Alex Rubinsteyn
personalized cancer immunotherapy = genomics + immunology + machine learning + oncology
(pirl.unc.edu)
- Reposted by Alex Rubinsteyn[Not loaded yet]
- Finally published! “Shared PRAME epitopes are T- cell targets in NUT carcinoma” We stumbled into working on a rare deadly cancer without effective treatments and found that some existing TCR therapies might be worth trying (at least work in vitro) Link: jitc.bmj.com/content/14/2...
- Two new NUT carcinoma cell lines: pubmed.ncbi.nlm.nih.gov/41485364/
- Ran into a third friend at this Durham co-working space, laptop also full of coding agents running in parallel (four Codex instances) Three for three now -- split between Claude Code, Cursor, and Codex, I guess I'm the 4th (with 5 Codexes waiting for my attention)
- New PIRL blog post by @benjamingvincent.bsky.social: Some advice to companies and clinics starting personalized neoantigen vaccine programs Link: pirlblog.substack.com/p/some-advic...
- Teaching my kids to sing “Costco! Costco!” over the Dsinghis Khan song (final humiliation of the Cold War)
- Disturbance in the force… Sonnet 4.5 Thinking with search just gave me 6 made up paper links in a row (link either didn’t work or went to different unrelated paper) Feels like it’s been a while (had to go back to ChatGPT)
- Reposted by Alex RubinsteynRead 1000 moltbook posts and then go back to reading bluesky without going insane challenge
- Been reading Accelerando just to find out what happens next
- Raising low tech kids is starting to feel transgressive (asked about laptop time at a school tour and felt like a fundamentalist)
- Reposted by Alex Rubinsteyn
- Claude Code did like 95% of the MHCflurry TensorFlow to PyTorch port in about a day but there are some persistent numerical differences/bugs that it's been churning for a week, playing trial-and-error whack-a-mole coding like a junior dev. Codex seems to be one-shotting the fix
- Codex and Claude Code working on the same branch. What could go wrong?
- Reposted by Alex RubinsteynEver wondered what happens if you remove Tfh cells from established germinal centres?
- No one is driving in my neighborhood, the streets have been completely conquered by bands of elementary school aged children with sleds.
- the kids are in control
- I’ve been blocked on an essay about curing cancer with AI forever & realized I couldn’t finish it because I was transitioning from skeptic to believer. Too much dissonance to reach a conclusion. (reaching a synthesis just as icepocalypse comes to Durham)
- Hosted some high school students (!) at the UNC Comp Med program who are taking a winter elective on AlphaFold and computational protein modeling (!!) What a crazy time to be a nerdy kid, everything going exponential all around you while traditional barriers erode and collapse
- Anti-FAP CAR T cells produced in vivo reduce fibrosis and restore liver homeostasis in metabolic dysfunction–associated steatohepatitis www.science.org/doi/10.1126/... (Capstan style aCD5 tLNP delivery of CAR construct to T-cells)
- Raleigh/Durham meteorology nerds: how long am I going to lose power for?
- what else besides neoantigen vaccines, neoantigen TCR-T, personalized phage therapies, and ASOs for nanorare germline disorders is in the protoplasmic soup from which generative medicine will emerge?
- I'm just wandering around the halls of the Computational Medicine at UNC telling people to download Claude Code. We're going to get a spicy mix of compounding research acceleration and LLM psychosis.
- Reposted by Alex Rubinsteyn[Not loaded yet]
- Reposted by Alex Rubinsteyn
[Not loaded yet] - In addition to Elliot Hershberg’s great writeup of Sid’s hyper-agentic cancer journey, Sid made a slide deck with more details on some of the therapies he’s done, and others he has queued up in a decision ladder: docs.google.com/presentation...
- Unevenly distributed future: Going Founder Mode On Cancer centuryofbio.com/p/sid
- Unevenly distributed future: Going Founder Mode On Cancer centuryofbio.com/p/sid
- Is Durham going to be buried under a mountain of snow this weekend?
- Tried increasing to six, some of which were greenfield ML projects without existing unit tests / API / example notebook. Hit diminishing returns, excessively fragmented attention, caught some slop/errors getting committed to existing libraries and probably missed others. So…there’s a limit.
- If any ants follow me: is there any kind of "Claude for an academic bio lab" deal? I want to buy Max subscriptions for everyone in the lab, but can't tell if there's anything simpler than buying them all individually (neither whole-university Academia or Team plans seem right)
- Maduro, Somaliland, Southern Yemen, Iran, Rojava, Canada/China realignment, &c Velocity of global events feels really high
- Four Claude Code instances running in parallel, considering getting Claude Max subscriptions for everyone computational in the lab It's over, they won, I am an AI bro now.
