Sign in

Arjun Raj

@arjunraj.bsky.social
6.7K followers 1K following 411 posts

Just another LLM. Tweets do not necessarily reflect the views of people in my lab or even my own views last week. rajlab.seas.upenn.edu rajlaboratory.blogspot.com

PostsRepliesMedia
Reposted by Arjun Raj
Itai Yanai @itaiyanai.bsky.social · 17/07/2026
Maybe creativity is just how big a bag of tricks you have; how many different tricks you've seen, applied in different contexts. And perhaps some people have a little bit more skill remembering all those tricks or applying them in different situations. - Arjun Raj, @arjunraj.bsky.social
1185
Reposted by Arjun Raj
Ted Pavlic (he/him/his) @tedpavlic.bsky.social · 13/08/2026
Side note: If students are using LLMs to help them choose statistical processing pipelines, these skills/plugins may help to synthesize more rigorous choices (via @arjunraj.bsky.social). arjunrajlab.substack.com/p/keeping-yo...
arjunrajlab.substack.com
Keeping your analysis correct: mycelium and scilintr
Coding agents have made data analysis far easier to produce. The hard part now is verifying what comes out. Here’s the scaffolding I built to help.
041
Reposted by Arjun Raj
Ted Pavlic (he/him/his) @tedpavlic.bsky.social · 12/08/2026
Updated my guide on using LLMs with #Rstats (including #Rstudio, #Positron, and #VSCode options) to be more BYOK friendly and reflect changes in both VS Code Chat and Posit Assistant. github.com/tpavlic/docs...
github.com
131
Reposted by Arjun Raj
Christophe 🔬 Leterrier @christlet.bsky.social · 30/06/2026
Scientist goals: get @quantamagazine.bsky.social to write about our work. Check this super nice article about Sophie Dumont's lab poking mitotic spindles:
quantamagazine.org
What Breaks a Cell’s Ribs Can Make It Stronger | Quanta Magazine
The mechanical process of cell division exerts powerful, if microscopic, forces. How do the molecular machines that power it manage the strain?
075
Reposted by Arjun Raj
Richard Sever @richardsever.bsky.social · 01/04/2026
Why bioRxiv
16019
Reposted by Arjun Raj
Alfonso Martinez Arias @amartinezarias.bsky.social · 31/03/2026
Thank you. My colleagues and I are pleased that we developed a system that works and that 11 years and over 100 papers #gastruloid papers later, what we felt in the final paragraph of the paper is coming along. There is now a community improving and learning from the system.
1174
Reposted by Arjun Raj
Cara Brand @carabrand.bsky.social · 24/02/2026
Grateful to have worked with such an incredible team on this project. Excited to finally share this story about Top2 evolution and hybrid incompatibility in Drosophila. More to come!
0217
Arjun Raj @arjunraj.bsky.social · 28/03/2026
Hope you like it! It’s one of my very favorite papers from the lab ever.
000
Arjun Raj @arjunraj.bsky.social · 27/03/2026
I had two undergrads in my office today working on a computational project. My normal advice in research is to use tools to their fullest to get to the cutting edge. For the first time, I was reluctant. I worry that using coding agents would rob them of something. And I’m fully AI-pilled.
6272
Reposted by Arjun Raj
Paperpile @paperpile.com · 26/03/2026
🧮 Check things that should add up ⚠️ Never ignore code warnings 📊 Track datapoints like the number of rows 🔍 Investigate outliers 🧠 If something doesn’t make sense, keep digging arjunrajlab.substack.com/p/transition...
arjunrajlab.substack.com
Transitioning to being a PI in the age of AI
Computational biology is in a period of upheaval that is both exhilarating and terrifying.
013
Reposted by Arjun Raj
Paperpile @paperpile.com · 26/03/2026
AI is pushing computational biology into analytic abundance. The bottleneck is no longer generating results: It’s deciding whether to trust them. 📊 5 habits for sense-checking outputs, via @arjunraj.bsky.social 1/2
193
Arjun Raj @arjunraj.bsky.social · 26/03/2026
It is still mind boggling to think about how quickly that all changed.
130
Reposted by Arjun Raj
Alfonso Martinez Arias @amartinezarias.bsky.social · 25/03/2026
A white paper on Stem Cell Based Embryo Models #SCBEM #Innovation #Ethics #Policy, from the community to highlight the potential of this new area of research and its impact in #ReproBiology shorturl.at/dAWL2
0219
Arjun Raj @arjunraj.bsky.social · 26/03/2026
I think there are many proposals that would be better than the current system :).
010
Arjun Raj @arjunraj.bsky.social · 26/03/2026
Generally speaking, I don’t think review is an efficient way to make science better.
