Andres M Bran @drecmb

CTO b12 Labs | YC S25 | https://t.co/u3rprn2qhQ Prev PhD @EPFL | @mpiMathSci. Building Crows for Chemists, Automating Synthesis 🐦‍⬛🚀 b12-labs.com San Francisco, CA Joined April 2016

Tweets

765
Followers

752
Following

649
Likes

36K

Andres M Bran @drecmb

4 days ago

@Satpathology Probs of success depends heavily on the asset itself - screening the same boring molecules over and over won't get us far here. Very bullish on design models (Iso, Boltz, etc), but making those molecules will quickly become the bottleneck

0 0 0 110 0

View Details

Andres M Bran @drecmb

5 days ago

@m_goes_distance airbnb for atoms

0 0 0 1 0

View Details

Andres M Bran @drecmb

5 days ago

@curiouswavefn Math is also kinda made up, and as long as the rules are respected the math can be correct. You can even come up with rules of your own! With chem and bio there's hardly any such rules and only appealing guesses or good heuristics - so yeah lab is king

0 0 1 198 1

View Details

Andres M Bran @drecmb

6 days ago

@michellearning It's not the main bottleneck - just as coding was never really the bottleneck. Yet coding agents are quite useful and enable to build many more things on the same components. Do agree there's much more to it than NL, but it does enable part of your last point

1 0 0 34 0

View Details

Andres M Bran @drecmb

2 weeks ago

@Dorialexander Fair enough - maybe less about the data than abt the physical deployment of intelligence and the loops created out of that

0 0 1 80 0

View Details

Andres M Bran @drecmb

2 weeks ago

@m_goes_distance Automated synthesis of complex molecules - synthesizing what the desgin models want b12-labs.com @b12Labs

0 0 0 42 0

View Details

Andres M Bran @drecmb

4 weeks ago

@owl_posting @FoundationOAI Big congrats!

0 0 2 86 0

View Details

Zlatko Jončev @ZJoncev

a month ago

If you want to get much much better performance in retrosynthsis and reaction optimization then just using LLMs, and actual execution of experiments talk to us we have been building and evaluating agents in this exact space for years. @b12Labs

Anthropic @AnthropicAI

a month ago

New Anthropic Science Blog: Making Claude a chemist. To manipulate a molecule, chemists first need to understand its structure. Their main tool is NMR spectroscopy. We found Opus 4.7 matches—and on some tasks beats—dedicated NMR software. Read more: anthropic.com/research/makin…

269 430 4K 501K 1K

0 1 6 215 0

View Details

Andres M Bran @drecmb

a month ago

@AnthropicAI Such an exciting direction! Esp what's next: synth planning and mechnisms. We did just that recently cell.com/matter/fulltex… and claude (Sonnet 3.7) was the first model ever achieve good scores at these tasks! We're continuing to build evals just for this at @b12Labs 🔥

0 2 7 223 0

View Details

b12 Labs @b12Labs

2 months ago

In the quest toward automated synthesis, there's a massive gap between "this reaction looks good in paper" and actually running it. Turns out, someone has to select the conditions: temperature, ligands, additives... the right conditions turn an impossible reaction into real product! Today we’re announcing Palladium, our agentic solution for reaction condition and HTE plate design. Instead of starting with blind optimization, Palladium leverages precedent experiments and substrate-specific reasoning to design a strong first plate. Our beta users in academia and pharma have found conditions as high as 98%, and typically above 90% yield, on the first experiment, often with no follow-up experiments needed. This is how at b12 Labs (YC S25) we accelerate real chemistry. Read more b12-labs.com/blog/palladium… If you’re a chemist trying to accelerate difficult reactions, we’d love to talk.

0 2 8 65K 1

View Details

Zlatko Jončev @ZJoncev

2 months ago

High-throughput platforms have found great application in process chemistry teams, where you need to debug reactions by exploring chemical space with a relatively standardized output to measure. But at the scale of 96-384-1536 wells at a time, even the best chemists struggle to keep all results and hypotheses in mind, and have mostly converged on factorial-based designs. Today, we are announcing Palladium, b12’s plate designer tool, which mimics the way chemists would think, hypothesize, test, analyze, and iterate on HTE conditions, and does so on scale. What I find amazing is that you can go from SMILES strings to complex hypothesis testing in just a few clicks. First results are very promising, stay tuned for experimental validation details soon.

b12 Labs @b12Labs

2 months ago

0 1 4 194 0

0 1 1 144 0

View Details

b12 Labs @b12Labs

2 months ago

The @b12Labs team is joining @FutureLabs_Live next week in Basel! Meet our founders @ZJoncev and @drecmb at Booth S9. At @b12Labs (YC S25) we believe the future of Synthetic Chemistry is Agentic, and we are building that future. If you're around, let's meet and discuss chemistry and AI: we'll be excited to share our latest breakthroughs in retrosynthesis, reaction optimization, and integration with robotic labs! We’d love to connect with partners and chemists who are ready to embrace the agentic future of the lab. Let’s talk about how we can optimize your reactions and automate your workflows. #FutureLabs #AgenticChemistry #AI4Science #Chemistry #Synthesis

2 2 5 136 0

View Details

b12 Labs @b12Labs

2 months ago

hello world 👀 🤖⚗️

0 4 5 299 0

View Details

Zlatko Jončev @ZJoncev

2 months ago

Great demos at Launch Live @ycombinator - remote control of robots, reinventing ultra sound, new transformer architectures for non-human tasks, and saving agents from dead-ends. YC events always feel like Im sent several years to the future.

0 3 5 319 0

View Details

Andres M Bran @drecmb

6 months ago

@rheejust @porterdotrun @FirstMarkCap @ycombinator @daltonc @ROWGHANI Huge congrats! Couldn't expect less from such a great team with a great product 🔥

1 0 1 63 0

View Details

Xuan-Vu Nguyen @XuanVuNguyen18

10 months ago

You don’t like molecular dynamics? We get it. That’s why at this year’s LLM hackathon for Chemistry and Materials Science, we built not one, but ✨two✨ AI agents for molecular dynamics 👇