Javier Tordable

Every time you get a cancer biopsy, the lab makes a tissue slide that costs about $5. It shows the shape of your cells under a microscope, and every cancer patient already has one on file. There’s a much fancier version of that test called multiplex immunofluorescence (basically a protein-level map showing which immune cells are near your tumor and what they’re doing). It costs thousands of dollars per sample, takes specialized equipment most hospitals don’t have, and barely scales. But it’s the kind of data oncologists need to figure out whether immunotherapy will actually work for you. Right now, only about 20 to 40% of cancer patients respond to immunotherapy, and one of the biggest reasons is that doctors can’t easily tell whether a tumor is “hot” (immune cells actively fighting it) or “cold” (immune system ignoring it). Microsoft, Providence Health, and the University of Washington trained an AI to analyze the $5 slide and predict what the expensive test would show across 21 different protein markers. They called it GigaTIME, trained it on 40 million cells in which both the cheap slide and the expensive test coexisted, and then turned it loose on 14,256 real cancer patients across 51 hospitals in 7 US states. The results landed in Cell, one of the most selective journals in biology. The model generated about 300,000 virtual protein maps covering 24 cancer types and 306 subtypes. It found 1,234 real, verified connections between immune cell behavior, genetic mutations, tumor staging, and patient survival that were previously invisible at this scale. When they tested it against a completely separate database of 10,200 cancer patients, the results matched up almost perfectly (0.88 out of 1.0 agreement). Nature Methods named spatial proteomics (mapping where specific proteins sit inside your tissue) its Method of the Year in 2024, and specifically cited GigaTIME in a March 2026 update as a model that “democratizes” this kind of analysis. The full model is open-source on Hugging Face. Any cancer research lab with archived biopsy slides, and most of them have thousands, can now run virtual immune profiling without buying a single piece of new equipment.

@elvissun @github Why not add a branch restriction to require a code review and then have the agent send the OR for review?

if you use --dangerously-skip-permissions you need to add this to your .bashrc right now. it'll block AI agents from merging PRs accidentally. thank me later. ps @github you need to separate merge from write permissions in PATs so agents can create PRs but not merge them.

Even @Delta diamond call center is now a stupid chatbot. What has the world come to?

@VijayInWA Where to, though?

Dark clouds have been gathering over Washington state for the last five years due to increasingly punitive Democrat tax policies. -Illegal capital gains tax -Almost doubling the estate tax -Pushing wealth and incomes taxes Entrepreneurs and businesses are looking for the exits.

Can’t wait for the class action lawsuit…

@thewardoll @treblewoe In your anglocentrism you may have misspelled The Cid.

Me, standing in the Starbucks line, casually wearing a shirt depicting Richard Lionheart caving in the skull of some saracen (I'm not ordering anything, just here to slap a Reconquista decal over the sodomite flag on the counter) Battle of Arsuf limited edition shirts available at war-doll.com/store 🏴

If you are a software engineer "experiencing some degree of mental health crisis", now hear this, because I've been coding for 50 years since the days of punched cards and I have a salutary kick in your ass to deliver. Get over yourself. Every previous "programming is obsolete" panic has been a bust, and this one's going to be too. The fundamental problem of mismatch between the intentions in human minds and the specifications that a computer can interpret hasn't gone away just because now you can do a lot of your programming in natural language to an LLM. Systems are still complicated. This shit is still difficult. The need for people who specialize in bridging that gap isn't going to go away. As usual, the answer is: upskill yourself and adapt. If a crusty old fart like me can do it, you can too.

I recently joined The Pauling Principle podcast with @tordable to discuss our research on RNA design, hot takes on architecture research in BioML, origins of life, and being in a wet lab! Feels pretty surreal that I'm interesting enough to be on a podcast (?) 🧵

This feeling is not unique. Many of us spent years and decades becoming good at something only to reach a point where technology is just as good. And clearly getting better every day. For some of us the only solution is to, transfer our skills into other areas, acquire new skills, and start businesses, putting ourselves in a position to use technology with leverage. For many others, especially those that are starting their career, it's a time to think very carefully about the future of the profession and whether they will be run over by the unstoppable train of AI progress.

