black formatting

gffutils/biopython_integration.py

@@ -47,9 +47,8 @@ def to_seqfeature(feature):
  # Convert from GFF 1-based to standard Python 0-based indexing used by
  # BioPython
  FeatureLocation(
- feature.start - 1,
- feature.stop,
- strand=_biopython_strand[feature.strand]),
+ feature.start - 1, feature.stop, strand=_biopython_strand[feature.strand]
+ ),
  id=feature.id,
  type=feature.featuretype,
  qualifiers=qualifiers,

gffutils/convert.py

@@ -3,7 +3,6 @@
 """
 
 
-
 def to_bed12(f, db, child_type="exon", name_field="ID"):
  """
  Given a top-level feature (e.g., transcript), construct a BED12 entry

gffutils/create.py

@@ -216,7 +216,8 @@ def _id_handler(self, f):
  "a single value is required for a primary key in the "
  "database. Consider using a custom id_spec to "
  "convert these multiple values into a single "
- "value".format(k))
+ "value".format(k)
+ )
  except KeyError:
  pass
  try:

gffutils/helpers.py

@@ -519,7 +519,6 @@ def canonical_transcripts(db, fasta_filename):
  """
  import pyfaidx
 
-
  fasta = pyfaidx.Fasta(fasta_filename, as_raw=False)
  for gene in db.features_of_type("gene"):
 
@@ -535,7 +534,20 @@ def canonical_transcripts(db, fasta_filename):
  cds_len += exon_length
  total_len += exon_length
 
- exon_list.append((cds_len, total_len, transcript, exons if cds_len == 0 else [e for e in exons if e.featuretype in ['CDS', 'five_prime_UTR', 'three_prime_UTR']]))
+ exon_list.append(
+ (
+ cds_len,
+ total_len,
+ transcript,
+ exons
+ if cds_len == 0
+ else [
+ e
+ for e in exons
+ if e.featuretype in ["CDS", "five_prime_UTR", "three_prime_UTR"]
+ ],
+ )
+ )
 
  # If we have CDS, then use the longest coding transcript
  if max(i[0] for i in exon_list) > 0:
@@ -548,7 +560,12 @@ def canonical_transcripts(db, fasta_filename):
 
  canonical_exons = best[-1]
  transcript = best[-2]
- seqs = [i.sequence(fasta) for i in sorted(canonical_exons, key=lambda x: x.start, reverse=transcript.strand != '+')]
+ seqs = [
+ i.sequence(fasta)
+ for i in sorted(
+ canonical_exons, key=lambda x: x.start, reverse=transcript.strand != "+"
+ )
+ ]
  yield transcript, "".join(seqs)
 
 

gffutils/interface.py

@@ -101,7 +101,7 @@ def __init__(
  keep_order=False,
  pragmas=constants.default_pragmas,
  sort_attribute_values=False,
- text_factory=str
+ text_factory=str,
  ):
  """
  Connect to a database created by :func:`gffutils.create_db`.
@@ -871,10 +871,21 @@ def _init_interfeature(f):
  Used to initialize a new interfeature that is ready to be updated
  in-place.
  """
- keys = ['id', 'seqid', 'source', 'featuretype', 'start', 'end',
- 'score', 'strand', 'frame', 'attributes', 'bin']
+ keys = [
+ "id",
+ "seqid",
+ "source",
+ "featuretype",
+ "start",
+ "end",
+ "score",
+ "strand",
+ "frame",
+ "attributes",
+ "bin",
+ ]
  d = dict(zip(keys, f.astuple()))
- d['source'] = 'gffutils_derived'
+ d["source"] = "gffutils_derived"
  return d
 
  def _prep_for_yield(d):
@@ -885,25 +896,26 @@ def _prep_for_yield(d):
  If start is greater than stop (which happens when trying to get
  interfeatures for overlapping features), then return None.
  """
- d['start'] += 1
- d['end'] -= 1
- new_bin = bins.bins(d['start'], d['end'], one=True)
- d['bin'] = new_bin
+ d["start"] += 1
+ d["end"] -= 1
+ new_bin = bins.bins(d["start"], d["end"], one=True)
+ d["bin"] = new_bin
 
- if d['start'] > d['end']:
+ if d["start"] > d["end"]:
  return None
 
  new_feature = self._feature_returner(**d)
 
