rectanglepy 0.4.7__tar.gz → 0.5.0__tar.gz

{rectanglepy-0.4.7 → rectanglepy-0.5.0}/.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.4.7
+current_version = 0.5.0
 tag = True
 commit = True
 

{rectanglepy-0.4.7 → rectanglepy-0.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.3
+Metadata-Version: 2.4
 Name: rectanglepy
-Version: 0.4.7
+Version: 0.5.0
 Summary: Hierarchical deconvolution of bulk  transcriptomics
 Project-URL: Documentation, https://rectanglepy.readthedocs.io/
 Project-URL: Source, https://github.com/ComputationalBiomedicineGroup/Rectangle
@@ -28,26 +28,29 @@ License: MIT License
         LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
         OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
         SOFTWARE.
+License-File: LICENSE
 Requires-Python: >=3.10
 Requires-Dist: anndata<0.10.9,>=0.8.0
 Requires-Dist: loguru
 Requires-Dist: numpy<2.0.0,>=1.0.0
 Requires-Dist: pydeseq2==0.4.11
 Requires-Dist: quadprog==0.1.12
+Requires-Dist: scipy==1.13.0
 Requires-Dist: statsmodels>=0.14.1
 Provides-Extra: dev
 Requires-Dist: bump2version; extra == 'dev'
 Requires-Dist: pre-commit; extra == 'dev'
 Requires-Dist: twine>=4.0.2; extra == 'dev'
 Provides-Extra: doc
+Requires-Dist: furo; extra == 'doc'
 Requires-Dist: ipykernel; extra == 'doc'
 Requires-Dist: ipython; extra == 'doc'
 Requires-Dist: myst-nb; extra == 'doc'
+Requires-Dist: sphinx; extra == 'doc'
 Requires-Dist: sphinx-autodoc-typehints; extra == 'doc'
-Requires-Dist: sphinx-book-theme>=1.0.0; extra == 'doc'
+Requires-Dist: sphinx-book-theme; extra == 'doc'
 Requires-Dist: sphinx-copybutton; extra == 'doc'
-Requires-Dist: sphinx>=4; extra == 'doc'
-Requires-Dist: sphinxcontrib-bibtex>=1.0.0; extra == 'doc'
+Requires-Dist: sphinxcontrib-bibtex; extra == 'doc'
 Provides-Extra: test
 Requires-Dist: pytest; extra == 'test'
 Description-Content-Type: text/markdown
@@ -79,7 +82,7 @@ Python installed, we recommend installing [Mambaforge](https://github.com/conda-
 
 How to install Rectangle:
 
-Install the latest release of `Rectangle` from `PyPI <https://pypi.org/project/rectanglepy/>`:
+Install the latest release of `Rectangle` from `PyPI` <https://pypi.org/project/rectanglepy/>:
 
 ```bash
 pip install rectanglepy

{rectanglepy-0.4.7 → rectanglepy-0.5.0}/README.md

@@ -25,7 +25,7 @@ Python installed, we recommend installing [Mambaforge](https://github.com/conda-
 
 How to install Rectangle:
 
-Install the latest release of `Rectangle` from `PyPI <https://pypi.org/project/rectanglepy/>`:
+Install the latest release of `Rectangle` from `PyPI` <https://pypi.org/project/rectanglepy/>:
 
 ```bash
 pip install rectanglepy

{rectanglepy-0.4.7 → rectanglepy-0.5.0}/docs/Makefile

@@ -18,3 +18,6 @@ help:
 # "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
 %: Makefile
 	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+html:
+	@$(SPHINXBUILD) -b html "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

rectanglepy-0.5.0/docs/api.md

@@ -0,0 +1,15 @@
+# API
+
+## Rectangle
+
+```{eval-rst}
+.. currentmodule:: rectanglepy
+
+.. autosummary::
+    :toctree: generated
+
+    rectangle
+    pp.build_rectangle_signatures
+    tl.deconvolution
+    pp.RectangleSignatureResult
+```

