Automatically remove redundant commas

Used this hack from psf/black#1288

$ pip install black==19.3b0 && black . && pip install black==19.10b && black .

I then manually reverted changes to a handful of explicit data
structures where the magic trailing comma should be retained
(indicates to black not to squash into one line).

Doing this dramatically improves the changes from trying black
version 21.7b0 (right now just four minor changes).

Bio/AlignIO/MsfIO.py

@@ -316,7 +316,7 @@ def __next__(self):
             )
 
         records = (
-            SeqRecord(Seq(s), id=i, name=i, description=i, annotations={"weight": w},)
+            SeqRecord(Seq(s), id=i, name=i, description=i, annotations={"weight": w})
             for (i, s, w) in zip(ids, seqs, weights)
         )
 

Bio/AlignIO/StockholmIO.py

@@ -231,10 +231,7 @@ def _write_record(self, record):
         seq_name = seq_name.replace(" ", "_")
 
         if "start" in record.annotations and "end" in record.annotations:
-            suffix = "/%s-%s" % (
-                record.annotations["start"],
-                record.annotations["end"],
-            )
+            suffix = "/%s-%s" % (record.annotations["start"], record.annotations["end"])
             if seq_name[-len(suffix) :] != suffix:
                 seq_name = "%s/%s-%s" % (
                     seq_name,

Bio/Blast/Record.py

@@ -252,7 +252,7 @@ def __str__(self):
         else:
             lines.append(
                 "Query:%8s %s...%s %s"
-                % (self.query_start, self.query[:45], self.query[-3:], self.query_end,)
+                % (self.query_start, self.query[:45], self.query[-3:], self.query_end)
             )
             lines.append("               %s...%s" % (self.match[:45], self.match[-3:]))
             lines.append(

Bio/GenBank/Scanner.py

@@ -529,7 +529,7 @@ def parse_records(self, handle, do_features=True):
                 yield record
 
     def parse_cds_features(
-        self, handle, alphabet=None, tags2id=("protein_id", "locus_tag", "product"),
+        self, handle, alphabet=None, tags2id=("protein_id", "locus_tag", "product")
     ):
         """Parse CDS features, return SeqRecord object iterator.
 

Bio/Nexus/Nexus.py

@@ -416,7 +416,7 @@ def combine(matrices):
             combined.matrix[t] += Seq(
                 str(m.matrix[t])
                 .replace(m.gap, combined.gap)
-                .replace(m.missing, combined.missing),
+                .replace(m.missing, combined.missing)
             )
         # replace date of missing taxa with symbol for missing data
         for t in combined_only:
@@ -425,7 +425,7 @@ def combine(matrices):
             combined.matrix[t] = Seq(combined.missing * combined.nchar) + Seq(
                 str(m.matrix[t])
                 .replace(m.gap, combined.gap)
-                .replace(m.missing, combined.missing),
+                .replace(m.missing, combined.missing)
             )
         combined.taxlabels.extend(m_only)  # new taxon list
         for cn, cs in m.charsets.items():  # adjust character sets for new matrix
@@ -1052,7 +1052,7 @@ def _matrix(self, options):
             # Reformat sequence for non-standard datatypes
             if self.datatype != "standard":
                 iupac_seq = Seq(
-                    _replace_parenthesized_ambigs(chars, self.rev_ambiguous_values),
+                    _replace_parenthesized_ambigs(chars, self.rev_ambiguous_values)
                 )
                 # first taxon has the reference sequence if matchhar is used
                 if taxcount == 1:

Bio/PDB/internal_coords.py

@@ -84,17 +84,7 @@
 from Bio.PDB.ic_data import ic_data_sidechain_extras, residue_atom_bond_state
 