  # concat list of ID to create uniq IDs because feature with
  # multiple values for their ID are no longer permitted since v0.11
  if "ID" in new_feature.attributes and len(new_feature.attributes["ID"]) > 1:
- new_id = '-'.join(new_feature.attributes["ID"])
+ new_id = "-".join(new_feature.attributes["ID"])
  new_feature.attributes["ID"] = [new_id]
  return new_feature
 
  # If not provided, use a no-op function instead.
  if not attribute_func:
+
  def attribute_func(a):
  return a
 
@@ -932,23 +944,23 @@ def attribute_func(a):
  nfeatures += 1
 
  # Adjust the interfeature dict in-place with coords...
- interfeature['start'] = last_feature.stop
- interfeature['end'] = f.start
+ interfeature["start"] = last_feature.stop
+ interfeature["end"] = f.start
 
  # ...featuretype
  if new_featuretype is None:
- interfeature['featuretype'] = "inter_%s_%s" % (
+ interfeature["featuretype"] = "inter_%s_%s" % (
  last_feature.featuretype,
  f.featuretype,
  )
  else:
- interfeature['featuretype'] = new_featuretype
+ interfeature["featuretype"] = new_featuretype
 
  # ...strand
  if last_feature.strand != f.strand:
- interfeature['strand'] = '.'
+ interfeature["strand"] = "."
  else:
- interfeature['strand'] = f.strand
+ interfeature["strand"] = f.strand
 
  # and attributes
  if merge_attributes:
@@ -963,7 +975,7 @@ def attribute_func(a):
  if update_attributes:
  new_attributes.update(update_attributes)
 
- interfeature['attributes'] = new_attributes
+ interfeature["attributes"] = new_attributes
 
  # Ready to yield
  new_feature = _prep_for_yield(interfeature)
@@ -1389,11 +1401,12 @@ def child_gen():
  splice_site.start = splice_site.end - 1
 
  # make ID uniq by adding suffix
- splice_site.attributes["ID"] = [new_featuretype + "_" + splice_site.attributes["ID"][0]]
+ splice_site.attributes["ID"] = [
+ new_featuretype + "_" + splice_site.attributes["ID"][0]
+ ]
 
  yield splice_site
 
-
  def _old_merge(self, features, ignore_strand=False):
  """
  DEPRECATED, only retained here for backwards compatibility. Please use
@@ -1709,10 +1722,12 @@ def merge_all(
  return result_features
 
  def children_bp(
- self, feature, child_featuretype="exon", merge=False,
- merge_criteria=(mc.seqid, mc.overlap_end_inclusive, mc.strand,
- mc.feature_type),
- **kwargs
+ self,
+ feature,
+ child_featuretype="exon",
+ merge=False,
+ merge_criteria=(mc.seqid, mc.overlap_end_inclusive, mc.strand, mc.feature_type),
+ **kwargs
  ):
  """
  Total bp of all children of a featuretype.
@@ -1751,9 +1766,14 @@ def children_bp(
  raise ValueError(
  "'ignore_strand' has been deprecated; please use "
  "merge_criteria to control how features should be merged. "
- "E.g., leave out the 'mc.strand' criteria to ignore strand.")
+ "E.g., leave out the 'mc.strand' criteria to ignore strand."
+ )
  else:
- raise TypeError("merge() got unexpected keyword arguments '{}'".format(kwargs.keys()))
+ raise TypeError(
+ "merge() got unexpected keyword arguments '{}'".format(
+ kwargs.keys()
+ )
+ )
 
  children = self.children(
  feature, featuretype=child_featuretype, order_by="start"
@@ -1940,7 +1960,6 @@ def seqids(self):
  for (i,) in c:
  yield i
 
-
  # Recycle the docs for _relation so they stay consistent between parents()
  # and children()
  children.__doc__ = children.__doc__.format(_relation_docstring=_relation.__doc__)

gffutils/test/conftest.py

@@ -1 +1 @@
-collect_ignore=["data"]
+collect_ignore = ["data"]

gffutils/test/test_1.py

@@ -636,7 +636,7 @@ def test_feature_merge():
  id_spec="gene_id",
  force_merge_fields=["start"],
  keep_order=True,
-  )
+ )
 
  # test that warnings are raised because of strand and frame
  with warnings.catch_warnings(record=True) as w:
@@ -933,17 +933,19 @@ def _transform(f):
  [(i.start, i.stop) for i in db.features_of_type("exon")]
  )
 
