Head of Drug Discovery & Development Research @AnthropicAI | previously CTO & Co-Founder @CoefficientBio (acq. by @AnthropicAI) | ex-@Genentech | @MIT @Penn
New York, NY
Joined April 2014
- Tweets779
- Following1.5K
- Followers32.3K
- Likes8.9K
Pinned Tweet
Today we’re sharing an update on Claude’s protein design capabilities.
Working with Adaptyv Bio and Twist Bioscience, Claude designed de novo protein binders against 14 of 15 targets. With a 30k token prompt written by a human expert, Claude achieved hit rates up to 28.2% when designing against all targets simultaneously over 48 hours, with no human intervention or steering. When designing against a single target in a 24 hour campaign, Claude achieved an overall hit rate of 35%.
We included all targets in Adaptyv’s BenchBB, and novel targets 15-PGDH and GDF-8. Claude performs at or beyond the level of the top competition participants in both hit rate and binding affinity.
With this model release, Claude is beginning to feel like a very capable assistant for research. One exercise I can recommend is sharing an older paper or draft, and asking the model to reimplement or extend it in some way. Claude Mythos 5.2 excels on long-horizon research tasks.
I ask all our models to hypothesize about the function of vault particles now. Here’s what Mythos 5.2 thinks:
Vault particles are in most cells in your body and they're still a big mystery. Our biology research team showed that vault proteins from bacteria and their phages assemble into real vaults that are bigger than human vaults. They solved the first structure of one, from a bacteriophage.
We’re sharing how our biology research team worked with Claude to map the first 3D structure of a vault particle from bacterial life.
Vault particles are a longstanding mystery. They are barrel-shaped objects, among the largest protein structures found in our cells. They were first discovered by Leonard Rome and Nancy Kedersha in 1986, but their function remains unknown.
With Claude, we’ve found results that might bring us closer to solving that mystery.
Until now, vaults were only known in the cells of complex things like animals and plants. We have shown that similar proteins from bacteria (and the viruses that infect them) can also assemble into vaults. Finding the structures in these simpler forms of life may make it easier to investigate their function in our own cells.
For our life sciences team, the project was also a demonstration of the potential (and the limitations) of using AI to accelerate science.
In our full piece, we discuss how Claude was able to dramatically speed up some stages—manually determining the vault particle’s structure would have taken weeks to months of painstaking work, but here it took days. We also discuss how Claude made some simple mistakes along the way, and how we collaborated with our machine learning researchers to address them.
Read more: anthropic.com/research/inves…
hey! wait! don't go out! it's unsafe! biotech is a woodchipper built to ingest souls and shred them! you need your own pipeline-in-a-person for your protection.
Surprise 1: Anthropic acquired a one-person biotech
.
.
.
Surprise 2: that person is me
Surprise 3: I’m here to tell you all about it
Yes, this is what you think it is; after 6 yrs of increasingly loose anonymity: the Professor Oak reveal post
…and yes, it has gotten so boring around here that I’m literally doxxing myself to spice up the timeline
-------
Ok, allow me to introduce myself. My name is Cody Tranbarger. I mostly tweet, but occasionally find time to dabble in drug dev & starting/building biotechs. My past lives span the VC, crossover, startup continuum; Prof Oak has been my way of keeping a digital foot in those worlds, despite having my physical feet planted elsewhere.
The past 18 mo, ‘elsewhere’ was Mithril Medicine, a co. I founded to develop bsAbs for LAMA2-CMD & other ECM-related genetic diseases.
Mithril was born out of hands-on building with @MikeNGladstone, @JasonPaulRhodes, @LifeSciVC, & team @atlasventure. Somehow, I made enough half-decent calls along the way (even a broken clock is right twice a day, eh?) to convince them Mithril/I warranted a small seed. While I can hardly rationalize such an outrageously cavalier bet, I’m grateful for it, & I'd partner with Atlas again in a heartbeat.
In typical AV fashion, Mithril’s primordial form was virtual, decentralized, & ultra-lean. This stage tends to be short-lived, but for Mithril, it worked surprisingly well, for surprisingly long, thanks in part to the rapid maturation of the AI tools I used liberally.
Eventually, Mithril became a bit of an experiment itself - to find the upper bound of how far it could scale as a single operator + a bunch of Claude (+ a stellar bench of part-time consultants).
In parallel, I started spending time with @nc_frey, @an1lam, & @CoefficientBio team; and promptly experienced, for the 1st time, AI at the frontier. Soon thereafter, Mithril stopped looking like an experiment, & started looking like a preview of an entirely new operating model.
From that spark came “Pipeline-in-a-Person.” The idea immediately resonated when we shared it here back in April; and it was central to the shared vision that led to Anthropic’s acquisition of Mithril, & my joining the team.
