正在加载视频...

视频加载失败

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 次观看 • 1 年前 •via X (Twitter)

32 条评论

Simon Kohl 的头像
Simon Kohl1 年前

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.

Simon Kohl 的头像
Simon Kohl1 年前

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!

Simon Kohl 的头像
Simon Kohl1 年前

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!

Simon Kohl 的头像
Simon Kohl1 年前

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.

Simon Kohl 的头像
Simon Kohl1 年前

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

microRoc 的头像
microRoc1 年前

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

Chaitanya K. Joshi 的头像
Chaitanya K. Joshi1 年前

Congrats team!!

Simon Kohl 的头像
Simon Kohl1 年前

Thank you, Chaitanya!

Charlie Harris 的头像
Charlie Harris1 年前

Congrats Simon!

Simon Kohl 的头像
Simon Kohl1 年前

Thank you, Charlie!

Aidan Gomez 的头像
Aidan Gomez1 年前

Congrats!!

Simon Kohl 的头像
Simon Kohl1 年前

Thank you, Aidan!!

Kentsis Research Group 的头像
Kentsis Research Group1 年前

Great to see joint operation on sequence and structure @CalebLareau

Simon Kohl 的头像
Simon Kohl1 年前

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

Rishabh 的头像
Rishabh1 年前

Awesome stuff, Simon!! 🥳🔥

Simon Kohl 的头像
Simon Kohl1 年前

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

Rishabh 的头像
Rishabh1 年前

Would love to! DM’d :D

Mati Staniszewski 的头像
Mati Staniszewski1 年前

Congratulations - that’s amazing!

Simon Kohl 的头像
Simon Kohl1 年前

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

Mattias Ordboken 的头像
Mattias Ordboken1 年前

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

Tomas Geffner 的头像
Tomas Geffner1 年前

Congrats @saakohl and team!

Simon Kohl 的头像
Simon Kohl1 年前

Thank you Tomas and congrats for La Proteina

Ethan Fast 的头像
Ethan Fast1 年前

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

Russ Wilcox 的头像
Russ Wilcox1 年前

What a massive change is coming for drug discovery

Simon Kohl 的头像
Simon Kohl1 年前

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!

Karsten Kreis 的头像
Karsten Kreis1 年前

Congrats to this strong release, Simon!

Simon Kohl 的头像
Simon Kohl1 年前

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

Gina El Nesr 的头像
Gina El Nesr1 年前

Awesome to see!! Congrats Simon!

Simon Kohl 的头像
Simon Kohl1 年前

Thank you, Gina!

Evgenii 的头像
Evgenii1 年前

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

Javin Oza 的头像
Javin Oza1 年前

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

Simon Kohl 的头像
Simon Kohl1 年前

Thanks for the interest! This model generates new binders.

相关视频