Delighted to finally announce that Lotfollahi Lab starts this year at @sangerinstitute and @CC4AIM in Cambridge University. The lab will develop core AI/ml systems and also generate large scale multi-modal cellular data to advance cell engineering: sanger.ac.uk/group/lotfollah…

Left Bulgaria at age of 15 to go to colleague in the US studying physics. Saw my family 4 times in the span of 20 years. Worked every Christmas and other holidays. All my grandparents died without me knowing. I haven’t met most of my cousins. My mom died without me knowing and I’ve never been to her grave. Graduated from UCSF with a Nature paper(among others) , was a WI /MIT fellow with a corresponding author Nature paper( among others) , was hired at Harvard as an assistant professor only to be called “Diversity Hire” by many. Thank you physics…

So true

Our spatio-temporal map of lesion repair in the heart at single-cell resolution is now published in @NatureCVR. nature.com/articles/s44161-0… We dissected dynamics of multicellular niches that control cardiac repair. See 🧵for highlights.

We are preparing for Halloween 🎃

Calling on all scientists to call out hype, grift & BS when u see it. If u don't, u risk anti-science grifters leveraging overhyped & underdelivered promises & shoddy science to destroy public trust in the enterprise. Keep science & science comm grounded & truthful.

Huge paper from Dan Landau! Such an exciting time for the somatic mutation field. Congrats Dan and team!

We had our first-ever Lotfollahi Lab retreat. Science, fun, and a lot of laughter all at once! 🎉 Big shoutout to our amazing experimental team and collaborators for bringing so much energy and inspiration 🌲🧬

it's been more than a decade since KD was proposed, and i've been using it all along .. but why does it work? too many speculations but no simple explanation. @_sungmin_cha and i decided to see if we can come up with the simplest working description of KD in this work. we ended up with a very simple explanation for any mixture distribution, starting from a mixture of gaussians. the key hypothesis was that using lower-entropic, approximate sampling from a teacher, results in a higher-precision but lower-recall student. since an autogressive LM is nothing but an infinite cascade of mixture distribution, we confirm this with SmolLM (thanks, @huggingface!) this is probably not the complete picture of KD, but i can definitely sleep better after writing down and confirming this minimal working explanation. as an extra take-away, this implies that our eval tends to be overly precision focused. we should really think of what we lose in terms of recalls, as this directly relates to what we miss out for whom when we build these large-scale, general-purpose models.

I came on an H1B “specialty occupation” visa and there’s no way I could have afforded a $100K fee. The US has just made it virtually impossible for people like me to come here

Working on a new blog post to estimate when we can simulate cells atom-by-atom. I analyzed 500 papers published in last 35 years to look at the duration of all-atom simulations and how many atoms can be modeled.

“The beauty of mathematics only shows itself to more patient followers.” - Maryam Mirzakhani

🚨 Two weeks left to apply for the EMBL-EBI–Sanger Postdoctoral (ESPOD) Programme. Ready to take the next step in your science career? Applications close on 30 Sept 2025. ebi.ac.uk/research/postdocs/… #postdoc #sciencecareers

Had the pleasure of presenting our lab's vision and new work at the Haus der Industrie for the AITHYRA Institute opening & science symposium. 🎉 Even better, it was my birthday! What a way to celebrate with science. Thanks @mmbronstein and AITHYRA team 🙌 PS: amazing dinner & visit with @kchonyc and @MoAlQuraishi at KHM Art History Museum, Vienna 🎨

Exciting chat with @dana_peer in Vienna, a lot of cool insights as always

It was a pleasure to present

AITHYRA Symposium #AIforLifeScience: One Cell at a Time—AI and the Single-Cell Revolution

New review 🔥 Single-cell RNA-Seq has been revolutionary for studying eukaryotic cells and now it's time for it to do the same for microbes! We describe the technology for single-bacterium RNA-Seq & the questions now studied using it.🧵⬇️ science.org/doi/10.1126/scie… @AndrewPountain

🌎👩‍🔬 For 15+ years biology has accumulated petabytes (million gigabytes) of🧬DNA sequencing data🧬 from the far reaches of our planet.🦠🍄🌵 Logan now democratizes efficient access to the world’s most comprehensive genetics dataset. Free and open. doi.org/10.1101/2024.07.30.6…

Select your cell: I'm prototyping an interactive sc RNA-seq portal where the UMAP is dynamically linked to morphing 3D artistic renders of each cell type. You can play with the initial build below.

🚨 Postdoc opportunity! Join the prestigious EMBL-EBI–Sanger Postdoctoral (ESPOD) Programme bridging @sangerinstitute & @embl 🔬 Projects: 1️⃣ AI-driven single-cell perturbation exp design m. (with @Muzz_Haniffa @saezlab) 2️⃣ Predicting cell phenotypes of new compounds using generative modeling (with Jess Ewald) 💰 £3,383/month (after tax) 📅 36 months | Start within 12 months ⏳ Apply by 30 Sept 2025 👉 apply here; ebi.ac.uk/research/postdocs/… #Postdoc #AI #SingleCell #Genomics #Career