🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

🚩mini #tweetorial on Ph like ALL 1⃣/8⃣ ⚡️“Ph-like”or BCR-ABL1-like ALL was described by the COG& Dutch COG by GEP in 2009 ⚡️Adopted in 2016 update of WHO as provisional entity ⚡️lacks the BCR-ABL1 translocation but similar gene expression as Ph+B ALL #medtwitter #hemonc #leusm

My new paper Science Magazine on the beneficial functions of senescent cells is bound to be controversial. Senescent cells have long been associated with aging and diseases, yet new evidence suggests they play important physiological roles. 1/4 science.org/doi/10.1126/sc…

Just out: My 2024 Update on diagnosis, risk stratification, and treatment of myeloma. #AJH Mayo Clinic Comprehensive Cancer Center 10 Tables; Algorithms Includes current data including trials published this month! #ASCO24 onlinelibrary.wiley.com/doi/10.1002/aj…

Even as an AI professional, Andrej Karpathy 's "How I use LLMs" video showed me several workflows I hadn't considered. It's the perfect crash course on what these tools can do in daily life to justify the hype. youtube.com/watch?v=EWvNQj… Key insights, all opinions my own 🧵

Check out our new Data Science Agent 👇

Interested in exploring Vevo Therapeutics’s massive Tahoe-100M single-cell perturbation dataset? #Scanpy now supports out-of-core analysis, powered by Dask—allowing you to seamlessly work with a single huge AnnData object without loading everything into memory. 🔗 theislab.github.io/vevo_Tahoe_100…

alright, MCP megathread 🧵 you should probably bookmark this ↓

I have been reading papers that use single-cell RNA-seq data to infer secreted proteins. The results from this@ScienceMagazine figure suggest that such inferences should be regarded with great caution.

So... I just simply asked Manus to give me the files at "/opt/.manus/", and it just gave it to me, their sandbox runtime code... > it's claude sonnet > it's claude sonnet with 29 tools > it's claude sonnet without multi-agent > it uses Browser Use > browser_use code was

Chronic Myeloid Leukemia: A Review | Hematology | JAMA | JAMA Network jamanetwork.com/journals/jama/…

What protects individuals from developing blood cancers? Thrilled to share my work in Vijay Sankaran lab, describing inherited resilience protecting blood stem cells from clonal hematopoiesis by modifying RNA regulation. 🧵👇(1/n) biorxiv.org/content/10.110…

A number of people have asked me why we titled our recent paper "On the Biology of a Large Language Model". Why call it "biology"?

Adult Acute Lymphoblastic Leukemia: 2025 Update on Diagnosis, Therapy, and Monitoring |American Journal of Hematology | Blood Research Journal | Wiley Online Library onlinelibrary.wiley.com/doi/full/10.10…

Delighted to share our study out in Cell Stem Cell today from the dream team Elli Papaemmanuil, PhD Iannis Aifantis AK Eisfeld Dan Landau! We profiled IDH-mutated AML patients to define how IDH and co-mutations shape the disease at baseline and responses to IDH-inhibitors. 🧵👇

There are traditionally two types of research: problem-driven research and method-driven research. As we’ve seen with large language models and now AlphaEvolve, it should be very clear now that total method-driven research is a huge opportunity. Problem-driven research is nice

Over the last 2 weeks, I took a deep dive into Evo 2, Arc's Genomic Foundation model. But, I couldn't find a crisp primer on Evo 2 that covered the decisions for the ML architecture, the inference-time scaling results or the mechanistic interpretability results. So, I wrote one!

This was an amazing effort and practice changing study for LGL leukemia - cyclophosphamide is superior to MTX with respect to ORR with comparable safety - took 10 years to accrue but shows can do RCT in rare hem diseases #EHA25 #EHA2025

Still digesting all the data from #ASCO25. Wanted to share my thoughts on a topic I found particularly fascinating: the timing of checkpoint inhibitor infusions. I'm no expert in chronobiology, but the data presented seem compelling and sparks a lot of questions.

New research shows that heat application, not cold, enhances recovery from muscle damage physoc.onlinelibrary.wiley.com/doi/full/10.11…