Extremely exciting day for open science. Another reason to be bullish on UK AI. Boltz, a startup that emerged out of MIT to be at the frontier of small molecule and protein design, has moved to London. I hear cases like this from a few founders, often a mix of fundamentals (talent)+personal.

Gabriele Corso@gcorso.bsky.social · 7mo ago

Big news from Boltz today: we’re launching Boltz Lab, a new platform with new small-molecule + protein design agents, announcing Boltz PBC and a $28M seed round, and sharing a multi-year partnership with Pfizer. More below!

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...

A Cambridge PhD thesis in three research questions

Geometric Deep Learning for Molecular Modelling and Design: A personal scientific journey

chaitjo.substack.com

Big news from Boltz today: we’re launching Boltz Lab, a new platform with new small-molecule + protein design agents, announcing Boltz PBC and a $28M seed round, and sharing a multi-year partnership with Pfizer. More below!

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! 🧵👇

Join us today at MIT from 5pm-6pm for a seminar for BoltzGen, which is free and open to the public! Looking forward to seeing you all later today! 🤩 If you plan to attend, don't forget to RSVP so we can plan accordingly: luma.com/7474iho2 #AISky #AcademicSky

One cool thing about BoltzGen is the flexibility of the conditioning information you can provide (e.g. "constrain the structure of these residues and also these but let their relative placement vary"). I'm really curious to see what the community does with it! github.com/HannesStark/...

GitHub - HannesStark/boltzgen

Contribute to HannesStark/boltzgen development by creating an account on GitHub.

github.com

Very happy @roman-bushuiev.bsky.social and I joined the amazing team led by @hannes-stark.bsky.social to work on BoltzGen, a generative model for binder design based on Boltz-2. Excited what it will enable!

Hannes Stark@hannes-stark.bsky.social · 9mo ago

Excited to release BoltzGen which brings SOTA folding performance to binder design! The best part of this project is collaborating with a broad network of leading wetlabs that test BoltzGen at an unprecedented scale, showing success on many novel targets and pushing the model to its limits!

Thrilled to contribute to this exciting work on protein binder design together w/ @hannes-stark.bsky.social , Felix Faltings, Regina Barzilay, Tommi Jaakkola, and co. We applied BoltzGen to design novel antimicrobial peptides targeting DNA gyrase based on inhibitory protein fragments. (1/n)

Hannes Stark@hannes-stark.bsky.social · 9mo ago

Excited to release BoltzGen which brings SOTA folding performance to binder design! The best part of this project is collaborating with a broad network of leading wetlabs that test BoltzGen at an unprecedented scale, showing success on many novel targets and pushing the model to its limits!

BoltzGen now published and available as MIT licensed software

Hannes Stark@hannes-stark.bsky.social · 9mo ago

Excited to release BoltzGen which brings SOTA folding performance to binder design! The best part of this project is collaborating with a broad network of leading wetlabs that test BoltzGen at an unprecedented scale, showing success on many novel targets and pushing the model to its limits!

I’ve been testing BoltzGen a bit recently and while I haven’t done any experimental testing yet, the quality of the software is very clear. It installs, runs, logs everything, has tons of options. Very excited to test out the designs irl!

Hannes Stark@hannes-stark.bsky.social · 9mo ago

Excited to release BoltzGen which brings SOTA folding performance to binder design! The best part of this project is collaborating with a broad network of leading wetlabs that test BoltzGen at an unprecedented scale, showing success on many novel targets and pushing the model to its limits!

Excited to release BoltzGen which brings SOTA folding performance to binder design! The best part of this project is collaborating with a broad network of leading wetlabs that test BoltzGen at an unprecedented scale, showing success on many novel targets and pushing the model to its limits!

Pretty surreal when out of the blue you see your model up on an ad on highway billboards and airport screens 🤯 (pictures from San Diego Airport and a highway in SF)

Boltz v2.2.1 out. A few improvements including support for .pdb templates, better treatment of stereochemistry in guidance potentials, and improved documentation. As always a great thank you to all those in the community who contributed via PR, raising issues or directly reporting issues to us.

