Sdeper

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

**Updates**:

* Added a step to remove mitochondrial genes during preprocessing.

* Introduced a PCA plot for visualizing the CVAE latent space and added density estimation based on PCA in diagnostic figures.

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

**Updates**:

* Introduced prediction of cell type proportions utilizing the CVAE latent space. Currently, the proportions are transferred from the scRNA-seq condition to the spatial condition in latent space. Then the predicted cell type proportions are used as initial value of :math:`\theta` for GLRM modeling (`13 <https://github.com/az7jh2/SDePER/issues/13>`_).

* Reused :math:`\theta` and :math:`e^{\alpha}` estimations from stage 1 of GLRM modeling for initializing stage 2 (`12 <https://github.com/az7jh2/SDePER/issues/12>`_).

* Increased the weight of spatial spots and scRNA-seq cells in CVAE training against generated pseudo-spots.

* Added support for retaining only highly variable genes in the spatial data. By default all genes are retained.

* SDePER options are written to a text file within the diagnosis folder, and only DE genes are retained in the CVAE-transformed data during saving if command-line option :option:`--redo_de` is ``true``.

* Decreased the default number of command-line option :option:`--n_pseudo_spot` to ``100,000``.


**Bug Fixes**:

* Resolved a bug where errors occurred during diagnostic UMAP drawing if only cell type markers were provided, and no scRNA-seq cells were available.

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

**Updates**:

* Implemented a GitHub Action triggered by new release publications to test the package installation (`10 <https://github.com/az7jh2/SDePER/issues/10>`_).

* Added a diagnostic UMAP plot of raw data before platform effect removal using CVAE. Also included new diagnostic plots depicting CVAE training loss.

* Changed the default value of the :option:`--n_marker_per_cmp` command-line option to ``20``.

* Added three command-line options: :option:`--use_batch_norm`, :option:`--use_spatial_pseudo` and :option:`--cvae_train_epoch`.

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

**Updates**:

* Revised the :mod:`cvae` module, implementing several updates including (`4 <https://github.com/az7jh2/SDePER/issues/4>`_):

* Integration of Batch Normalization into the CVAE training process.
* Inclusion of a logarithmic transformation in the preprocessing of gene expression data for CVAE input.
* Generation of "pseudo-spots" under spatial conditions through the random combination of spatial spots.
* Addition of two command-line options: :option:`--n_pseudo_spot` and :option:`--num_hidden_layer`. Also adjusted the default value of :option:`--cvae_init_lr`.

* Relocated all code related to generating diagnostic figures to a new module, :mod:`diagnosis_plots`. Additionally organized the output figures into a folder named `diagnosis` within the output path (`6 <https://github.com/az7jh2/SDePER/issues/6>`_).

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

**Updates**:

* Improved differential analysis strategy for maker gene identification. Added 8 new related command-line options and modified the default value of 2 options (`3 <https://github.com/az7jh2/SDePER/issues/3>`_).

* Updated help messages (`7 <https://github.com/az7jh2/SDePER/issues/7>`_).

* Add support for installation via Conda (`2 <https://github.com/az7jh2/SDePER/issues/2>`_, `#8 <https://github.com/az7jh2/SDePER/issues/8>`_).

* Add source code and relevant documentation into the package documentation (`9 <https://github.com/az7jh2/SDePER/issues/9>`_).

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

**Bug Fixes**:

* Resolved the version determination bug in release v1.0.2 (`8 <https://github.com/az7jh2/SDePER/issues/8>`_).

**Updates**:

* Automatically publishing new releases to PyPI using GitHub Actions.