{rectanglepy-0.4.7 → rectanglepy-0.5.0}/docs/conf.py

@@ -104,7 +104,7 @@ exclude_patterns = ["_build", "Thumbs.db", ".DS_Store", "**.ipynb_checkpoints"]
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 #
-html_theme = "sphinx_book_theme"
+html_theme = "furo"
 html_static_path = ["_static"]
 html_title = "rectangle"
 
@@ -114,16 +114,6 @@ html_theme_options = {
     "path_to_docs": "docs/",
 }
 
-pygments_style = "emacs"
-
-nitpick_ignore = [
-    # If building the documentation fails because of a missing link that is outside your control,
-    # you can add an exception to this list.
-    #     ("py:class", "igraph.Graph"),
-]
-
-print("Pygments style:", pygments_style)
-
 
 def setup(app):
     """App setup hook."""

{rectanglepy-0.4.7 → rectanglepy-0.5.0}/docs/contributing.md

@@ -7,48 +7,6 @@ information to get you started on contributing.
 We assume that you are already familiar with git and with making pull requests on GitHub. If not, please refer
 to the [scanpy developer guide][].
 
-## Installing dev dependencies
-
-In addition to the packages needed to _use_ this package, you need additional python packages to _run tests_ and _build
-the documentation_. It's easy to install them using `pip`:
-
-```bash
-cd Rectangle
-pip install -e ".[dev,test,doc]"
-```
-
-## Code-style
-
-This template uses [pre-commit][] to enforce consistent code-styles. On every commit, pre-commit checks will either
-automatically fix issues with the code, or raise an error message. See [pre-commit checks](template_usage.md#pre-commit-checks) for
-a full list of checks enabled for this repository.
-
-To enable pre-commit locally, simply run
-
-```bash
-pre-commit install
-```
-
-in the root of the repository. Pre-commit will automatically download all dependencies when it is run for the first time.
-
-Alternatively, you can rely on the [pre-commit.ci][] service enabled on GitHub. If you didn't run `pre-commit` before
-pushing changes to GitHub it will automatically commit fixes to your pull request, or show an error message.
-
-If pre-commit.ci added a commit on a branch you still have been working on locally, simply use
-
-```bash
-git pull --rebase
-```
-
-to integrate the changes into yours.
-While the [pre-commit.ci][] is useful, we strongly encourage installing and running pre-commit locally first to understand its usage.
-
-Finally, most editors have an _autoformat on save_ feature. Consider enabling this option for [black][black-editors]
-and [prettier][prettier-editors].
-
-[black-editors]: https://black.readthedocs.io/en/stable/integrations/editors.html
-[prettier-editors]: https://prettier.io/docs/en/editors.html
-
 ## Writing tests
 
 ```{note}
@@ -102,38 +60,6 @@ to publish the created tag on GitHub.
 
 [bump2version]: https://github.com/c4urself/bump2version
 
-### Building and publishing the package on PyPI
-
-Python packages are not distributed as source code, but as _distributions_. The most common distribution format is the so-called _wheel_. To build a _wheel_, run
-
-```bash
-python -m build
-```
-
-This command creates a _source archive_ and a _wheel_, which are required for publishing your package to [PyPI][]. These files are created directly in the root of the repository.
-
-Before uploading them to [PyPI][] you can check that your _distribution_ is valid by running:
-
-```bash
-twine check dist/*
-```
-
-and finally publishing it with:
-
-```bash
-twine upload dist/*
-```
-
-Provide your username and password when requested and then go check out your package on [PyPI][]!
-
-For more information, follow the [Python packaging tutorial][].
-
-It is possible to automate this with GitHub actions, see also [this feature request][pypi-feature-request]
-in the cookiecutter-scverse template.
-