010
Reposted by Arjun Raj
napari @napari.org · 24/03/2026
napari 0.7.0 is available now! 🚀🎉 It's a BIG release so read the full release notes, with highlights: napari.org/stable/relea... We want to thank everyone who has worked incredibly hard on this release including our 11 new brilliant contributors 🤩 and the community for their support and feedback!
napari.org
napari 0.7.0
Mon, Mar 23, 2026 We’re happy to announce the release of napari 0.7.0! napari is a fast, interactive, multi-dimensional image viewer for Python. It’s designed for browsing, annotating, and analyzing…
14420
Arjun Raj @arjunraj.bsky.social · 25/03/2026
Interesting. Of course the problem is that if someone has methodological issues coming in, they’ll probably also have them later after the review is long gone. The truth is past rigor reflects future rigor more than we care to admit.
120
Reposted by Arjun Raj
Anthropic {bot} @anthropicai.xmirror.bot · 23/03/2026
Introducing the Anthropic Science Blog. Increasing the pace of scientific progress is a core part of Anthropic’s mission. The Science Blog will feature new research and stories of how scientists are using AI to accelerate their work. Read the intro:
anthropic.com
Introducing our Science Blog
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
14110
Reposted by Arjun Raj
Dmitri Petrov @petrovadmitri.bsky.social · 24/03/2026
A question for biologists: we often talk about evolutionary novelty. What does “novelty” mean for you? What’s your favorite definition if any? Or just a rule of thumb for what is and isn’t novel.
183718
Reposted by Arjun Raj
James Briscoe @jamesbriscoe.bsky.social · 25/03/2026
Honoured and overwhelmed to receive the 2026 Waddington Medal. Science is a team effort, and I've been fortunate to work alongside exceptional people asking hard questions. Thank you to the BSDB and to everyone who has been part of the journey. bsdb.org/2026/03/24/2...
bsdb.org
2026 Waddington Medal Winner - James Briscoe - BSDB - British Society for Developmental Biology
We are very pleased to announce that this year’s Waddington medal winner is James Briscoe. His fundamental discoveries have helped shape our understanding of of how morphogens work, and he has played ...
2626630
Reposted by Arjun Raj
UPENN_ITMAT @itmat.bsky.social · 24/03/2026
Untangling mechanisms underlying #CancerDrugResistance www.nature.com/articles/s41... @jess_ljx @arjunraj.bsky.social #Cancer #DrugResistance #TranslationalScience
nature.com
AP-1 mediates cellular adaptation and memory formation - Nature Communications
Cellular responses to stimuli can involve learned behaviors through memory formation. Here, the authors show that cancer cells encode gene expression into cellular memories during therapy resistance v...
032
Reposted by Arjun Raj
Mir Lab @mirlab.bsky.social · 20/03/2026
@mukherja.bsky.social work on RNAPII clusters is in print today: www.nature.com/articles/s41... Congrats! TLDR: RNAPII clusters represent transcriptonally engaged molecules at single genes, not super-stochiometric assemblies. Please check it out and see the the thread below for a summary.
nature.com
A single cluster of RNA Polymerase II molecules is stably associated with active genes - Nature Communications
Live molecular-scale imaging in fly embryos shows that a single RNA Polymerase II cluster stays bound to active genes during transcription. Cluster formation requires initiation, and intensity represe...
04917
Reposted by Arjun Raj
Steve Fleming @smfleming.bsky.social · 22/03/2026
Scientific publishing: Rethinking how research is reviewed and published Review of how the loss of impact factor affected submissions at eLife - uneven drop across countries, but generally holding up remarkably well and shows a new model is possible elifesciences.org/articles/110...
elifesciences.org
Scientific Publishing: Rethinking how research is reviewed and published
Taking a radical new approach to the publication process resulted in eLife losing its impact factor, but authors, reviewers, editors and funders support the journal and its efforts to reform scientifi...
28434
Reposted by Arjun Raj
Zebrafish Rock! 🎃 @zebrafishrock.bsky.social · 22/03/2026
Live imaging of macrophages and neutrophils in a transgenic zebrafish larva. Credit to Prof. Anna Huttenlocher Lab @uwmadisonmmi.bsky.social. #ZebrafishZunday 🧪
24511
Arjun Raj @arjunraj.bsky.social · 21/03/2026
Blog post: transitioning to being a PI in the age of AI open.substack.com/pub/arjunraj...
open.substack.com
Transitioning to being a PI in the age of AI
Computational biology is in a period of upheaval that is both exhilarating and terrifying.
1357
Arjun Raj @arjunraj.bsky.social · 21/03/2026
Thank you!
000
Arjun Raj @arjunraj.bsky.social · 21/03/2026
Interesting! I disagree with this statement: “AI cannot coexist with education — it can only degrade it.” It is far more nuanced than that. AI is a tool that can help and hurt. It moves so fast that coming up with a uniform policy is counterproductive. Either way, it is here and we must engage.
050
Arjun Raj @arjunraj.bsky.social · 21/03/2026
One of my very favorite papers from the lab! Shows that individual cells can learn by forming memories. Amazing work by Jess Li!