 # for type checking only
-from typing import (
-    List,
-    Dict,
-    Set,
-    TextIO,
-    Union,
-    Tuple,
-    cast,
-    TYPE_CHECKING,
-    Optional,
-)
+from typing import List, Dict, Set, TextIO, Union, Tuple, cast, TYPE_CHECKING, Optional
 
 if TYPE_CHECKING:
     from Bio.PDB.Residue import Residue
@@ -606,7 +596,7 @@ def init_atom_coords(self) -> None:
         a4shift[udFwd] = self.hedraIC[self.dH2ndx, 0][mdFwd]  # len12
 
         self.a4_pre_rotation[:, 2][self.dAtoms_needs_update] = numpy.add(
-            self.a4_pre_rotation[:, 2][self.dAtoms_needs_update], a4shift,
+            self.a4_pre_rotation[:, 2][self.dAtoms_needs_update], a4shift
         )  # so a2 at origin
 
         # build rz rotation matrix for dihedral angle
@@ -1649,7 +1639,7 @@ def clear_transforms(self):
             d.rcst = None
 
     def assemble(
-        self, resetLocation: bool = False, verbose: bool = False,
+        self, resetLocation: bool = False, verbose: bool = False
     ) -> Union[Dict["AtomKey", numpy.array], Dict[HKT, numpy.array], None]:
         """Compute atom coordinates for this residue from internal coordinates.
 
@@ -2841,11 +2831,7 @@ def __init__(self, *args: Union[List["AtomKey"], HKT], **kwargs: str) -> None:
 
         if "len12" in kwargs:
             self.lal = numpy.array(
-                (
-                    float(kwargs["len12"]),
-                    float(kwargs["angle"]),
-                    float(kwargs["len23"]),
-                )
+                (float(kwargs["len12"]), float(kwargs["angle"]), float(kwargs["len23"]))
             )
         else:
             self.lal = numpy.zeros(3)

Bio/SeqIO/FastaIO.py

@@ -203,7 +203,7 @@ def iterate(self, handle):
                     # Should we use SeqRecord default for no ID?
                     first_word = ""
                 yield SeqRecord(
-                    Seq(sequence), id=first_word, name=first_word, description=title,
+                    Seq(sequence), id=first_word, name=first_word, description=title
                 )
 
 
@@ -239,7 +239,7 @@ def iterate(self, handle):
                 # Should we use SeqRecord default for no ID?
                 first_word = ""
             yield SeqRecord(
-                Seq(sequence), id=first_word, name=first_word, description=title,
+                Seq(sequence), id=first_word, name=first_word, description=title
             )
 
 

Bio/SeqIO/PirIO.py

@@ -171,7 +171,7 @@ def iterate(self, handle):
 
             # Return the record and then continue...
             record = SeqRecord(
-                Seq(seq[:-1]), id=identifier, name=identifier, description=description,
+                Seq(seq[:-1]), id=identifier, name=identifier, description=description
             )
             record.annotations["PIR-type"] = pir_type
             if _pir_mol_type[pir_type]:

Bio/SeqIO/SffIO.py

@@ -1044,7 +1044,7 @@ def iterate(self, handle):
                 # the index_offset so we can skip extra handle.tell() calls:
                 index_offset = 0
             yield _sff_read_seq_record(
-                handle, number_of_flows_per_read, flow_chars, key_sequence, trim,
+                handle, number_of_flows_per_read, flow_chars, key_sequence, trim
             )
         _check_eof(handle, index_offset, index_length)
 

Bio/SeqIO/_index.py

@@ -141,7 +141,7 @@ def get(self, offset):
         handle = self._handle
         handle.seek(offset)
         return SeqIO.SffIO._sff_read_seq_record(
-            handle, self._flows_per_read, self._flow_chars, self._key_sequence,
+            handle, self._flows_per_read, self._flow_chars, self._key_sequence
         )
 
     def get_raw(self, offset):

Bio/codonalign/__init__.py

@@ -246,7 +246,7 @@ def _get_aa_regex(codon_table, stop="*", unknown="X"):
 
 
 def _check_corr(
-    pro, nucl, gap_char, codon_table, complete_protein=False, anchor_len=10,
+    pro, nucl, gap_char, codon_table, complete_protein=False, anchor_len=10
 ):
     """Check if the nucleotide can be translated into the protein (PRIVATE).
 
