Scanpy – Single-Cell Analysis in Python
Scanpy is a scalable toolkit for analyzing single-cell gene expression data built jointly with anndata. It includes preprocessing, visualization, clustering, trajectory inference and differential expression testing. The Python-based implementation efficiently deals with datasets of more than one million cells.
Follow changes in the release notes.
Check out our contributing guide for development practices.
Scanpy hits 100 contributors! 2022-03-31
Of course, contributions to the project are not limited to direct modification of the source code. Many others have improved the project by building on top of it, participating in development discussions, helping others with usage, or by showing off what it’s helped them accomplish.
Thanks to all our contributors for making this project possible!
New community channels 2022-03-31
We’ve moved our forums and have a new publicly available chat!
Toolkit for spatial (squidpy) and multimodal (muon) published 2022-02-01
Two large toolkits extending our ecosystem to new modalities have had their manuscripts published!
Fix handling of numpy array palettes for old numpy versions PR 2832 P Angerer
Fix handling of numpy array palettes (e.g. after write-read cycle) PR 2734 P Angerer
Specify correct version of
matplotlibdependency PR 2733 P Fisher
Prevent pandas from causing infinite recursion when setting a slice of a categorical column PR 2719 P Angerer
Remove use of deprecated
dtypeargument to AnnData constructor PR 2658 Isaac Virshup
Support scikit-learn 1.3 PR 2515 P Angerer
Nonevalue vanishing from things like
.uns['log1p']PR 2546 SP Shen
python-igraphPR 2566 P Angerer
_choose_representation()now works with
n_pcsif bigger than
settings.N_PCSPR 2610 S Dicks
Fix compatibility with matplotlib 3.7 PR 2414 I Virshup P Fisher
Fix scrublet numpy matrix compatibility issue PR 2395 A Gayoso
New tutorial on the usage of Pearson Residuals: → tutorial: tutorial_pearson_residuals J Lause, G Palla
normalize_pearson_residuals()for Pearson Residuals normalization
highly_variable_genes()for HVG selection with Pearson Residuals
normalize_pearson_residuals_pca()for Pearson Residuals normalization and dimensionality reduction with PCA
recipe_pearson_residuals()for Pearson Residuals normalization, HVG selection and dimensionality reduction with PCA
Embedding plots can now pass
colorbar_locto specify the location of colorbar legend, or pass
Noneto not show a colorbar PR 1821 A Schaar I Virshup
Embedding plots now have a
dimensionsargument, which lets users select which dimensions of their embedding to plot and uses the same broadcasting rules as other arguments PR 1538 I Virshup
Multiple packages have been added to our ecosystem page, including:
pytablesdependency by implementing
h5pydue to installation errors on Windows PR 2064