Fixes for JASPAR 2026

.github/workflows/test.yaml

@@ -9,6 +9,8 @@ on:
     branches:
     - main
     - devel
+  schedule:
+  - cron: '15 3 1 * *'  # 1st of every month at 3:15
   workflow_dispatch:
 
 jobs:
@@ -18,7 +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 }}
 

README.md

@@ -1,5 +1,5 @@
-[![master](https://github.com/ladislav-hovan/sponge/actions/workflows/test.yaml/badge.svg?branch=main)](https://github.com/ladislav-hovan/sponge/actions/workflows/test.yaml)
-[![devel](https://github.com/ladislav-hovan/sponge/actions/workflows/test.yaml/badge.svg?branch=devel)](https://github.com/ladislav-hovan/sponge/actions/workflows/test.yaml)
+[![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)
 [![License: GPL v3](https://img.shields.io/badge/License-GPLv3-blue.svg)](https://www.gnu.org/licenses/gpl-3.0)
 
 

pyproject.toml

@@ -2,9 +2,6 @@
 requires = ["setuptools", "setuptools-scm"]
 build-backend = "setuptools.build_meta"
 
-[tool.setuptools.packages.find]
-namespaces = false
-
 [project]
 name = "netzoopy-sponge"
 authors = [
@@ -20,14 +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]
@@ -52,15 +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'"

sponge/modules/data_retriever/region_retriever.py → 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)

sponge/modules/ppi_retriever/ppi_retriever.py → 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: '

sponge/modules/utils/tfbs_filtering.py → 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