@@ -571,7 +571,7 @@ def get_aa_from_codonre(re_aa):
 
 
 def _get_codon_rec(
-    pro, nucl, span_mode, gap_char, codon_table, complete_protein=False, max_score=10,
+    pro, nucl, span_mode, gap_char, codon_table, complete_protein=False, max_score=10
 ):
     """Generate codon alignment based on regular re match (PRIVATE).
 

Bio/codonalign/codonalignment.py

@@ -65,7 +65,7 @@ def __str__(self):
         rows = len(self._records)
         lines = [
             "CodonAlignment with %i rows and %i columns (%i codons)"
-            % (rows, self.get_alignment_length(), self.get_aln_length(),)
+            % (rows, self.get_alignment_length(), self.get_aln_length())
         ]
 
         if rows <= 60:

Bio/codonalign/codonseq.py

@@ -276,9 +276,7 @@ def _get_codon_list(codonseq):
     return codon_lst
 
 
-def cal_dn_ds(
-    codon_seq1, codon_seq2, method="NG86", codon_table=None, k=1, cfreq=None,
-):
+def cal_dn_ds(codon_seq1, codon_seq2, method="NG86", codon_table=None, k=1, cfreq=None):
     """Calculate dN and dS of the given two sequences.
 
     Available methods:

BioSQL/BioSeq.py

@@ -321,7 +321,7 @@ def _retrieve_annotations(adaptor, primary_id, taxon_id):
 
 def _retrieve_alphabet(adaptor, primary_id):
     results = adaptor.execute_and_fetchall(
-        "SELECT alphabet FROM biosequence WHERE bioentry_id = %s", (primary_id,),
+        "SELECT alphabet FROM biosequence WHERE bioentry_id = %s", (primary_id,)
     )
     assert len(results) == 1
     alphabets = results[0]

Scripts/PDB/hsexpo.py

@@ -43,7 +43,7 @@
     default="HSEb",
 )
 ap.add_argument(
-    "-o", "--out", dest="outfile", help="output to PDB file (B factor=exposure)",
+    "-o", "--out", dest="outfile", help="output to PDB file (B factor=exposure)"
 )
 ap.add_argument(
     "-r",

Tests/common_BioSQL.py

@@ -495,12 +495,7 @@ def test_convert(self):
     def test_addition(self):
         """Check can add Seq objects from BioSQL together."""
         test_seq = self.item.seq
-        for other in [
-            Seq("ACGT"),
-            MutableSeq("ACGT"),
-            "ACGT",
-            test_seq,
-        ]:
+        for other in [Seq("ACGT"), MutableSeq("ACGT"), "ACGT", test_seq]:
             test = test_seq + other
             self.assertEqual(test, str(test_seq) + str(other))
             self.assertIsInstance(test, Seq)

Tests/pairwise2_testCases.py

@@ -855,10 +855,7 @@ def test_clean_alignments(self):
             ("ACCGT", "AC-G-", 3.0, 0, 4),
             ("ACCGT", "A-CG-", 3.0, 0, 4),
         ]
-        expected = [
-            ("ACCGT", "AC-G-", 3.0, 0, 4),
-            ("ACCGT", "A-CG-", 3.0, 0, 4),
-        ]
+        expected = [("ACCGT", "AC-G-", 3.0, 0, 4), ("ACCGT", "A-CG-", 3.0, 0, 4)]
         result = pairwise2._clean_alignments(alns)
         self.assertEqual(expected, result)
 

Tests/test_AlignIO.py

@@ -451,7 +451,7 @@ def test_reading_alignments_nexus2(self):
         self.check_alignment_rows(
             alignment,
             [
-                ("Aegotheles", "AAAAAGGCATTGTGGTGGGAAT",),
+                ("Aegotheles", "AAAAAGGCATTGTGGTGGGAAT"),
                 ("Aerodramus", "?????????TTGTGGTGGGAAT"),
             ],
         )

