Phil Leung

cofounder @Xaira_Thera | formerly @UWProteinDesign

[Phil Leung @proleu]

My doctoral advisor @UWMolES / @UWproteindesign (and current scientific advisory board membe @Xaira_Thera) David Baker won the nobel prize!! So stoked and extremely determined to deliver on the promise of this tech! https://t.co/jWl7ExL9uy

[Phil Leung @proleu]

@DdelAlamo Le ddg have arrived (it never left)

[Phil Leung @proleu]

Gonna start rating random proteins today we have "major vault protein". TLDR: S tier 10/10 protein
- Literally MVP
- D39 symmetry is giving main character energy
- Doesn't just look cool, also does useful stuff (a bonus imo)
- If there was a @ContainerStore for proteins it would probably be available there

[News from Science @NewsfromScience]

Leonard Rome’s lab discovered an odd, abundant component of cells in the 1980s—and he’s still trying to figure out what it does.

Learn more: https://t.co/IeKolH7PK9 #ScienceMagArchives

[Phil Leung @proleu]

@anthonygitter I read this as just a hard subset of this benchmark, which is often reported for protein language modeling papers: https://t.co/djFroZ3Zho

General LLMs are starting to get close to pLMs

[Phil Leung @proleu]

Protein design is such a great way to evaluate agent capabilities over a complicated long horizon task, especially if you have lab feedback.

[Nathan C. Frey @nc_frey]

Today, we’re announcing Claude Opus 5. Opus 5 is now our most capable generally available model for biology and chemistry. It shows better performance than Opus 4.8 on all of our bio evals, and is especially good at organic chemistry and protein design.

Opus 5 feels smarter than any previous Opus-class model on biology and drug discovery, and is great as a daily driver for hours-long research tasks.

[Phil Leung @proleu]

It's really cool to see some of these recent papers from @davidrliu lab and Doudna lab using generative models for protein sequence design (a.k.a. "inverse-folding" AI models) in combination with evolutionary insights and techniques.

In the Liu lab paper, https://t.co/KDdhqzclUd they used proteinMPNN (my beloved) to improve important properties like thermostability and expression, and enhance enzymatic activities for proteases. Critically, they redesigned regions were not allowed to touch the active site so the mutations are expected to improve the structural stability of the overall fold. They did this to "polish" evolutionary starting points and also to seed laboratory evolution trajectories. Both approaches improved nontrivially on what would have been sampled through evolution alone.

In the Doudna lab paper, https://t.co/OhEjirSSvx they used ESM-IF1 to make a synthetic Cas12 variant with improved activity compared to the native. Critically, they avoid mutating the most evolutionarily conserved positions. They suggest the structure structure aware ESM-IF is able to explore much more diverse areas of sequence space than standard sequence-only pLMs.

In both of these cases, generative models for protein sequence design added genuine value when combined with expert scientific intuition on which problems to apply them to and how to configure ("prompt") them.

These papers coming out is kind of a full circle moment for me; I worked on this older paper, https://t.co/VdSwuw4FJR with Doudna on Cas12a which is the same Cas family they chose to make a synthetic version of, right before I went to @UWproteindesign and got to help with proteinMPNN.

Congrats to the authors

@NicholasKrasnow et al. and

@PetrSkopintsev @isabelesain @evandeturk et al.

#ProteinDesign #CRISPR #ArtificialIntelligence

[Phil Leung @proleu]

@RegenbaumShaun @biospace @Xaira_Thera clinical trials take a long time 😭

[Phil Leung @proleu]

Great article from @biospace about our thinking on pharma deals here at @Xaira_Thera . From the beginning we've focused on solving hard problems in AI drug design, excited to see what the next few years hold: https://t.co/av8L4HWbOa

[Phil Leung @proleu]

@anindyadeeps Distillation sets matter 👀

[Phil Leung @proleu]

@meawoppl Claude abuse 😭😂

[Phil Leung @proleu]

A colleague of mine posted this great short read from @ScottWRobinson

I've felt similarly for the last several months. As 🤖 for codegen becomes the norm it's increasingly important to adhere to best implementation practices and tidy patterns, LLMs tend to elevate or drop to the level of the context they see in the codebase there working in:

https://t.co/8GDfsGUsUV

[Magnus Bauer @kinasekid]

Can we program a kinase like a switch? Inspired by natural autoinhibitory complexes, we designed miniproteins against active- and inactive-like conformations of Focal Adhesion Kinase. Depending on the targeted state, the resulting binders either activated or inhibited the kinase.

[Phil Leung @proleu]

Glad to see our antibody design paper finally out in @Nature (and congrats to lead authors and everyone involved )!
At @Xaira_Thera we are excited about pushing antibody design further to bind harder targets and make drugs for unmet medical needs.
Paper:
https://t.co/h2bXGOvuGW

[Phil Leung @proleu]

Congrats @adam_broerman @FloPraetorius @UWproteindesign and team!

[Phil Leung @proleu]

Showcase of #proteindesign possibilities+why they matter!
- minibinders (rigid fusions; composability with other denovo designs)
- tunable biophysical properties (modulate k_off, flexibility, strain)
- #crispyshifty hinges (allosteric control of binding kinetics to native target)

[Adam Broerman @adam_broerman]

We sought to make proteins both potent and FAST. We used #proteindesign to design precise control over protein interaction lifetimes, enabling us to construct rapid-response circuits, biosensors, and switchable cytokines. Now published @Nature! Links to paper and tutorial below.

[Jeff Nivala @jeffnivala]

We searched for Bigfoot using CRISPR. DNA storage meets CRISPR search: AI maps the data, Cas9 slices it, nanopores read it. Multiplexed molecular search with semantic retrieval across a database of DNA-encoded images. Off-targets = a feature, not a bug. https://t.co/l7FLfxnBPL

[Susana Vazquez Torres @SusanaVazTor]

Thrilled to share our latest publication in Nature: https://t.co/GDbQL0fUIO. This work reflects a fantastic collaboration—special thanks to David Baker and @TimothyPJenkins. Hoping it sparks attention to this neglected health issue and drives solutions in the years ahead!

[Phil Leung @proleu]

Bonus Flo reunion pic! @FloPraetorius

[Phil Leung @proleu]

What an immense privilege to celebrate the #NobelPrize with David, former colleagues from @UWproteindesign , current colleagues at @Xaira_Thera and @RosettaCommons family!

[Phil Leung @proleu]

So cool to see #CrispyShifty hinges applied this way! Congrats @adam_broerman

[Adam Broerman @adam_broerman]

Excited to announce our new #proteindesign strategy for allosterically controlling the kinetics of protein-protein interactions! Read on for cool applications in cytokine signaling, biosensing, and protein circuits. https://t.co/jBIHq10Ykd

[Adam Broerman @adam_broerman]

Excited to announce our new #proteindesign strategy for allosterically controlling the kinetics of protein-protein interactions! Read on for cool applications in cytokine signaling, biosensing, and protein circuits. https://t.co/jBIHq10Ykd