Vivian Cai

i hate to be the one to say this, but as an asian woman myself, i feel really odd scrolling on x today... seeing other chinese women play into the "honeypot" jokes for views. i know it's meant to be funny, but to me it just reinforces the racist and sexist stereotypes we already deal with, so let's NOT set us back even further by sexualizing ourselves...

figured i’d share a little about what we’ve been working on at @onwardbio we started with a simple q- what would it take for AI to actually help cure diseases? give a model a patient’s records from before treatment and ask what happens next; give it results and ask what it would test next, run to see if it was right to do that, you need a scan, a lab result, and a followup note that all belong to the same patient i’m excited about what happens when a model gets something wrong- can we figure out what evidence was missing, go collect it, and see if it does better next time? if you’re building AI for bio, would love to connect let’s cure them all.

designed a TNBC cancer vaccine with claude this weekend picking antigens is the billion dollar question TNBC has low mutational burden, so personalized neoantigens alone leave almost nothing to encode, so need a hybrid approach of ~20 personalized neoantigens plus a shared module a shared shortlist is: CT83: ~65% of TNBC. ZNF165: required for TNBC survival. ACTL8: highest expression of anything screened then I looked for data: everything public is single timepoint. a vaccine has to hit the clones that survive chemo, and one biopsy can't tell you which so I'm building that dataset at @onwardbio matched pre and post treatment tumor, same patient, DNA and RNA

New on our Science Blog: How AI is beginning to change scientific modeling. Scientific models help researchers explain and predict real-world systems—like how a single nerve cell fires, or what happens when neutron stars collide. Recent advances have transformed how scientists fit complex models to data. But scientists still typically write the models manually, and usually need to weigh up several competing versions, each of which might explain the data in a different way. In a guest post, Jakob Macke, Daniel Gedon, and Stefan Wahl describe how AI is starting to help with these parts of the process. By writing, running, fitting, and revising scientific models as code, AI can explore many possible model structures, and find out which explanations the data support. anthropic.com/research/teach…

Had a great time cohosting Reward Snacking Vol. 2 with @yrv_23 at Harborview SF last night! Thanks to everyone who joined us!

Biological simulation can be learned. We trained a 27B model in BioSimGym, our RL environments for biology. It outscores the best frontier model on every BioSimBench task.

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…

this is the direction we’re building toward > we’re sourcing oncology cohorts with blood, h&e pathology and linked clinical data, exploring patient-matched multi omics and more we also have our own patient cohort, with pre- and post-treatment data collection and longitudinal followup, subject to ethics approval and informed consent the goal is to connect molecular measurements, pathology, treatment, and outcomes from the same patients over time. oncology is our starting point if you’re building medical ai, or interested in a research collaboration, let’s talk

could a vaccine help prevent the most prevalent cancer in women? three years into researching it, this is the question that keeps bringing me back to my desk we’re exploring what that vaccine should target- antigens that appear early, are recognizable to immune cells, and could be targeted without harming healthy tissue which targets persist over time? which disappear? when does the tumor stop presenting them? to investigate, we’re seeking breast tissue sequencing, HLA typing, and matched blood/T cell data across timepoints. early lesions and normal tissue are especially important for evaluating prevention targets if you work at a hospital, lab or biobank with these samples or data, would love to connect