+
 def clean_tempdir():
  tempfile.tempdir = tempdir
  if os.path.exists(tempdir):
  shutil.rmtree(tempdir)
  os.makedirs(tempdir)
 
+
 # specify a writeable temp dir for testing
 tempdir = "/tmp/gffutils-test"
 
-def test_tempfiles():
 
+def test_tempfiles():
 
  clean_tempdir()
 
@@ -991,6 +993,7 @@ def test_tempfiles():
  assert len(filelist) == 1, filelist
  assert filelist[0].endswith(".GFFtmp")
 
+
 @pytest.mark.skip(reason="Unclear if still needed; currently failing")
 def test_parallel_db():
  # DISABLING in v0.12
@@ -1113,7 +1116,7 @@ def test_deprecation_handler():
  gffutils.example_filename("FBgn0031208.gtf"),
  ":memory:",
  infer_gene_extent=False,
-  )
+ )
 
 
 def test_nonsense_kwarg():
@@ -1122,7 +1125,7 @@ def test_nonsense_kwarg():
  gffutils.example_filename("FBgn0031208.gtf"),
  ":memory:",
  asdf=True,
-  )
+ )
 
 
 def test_infer_gene_extent():
@@ -1241,7 +1244,8 @@ def test_create_splice_sites():
  db = gffutils.create_db(fn, ":memory:")
  db = db.update(db.create_splice_sites())
  observed = "\n".join(str(feature) for feature in db.all_features())
- expected = dedent("""\
+ expected = dedent(
+ """\
  chr1 ensGene gene 4763287 4775820 . - . Name=ENSMUSG00000033845;ID=ENSMUSG00000033845;Alias=ENSMUSG00000033845;gid=ENSMUSG00000033845
  chr1 ensGene mRNA 4764517 4775779 . - . Name=ENSMUST00000045689;Parent=ENSMUSG00000033845;ID=ENSMUST00000045689;Alias=ENSMUSG00000033845;gid=ENSMUSG00000033845
  chr1 ensGene CDS 4775654 4775758 . - 0 Name=ENSMUST00000045689.cds0;Parent=ENSMUST00000045689;ID=ENSMUST00000045689.cds0;gid=ENSMUSG00000033845
@@ -1259,13 +1263,12 @@ def test_create_splice_sites():
  chr1 gffutils_derived three_prime_cis_splice_site 4772815 4772816 . - . Name=ENSMUST00000045689.exon0,ENSMUST00000045689.exon1;Parent=ENSMUST00000045689;ID=three_prime_cis_splice_site_ENSMUST00000045689.exon0-ENSMUST00000045689.exon1;gid=ENSMUSG00000033845
  chr1 gffutils_derived five_prime_cis_splice_site 4767604 4767605 . - . Name=ENSMUST00000045689.exon2,ENSMUST00000045689.exon3;Parent=ENSMUST00000045689;ID=five_prime_cis_splice_site_ENSMUST00000045689.exon2-ENSMUST00000045689.exon3;gid=ENSMUSG00000033845
  chr1 gffutils_derived five_prime_cis_splice_site 4772647 4772648 . - . Name=ENSMUST00000045689.exon1,ENSMUST00000045689.exon2;Parent=ENSMUST00000045689;ID=five_prime_cis_splice_site_ENSMUST00000045689.exon1-ENSMUST00000045689.exon2;gid=ENSMUSG00000033845
- chr1 gffutils_derived five_prime_cis_splice_site 4775652 4775653 . - . Name=ENSMUST00000045689.exon0,ENSMUST00000045689.exon1;Parent=ENSMUST00000045689;ID=five_prime_cis_splice_site_ENSMUST00000045689.exon0-ENSMUST00000045689.exon1;gid=ENSMUSG00000033845""")
+ chr1 gffutils_derived five_prime_cis_splice_site 4775652 4775653 . - . Name=ENSMUST00000045689.exon0,ENSMUST00000045689.exon1;Parent=ENSMUST00000045689;ID=five_prime_cis_splice_site_ENSMUST00000045689.exon0-ENSMUST00000045689.exon1;gid=ENSMUSG00000033845"""
+ )
 
  assert observed == expected
 
 
-
-
 if __name__ == "__main__":
  # this test case fails
  # test_attributes_modify()