Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

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: Blog: Technical report:

57,495 Aufrufe • vor 1 Jahr •via X (Twitter)

32 Kommentare

Profilbild von Simon Kohl
Simon Kohlvor 1 Jahr

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.

Profilbild von Simon Kohl
Simon Kohlvor 1 Jahr

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!

Profilbild von Simon Kohl
Simon Kohlvor 1 Jahr

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!

Profilbild von Simon Kohl
Simon Kohlvor 1 Jahr

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.

Profilbild von Simon Kohl
Simon Kohlvor 1 Jahr

Starting with macrocycles and mini-binders. Can't wait for your feedback! More to come! For requests beyond current platform capabilities: [email protected].

Profilbild von microRoc
microRocvor 1 Jahr

@razoralign Want to say a word or two about your user agreement?

Profilbild von Chaitanya K. Joshi
Chaitanya K. Joshivor 1 Jahr

Congrats team!!

Profilbild von Simon Kohl
Simon Kohlvor 1 Jahr

Thank you, Chaitanya!

Profilbild von Charlie Harris
Charlie Harrisvor 1 Jahr

Congrats Simon!

Profilbild von Simon Kohl
Simon Kohlvor 1 Jahr

Thank you, Charlie!

Profilbild von Aidan Gomez
Aidan Gomezvor 1 Jahr

Congrats!!

Profilbild von Simon Kohl
Simon Kohlvor 1 Jahr

Thank you, Aidan!!

Profilbild von Kentsis Research Group
Kentsis Research Groupvor 1 Jahr

Great to see joint operation on sequence and structure @CalebLareau

Profilbild von Simon Kohl
Simon Kohlvor 1 Jahr

@CalebLareau Thank you, looking forward to having you try the model!

Profilbild von Rishabh
Rishabhvor 1 Jahr

Awesome stuff, Simon!! 🥳🔥

Profilbild von Simon Kohl
Simon Kohlvor 1 Jahr

Thank you Rishabh! It would be great to get your feedback on the platform!

Profilbild von Rishabh
Rishabhvor 1 Jahr

Would love to! DM’d :D

Profilbild von Mati Staniszewski
Mati Staniszewskivor 1 Jahr

Congratulations - that’s amazing!

Profilbild von Simon Kohl
Simon Kohlvor 1 Jahr

Thank you Mati - it’s fantastic to have you on board!

Profilbild von Mattias Ordboken
Mattias Ordbokenvor 1 Jahr

@saakohl Awesome work and business model - congratulations. When will we see models further downstream, e.g. ADME?

Profilbild von Tomas Geffner
Tomas Geffnervor 1 Jahr

Congrats @saakohl and team!

Profilbild von Simon Kohl
Simon Kohlvor 1 Jahr

Thank you Tomas and congrats for La Proteina

Profilbild von Ethan Fast
Ethan Fastvor 1 Jahr

congrats on the launch, very exciting! just filled out your interest form, we'd love to give the model a try

Profilbild von Russ Wilcox
Russ Wilcoxvor 1 Jahr

What a massive change is coming for drug discovery

Profilbild von Simon Kohl
Simon Kohlvor 1 Jahr

Thank you @Russ_Wilcox, and thanks for being onboard from the start! We can't wait to see what our partners and users are achieving with it!

Profilbild von Karsten Kreis
Karsten Kreisvor 1 Jahr

Congrats to this strong release, Simon!

Profilbild von Simon Kohl
Simon Kohlvor 1 Jahr

Thank you Karsten, really appreciate it! Congrats on La Proteina as well!

Profilbild von Gina El Nesr
Gina El Nesrvor 1 Jahr

Awesome to see!! Congrats Simon!

Profilbild von Simon Kohl
Simon Kohlvor 1 Jahr

Thank you, Gina!

Profilbild von Evgenii
Evgeniivor 1 Jahr

Looks neat! Why you didn't validate the structures? These binders look small enough to be tested by NMR or X-rays.

Profilbild von Javin Oza
Javin Ozavor 1 Jahr

Does it only generate new binders or Is it possible to do 'affinity maturation' if a know binding pair is provided?

Profilbild von Simon Kohl
Simon Kohlvor 1 Jahr

Thanks for the interest! This model generates new binders.

Ähnliche Videos