Class testing

Dockerfile

@@ -1,4 +1,4 @@
-# Copyright (C) 2025 Ladislav Hovan <ladislav.hovan@ncmbm.uio.no>
+# Copyright (C) 2026 Ladislav Hovan <ladislav.hovan@ncmbm.uio.no>
 #
 # SPDX-License-Identifier: GPL-3.0-or-later
 #

README.md

@@ -1,5 +1,5 @@
-[![master](https://github.com/kuijjerlab/sponge/actions/workflows/test.yaml/badge.svg?branch=main)](https://github.com/kuijjerlab/sponge/actions/workflows/test.yaml)
-[![devel](https://github.com/kuijjerlab/sponge/actions/workflows/test.yaml/badge.svg?branch=devel)](https://github.com/kuijjerlab/sponge/actions/workflows/test.yaml)
+[![main](https://img.shields.io/github/actions/workflow/status/kuijjerlab/sponge/test.yaml?branch=main&label=main)](https://github.com/kuijjerlab/sponge/actions/workflows/test.yaml)
+[![devel](https://img.shields.io/github/actions/workflow/status/kuijjerlab/sponge/test.yaml?branch=devel&label=devel)](https://github.com/kuijjerlab/sponge/actions/workflows/test.yaml)
 [![License: GPL v3](https://img.shields.io/badge/License-GPLv3-blue.svg)](https://www.gnu.org/licenses/gpl-3.0)
 
 
@@ -247,7 +247,7 @@ In HPC environments, something like the `apptainer shell` command would
 work.
 
 Because of the libraries used for bigbed format support, SPONGE is not
-currently supported on Windows. 
+currently supported on Windows.
 Therefore, this container is probably the best way to run it there,
 and the command equivalent to the above in the command prompt would look
 like this:
@@ -263,7 +263,8 @@ The project is: _in progress_.
 
 ## Room for Improvement
 Room for improvement:
-- Better tests
+- More test cases
+- Tests with expected failure
 
 To do:
 - Support for more species

pyproject.toml

@@ -17,14 +17,15 @@ classifiers = [
     "Programming Language :: Python :: 3",
     "Topic :: Scientific/Engineering :: Bio-Informatics",
 ]
-dependencies = [ 
+dependencies = [
     "bioframe>=0.8.0,<0.9",
     "matplotlib>=3.10.8,<4",
     "numpy>=1.19.0,<3",
     "pandas>=2.0.0,<3",
     "pybbi>=0.4.0,<0.5",
     "pyjaspar>=4.0.0,<5",
     "scikit-learn>=1.7.2,<2",
+    "setuptools-scm>=8.3.0,<9",
     "tqdm>=4.67.1,<5",
 ]
 

requirements.txt

@@ -5,4 +5,5 @@ pandas
 pybbi
 pyjaspar
 scikit-learn
+setuptools-scm
 tqdm

src/sponge/cli.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2025 Ladislav Hovan <ladislav.hovan@ncmbm.uio.no>
+# Copyright (C) 2026 Ladislav Hovan <ladislav.hovan@ncmbm.uio.no>
 #
 # SPDX-License-Identifier: GPL-3.0-or-later
 #
@@ -22,12 +22,13 @@
 from argparse import (ArgumentDefaultsHelpFormatter, ArgumentParser,
     RawDescriptionHelpFormatter)
 from pathlib import Path
+from setuptools_scm import get_version
 
 from .sponge import Sponge
 
 ### Class definition ###
 class CustomFormatter(
-    ArgumentDefaultsHelpFormatter, 
+    ArgumentDefaultsHelpFormatter,
     RawDescriptionHelpFormatter,
 ):
     """
@@ -47,7 +48,7 @@ def cli(
     """
 
     DESCRIPTION = """
-    SPONGE  Copyright (C) 2025  Ladislav Hovan  <ladislav.hovan@ncmbm.uio.no>
+    SPONGE  Copyright (C) 2026  Ladislav Hovan  <ladislav.hovan@ncmbm.uio.no>
     This program comes with ABSOLUTELY NO WARRANTY.
     This is free software, and you are welcome to redistribute it under certain conditions.
     Please refer to the GPL-3.0 license for more details.
@@ -70,10 +71,15 @@ def cli(
         help='create an example config file with the default values called '
             'user_config.yaml and exit',
         action='store_true')
+    parser.add_argument('-v', '--version', dest='show_version',
+        help='show the current version and exit', action='store_true')
 
     args = parser.parse_args()
 
