←
Daniel Bryan Goodman2,515 posts
Daniel Bryan Goodman avatar

Daniel Bryan Goodman

@dbgoodman

Immuno/Synth Bio/ML. PI @PennMedicine/@parkerici. Using DNA synth, multiplex assays & generative models to understand & engineer immune cells. @geochurch alum.

◷ Joined May 2009▧ 30 Photos and videos
Anselm Levskaya avatar
⟳ Daniel Bryan Goodman retweeted
Anselm Levskaya@anselmlevskaya·Nov 11

I was an experimental biologist for 17 years. I'm pilled enough that I switched to scaling AI a decade ago - I've been doing nothing but scaling transformers for like 8 years. I think we'll eventually make great impacts with AI in Bio. But there's still a level of really basic delusion at play here. The timescales for testing even simple interventions in human bio is *years*. You can't iterate on a physical system faster than you can intervene. Do you have any idea how long and hard it is to recruit patients to a trial for schizophrenia or Alzheimers and how long it takes to get a readout? Same for a decent study on oncology or cardiovascular disease. There's a reason biomed people are calling this stuff out - it's Theranos-level magical thinking or borderline unethical roadshow hype.

Linda Goodman avatar
⟳ Daniel Bryan Goodman retweeted
Linda Goodman@LindaBGoodman·Nov 11

Big news! Full article below 👇 Fauna Bio’s rare biological data and powerful AI approaches have uncovered another promising obesity drug target. @EliLillyandCo has made an additional milestone payment for a second target identified through Convergence™ AI. Huge congratulations to the @faunabio team 🚀 businesswire.com/news/home/2…

Post attachment
Sidi Chen avatar
⟳ Daniel Bryan Goodman retweeted
Sidi Chen@sidichen·Nov 4

11/4/2026 Excited to share our new Nature paper “In vivo CAR-T double knockout screen maps synergistic antitumour gene pairs”. Led by Liqun, with Paul, Kaiyuan, Ariel. Also Tx to support from lab members and Markus, Stephen and Nidhi’s groups. Kudos team! nature.com/articles/s41586-0…

Hani Goodarzi avatar
⟳ Daniel Bryan Goodman retweeted
Hani Goodarzi@genophoria·Oct 18

A couple days ago, @AnthropicAI published this interesting post, and I just got a chance to read it. It focuses on what AI did to their own hiring. Junior hires fell 3x & their managers now hire for autonomy and judgment (agents cover execution). anthropic.com/research/emplo…

Dean W. Ball avatar
⟳ Daniel Bryan Goodman retweeted
Dean W. Ball@deanwball·Oct 9

The mood has been a bit dour lately, so here are some less-obvious things that I expect to take shape over the next decade that I am excited about: 1. Space! Lots and lots of stuff is going to be happening in space by the mid-2030s, and right now the U.S. looks like it will be the leader by default, modulo the overhyped “race” to land a human on the moon again. Robots on the moon building and digging and cutting and adhering are more exciting than a person standing there taking pictures. The humans can come once the machines have built us habitats. 2. Increasing substitutability of hydrocarbons. This will lead to fewer supply chain disruptions and more stable, lower prices. This is a story about both supply elasticity and demand elasticity, and the geopolitical implications are underrated. Amazing for North America. 3. Private market exposure increasingly being an option for public investors, combined with Silicon Valley figuring how to use debt and other financial instruments more creatively than in the past. This seems like something America will be uniquely good at and I expect it to boost our already enviable lead in emerging technology capital allocation. 4. State and local government adoption of AI. This will vary widely by jurisdiction, but in at least some places you will see government administrative processes and public service provision have huge increases in efficiency. State and local government is where most of the American public services that people rely on are actually administered, so this is high-impact for people’s lives. 5. Advances in mathematics rapidly diffused to other fields. Historically it takes on the order of decades or centuries for discoveries from the bleeding edge of mathematics to be translated into practical applications, but I think AI will accelerate this dramatically. Lots of this will have the flavor of “small steps toward a much better world,” but it will accumulate. 6. Speaking of mathematics, lean! Lean is a programming language used by mathematicians to formally guarantee the truth of a proof. AIs can write lean and eventually they will be superhuman at it. This will have applications far beyond math, including cybersecurity and contract writing/negotiation/execution. 7. Fixing American’s shipbuilding problem by building boats instead. America has great boat-building capacity, but is awful at building ships. I want us to get better at building ships, but I am confident we can scale boat production. The Navy will soon have massive fleets of autonomous boats everywhere in the world. 8. New kinds of agriculture will become possible because of autonomy. Row-crop agriculture is heavily mechanized already, and automating the tractor, by itself, does less than you think for the economics of a farm. But with time, more labor-intensive crops will become economical. And vastly more diverse and complex crop arrangements will become possible too, which will be both ecologically, economically, and culinarily beneficial. The economics of agriculture could start to be kinder to small farms again. 9. Because of the previous item and advancements in biotechnology, logistics, and robotics, I expect that people are underrating how much healthier, more diverse, and flat-out better the American diet will be in 2035. 10. The subterranean will become an increasingly important field of human activity. New imaging sensors, including ones enhanced by an abundance of space-based imaging platforms, will make the subterranean more immediately legible. Better drilling and digging will become cheap and widely diffused. Among many other things, the opening up of the subterranean as an industrial frontier will change what we think of as a usable natural resource. 11. Greater variety and ornamentation in the physical world. Standardization is partially a function of scarce labor. Robotics can make beauty accessible again, if we choose to let it. There are many others, but I am out of time and space.

