Scvi-tools

Latest version: v1.2.2.post1

Safety actively analyzes 706267 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 7 of 16

0.16.2

Changes

Breaking changes

Bug Fixes

- Raise appropriate error when `backup_url` is not provided and file is missing on
{meth}`~scvi.model.base.BaseModelClass.load` ([1527]).
- Pipe `loss_kwargs` properly in {class}`~scvi.train.AdversarialTrainingPlan`, and fix incorrectly
piped kwargs in {class}`~scvi.model.TOTALVI` and {class}`~scvi.model.MULTIVI` ([1532]).

Contributors

- [jjhong922]
- [adamgayoso]

0.16.1

Changes

- Update scArches Pancreas tutorial, DestVI tutorial ([1520]).

Breaking changes

- {class}`~scvi.dataloaders.SemiSupervisedDataLoader` and
{class}`~scvi.dataloaders.SemiSupervisedDataSplitter` no longer take `unlabeled_category` as an
initial argument. Instead, the `unlabeled_category` is fetched from the labels state registry,
assuming that the {class}`~scvi.data.AnnDataManager` object is registered with a
{class}`~scvi.data.fields.LabelsWithUnlabeledObsField` ([1515]).

Bug Fixes

- Bug fixed in {class}`~scvi.model.SCANVI` where `self._labeled_indices` was being improperly set
([1515]).
- Fix issue where {class}`~scvi.model.SCANVI.load_query_data` would not properly add an obs column
with the unlabeled category when the `labels_key` was not present in the query data.
- Disable extension of categories for labels in {class}`~scvi.model.SCANVI.load_query_data`
([1519]).
- Fix an issue with {meth}`~scvi.model.SCANVI.prepare_query_data` to ensure it does nothing when
genes are completely matched ([1520]).

Contributors

- [jjhong922]
- [adamgayoso]

0.16

0.16.0

This release features a refactor of {class}`~scvi.model.DestVI` ([1457]):

1. Bug fix in cell type amortization, which leads to on par performance of cell type amortization
`V_encoder` with free parameter for cell type proportions `V`.
1. Bug fix in library size in {class}`~scvi.model.CondSCVI`, that lead to downstream dependency
between sum over cell type proportions `v_ind` and library size `library` in
{class}`~scvi.model.DestVI`.
1. `neg_log_likelihood_prior` is not computed anymore on random subset of single cells but cell
type specific subclustering using cluster variance `var_vprior`, cluster mean `mean_vprior` and
cluster mixture proportion `mp_vprior` for computation. This leads to more stable results and
faster computation time. Setting `vamp_prior_p` in {func}`~scvi.model.DestVI.from_rna_model` to
the expected resolution is critical in this algorithm.
1. The new default is to also use dropout `dropout` during the decoder of
{class}`~scvi.model.CondSCVI` and subsequently `dropout_decoder` in
{class}`~scvi.model.DestVI`, we found this to be beneficial after bug fixes listed above.
1. We changed the weighting of the loss on the variances of beta and the prior of eta.

:::{note}
Due to bug fixes listed above this version of {class}`~scvi.model.DestVI` is not backwards
compatible. Despite instability in training in the outdated version, we were able to reproduce
results generated with this code. We therefore do not strictly encourage to rerun old experiments.
:::

We published a new tutorial. This new tutorial incorporates a new utility package
[destvi_utils](https://github.com/YosefLab/destvi_utils) that generates exploratory plots of the
results of {class}`~scvi.model.DestVI`. We refer to the manual of this package for further
documentation.

Changes

- Docs changes (installation [1498], {class}`~scvi.model.DestVI` user guide [1501] and [1508],
dark mode code cells [1499]).
- Add `backup_url` to the {meth}`~scvi.model.base.BaseModelClass.load` method of each model class,
enabling automatic downloading of model save file ([1505]).

Breaking changes

- Support for loading legacy loading is removed from {meth}`~scvi.model.base.BaseModelClass.load`.
Utility to convert old files to the new file as been added
{meth}`~scvi.model.base.BaseModelClass.convert_legacy_save` ([1505]).
- Breaking changes to {class}`~scvi.model.DestVI` as specified above ([1457]).

Bug Fixes

- {meth}`~scvi.model.base.RNASeqMixin.get_likelihood_parameters` fix for `n_samples > 1` and
`dispersion="gene_cell"` [1504].
- Fix backwards compatibility for legacy TOTALVI models [1502].

Contributors

- [cane11]
- [jjhong922]
- [adamgayoso]
- [romain-lopez]

0.15.5

Changes

- Add common types file [1467].
- New default is to not pin memory during training when using a GPU. This is much better for shared
GPU environments without any performance regression [1473].

Bug fixes

- Fix LDA user guide bugs [1479].
- Fix unnecessary warnings, double logging [1475].

Contributors

- [jjhong922]
- [adamgayoso]

0.15.4

Changes

- Add peakVI publication reference [1463].
- Update notebooks with new install functionality for Colab [1466].
- Simplify changing the training plan for pyro [1470].
- Optionally scale ELBO by a scalar in {class}`~scvi.train.PyroTrainingPlan` [1469].

Bug fixes

Contributors

- [jjhong922]
- [adamgayoso]
- [vitkl]

Page 7 of 16

© 2025 Safety CLI Cybersecurity Inc. All Rights Reserved.