-    if args.example_config:
+    if args.show_version:
+        print (get_version(version_scheme='only-version',
+            local_scheme='no-local-version'))
+    elif args.example_config:
         file_dir = Path(__file__).parents[0]
         shutil.copy(os.path.join(file_dir, 'user_config.yaml'),
             'user_config.yaml')

src/sponge/config_manager.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2025 Ladislav Hovan <ladislav.hovan@ncmbm.uio.no>
+# Copyright (C) 2026 Ladislav Hovan <ladislav.hovan@ncmbm.uio.no>
 #
 # SPDX-License-Identifier: GPL-3.0-or-later
 #

src/sponge/modules/analysis/analysis.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2025 Ladislav Hovan <ladislav.hovan@ncmbm.uio.no>
+# Copyright (C) 2026 Ladislav Hovan <ladislav.hovan@ncmbm.uio.no>
 #
 # SPDX-License-Identifier: GPL-3.0-or-later
 #
@@ -43,7 +43,7 @@ def load_prior(
         The processed pandas DataFrame
     """
 
-    return pd.read_csv(path, sep='\t', header=None, names=names)
+    return pd.read_table(path, header=None, names=names)
 
 
 def describe_prior(

src/sponge/modules/data_retriever/data_retriever.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2025 Ladislav Hovan <ladislav.hovan@ncmbm.uio.no>
+# Copyright (C) 2026 Ladislav Hovan <ladislav.hovan@ncmbm.uio.no>
 #
 # SPDX-License-Identifier: GPL-3.0-or-later
 #
@@ -17,7 +17,7 @@
 
 ### Imports ###
 from pathlib import Path
-from typing import List
+from typing import Optional
 
 from sponge.config_manager import ConfigManager
 from sponge.modules.version_logger import VersionLogger
@@ -33,7 +33,7 @@ def __init__(
         temp_folder: Path,
         core_config: ConfigManager,
         user_config: ConfigManager,
-        version_logger: VersionLogger,
+        version_logger: Optional[VersionLogger] = None,
     ):
         """
         Class that retrieves the data required for the running of
@@ -47,8 +47,9 @@ def __init__(
             Core configuration of SPONGE
         user_config : ConfigManager
             User-provided configuration of SPONGE
-        version_logger : VersionLogger
-            Version logger to keep track of the retrieved files
+        version_logger : Optional[VersionLogger], optional
+            Version logger to keep track of the retrieved files or None
+            to not use one, by default None
         """
 
         # JASPAR bigbed file (if appropriate)
@@ -72,8 +73,9 @@ def __init__(
             core_config['default_chromosomes'],
         )
         # Register the classes for version logging
-        version_logger.register_class(self.tfbs)
-        version_logger.register_class(self.regions)
+        if version_logger is not None:
+            version_logger.register_class(self.tfbs)
+            version_logger.register_class(self.regions)
 
 
     def retrieve_data(

src/sponge/modules/data_retriever/file_retriever.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2025 Ladislav Hovan <ladislav.hovan@ncmbm.uio.no>
+# Copyright (C) 2026 Ladislav Hovan <ladislav.hovan@ncmbm.uio.no>
 #
 # SPDX-License-Identifier: GPL-3.0-or-later
 #

src/sponge/modules/data_retriever/region_retriever.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2025 Ladislav Hovan <ladislav.hovan@ncmbm.uio.no>
+# Copyright (C) 2026 Ladislav Hovan <ladislav.hovan@ncmbm.uio.no>
 #
 # SPDX-License-Identifier: GPL-3.0-or-later
 #
@@ -80,7 +80,7 @@ def __init__(
         self.rest = rest_url
         self.mapping_url = mapping_url
         self.assembly = genome_assembly
-        self.mapping = default_mapping
+        self.mapping = pd.Series(default_mapping)
 
         if region_settings['chromosomes'] is None:
             region_settings['chromosomes'] = default_chromosomes
@@ -105,33 +105,38 @@ def _retrieve_region(
             Version of the Ensembl database corresponding to the file
         """
 
