Jason (@jasonyi96) header
Jason (@jasonyi96) profile picture

CAR-T 🤝 AI

Cambridge, MA
Joined November 2013
Photo by Jason (@jasonyi96)Photo by Jason (@jasonyi96)Photo by Jason (@jasonyi96)Photo by Jason (@jasonyi96)Photo by Jason (@jasonyi96)Photo by Jason (@jasonyi96)Photo by Jason (@jasonyi96)Photo by Jason (@jasonyi96)Photo by Jason (@jasonyi96)Photo by Jason (@jasonyi96)
Less really is more. Next for us: target selection for early stage solid tumors with @AnthropicAI
What will drug discovery look like when intelligence is abundant? Our team at @generate_biomed began with this question, and we’re excited to share some results! We took on in vivo CAR-T and designed a scaffold 70% smaller than ones in the clinic, with 3x the potency 🧵
5
39
5,333
Brain maps usually show genes or cell types. Membrane lipids, which are essential for synaptic transmission and whose altered composition is linked to many brain diseases, remained poorly mapped by comparison. Fusar Bassini, La Manno and colleagues asked whether lipids simply follow the brain’s known anatomy or reveal an organization of their own. They measured 172 lipids across the whole mouse brain and found 539 chemically distinct territories, which they call lipizones. Most overlap known cell-type territories, but lipid patterns could be only partly predicted from gene expression. Regions connected by axons, even distant ones, were more likely to share lipid signatures. In pregnant mice, the white matter and specific cortical territories changed their lipid composition. The map is public, so other labs can use it to locate where lipid changes occur in disease, which gene-expression maps cannot show. As a descriptive resource, it does not test what these territories do for neural function, and the pregnancy comparison rests on a small number of mice. Fig. 1 from Fusar Bassini et al. (2026), Nature. CC BY 4.0.
7
16
1
88
2,607
Whole in One: Expansion microscopy + machine learning combined in WHOLISTIC – a means to image networks of cellular activity body wide 📹 Virginie M. S. Ruetten et al @HHMIJanelia in @Nature ➡️ bpod.org.uk/archive/2026/10/… with @DrJohnAnkers
8
47
2,738
The "Age of Miracles" era: I took a look inside Anthropic's latest progress in the life sciences, including working with a ton of biopharma partners and a new acquisition disclosure All coming before what is likely the business world's largest IPO: endpoints.news/anthropic-pit…
1
7
1
19
3,250
Jason retweeted
Great analysis from @owl_posting as always. Expanding a bit on our work @generate_biomed particularly on the literature, novelty, and creativity đź§µ
incredible work. im in awe of anthropic’s pace, and am grateful for the transparency of process+results i went through 3 out of the 5 case studies they released and wrote down my thoughts on each. in italics are LLM-summarizations for the cases for those who havent read them
3
3
28
1,832
Jason retweeted
Incredibly cool to see. This + the one-man biotech acquisition by Anthropic are lead indicators of the future AI will spawn a thousand flowers in biology. “Why not me?”
What will drug discovery look like when intelligence is abundant? Our team at @generate_biomed began with this question, and we’re excited to share some results! We took on in vivo CAR-T and designed a scaffold 70% smaller than ones in the clinic, with 3x the potency 🧵
2
2
13
1,722
Making medicines is really hard. Excited to share some early work from the team @generate_biomed with our partners @AnthropicAI on how we can leverage agentic tools to rapidly advance science. While it is still early days, the signals are very promising and patients are waiting.
Over the past few months, Anthropic scientists have engaged in deep research partnerships with six organizations developing new medicines. We've also begun drug discovery efforts of our own. In doing so, we’ve learned much more about how Claude can support the many stages of drug development. In this blog post, we share some early results from these efforts, and describe how this work fits in with our wider ambitions in the life sciences. anthropic.com/research/early…
1
3
20
1,198
I've been hanging out with this rock star team at @generate_biomed for the past few weeks and while this result is worth a deep dive, the way they work is the real game changer. They've allowed AI to remove the friction in the organization. As AI-pilled as I am, it's taken some adapting to transform to the way the future will look, but there is no catering to the 'old' way. And that's the only way the true impact of AI will be seen, not just in the frontier labs, but also in the AI native biotechs working to bring real cures to patients fater. Things are going to change quickly and the hardest part is going to be how people and systems adapt to move at speed. And this team is doing it. Congrats @jasonyi96, @liambai21, @wwang002, @KaggenA!