Alex Tabarrok avatar
⟳ Daniel Bryan Goodman retweeted
Alex Tabarrok@ATabarrok·Oct 7

Last night my 9-year-old son was taunting my wife, complexity theorist Dana Moshkovitz, as follows: “mommy, I heard you got cooked! I heard that a robotsolved the math problem you worked on for your whole career! OOF!” scottaaronson.blog/?p=10169

Daniel Bryan Goodman avatar
Daniel Bryan Goodman@dbgoodman·Oct 7

👇👇👇👇👇👇

In the AI era, I expect to see many new modalities emerge in biotech. These will be therapeutics in unusual shapes and sizes, not the legacy small molecule drugs that our IP laws, tech transfer departments and biopharma term sheets were designed to bring to market. CRISPR was a practice run. It was an experiment to see how well the existing biotech ecosystem is set up to commercialize new modalities. 14 years after the CRISPR patent wars, it should be seen as a failure and motivate significant reform. Imo the failure of CRISPR reveals two needs: 1) We need better legal and financial tools for nonexclusive foundational IP licenses. If a new modality has 100 applications, we can't assign exclusive rights to 3 companies who then spend the next decade suing each other. 2) We need better infrastructure for modality-wide safety trials and re-use of clinical data. If a new modality has 100 applications, we shouldn't demand that each use build a new portfolio of clinical evidence from scratch. I believe the AI era will deliver dozens of CRISPR-scale new medical innovations. Let's not allow the CRISPR fiasco to happen again. statnews.com/2026/10/07/cari…

Pranam Chatterjee avatar
⟳ Daniel Bryan Goodman retweeted
Pranam Chatterjee@pranamanam·Oct 6

Phosphorylation controls protein activity but can also drive disease. ❤️‍🩹 What if we could programmably dephosphorylate any target? Building on our pLM-generated peptide guides for E3s (uAbs) and DUBs (duAbs), we introduce PepRePs: peptide-retargeted phosphatases! 🎯 📜: biorxiv.org/content/10.64898… 🧵👇

Rohit Singh avatar
⟳ Daniel Bryan Goodman retweeted
Rohit Singh@rohitsingh8080·Oct 3

Biosecurity is too important for security theater. In a quick test with Raygun, we found that DeepMind's SynthIDBio watermark signal could be washed out while preserving the predicted structure. We don’t think protein sequence watermarks buy much biosecurity.

Post attachment
Anselm Levskaya avatar
⟳ Daniel Bryan Goodman retweeted
Anselm Levskaya@anselmlevskaya·Sep 30

Many policy folks fixate on AI biorisk stories, and ignore the real engines of pandemics - animal agriculture - because it's boring. There is so much more latent computational power for running selections in living animals out there than anything we can do on measly computers.

There's an active H5N1 outbreak on a mink farm in Utah and no one is doing much about it: sltrib.com/news/2026/09/27/a… This seems under-reported. I think it illustrates the danger of the virus, the need for more institutional competence, and the comparative risks of farms vs virology

donald avatar
⟳ Daniel Bryan Goodman retweeted
donald@donaldjewkes·Sep 23

I made this with one prompt using Opus 5.5 I spoke to my computer for 5mins, claude worked for 12 hours, and I woke up to this full prompt:

2:22

Claude Opus 5.5 has the best visual design of any model I have tested so far

2:37
Pierce avatar
⟳ Daniel Bryan Goodman retweeted
Pierce@PierceOgdenJ·Sep 22

Today, we’re announcing mBER-2, our latest AI protein design system, and sharing a bit of how we use it to explore biology in vivo at scale. For a long time, we’ve been working on what I think of as “frontier problems” in medicine and biology. We know a lot about the targets involved in disease, but there is still an enormous amount of biology we haven’t explored, and potential uses for that biology we haven’t discovered. One of those problems is drug delivery. There are thousands of potential targets, and most receptors remain unexplored as routes for delivering medicines. We want to understand which ones we can use, where they can take a drug, and what kinds of molecules make that possible. Ultimately, we need to test these molecules in vivo to understand what they actually do. We’ve spent the last six years building measurement technologies that let us generate millions of measurements in living systems. mBER-2 is an AI protein design system built for that scale of in vivo measurement. Our goal is to generate binders across the full range of targets we care about, while systematically exploring the possible binding sites on each one. It’s not just what you bind, but where and how you bind that determines whether a molecule performs it's function. mBER-2 lets us probe those differences at massive scale. We’re also sharing a look at some of our in vivo data. We’ve designed more than 50 million molecules across over 4,000 targets, and screened millions of molecules in living systems. By probing hundreds of receptors, we’ve found new pathways for delivering genetic medicines into fat that outperform industry benchmarks by a large margin. This is just the beginning. We call the space of all bindable sites across proteomes the EpiTome. As we explore it, we’re building the data to connect AI design, receptor binding, and what a molecule actually does in a living organism. Much like the idea of a virtual cell, we envision a Virtual Organism that helps us design medicines with specific properties in mind. The foundation is our own in vivo data, connecting molecular design to outcomes measured in living systems. The endgame is to use AI to explore more biology, measure what happens, and use what we learn to design better medicines. Every round should deepen our understanding of biology and improve our ability to build molecules that do what we need them to do.

Anthropic avatar
⟳ Daniel Bryan Goodman retweeted
Anthropic@AnthropicAI·Sep 17

Biologists use specialized open-source models for tasks like modeling the structure of molecular systems, designing drug-like molecules, and predicting the effects of genetic mutations. But these models are often expensive to run, potentially limiting their impact. In our latest Science Blog, we share how Claude was able to optimize inference for more than 30 open-source models, making them 4x faster on average, partly by writing custom software for GPUs. We’re open sourcing all of the optimization code. Read more: anthropic.com/research/claud…

0:18