tests/sponge/test_motif_prior.tsv

@@ -2,13 +2,15 @@ FOXF2	AATBC	1
 FOXF2	ABCC13	1
 FOXF2	AGPAT3	1
 FOXF2	ASMER1	1
+FOXF2	B3GALT5	1
 FOXF2	BACH1	1
 FOXF2	BACH1-IT1	1
 FOXF2	BACH1-IT3	1
 FOXF2	BAGE2	1
 FOXF2	BTF3P6	1
 FOXF2	C21orf58	1
 FOXF2	C21orf91	1
+FOXF2	CFAP298	1
 FOXF2	CFAP298-TCP10L	1
 FOXF2	CHODL	1
 FOXF2	CLDN14	1
@@ -51,7 +53,6 @@ FOXF2	ENSG00000231713	1
 FOXF2	ENSG00000232193	1
 FOXF2	ENSG00000232360	1
 FOXF2	ENSG00000232806	1
-FOXF2	ENSG00000232855	1
 FOXF2	ENSG00000232884	1
 FOXF2	ENSG00000233783	1
 FOXF2	ENSG00000234340	1
@@ -151,9 +152,11 @@ FOXF2	ENSG00000310309	1
 FOXF2	ERG	1
 FOXF2	ETS2	1
 FOXF2	ETS2-AS1	1
+FOXF2	EVA1C	1
 FOXF2	FDPSP6	1
 FOXF2	FGF7P2	1
 FOXF2	FTCD	1
+FOXF2	GART	1
 FOXF2	GET1	1
 FOXF2	GPX1P2	1
 FOXF2	GRIK1-AS1	1
@@ -166,6 +169,7 @@ FOXF2	IL10RB	1
 FOXF2	IMMTP1	1
 FOXF2	ITSN1	1
 FOXF2	KCNE1	1
+FOXF2	KCNJ15	1
 FOXF2	KCNJ6-AS1	1
 FOXF2	KRTAP10-11	1
 FOXF2	KRTAP13-5P	1
@@ -199,6 +203,7 @@ FOXF2	LINC01687	1
 FOXF2	LINC01695	1
 FOXF2	LINC01700	1
 FOXF2	LINC03105	1
+FOXF2	LINC03138	1
 FOXF2	LIPI	1
 FOXF2	LLPHP2	1
 FOXF2	LNCTSI	1
@@ -249,10 +254,12 @@ FOXF2	SAMSN1-AS1	1
 FOXF2	SETD4	1
 FOXF2	SH3BGR	1
 FOXF2	SIM2	1
+FOXF2	SLC19A1	1
 FOXF2	SOD1-DT	1
 FOXF2	SPATA20P1	1
 FOXF2	TIMM9P2	1
 FOXF2	TMPRSS15	1
+FOXF2	TMPRSS2	1
 FOXF2	TMPRSS3	1
 FOXF2	TRPM2-AS	1
 FOXF2	U6	1
@@ -264,6 +271,7 @@ FOXF2	ZNF295-AS1	1
 FOXF2	ZNF299P	1
 FOXF2	ZNF355P	1
 GATA2	ABCC13	1
+GATA2	BACH1	1
 GATA2	BACH1-IT1	1
 GATA2	C1QBPP1	1
 GATA2	C2CD2	1
@@ -366,6 +374,7 @@ GATA2	GRIK1-AS1	1
 GATA2	HLCS	1
 GATA2	HLCS-IT1	1
 GATA2	ITSN1	1
+GATA2	KCNJ15	1
 GATA2	KCNJ6	1
 GATA2	KRTAP19-10P	1
 GATA2	KRTAP19-7	1
@@ -387,6 +396,7 @@ GATA2	LINC01700	1
 GATA2	LINC02573	1
 GATA2	LINC02940	1
 GATA2	LNCTSI	1
+GATA2	MAP3K7CL	1
 GATA2	MIR3156-3	1
 GATA2	MIR4327	1
 GATA2	MIR4760	1
@@ -396,6 +406,7 @@ GATA2	MX1	1
 GATA2	MX2	1
 GATA2	NCAM2	1
 GATA2	NIPA2P3	1
+GATA2	OLIG2	1
 GATA2	RHOT1P2	1
 GATA2	RN7SL163P	1
 GATA2	RNU6-113P	1
@@ -409,10 +420,12 @@ GATA2	RUNX1-AS1	1
 GATA2	SAMSN1	1
 GATA2	SAMSN1-AS1	1
 GATA2	TERF1P1	1
+GATA2	TMPRSS2	1
 GATA2	U3	1
 GATA2	UBE2G2	1
 GATA2	UBE3AP2	1
 GATA2	Y_RNA	1
+GATA2	ZBTB21	1
 GATA2	ZNF295-AS1	1
 JUN	AATBC	1
 JUN	ABCC13	1
@@ -422,6 +435,7 @@ JUN	AGPAT3	1
 JUN	AIRE	1
 JUN	APP	1
 JUN	ASMER1	1
+JUN	ATP5PF	1
 JUN	B3GALT5	1
 JUN	BACH1-IT2	1
 JUN	BRWD1-AS1	1
@@ -479,7 +493,6 @@ JUN	ENSG00000231136	1
 JUN	ENSG00000231867	1
 JUN	ENSG00000231986	1
 JUN	ENSG00000232124	1
-JUN	ENSG00000232855	1
 JUN	ENSG00000233783	1
 JUN	ENSG00000235023	1
 JUN	ENSG00000235277	1
@@ -596,6 +609,7 @@ JUN	ETS2	1
 JUN	ETS2-AS1	1
 JUN	EXOSC3P1	1
 JUN	FAM3B	1
+JUN	GABPA	1
 JUN	GATD3	1
 JUN	GET1	1
 JUN	GET1-SH3BGR	1
@@ -604,6 +618,7 @@ JUN	HLCS-IT1	1
 JUN	HSF2BP	1
 JUN	IFNAR1	1
 JUN	IFNAR2	1
+JUN	ITGB2	1
 JUN	KCNE1	1
 JUN	KCNJ15	1
 JUN	KCNJ6-AS1	1
@@ -641,6 +656,7 @@ JUN	LINC01690	1
 JUN	LINC01695	1
 JUN	LINC02573	1
 JUN	LINC03104	1
+JUN	LINC03138	1
 JUN	LTN1	1
 JUN	MIR155HG	1
 JUN	MIR4760	1
@@ -654,6 +670,7 @@ JUN	MTCO1P3	1
 JUN	MTND6P21	1
 JUN	MTRES1P2	1
 JUN	MX1	1
+JUN	MX2	1
 JUN	MYL6P1	1
 JUN	MYL6P2	1
 JUN	OLIG2	1
@@ -662,6 +679,7 @@ JUN	PCBP3-AS1	1
 JUN	PCP4	1
 JUN	PCSEAT	1
 JUN	PICSAR	1
+JUN	PKNOX1	1
 JUN	PLAC4	1
 JUN	POLR2CP1	1
 JUN	PSMA6P3	1
@@ -688,10 +706,13 @@ JUN	RPSAP68	1
 JUN	RRP1	1
 JUN	RRP1B	1
 JUN	RUNX1	1
+JUN	S100B	1
 JUN	SAMSN1-AS1	1
 JUN	SETD4	1
 JUN	SIK1	1
+JUN	SLC19A1	1
 JUN	SLC37A1	1
+JUN	SMIM11	1
 JUN	SMIM34	1
 JUN	SNX18P10	1
 JUN	SOD1	1
@@ -700,6 +721,7 @@ JUN	TCP10L	1
 JUN	TFF1	1
 JUN	TIAM1	1
 JUN	TMEM97P1	1
+JUN	TMPRSS2	1
 JUN	TMPRSS3	1
 JUN	TPT1P1	1
 JUN	TRPM2-AS	1

tests/sponge/test_user_config.yaml

@@ -30,4 +30,4 @@ motif_output:
   weighted: False  # False by default
 ppi_output:
   file_name: "ppi_prior.tsv"
-  weighted: False  # False by default
+  weighted: False  # False by default

tests/test_sponge.py

@@ -9,7 +9,7 @@
 
 from Bio.motifs.jaspar import Motif
 from pathlib import Path
-from pyjaspar import jaspardb
+from pyjaspar import jaspardb, JASPAR_LATEST_RELEASE
 from typing import Tuple
 
 from sponge.config_manager import ConfigManager
@@ -221,7 +221,7 @@ def test_recursive_update(input, expected_output):
 import sponge.modules.utils.jaspar_versioning as jaspar_f
 
 @pytest.mark.parametrize('input, expected_output', [
-    (None, 'JASPAR2024'),
+    (None, JASPAR_LATEST_RELEASE),
     ('JASPAR2022', 'JASPAR2022'),
     ('2024', 'JASPAR2024'),
 ])
@@ -417,7 +417,7 @@ def test_full_default_workflow(tmp_path):
     _,_ = run_integration_test_common(
         tmp_path,
         # Default config file
-        os.path.join('sponge', 'user_config.yaml'),
+        os.path.join('src', 'sponge', 'user_config.yaml'),
     )