@DrInsensitive Many other sunscreens are forbidden in Hawaii because they end up in the water and are toxic for the local fauna and flora. Titanium oxide is better for you anyway.

Based on replies telling me I am wrong, I checked a 3rd store: The ABC market. Nope. All sunscreens are zinc or titanium oxide. Sorry the video is jerky because I was angry. I got one that says it blends in easily. Now I will see if it actually protects me.

@chrisleiter_ @m_goes_distance @atriaVC 👏

@m_goes_distance have funded or previously funded all of these businesses (at pre seed) - so count at least one fund @atriaVC

we actually need more niche VCs in biotech there are 100 funds chasing "novel therapeutics" zero funds focused on: >making trials 10x cheaper >peptide supply chain infrastructure >decentralized clinical trial platforms >gene therapy manufacturing at scale the infrastructure plays is what will unlock the progress we yearn for.

@thesavvyghost @m_goes_distance Early discovery and novel biology are areas where China doesn't have an advantage yet.

@m_goes_distance Or just conduct all biotech in china

@m_goes_distance Just shamelessly plugging in here in case someone wants to talk about making drug discovery more efficient pauling.ai

@bluewmist 3 days may be a bit optimistic for most people, but a month or so should be realistic. Also, yes, it's the phone. For a longer read I would look at this one: tryunplug.com/guide.html

Thank you Alec Crawford and the AI Risk Reward podcast team! It was a pleasure speaking with you, and sharing the story of how we at Pauling are trying to accelerate the discovery of new medicines.

🎙️ Final Podcast Episode of the Year 🧬🤖 We’re closing out the year with a powerful conversation. In this episode, Alec Crawford speaks with Javier Tordable, CEO & Founder of Pauling.AI, about how artificial intelligence is transforming drug discovery—from automating the path from scientific hypothesis to molecule testing, to navigating ethics and regulation in healthcare. ✨ Key topics include: 🧬 Using AI to accelerate and lower the cost of drug discovery 🧠 Ethical and dual-use considerations in life sciences 🤝 Why pharma leaders should partner with AI experts ⚖️ The evolving role of global regulators in healthcare innovation 🎧 Listen & watch the final episode of the year: 🎙️ Spotify: open.spotify.com/episode/1Ira4k… ▶️ YouTube: youtu.be/hqCNlorDVg0 🌐 Website: aicrisk.com/podcast/episod…

@astrodanish You are going to love drug discovery…

This has been my major issue transitioning from aerospace to biomedical engineering. In aerospace, EVERYTHING is up for debate. you wana put the wings backwards on a plane? fuck it, Sukhoi su-47. Oh you want intermeshing rotors? Kaman K-max it is. In medicine, people flex their credentials (“doctor here 👋”) and rely on prior art: “usually are not” “standard practice” “typically not” EVERYTHING should be grounded in first principles and rigorous testing. Medicine is not like that, because of people like Dr. Kelly Morrison who look at a miraculous full body scanning technology that can see through you at unprecedented resolution- LITERALLY SCI-FI TECHNOLOGY- and can’t imagine using it for preventative means- simply because people haven’t done that before. You could give a magic X-ray gun to some third world, medieval shaman or witch-doctor and the first thing they would say is “yo we should scan everyone and make sure nothing looks weird inside”. How is this not the obvious response? I can’t see a future in which everyone isn’t getting MRI’d and having their images analyzed by AI. The future of medicine IS PREVENTATIVE. i don’t give a fuck what any doctor or pharma company says about it. Their incentive structures have been broken for the last hundred years. An ounce of prevention > a pound of cure. Please, for the love of God, think a LITTLE outside the box for once!

Is Antigravity worth it? vs CLI tools