Chaitanya K. Joshi @chaitjo.bsky.social · 14/04/2026Excited to have Edric Choi present his latest work on RNA chemical mapping at the CASP Nucleic Acids Reading Group! Thursday April 16 2026 on Zoom; Pacific Daylight Saving Time 8 am / Eastern Daylight Saving Time 11 am -- free to attend and full of interactive discussions. 011
Chaitanya K. Joshi @chaitjo.bsky.social · 06/02/2026I 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... 030
Chaitanya K. Joshi @chaitjo.bsky.social · 08/01/2026Four years of research on Geometric Deep Learning & Molecular Design, summarized in 3 questions: - How expressive are our models? (Theory) - Can we build foundation models for molecules? (Architecture) - Can AI design RNA in the real world? (Application) 000
Chaitanya K. Joshi @chaitjo.bsky.social · 08/01/2026New 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...chaitjo.substack.comA Cambridge PhD thesis in three research questionsGeometric Deep Learning for Molecular Modelling and Design: A personal scientific journey 1112
Chaitanya K. Joshi @chaitjo.bsky.social · 04/01/2026It relies on new algorithms for template search, invented by Kagglers such as G. John Rao. If no templates are found, the model can still work and works decently well without templates, too. 010
Chaitanya K. Joshi @chaitjo.bsky.social · 02/01/2026The main takeaway from the Kaggle competition was how powerful RNA template modeling can be — it was kind of shocking to us 🤯 RNAPro integrates 3D templates into Protenix/the AF3 architecture, and this moves the needle on automated RNA structure prediction! 120
Chaitanya K. Joshi @chaitjo.bsky.social · 02/01/2026Happy 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) 182
Chaitanya K. Joshi @chaitjo.bsky.social · 26/12/2025The video was largely created using AI text-to-video, and I must say the results are pretty impressive! There's huge potential for this technology to make science more approachable, just like Google's NotebookLM. 000
Chaitanya K. Joshi @chaitjo.bsky.social · 26/12/2025Merry 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...youtube.comAI vs. Humans: The "AlphaGo Moment" for RNA DesignYouTube video by Chaitanya K. Joshi 120
Chaitanya K. Joshi @chaitjo.bsky.social · 18/12/2025I 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...chaitjo.substack.comAn AI Researcher in the Cathedral of Molecular BiologyHow we designed catalytic RNA functions, and what I learned holding a pipette at the MRC Laboratory of Molecular Biology. 041
Chaitanya K. Joshi @chaitjo.bsky.social · 15/12/2025- How to set up the design prompt just right? - How many sequences to sample and how to make them diverse? - How exactly is filtering done step-by-step? - How to analyze wet-lab results and create figures? You can find out all of that in our GitHub codebase! 💻: github.com/chaitjo/geom...github.comGitHub - chaitjo/geometric-rna-design: gRNAde is a Generative AI framework for inverse design of 3D RNA structure and functiongRNAde is a Generative AI framework for inverse design of 3D RNA structure and function - chaitjo/geometric-rna-design 030
Chaitanya K. Joshi @chaitjo.bsky.social · 15/12/2025With this release, we are fully openly releasing all the tacit knowledge for getting biomolecule design models to actually work in wet labs! Seemingly small-but-critical details are often missing in flagship papers, and it took us a while to finetune our pipeline: 130
Chaitanya K. Joshi @chaitjo.bsky.social · 15/12/2025Many papers have built their RNA design pipelines using the gRNAde code & data from our ICLR 2025 spotlight paper - that's been exciting to see! Especially the attempt at biologically meaningful benchmarks 🤗 But how to take ML conference papers to wet-lab validated results? 100
Chaitanya K. Joshi @chaitjo.bsky.social · 15/12/2025Excited 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! 182
Reposted by Chaitanya K. JoshiRocío Mercado Oropeza @rociomer.bsky.social · 09/12/2025Happy 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 1/4arxiv.orgLeMat-GenBench: A Unified Evaluation Framework for Crystal Generative ModelsGenerative machine learning (ML) models hold great promise for accelerating materials discovery through the inverse design of inorganic crystals, enabling an unprecedented exploration of chemical spac... 1103
Reposted by Chaitanya K. JoshiArc Institute @arcinstitute.org · 07/12/2025Thank 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. 281
Chaitanya K. Joshi @chaitjo.bsky.social · 08/12/2025I 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) 160
Chaitanya K. Joshi @chaitjo.bsky.social · 04/12/2025Thankful for the tireless work and motivation from yourself and the Eterna team! 010
Reposted by Chaitanya K. JoshiJill Townley @jilltownley.bsky.social · 03/12/2025An 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. 😎 162
Reposted by Chaitanya K. JoshiErik Poppleton @poppleton.phd · 03/12/2025Enumerating 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! 🧬🧪 0176
Chaitanya K. Joshi @chaitjo.bsky.social · 03/12/20255/ Want the story behind the science? 🏰 I wrote a blog post about our "AlphaGo Moment" and what it was like being an AI researcher embedded at the legendary @mrclmb.bsky.social (holding a pipette for the first time!) Read it on Substack: chaitjo.substack.com/p/alphago-mo...chaitjo.substack.comAn AlphaGo moment for RNA designHow our AI system, gRNAde, matched human experts at the complex game of RNA folding—and why it matters. 010
