Justin Hong

1/ I’m excited to share recent work on inferring cell-cell interactions using attention by @justjhong.bsky.social and me, supervised by @elhamazizi.bsky.social . Open the thread 🧵 for a brief overview of our method. bioRxiv link: www.biorxiv.org/content/10.1....

For our third Computational Spatial Biology seminar, we will be speaking with @wencksternjo.bsky.social about VirTues, a foundation model framework for analyzing complex tissue architectures.

Tune in this Wed, May 7 @ 11AM ET! Full schedule and last week's recording: csbseminar.github.io

For our next Computational Spatial Biology seminar, we will talking with @siyuhe.bsky.social about CORAL, a deep graph generative model learning integrated representations of multimodal spatial omics data.

Tune in next Wednesday, April 30 @ 12PM ET!
Full schedule: csbseminar.github.io

To kick off the Computational Spatial Biology seminar series with Nathan Levy, we will be discussing LUNA with Yist Yu from EPFL. LUNA is a generative AI model that reassembles complex tissue structures from gene expressions of cells.

Tune in next Wednesday, April 9 @ 11AM ET!

Cover photo of the Computational Spatial Biology Seminar website

Announcing the Computational Spatial Biology seminar!

With Nathan Levy (Yosef Lab), we’re bringing together researchers at the intersection of AI & spatial biology to share their work.

Kicking off April 9th with Yist Yu presenting LUNA!

Explore the lineup here:
csbseminar.github.io

🧵 Excited to share #Echidna, a Bayesian framework for quantifying the impact of gene dosage on phenotypic plasticity: tinyurl.com/296kf7hf!
With @elhamazizi.bsky.social and @mingxz.bsky.social, we integrate scRNA-seq & WGS to uncover how CNAs drive tumor evolution and transcriptional variability.

Samples y | x from Treeffuser vs. true densities, for multiple values of x under three different scenarios. Treeffuser captures arbitrarily complex conditional distributions that vary with x.

I am very excited to share our new Neurips 2024 paper + package, Treeffuser! 🌳 We combine gradient-boosted trees with diffusion models for fast, flexible probabilistic predictions and well-calibrated uncertainty.

paper: arxiv.org/abs/2406.07658
repo: github.com/blei-lab/tre...

🧵(1/8)

I've followed just the right set of accounts that my feed is just pictures of space and cats doing weird stuff. I'll add more, but for now... it's perfect