David Dangond

@davedangond

AI + Drug Discovery. Member of Technical Staff @OracleHealth. B.S. Bioengineering @ucberkeley. Author of http://sprintome.com. Opinions are my own.

New York, NY

Joined January 2013

204Following

71Followers

Pinned

David Dangond@davedangond · Jun 16

1,000x faster. Boltz‑2 makes folding and affinity prediction fast and affordable. A real alternative to traditional FEP simulations for drug discovery. 👏 @GabriCorso @jeremyWohlwend @AIHealthMIT @RecursionPharma ⚡️Read the full breakdown: open.substack.com/pub/sprintome/…

davedangond's tweet image. 1,000x faster.

Boltz‑2 makes folding and affinity prediction fast and affordable. A real alternative to traditional FEP simulations for drug discovery.

👏 @GabriCorso @jeremyWohlwend @AIHealthMIT @RecursionPharma

⚡️Read the full breakdown:
open.substack.com/pub/sprintome/…

173

12.0K

David Dangond Retweeted

Kexin Huang@KexinHuang5 · Jul 4

🤝Excited to announce @ProjectBiomni × @AnthropicAI! AI agents are set to transform how biologists do everyday research. Thanks to this partnership, the platform is now free for scientists worldwide: biomni.stanford.edu Learn more: anthropic.com/customers/biom…

422

218

40.0K

David Dangond@davedangond · Jun 30

The past few years of "AI for life sciences" has been all about the models: AF3, NNPs, PLMs, binder generation, docking, co-folding, ADMET, &c. But Chai-2, and lots of related work, shows us that the vibes are shifting. Models themselves are becoming just a building block; the…

AAri Wagen@AriWagen · Jun 30

What is Chai-2? It is a "series of models." This includes a "multimodal generative architecture, integrating all-atom structure prediction and generative modeling" (to me this sounds like AF3 and their earlier Chai-1). The release is a bit vague; this graphic is the best info:

201

172

24.0K

David Dangond@davedangond · Jun 30

I've been working on variants of this problem for my entire career, and have only dreamed of designing molecules on the computer with success rates this high. Proud of @chaidiscovery for pulling this off, and doing it with the speed, rigor and grace that was only imaginable ✨

CChai Discovery@chaidiscovery · Jun 30

We’re excited to introduce Chai-2, a major breakthrough in molecular design. Chai-2 enables zero-shot antibody discovery in a 24-well plate, exceeding previous SOTA by >100x. Thread👇

227

32.0K

David Dangond Retweeted

vittorio@IterIntellectus · Jun 25

holy shit, it’s here! deepmind just released AlphaGenome. an AI model that reads 1 million bases of DNA and predicts how any mutation changes molecular function not just in single genes but across the entire regulatory genome. DNA is code, and you are software 1/

210

960

6.0K

4.0K

714.0K

David Dangond Retweeted

Gabriele Corso@GabriCorso · Jun 6

Excited to unveil Boltz-2, our new model capable not only of predicting structures but also binding affinities! Boltz-2 is the first AI model to approach the performance of FEP simulations while being more than 1000x faster! All open-sourced under MIT license! A thread… 🤗🚀

417

2.0K

807

295.0K

David Dangond Retweeted

Sprintome@sprintome · May 25

@Vant_AI and @BlueprintMeds are revising their partnership to tackle "historically undruggable targets," citing the use of Neo-1, VantAI's foundation model, as key to the partnership. The deal includes up to $1.67 Billion in future milestone payments. So what is Neo-1? 🧵

128

David Dangond Retweeted

Sprintome@sprintome · May 17

The Biotech 'DeepSeek' moment? China’s DeepSeek moment in biotech is already here, says Simone Song, founder at Hong Kong-based VC firm ORI Capital. 🧶

127

David Dangond Retweeted

Sprintome@sprintome · May 12

H-optimus-1 now on AWS Marketplace means faster, secure deployment of cutting-edge pathology AI for *all* organizations, commercial and academic 🌍.

115

David Dangond@davedangond · May 6

We're launching an agent that can do bioinformatics analysis, including repeating analysis from research papers. It is multimodal and results in a complete jupyter notebook (python or R) that ends in a concrete conclusion. Starting with closed-beta now

SSam Rodriques@SGRodriques · May 6

Introducing Finch, a new agent that fully automates data-driven discovery in biology. We are launching a closed beta for it today (sign up below). This is still early, but impressive, maybe similar to a good 1st yr grad student. In the video, see how it independently reproduces…

426

313

32.0K

David Dangond@davedangond · May 6

Increasing model size from 339M to 46B parameters enables models to grasp core 'protein grammar,' leading to higher-quality sequences that pass more rigorous filters. Size matters! More parameters = better foundational understanding in protein design.

SSprintome@sprintome · May 6

📖 Don't miss it: open.substack.com/pub/sprintome/…

David Dangond@davedangond · May 6

My new post exploring Protein Language Models + Scaling Laws in Biology. If you're interested in what @ProfluentBio accomplished with this paper, or simply want to understand more about what a protein language model is -- I suggest to take a read! open.substack.com/pub/sprintome/…

SSprintome@sprintome · May 6

Just dropped “The Protein Language Model: Bigger = Better?” — a quick dive into ProGen 3, scaling laws & alignment magic. Massive kudos to the crew at @ProfluentBio— @thisismadani, @jeffruffolo, @AadyotB & co.—for turning AI horsepower into real proteins. 🧬🤖

188