Chaitanya K. Joshi @chaitjo.bsky.social · 03/12/20254/ This was a massive team effort bridging AI and biology, from one end of Cambridge to another 🤗🚲 Thanks to Edo Gianni* @edogia.bsky.social, Sam Kwok*, @simonmathis.bsky.social, Pietro Liò, and @philholliger.bsky.social for this journey! 📄 Preprint: tinyurl.com/gRNAde-papertinyurl.comGenerative inverse design of RNA structure and function with gRNAdeThe design of RNA molecules with bespoke three-dimensional structures and functions is a central goal in synthetic biology and biotechnology. However, progress has been limited by the challenges of de... 141
Chaitanya K. Joshi @chaitjo.bsky.social · 03/12/20253/ The Mechanistic Insight 👽 What did gRNAde learn? Humans stick close to nature, but gRNAde changes ~70% vs. WT sequence. And it "sees" invisible 3D constraints that rational methods miss, allowing us to make "generative jumps" to new functional islands in sequence space 🏝️ 100
Chaitanya K. Joshi @chaitjo.bsky.social · 03/12/20252/ The Function Challenge ⚙️ But can we move from static shape to dynamic RNA machines? We show how with a complex RNA Polymerase Ribozyme. Rational design failed (3% success). gRNAde succeeded (31.5% active), discovering improved variants 15-20 mutations away from nature. 100
Chaitanya K. Joshi @chaitjo.bsky.social · 03/12/20251/ The Structure Challenge 🧩 We entered gRNAde into Eterna OpenKnot: a CASP-style blinded, wet-lab competition by @eternagame.org The result? Parity with the world's best humans, and big gains over Rosetta, RFdiffusion. We can automate expert intuition for complex RNA folding! 120
Chaitanya K. Joshi @chaitjo.bsky.social · 03/12/2025Introducing 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! 🧵👇 2296
Reposted by Chaitanya K. JoshiJamie Cate @jhdcate.bsky.social · 15/11/2025To make future progress it’s worth revisiting the past. From Olke Uhlenbeck, “Keeping RNA Happy” pmc.ncbi.nlm.nih.gov/articles/PMC...pmc.ncbi.nlm.nih.govKeeping RNA happyAn official website of the United States government 041
Chaitanya K. Joshi @chaitjo.bsky.social · 15/11/2025🚀🧬 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...chaitjo.substack.comBeyond structure-based biomolecule designDynamics, black-box data, and the antedisciplinary frontier of biomolecule design 042
Chaitanya K. Joshi @chaitjo.bsky.social · 18/10/2025And at big industrial labs with large budgets, the scientists are just able to do a lot more intuition-building. They are able to try ideas a lot faster, and get a 'feel' for what ideas will work much faster as a result. 120
Chaitanya K. Joshi @chaitjo.bsky.social · 18/10/2025Why 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. 140
Reposted by Chaitanya K. JoshiDas Lab @rdaslab.bsky.social · 24/09/2025The 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... 0145
Reposted by Chaitanya K. JoshiMLSB (in San Diego + Copenhagen) @workshopmlsb.bsky.social · 17/09/2025🚨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. 033
Reposted by Chaitanya K. JoshiKevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · 17/09/2025Genome 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... 2319
Reposted by Chaitanya K. JoshiSamuel King @samuelhking.bsky.social · 17/09/2025Many 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 🧵 35020
Reposted by Chaitanya K. JoshiJase Gehring @skyjase.bsky.social · 18/09/2025very 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 2149
Reposted by Chaitanya K. JoshiMLSB (in San Diego + Copenhagen) @workshopmlsb.bsky.social · 12/09/2025You 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💫 2106
Chaitanya K. Joshi @chaitjo.bsky.social · 05/09/2025The 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) 040
Reposted by Chaitanya K. JoshiRachael Kretsch @rachael-kretsch.bsky.social · 02/09/2025We 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 1134
Chaitanya K. Joshi @chaitjo.bsky.social · 31/08/2025Scaling 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 🤯 000
Reposted by Chaitanya K. JoshiNate Corley @ncorley.bsky.social · 15/08/2025(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) [www.biorxiv.org/content/10.1101/202…...)biorxiv.orgAccelerating Biomolecular Modeling with AtomWorks and RF3Deep learning methods trained on protein structure databases have revolutionized biomolecular structure prediction, but developing and training new models remains a considerable challenge. To facilita... 26728
Chaitanya K. Joshi @chaitjo.bsky.social · 16/08/2025It can train foundation models, but can it train frontier models too? ;) 000
Chaitanya K. Joshi @chaitjo.bsky.social · 15/08/2025📢 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/MLSB2025mlsb.ioMLSB 2025 WorkshopWorkshop on Machine Learning in Structural Biology co-located with NeurIPS 2025 032
Chaitanya K. Joshi @chaitjo.bsky.social · 15/08/2025RosettaFold 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... 05418
Chaitanya K. Joshi @chaitjo.bsky.social · 05/08/2025Great image of organizers space group symmetry! 130
Chaitanya K. Joshi @chaitjo.bsky.social · 01/08/2025Really insightful post and responses - this is why I keep coming back to science social media! 010
Chaitanya K. Joshi @chaitjo.bsky.social · 31/07/2025Alex’s explainer thread is a heartfelt one: x.com/Alex__Abruda... And the preprint is on arXiv link: www.arxiv.org/abs/2507.21938x.com 000
Chaitanya K. Joshi @chaitjo.bsky.social · 31/07/2025🧬 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! 191
Reposted by Chaitanya K. JoshiMartin Pacesa @martinpacesa.bsky.social · 25/07/2025I 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! 2321839
Reposted by Chaitanya K. JoshiEterna @eternagame.org · 23/07/2025Coming 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 052