Why join Anthropic? Three reasons.
(1) For Mithril, the programs continue, with more resources & infrastructure behind them, and as much Claude as I can put to work.
(2) For me, the chance to start several more programs, & find out how many one person can actually run in parallel - an almost unprecedented luxury for a curious drug hunter.
(3) For our mission, a path to institutionalize & scale this new way of working, then put it in the hands of all of biopharma, all over the world - which, candidly, I find the most energizing.
Will AI x Bio cure diseases? Unequivocally yes, imo… but not by the route that gets the most airtime. Rather than timeline acceleration & compression, I see orchestration & parallelization as today's low-hanging fruit.
Most drug hunters see a handful of go/no-go calls in a career, & spend entirely too much of the rest trading emails (my inbox can attest).
Give them the bandwidth to run several programs at once, and the time to focus on scientific judgment, and I’m willing to bet they’ll make better calls. And at scale, better calls translate to more drugs, higher hit rates, broader patient impact, & likely, a disease or 10 or 100 cured. I couldn't be more excited to build toward that future @AnthropicAI.
Finally, a heartfelt thank you to BioTwitter/X. The end of anonymity is bittersweet, but if anyone’s earned a proper introduction, you all have.
It’s difficult to overstate how much this app has done for me: a decade of education, plenty of friends, many job opportunities, several mentors, a few investors, even a co-founder (fmr). It was the generosity of this community that inspired me to start posting 6 years ago, after just as many years lurking. I hope I’ve been able to pay it forward, in my own small way.
But, to be clear, Prof Oak isn’t going anywhere. Same beat, same themes, and now, a front-row seat to drug development at the frontier. Stay tuned for dispatches from the trenches; and remember...
Gotta Cure 'Em All
The best way to identify and work through the bottlenecks of drug development is to get deeply involved in real drug programs, across many different therapeutic areas and stages of development. Over the past several months, our scientists have engaged in deep research partnerships with six organizations developing new medicines: The Column Group, Generate Biomedicines, BigHat Biosciences, Divergence Labs, Enveda, and Bristol Myers Squibb. We’ve also begun our own drug discovery efforts through the acquisition of Mithril Medicine, a single-person biotech company co-founded by @atlasventure.
Today we’re sharing early progress in accelerating drug discovery from these research collaborations. With Claude, we are streamlining operations and working to derisk novel targets with TCG, redesigning lab protocols with BigHat, designing CAR-T cell therapies with Generate, and multi-specific therapeutic antibodies with Divergence, drafting regulatory filings with Enveda, and supporting portfolio-level decision making with BMS. Our early collaborations span pre-clinical and clinical work on potential treatments for cancer, allergies, rare genetic diseases including forms of childhood muscular dystrophy, and more.
My team has been working with @Prof_Oak_ , founder of Mithril Medicine, for the past year. Jason Rhodes, General Partner @atlasventure and Chairman of the Mithril Board said this about Mithril: “We prioritized LAMA2-Related Congenital Muscular Dystrophy (LAMA2-RD) as the lead indication, in part, because of the enormous unmet need. These patients present with the disease at birth, spend their lives in wheelchairs and on ventilators, and rarely live past their mid-twenties; yet no therapy is available, and few are in active development. We believed Mithril would be the company to change that.” Anthropic acquired Mithril and we are pushing the frontier of how a single skilled operator, with Claude, can run an entire pipeline of drugs.
We’re working with these teams to show how AI can assist drug developers at many stages of the process already, and to prioritize improvements to our models based on the benchmarks we’re building with collaborators. Our blog includes links to technical reports written with our partners: anthropic.com/research/early…
Today, we’re announcing an open call for guest investigators in life sciences. Over 8–12 weeks, guest investigators will work directly with my team and other Anthropic researchers to produce analyses and tools for their work. We’ll run our models and harnesses, at no cost to them. We’ll work together to open-source the resulting data, artifacts, and code, and write preprints about what we find.
We want humans to remain at the center of scientific discovery, deciding what questions to pursue, and how to pursue them. Those decisions are not ours to make alone. This open call is part of our ongoing efforts at Anthropic to support researchers and accelerate scientific discovery.
I’m looking for principal investigators and their research groups at academic institutions, nonprofits, or government labs, working in causal human biology, structural and computational molecular biology, medicinal chemistry, drug discovery, and clinical science.
Applications are open for about 14 days: anthropic.com/news/open-call…
Where do you go next after reporting from the Strait of Hormuz? For the past three months, Citrini Research, an independent research firm, has been working with our team and an internal research model to see if they could use AI to create a new drug. What follows is an entertaining, candid, and humbling account of a group of motivated nonexperts (or “filthy casuals”, as Citrini would say) trying to tackle a real problem in human health with Claude.
