Merge pull request #60 from peterjc/no_alpha

Cope without Bio.Alphabet for Biopython 1.78 onwards

deepbgc/util.py

@@ -15,7 +15,6 @@
 
 import six
 from Bio import SeqIO
-from Bio.Alphabet import SingleLetterAlphabet, generic_dna
 from appdirs import user_data_dir
 try:
     from urllib.request import urlretrieve
@@ -509,10 +508,10 @@ def fix_duplicate_cds(record):
 
 
 def fix_dna_alphabet(record):
-    if type(record.seq.alphabet) == SingleLetterAlphabet:
-        logging.warning('Updating record alphabet to generic_dna')
-        record.seq.alphabet = generic_dna
-    record.seq.alphabet = generic_dna
+    """Explicitly label a SeqRecord as DNA (e.g. for GenBank output)."""
+    if "DNA" != record.annotations.get("molecule_type", ""):
+        logging.warning('Updating record molecule type to DNA')
+    record.annotations['molecule_type'] = 'DNA'
 
 
 def read_compatible_csv(path):

setup.py

@@ -8,7 +8,7 @@
 
 install_requires = [
     'argparse',
-    'biopython==1.76', # support for structured comments from version 1.70, removed Alphabet in version 1.78
+    'biopython>=1.78', # Bio.Alphabet was removed then
     'scikit-learn==0.21.3', # sklearn with random forest compatibility
     'pandas==0.24.1',
     'numpy==1.16.1',

test/unit/output/test_unit_writers.py

@@ -13,7 +13,6 @@
 from Bio.Seq import Seq
 from Bio.SeqRecord import SeqRecord
 from Bio.SeqFeature import SeqFeature, FeatureLocation
-from Bio.Alphabet import generic_dna
 import os
 import pytest
 
@@ -45,7 +44,8 @@ def __repr__(self):
 @pytest.fixture
 def processed_record(detector_name='deepbgc', detector_label='deepbgc', score_threshold=0.5):
     comment_key = util.format_detector_meta_key(detector_label)
-    record = SeqRecord(Seq('ACTGCTCGACTGATT', alphabet=generic_dna))
+    record = SeqRecord(Seq('ACTGCTCGACTGATT'))
+    record.annotations['molecule_type'] = 'DNA'
     record.annotations['structured_comment'] = collections.OrderedDict()
     record.annotations['structured_comment'][comment_key] = collections.OrderedDict(
         name=detector_name,