLSB Workshop @ NeurIPS (@workshopmlsb.bsky.social) was rejected this year. Feedback from the deciding committee indicates it was a coin flip decision, with 283 proposals & a number related to “computational biology” More on the future of MLSB soon…

Needing a permanent doi was a forcing function to revisit this article on Transformers and Graph Neural Networks: arxiv.org/abs/2506.22084 This is (very) old news, so what's new?

This was posed by a VC (@dreidco.bsky.social ) on LinkedIn. Just a thought: Maybe Boltz-2 is also a moment similar to GPT-3 where a sizeable part of the community moves on from academic publishing and to the world of capabilities, tech reports, and shipping models

Check out this post from @ffabffrasca.bsky.social and the GLOW reading group on the future of graph learning! I’ve also contributed and my main take is - its actually working and its an exciting moment to work on applications! open.substack.com/pub/glowread...

Interested in a postdoc position combining computational protein design and molecular simulation? There is an open position in my group at the MRC-LMB in Cambridge, UK. www.nature.com/naturecareer... Feel free to message me with any questions.

Have you ever been frustrated by how hard it is to tinker with AlphaFold 3? Here's a (hopefully) simple repo to instal locally on laptop/single-GPU and a handy notebook to play around with! github.com/chaitjo/alph...

After a long hiatus, I've started blogging again! My first post was a difficult one to write, because I don't want to keep repeating what's already in papers. chaitjo.substack.com/p/transforme...

How did life on Earth begin? 🌍🧬 New #LMBResearch from Phil Holliger’s group, including James Attwater (now @uclchemistry.bsky.social‬‬ @uclnews.bsky.social) shows how pH-freeze-thaw cycles enables RNA self-replication, overcoming a key evolutionary hurdle.‬ Read more: www.ucl.ac.uk/news/2025/ma...

New paper from my group rdcu.be/eoaRr "Trinucleotide substrates under pH–freeze–thaw cycles enable open-ended exponential RNA replication by a polymerase ribozyme" in Nature Chemistry — great collaboration with attwaterlab.uk.

Sharing a surprising result on AI molecule generation with Transformers: All-atom DiT with minimal molecular inductive bias is on par with SOTA equivariant diffusion (SemlaFlow, a very strong and optimized model) Scaling pure Transformers can alleviate explicit bond prediction!

What is the status of nucleic acid structure prediction? Our analysis of CASP16 (doi.org/10.1101/2025...) reveals human expertise is still necessary for the most accurate prediction, but accuracy still heavily relies on templates; having seen a similar structure already.

Happy to be a small part of this humongous effort by the inimitable Srijit!

Equivariance is dead - long live equivariance? Scaling pure Transformers is the future of molecular generative models? I think its a lot more nuanced -- I tried to give some perspectives in my spotlight talk at #ICLR2025 AI4Mat Workshop last week Full video here: youtu.be/NiY4NLzemnU?...