Sabitlenmiş Tweet
We're stil writing the @ManifoldBio story, but @ElliotHershberg just dropped a fantastic piece capturing the journey so far on his blog Century of Biology.
English
Gleb Kuznetsov
550 posts
Gleb Kuznetsov
@glebkuz
Co-Founder and CEO @ManifoldBio // in vivo-centric AI-guided drug design
Boston, MA Katılım Aralık 2008
417 Takip Edilen2.2K Takipçiler
Gleb Kuznetsov retweetledi
If you're at #ADPD2026, don't miss Naveen Mehta’s talk on @ManifoldBio’s approach to one of the core challenges in treating neurodegenerative diseases: getting drugs across the blood-brain barrier.
English
For those trying to follow Nvidia GTC from home and curious about the vibe on the ground, the vibe:
English
Gleb Kuznetsov retweetledi
Gleb Kuznetsov retweetledi
The proteinologist community trying to follow up on the papers of
OpenFold3
x.com/MoAlQuraishi/s…
31M complexes added to the AlphaFold DB
x.com/pushmeet/statu…
Proteina-Complexa testing 1M binders in the lab
x.com/DidiKieran/sta…
x.com/ManifoldBio/st…
GIF
Manifold Bio@ManifoldBio
@ManifoldBio and @NVIDIAHealth announce a joint study validating Proteina-Complexa, NVIDIA's latest BioNeMo model for protein binder design.
English
Behold the power of massively parallel multiplexing @ManifoldBio brought to this study
Kieran Didi@DidiKieran
@ManifoldBio @viva_biotech @novonordisk @Cambridge_Uni @DukeU @LMU_Muenchen Massive campaign: ~1M designed candidates screened across 127 diverse/challenging targets with all-to-all binding readouts. We solve more than 2/3 of the targets given a very limited compute budget and often quite challenging hotspots and crops 11/n
English
Gleb Kuznetsov retweetledi
🔸 Now experimental results. We conducted a massive campaign in collaboration with @ManifoldBio, @viva_biotech, @novonordisk, @Cambridge_Uni, @DukeU, @LMU_Muenchen.
🧬 "Latent Generative Search unlocks de novo Design of Untapped Biomolecular Interactions at Scale."
(10/n)
English
Gleb Kuznetsov retweetledi
📢📢 Proteina-Complexa 📢📢
Atomistic Binder Design with Generative Pretraining and Test-Time Compute + Experimental Validation at Scale
⭐️ Project page (research.nvidia.com/labs/genair/pr…) for:
📜 Method paper (ICLR 2026 Oral)
🧬 Wet lab paper
🛠️ Code & models
📁 Data
🧵 Thread
(1/n)
English
Gleb Kuznetsov retweetledi
Really great collaboration between @ManifoldBio and @nvidia to test 1M de novo designed binders against 127 targets, measuring over 100 million potential protein-protein interactions! This was a great collaboration with some very exciting results. NVIDIA's new Proteina-Complexa method is SOTA for de novo minibinder design. If you're interested in designing minibinders to targets you couldn't hit with other methods, try it out!
I'm particularly excited about what this large scale data enables. As we generate 1000s of experimentally validated structures, this data becomes the input to training new protein design models. At Manifold, we are generating datasets of this size continuously, and have experimentally validated thousands of de novo designed binders across many formats (VHH, minibinders, peptides, etc). New models will open up new hard to hit targets, paired with our large scale in vivo measurement, will enable us to create previously impossible therapeutics.
Up next is training new models on this and other data we have generated, stay tuned! And thanks to NVIDIA for setting up such a great collaboration, its been fun and fruitful!
Christian Dallago@sacdallago
🧵 We ran the largest head-to-head benchmark of protein binder design methods in the wet lab. Project page: research.nvidia.com/labs/genair/pr… 1 million designs. 127 targets. RFdiffusion, BindCraft, BoltzGen, and Proteina-Complexa — all tested side by side.👇
English
Gleb Kuznetsov retweetledi
"AI drug development" needs a real-world reinforcement learning (RL) loop, like @ManifoldBio enables.
This is how you get LLM & world models that work. Paving the path to true zero-shot clinical design.
Great job @GlebKuz, @PierceOgdenJ & Team!