What will drug discovery look like when intelligence is abundant? Our team at @generate_biomed began with this question, and we’re excited to share some results! We took on in vivo CAR-T and designed a scaffold 70% smaller than ones in the clinic, with 3x the potency 🧵
4
4
34
4,197
Over the past few months, Anthropic scientists have engaged in deep research partnerships with six organizations developing new medicines. We've also begun drug discovery efforts of our own. In doing so, we’ve learned much more about how Claude can support the many stages of drug development. In this blog post, we share some early results from these efforts, and describe how this work fits in with our wider ambitions in the life sciences. anthropic.com/research/early…
753
1,330
687
11,807
3,541,504
A smaller CAR T-cell receptor could make room for a more capable therapy. In our collaboration with @AnthropicAI, six of our scientists used @claudeai alongside our own models, computational tools, and wet lab data to refactor a CAR T-cell receptor for solid tumors. The redesigned signaling component was about 70% shorter than a standard design, making room for new functions and improving cancer-cell killing in laboratory tests. Watch how our scientists turned years of work into months, at a fraction of the cost, expanding what we can engineer for patients. @AnthropicAI's case study → anthropic.com/research/early… Our preprint → generatebiomedicines.com/pub… Our blog → generatebiomedicines.com/blo…
2
10
43
3,361
Public preview of BioEmu2! @MSFTResearch AI for Science’s new foundation model for biomolecular structure, dynamics and function. Open weights, MIT license. github.com/microsoft/bioemu2 Movie: BioEmu2-simulated binding of intrinsically disordered peptide PUMA to MCL-1 receptor. 🧵⬇️
23
245
28
908
68,396
Jason retweeted
Excited to share what we’ve been building with Chaperone! In our benchmark, Chaperone reduced token usage by 86%. We also went from hypothesis to sequences ready for wet-lab testing in just two weeks—yielding a 1.32 nM cortisol binder in the first experimental round!
8
48
4
279
56,435
Today we are excited to release Artios, a fully open source system for designing functional de novo enzymes. Enzymes present a new frontier for de novo protein design models due to the challenge of coordinating precise chemistry, rather than binding a target. Enzymes are life’s biological machines and by designing them we can truly start to engineer biology. We believe these fundamental capabilities should be built in the open and shared with the community to progress science faster. 🧵 1/6
23
93
11
422
30,045
1/ We discovered something totally unexpected about the neural structure of consciousness that overturns decades of thinking on its biological basis and brings us significantly closer to the recipe for generating conscious awareness. New preprint: biorxiv.org/content/10.64898… (led by @HesseJanis, with @FrankLanfranchi, @_conor_mcgrory, @Yuelin_Shi, and @EngelTatiana)
392
1,694
534
11,331
2,195,763
Introducing Prime Agent: A self-improving RLM harness for coding and long-running autonomous tasks. Designed to be both token-efficient and expressive through programmatic tool calling, context as a variable, multi-agent messaging, and a self-modifiable harness state.
399
831
576
8,166
3,227,212
Sonoluminescence - If you collapse an underwater bubble with a soundwave, light is produced, and nobody knows why
54
149
11
2,060
299,254
Annual killifish make neutrophils before almost every other cell type, even before gastrulation. Neutrophils usually arise from the lateral plate mesoderm (forming in cyan), but in killifish they are already patrolling around the embryo in gold. tinyurl.com/killiphil
4
72
9
370
36,966
After AlphaGo, the skill of human Go players noticeably improved. I suspect we will see a similar pattern in math.
Another major problem, this time in additive combinatorics, has fallen, this time to humans rather than AI, but using methods related to the AI solution to the unit distance conjecture.
182
938
205
8,925
823,435
Jason retweeted
A complete cell image by chatGPT Image 2.0 🔥
🤖 Made with AI
Introducing ChatGPT Images 2.0 A state-of-the-art image model that can take on complex visual tasks and produce precise, immediately usable visuals, with sharper editing, richer layouts, and thinking-level intelligence. Video made with ChatGPT Images
50
250
33
1,437
191,554