Scvi-tools

- do not automatically upper case genes [adam]
- AutoZI [oscar]
- Made the intro tutorial more user friendly [adam]
- Tests for LDVAE notebook [adam]
- black codebase [achille] [gabriel] [adam]
- fix compatibility issues with sklearn and numba [romain]
- fix Anndata [francesco-brundu]
- docstring, totalVI, totalVI notebook and CITE-seq data [adam]
- fix type [eduardo-beltrame]
- fixing installation guide [jeff]
- improved error message for dispersion [stephen-flemming]

- docstring [achille]
- differential expression [oscar] [pierre]

- gimVI [achille]
- synthetic correlated datasets, fixed bug in marginal log likelihood [oscar]
- autotune, dataset enhancements [gabriel]
- documentation [jeff]
- more consistent posterior API, docstring, validation set [adam]
- fix anndataset [michael-raevsky]
- linearly decoded VAE [valentine-svensson]
- support for scanpy, fixed bugs, dataset enhancements [achille]
- fix filtering bug, synthetic correlated datasets, docstring, differential expression [pierre]
- better docstring [jamie-morton]
- classifier based on library size for doublet detection [david-kelley]

- corrected notebook [jules]
- added UMAP and updated harmonization code [chenling] [romain]
- support for batch indices in csvdataset [primoz-godec]
- speeding up likelihood computations [william-yang]
- better anndata interop [casey-greene]
- early stopping based on classifier accuracy [david-kelley]

- updated to torch v1 [jules]
- added stress tests for harmonization [chenling]
- fixed autograd breaking [romain]
- make removal of empty cells more efficient [john-reid]
- switch to os.path.join [casey-greene]

- added baselines and datasets for sMFISH imputation [jules]
- added harmonization content [chenling]
- fixing bugs on DE [romain]