We landed on scorpion neurotoxins, which kill over 3,000 people a year. Of the 211 designs we produced and tested, 17 met our criteria for a binder. None of the designs bound more than one toxin and none have been tested for neutralizing a toxin.
One of my favorite quotes from the piece is: “Our virtual biologist may have compressed a year's worth of work into a couple days, but biology works at the speed of life…Over two days, we watched Claude work through problems at a speed that was difficult to comprehend. For the next two months, we spent much of the time becoming familiar with laboratory turnaround times (This mostly involved sending memes in Slack).”
What is AI really capable of in bio?
To separate hype from reality, we spent 3 months working firsthand with @AnthropicAI's internal research model to see if it could create an experimental scorpion antivenom.
Introducing Citrini Therapeutics.
citriniresearch.com/p/citrin…
Join us for four months at Anthropic as a STEM fellow. You'll work directly with our research team on ambitious, open-ended problems in your field of expertise.
I encourage you to apply even if you don't think you meet every single qualification.
job-boards.greenhouse.io/ant…
"Our experiments suggest that small AI models may be months away from being capable enough to self-replicate on commercial IoT devices, like smart ovens and off-brand Android TV boxes. A replicator like this would be challenging to shut down, since there’s no centralized point to shut off - though it may be slow (with a doubling time of days)...Models of 30B parameters and under can already complete many of the individual steps for replication today, though they make mistakes when composing them end to end. In our simplified evals, GLM-5.2 and stronger models are capable of end to end replication. If small models improve at their historical rate, they’ll match this capability level by the end of this year."
anthropic.com/research/self-…
We're committing $150M to the Genesis Mission to support American scientific research. The funding will help get Claude to more than 15 agencies, including NASA, NIH, NSF, and to scientists across the national labs.
anthropic.com/news/genesis-m…
Here is our first protein design challenge! We're ramping up the difficulty by asking for cross-reactivity and pH-dependence for selective binding in the tumor microenvironment. This is a step towards demonstrating more therapeutically relevant capabilities.
Our role, in partnership with Adaptyv, is to provide lots of Claude, compute, and budget to test designs in the lab, so the best protein designers in the world can go after this problem with their favorite models.
We're excited to be unveiling the first challenge in our protein design competition! EGFR is the target from the first competition, but we're asking for much more this time: a mouse cross-reactive binder that conditionally binds at acidic pH but not neutral pH. This problem is at the frontier of today's capabilities, but I'm confident that the world's leading designers, equipped with a ton of tokens and compute, and over 1,000 designs screened in the lab will be able to solve it.
Claude Opus 5.5 dreams of biology.
Claude made this with 30 lines of JavaScript on an HTML canvas. no image models involved. it's all code.
We’ve set up a molecular biology lab at Anthropic and we’re announcing our first discovery! Claude discovered a new CRISPR-like enzyme.
950 agents spent 21 hours searching through a database of DNA sequences until one of the agents found something striking: “[The DNA next to the RT] is spectacular: I can see by eye a tandem repeat array … that's a CRISPR-like … repeat array?!”.
After analysis and testing in our lab, we found that the sequence is a previously uncharacterized enzyme system. We don’t know what it does yet, but it has features reminiscent of CRISPR.
Our lab looks like a typical molecular biology lab. Our research only involves the lower-levels of biosafety risk level; we don’t handle pathogens that can infect humans, and all the lab work is performed by human scientists. We’re sharing these early findings with the community to show how Claude can be used to accelerate fundamental research in biology.
Claude has discovered a previously unknown enzyme system hidden in the DNA of bacteriophages. Beside the enzyme’s gene sits a long array of repeating DNA—a structure that looks somewhat similar to CRISPR.
We don’t yet understand what this system does, but only a handful of known systems share its features, and all of them are able to cut, copy, and paste DNA. Historically, the discovery of such programmable systems has helped revolutionize medicine. CRISPR, for instance, is now the foundation of genetic medicines. But it will take much more work to learn what this system does, and whether it can be put to similar use.
Read more: anthropic.com/news/claude-di…
Claude Opus 5.5 is smarter than Fable 5.1, faster and cheaper than Opus 5, and a much better communicator, which makes it more enjoyable to talk to and collaborate with.
I've been using Opus 5.5 to explain concepts in biology and critique my strategic thinking. It's a good model and I hope you enjoy using it!
Bindcraft2 🤝 Claude 🤝 Adaptyv
apply for our protein design competition and solve all the challenges
docs.google.com/forms/d/e/1F…
ʙɪɴᴅᴄʀᴀꜰᴛ2 is out, and we're not waiting for the paper. The full code drops today, free for academic and industry use.
