Arjun Raj
@arjunrajlab
Just another LLM. Tweets do not necessarily reflect the views of people in my lab or even my own views last week. http://rajlab.seas.upenn.edu
Good news. After 2 rounds of venetoclax, GO, + chemo, my daughter has had a complete response. No detectable signs of the tumor that had completely shut her eye, which she was dangerously close to losing. 🙏🏾 to the amazing team @StJude & the community for helping us get here.
Honored to receive the Kabiller Rising Star Award along with other awardees @NPeppas and Nathan Gianneschi! Blessed to have incredible students, postdocs, and collaborators that make this possible. Look forward to sharing the latest @MJMitchell_Lab work at @IINanoNU this Fall!
Michael Mitchell receives the Kabiller Rising Star Award. His innovations in cancer immunotherapy and gene delivery at @PennEngineers are shaping next-generation treatments and inspiring future bioengineers.
The equivocation of age comes both with the worry of a creeping relativism and the hopefulness of compassion.
I’d love to hear biologists weigh in on the fundamental question: can you predict the impact of cell perturbations better by studying the natural variation in a population of healthy cells (more data), or by studying cells that have been perturbed genetically or chemically?
virtual cells are currently bottlenecked by compute, not novel data: drug discovery is an iterative search process (design, test, analyze) through therapeutic design space guided by a dynamics model directly trawling this therapeutic space with large hypothesis-free…
For biological data, if you don't have deep expertise in this low value work called data cleaning, u r lacking a fundamental understanding of the idiosyncrasies of the data. Without this knowledge, it is impossible to seriously model data.
Academia must be the only industry where extremely high-skilled PhD students spend much of their time doing low value work (like data cleaning). A 1st year management consultant outsources this immediately. Imagine the productivity gains if PhDs could focus on thinking
A creative use of the main features of #gastruloids to explore some important issues of #DevBio. An experimental tour de Force with some really interesting results and questions. We learn from models! #Heterogeneities #PatternFormation #Embryos #SCBEMs.
[1/8] We used a fluorescence-based lineage tracing approach to track individual clones in a polyclonal aggregate. Pure clones are worse at forming gastruloids. But crazily enough, if you mix them with the original bulk population, they do great!
Wonderful work on a system w/some/much of the embryo complexity but is simple enough to allow exploration of details & learn something from the work. Love the development of #NewMeasurements. Much insight and emergence of important questions @ #PatternFormation #Gastruloid
Link to BioRxiv: biorxiv.org/content/10.110…
Check out this awesome work from @VinayA116! Embryo Economics!
[0/8] Super stoked to share our work with @arjunrajlab on tissue organization in the gastruloid. We use lineage tracing and spatial transcriptomics to show that diversity among stem cell clones promotes, rather than hinders, gastruloid development: biorxiv.org/content/10.110…
I'm happy to share a highlight from our recent work!
New online! Spatial multi-omics of nuclear architecture with two-layer seqFISH+ bit.ly/46eTdez
RT to help Simon raise awareness of prompt injection attacks in LLMs. Feels a bit like the wild west of early computing, with computer viruses (now = malicious prompts hiding in web data/tools), and not well developed defenses (antivirus, or a lot more developed kernel/user…
If you use "AI agents" (LLMs that call tools) you need to be aware of the Lethal Trifecta Any time you combine access to private data with exposure to untrusted content and the ability to externally communicate an attacker can trick the system into stealing your data!
Excited to share our new study on how resistance to AKT inhibition is linked to lineage differences within breast cancer 👇🏽biorxiv.org/content/10.110… and also surprisingly/worryingly good AI generated podcast 🎧notebooklm.google.com/notebook/28ebc…