Sdeper

--------------------------

**Updates**:

* The default values of :option:`--lambda_r_range_max` and :option:`--lambda_g_range_max` have been changed from 100 to 50. The default values of :option:`--lambda_r_range_k` and :option:`--lambda_g_range_k` have been changed from 8 to 6.

--------------------------

**Bug Fixes**:

* Upgrade certain dependencies to ensure successful installation via both PyPI and Conda.

--------------------------

**Bug Fixes**:

* Changed the dependency to the headless version of OpenCV to avoid installation issues and since no GUI functionality is required.

--------------------------

**Updates**:

* The :mod:`imputation` module has been completely rewritten, significantly improving contour finding and grid generation for enhanced performance and accuracy (`1 <https://github.com/az7jh2/SDePER/issues/1>`_).

--------------------------

**Updates**:

* The optimization of cell type proportion :math:`\theta` is skipped if the initial value of :math:`\theta` indicates the presence of only one cell type in the spot.

* When predicting cell type proportions utilizing the CVAE latent space, the values of the CVAE latent space are now directly used instead of PCA embeddings for proportion transferring.

* The default number of hidden layers has been changed from 2 to 1.

--------------------------

**Updates**:

* Added single cell augmentation feature for scRNA-seq reference data.

* Implemented failure steps for handling irregular :math:`\theta` values after optimization.

* Added support for transferring cell type proportions based on PCA or UMAP embeddings of latent space, or directly on the original latent space in cell type proportion prediction using CVAE.

* Introduced caching in GLRM to accelerate computations by storing calculated likelihood values, reducing duplicate calculations. Note: This feature is disabled by default due to potential optimization failures caused by unknown reasons (`5 <https://github.com/az7jh2/SDePER/issues/5>`_).

**Bug Fixes**:

* Resolved issue with spot name inconsistencies when spots are filtered out if cell type proportions predicted by CVAE were used for :math:`\theta` initialization in GLRM modeling.

* Fixed bug causing errors when plotting CVAE loss during training in the absence of validation data.