Merge pull request #68 from schillerlab/feature/pseudobulk

Add calc pseudobulk

.cookietemple.yml

@@ -16,5 +16,5 @@ email: [email protected]
 project_name: sc-toolbox
 project_short_description: A collection of project templates and useful code snippets
   for single-cell data analysis with Scanpy.
-version: 0.8.0
+version: 0.9.0
 license: MIT

.github/release-drafter.yml

@@ -1,5 +1,5 @@
-name-template: "0.8.0 🌈" # <<COOKIETEMPLE_FORCE_BUMP>>
-tag-template: 0.8.0 # <<COOKIETEMPLE_FORCE_BUMP>>
+name-template: "0.9.0 🌈" # <<COOKIETEMPLE_FORCE_BUMP>>
+tag-template: 0.9.0 # <<COOKIETEMPLE_FORCE_BUMP>>
 categories:
     - title: "🚀 Features"
       labels:

cookietemple.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.8.0
+current_version = 0.9.0
 
 [bumpversion_files_whitelisted]
 init_file = sc_toolbox/__init__.py

docs/conf.py

@@ -52,9 +52,9 @@
 # the built documents.
 #
 # The short X.Y version.
-version = "0.8.0"
+version = "0.9.0"
 # The full version, including alpha/beta/rc tags.
-release = "0.8.0"
+release = "0.9.0"
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "sc-toolbox"
-version = "0.8.0"  # <<COOKIETEMPLE_FORCE_BUMP>>
+version = "0.9.0"  # <<COOKIETEMPLE_FORCE_BUMP>>
 description = "A collection of project templates and useful code snippets for single-cell data analysis with Scanpy."
 authors = ["Lukas Heumos <[email protected]>"]
 license = "MIT"

sc_toolbox/__init__.py

@@ -2,6 +2,6 @@
 
 __author__ = "Lukas Heumos"
 __email__ = "[email protected]"
-__version__ = "0.8.0"
+__version__ = "0.9.0"
 
 from sc_toolbox.api import calc, plot, util

sc_toolbox/api/calc/__init__.py

@@ -449,6 +449,35 @@ def extended_marker_table(
     return all_markers_df
 
 
+def generate_pseudobulk(adata: AnnData, group_key: str = "identifier", sep="\t", save: str = None) -> pd.DataFrame:
+    """
+    Generates a pseudobulk for a given key of groups in the AnnData object.
+    Looks like:
+      Genes    group_member_1    group_member_2
+    1 gene_1   value_1           value_2
+    2 gene_2   value_3           value_4
+
+    Args:
+        adata: AnnData object
+        group_key: The key to group by. E.g. by mice, by condition, ... (default: 'identifier')
+        sep: Separator to use when saving the pseudobulk table (default: '\t')
+        save: Path to save the pseudobulk table to (default: None)
+
+    Returns:
+        A Pandas DataFrame containing the pseudobulk table
+    """
+    pseudobulk = pd.DataFrame(data=adata.var_names.values, columns=["Genes"])
+
+    for i in adata.obs.loc[:, group_key].cat.categories:
+        temp = adata.obs.loc[:, group_key] == i
+        pseudobulk[i] = adata[temp].X.sum(0, dtype=int)  # column sums (genes)
+
+    if save:
+        pseudobulk.to_csv(save, sep=sep, index=False)
+
+    return pseudobulk
+
+
 def automated_marker_annotation(
     adata: AnnData,
     organism: str,