-[python packaging tutorial]: https://packaging.python.org/en/latest/tutorials/packaging-projects/#generating-distribution-archives
-[pypi-feature-request]: https://github.com/scverse/cookiecutter-scverse/issues/88
-
 ## Writing documentation
 
 Please write documentation for new or changed features and use-cases. This project uses [sphinx][] with the following features:

{rectanglepy-0.4.7 → rectanglepy-0.5.0}/docs/notebooks/example.ipynb

@@ -200,39 +200,11 @@
   },
   {
    "cell_type": "markdown",
-   "source": "signature_result is a [`RectangleSignatureResult`](../generated/rectanglepy.pp.RectangleSignatureResult.rst) object. ",
+   "source": "signature_result is a [`RectangleSignatureResult`](../generated/rectanglepy.pp.RectangleSignatureResult.rst) object.",
    "metadata": {
     "collapsed": false
    }
   },
-  {
-   "cell_type": "markdown",
-   "source": "## Running Rectangle in Consensus mode",
-   "metadata": {
-    "collapsed": false
-   }
-  },
-  {
-   "cell_type": "markdown",
-   "source": "For some scRNA-seq datatasets it may be beneficial to run rectangle in consensus mode. In this function we run the rectangle algorithm multiple times (`consensus_runs`), where on each iteration we sample  `sample_size` cells of each cell type. The final cell type proportions are the median of the proportions estimated in each run.",
-   "metadata": {
-    "collapsed": false
-   }
-  },
-  {
-   "cell_type": "code",
-   "outputs": [],
-   "source": "estimations, signature_result, consensus_result = rectangle.rectangle_consens(sc_adata, bulks, consensus_runs=5, sample_size=1500)",
-   "metadata": {
-    "collapsed": false
-   },
-   "execution_count": null
-  },
-  {
-   "metadata": {},
-   "cell_type": "markdown",
-   "source": "signature_result holds the signature result([`RectangleSignatureResult`](../generated/rectanglepy.pp.RectangleSignatureResult.rst)) for the most recent consensus run, while consensus_result is a [`ConsensusResult`](../generated/rectanglepy.ConsensusResult.rst) object that holds the results of all the runs."
-  },
   {
    "cell_type": "markdown",
    "source": [

{rectanglepy-0.4.7 → rectanglepy-0.5.0}/pyproject.toml

@@ -4,7 +4,7 @@ requires = ["hatchling"]
 
 [project]
 name = "rectanglepy"
-version = "0.4.7"
+version = "0.5.0"
 description = "Hierarchical deconvolution of bulk  transcriptomics"
 readme = "README.md"
 requires-python = ">=3.10"
@@ -20,11 +20,13 @@ urls.Source = "https://github.com/ComputationalBiomedicineGroup/Rectangle"
 urls.Home-page = "https://github.com/ComputationalBiomedicineGroup/Rectangle"
 dependencies = [
     "pydeseq2==0.4.11",
+    "scipy==1.13.0",
     "quadprog==0.1.12",
     "loguru",
     "numpy>=1.0.0,<2.0.0",
     "anndata>=0.8.0,<0.10.9",
     "statsmodels>=0.14.1"
+
 ]
 
 [project.optional-dependencies]
@@ -34,15 +36,16 @@ dev = [
     "twine>=4.0.2"
 ]
 doc = [
-    "sphinx>=4",
-    "sphinx-book-theme>=1.0.0",
+    "sphinx",
+    "sphinx-book-theme",
     "myst-nb",
-    "sphinxcontrib-bibtex>=1.0.0",
+    "sphinxcontrib-bibtex",
     "sphinx-autodoc-typehints",
     # For notebooks
     "ipykernel",
     "ipython",
     "sphinx-copybutton",
+    "furo",
 ]
 test = [
     "pytest",

rectanglepy-0.5.0/src/rectanglepy/__init__.py

@@ -0,0 +1,8 @@
+from importlib.metadata import version
+
+from . import pp, tl
+from .rectangle import load_tutorial_data, rectangle
+
+__all__ = ["pp", "tl", "load_tutorial_data", "rectangle"]
+
+__version__ = version("rectanglepy")

{rectanglepy-0.4.7 → rectanglepy-0.5.0}/src/rectanglepy/pp/create_signature.py

@@ -285,10 +285,7 @@ def build_rectangle_signatures(
     raw: bool = False,
     p=0.015,
     lfc=1.5,
-    subsample: bool = False,
-    sample_size: int = 1500,
     n_cpus: int = None,
