Merge branch 'release/0.18.4'

Author: siebrenf

.rtd-environment.yml

@@ -22,10 +22,10 @@ dependencies:
   - pandas >=1.3, <3
   - pybedtools >=0.9.0
   - pysam >=0.16
-  - python >=3.9, <3.12           # Motifsampler & setuptools break from py3.12
+  - python >=3.9
   - python-xxhash
   - qnorm  >=0.8.1
-  - scikit-learn >=0.23.2         # https://scikit-learn.org/stable/install.html#installing-the-latest-release
+  - scikit-learn >=0.23.2, <1.7   # v1.7 deprecated n_alphas
   - scipy >=1.5                   # https://docs.scipy.org/doc/scipy/dev/toolchain.html#numpy
   - seaborn >=0.10.1
   - statsmodels

CHANGELOG.md

@@ -9,6 +9,14 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).
 
 
 
+## [0.18.4] - 2026-06-19
+
+### Fixed
+
+- `gimme motif2factors` now works with orthofinder 3.1.5 
+
+
+
 ## [0.18.3] - 2026-06-09
 
 ### Added
@@ -533,6 +541,7 @@ manage your genomes.
 
 
 [Unreleased]: https://github.com/vanheeringen-lab/gimmemotifs/compare/master...develop
+[0.18.4]: https://github.com/vanheeringen-lab/gimmemotifs/compare/0.18.3...0.18.4
 [0.18.3]: https://github.com/vanheeringen-lab/gimmemotifs/compare/0.18.2...0.18.3
 [0.18.2]: https://github.com/vanheeringen-lab/gimmemotifs/compare/0.18.1...0.18.2
 [0.18.1]: https://github.com/vanheeringen-lab/gimmemotifs/compare/0.18.0...0.18.1

gimmemotifs/__about__.py

@@ -1 +1 @@
-__version__ = "0.18.3"
+__version__ = "0.18.4"

gimmemotifs/orthologs.py

@@ -112,12 +112,12 @@ def motif2factor_from_orthologs(
 
     # run orthofinder on our primary genes
     logger.info("Running orthofinder to find orthologs.")
-    orthofinder_result = _orthofinder(f"{tmpdir}/prim_genes", threads)
+    orthofinder_results_dir = _orthofinder(f"{tmpdir}/prim_genes", threads)
 
     # now parse the output of orthofinder
     logger.info("Storing everything in a database.")
     orthogroup_db = f"{tmpdir}/orthologs.sqlite"
-    load_orthogroups_in_db(orthogroup_db, all_genomes, orthofinder_result)
+    load_orthogroups_in_db(orthogroup_db, all_genomes, orthofinder_results_dir)
 
     # get all motifs and related factors from motif database
     motifs = read_motifs(database)
@@ -173,10 +173,12 @@ def _orthofinder(peptide_folder, threads):
     logger.debug(f"""stdout of orthofinder:\n {result.stdout.decode("utf-8")}""")
     logger.debug(f"""stderr of orthofinder:\n {result.stderr.decode("utf-8")}""")
 
-    orthofinder_result = re.search(
-        "Results:\n    (.*)", result.stdout.decode("utf-8")
+    # [^/]+: match anything except forward slashes (including the present ANSI codes)
+    # (.+)/: match anything until the last forward slash before a newline
+    orthofinder_results_dir = re.search(
+        "Results directory:[^/]+(.+)/", result.stdout.decode("utf-8")
     ).group(1)
-    return orthofinder_result
+    return orthofinder_results_dir
 
 
 def _prepare_genomes_with_annot(genome, genome_dir, outdir):
@@ -354,7 +356,7 @@ def annot2primpep(genome, outdir):
             f.write("\n")
 
 
-def load_orthogroups_in_db(db, genomes, orthofinder_result):
+def load_orthogroups_in_db(db, genomes, orthofinder_results_dir):
     """
     Save the results of orthofinder (tsv file) in a relational database
     (SQLite). This makes it possible to easily switch between genes and
@@ -363,15 +365,16 @@ def load_orthogroups_in_db(db, genomes, orthofinder_result):
     We create three tables; genes, orthogroups, and assemblies.
     """
     orthogroups = pd.read_table(
-        f"{orthofinder_result}/Phylogenetic_Hierarchical_Orthogroups/N0.tsv"
+        f"{orthofinder_results_dir}/Orthogroups/Orthogroups.tsv"
     )
     unassigned = pd.read_table(
-        f"{orthofinder_result}/Orthogroups/Orthogroups_UnassignedGenes.tsv"
+        f"{orthofinder_results_dir}/Orthogroups/Orthogroups_UnassignedGenes.tsv"
     )
 
-    # remove old db if it exists (TODO: shouldnt be necessary?)
+    # remove old db if it exists
     if os.path.exists(db):
         os.remove(db)
+
     conn = sqlite3.connect(db)
     conn.execute(
         """
@@ -412,7 +415,7 @@ def load_orthogroups_in_db(db, genomes, orthofinder_result):
 
     # fill up our database
     # all orthogroups
-    for orthogroup in orthogroups["HOG"]:  # <-- all Hierarchical OrthoGroups
+    for orthogroup in orthogroups["Orthogroup"]:  # <-- all Hierarchical OrthoGroups
         conn.execute(f"INSERT INTO orthogroups VALUES(NULL, '{orthogroup}')")
     conn.execute("INSERT INTO orthogroups VALUES(NULL, 'UNASSIGNED')")
 
@@ -423,7 +426,7 @@ def load_orthogroups_in_db(db, genomes, orthofinder_result):
     # all genes per species
     for assembly in genomes:
         for orthogroup, genes in zip(
-            orthogroups["HOG"], orthogroups[f"{assembly}.pep"]
+            orthogroups["Orthogroup"], orthogroups[f"{assembly}.pep"]
         ):
             if isinstance(genes, float) and np.isnan(genes):
                 continue

requirements.yaml

@@ -26,9 +26,15 @@ dependencies:
   - statsmodels
   - tqdm >=4.46.1
   - xdg
-  - xgboost >=1.0.2               # optional: xgboost regression predictor for MOAP. 1 GB
 
-  # motif discovery tools
+  # gimme maelstrom (optional)
+  - xgboost >=1.0.2               # xgboost regression predictor for MOAP. 1 GB
+
+  # gimme motif2factors (optional)
+  - gffread >=0.12.7
+  - orthofinder >=3.1.5           # requires python >=3.11
+
+  # gimme motifs (optional)
   - gcc                           # optional: necessary to install motif discovery tools
   # AMD                           # installed from source
   # BioProspector                 # installed from source