Overlap enhancement

.github/workflows/test.yaml

@@ -20,7 +20,7 @@ jobs:
     strategy:
       matrix:
         os: [ 'ubuntu-latest', 'macos-latest' ]
-        python: [ '3.9', '3.10', '3.11', '3.12' ]
+        python: [ '3.10', '3.11', '3.12', '3.13' ]
 
     runs-on: ${{ matrix.os }}
 

pyproject.toml

@@ -17,14 +17,14 @@ classifiers = [
     "Programming Language :: Python :: 3",
     "Topic :: Scientific/Engineering :: Bio-Informatics",
 ]
-dependencies = [
-    "bioframe",
-    "numpy",
-    "pandas",
-    "pybbi",
-    "pyjaspar",
-    "scikit-learn",
-    "tqdm",
+dependencies = [ 
+    "bioframe>=0.8.0,<0.9",
+    "numpy>=2.2.6,<3",
+    "pandas>=2.3.3,<3",
+    "pybbi>=0.4.2,<0.5",
+    "pyjaspar>=4.0.0,<5",
+    "scikit-learn>=1.7.2,<2",
+    "tqdm>=4.67.1,<5",
 ]
 
 [project.scripts]
@@ -49,15 +49,16 @@ channels = ["conda-forge"]
 platforms = ["linux-64"]
 
 [tool.pixi.tasks]
+sponge = "netzoopy-sponge"
 
 [tool.pixi.dependencies]
-python = "3.10.*"
+python = ">=3.10.0"
 
 [tool.pixi.pypi-dependencies]
 netzoopy-sponge = { path = ".", editable = true }
 
 [tool.pixi.feature.sponge-dev.dependencies]
-pytest = "*"
+pytest = ">=8.4.0"
 
 [tool.pixi.feature.sponge-dev.tasks]
 test = "pytest -m 'not slow'"

src/sponge/modules/data_retriever/region_retriever.py

@@ -121,7 +121,7 @@ def _retrieve_region(
         # Convert the response into a DataFrame
         df = pd.read_csv(buffer, sep='\t', dtype=dtype_dict)
 
-        print ('Filtering and modifying dataframe...')
+        print ('\nFiltering and modifying dataframe...\n')
         if self.settings['filter_basic']:
             # Filter only for GENCODE basic
             df = df[df['GENCODE basic annotation'] == 'GENCODE basic'].copy()
@@ -162,7 +162,7 @@ def _retrieve_region(
         # Columns to be saved into a file
         columns = ['Chromosome', 'Start', 'End', 'Transcript stable ID',
             'Gene stable ID', 'Gene name', 'Gene type']
-        print (f'Saving data to: {self.temp_filename}')
+        print (f'\nSaving data to: {self.temp_filename}')
         # Save the file
         self.df = df[columns]
         self.df.to_csv(self.temp_filename, sep='\t', index=False)

src/sponge/modules/ppi_retriever/ppi_retriever.py

@@ -141,8 +141,8 @@ def retrieve_ppi(
             'preferredName_B': 'tf2'}, inplace=True)
         if len(ids_to_check) > 0:
             # Replace with names that have been queried (as used by JASPAR)
-            ppi_df['tf1'].replace(p_to_q, inplace=True)
-            ppi_df['tf2'].replace(p_to_q, inplace=True)
+            ppi_df['tf1'] = ppi_df['tf1'].replace(p_to_q)
+            ppi_df['tf2'] = ppi_df['tf2'].replace(p_to_q)
         ppi_df.sort_values(by=['tf1', 'tf2'], inplace=True)
 
         print ('\nFinal number of TFs in the PPI network: '

src/sponge/modules/utils/tfbs_filtering.py

@@ -78,6 +78,11 @@ def filter_edges(
         start,end = bed_df.loc[transcript][['Start', 'End']]
         # Load all matches in that region from the bigbed file
         motifs = bioframe.read_bigbed(bb_ref, chrom, start=start, end=end)
+        # This is a temporary guard until the name of TFName column
+        # is fixed for the 2026 release
+        colnames = ['chrom', 'start', 'end', 'name', 'score', 'strand',
+            'TFName']
+        motifs.columns = colnames
         # Ensure the entire motif fits within range (not default behaviour)
         motifs = motifs[(motifs['start'] >= start) & (motifs['end'] <= end)]
         # Filter only the transcription factors in the list