v0.1.6

What's Changed

New Features

• Add rho_sparsity parameter to deconvolve function for L1 sparsity penalty control
• Add preprocess option to deconvolve function
• Add reproducibility support with random_state parameter
• Add Stereo-seq platform guide

Bug Fixes

• Fix normalization for sparse matrices in deconv
• Handle empty inputs and validate graph coordinates
• Handle sparse references and clamp k in KNN graph
• Clamp k bounds and use clamped min_k in estimator
• Correct Visium HD typical UMI/spot values based on published data

Improvements

• Input validation and robustness fixes across modules
• Validation, dtype fixes, and safe correlation handling
• Performance and robustness improvements
• Change lambda_spatial default to auto
• Change license from GPL-3.0 to BSD-3-Clause

Documentation

• Add comprehensive spatial deconvolution tutorial notebook
• Add reference data quality guide
• Clarify and standardize rho_sparsity scaling and docs
• Document the impact of unknown cells in deconvolution
• Revise and expand README with updated features and benchmarks
• Add Zenodo DOI badge to README

Full Changelog: v0.1.3...v0.1.6

v0.1.3

What's Changed

• Added Zenodo integration for DOI generation
• Minor maintenance updates

Citation

If FlashDeconv helps your research, please cite:

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

Full Changelog: v0.1.2...v0.1.3

v0.1.2

What's New

New Features

• Scanpy-style API: Added fd.tl.deconvolve() for seamless AnnData integration
  • Results stored in adata.obsm['flashdeconv']
  • Compatible with sc.pl.spatial() visualization
  • Simplified workflow for scanpy users

Improvements

• Added Python 3.12 support
• Updated documentation with bioRxiv citation (DOI: 10.64898/2025.12.22.696108)

Example Usage

import scanpy as sc
import flashdeconv as fd

adata_st = sc.read_h5ad('visium.h5ad')
adata_ref = sc.read_h5ad('reference.h5ad')

fd.tl.deconvolve(adata_st, adata_ref, cell_type_key='cell_type')
sc.pl.spatial(adata_st, color='flashdeconv_dominant')

Full Changelog: v0.1.1...v0.1.2

v0.1.1

Changes

• Fix citation year to 2025
• README improvements
• No API changes

Installation

pip install flashdeconv==0.1.1