-    run: int = 0,
     gene_expression_threshold=0.5,
 ) -> RectangleSignatureResult:
     r"""Builds rectangle signatures based on single-cell  count data and annotations.
@@ -305,10 +302,6 @@ def build_rectangle_signatures(
         The Anndata layer to use for the single-cell data. Defaults to None.
     raw
         A flag indicating whether to use the raw Anndata data. Defaults to False.
-    subsample : bool
-        A flag indicating whether to balance the single-cell data. Defaults to False.
-    sample_size : int
-        The number of cells to balance the single-cell data to. Defaults to 1500. If cell number is less than this number it takes the original number of cells.
     optimize_cutoffs
         Indicates whether to optimize the p-value and log fold change cutoffs using gridsearch. Defaults to True.
     p
@@ -317,8 +310,6 @@ def build_rectangle_signatures(
         The log fold change threshold for the DE analysis (only used if optimize_cutoffs is False).
     n_cpus
         The number of cpus to use for the DE analysis. Defaults to the number of cpus available.
-    run
-        The consensus run number for the analysis. Defaults to 0.
     gene_expression_threshold
         The gene expression threshold for the DE analysis. How many cells need to express a gene to be considered in DGE
 
@@ -336,10 +327,6 @@ def build_rectangle_signatures(
         logger.info(f"Using {len(genes)} common genes between bulks and single-cell data")
         adata = adata[:, genes]
 
-    if subsample:
-        annotations = _even(annotations, sample_size, run)
-        adata = adata[annotations.index]
-
     if layer is not None:
         sc_counts = adata.layers[layer]
     elif raw:
@@ -509,15 +496,3 @@ def _reduce_to_common_genes(bulks: pd.DataFrame, sc_data: pd.DataFrame):
     sc_data = sc_data.loc[genes].sort_index()
     bulks = bulks.loc[genes].sort_index()
     return bulks, sc_data
-
-
-def _even(annotations: pd.Series, number: int, run=0) -> pd.Series:
-    np.random.seed(run)
-    assert number > 0, "Number of cells must be greater than 0"
-    annotation_counts = annotations.value_counts()
-    selected_cells = []
-    for annotation in annotation_counts.index:
-        cells = annotations[annotations == annotation].index
-        cells = np.random.choice(cells, min(number, len(cells)), replace=False)
-        selected_cells.extend(cells)
-    return annotations.loc[selected_cells]

rectanglepy-0.5.0/src/rectanglepy/rectangle.py

@@ -0,0 +1,112 @@
+import pandas as pd
+from anndata import AnnData
+from loguru import logger
+from pandas import DataFrame
+from pkg_resources import resource_stream
+
+from .pp import RectangleSignatureResult, build_rectangle_signatures
+from .tl import deconvolution
+
+
+def rectangle(
+    adata: AnnData,
+    bulks: DataFrame,
+    cell_type_col: str = "cell_type",
+    *,
+    layer: str = None,
+    raw: bool = False,
+    correct_mrna_bias: bool = True,
+    optimize_cutoffs=True,
+    p=0.015,
+    lfc=1.5,
+    n_cpus: int = None,
+    gene_expression_threshold=0.5,
+) -> tuple[DataFrame, RectangleSignatureResult]:
+    r"""All in one deconvolution method. Creates signatures and deconvolutes the bulk data. Has options for subsampling and consensus runs.
+
+    Parameters
+    ----------
+    adata
+        The single-cell count data as a DataFrame. DataFrame must have the genes as index and cell identifier as columns. Each entry should be in raw counts.
+    bulks
+        The bulk data as a DataFrame. DataFrame must have the bulk identifier as index and the genes as columns. Each entry should be in transcripts per million (TPM).
+    cell_type_col
+        The annotations corresponding to the single-cell count data. Series data should have the cell identifier as index and the annotations as values.
