Aaron Ring

Associate Professor at @FredHutch
Studying cytokines, (auto)antibodies, and cancer immunotherapy
Founder: @SimchaTx, @Seranova, @StippleBio, and @AriaxBio

[Aaron Ring @aaronmring]

T cells do the heavy lifting when it comes to the anti-tumor action of checkpoint immunotherapy. But do antibodies play a role too?

That’s the question @yile_dai looked to answer in his thesis work, out today in @Nature! 🧵below

https://t.co/VgTByRKRCX

[Thomas Hayes @THayes427]

We’re excited to share the full binder design protocol. Check it out here: https://t.co/AtkipkiYtS.

The notebook includes support for @modal to easily scale up binder generation.

Give it a try and let us know how it works!

You can read more about ESMFold2, ESMC, ESM Atlas, and the full results in the paper here: https://t.co/M3rt00pU8Z.

[Aaron Ring @aaronmring]

@lucas_nivon @SylvainGariel Hyped about this

[Aaron Ring @aaronmring]

@MartinPacesa @thermofisher Class action lawsuit may be appropriate

[Aaron Ring @aaronmring]

@SylvainGariel Sorry didn't mean as a correction. ByteDance/Protenix were open source leaders until a few months ago. The team is outstanding, you are spot on with this analysis.

[Alex Rives @alexrives]

Today we're announcing ESMFold2, an open scientific engine to power prediction, design, and discovery across protein biology.

The new model delivers state of the art performance on protein interactions, especially antibodies, a critical modality for therapeutics.

We have designed and validated miniprotein binders and single chain antibodies across five therapeutic targets that are important in cancer and immunology. We are seeing very high success rates, and affinities at levels consistent with therapeutic activity.

We’re also releasing an atlas of 6.8 billion proteins, and 1.1 billion predicted structures.

ESMFold2 is built on a state of the art language model that has been trained on billions of protein sequences.

A world model of protein biology emerges through language modeling.

We’ve used the techniques of mechanistic interpretability developed to understand large language models to understand the concepts ESM uses to represent proteins.

The model’s representation space has a compositional organization of features across scales, levels of complexity, and abstraction, that reflects and mirrors the understanding of protein biology developed through a century of empirical science.

This understanding emerges without prior knowledge, just from language modeling of protein sequences.

Language models are becoming a powerful substrate to understand and program biology.

The design of protein interactions is one of the most fundamental problems in biophysics, and has critical implications for the discovery of new medicines. A simple gradient based search with the model was able to discover high-affinity protein binders.

I'm excited by the potential this has to accelerate basic science and the understanding of proteins. And especially for the new avenues it opens up for therapeutic design and medicine.

[Aaron Ring @aaronmring]

Gene editing is incredible, no one here is doubting that. The issue being raised is equipoise for gene editing in this indication. We already have incredible treatments for lipid lowering that are proven safe in the real world. This approach offers better convenience and compliance, but not better efficacy. So no, I'm not wringing my hands. Just saying I don't feel the need to edit my genes with current tech to lower my cholesterol when I can achieve the same or better with approved drugs. This calculus obviously will change as the tech matures.

[Aaron Ring @aaronmring]

@ladanuzhna PCSK9 biology is not the safety issue that concerns me. Mistakes in somatic genome editing do. Prime editing is better than vanilla crispr but it still induces off-target DNA modifications. You won't see AEs like cancer in a small phase 1 study with short follow up.

[Aaron Ring @aaronmring]

@ladanuzhna @cremieuxrecueil It is annoying that inclisran can't be self injected I agree

[Aaron Ring @aaronmring]

@kansagraMD @HiraSMian @RahulBanerjeeMD @HadidiSamer @rajshekharucms @Rfonsi1 @DrRakeshPopat @bdermanmd Is this seen with CAR-T as well?

[Aaron Ring @aaronmring]

@dgermain21 I don't think we captured this one in our structure paper, but we can toss this antibody into an upcoming reap run sometime in the future.

[Aaron Ring @aaronmring]

@dgermain21 👀

[Aaron Ring @aaronmring]

Another banger from @ChoYehlin !

[Yehlin Cho @ChoYehlin]

🚀 Excited to share our new work: Absolute Stability Predictor!

📊: https://t.co/gtgQjPRAX6

Built the MGnify Stability Dataset (1.8M+ measurements) and developed stability prediction models, together with @grocklin, @KotaroTsuboyama, @sokrypton, and teams.

[Aaron Ring @aaronmring]

@ATinyGreenCell Can you clone as zerg or protoss? This is important to me.

[Aaron Ring @aaronmring]

@design_proteins dude that is lit. Can you post the prompt or create a skill?

[Aaron Ring @aaronmring]

@SamDavisEsq @PearlF @ablT315I @damiangarde For mAbs, "best in class" is usually cope. Look at PD1 for example. They are all virtually the same. First is best in some cases. I agree it's a stretch, but the investor's point is directionally right. Things cost half as much and get done twice as fast in China.

[Aaron Ring @aaronmring]

@SamDavisEsq @PearlF @ablT315I @damiangarde For a vanilla mAb it's reasonable for a tier 1b/tier 2 Chinese CDMO.

[Aaron Ring @aaronmring]

@PearlF @ablT315I @damiangarde Probably referring to using a CRO/CDMO to do the discovery/development work on a new asset, not buying an existing asset.