Gleb Kuznetsov@glebkuz
Just announced our joint study with @NVIDIAHealth running a million molecule benchmark of AI-designed proteins for Nvidia's new model Protein-Complexa. Here we brought our massively multiplexed all-against-all AI binder testing platform that has been core to progressing our own protein design model mBER. The key to advancing protein design models beyond what's possible from public data is experiment scale that can match the scale of generative AI. Together we were able to show some quite fantastic results with a 68% hit rate for Protein-Complexa. More designs generated and more designs tested is better (when you can do it efficiently).
English
Check out the Nvidia + Manifold paper here: research.nvidia.com/labs/genair/pr…
English
Just announced our joint study with @NVIDIAHealth running a million molecule benchmark of AI-designed proteins for Nvidia's new model Protein-Complexa.
Here we brought our massively multiplexed all-against-all AI binder testing platform that has been core to progressing our own protein design model mBER.
The key to advancing protein design models beyond what's possible from public data is experiment scale that can match the scale of generative AI.
Together we were able to show some quite fantastic results with a 68% hit rate for Protein-Complexa.
More designs generated and more designs tested is better (when you can do it efficiently).
Manifold Bio@ManifoldBio
@ManifoldBio and @NVIDIAHealth announce a joint study validating Proteina-Complexa, NVIDIA's latest BioNeMo model for protein binder design.
English
I'll be in town for GTC next week. We continue to scale up our protein design (#mBER) and model training. We're also expanding the AI team. Looking forward to seeing folks there.
Manifold Bio@ManifoldBio
We're heading to @NVIDIA GTC! 🤖 Come find us in San Jose, March 16–19. @glebkuz and @slofgren will be on the ground and would love to connect. DM Gleb or Shane to set up a time to talk. See you there!
English
We're growing the AI team at @ManifoldBio, starting with a role to train protein foundation models on our proprietary data.
I believe Manifold is the most interesting place to work on protein design. We're designing and testing millions of binders per month, including in vivo, and accelerating. No one else has data like this.
If you have deep experience pretraining or fine-tuning protein models and want to work somewhere the data actually lets you push beyond what public datasets can enable, please reach out.
English
Gleb Kuznetsov retweetledi
We believe Cursor discovered a novel solution to Problem Six of the First Proof challenge, a set of math research problems that approximate the work of Stanford, MIT, Berkeley academics. Cursor's solution yields stronger results than the official, human-written solution.
Notably, we used the same harness that built a browser from scratch a few weeks ago. It ran fully autonomously, without nudging or hints, for four days.
This suggests that our technique for scaling agent coordination might generalize beyond coding.
English
Strongly endorse the team at @TriatomicCap and their epic portfolio coming into focus.
@jhuber and team recognized the potential of @ManifoldBio ...well before it was obvious with our massive $2B deal with Roche.
Jeff Huber 🇺🇸@jhuber
Nominating a rising star – Triatomic Capital (@TriatomicCap) Awesome Fund I next-gen compute, deeptech & engineered-biology portcos: . @MatXComputing . @dMatrix_AI . @EdisonSci . @ManifoldBio . @chalk . @ChemifyX . @iPronics . @efficient_hq . @gimletlabs . @axiommathai . @coworkerapp . @ElegenBio . @atumworks . @dimensionalos . @LytenInc + more announced soon ... and Fund II in-flight. :)
English
Gleb Kuznetsov retweetledi
#AI can generate millions of drug candidates. But if you can only test a handful in vivo, you’d still hit a bottleneck.
@ManifoldBio CEO @glebkuz explains how screening hundreds of thousands of antibody designs per animal (including 587,000 in a single non-human primate) changes what’s possible in drug discovery.
On #Transcribed, he talks about the “dark art of multiplexing,” AI, and how the intersection of these technologies is redefining what “scale” means in biology.
English
@agupta It's a well known fact that California drivers are the worst and waymo is largely deployed throughout so the meme doesn't make sense already.
English
“I’ll trust waymo when they can handle <city with nothing special about it>” is a meme I’m hoping finally dies this year.
No your city’s local drivers aren’t worse, no your city grid isn’t more complicated, and no your roads aren’t worse.
English
Presented how @ManifoldBio does rapid in vivo iteration at the aptly named "Rapid In Vivo Iteration" event in SF hosted by @shelbynewsad and @CompoundVC
English