+        # Attempt to retrieve mapping
+        mapping = get_chromosome_mapping(self.assembly, self.mapping_url)
+        if mapping is not None:
+            # Managed to retrieve it, overwrite the default
+            self.mapping = mapping
+        # Inverted mapping to apply chromosome filtering
+        inv_mapping = pd.Series(self.mapping.index, index=self.mapping.values)
+        # Filter for the required chromosomes
+        chroms = [inv_mapping[chrom] for chrom in self.settings['chromosomes']]
+        filter = {'chromosome_name': chroms}
         # Attributes to retrieve
-        attributes = ['ensembl_transcript_id', 'transcript_gencode_basic',
+        ATTRIBUTES = ['ensembl_transcript_id', 'transcript_gencode_basic',
             'chromosome_name', 'transcription_start_site', 'strand',
             'ensembl_gene_id', 'external_gene_name', 'gene_biotype']
         # Submit and retrieve the response
-        buffer = retrieve_ensembl_data('hsapiens_gene_ensembl', attributes,
-            self.xml)
+        buffer = retrieve_ensembl_data('hsapiens_gene_ensembl', ATTRIBUTES,
+            self.xml, filter)
 
         # Dictionary of types for conversion from the response, default strings
         dtype_dict = defaultdict(lambda: str)
         # Change the types that are not strings but integers
         dtype_dict['Transcription start site (TSS)'] = int
         dtype_dict['Strand'] = int
         # Convert the response into a DataFrame
-        df = pd.read_csv(buffer, sep='\t', dtype=dtype_dict)
+        df = pd.read_table(buffer, dtype=dtype_dict)
 
-        print ('\nFiltering and modifying dataframe...\n')
+        print ('\nFiltering and modifying dataframe...')
         if self.settings['filter_basic']:
             # Filter only for GENCODE basic
             df = df[df['GENCODE basic annotation'] == 'GENCODE basic'].copy()
             df.drop(columns='GENCODE basic annotation', inplace=True)
         # Convert chromosome names to match with other inputs
-        # Attempt to retrieve mapping
-        mapping = get_chromosome_mapping(self.assembly, self.mapping_url)
-        if mapping is not None:
-            # Managed to retrieve it, overwrite the default
-            self.mapping = mapping
         df['Chromosome'] = df['Chromosome/scaffold name'].apply(lambda x:
             self.mapping[x] if x in self.mapping else None)
         not_mapped = df['Chromosome'].isna().sum()
@@ -160,11 +165,11 @@ def _retrieve_region(
         df.sort_values(['Chromosome', 'Start'], inplace=True)
 
         # Columns to be saved into a file
-        columns = ['Chromosome', 'Start', 'End', 'Transcript stable ID',
+        COLUMNS = ['Chromosome', 'Start', 'End', 'Transcript stable ID',
             'Gene stable ID', 'Gene name', 'Gene type']
         print (f'\nSaving data to: {self.temp_filename}')
         # Save the file
-        self.df = df[columns]
+        self.df = df[COLUMNS]
         self.df.to_csv(self.temp_filename, sep='\t', index=False)
 
         return get_ensembl_version(self.rest)

src/sponge/modules/data_retriever/tfbs_retriever.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2025 Ladislav Hovan <ladislav.hovan@ncmbm.uio.no>
+# Copyright (C) 2026 Ladislav Hovan <ladislav.hovan@ncmbm.uio.no>
 #
 # SPDX-License-Identifier: GPL-3.0-or-later
 #
@@ -65,6 +65,8 @@ def __init__(
         self.jaspar_release = motif_settings['jaspar_release']
         self.genome_assembly = genome_assembly
         self.urls = motif_url
+        if type(self.urls) is not list:
+            self.urls = [self.urls]
 
         temp_filename = os.path.join(temp_folder, self._default_filename)
 

src/sponge/modules/file_writer/file_writer.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2025 Ladislav Hovan <ladislav.hovan@ncmbm.uio.no>
+# Copyright (C) 2026 Ladislav Hovan <ladislav.hovan@ncmbm.uio.no>
 #
 # SPDX-License-Identifier: GPL-3.0-or-later
 #
@@ -19,7 +19,7 @@
 import pandas as pd
 
 from pathlib import Path
-from typing import Iterable
+from typing import Iterable, Union
 
