Prescient Design
@PrescientDesign
A @Genentech Accelerator
CDS PhD student @_angie_chen presents LLOME, using LLMs to optimize synthetic sequences with potential applications for drug design. Co-led by @samuel_stanton_ & @nc_frey and with insights from @kchonyc, @RichBonneauNYC, and others at @PrescientDesign. nyudatascience.medium.com/language-model…
Gave my PhD dissertation talk! 🧬 Tried my best to make AI for drug discovery & protein design accessible for ML folks: Beyond lucky & grateful to have had @pabbeel @nc_frey @KevinKaichuang @PrescientDesign @berkeley_ai + many other collaborators & friends on this journey.🎈
We're hiring! 🎉 Join our @PrescientDesign @genentech team in NYC! We're hiring a Principal Software Engineer to lead the development of our flagship AI/ML Lab-in-the-Loop platform for therapeutic molecular design 🧬 Drive impact w/ full-stack skills (esp. front-end) as part of…
We're hiring! Come work with me, @timbitsz, and the fantastic teams @genentech Comp Bio / Disco Onc & @PrescientDesign as a postdoc. Link to apply below 👇
Congratulations to our cofounder @kchonyc for being the recipient of the Glen de Vries Chair of Health Statistics by @nyuniversity and @NYU_Courant!
Kyunghyun Cho (@kchonyc), Professor of Computer Science and Data Science, has been named recipient of the Glen de Vries Chair for Health Statistics by the Courant Institute and New York University. Congratulations!
Lab-in-the-loop therapeutic antibody design At @PrescientDesign @genentech we have spent 3+ years reimagining drug discovery. We built a machine learning system to design and execute experiments. Here's how it works and what we can do 🧵 1/
stay tuned for more proper, detailed and exciting cover of this preprint, but whoa i'm so proud of the team @PrescientDesign and our achievements on <Lab-in-the-loop therapeutic antibody design with deep learning>!
We’ve started a new blog! 🎉 🫡 In the inaugural post,@keunwoochoi, Sr. Principal Scientist and Head of our LM team walks through how to scale model training using Torchdata and its multi-threaded parallelism.
doing any data loading in Torch? i wrote a beginner's guide (as a beginner) to Torchdata 0.10.1, the first version with data Nodes. (cc' @ho_andrew) i already started using it. it's great! this is also @PrescientDesign's first blog post :D medium.com/@prescientdesi…
Protein engineering in low-data regimes with pairwise representations A 🧵on our latest preprint: DyAb predicts binding affinity with high accuracy using as little as 100 training examples and generates designs with > 10x improved binding 1/
Research Intern position @PrescientDesign in Switzerland 🇨🇭💊 join our Frontier Research team in 2025! Apply now or share with anyone who might be interested: roche.wd3.myworkdayjobs.com/roche-ext/job/…
[1/n] Does AlphaFold3 "know" biophysics and the physics of protein folding? Are protein language models (pLMs) learning coevolutionary patterns? You can try to guess the answer to these questions using mechanistic interpretability. But the thing is, more often than not, we know…
1/🧬 Excited to share PLAID, our new approach for co-generating sequence and all-atom protein structures by sampling from the latent space of ESMFold. This requires only sequences during training, which unlocks more data and annotations: bit.ly/plaid-proteins 🧵
we'll also hire 2025 summer interns for LLM product dev @PrescientDesign @genentech. it's taking time for the job description to be out, please feel free to share your resume & short intro to my `[email protected]` in the meantime.
My team at @PrescientDesign is hiring! 🎉 @keunwoochoi, @kchonyc, and I are looking for ML engineers to develop our internal LLMs & foundation models for drug discovery. Feel free to DM or reach out to us at #neurips2024! Link: tinyurl.com/prescient-llm
My team at @PrescientDesign is hiring! 🎉 @keunwoochoi, @kchonyc, and I are looking for ML engineers to develop our internal LLMs & foundation models for drug discovery. Feel free to DM or reach out to us at #neurips2024! Link: tinyurl.com/prescient-llm
Say hi at @emnlpmeeting #EMNLP2024 ! Here in Miami to spread the good word about our job openings, look at tons of posters, and connect with old friends and new :)
we're still hiring fresh phd level MLEs for LLMs. roche.wd3.myworkdayjobs.com/ROG-A2O-GENE/j… as well as slightly seniors (LLMs) roche.wd3.myworkdayjobs.com/en-US/ROG-A2O-… and also infrastructure MLEs roche.wd3.myworkdayjobs.com/en-US/ROG-A2O-…
LLMs are highly constrained biological sequence optimizers. In new work led by @_angie_chen & @samuel_stanton_ , we show how to drive an active learning loop for protein design with an LLM. 1/
Presenting JAMUN: a model that samples conformational diversity of proteins through Langevin dynamics on a learned smoothed learned manifold and denoising to the physical manifold, demonstrating transferability on a dataset of 2AA. This is just the start! arxiv.org/abs/2410.14621