The dichotomy between the mainstream media Draco Ian narrative to nationalize and cancel education and silo communications versus the reality of highly credentialed computer nerds playing God casually
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.
@Admiral_Ragnar@FitAndFortune@_sorrengailll and they built no character and learned no perseverance, patience, critical thinking, basic anatomy etc by losing weight to balance their compulsive greed which wiill now instead be channeled into sports betting and cp and fomo anxiety . Almost like a closed loop ecosystem
@Admiral_Ragnar@FitAndFortune@_sorrengailll Now those people are indefinitely dependent on the pharmaceutical company so they can be instagram ready when they receive their government issue crypto currency check because they are jobless and won’t get off their formerly fat ass
@FitAndFortune@_sorrengailll You solved convenience * for the affluent and techies who already had white collar jobs and then ground the middle class into the dirt. Ftfy
@iveyzackary73 @LegalTule Just curious why the little ad mark disappeared now. Did you de-monetize the post ? Otherwise it wasn’t really shared out of love
@iveyzackary73 @LegalTule It’s a label not an insult. You are a tool contributing to the alt right agenda which cut outside advertisers from this site to give room for pay to play extremists with a shared agenda.
Not to mention you are profiteering off g-d’s word which is performative and trump adjacent.
@iveyzackary73 @LegalTule This makes sense because musk is the dummy buffer separating x/former twitter from being considered a govt run agency and thus sheltered from sep. of church and state. Thanks
@BaronBoehm@AutismCapital Is that kalshi? Funny how prez used the media and slews of email spam (still deleting from 2020) to defend against witch-hunts then pulls one on Christmas
Do I get a medal for showing that it’s white male woman hating faux Christians controlling this entire land of Oz that makes all the little girls kill themselves or do I get black bagged and shot in the face in an alley somewhere or stabbed like the cash app guy