-- Hiring ML Engineers time! -- Are you a smart person who wants to make therapeutics to help people using your ML chops? We will hire two engineers. We don't care about your pedigree, just your skills. Prove them by attempting the exercise linked below (<6 hours) 🧵

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.

Lots in this morning's Agenda: - The under-the-radar takeaway from Gemma's release yesterday - Finpilot, a startup building copilots for finance analysts, raises seed funding from @MadronaVentures - Thoughts on Nvidia's blowout earnings theinformation.com/articles/…

Had a blast sitting down with @jeffreyhuber, CEO @trychroma, an open source vector DB exploding in popularity (2M+ downloads; 500K+ in the past 30 days 🤯). Jeff is a 2nd time founder and shared amazing tips on hiring, building community, and much more! madrona.libsyn.com/chromas-j…

There is so much happening in AI! Apps that used to take years to build are being built in days. It’s a testament to the power of FMs and progress at the infra layer to put that power in the hands of more developers. Below are the emerging components of a #generativeai stack

Another trailer for the Netflix Tour series just dropped. Get excited 🔥

Despite the high pace of activity from well-capitalized Big Tech giants, we believe there are several ways startups can create value and utilize #generativeAI to build meaningful solutions. 👉 bit.ly/3mzx7Pm @SSomasegar @aseemd @palak_go #startups #UX

Some news - excited to share that I've joined @MadronaVentures as a Partner based in the Bay Area! Madrona has built an amazing foundation in Seattle over the past 20+ years, and I'm fired up to help expand our focus on helping founders beyond the PNW, from seed through growth

Most company stories can be told in 3 hours or less. But not this one. acquired.fm/episodes/amazon-…