Fixes

• Enable compatibility of in-place filtering with the latest anndata (#148)
• Fixtfidf when using data from a layer (#147)
• Fix custom chromosome names incount_fragments_features (#140)
• Prepare to count unique fragments incount_fragments_features from the next version (see#110)
• Improvemu.pl.scatter()

🐛 → 🦋

Fixes and enhancements

• ✨ extend _l2norm for sparse inputs (#114)
• improve data type handling for MOFA (#112)
• improve compatibility with the recent scanpy versions (#136)

Fixes

• fix handling and saving colour palettes in MuData for categorical and continuous variables (#109)
• fix when using sparse matrices in the MOFA interface to combine modalities with missing samples (#106)
• fix error messages (#95) and mixing metadata and features (#96) when plotting across modalities

Improvements and fixes

• mu.pp.intersect_obs now works for modalities that have no.X (#93)
• mu.pl.embedding now saves the colour palette in.uns
• ac.pl.fragment_histogram andmu.pl.histogram now have save/show arguments (#101)
• ac.tl.count_fragments_features now has astranded argument
• ac.tl.nucleosome_signal now works on morepysam setups (#105)
• support for numpy 1.24 and newer scanpy versions

Tools

• MOFA can be now run in the stochastic mode (SVI) using the new arguments formuon.tl.mofa (#47)
• Model weights can be visualised withmu.pl.mofa_loadings

Plotting

• Plotting module has gained new plots such asmu.pl.scatter (#48)
• It is now possible to define layers as{modality: layer} inmu.pl.scatter

ATAC module

• pysam not being installed is now handled more gracefully (#46)
• Improvements to the TF-IDF normalisation interface including view handling (#88)

General

• sklearn vsscikit-learn dependency issue is fixed (#91)

This is a point release with fixes. Consecutive in-place filtering now works as expected (#43).

An update to muon with fixes and improvements.MuData has found a new home in a standalone package.

Initial muon release withMuData,atac andprot modules, and multi-omics integration with MOFA and WNN.