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.
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...
Thanks, Nick!
We will also be hosting Boltz launch parties that will include a demo, drinks, awesome discussions, and a giveaway of free credits. Sign up!
San Francisco, Jan 15th: luma.com/yogmbte1
Boston, Jan 22nd: luma.com/6txhgndf
London, Jan 29th: luma.com/8rar11y4
Virtual, Feb 2nd: luma.com/ttuhzb92
Read more from the following longer-form blogs posts:
- Our company manifesto: boltz.bio/manifesto
- Our platform and agents announcement: boltz.bio/boltzlab
- Our press release with Pfizer: boltz.bio/pfizer-partn...
- Andrew Dunn article on Endpoints: endpoints.news/exclusive-bo...
Sign up to Boltz Lab today and you will also receive credits to start using the platform for free. We can’t wait to see what you build on Boltz Lab! lab.boltz.bio
All of this would not have been possible without first assembling an exceptional team. To support this team, we are honored to announce we’ve raised $28M seed round led by Zetta, Amplify, and a16z along with strategic angels including @clem.hf.co & @matthartman.bsky.social
Over the past few months, we have already seen the success of the new agents and Boltz Lab in the hands of scientists across the field. Whether you are an individual researcher or a company the size of Pfizer, we can’t wait to see what you build with our tools in your hands.
We are also excited to announce a multi-year collaboration with Pfizer, to put Boltz Lab and its agents in the hands of Pfizer scientists, and to work together on new foundation models leveraging Pfizer data.
We’ve focused on optimization + infrastructure so results arrive quickly, we have generous free tiers, and costs are lower than open-source, without users taking on the engineering. We have clear terms: you own your outputs, your data stays secure, and we don’t train on your data
We’ve made these agents the core of Boltz Lab, a new platform designed around real bio/chem workflows, removing adoption bottlenecks like compute cost, scalable infrastructure, and collaborative interfaces.
We have been hard at work building and validating the next generation of small-molecule and protein design agents that more deeply leverage our models driving significant improvements. We’re releasing the first versions of these agents and sharing some great initial results!
We are not a therapeutics company. Our goal is to build a product that allows every scientist to go from a therapeutic hypothesis to a human-ready molecule without leaving their computer. As a first step, we are releasing a preview of Boltz Lab, our platform alongside new AI agents.
We believe the frontier should stay open enough to maximize scientific and patient impact. That’s why we founded Boltz PBC, a Public Benefit Corporation: advance AI for biology through open science, and make it accessible to every scientist building a healthier future.
As researchers, we have seen firsthand the power of open science. Our models, Boltz-1, Boltz-2 and BoltzGen, have already been used by over a hundred thousand scientists in both academia and industry and form the foundation for countless pipelines, agents, and platforms.
AI-powered molecular modeling is advancing fast with the promise of making biology programmable, digitizing experiments, and dramatically speeding up drug discovery. But the field is trending more closed, severely limiting the impact on science and, most importantly, on patients.
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! 🧵👇
Blue and white graphic overlaid with text that reads "Introducing BoltzGen: Toward Universal Binder Design" followed by headshots and names of the speakers starting from the top "Hannes Stark, PhD student, MIT; Regina Barzilay, AI Faculty Lead, MIT Jameel Clinic; Tommi Jaakkola, Principal Investigator, MIT Jameel Clinic" Followed by event details: "When: Thursday, Oct. 30, 5pm-6pm; Where: 32-123, Stata Center; RSVP jclinic.mit.edu/events/boltzgen/"
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/...
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!
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)
BoltzGen now published and available as MIT licensed software
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!
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)
You can find all the code and documentation at: github.com/jwohlwend/bo...
Join our community Slack: boltz.bio/join-slack
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! 🤗
