Aaron Greenblatt, PhD

RFdiffusion2 now available! Atomic-level scaffolding for complex active sites Try it out on Tamarind Bio now: https://lnkd.in/ghapF6ak RFdiffusion2 shows state-of-the-art atomic-level scaffolding that generalizes to complex, multi-island active sites, and it reliably yields active enzymes with modest screening, though activities are still below the best native enzymes and should improve with richer theozymes and sequence/pocket co-design. In a curated benchmark of 41 Atomic Motif Enzyme benchmark spanning EC 1–5 with ligands and atomic constraints. RFdiffusion2 produced at least one success for 41/41 cases vs 16/41 for prior RFdiffusion. Where success is defined as catalytic-atom heavy-atom RMSD <1.5 Å in prediction and no ligand clashes. RFdiffusion2 is a generative model that directly scaffolds atomic active-site descriptions (theozymes) without pre-specifying residue indices or side-chain rotamers. It can infer indices and rotamers jointly, control ligand burial via per-atom RASA labels, steer pocket orientation with an ORI pseudo-atom, and complete partial ligands during generation. Disclaimer: The code released by the authors is still early, we will be updating as changes are made. Movie credit: Institute for Protein Design, University of Washington —————— Tamarind Bio is the leading library of the best molecular design tools, including RFdiffusion2, AlphaFold, Boltz, and hundreds more!

538

7 Comments

NVIDIA CEO Jensen Huang: “I really discourage 1-on-1s” Jensen famously has 60 direct reports. When Stripe founder Patrick Collison points out that this isn’t conventionally considered best practice, Jensen shares his reasoning: “I don’t do 1-on-1s, and almost everything I say, I say to everybody all the time. I don’t really believe there’s any information that I operate on that only one or two people should hear about… I believe that when you give everybody equal access to information, that empowers people. And so that’s number one… Number two, if the CEO’s direct staff is 60 people, the number of layers you’ve removed in a company is probably something like seven.” Patrick offers to steal man the other side of the argument: “1-on-1s are where you provide coaching, where you maybe talk through personal goals and career advancement, where maybe you give feedback on something that you see somebody systematically not doing so well… Do you not do those things or do you do them in a different way?” Jensen responds: “I give you feedback right there in front of everybody. In fact, this is a really big deal. First of all, feedback is learning. For what reason are you the only person who should learn this?… We should all learn from that opportunity… Half the time I’m not right, but for me to reason through it in front of everybody helps everybody learn how to reason through it. The problem I have with 1-on-1s and taking feedback aside is you deprive a whole bunch of people that same learning. Learning from other people’s mistakes is the best way to learn.” I broke down the full operating mindset Jensen Huang chose to build NVIDIA, and the price he paid to make it last. Full breakdown here 👇 https://lnkd.in/ePbQi9ig

33

1 Comment

I was listening to this https://lnkd.in/giycVEkG and had a thought I can't shake: What if foundation models are AI's genetic code? DNA gives us instincts... babies cry, calves walk to milk without learning. Foundation models feel similar: pre-loaded with language and reasoning. But evolution doesn't create one perfect organism. It creates fish, mammals, birds... each specialized. Maybe AI works the same way? Not one AGI, but multiple species and individuals that learn and evolve. If foundation models are our "genetic code"... we need to be careful what we embed there. These become instincts for all future AI. Like Sutton says, learning is fundamental and the next crucial piece: how do we take what AI systems learn and feed it back to the next generation? In biology, successful traits get passed down... what's the AI equivalent? Maybe we're not just building better AI... maybe we're designing artificial evolution.

11