Johnny Yu

Hey would a presentation on tahoe100 be a good one for this?

We had a lot of fun with this project. From idea to preprint it was only 4 months! ⚡

Team work makes the dream work!

Just the start of a movement

Yup split pool was an early key choice we made. Data is really not bad though, 1tb and you'll probably see some ultra dask type data structures to remove ram limitations super soon. So just solid state hdd and that'll be easy for a 1tb dataset

This is a good question

Let's go 🚀🌕

We're excited! Stay tuned as this year several models built on this data are going to come out in quick succession 🙂

Keep an eye on this - we're just getting started! Hope to have the ML community engaged as we continue in this direction 🚀

Tahoe-100M: A Giga-Scale Single-Cell Perturbation Atlas for Context-Dependent Gene Function and Cellular Modeling Building predictive models of the cell requires systematically mapping how perturbations reshape each cell's state, function, and behavior. Here, we present Tahoe-100M, a giga-scale single-cell atlas ...

@thejohnnyyu.bsky.social, @therealnima.bsky.social, and I, are excited to tell you about Tahoe-100M! The largest publicly available single-cell dataset that measures the effect of 1200 genes on 50 cell line models. The Vevo team has outdone itself. #Tahoe100M www.biorxiv.org/content/10.1...

This was all made possible by the Mosaic platform! What is Mosaic? @thejohnnyyu.bsky.social took his work in our lab, and scaled it in every dimension… Mosaic brings a highly diversified, exquisitely optimized, and optimally balanced “cell village” approach to perturbation data collection.

Vevo Therapeutics Open Sources Tahoe-100M, the World's Largest Single-Cell Dataset, as the Inaugural Contribution to Arc Institute's New Virtual Cell Atlas /PRNewswire/ -- In a landmark move to advance AI-driven biological research, Arc Institute and Vevo Therapeutics announced today that they have partnered on...

If you are intrigued by this, and if you're working on AI/ML, single-cell biology, or drug discovery, I urge y’all to reach out to @thejohnnyyu.bsky.social, @therealnima.bsky.social or any of the @vevotherapeutics.bsky.social team. www.prnewswire.com/news-release...

YouTube video by No Priors: AI, Machine Learning, Tech, & Startups No Priors Ep. 103 | With Vevo Therapeutics and the Arc Institute

Watch @thejohnnyyu.bsky.social @therealnima.bsky.social (@vevotherapeutics.bsky.social), @pdhsu.bsky.social , Dave Burke and I (@arcinstitute.org) talking about virtual cells, and how #Tahoe100M, now on. @arcinstitute.org's Virtual Cell Atlas, can change the game!

www.youtube.com/watch?v=ak_f...

Multiplexed mosaic tumor models reveal natural phenotypic variations in drug response within and between populations Many agents that show promise in preclinical cancer models lack efficacy in patients due to patient heterogeneity that is not captured in traditional assays. To address this problem, we have developed...

Our latest from the indefatigable @thejohnnyyu.bsky.social in collaboration with Weissman and Shokat labs. Meet GENEVA, which enables simultaneous phenotyping and profiling of cancer cell drug responses at scale; both in vitro and in vivo across a variety of models: www.biorxiv.org/content/10.1...

This will be instrumental for data sets like our Tahoe 100 million. Especially as we scale into normalizing 100 million cell data sets

scRNA-seq data sets exploding in number and size - check out scanpy & anndata for >1b cells: new experimental update includes APIs for scaling with dask from anndata, integrated with lots of scanpy and rapids-singlecell functions.
gist.github.com/ilan-gold/98...

keep in touch!

100M dataset!

@thejohnnyyu.bsky.social, @therealnima.bsky.social
, Kevan Shokat, and I are excited to announce a historic achievement by our team at @vevotherapeutics.bsky.social: tinyurl.com/4rrvap3t