Simon Kohl

It's been great to talk to Tom Mackenzie of Bloomberg News about the launch of our protein design model and platform this morning!

🧬Latent-X is our first frontier model for protein design.

For mini-binders, our AI model achieved picomolar binding affinities — the strongest reported vs prior methods in head-to-head lab validation.

Explore our best binders here: platform.latentlabs.com

More details on the breakthrough in this🧵

Starting with macrocycles and mini-binders. Can't wait for your feedback!

More to come! For requests beyond current platform capabilities: partnerships@latentlabs.com.

We’re making Latent-X available with a free tier for commercial and academic users alike.

We want to get cutting-edge AI into the hands of scientists at big pharma and small labs without needing AI teams or infrastructure.

What excites me most: getting this into the hands of scientists through our no-code platform. Replicates our validated workflows, no AI background required.

And it’s fast — up to 10x faster than prior methods!

Latent-X generates novel binders from scratch, solving the geometric puzzle of binding at the all-atom level while obeying biochemical rules nature follows.

I'm still mesmerized watching the model generate successful binders directly at the atom level — hydrogen bonds included!

Latent-X achieved breakthrough lab results:

Picomolar binding affinities, directly outperforming prior methods in head-to-head validation.

Leading experimental hit rates:
* 91-100% for macrocycles
* 10-64% for mini-binders

Testing 30-100 designs per target vs millions traditionally.

Introducing Latent-X — our all-atom frontier AI model for protein binder design.

State-of-the-art lab performance, widely accessible via the Latent Labs Platform.

Free tier: platform.latentlabs.com
Blog: latentlabs.com/latent-x/
Technical report: tinyurl.com/latent-X

5 months from funding to shipping our first frontier model. Latent-X achieves state-of-the-art hit rates for macrocycles and mini-binders, with picomolar binding affinities — a breakthrough in de novo protein binder design.

Available now on our no-code platform!

Thanks very much, Frank!

Thank you, Jason! It has been awesome to work with you when starting the protein design team at DM and fantastic to see all your work since then :)

It's been great to discuss our work with @hannahkuchler.bsky.social & @melissahei.bsky.social at the @financialtimes.com!

Apply to access our tools or join the team www.latentlabs.com

It is clear protein design has the potential to transform medicine and scientific discovery. I believe Latent Labs will be the team to fully realize its potential. It’s a vast field and there’s so much still to do. Let’s go!

I loved my time at DeepMind working on AlphaFold2 and to be there in Stockholm to watch Demis Hassabis and John Jumper accept the Nobel Prize was incredible.

We’ve built an exceptional founding team – and are hiring in London and San Francisco! Come join the likes of Alex Bridgland (AlphaFold 1, 2 & 3), Annette Obika-Mbatha (multiple DeepMind programs), Dave Yuan (Mammoth Bio) and amazing people from Microsoft, Google, Altos Labs, Stability AI and more.

Our Angels include Google Chief Scientist @jeffdean.bsky.social, Transformer architecture co-inventor and Cohere founder @aidangomez.bsky.social, and ElevenLabs founder Mati Staniszewski.

The funding includes our Series A co-led by Radical Ventures and Sofinnova Partners, with existing investors Pillar VC, Kindred Capital and 8VC participating alongside new investors Isomer Capital and Flying Fish.

Every biotech or pharma company searching for the best therapeutic molecules understands the role AI can play - but not all are in a position to develop their own advanced models. That’s where @latentlabs.bsky.social comes in.

Latent Labs comes out of stealth today with $50M funding. Our goal? To push the frontiers of generative biology, giving partners instant access to tools capable of accelerating drug design