WaveFactor (formerly WaviFM) is a Bayesian factor modeling framework for spatial transcriptomics that explicitly models spatial length scales by performing Coordinate Ascent Variational Inference (CAVI) directly on 2D Discrete Wavelet Transform (DWT) coefficients.
Install WaveFactor with pip:
pip install wavefactorVerify your installation:
python -c "import wavefactor as wf; print('WaveFactor version:', wf.__version__)"Please refer to the documentation for installation, code snippets, examples, etc.
Run both the compiled C++ and Python test suite with the command:
# Run ALL tests (automatically compiles/checks C++ targets)
python tests/run_all_tests.pyOptions:
python tests/run_all_tests.py --verbose: Verbose test output.python tests/run_all_tests.py -v: Verbose test output (same as--verboseflag).
docs/: Documentation filesdev/: Developer filesexamples/: Example scriptslib/: External librariessrc/: C++ CAVI engine source filestest/: C++ testing suitetests/: Python test suitewavefactor/: Python package
Preprint: Coming soon, stay tuned!
Research Poster (2026 November): View PDF
Authors
Yulin Wu¹²³
- Email: yulin4@student.unimelb.edu.au
- LinkedIn: www.linkedin.com/in/yulin-wu-59a0591b0
Heejung Shim¹²³⁴⁵⁶⁷
Affiliations
¹ Melbourne Integrative Genomics, The University of Melbourne
² School of Mathematics and Statistics, The University of Melbourne
³ ARC Centre of Excellence for the Mathematical Analysis of Cellular Systems, The University of Melbourne
⁴ Snow Vision Accelerator, The University of Sydney
⁵ Charles Perkins Centre, The University of Sydney
⁶ Sydney Precision Data Science Centre, The University of Sydney
⁷ School of Mathematics and Statistics, The University of Sydney