Moe Samour

Malignant Hematology physician. Cleveland Clinic - NIH - Geisinger. What opinions?

[Vincent Rajkumar @VincentRK]

Just out: Chronic myeloid leukemia: the definitive CML review and current treatment algorithms by @FadiHaddad_MD @DrHKantarjian @BloodCancerJnl #OpenAccess

https://t.co/U28uIP1Ltc

[Moe Samour @mosamour]

@Papa_Heme I also include 4. Consumption when I teach students. Easy to forget

[Moe Samour @mosamour]

@Papa_Heme Yep

[Moe Samour @mosamour]

Will be in NYC for tech week events this weekend. Hmu if you're curious, interested, or working in digital health or AI in clinical medicine.

[Moe Samour @mosamour]

@ycombinator @Plena_Health I wonder who coined the term AI OS?

[Moe Samour @mosamour]

@MarkFaberDO Not always concordant. treating someone with hydrea (which technically reduces counts) doesnt help from the very limited experience (vs HMA). It's not simply about "count reduction" in the PB

[Moe Samour @mosamour]

Third patient with lysozyme induced kidney injury from MPN/MDS in less than a year. I think this is under recognized.

[Moe Samour @mosamour]

@msnnaydn Send for lysozyme/muramidase in the blood. if really high, consider kidney biopsy. Obv don't send this on everyone. Look at CBC (absolute monos) trends over time and track with Scr for clues

[Moe Samour @mosamour]

@DavidBursteinMD I am building this

[Moe Samour @mosamour]

@ColtonOrtolf Working on it!

[Moe Samour @mosamour]

@VincentRK @RahulBanerjeeMD Ah, you didn't say "don't make mistakes" that's why

[Moe Samour @mosamour]

@HealthcareAIGuy @Peterson_HTI I expected this and have a solution for it!

[Henry C Fung| MM, lymphoma, leukemia & CART @HenrychihangFu1]

S2213 asks whether SCT adds value after modern ind in good-risk AL. At best, SCT may modestly improve PFS or MRD depth not OS. But tx interruption & toxi remain concerns, parti with cardiac AL.
In AL, rapid and sustained LC suppression may matter more than maximal cytoreduction

[Moe Samour @mosamour]

@Papa_Heme I am building this actually

[Moe Samour @mosamour]

@Papa_Heme @forallcurious Triple therapy targeting KRAS/EGFR/STAT3 apparently... Revolutionary! /s

[Moe Samour @mosamour]

@sundarpichai @GoogleResearch @fmahvar @osanseviero @asellerg @virmani https://t.co/41NWl7iZWu

[Ilya Abyzov @IlyaAbyzov]

OpenAI has acquired 🔥@TorchHealth

The Torch team and I are joining OAI to help build ChatGPT Health into the best AI tool in the world for health and wellness.

[Moe Samour @mosamour]

@sundarpichai @GoogleResearch @fmahvar @osanseviero @asellerg @virmani

[Moe Samour @mosamour]

@sundarpichai Thanks! I'm building my entire stack over medgemma models

[Moe Samour @mosamour]

@oozn Turkish airlines has some of the best plane food

[Markus J. Buehler @ProfBuehlerMIT]

How does an embryo reliably "compute" its form - "cell by cell" - using only local interactions and mechanics, yet produce a precise global body plan? I’m excited to share our Nature Methods paper "MultiCell: geometric learning in multicellular development", presenting #AIxBiology research led by @HaiqianYang and the result of a great collaboration with Ming Guo, George Roy, Tomer Stern, Anh Nguyen and Dapeng Bi.
A long-standing challenge in developmental biology is to predict how thousands of cells collectively self-organize as tissues fold, divide, and rearrange. In MultiCell, we represent a developing embryo as a dual graph that unifies two complementary views of tissue mechanics with single-cell resolution: cells as moving points (granular) and cells as a connected foam (junction network). This lets the model learn dynamics from both geometry and cell–cell connectivity.
On whole-embryo 4D light-sheet movies of Drosophila gastrulation (~5,000 cells), our model predicts key cell behaviors and the timing of events, including junction loss, rearrangements, and divisions with high accuracy, at single-cell resolution. Beyond prediction, the same representation supports robust time alignment across embryos and offers interpretable activation maps that highlight the morphogenetic "drivers" of development. The broader goal is a foundation for cell-by-cell forecasting in more complex tissues, and eventually for detecting subtle dynamical signatures of disease.
Kudos to the team for this inspiring collaboration with brilliant researchers to push the boundary of AI for biology!
Citation: Yang, H., Roy, G., Nguyen, A.Q., Buehler, M.J., et al. MultiCell: geometric learning in multicellular development. Nature Methods (2025), DOI: 10.1038/s41592-025-02983-x
Code/data links are in the manuscript.