Jacob Stern

AI scientist @ Absci / deep learning for de novo antibody design

[Jacob Stern @jacobastern]

@therobbieharvey Heartbreaking story.

A bit of good news - we (my company, not me personally) are working on this - targeting Phase 2 trial initiation of ABS-201 for endo late this year, with interim data readout in 2027.

Hopefully endometriosis will be treatable without surgery within a decade

[Perturb.ai @perturbai_tx]

Introducing PerturbAI.

Today we announced our emergence from stealth with the release of the world’s largest in vivo CRISPR data engine, interrogating the effects of thousands of genetic perturbations across 8 million cells throughout the whole brain.

This dataset represents a new category of biological data: organism-level, circuit-resolved causal genomics leading to novel targets and therapeutics.

By combining scalable in vivo CRISPR perturbation with AI, we model biological systems at unprecedented resolution and simulate therapeutic interventions before committing to expensive downstream development.

We’re grateful to our collaborators at @NVIDIAHealth and @10xGenomics for helping make this landmark dataset possible.

Read More: https://t.co/acsEDLr8RL

#CRISPR #AI #DrugDiscovery #FunctionalGenomics #Biotech

[Jacob Stern @jacobastern]

New SOTA on antibody-antigen complex prediction 🔥

[Protenix @ai4s_protenix]

🚀 Introducing Protenix-v1, the first open-source model achieving AF3-level performance

Highlights:
🔹 Verified inference-time scaling behavior
🔹 RNA MSA & protein template support
🔹 Additional release: Protenix-v1-20250630 trained on a larger dataset
🔹 PXMeter v1.0.0 for transparent evaluation (6k+ complexes, time-split & domain-specific subsets)

🔗 Code: https://t.co/b8l3oit9PG
🔗 Eval toolkit: https://t.co/5tAFqKboSV
🔗 Online server: https://t.co/iBGZu9vT92

[Jacob Stern @jacobastern]

https://t.co/hlNGPIdey9

[Jacob Stern @jacobastern]

We are hiring AI scientists with a strong DL background, with experience training diffusion/flow matching models for molecular prediction.

If you are interested in working on an AI team deeply integrated with a wet lab, please apply!

DMs open, listing in the next post 👇

[Amir Shanehsazzadeh @amirshanehsaz]

We @abscibio are excited to share Origin-1, our platform for de novo antibody design! We select "zero-prior" epitopes without guidance from or the availability of solved protein-protein complex structures and, using fewer than 100 designs per target, achieve success against four targets: COL6A3, AZGP1, CHI3L2, and IL36RA.

We validate binding, developability, and function via multiple orthogonal assays and confirm atomic accuracy with Cryo-EM for two targets.

We share detailed methods, including on the models underlying Origin-1, and release our data as a resource for the community.
📄 Read the preprint: https://t.co/bGN6nffuri
📊 Access our data: https://t.co/F4cZvzFV1Z

[Jacob Stern @jacobastern]

Excited to share our recipe for 100-shot de novo antibody design!

- Binders against de novo epitopes
- Cryo-EM structures with atomic fidelity to designs
- Functional potency at 100nm concentration

[Amir Shanehsazzadeh @amirshanehsaz]

We @abscibio are excited to share Origin-1, our platform for de novo antibody design! We select "zero-prior" epitopes without guidance from or the availability of solved protein-protein complex structures and, using fewer than 100 designs per target, achieve success against four targets: COL6A3, AZGP1, CHI3L2, and IL36RA.

We validate binding, developability, and function via multiple orthogonal assays and confirm atomic accuracy with Cryo-EM for two targets.

We share detailed methods, including on the models underlying Origin-1, and release our data as a resource for the community.
📄 Read the preprint: https://t.co/bGN6nffuri
📊 Access our data: https://t.co/F4cZvzFV1Z

[Hannes Stark @HannesStaerk]

Excited to release BoltzGen which brings SOTA folding performance to binder design! The best part of this project has been collaborating with many leading biologists who tested BoltzGen at an unprecedented scale, showing success on many novel targets and pushing its limits! 🧵..

[Sean McClain @SeanRMcClain]

Hair isn’t just about appearance — it’s about identity.

For many, hair loss affects confidence and how we show up in the world. That’s why I’m proud of what our @abscibio team is doing with ABS-201, our AI-designed biologic now preparing for first-in-human trials in Australia 🇦🇺

ABS-201 targets the prolactin receptor to reactivate dormant follicles — a potential once-quarterly injection that we believe will offer an alternative to daily pills or topicals.

Built in ~24 months using our gen AI drug design platform, it shows what’s possible when we design new biologics with speed, precision, and purpose.

Grateful to collaborate with Drs. Anthony Rossi, David Goldberg, Rodney Sinclair, and Prof. Ralf Paus — their expertise has been instrumental.

Read more about the science behind ABS-201 in Popular Mechanics 👇 https://t.co/GE5AxJ7mpC

[Sean McClain @SeanRMcClain]

Love the question @pmarca. Thick, dark hair regrowth in monkeys and mice👇

ABS-201 human interim efficacy readout expected next year. Hair’s next big moment 🛰️

@elonmusk @davidasinclair @abscibio $absi

[Jacob Stern @jacobastern]

@JacobAShell This is my favorite weird map.

The longer you look at it the more questions you have...

[Jacob Stern @jacobastern]

Where can I find the version of X with

1. no images
2. no videos

All I want is an idea-dense feed on a soothing black background

[Jacob Stern @jacobastern]

@Austen You made a comment a few weeks ago about the mortgage interest deduction that we missed when filing.

We amended and you saved me $10k.

[Jacob Stern @jacobastern]

Thanks to the great work of my collaborators Dennis Della Corta, Siba Alharbi, Anandsukeerthi Sandholu, and Stefan Arold, who turned a fun computational idea into compelling experimental results!

[Jacob Stern @jacobastern]

Excited to share some new work (@ ICLR GemBio)!

🧪Conformation-specific protein design 🧪

Many protein sequences are known to be "promiscuous" - they fold to multiple structures. How do we design a variant with high preference to a certain state?

[Jacob Stern @jacobastern]

There are many potential extensions of this idea (think: allosteric protein design!).

Feel free to stop by and chat by our poster at the ICLR GemBio workshop today.

Paper:
https://t.co/4STwc8IPvL…

Code:
https://t.co/6lVupo7b3W
https://t.co/YIbZPQXoUK