+    layer
+        The Anndata layer to use for the single-cell data.
+    raw
+        A flag indicating whether to use the raw Anndata data.
+    optimize_cutoffs
+        Indicates whether to optimize the p-value and log fold change cutoffs using gridsearch.
+    p
+        The p-value threshold for the DE analysis (only used if optimize_cutoffs is False).
+    lfc
+        The log fold change threshold for the DE analysis (only used if optimize_cutoffs is False).
+    n_cpus
+        The number of cpus to use for the DE analysis. None value takes all cpus available.
+    correct_mrna_bias : bool
+        A flag indicating whether to correct for mRNA bias. Defaults to True.
+    gene_expression_threshold : float
+        The threshold for gene expression. Genes with expression below this threshold are removed from the analysis.
+
+    Returns
+    -------
+    DataFrame : The estimated cell fractions.
+    RectangleSignatureResult : The result of the rectangle signature analysis.
+    """
+    assert isinstance(adata, AnnData), "adata must be an AnnData object"
+    assert isinstance(bulks, DataFrame), "bulks must be a DataFrame"
+
+    signatures = build_rectangle_signatures(
+        adata,
+        cell_type_col,
+        bulks=bulks,
+        optimize_cutoffs=optimize_cutoffs,
+        layer=layer,
+        raw=raw,
+        p=p,
+        lfc=lfc,
+        n_cpus=n_cpus,
+        gene_expression_threshold=gene_expression_threshold,
+    )
+
+    estimations = deconvolution(signatures, bulks, correct_mrna_bias, n_cpus)
+
+    if "Unknown" in estimations.columns:
+        try:
+            unkn_gene_corr = _genes_linked_to_unkn(bulks, estimations["Unknown"])
+        except Exception as e:
+            logger.warning(f"Could not calculate gene correlation with unknown cell type: {e}")
+            unkn_gene_corr = None
+    else:
+        unkn_gene_corr = None
+    signatures.unkn_gene_corr = unkn_gene_corr
+
+    return estimations, signatures
+
+
+def load_tutorial_data() -> tuple[pd.DataFrame, pd.DataFrame, pd.DataFrame]:
+    """Loads the single-cell count data, annotations, and bulk data from the tutorial.
+
+    Returns
+    -------
+    The single-cell count data, annotations, and bulk data.
+    """
+    with resource_stream(__name__, "data/hao1_annotations_small.zip") as annotations_file:
+        annotations = pd.read_csv(annotations_file, index_col=0, compression="zip")["0"]
+
+    with resource_stream(__name__, "data/hao1_counts_small.zip") as counts_file:
+        sc_counts = pd.read_csv(counts_file, index_col=0, compression="zip").astype("int")
+
+    with resource_stream(__name__, "data/small_fino_bulks.zip") as bulks_file:
+        bulks = pd.read_csv(bulks_file, index_col=0, compression="zip")
+
+    return sc_counts.T, annotations, bulks.T
+
+
+def _genes_linked_to_unkn(bulks: DataFrame, unkn_fractions: pd.Series):
+    genes = bulks.columns.drop_duplicates()
+    corr = []
+    for gene in genes:
+        corr.append(unkn_fractions.corr(bulks.loc[:, gene]))
+    return pd.Series(corr, index=genes).sort_values(ascending=False)

{rectanglepy-0.4.7 → rectanglepy-0.5.0}/tests/test_pp.py

@@ -16,7 +16,6 @@ from rectanglepy.pp.create_signature import (
     _create_linkage_matrix,
     _create_pseudo_count_sig,
     _de_analysis,
-    _even,
     _generate_pseudo_bulks,
     _get_fcluster_assignments,
     _run_deseq2,
@@ -209,39 +208,6 @@ def test_de_analysis(small_data):
     assert len(r2) == 3
 
 
-def test_even(small_data):
-    sc_data, annotations, _ = small_data
-    even_annotation = _even(annotations, 20)
-    assert len(even_annotation) == 51
-    counts = annotations.loc[even_annotation.index].value_counts()
