rectanglepy 0.3.0__tar.gz → 0.4.3__tar.gz

{rectanglepy-0.3.0 → rectanglepy-0.4.3}/.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.3.0
+current_version = 0.4.3
 tag = True
 commit = True
 

{rectanglepy-0.3.0 → rectanglepy-0.4.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: rectanglepy
-Version: 0.3.0
+Version: 0.4.3
 Summary: Hierarchical deconvolution of bulk  transcriptomics
 Project-URL: Documentation, https://rectanglepy.readthedocs.io/
 Project-URL: Source, https://github.com/ComputationalBiomedicineGroup/Rectangle

{rectanglepy-0.3.0 → rectanglepy-0.4.3}/pyproject.toml

@@ -4,7 +4,7 @@ requires = ["hatchling"]
 
 [project]
 name = "rectanglepy"
-version = "0.3.0"
+version = "0.4.3"
 description = "Hierarchical deconvolution of bulk  transcriptomics"
 readme = "README.md"
 requires-python = ">=3.10"

{rectanglepy-0.3.0 → rectanglepy-0.4.3}/src/rectanglepy/pp/create_signature.py

@@ -170,8 +170,8 @@ def _create_bootstrap_signature(countsig, sc_data, annotations) -> pd.DataFrame:
         sc_data = sc_data.toarray()
     celltypes = countsig.columns
     bootstrapped_signature = pd.DataFrame()
-    number_of_bootstraps = 5
-    samples_per_bootstrap = 250
+    number_of_bootstraps = 7
+    samples_per_bootstrap = 500
     for celltype in celltypes:
         sc_data_filtered = sc_data.T[annotations == celltype]
         for i in range(number_of_bootstraps):
@@ -179,6 +179,9 @@ def _create_bootstrap_signature(countsig, sc_data, annotations) -> pd.DataFrame:
             summed_rows = sc_data_filtered[selected_rows].sum(axis=0)
             bootstrapped_signature[f"{celltype}_{i}"] = list(summed_rows)
     bootstrapped_signature.index = countsig.index
+    # to int
+    samples_per_bootstrap = samples_per_bootstrap / 2.5
+    bootstrapped_signature = bootstrapped_signature.astype(int)
     return bootstrapped_signature
 
 

{rectanglepy-0.3.0 → rectanglepy-0.4.3}/src/rectanglepy/tl/deconvolution.py

@@ -311,7 +311,7 @@ def correct_for_unknown_cell_content(
     if estimates.sum() == 0:
         estimates_fix = estimates
         # analysis fails if all cell fractions are zero, so we set the unknown cell content to ß
-        estimates_fix.loc["Unknown"] = 0
+        estimates_fix["Unknown"] = 0
         return estimates_fix
 
     signature_genes = pseudo_signature_cpm.index
@@ -333,6 +333,6 @@ def correct_for_unknown_cell_content(
     # Correct (i.e. scale) the cell fraction estimates so that their sum
     # equals 1 - the unknown cellular content estimated above
     estimates_fix = estimates / estimates.sum() * (1 - ukn_cc)
-    estimates_fix.loc["Unknown"] = abs(ukn_cc)
+    estimates_fix["Unknown"] = abs(ukn_cc)
 
     return estimates_fix

{rectanglepy-0.3.0 → rectanglepy-0.4.3}/tests/test_pp.py

@@ -243,7 +243,7 @@ def test_build_rectangle_signatures_even(small_data):
 
 
 def test_create_bootstrap_signature(small_data):
-    bootstraps_per_cell = 5
+    bootstraps_per_cell = 7
     sc_counts, annotations, bulk = small_data
     sc_counts = sc_counts.astype("int")
     sc_pseudo = sc_counts.groupby(annotations.values, axis=1).sum()

rectanglepy-0.4.3/tests/test_rectangle.py

@@ -0,0 +1,25 @@
+import pandas as pd
+from anndata import AnnData
+
+import rectanglepy.rectangle
+from rectanglepy.pp import RectangleSignatureResult
+
+
+def test_load_tutorial_data():
+    sc_data, annotations, bulks = rectanglepy.load_tutorial_data()
+    assert isinstance(sc_data, pd.DataFrame)
+    assert isinstance(annotations, pd.Series)
+    assert isinstance(bulks, pd.DataFrame)
+
+
+def test_rectangle():
+    sc_data, annotations, bulks = rectanglepy.load_tutorial_data()
+    sc_data = sc_data.iloc[:, :2000]
+    sc_data_adata = AnnData(sc_data, obs=annotations.to_frame(name="cell_type"))
+
+    result = rectanglepy.rectangle(sc_data_adata, bulks)
+    estimations, signatures = result
+
+    assert isinstance(estimations, pd.DataFrame)
+    assert isinstance(signatures, RectangleSignatureResult)
+    assert isinstance(signatures.unkn_gene_corr, pd.Series)

rectanglepy-0.3.0/tests/test_rectangle.py

@@ -1,51 +0,0 @@
-import pandas as pd
-from anndata import AnnData
-
-import rectanglepy.rectangle
-from rectanglepy import ConsensusResult
-from rectanglepy.pp import RectangleSignatureResult
-
-
-def test_load_tutorial_data():
-    sc_data, annotations, bulks = rectanglepy.load_tutorial_data()
-    assert isinstance(sc_data, pd.DataFrame)
-    assert isinstance(annotations, pd.Series)
-    assert isinstance(bulks, pd.DataFrame)
-
-
-def test_rectangle():
-    sc_data, annotations, bulks = rectanglepy.load_tutorial_data()
-    sc_data = sc_data.iloc[:, :2000]
-    sc_data_adata = AnnData(sc_data, obs=annotations.to_frame(name="cell_type"))
-
-    result = rectanglepy.rectangle(sc_data_adata, bulks)
-    estimations, signatures = result
-
-    assert isinstance(estimations, pd.DataFrame)
-    assert isinstance(signatures, RectangleSignatureResult)
-    assert isinstance(signatures.unkn_gene_corr, pd.Series)
-
-
-def test_rectangle_consensus():
-    sc_data, annotations, bulks = rectanglepy.load_tutorial_data()
-    sc_data = sc_data.iloc[:, :500]
-    sc_data_adata = AnnData(sc_data, obs=annotations.to_frame(name="cell_type"))
-
-    result = rectanglepy.rectangle_consens(
-        sc_data_adata, bulks, optimize_cutoffs=False, p=0.2, lfc=0.0, consensus_runs=3, sample_size=50
-    )
-
-    assert isinstance(result[0], pd.DataFrame)
-    assert isinstance(result[1], RectangleSignatureResult)
-    assert isinstance(result[2], ConsensusResult)
-
-    estimations = result[0]
-    consensus_results = result[2]
-    signature_results = consensus_results.rectangle_signature_results
-    bias_factors = [result.bias_factors for result in signature_results]
-    # there was a problem with the random sampling, the bias factors should differ
-    assert bias_factors[0]["Monocytes"] != bias_factors[1]["Monocytes"]
-    assert bias_factors[0]["Monocytes"] != bias_factors[2]["Monocytes"]
-    assert bias_factors[1]["Monocytes"] != bias_factors[2]["Monocytes"]
-    # in the consensus we have to make sure that the estimations are again normalized to 1
-    assert estimations.sum(axis=1).all() == 1.0