Eli Weinstein

We further validated LIDS on protein language model (PLM) oracles in silico. It is very fast. Here, LIDS can find the optimum in 2 experimental rounds (median), while individual synthesis alternatives need an order of magnitude more experiments.

Very excited for my first PhD student’s first preprint. We’re bringing generative model-controlled stochastic synthesis beyond DNA and into new areas of chemistry, without the need for barcoding or sequencing-based readouts.

Introducing: continuous variational synthesis 📄 jurabio.com/s/cvs.pdf We’re pleased to announce a new advance in our ability to synthesize generative model-designed DNA sequences at petascale.

On model ablations: Linear models plateau on this data (dashed), even with foundation model representations (colors). We needed big transformers (solid) to scale.

Very excited about our new results, showing variational synthesis + large scale screens + co-designed training -> robust scaling laws for sequence-activity models.

We are hiring at @jura.bsky.social both on the ML team (worldwide) and the wetlab team (Boston). Please get in touch if you've been thinking about it. ⏩ careers@jurabio.com

variational synthesis is now published, with the addition of large functional studies. we've now scaled the assays further, to train massive sequence-activity models www.jurabio.com/blog/scaling...

Ever wondered what it'd be like to run a de novo antibody campaign against 100 of the hardest targets, simultaneously, with 76% success rate, and have the complete wetlab validated results days from the project's start? We show you what that looks like, too: www.jurabio.com/mesa

Prediction is overhead when verification is cheap. We've spent years building a system where verification is cheap -- generationally so. This changes the logic of discovery in ways that are easy to underestimate. I tried to write a little about what that means: www.jurabio.com/blog/onebill...

We are at the #StartupVillage at #EurIPS today — come say hi 👋 @jura.bsky.social

Today we're releasing a technical blogpost on LIFT, a system that increases the information density of wetlab experiments by orders of magnitude without requiring more cells, more reagents, or more sequencing.

Applications are open for the @crg_eu PhD Programme! 20 fully funded positions — including one in our group through the Evolutionary Medical Genomics ITN. Join us to develop deep generative models of cross-species data to tackle open questions in disease genetics. www.crg.eu/en/content/t...

For every Nobel that goes to a criminally under-recognized woman scientist (Brunkow, Karikó), or fails to go (Candy Lee), a week of mourning and reform for an academic system wherein you can do Nobel-prize-worthy-work and still end up without a conceivable path to being a professor.

You can read more in our post at www.jurabio.com/blog/leavs; preprint forthcoming. @jura.bsky.social @eliweinstein.bsky.social @mgollub.bsky.social @highvariance.bsky.social

I'm looking for my first PhD student! We will push the frontiers of probabilistic machine learning for the molecular sciences, and study how to design new algorithms that exploit the unique properties of molecular systems to learn about the world. efzu.fa.em2.oraclecloud.com/hcmUI/Candid...

So excited about this - we did iterative generative design at large scale with variational synthesis, and got human scFv candidates against some of the hardest therapeutic targets around.

🔊 The call for the first round of open PhD fellowships from the newly formed Danish Advanced Research Academy (DARA) has just been announced: daracademy.dk/fellowship/f... Exceptional candidates with a strong background in theoretical chemistry are more than welcome to reach out to me for support.

We can make population genetics studies more powerful by building priors of variant effect size from features like binding. But we’ve been stuck on linear models! We introduce DeepWAS to learn deep priors on millions of variants! #ICML2025 Andres Potapczynski, @andrewgwils.bsky.social 1/7

The BayesComp workshop on 'Bayesian Computation and Inference with Misspecified Models' will take place in Singapore on the 16-17th June. We have an open call for posters/contributed calls, with a deadline on the 1st May. More details on the website: postbayes.github.io/BayesMisspec...

This Thursday, 1PM, @eweinstein.bsky.social is headed back to CMU, this time to the Machine Learning Department. He'll be sharing his work on hierarchical causal models. If you're on campus, I encourage to you check it out! www.ml.cmu.edu/calendar/

Tomorrow -- another chance to learn about variational synthesis, probabilistic experimental design methods, & ways to capture scaled functional data for model training: this time with zoom access for those of you remote, 1pm at @cmu.edu Computer Science. Details at: www.cs.cmu.edu/calendar/181...

Today at UPenn's CIS Seminar: a chance to hear about variational synthesis, probabilistic experimental design methods, and ways to capture modern ML-scale functional data for biology: events.seas.upenn.edu/event/13596/

1/n I'm thrilled to share *Deep generative modelling of the human proteome reveals over a hundred novel genes involved in rare genetic disorders* t.co/DoN4DrSFbS from a wonderful collaboration between the Marks Lab and Dias and Frazer group, with @roseorenbuch as lead! 🧵:

The news came out! Last week we signed a deal with the fantastic team at Replay Bio and their product company Syena to develop a KRAS G12D specific therapeutic TCR therapy. So proud and excited! www.businesswire.com/news/home/20...