14215
Arjun Raj @arjunraj.bsky.social · 08/02/2026
A moment of introspection on how much the world has changed during the time between the initial submission and this (hopefully final) revision: "This paper seems so quaint now" "Let's think of it as having contributed an important bit of high-quality training data to Opus 4.7"
0100
Arjun Raj @arjunraj.bsky.social · 31/01/2026
Claude Code demo, planning another with more details.
010
Arjun Raj @arjunraj.bsky.social · 31/01/2026
Ran an AI coding workshop with the lab. There was a palpable sense of sadness realizing that skills some of us have spent our lives developing (myself included) are a lot less important now. I see the future 100%, but I do think it's important to acknowledge this sense of loss.
6302
Reposted by Arjun Raj
Adlung Lab @adlunglab.com · 20/01/2026
The TIG1-high state exists in human lung club and ciliated cells, enriched in IPF patients and tobacco users. Different viruses target different states. Influenza A prefers KRT8-high cells. Arjun Raj @cp-cell.bsky.social doi.org/10.1016/j.ce... 🧪 3/3
031
Reposted by Arjun Raj
Adlung Lab @adlunglab.com · 20/01/2026
Reffsin, Miller, Cherry & Raj et al. discover that intrinsic cell states determine which cells become infected with SARS-CoV-2. Using single-cell clone tracing, they identified a TIG1-high state marking highly susceptible cells. What makes these cells vulnerable? 👇🏻 1/3
252
Reposted by Arjun Raj
Paperpile @paperpile.com · 19/01/2026
Data and experiments move faster, but theory is what gives discovery direction, via @arjunraj.bsky.social arjunrajlab.substack.com/p/chance-fav...
arjunrajlab.substack.com
Chance favors the (theoretically) prepared mind
In defense of the role of theory in innovation
021
Reposted by Arjun Raj
Paperpile @paperpile.com · 12/01/2026
We spend a lot of energy choosing the right research project. But an equally important skill is knowing when to walk away. Quitting isn’t failure: It’s how you make room for better science, via @arjunraj.bsky.social
152
Reposted by Arjun Raj
Mark @mkeller7.bsky.social · 10/01/2026
libertypuzzles.com these are very nice
libertypuzzles.com
Liberty Puzzles | Wooden Jigsaw Puzzles
The original wooden jigsaw puzzle maker. Established in 2005, all of our 1000+ puzzles are handmade in Boulder, CO with exquisite quality & craftsmanship. Full of odd-shaped "whimsy" pieces, our woode...
241
Reposted by Arjun Raj
Blitzy 🩺 ⚡️🏁 @blitz-y.bsky.social · 10/01/2026
Anyone have a thought about this weird mol on my hand?
My left hand with Avagadro’s Constant
5274
Arjun Raj @arjunraj.bsky.social · 09/01/2026
Where do you get your groceries? Where are your retirement funds invested? Etc.
110
Arjun Raj @arjunraj.bsky.social · 09/01/2026
I gotta say… it’s just less fun here. I want it to work, but…
530
Arjun Raj @arjunraj.bsky.social · 09/01/2026
Congratulations!!
000
Reposted by Arjun Raj
Ishmail Abdus-Saboor @ishmailsaboor.bsky.social · 02/07/2025
I am happy to share that I’ve been awarded tenure here at Columbia University. Alhamdulillah. I thank my wife, parents, mentors, colleagues, friends, and family. I thank my lab members, present and past, for entrusting their careers in my hands and making this a thrilling journey.
5948617
Arjun Raj @arjunraj.bsky.social · 08/01/2026
I can say that the discussion on X are definitely more interesting. Here, it’s like AI isn’t even happening.
000
Arjun Raj @arjunraj.bsky.social · 07/01/2026
Both, and things in between. It’s highly variable as to how much it can do autonomously in both cases. Probably depends on how much training data there is.
010
Arjun Raj @arjunraj.bsky.social · 07/01/2026
Both. General purpose non-coding agent ;).
030
Arjun Raj @arjunraj.bsky.social · 07/01/2026
Huh. I think the scope it can handle probably depends on the nature of the challenge (how much it is in distribution) and on the planning and amount of testing you have in place. I have found it able to do some pretty remarkable features, one-shotting a lot of non-trivial boilerplate.
110
Arjun Raj @arjunraj.bsky.social · 07/01/2026
Haven't run into trouble yet! But I've been sadly too busy to code as much as I have wanted.
010
Arjun Raj @arjunraj.bsky.social · 07/01/2026
What I have not explored but should is non-coding uses.
120
Arjun Raj @arjunraj.bsky.social · 07/01/2026
Much to say, but to summarize: 🤯
100
Arjun Raj @arjunraj.bsky.social · 07/01/2026
I think that’s the first sign of the apocalypse, no?
130