DrORourke

Neurosurgeon-Scientist at UPenn. Director, Glioblastoma Translational Center of Excellence, Abramson Cancer Center. Innovator. Working to cure brain cancer.

[DrORourke @DrORourke2]

This is absurdly naive - biology “programmable” - Biology has variables we don’t even yet fully appreciate. All these simulations will require in vivo validation no matter how good AI gets

[Jon Hernandez @JonhernandezIA]

“Once the platform works, biology becomes programmable.”

Demis Hassabis, CEO of Google DeepMind, says AI drug discovery won’t progress gradually.

It will look more like AlphaFold, years of quiet infrastructure work, then a sudden leap where the system can scale across entire disease areas.

[DrORourke @DrORourke2]

This is completely off base. Academic success is rooted in focused scholarship, not changing course when the financial winds flow in another direction

[Henry Shevlin @dioscuri]

Academia is cruel because it selects for people obsessively interested in a narrow topic, but what’s actually rewarded is the ability to pivot fluidly to whatever’s new and fundable.

[DrORourke @DrORourke2]

Not unless they engage true disease experts - which is so self evident that it shouldn’t need to be stated

[Derya Unutmaz, MD @DeryaTR_]

Kudos to @JoshuaKushner & Thrive Capital for leading this $2 billion raise for Isomorphic led by @demishassabis! Arguably, Isomorphic will become the most impactful company in history for human health & life and a key to my bold claim that we will treat most diseases in a decade!

[DrORourke @DrORourke2]

Have you validated this model in vivo?

[Markus J. Buehler @ProfBuehlerMIT]

The next frontier in protein design will not be defined by structure alone, but by the capacity to engineer motion as a first-class principle of function. This is because dynamics is where the real biology lives.

Foundational work by Karplus, Levitt & Warshel made clear that chemistry cannot be understood without motion, mechanism, and scale. Gō, Brooks & others showed that proteins possess characteristic collective motions - low-frequency normal modes that capture how whole molecules bend, breathe, and fluctuate. Frauenfelder then sharpened the picture further: proteins are not static objects occupying a single minimum, but dynamic ensembles traversing rugged energy landscapes.

And yet the modern AI revolution in protein science has been, above all, a revolution in structure. In our new paper in Matter, @_Bo_Ni and I ask a different question: not what structure will this sequence adopt? but what sequence will realize a prescribed pattern of motion?

VibeGen inverts the conventional design paradigm. Rather than treating dynamics as a consequence to be analyzed after the fact, it makes dynamics the design objective from the outset. Using a language diffusion model with two cooperating agents - a designer that proposes sequences and a predictor that critiques them against the target motion profile - the system converges on de novo proteins with tailored vibrational behavior.

One of the most intriguing results is a form of functional degeneracy - distinct sequences and distinct folds can satisfy the same target dynamical specification. For a given functional pattern of motion, evolution may have sampled only a small region of the physically realizable design space. The space of viable molecular mechanics may be far larger than the repertoire biology happened to discover.

We have made "vibe" into a cultural metaphor - something intuitive, affective, subjective. But at the molecular scale, vibe is not metaphor: It is physics. For a protein, the vibe is the pattern of motion itself; the fluctuations, resonances, and collective displacements that determine what the molecule can do.

[DrORourke @DrORourke2]

Doesn’t sound like you know much about the complexity of human disease “sick care” and “health care” sound like great buzz words for the tech bros

[Cathie Wood @CathieDWood]

Unfortunately, most equity investors are not willing to underwrite @demishassabis’s vision of turning “sickcare” into healthcare: prevention and cures. Indeed, the market caps of two of the most important patent holders, $CRSP and $NTLA, are only ~$5B and ~$1.5B, respectively.

[DrORourke @DrORourke2]

We need to talk about #GBM - I saw you on speaker list at @Unlock2026AI
We need your input

[Ron Alfa @Ronalfa]

Processing hundreds of tumor samples per week now to train the largest cancer foundation models. AI will cure cancer.

[DrORourke @DrORourke2]

Awesome system and great presentation- thank you !

[Julia Bauman @JuliaBauman2]

The most beautiful molecular recorder 😍

GEMINI is a self-assembling protein system that records cellular events as physical layers, readable via imaging. Achieves down to 15 min resolution and works nicely in vivo!

From @DingchangLin's lab in @Nature

[DrORourke @DrORourke2]

It amuses me when people outside of deep immersive biomedical research and clinical medicine think that they are not subject to the rules of biology. I think you would better serve your goals by balancing grandiose ideas with some humility, i e the ultimate lesson of biology

[Daniel Shur @teleodaniel]

Two young Harvard professors are coming for the supplements industry.

@omarabudayyeh and @jgooten run a joint lab at @harvardmed, have co-founded 4 biotechs, and raised over $300M to develop genetic medicines and diagnostics.

But what surprised me most: they think like consumer tech founders, not academics. They start with what people actually want and work backwards from there.

And best of all? They’re totally longevity-pilled. Consumers want to feel younger and healthier, and big pharma is waking up to it.

In this week’s episode of the Free Radicals podcast, we discuss the biology of aging, the future of longevity therapeutics, and how Harvard can bring legitimacy to the supplements industry.

One of my favorite episodes yet.

Be sure to follow me, @EricDai_BioE and @FreeRadicalsBio to stay up to date on the latest news in longevity biotech!

[DrORourke @DrORourke2]

Try 6-12 years and you will have started

[Antonio Linares @alc2022]

My plan for the next 6-12 months is to get as good as possible at biology.