-    assert counts.equals(pd.Series({"T cell CD4": 20, "T cell CD8": 20, "NK cell": 11}))
-
-    even_sc_data = sc_data.loc[:, _even(annotations, 100).index]
-
-    assert round(even_sc_data.sum().sum(), 3) == round(sc_data.sum().sum(), 3)
-
-
-def test_build_rectangle_signatures_even(small_data):
-    sc_counts, annotations, bulk = small_data
-    sc_counts = sc_counts.astype("int")
-    adata = AnnData(sc_counts.T, obs=annotations.to_frame(name="cell_type"))
-    results_even = build_rectangle_signatures(
-        adata,
-        "cell_type",
-        bulks=bulk.T,
-        p=0.5,
-        lfc=0.1,
-        optimize_cutoffs=False,
-        subsample=True,
-        sample_size=1000,
-    )
-    results_uneven = build_rectangle_signatures(
-        adata, "cell_type", bulks=bulk.T, p=0.5, lfc=0.1, optimize_cutoffs=False
-    )
-
-    assert results_even.bias_factors.equals(results_uneven.bias_factors)
-
-
 def test_create_bootstrap_signature(small_data):
     bootstraps_per_cell = 7
     sc_counts, annotations, bulk = small_data

rectanglepy-0.4.7/docs/api.md

@@ -1,17 +0,0 @@
-# API
-
-## Rectangle
-
-```{eval-rst}
-.. currentmodule:: rectanglepy
-
-.. autosummary::
-    :toctree: generated
-
-    rectanglepy.rectangle
-    rectanglepy.rectangle_consens
-    rectanglepy.pp.build_rectangle_signatures
-    rectanglepy.tl.deconvolution
-    rectanglepy.pp.RectangleSignatureResult
-    rectanglepy.ConsensusResult
-```

rectanglepy-0.4.7/src/rectanglepy/__init__.py

@@ -1,8 +0,0 @@
-from importlib.metadata import version
-
-from . import pp, tl
-from .rectangle import ConsensusResult, load_tutorial_data, rectangle, rectangle_consens
-
-__all__ = ["pp", "tl", "load_tutorial_data", "rectangle", "rectangle_consens", "ConsensusResult"]
-
-__version__ = version("rectanglepy")

rectanglepy-0.4.7/src/rectanglepy/rectangle.py

@@ -1,222 +0,0 @@
-import pandas as pd
-from anndata import AnnData
-from loguru import logger
-from pandas import DataFrame
-from pkg_resources import resource_stream
-
-from .pp import RectangleSignatureResult, build_rectangle_signatures
-from .tl import deconvolution
-
-
-class ConsensusResult:
-    """A class used to represent the consensus result of the rectangle_consens function.
-
-    Parameters
-    ----------
-    estimations
-        A list of DataFrame objects representing the estimations from each consensus run.
-    rectangle_signature_results
-        A list of RectangleSignatureResult objects representing the rectangle signature results from each consensus run.
-    """
-
-    def __init__(self, estimations: list[DataFrame], rectangle_signature_results: list[RectangleSignatureResult]):
-        self.estimations = estimations
-        self.rectangle_signature_results = rectangle_signature_results
-
-
-def rectangle_consens(
-    adata: AnnData,
-    bulks: DataFrame,
-    cell_type_col: str = "cell_type",
-    *,
-    layer: str = None,
-    raw: bool = False,
-    subsample: bool = True,
-    sample_size: int = 1500,
-    consensus_runs: int = 5,
-    correct_mrna_bias: bool = True,
-    optimize_cutoffs=True,
-    p=0.015,
-    lfc=1.5,
-    n_cpus: int = None,
-    gene_expression_threshold=0.5,
-) -> tuple[DataFrame, RectangleSignatureResult, ConsensusResult]:
-    r"""All in one deconvolution method. Creates signatures and deconvolutes the bulk data. Has options for subsampling and consensus runs.
-
-    Parameters
-    ----------
-    adata
-        The single-cell count data as a DataFrame. DataFrame must have the genes as index and cell identifier as columns. Each entry should be in raw counts.
-    bulks
-        The bulk data as a DataFrame. DataFrame must have the bulk identifier as index and the genes as columns. Each entry should be in transcripts per million (TPM).
-    cell_type_col
-        The annotations corresponding to the single-cell count data. Series data should have the cell identifier as index and the annotations as values.
-    layer
-        The Anndata layer to use for the single-cell data. Defaults to None.
-    raw
-        A flag indicating whether to use the raw Anndata data. Defaults to False.
-    subsample : bool
-        A flag indicating whether to balance the single-cell data.
-    sample_size : int
-        The number of cells to balance the single-cell data to. If cell number is less than this number it takes the original number of cells.
-    consensus_runs : int
-        The number of consensus runs to perform. Consensus runs are performed by subsampling the single-cell data and running the analysis multiple times. The results are then aggregated.
-    optimize_cutoffs
-        Indicates whether to optimize the p-value and log fold change cutoffs using gridsearch.
-    p
-        The p-value threshold for the DE analysis (only used if optimize_cutoffs is False).
-    lfc
-        The log fold change threshold for the DE analysis (only used if optimize_cutoffs is False).
-    n_cpus
-        The number of cpus to use for the DE analysis. None value takes all cpus available.
-    correct_mrna_bias : bool
-        A flag indicating whether to correct for mRNA bias. Defaults to True.
-    gene_expression_threshold : float
-        The threshold for gene expression. Genes with expression below this threshold are removed from the analysis.
-
-    Returns
-    -------
-    DataFrame : The estimated cell fractions consens.
-    RectangleSignatureResult : The result of the last consensus run.
-    ConsensusResult : Estimations and rectangle signature results for each consensus run.
-    """
-    assert isinstance(adata, AnnData), "adata must be an AnnData object"
-    assert isinstance(bulks, DataFrame), "bulks must be a DataFrame"
-
-    if consensus_runs > 1:
-        logger.info(f"Running {consensus_runs} consensus runs with subsample size {sample_size}")
-        subsample = True
-
-    estimations = []
-    rectangle_signature_results = []
-    most_recent_signatures = None
-
-    for i in range(consensus_runs):
-        logger.info(f"Running consensus run {i + 1} of {consensus_runs}")
-        signatures = build_rectangle_signatures(
-            adata,
-            cell_type_col,
-            bulks=bulks,
-            optimize_cutoffs=optimize_cutoffs,
-            layer=layer,
-            raw=raw,
-            p=p,
-            lfc=lfc,
-            n_cpus=n_cpus,
-            subsample=subsample,
-            sample_size=sample_size,
-            run=i,
-            gene_expression_threshold=gene_expression_threshold,
-        )
-        most_recent_signatures = signatures
-        cell_fractions = deconvolution(signatures, bulks, correct_mrna_bias, n_cpus)
-        estimations.append(cell_fractions)
-        if "Unknown" in cell_fractions.columns:
-            try:
-                unkn_gene_corr = _genes_linked_to_unkn(bulks, cell_fractions["Unknown"])
-            except Exception as e:
-                logger.warning(f"Could not calculate gene correlation with unknown cell type: {e}")
-                unkn_gene_corr = None
-        else:
-            unkn_gene_corr = None
-        signatures.unkn_gene_corr = unkn_gene_corr
-        rectangle_signature_results.append(signatures)
-    consensus_estimations = pd.concat(estimations).groupby(level=0).median()
-
-    # normalize the estimations to 1, needed for the consensus
-    consensus_estimations = consensus_estimations.div(consensus_estimations.sum(axis=1), axis=0)
-    consensus_estimations[consensus_estimations < 0] = 0
-    consensus_results = ConsensusResult(estimations, rectangle_signature_results)