 ### Class definition ###
 class FileWriter:
@@ -30,14 +30,14 @@ def __init__(
         """
         Class which writes prior networks to files.
         """
-        
+
         pass
 
 
     def write_network_file(
         self,
         df: pd.DataFrame,
-        node_columns: Iterable[str],
+        node_columns: Union[Iterable[str], str],
         weight_column: str,
         file_name: Path,
     ):
@@ -55,7 +55,9 @@ def write_network_file(
         file_name : Path
             Where to write the network to
         """
-
+
+        if type(node_columns) == str:
+            node_columns = [node_columns]
         sorted_df = df.sort_values(by=node_columns)
         sorted_df[node_columns + [weight_column]].to_csv(
             file_name, sep='\t', index=False, header=False)

src/sponge/modules/match_aggregator/match_aggregator.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2025 Ladislav Hovan <ladislav.hovan@ncmbm.uio.no>
+# Copyright (C) 2026 Ladislav Hovan <ladislav.hovan@ncmbm.uio.no>
 #
 # SPDX-License-Identifier: GPL-3.0-or-later
 #
@@ -47,7 +47,7 @@ def __init__(
         """
 
         self.initial_edges = edges
-        self.regions = pd.read_csv(regions_file, sep='\t')
+        self.regions = pd.read_table(regions_file)
         self.homolog_mapping = homolog_mapping
         # To be overwritten once retrieved
         self.edges = None

src/sponge/modules/match_filter/match_filter.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2025 Ladislav Hovan <ladislav.hovan@ncmbm.uio.no>
+# Copyright (C) 2026 Ladislav Hovan <ladislav.hovan@ncmbm.uio.no>
 #
 # SPDX-License-Identifier: GPL-3.0-or-later
 #

src/sponge/modules/motif_selector/homology_retriever.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2025 Ladislav Hovan <ladislav.hovan@ncmbm.uio.no>
+# Copyright (C) 2026 Ladislav Hovan <ladislav.hovan@ncmbm.uio.no>
 #
 # SPDX-License-Identifier: GPL-3.0-or-later
 #
@@ -112,6 +112,7 @@ def find_homologs(
 
         # Get the non-species motif names
         xeno_motif_names = [motif.name for motif in xeno_motifs]
+        xeno_motif_ids = [motif.matrix_id for motif in xeno_motifs]
         # Compare against NCBI homologs
         found_names = [adjust_gene_name(motif.name) for motif in xeno_motifs
             if not False in [acc in homologs for acc in motif.acc]]
@@ -129,7 +130,8 @@ def find_homologs(
             for motif in xeno_motifs
             if not False in [acc in homologs for acc in motif.acc]
         }
-        corr_df = pd.DataFrame(xeno_motif_names, columns=['Original Name'])
+        corr_df = pd.DataFrame({'Original Name': xeno_motif_names,
+            'Matrix ID': xeno_motif_ids})
         corr_df['Adjusted Name'] = corr_df['Original Name'].apply(
             adjust_gene_name)
         corr_df['Species Name'] = corr_df['Original Name'].apply(
@@ -146,10 +148,11 @@ def find_homologs(
                 print (f'{i}:', to_print.loc[i])
 
             # Calculate the information content for duplicates
-            duplicated['IC'] = duplicated['Original Name'].apply(lambda x:
-                max(tf_to_motif[x].values()))
+            duplicated['IC'] = duplicated.apply(lambda row:
+                tf_to_motif[row['Original Name']][row['Matrix ID']], axis=1,
+                result_type='reduce')
             # Keep the highest IC amongst the duplicates
-            to_drop = duplicated['Original Name'][duplicated.sort_values(
+            to_drop = duplicated['Matrix ID'][duplicated.sort_values(
                 'IC').duplicated('Species Name', keep='last')]
         else:
             to_drop = []
@@ -164,7 +167,7 @@ def find_homologs(
         # homologs
         corr_df_final = corr_df[(corr_df['Duplicate'] == False) &
             (~corr_df['Species Name'].isna()) &
-            (corr_df['Original Name'].isin(to_drop) == False)]
+            (corr_df['Matrix ID'].isin(to_drop) == False)]
 
         # The mapping of out-species to in-species names
         # and the matrix IDs to be kept

src/sponge/modules/motif_selector/jaspar_retriever.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2025 Ladislav Hovan <ladislav.hovan@ncmbm.uio.no>
+# Copyright (C) 2026 Ladislav Hovan <ladislav.hovan@ncmbm.uio.no>
 #
 # SPDX-License-Identifier: GPL-3.0-or-later
 #