I’m going to be deep diving into everything because there’s a massive TSUNAMI of wealth & health coming.

[DrORourke @DrORourke2]

That would be a No

[Anthony M. Hopper @elander777]

@DrORourke2 New Limit's employees have plenty of "biological research and clinical training." In fact, they are top notch... https://t.co/XXMHTfYYyu

[DrORourke @DrORourke2]

Humorous stuff here! Keep this coming !

[Antonio Linares @alc2022]

Being a doctor is no longer core

An autist equipped with a frontier LLM and some mid lab capabilities can outperform you

[DrORourke @DrORourke2]

Not one iota of real immersive biological research or clinical training

[David Senra @davidsenra]

Brian is heavily invested in this area. We discussed this on my podcast. He started @newlimit to extend human healthspan using epigenetic reprogramming and committed $100M of his own money.

[DrORourke @DrORourke2]

Think that one through and you will arrive at a different conclusion

[Paul D. Rennert @PDRennert]

no one is focused on allo

[DrORourke @DrORourke2]

Doubtful unless the application is autoimmunity and B cell aplasia - I love Justin and the approach but disease experts agree with my view

[Sean @S_Gallagher23]

@DrORourke2 @DrORourke2 Fair point - specialized T cells are definitely a hurdle for certain cancers . Still, the Nature paper makes a strong case for skipping manufacturing altogether in many other cancers, potentially making the allo/auto debate irrelevant there.

[DrORourke @DrORourke2]

No - it won’t - at least not for cancer for which specialized cells will be required that cannot be generated by in vivo transduction

[Sean @S_Gallagher23]

Everyone is focused on allogeneic as the fix for CAR-T access.

But a Nature paper this month made a stronger case for something else entirely: skip the manufacturing step altogether.

In vivo CAR-T is coming. And it could make the autologous vs. allogeneic debate irrelevant.

https://t.co/jEmD1Raber

[DrORourke @DrORourke2]

Agree fully- the hope is clearly demonstrated in this brilliant work

[Aaron Gwyn @AmericanGwyn]

@BMcGrewvy It's not nihilistic at all. People just dislike what the novel espouses.

[DrORourke @DrORourke2]

Grossly simplified - you are not accounting for profound pathway redundancy observed in pathologic conditions. If this has been solved provide an example. I see unsubstantiated hype that isn’t close to replacing real experimentation

[Ron Alfa @Ronalfa]

Massive unlock for biology comes from LLM-powered agents reasoning and running virtual experiments with human bio world models.

[DrORourke @DrORourke2]

Naive is an understatement- he knows nothing about the biology he purports to understand

[The AI Investor @The_AI_Investor]

Jensen Huang on his prediction about the next revolution: digital biology

‘It’s the next revolution. It’s going to be flat-out one of the biggest ones ever.’

[DrORourke @DrORourke2]

Thanks for giving me a good laugh today! And thank Jensen too! You guys simulate biology and think you understand it @PennCancer

[Dustin @r0ck3t23]

Jensen Huang just called the exact top of the pharmaceutical industry.

Not a pivot. Not a disruption.

An extinction event.

Huang: “Where do I think the next amazing revolution is going to come? And this is going to be flat out one of the biggest ones ever. There’s no question that digital biology is going to be it.”

The medical establishment has spent centuries playing a chaotic game of trial and error.

We’re about to mathematically engineer the human operating system.

Huang: “For the very first time in human history, biology has the opportunity to be engineering, not science. When something becomes engineering, not science, it becomes less sporadic and exponentially improving.”

Biology is no longer the dark art of random discovery.

It’s a predictable, compounding execution loop.

Translate the chaotic variables of chemistry into the laws of computer science and you stop waiting for accidental breakthroughs.

You simply compute the cure.

That line should terrify every pharmaceutical executive alive.

Huang: “It can compound on the benefits of the previous years. And every researcher’s contributions compound on each other.”

For decades, drug discovery has been an isolated, artisanal process.

One lab. One team. One molecule. Years of blind iteration.

The algorithm just shattered that entire bottleneck.

Every failed protein fold, every successful synthetic molecule instantly trains the foundational model.

Makes the next iteration mathematically smarter.

Huang: “We’re going to have incredible tools that bring the world of biology, which is very chaotic and constantly changing and diverse and complex, into the world of computer science. And that is going to be profound.”

Incumbent pharma looks at the human body and sees an unmanageable wall of variables.

Engineers look at that exact same body and see raw data waiting to be compiled.

No longer guessing how a molecule will react in the physical world.

Running millions of zero-cost simulated iterations before a single test tube is ever touched.

Rip the chaotic friction out of the physical lab and drop it directly into a massive GPU cluster?

The timeline to map, edit, and optimize the biological machine doesn’t shrink.

It collapses.

[DrORourke @DrORourke2]

The naïveté of this is both stunning and dangerous- completely uninformed

[Mikli @CryptoMikli]

Bryan Johnson explains why hyperbaric therapy is one of the best therapies for your body

“We did a 250 biomarker measurement, and after 60 sessions we saw changes in my brain, skin, blood inflammation. It had a whole body effect. It's the best skin rejuvenation protocol in the world. It rebuilds collagen and elastin fibers, and it gets rid of senescent cells”

“The problem is you need to do 60 sessions, each is 90 minutes, within 90 days. And you can’t have electronics in there because it's too dangerous, so it requires a lot of time. It's really inaccessible for a lot of people”