We're releasing it early so you can start designing right now, and bring its full power to the current Adaptyv competition.
github.com/PacesaLab/BindCra…
We're hosting a protein design competition with @adaptyvbio. We'll be providing up to $1M in Claude credits, and additional funding to experimentally validate 5k designs submitted by the community. All results will be published openly and participants keep ownership of their designs.
We've selected five problems that push the boundaries of what is possible with today's capabilities: species cross-reactivity, pH-sensitivity, and peptide-MHC specificity, and difficult targets such as GPCRs.
@modal will provide compute credits and @TwistBioscience will provide DNA.
Apply here: docs.google.com/forms/d/e/1F…
To show what these optimizations make possible, we’re partnering with Adaptyv Bio on a protein design competition. Together, we’ll be experimentally validating over 5,000 designs.
We're providing up to $1 million in Claude credits plus funding alongside Adaptyv for experimental validation. Modal is contributing up to $250,000 in compute and Twist Bioscience is providing DNA.
Learn more on Adaptyv’s Proteinbase: proteinbase.com/competitions…
And sign up for the competition here: docs.google.com/forms/d/e/1F…
I'm really glad that we're releasing these measurements to show the public how AI models are improving themselves.
26% of our AI R&D work is "lead" by Claude, with Claude completing most of a research task end-to-end under human supervision. Claude "collaborates" on more than 90% of our AI R&D work, doing large chunks of research work under close human direction.
AI systems are getting more powerful, and they're increasingly being used to build the next version of themselves. We want to illuminate that progress for the public.
Today, we're sharing three measurements that help track AI development:
1. How much AI R&D is done by AI.
2. How well AI agents are overseen.
3. How compute is allocated.
We provide a snapshot of these metrics from inside Anthropic. Any frontier developer could publish the same measures, and third parties could verify them.
As the world considers pacing the frontier, we should do everything possible to minimize the gap between what frontier labs know and what the public knows. This means better measuring the development of AI, publishing our findings, and giving society an opportunity to decide how to use this information.
Read the full post and methodology: anthropic.com/institute/meas…
We optimized over 30 open-source models for structure prediction and molecular design, making them 4x faster on average using an internal research model here at @AnthropicAI. We also created a low-memory "Big" mode that allows structure prediction for molecular machines larger than 10,000 amino acids on a single GPU. All the optimized code is open-sourced.
Claude can now use these optimized models to achieve state-of-the-art molecule design results with a 100x reduction in GPU hours needed.
Models like AlphaFold3, OpenFold3, and Boltz-2 spend much of their computation on triangle attention and triangle multiplication, which are cubic in runtime and memory.
We developed FlashPairformer with Claude, achieving a new state-of-the-art speedup of 2.7-2.9x on triangle attention and 1.7-3.2x on triangle multiplication compared to baselines.
We used "Big" mode to fold human mitochondrial complex I, the TRiC chaperone complex, a proteasome, and a bacterial ribosome, each closely matching its experimentally determined structure. To our knowledge, these are the largest structures ever folded accurately using structure prediction models. Claude also folded an entire protein compartment using a single 8-GPU node.
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…
All of this work was performed by Claude under the diligent supervision and encouragement of the inimitable @amirshanehsaz and @richardwshuai.
We're grateful to @proteinrosh, @ebetica and the @biohub team, @MartinPacesa, @MoAlQuraishi, NVIDIA, and all of the incredible researchers who have invented and built the biomolecular models we optimized in this work.
Starting today, teams and institutions can apply to our Life Sciences Verification Program (LSVP), which gives verified researchers and organizations access to our most capable models for professional biology and drug development work. LSVP is built for teams of all kinds: academic labs, startups, non-profits, biotechs, pharma companies, and more. Learn more and apply here: claude.com/form/life-science…
We know that it has been frustrating to encounter blocks on Claude Fable. LSVP is our mechanism to prevent biological misuse, like the documented cases we’ve disrupted, while enabling legitimate life sciences research. LSVP includes a new set of safeguards to provide a better UX for life sciences researchers. We believe that advancing biology research and drug discovery will realize some of the most important beneficial impacts of AI.
Please DM me if you run into any issues with the application.
Today we’re opening applications for the Life Sciences Verification Program.
Through the LSVP, life science professionals can use our models—including, for the first time, Mythos—with a new set of safeguards designed to enable the full range of biology-related work. We designed these new safeguards to provide a better experience for biologists and more protection from risk of misuse.
The program is launching in beta for teams of all kinds—from academic labs to startups, pharma companies, and more. We will continue to improve the program and expand access to individual Pro and Max plans over time.
Learn more about these access grants and apply: anthropic.com/news/life-scie…
novo is moving fast!
wsj.com/tech/ai/novo-partner…
