MAINT: update to latest cogent3

pyproject.toml

@@ -12,7 +12,7 @@ readme = "README.md"
 license = { file = "license.txt" }
 requires-python = ">=3.10,<3.14"
 dependencies = ["click",
-        "cogent3",
+        "cogent3>=2025.7.10a3",
         "kaleido",
         "numpy",
         "scipy",

src/mutation_motif/__init__.py

@@ -1,9 +1,9 @@
-"""mutation_motif, software for naalyses of point mutations, see https://www.ncbi.nlm.nih.gov/pubmed/27974498"""
+"""mutation_motif, software for analyses of point mutations, see https://www.ncbi.nlm.nih.gov/pubmed/27974498"""
 
 from warnings import filterwarnings
 
 filterwarnings("ignore", "Attempting to set identical bottom==top")
 filterwarnings("ignore", "invalid value encountered.*")
 
 __license__ = "BSD-3"
-__version__ = "2025.01.28"
+__version__ = "2025.7.17"

src/mutation_motif/aln_to_counts.py

@@ -3,8 +3,10 @@
 import os
 import re
 
+import cogent3
+
 from mutation_motif import motif_count, profile
-from mutation_motif.util import just_nucs, load_from_fasta, makedirs
+from mutation_motif.util import just_nucs, makedirs
 
 fn_suffixes = re.compile(r"\.(fa|fasta)\.*(gz|gzip|bz2)*$")
 
@@ -44,7 +46,7 @@ def align_to_counts(
 
     direction = tuple(direction.split("to"))
     chosen_base = direction[0]
-    orig_seqs = load_from_fasta(os.path.abspath(align_path))
+    orig_seqs = cogent3.load_aligned_seqs(os.path.abspath(align_path), moltype="dna")
     seqs = orig_seqs.array_seqs
     seqs = just_nucs(seqs)
     if not randomise:

src/mutation_motif/complement.py

@@ -17,7 +17,7 @@ def _reverse_complement(table):
     rows = table.to_list()
     for row in rows:
         # we use the cogent3 DnaSeq object to do reverse complementing
-        seq = DNA.make_seq("".join(row[i] for i in pos_indices))
+        seq = DNA.make_seq(seq="".join(row[i] for i in pos_indices))
         seq = list(seq.rc())
         for i, index in enumerate(pos_indices):
             row[index] = seq[i]

src/mutation_motif/log_lin.py

@@ -5,7 +5,7 @@
 import pandas
 import statsmodels.api as sm
 import statsmodels.formula.api as smf
-from cogent3.util.table import Table
+from cogent3.core.table import Table
 from scipy.stats import chi2
 
 _poisson = sm.families.Poisson()

src/mutation_motif/motif_count.py

@@ -1,10 +1,12 @@
 from collections import Counter
 from itertools import product
 
-from cogent3 import make_table
+from cogent3 import get_moltype, make_table
 
 from mutation_motif.util import array_to_str
 
+dna_alpha = get_moltype("DNA").most_degen_alphabet()
+
 
 def profile_to_seq_counts(data, flank_size):
     """converts data to seqs and returns sequence counts"""

src/mutation_motif/util.py

@@ -11,8 +11,6 @@
 
 import numpy
 from cogent3 import DNA, load_table, make_table, open_
-from cogent3.core.alignment import ArrayAlignment
-from cogent3.parse.fasta import iter_fasta_records
 from cogent3.util.union_dict import UnionDict
 from pandas import read_json
 
@@ -151,13 +149,9 @@ def is_valid(data):
     return (data >= 0).all() and (data < 4).all()
 
 
-def load_from_fasta(filename):
-    seqs = list(iter_fasta_records(filename))
-    return ArrayAlignment(data=seqs, moltype=DNA)
-
-
 def array_to_str(data):
     """convert numpy array back to DNA sequence"""
+    data = data.astype(numpy.uint8)
     return ["".join(DNA.alphabet.from_indices(v)) for v in data]
 
 

tests/test_control.py

@@ -178,7 +178,7 @@ def test_get_random_indices(self):
 class TestAlignSnpAnnotation(TestCase):
     seqs = [("seq_0", "ATCAACATATAAAAAGGAAAT")]
 
-    d_aln = make_aligned_seqs(data=seqs, array_align=True, moltype=DNA).array_seqs
+    d_aln = make_aligned_seqs(seqs, moltype=DNA).array_seqs
     step = 3
     slice_side = 7
     direction = "AtoC"

tests/test_entropy.py

@@ -16,42 +16,39 @@
 def ref_aln(DATA_DIR):
     return load_aligned_seqs(
         DATA_DIR / "entropy/ref.fasta",
-        array_align=True,
         moltype=DNA,
     )
 
 
 @pytest.fixture(scope="session")
 def ref_data(ref_aln):
-    return ref_aln.seq_data
+    return ref_aln.array_seqs
 
 
 @pytest.fixture(scope="session")
 def ctl_aln(DATA_DIR):
     return load_aligned_seqs(
         DATA_DIR / "entropy/control.fasta",
-        array_align=True,
         moltype=DNA,
     )
 
 
 @pytest.fixture(scope="session")
 def ctl_data(ctl_aln):
-    return ctl_aln.seq_data
+    return ctl_aln.array_seqs
 
 
 @pytest.fixture(scope="session")
 def gap_aln(DATA_DIR):
     return load_aligned_seqs(
         DATA_DIR / "entropy/gap.fasta",
-        array_align=True,
         moltype=DNA,
     )
 
 
 @pytest.fixture(scope="session")
 def gap_data(gap_aln):
-    return gap_aln.seq_data
+    return gap_aln.array_seqs
 
 
 def test_validity(ref_data, gap_data):

tests/test_motif_count.py

@@ -1,7 +1,6 @@
 from unittest import TestCase, main
 
-from cogent3 import DNA
-from cogent3.core.alignment import ArrayAlignment
+from cogent3 import DNA, make_aligned_seqs
 
 from mutation_motif.motif_count import (
     get_combined_counts,
@@ -36,7 +35,7 @@
 
 def _get_seq_array(data):
     """returns [(n, seq), ...] as DenseArray"""
-    return ArrayAlignment(data=data, moltype=DNA).array_seqs
+    return make_aligned_seqs(data, moltype=DNA).array_seqs
 
 
 class TestMotifCount(TestCase):

tests/test_util.py

@@ -18,7 +18,6 @@
 def aln(DATA_DIR):
     return load_aligned_seqs(
         DATA_DIR / "just_nuc.fasta",
-        array_align=True,
         moltype=DNA,
     )
 
@@ -49,7 +48,6 @@ def test_just_nucs(aln):
 def d_aln(DATA_DIR):
     return load_aligned_seqs(
         DATA_DIR / "load_seqs_to_array.fasta",
-        array_align=True,
         moltype=DNA,
     )