Uri Laserson
@laserson
Followers
1K
Following
1K
Media
23
Statuses
1K
CTO at Patch Bio. Formerly PI @IcahnMountSinai, data science @cloudera, co-founder @gsgenetics, and genomics @geochurch.
New York, NY
Joined February 2009
2/ First, a new antibody discrete diffusion model. We specifically build on EvoDiff (@MSFTResearch) and D3PM to develop a diffusion-based tool for antibody sequence design. This complements Ginkgo’s scalable data product for antibody developability. https://t.co/NoARksYH1w
ai.ginkgo.bio
Generating antibody sequences reflecting natural variability at high resolution
1
6
34
Incredibly excited to share new results from Nabla Bio where we show we can design antibodies de novo for use in therapeutic discovery. We introduce JAM, an AI system we’ve developed to design de novo antibodies with good affinities, early stage developability, and function.
12
61
239
A quick personal update: after 3.5 amazing years at Notion and some time off, I've started a company that's at the intersection of everything I learned at Stripe, Notion, and Google—AI, fintech, productivity, and search. Our small team is growing, and we're looking for founding
17
12
275
Thrilled to share our research on designing better 3' UTRs for mRNA therapeutics and vaccines! By integrating high-throughput stability assays, machine learning models, and mRNA domain expertise, we engineered 3' UTRs that improve mRNA stability and protein production in vivo.
Excited to share our recent work at @Ginkgo . TLDR: high quality mRNA stability data -> performant ML models -> design 3’UTRs that increase stability -> in vivo validated ML 3’UTRs beat benchmark. https://t.co/z7PUAHaHHg
1
2
4
Excited to share our recent work at @Ginkgo . TLDR: high quality mRNA stability data -> performant ML models -> design 3’UTRs that increase stability -> in vivo validated ML 3’UTRs beat benchmark. https://t.co/z7PUAHaHHg
1
7
38
Nice work. A few important quotes "While top convolutional neural network models performed slightly better than top LSTM models, transformers performed worse than both LSTMs and residual convolutional models" 1/
Really excited to share work from our team at @Ginkgo, led by @AlyssaKMorrow, on ML guided 3’ UTR design. https://t.co/XQ997bw5wb It's a great story of dataset generation, model training, generative design, in-vivo validation, and model release. More details in thread!
1
12
68
Really excited to share work from our team at @Ginkgo, led by @AlyssaKMorrow, on ML guided 3’ UTR design. https://t.co/XQ997bw5wb It's a great story of dataset generation, model training, generative design, in-vivo validation, and model release. More details in thread!
biorxiv.org
Using mRNA as a therapeutic has received enormous attention in the last few years, but instability of the molecule remains a hurdle to achieving long-lasting therapeutic levels of protein expression....
5
50
227
https://t.co/QCtOIaybOj Nice benchmark of single cell "foundation models" (scGPT, scFoundation) and GEARS (a GNN model) further hyped as "virtual cell models" against linear baselines on perturbation prediction. Long-story short: they can't beat the linear baselines. 1/
biorxiv.org
Advanced deep-learning methods, such as transformer-based foundation models, promise to learn representations of biology that can be employed to predict in silico the outcome of unseen experiments,...
7
119
488
I’m going to be judging at @Lux_Capital, @EvoscaleAI & @envedabio’s Bio x ML hackathon! Don’t miss out. Apply by Sept 22: https://t.co/lO1Lzq43Yd - open globally.
0
5
32
Big day today at @Ginkgo: we're pulling back the curtain on our proprietary biological foundation models and launching a model API! Our API will support private and open models, and we're pricing it competitively to enable others to build on top of it. Details in 🧵👇
Today, we’re thrilled to announce two exciting launches, powered by our partnership with @googlecloud: our first protein LLM, AA-0, and our new model API, a powerful tool designed to bring biological AI models directly to machine learning scientists. https://t.co/Ku9Cx1gh0M
11
40
266
We've started IND-enabling studies on a small molecule corrector for Rho-associated autosomal dominant retinitis pigmentosa (Rho-adRP). I thought it would be fun to spend some time walking through our approach and why we are excited. Long 🧵1/
25
72
429
OpenFold paper is now out in @naturemethods. Timely. I’ll say more about AF3 at the end of this thread, but first I wanted to highlight what’s new since our initial release. (1/9)
11
262
1K
Is there an AI-powered tool I can converse with to help create a "Figure 1" diagram in Adobe Illustrator?
1
0
1
Reading this made me think that we're only a little bit away from "Can a biologist fix a large language model?"
🛠 New posts on Prompt Engineering: Steer a large pretrained language model to do what you want wo/ updating the model weights. https://t.co/bEw3ZcmDuY Most importantly this just introduces general ideas, but for your own problem, you always need tuning and experimentation.
0
0
1
Is it possible to run a CITE-seq-style assay with a sci-RNA-style protocol? cc @JShendure
0
0
0
Always take the opportunity to go work with @srikosuri!
So @nlarusstone finally gave his notice to leave @OctantBio and start his journey as a founder. We'll miss him, but it also means we are hiring his replacement. More in the 🧵
0
0
9
Taxiing BOS 🛫SFO on a mission to fund a scalable model that accelerates data-intensive science and health research as a public good, via foundational open-source infrastructure and global collaboration. If you know aligned philanthropists, please reach out 🙏. More context in🧵:
But an RSE per lab will not suffice to democratize @DeepMind's powerful engine (dream up experiment by 10, implement by 12, run at scale by 1, think until 5) to all RSEs / CompBios. Rather, I'm thinking a lot about economies of OS scale 🧢 @Convergent_FROs
https://t.co/vrJ4Qtvp3p
7
28
98
So what's going on with the formula shortage?? It's still very difficult to find Nutramigen, for instance.
0
0
0