Sitting at the #AITHYRA symposium hearing about incredible new high-throughput datasets 🤯! If you have developed new data that you think could improve Boltz, e.g. protein small-molecule affinity, protein protein affinity, binding site (eg via proteomics), let's work together! 🤗

Here's how to predict binding of tens or hundreds of small molecules to protein assemblies using Boltz 2 in ChimeraX. Accuracy depends on how similar the ligands and binding pockets are to existing experimental structures. www.rbvi.ucsf.edu/chimerax/dat...

On #Boltz and #drugdesign by @gcorso.bsky.social #PragueBioML @elixircz.bsky.social

If you use Boltz1/2, BioEmu, Chai1, or other MSA-dependent models, you’re likely using our ColabFold server. Please be considerate! Avoid large submissions across many IPs instead generate the MSA locally. Our server is an old-timer from 2014 and can’t handle that load.

ChimeraX daily builds can predict binding affinity of small molecules using Boltz 2 on your Mac, Windows or Linux computer. www.rbvi.ucsf.edu/chimerax/dat...

Excited to share our work on modeling the human protein interactome in 3D. This currently includes 1,394 interaction structures predicted with Boltz-2. Grateful for the open-access resources making this possible! Preprint: doi.org/10.1101/2025...

Gabriele Corso@gcorso.bsky.social · last yr.

Excited to unveil Boltz-2, our new model capable not only of predicting structures but also binding affinities! Boltz-2 is the first AI model to approach the performance of FEP simulations while being more than 1000x faster! All open-sourced under MIT license! A thread… 🤗🚀

Boltz-2 : Towards accurate and efficient binding affinity prediction by @gcorso.bsky.social Saro Passaro and Jeremy Wohlwend youtu.be/iHDauMATkr0?...

Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction

YouTube video by Valence Labs

youtu.be

Nice interview of Phil Sharp on the controversial birth of biotech and recombinant DNA with some great analogies to the current discourse on AI and gene editing! - YouTube www.youtube.com/watch?v=LLij... - Spotify spotifycreators-web.app.link/e/NNmzqnTjgUb - Apple podcasts.apple.com/us/podcast/h...

The Nobel that Sparked Biotech - Prof Phil Sharp

YouTube video by Health Horizons

youtube.com

Thank you everyone for attending the Boltz-2 Boston, San Francisco and Paris events this week! Given the success of the in-person seminars and the many requests, we are organizing a virtual seminar on Tuesday at 12pm ET / 6pm CET! Sign up here: lu.ma/4bpuwbsr

A new AI model jointly predicts protein structure and binding affinity, enabling rapid, accurate screening of small molecules and accelerating early-stage drug discovery. Boltz-2 is now open source.

Protein-binding affinity model expands role of AI in drug discovery

Understanding how molecules interact is central to biology: from decoding how living organisms function to uncovering disease mechanisms and developing life-saving drugs.

phys.org

Open science, activated. Since the release of Boltz-2 last Friday – the new open-source protein structure and protein binding affinity model from MIT & Recursion – we’ve been introducing the model to the broader community and the reception has been terrific. 🧵

On June 18 at the Molecular Machine Learning Conference (MoML) at MILA, Gabriele Corso, one of the lead researchers behind Boltz-2, will present more on this latest breakthrough in AI drug discovery alongside researchers from Valence. 👉 Learn more: portal.ml4dd.com #MOML2025

Boltz-2 just dropped: open-source AI that predicts both protein complex folds ✚ binding affinities in one shot 🚀 This is a win for protein AI, but let's not forget MSAs, the bioinformatics backbone many structure models lean on.

It's exciting to see our software used as a benchmark for cutting-edge AI methods!

Gabriele Corso@gcorso.bsky.social · last yr.

On the standard FEP+ affinity benchmark, whose targets were held out of training, Boltz-2 achieves an average Pearson of 0.62—comparable to OpenFE, a widely adopted open-source FEP pipeline, while being over 1000x faster!

A team led by Regina Barzilay, a computer science professor at MIT, has launched Boltz-2, an algorithm that unites protein folding and prediction of small-molecule binding affinity in one package. cen.acs.org/pharmaceutic... #chemsky 🧪

MIT and Recursion partner for AI drug discovery tool

Freely available Boltz-2 algorithm can predict small-molecule binding affinities

cen.acs.org

What a turnout! 🤯 Thank you to the 400+ attendees who came to listen to the first-ever Boltz-2 presentation in-person and for asking great questions! We look forward to seeing how Boltz-2 will empower future research in biomolecular structure prediction! 🧬🔥 #AIsky