Profile avatar
arjunraj.bsky.social
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 https://rajlaboratory.blogspot.com
321 posts 6,194 followers 1,006 following
Prolific Poster
Conversation Starter

NimbusImage is great for spot analysis using the Piscis model from Will Niu; give it a try! www.nimbusimage.com www.loom.com/share/49d795...

Awesome work from @atishayjay.bsky.social!

You can just take academic papers and paste them into Gemini 2.5/ChatGPT o3/Claude 4 with the prompt "build me a game based on this paper, make it interesting and thematic but still conveying key findings" and get a tiny working educational game. (In this case, I used Gemini)

I wonder if it would be worth doing the exercise of asking, assuming we could measure absolutely everything, what should we *not* bother measuring?

Today, I hooded a PhD student who is about to begin an exciting new chapter of their life. Later in the day, I called my PhD advisor to catch up after a few years. A good day, all in all.

Just like most drivers think they are above average at driving, most scientists think they are above average at writing.

Are you interested in synthetic and systems biology approaches to study #spatiotemporal processes in cancer? Join NCI for virtual workshops on May 13, 15, & 20 (next week!) from 12:00–4:30 PM ET: registration: events.cancer.gov/nci/syntheti... #SynSysBio4SpatialCancerResearch

It is somewhat jarring to think that it is reasonable to ask which will happen first: achieving AGI or getting the second round of reviews back on our paper.

This is the best place in Paris to buy reagents to quench your crosslinking experiment

Here it is! Bonsai. Now there is really no more excuse for using t-SNE/UMAP. Bonsai not only makes cool pictures of your data. It actually rigorously preserves its structure. No tunable parameters. Incredible work by @dhdegroot.bsky.social. I'm so excited about this! www.biorxiv.org/content/10.1...

Is it bad that my favorite gene is EEF2 because it gives really good RNA FISH signal?

Wow, just implemented the new Cellpose-SAM from @computingnature.bsky.social in NimbusImage and it's *awesome*! Give it a try! nimbusimage.com

🚀🔬🦠 Releasing 🤖Cellpose-SAM🤖, a cellular segmentation algorithm with superhuman generalization 🦸‍♀️. Try it now on 🤗 huggingface.co/spaces/mouse... paper: www.biorxiv.org/content/10.1... w/ @computingnature.bsky.social 1/n

While I understand the sentiment, I must disagree. We are already required to do too many different things at a high level. Communicating with the public is not an easy skill and requiring that students be good at it is in some ways another barrier. Instead, make a podcast with NotebookLM!

Friends. This is the first orchid ever I have not killed, and that has come back to life underneath my very not green thumbs. Please clap.

New podcast episode about @aofarrell.bsky.social's latest prepeint! creators.spotify.com/pod/show/arj...

Check out our latest preprint, led by Dr. Siyu Chen, that brings together an amazing team of scientists from several labs ( @vram142.bsky.social, Tavazoie, and Navickas) to tackle a fundamental problem in biology: how do cells regulate expression of their tRNAs? www.biorxiv.org/content/10.1...

very few things make me as happy as data replication by different hands.

Honored and humbled. I have been very fortunate to have worked with amazing, inspirational colleagues in my lab, at Penn and in the broader community. Science matters www.nasonline.org/news/2025-na...

🌍 GloBIAS is now open for members! Join our global community of scientists, developers & microscopists advancing BioImage Analysis. Let’s build tools, share knowledge & shape the field together. 🔗 More information: tinyurl.com/mtvjadex #BioImageAnalysis #GloBIAS #OpenScience

🚀 Excited to share that our work on BiaPy has been published today in Nature Methods! BiaPy makes deep learning accessible for bioimage analysis, from small datasets to terabyte-scale 3D images. 👇 (1/7) 🔗 www.nature.com/articles/s41... #DeepLearning #BioimageAnalysis #OpenSource #BiaPy

Pull apart a bronze trilobite (Cryptolithus bellulus) and put it back together. #TrilobiteTuesday #InverteFest (sound on for satisfying clicks)

So excited to see this live! Awesome work from @giannatbusch.bsky.social on the concept of population-based synergy—using cell-to-cell heterogeneity to uncover new therapeutic vulnerabilities!

Thank you to @arjunraj.bsky.social, of @pennmedicine.bsky.social, who spoke with us during #AACR25 about sensitivity to second-line inhibitors in treatment-resistant melanoma! Check out our site for more conference insights! @theaacr.bsky.social #melsm #oncology www.onclive.com/conference/a...

It’s out! The evolutionary origins of yeast point centromeres uncovered! “Ancient co-option of LTR retrotransposons as yeast centromeres” www.biorxiv.org/content/10.1...

“We tested whether [cellular pathway or process X] upregulates [cellular pathway or process Y]. It does!*” (Don’t forget to put * p=0.5) “We tested whether [cellular pathway or process X] affects [cellular pathway or process Y]. It does!*” (Don’t forget to put * p=1.0)

As a listener, the flip side *could* be: thank you for not subjecting me to your terrible hand-made presentation and instead giving me something far more clear and comprehensible. I suspect this complaint is actually more about the content itself.

Check out our paper, now extensively revised and published in @cp-molcell.bsky.social! This has been a real tour de force led by Stephanie Sansbury and @ysereb.bsky.social and we are very excited about the findings and future potential of this approach www.cell.com/molecular-ce...

It was so much fun to write this review with @usymmons.bsky.social on the conceptual underpinnings of single cell biology!

Yesterday, we discussed biological questions that need single-cell proteomics, which reminded me of this article: Single cell protein analysis for systems biology portlandpress.com/essaysbioche... 1/2

this is like one of the two best jokes in computer science

One of the toughest parts of the field of massively parallel reporter assays to measure >~thousands of elements is that there are hundreds of pubs using them, but no central repo to easily locate the results....until now! Great collab w/ Jingjing Zhao, Ilias G-S, and @nadavahituv.bsky.social!!