Skip to content

Add FlashDeconv to Cell Type Deconvolution section#26

Open
cafferychen777 wants to merge 1 commit intoOmicsML:mainfrom
cafferychen777:add-flashdeconv
Open

Add FlashDeconv to Cell Type Deconvolution section#26
cafferychen777 wants to merge 1 commit intoOmicsML:mainfrom
cafferychen777:add-flashdeconv

Conversation

@cafferychen777
Copy link
Contributor

Summary

Add FlashDeconv to the Cell Type Deconvolution section.

FlashDeconv is a high-performance spatial transcriptomics deconvolution method using structure-preserving randomized sketching. It achieves atlas-scale processing (1M spots in ~3 minutes) with linear O(N) complexity.

Key Features

  • Structure-preserving randomized sketching with leverage-score importance sampling
  • Linear O(N) scaling for time and memory
  • Optimized for subcellular-resolution platforms (Visium HD, Stereo-seq, Xenium)
  • Preserves rare cell type signals that variance-based methods miss

Publication

Yang, C., Chen, J. & Zhang, X. FlashDeconv enables atlas-scale, multi-resolution spatial deconvolution via structure-preserving sketching. bioRxiv (2025). https://doi.org/10.64898/2025.12.22.696108

Code

https://github.com/cafferychen777/flashdeconv

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant