rectanglepy 1.4.2__tar.gz → 1.5.0__tar.gz

{rectanglepy-1.4.2 → rectanglepy-1.5.0}/.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 1.4.2
+current_version = 1.5.0
 tag = True
 commit = True
 

{rectanglepy-1.4.2 → rectanglepy-1.5.0}/.readthedocs.yaml

@@ -1,7 +1,7 @@
 # https://docs.readthedocs.io/en/stable/config-file/v2.html
 version: 2
 build:
-    os: ubuntu-20.04
+    os: ubuntu-24.04
     tools:
         python: "3.10"
 sphinx:

{rectanglepy-1.4.2 → rectanglepy-1.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rectanglepy
-Version: 1.4.2
+Version: 1.5.0
 Summary: Hierarchical deconvolution of bulk  transcriptomics
 Project-URL: Documentation, https://rectanglepy.readthedocs.io/
 Project-URL: Source, https://github.com/ComputationalBiomedicineGroup/Rectangle

{rectanglepy-1.4.2 → rectanglepy-1.5.0}/pyproject.toml

@@ -4,7 +4,7 @@ requires = ["hatchling"]
 
 [project]
 name = "rectanglepy"
-version = "1.4.2"
+version = "1.5.0"
 description = "Hierarchical deconvolution of bulk  transcriptomics"
 readme = "README.md"
 requires-python = ">=3.10"

{rectanglepy-1.4.2 → rectanglepy-1.5.0}/src/rectanglepy/__init__.py

@@ -1,8 +1,9 @@
 from importlib.metadata import version
 
 from . import pp, tl
+from .parameters import RectangleAdvancedParameters
 from .rectangle import load_tutorial_data, rectangle
 
-__all__ = ["pp", "tl", "load_tutorial_data", "rectangle"]
+__all__ = ["pp", "tl", "RectangleAdvancedParameters", "load_tutorial_data", "rectangle"]
 
 __version__ = version("rectanglepy")

rectanglepy-1.5.0/src/rectanglepy/parameters.py

@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: BSD-3-Clause OR LicenseRef-Rectangle-Commercial
+
+from dataclasses import dataclass
+
+
+@dataclass(frozen=True)
+class RectangleAdvancedParameters:
+    """Advanced parameters for Rectangle internals."""
+
+    number_of_bootstraps: int = 7
+    grid_search_split_size: int = 50

{rectanglepy-1.4.2 → rectanglepy-1.5.0}/src/rectanglepy/pp/create_signature.py

@@ -13,6 +13,7 @@ from scipy.cluster.hierarchy import fcluster, linkage
 from scipy.stats import pearsonr
 from sklearn.metrics import silhouette_score
 
+from rectanglepy.parameters import RectangleAdvancedParameters
 from rectanglepy.tl.deconvolution import solve_qp
 
 from .rectangle_signature import RectangleSignatureResult
@@ -129,11 +130,16 @@ def _filter_de_analysis_results(de_analysis_result, p, logfc):
 
 
 def _run_deseq2(
-    countsig: pd.DataFrame, sc_data, annotations: pd.Series, n_cpus: int = None, gene_expression_threshold=0.5
+    countsig: pd.DataFrame,
+    sc_data,
+    annotations: pd.Series,
+    n_cpus: int = None,
+    gene_expression_threshold=0.5,
+    number_of_bootstraps: int = 7,
 ) -> dict[str | int, pd.DataFrame]:
     results = {}
     inference = DefaultInference(n_cpus=n_cpus)
-    bootstrapped_signature = _create_bootstrap_signature(countsig, sc_data, annotations)
+    bootstrapped_signature = _create_bootstrap_signature(countsig, sc_data, annotations, number_of_bootstraps)
     np.random.seed(42)
     for _i, cell_type in enumerate(countsig.columns):
         bootstrapped_signature_copy = bootstrapped_signature.copy()
@@ -167,12 +173,11 @@ def _run_deseq2(
     return results
 
 
-def _create_bootstrap_signature(countsig, sc_data, annotations) -> pd.DataFrame:
+def _create_bootstrap_signature(countsig, sc_data, annotations, number_of_bootstraps: int = 7) -> pd.DataFrame:
     if scipy.sparse.issparse(sc_data):
         sc_data = sc_data.toarray()
     celltypes = countsig.columns
     bootstrapped_signature = pd.DataFrame()
-    number_of_bootstraps = 7
     samples_per_bootstrap = 500
     np.random.seed(42)
     for celltype in celltypes:
@@ -198,14 +203,30 @@ def _de_analysis(
     n_cpus: int = None,
     genes=None,
     gene_expression_threshold=0.5,
+    advanced_parameters: RectangleAdvancedParameters = None,
 ) -> tuple[Series, dict[str, [str]] :, DataFrame | None]:
     logger.info("Starting DE analysis")
-    deseq_results = _run_deseq2(pseudo_count_sig, sc_data, annotations, n_cpus, gene_expression_threshold)
+    advanced_parameters = advanced_parameters or RectangleAdvancedParameters()
+    deseq_results = _run_deseq2(
+        pseudo_count_sig,
+        sc_data,
+        annotations,
+        n_cpus,
+        gene_expression_threshold,
+        advanced_parameters.number_of_bootstraps,
+    )
     optimization_results = None
 
     if optimize_cutoffs:
         logger.info("Optimizing cutoff parameters p and lfc")
-        optimization_results = _optimize_parameters(sc_data, annotations, pseudo_count_sig, deseq_results, genes)
+        optimization_results = _optimize_parameters(
+            sc_data,
+            annotations,
+            pseudo_count_sig,
+            deseq_results,
+            genes,
+            advanced_parameters.grid_search_split_size,
+        )
         p, lfc = optimization_results.iloc[0, 0:2]
         logger.info(f"Optimization done\n Best cutoffs  p: {p} and lfc: {lfc}")
 
@@ -287,6 +308,7 @@ def build_rectangle_signatures(
     lfc=1.5,
     n_cpus: int = None,
     gene_expression_threshold=0.5,
+    advanced_parameters: RectangleAdvancedParameters = None,
 ) -> RectangleSignatureResult:
     r"""Builds rectangle signatures based on single-cell  count data and annotations.
 
@@ -303,7 +325,7 @@ def build_rectangle_signatures(
     raw
         A flag indicating whether to use the raw Anndata data. Defaults to False.
     optimize_cutoffs
-        Indicates whether to optimize the p-value and log fold change cutoffs using gridsearch. Defaults to True.
+        Indicates whether to optimize the log fold change cutoffs using gridsearch. Defaults to True.
     p
         The p-value threshold for the DE analysis (only used if optimize_cutoffs is False).
     lfc
@@ -312,11 +334,14 @@ def build_rectangle_signatures(
         The number of cpus to use for the DE analysis. Defaults to the number of cpus available.
     gene_expression_threshold
         The gene expression threshold for the DE analysis. How many cells need to express a gene to be considered in DGE
+    advanced_parameters
+        Optional advanced Rectangle parameters. Defaults are used when not provided.
 
     Returns
     -------
     The result of the rectangle signature analysis which is of type RectangleSignatureResult.
     """
+    advanced_parameters = advanced_parameters or RectangleAdvancedParameters()
     annotations = adata.obs[cell_type_col]
     adata = adata[:, adata.X.sum(axis=0) > len(annotations.value_counts())]
     assert adata.var_names.is_unique, "Duplicate gene found in adata"
@@ -344,7 +369,16 @@ def build_rectangle_signatures(
     m_rna_biasfactors = _create_bias_factors(pseudo_sig_counts, sc_counts, annotations)
 
     marker_genes, marker_genes_per_cell_type, optimization_result = _de_analysis(
-        pseudo_sig_counts, sc_counts, annotations, p, lfc, optimize_cutoffs, n_cpus, genes, gene_expression_threshold
+        pseudo_sig_counts,
+        sc_counts,
+        annotations,
+        p,
+        lfc,
+        optimize_cutoffs,
+        n_cpus,
+        genes,
+        gene_expression_threshold,
+        advanced_parameters,
     )
     pseudo_sig_cpm = _convert_to_cpm(pseudo_sig_counts)
     logger.info("Starting rectangle cluster analysis")
@@ -371,6 +405,7 @@ def build_rectangle_signatures(
         lfc,
         False,
         gene_expression_threshold=gene_expression_threshold,
+        advanced_parameters=advanced_parameters,
     )
     clustered_signature = _convert_to_cpm(clustered_signature)
     return RectangleSignatureResult(
@@ -400,7 +435,12 @@ def _create_pseudo_count_sig(sc_counts: np.ndarray, annotations: pd.Series, var_
 
 
 def _optimize_parameters(
-    sc_data: pd.DataFrame, annotations: pd.Series, pseudo_signature_counts: pd.DataFrame, de_results, genes=None
+    sc_data: pd.DataFrame,
+    annotations: pd.Series,
+    pseudo_signature_counts: pd.DataFrame,
+    de_results,
+    genes=None,
+    grid_search_split_size: int = 50,
 ) -> pd.DataFrame:
     # search space for p and lfc
     lfcs = [x / 100 for x in range(160, 230, 10)]
@@ -408,7 +448,7 @@ def _optimize_parameters(
 
     results = []
     logger.info("generating pseudo bulks")
-    bulks, real_fractions = _generate_pseudo_bulks(sc_data, annotations, genes)
+    bulks, real_fractions = _generate_pseudo_bulks(sc_data, annotations, genes, grid_search_split_size)
     for p in ps:
         for lfc in lfcs:
             try:
@@ -441,9 +481,8 @@ def _assess_parameter_fit(
     return rsme, pearson_r
 
 
-def _generate_pseudo_bulks(sc_data, annotations, genes=None):
+def _generate_pseudo_bulks(sc_data, annotations, genes=None, split_size: int = 50):
     number_of_bulks = 50
-    split_size = 50
     bulks = []
     real_fractions = []
     np.random.seed(42)

{rectanglepy-1.4.2 → rectanglepy-1.5.0}/src/rectanglepy/rectangle.py

@@ -7,6 +7,7 @@ from anndata import AnnData
 from loguru import logger
 from pandas import DataFrame
 
+from .parameters import RectangleAdvancedParameters
 from .pp import RectangleSignatureResult, build_rectangle_signatures
 from .tl import deconvolution
 
@@ -24,6 +25,7 @@ def rectangle(
     lfc=1.5,
     n_cpus: int = None,
     gene_expression_threshold=0.5,
+    advanced_parameters: RectangleAdvancedParameters = None,
 ) -> tuple[DataFrame, RectangleSignatureResult]:
     r"""All in one deconvolution method. Creates signatures and deconvolutes the bulk data. Has options for subsampling and consensus runs.
 
@@ -40,7 +42,7 @@ def rectangle(
     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.
+        Indicates whether to optimize the log fold change cutoffs using gridsearch.
     p
         The p-value threshold for the DE analysis (only used if optimize_cutoffs is False).
     lfc
@@ -51,6 +53,8 @@ def rectangle(
         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.
+    advanced_parameters
+        Optional advanced Rectangle parameters. Defaults are used when not provided.
 
     Returns
     -------
@@ -71,6 +75,7 @@ def rectangle(
         lfc=lfc,
         n_cpus=n_cpus,
         gene_expression_threshold=gene_expression_threshold,
+        advanced_parameters=advanced_parameters,
     )
 
     estimations, bulk_err = deconvolution(signatures, bulks, correct_mrna_bias, n_cpus)

{rectanglepy-1.4.2 → rectanglepy-1.5.0}/tests/test_pp.py

@@ -6,6 +6,7 @@ import pytest
 from anndata import AnnData
 
 import rectanglepy as rectangle
+from rectanglepy import RectangleAdvancedParameters
 from rectanglepy.pp.create_signature import (
     _assess_parameter_fit,
     _calculate_cluster_range,
@@ -18,6 +19,7 @@ from rectanglepy.pp.create_signature import (
     _de_analysis,
     _generate_pseudo_bulks,
     _get_fcluster_assignments,
+    _optimize_parameters,
     _run_deseq2,
     build_rectangle_signatures,
 )
@@ -154,6 +156,7 @@ def test_generate_pseudo_bulks(small_data):
     sc_counts = sc_counts.astype("int")
     adata = AnnData(sc_counts.T, obs=annotations.to_frame(name="cell_type"))
     result, _ = _generate_pseudo_bulks(adata.X.T, annotations, adata.var_names)
+    custom_result, _ = _generate_pseudo_bulks(adata.X.T, annotations, adata.var_names, split_size=10)
 
     sc_data = sc_counts.astype(pd.SparseDtype("int"))
     csr_sparse_matrix = sc_data.sparse.to_coo().tocsr()
@@ -162,11 +165,40 @@ def test_generate_pseudo_bulks(small_data):
     result_sparse, _ = _generate_pseudo_bulks(adata_sparse.X.T, annotations, adata_sparse.var_names)
 
     assert len(result) == 1000 and len(result.columns) == 50
+    assert custom_result.shape == result.shape
+    assert not np.allclose(result, custom_result)
     # first gene should have all 0s
     assert result.iloc[0, :].sum() == 0
     assert np.allclose(result, result_sparse)
 
 
+def test_optimize_parameters_uses_grid_search_split_size(monkeypatch):
+    seen = {}
+
+    def fake_generate_pseudo_bulks(sc_data, annotations, genes=None, split_size=50):
+        seen["split_size"] = split_size
+        bulks = pd.DataFrame([[1.0]], index=["gene"], columns=["bulk"])
+        real_fractions = pd.DataFrame([[1.0]], index=["cell_type"], columns=["bulk"])
+        return bulks, real_fractions
+
+    def fake_assess_parameter_fit(lfc, p, bulks, real_fractions, pseudo_signature_counts, de_results):
+        return 0.0, 1.0
+
+    monkeypatch.setattr(rectangle.pp.create_signature, "_generate_pseudo_bulks", fake_generate_pseudo_bulks)
+    monkeypatch.setattr(rectangle.pp.create_signature, "_assess_parameter_fit", fake_assess_parameter_fit)
+
+    results = _optimize_parameters(
+        pd.DataFrame(),
+        pd.Series(dtype=str),
+        pd.DataFrame(),
+        {},
+        grid_search_split_size=13,
+    )
+
+    assert seen["split_size"] == 13
+    assert results.iloc[0]["pearson_r"] == 1.0
+
+
 def test_asses_fit(small_data):
     sc_counts, annotations, bulk = small_data
     sc_counts = sc_counts.astype("int")
@@ -217,3 +249,20 @@ def test_create_bootstrap_signature(small_data):
     bootstrap = _create_bootstrap_signature(sc_pseudo, adata.X.T, annotations)
 
     assert len(bootstrap.columns) == len(sc_pseudo.columns) * bootstraps_per_cell
+
+
+def test_create_bootstrap_signature_with_advanced_parameter(small_data):
+    bootstraps_per_cell = 3
+    advanced_parameters = RectangleAdvancedParameters(number_of_bootstraps=bootstraps_per_cell)
+    sc_counts, annotations, bulk = small_data
+    sc_counts = sc_counts.astype("int")
+    sc_pseudo = sc_counts.groupby(annotations.values, axis=1).sum()
+    adata = AnnData(sc_counts.T, obs=annotations.to_frame(name="cell_type"))
+    bootstrap = _create_bootstrap_signature(
+        sc_pseudo,
+        adata.X.T,
+        annotations,
+        advanced_parameters.number_of_bootstraps,
+    )
+
+    assert len(bootstrap.columns) == len(sc_pseudo.columns) * bootstraps_per_cell