attempt to fix missing interactions 1

ktplotspy/plot/plot_cpdb.py

@@ -34,6 +34,7 @@
     DEFAULT_SPEC_PAT,
     DEFAULT_CELLSIGN_ALPHA,
     DEFAULT_COLUMNS,
+    DEFAULT_CPDB_SEP,
 )
 from ktplotspy.utils.support import (
     ensure_categorical,

ktplotspy/plot/plot_cpdb_heatmap.py

@@ -7,8 +7,8 @@
 from matplotlib.colors import ListedColormap
 from typing import Optional, Union, Dict, List
 
-from ktplotspy.utils.support import diverging_palette, sub_pattern
-from ktplotspy.utils.settings import DEFAULT_V5_COL_START, DEFAULT_COL_START, DEFAULT_CLASS_COL, DEFAULT_SPEC_PAT
+from ktplotspy.utils.support import diverging_palette
+from ktplotspy.utils.settings import DEFAULT_V5_COL_START, DEFAULT_COL_START, DEFAULT_CLASS_COL, DEFAULT_CPDB_SEP
 
 
 def plot_cpdb_heatmap(
@@ -27,7 +27,6 @@ def plot_cpdb_heatmap(
     title: str = "",
     return_tables: bool = False,
     symmetrical: bool = True,
-    special_character_regex_pattern: Optional[str] = None,
     **kwargs
 ) -> Union[sns.matrix.ClusterGrid, Dict]:
     """Plot cellphonedb results as total counts of interactions.
@@ -67,8 +66,6 @@ def plot_cpdb_heatmap(
         Whether to return the dataframes storing the interaction network.
     symmetrical : bool, optional
         Whether to return the sum of interactions as symmetrical heatmap.
-    special_character_regex_pattern : Optional[str], optional
-        Regular expression pattern to handle special characters from celltype names.
     **kwargs
         Passed to seaborn.clustermap.
 
@@ -78,25 +75,25 @@ def plot_cpdb_heatmap(
     Union[sns.matrix.ClusterGrid, Dict]
         Either heatmap of cellphonedb interactions or dataframe containing the interaction network.
     """
-    if special_character_regex_pattern is None:
-        special_character_regex_pattern = DEFAULT_SPEC_PAT
     all_intr = pvals.copy()
     intr_pairs = all_intr.interacting_pair
     col_start = (
         DEFAULT_V5_COL_START if all_intr.columns[DEFAULT_CLASS_COL] == "classification" else DEFAULT_COL_START
     )  # in v5, there are 12 columns before the values
     all_int = all_intr.iloc[:, col_start : all_intr.shape[1]].T
     all_int.columns = intr_pairs
-    if cell_types is not None:
-        cell_types = [sub_pattern(cell_type=cell_type, pattern=special_character_regex_pattern) for cell_type in cell_types]
-        cell_types_comb = ["|".join(list(x)) for x in list(product(cell_types, cell_types))]
-        cell_types_keep = [ct for ct in all_int.index if ct in cell_types_comb]
-        empty_celltypes = list(set(cell_types_comb) ^ set(cell_types_keep))
-        all_int = all_int.loc[cell_types_keep]
-        if len(empty_celltypes) > 0:
-            tmp_ = np.zeros((len(empty_celltypes), all_int.shape[1]))
-            tmp_ = pd.DataFrame(tmp_, index=empty_celltypes, columns=all_int.columns)
-            all_int = pd.concat([all_int, tmp_], axis=0)
+    if cell_types is None:
+        cell_types = sorted(list(set([y for z in [x.split(DEFAULT_CPDB_SEP) for x in all_intr.columns[col_start:]] for y in z])))
+    cell_types_comb = ["|".join(list(x)) for x in list(product(cell_types, cell_types))]
+    cell_types_keep = [ct for ct in all_int.index if ct in cell_types_comb]
+    empty_celltypes = list(set(cell_types_comb) ^ set(cell_types_keep))
+    all_int = all_int.loc[cell_types_keep]
+    if len(empty_celltypes) > 0:
+        tmp_ = np.zeros((len(empty_celltypes), all_int.shape[1]))
+        if not degs_analysis:
+            tmp_ += 1
+        tmp_ = pd.DataFrame(tmp_, index=empty_celltypes, columns=all_int.columns)
+        all_int = pd.concat([all_int, tmp_], axis=0)
     all_count = all_int.melt(ignore_index=False).reset_index()
     if degs_analysis:
         all_count["significant"] = all_count.value == 1

ktplotspy/utils/settings.py

@@ -13,3 +13,4 @@
 DEFAULT_V5_COL_START = 13
 DEFAULT_COL_START = 11
 DEFAULT_CLASS_COL = 12
+DEFAULT_CPDB_SEP = "|"

ktplotspy/utils/support.py

@@ -15,7 +15,7 @@
 from typing import Dict, List, Optional
 
 
-from ktplotspy.utils.settings import DEFAULT_SEP
+from ktplotspy.utils.settings import DEFAULT_SEP, DEFAULT_CPDB_SEP
 
 
 def set_x_stroke(df: pd.DataFrame, isnull: bool, stroke: int):
@@ -234,7 +234,7 @@ def prep_table(data: pd.DataFrame) -> pd.DataFrame:
     """
     dat = data.copy()
     dat.index = [x + DEFAULT_SEP * 3 + y for x, y in zip(dat.id_cp_interaction, dat.interacting_pair)]
-    dat.columns = [re.sub("\\|", DEFAULT_SEP, col) for col in dat.columns]
+    dat.columns = [re.sub(f"\\{DEFAULT_CPDB_SEP}", DEFAULT_SEP, col) for col in dat.columns]
     dat.index = [re.sub("_", "-", row) for row in dat.index]
     dat.index = [re.sub("[.]", " ", row) for row in dat.index]
 

tests/test_plot_cpdb_heatmap.py

@@ -75,9 +75,9 @@ def test_plot_cpdb_heatmap_return(adata, pvals):
 
 @patch("matplotlib.pyplot.show")
 @pytest.mark.usefixtures("adata", "pvals")
-def test_plot_cpdb_heatmap_celltypes(mock_show, adata, pvals):
+def test_plot_cpdb_heatmap_celltypes(mock_show, adata, pvals_v5):
     g = plot_cpdb_heatmap(
-        pvals=pvals,
-        cell_types=["CD4 T cell", "CD8 T cell", "B cell"],
+        pvals=pvals_v5,
+        cell_types=["iEVT", "PV MYH11", "PV STEAP4", "EVT_1"],
     )
     g