-    return consensus_estimations, most_recent_signatures, consensus_results
-
-
-def rectangle(
-    adata: AnnData,
-    bulks: DataFrame,
-    cell_type_col: str = "cell_type",
-    *,
-    layer: str = None,
-    raw: bool = False,
-    correct_mrna_bias: bool = True,
-    optimize_cutoffs=True,
-    p=0.015,
-    lfc=1.5,
-    n_cpus: int = None,
-    gene_expression_threshold=0.5,
-) -> tuple[DataFrame, RectangleSignatureResult]:
-    r"""All in one deconvolution method. Creates signatures and deconvolutes the bulk data. Has options for subsampling and consensus runs.
-
-    Parameters
-    ----------
-    adata
-        The single-cell count data as a DataFrame. DataFrame must have the genes as index and cell identifier as columns. Each entry should be in raw counts.
-    bulks
-        The bulk data as a DataFrame. DataFrame must have the bulk identifier as index and the genes as columns. Each entry should be in transcripts per million (TPM).
-    cell_type_col
-        The annotations corresponding to the single-cell count data. Series data should have the cell identifier as index and the annotations as values.
-    layer
-        The Anndata layer to use for the single-cell data.
-    raw
-        A flag indicating whether to use the raw Anndata data.
-    optimize_cutoffs
-        Indicates whether to optimize the p-value and log fold change cutoffs using gridsearch.
-    p
-        The p-value threshold for the DE analysis (only used if optimize_cutoffs is False).
-    lfc
-        The log fold change threshold for the DE analysis (only used if optimize_cutoffs is False).
-    n_cpus
-        The number of cpus to use for the DE analysis. None value takes all cpus available.
-    correct_mrna_bias : bool
-        A flag indicating whether to correct for mRNA bias. Defaults to True.
-    gene_expression_threshold : float
-        The threshold for gene expression. Genes with expression below this threshold are removed from the analysis.
-
-    Returns
-    -------
-    DataFrame : The estimated cell fractions.
-    RectangleSignatureResult : The result of the rectangle signature analysis.
-    """
-    estimations, signatures, _ = rectangle_consens(
-        adata,
-        bulks,
-        cell_type_col,
-        layer=layer,
-        raw=raw,
-        subsample=False,
-        sample_size=-1,
-        consensus_runs=1,
-        correct_mrna_bias=correct_mrna_bias,
-        optimize_cutoffs=optimize_cutoffs,
-        p=p,
-        lfc=lfc,
-        n_cpus=n_cpus,
-        gene_expression_threshold=gene_expression_threshold,
-    )
-    return estimations, signatures
-
-
-def load_tutorial_data() -> tuple[pd.DataFrame, pd.DataFrame, pd.DataFrame]:
-    """Loads the single-cell count data, annotations, and bulk data from the tutorial.
-
-    Returns
-    -------
-    The single-cell count data, annotations, and bulk data.
-    """
-    with resource_stream(__name__, "data/hao1_annotations_small.zip") as annotations_file:
-        annotations = pd.read_csv(annotations_file, index_col=0, compression="zip")["0"]
-
-    with resource_stream(__name__, "data/hao1_counts_small.zip") as counts_file:
-        sc_counts = pd.read_csv(counts_file, index_col=0, compression="zip").astype("int")
-
-    with resource_stream(__name__, "data/small_fino_bulks.zip") as bulks_file:
-        bulks = pd.read_csv(bulks_file, index_col=0, compression="zip")
-
-    return sc_counts.T, annotations, bulks.T
-
-
-def _genes_linked_to_unkn(bulks: DataFrame, unkn_fractions: pd.Series):
-    genes = bulks.columns.drop_duplicates()
-    corr = []
-    for gene in genes:
-        corr.append(unkn_fractions.corr(bulks.loc[:, gene]))
-    return pd.Series(corr, index=genes).sort_values(ascending=False)