Tests/test_Align_emboss.py

@@ -960,21 +960,17 @@ def test_local_water2(self):
             repr(alignment.sequences[0].seq),
             "Seq({78: 'CGTTTGAGTCTGGGATG'}, length=95)",
         )
-        self.assertEqual(
-            alignment.sequences[0].seq[78:95], "CGTTTGAGTCTGGGATG",
-        )
-        self.assertEqual(
-            alignment.sequences[1].seq[0:18], "CGTTTGAGTACTGGGATG",
-        )
+        self.assertEqual(alignment.sequences[0].seq[78:95], "CGTTTGAGTCTGGGATG")
+        self.assertEqual(alignment.sequences[1].seq[0:18], "CGTTTGAGTACTGGGATG")
         self.assertTrue(
             numpy.array_equal(
-                alignment.coordinates, numpy.array([[78, 87, 87, 95], [0, 9, 10, 18]]),
+                alignment.coordinates, numpy.array([[78, 87, 87, 95], [0, 9, 10, 18]])
             )
         )
         self.assertEqual(alignment[0], "CGTTTGAGT-CTGGGATG")
         self.assertEqual(alignment[1], "CGTTTGAGTACTGGGATG")
         self.assertEqual(
-            alignment.column_annotations["emboss_consensus"], "||||||||| ||||||||",
+            alignment.column_annotations["emboss_consensus"], "||||||||| ||||||||"
         )
 
 

Tests/test_BioSQL_sqlite3.py

@@ -16,11 +16,7 @@
 from common_BioSQL import *  # noqa: F403
 
 # Import these explicitly to avoid flake8 F405 below:
-from common_BioSQL import (
-    load_biosql_ini,
-    check_config,
-    temp_db_filename,
-)
+from common_BioSQL import load_biosql_ini, check_config, temp_db_filename
 
 # Constants for the database driver
 DBDRIVER = "sqlite3"

Tests/test_CAPS.py

@@ -20,7 +20,7 @@ def createAlignment(sequences):
         (
             SeqRecord(Seq(s), id="sequence%i" % (i + 1))
             for (i, s) in enumerate(sequences)
-        ),
+        )
     )
 
 

Tests/test_Emboss.py

@@ -305,7 +305,7 @@ def test_ig(self):
         # NOTE - EMBOSS considers "genbank" to be for nucleotides only,
         # and will turn "X" into "N" for GenBank output.
         self.check_SeqIO_to_EMBOSS(
-            "IntelliGenetics/VIF_mase-pro.txt", "ig", skip_formats=["genbank", "embl"],
+            "IntelliGenetics/VIF_mase-pro.txt", "ig", skip_formats=["genbank", "embl"]
         )
         # TODO - What does a % in an ig sequence mean?
         # e.g. "IntelliGenetics/vpu_nucaligned.txt"
@@ -457,13 +457,13 @@ def pairwise_alignment_check(self, query_seq, targets, alignments, local=True):
                 # Local alignment
                 self.assertIn(str(alignment[0].seq).replace("-", ""), query_seq)
                 self.assertIn(
-                    str(alignment[1].seq).replace("-", "").upper(), target.seq.upper(),
+                    str(alignment[1].seq).replace("-", "").upper(), target.seq.upper()
                 )
             else:
                 # Global alignment
                 self.assertEqual(query_seq, str(alignment[0].seq).replace("-", ""))
                 self.assertEqual(
-                    target.seq.upper(), str(alignment[1].seq).replace("-", "").upper(),
+                    target.seq.upper(), str(alignment[1].seq).replace("-", "").upper()
                 )
         return True
 

Tests/test_Entrez.py

@@ -144,7 +144,7 @@ def test_construct_cgi_ecitmatch(self):
         self.assertEqual(get_base_url(parsed), URL_HEAD + "ecitmatch.cgi")
         query.pop("bdata")  # TODO
         self.assertDictEqual(
-            query, {"retmode": ["xml"], "db": [variables["db"]], **QUERY_DEFAULTS},
+            query, {"retmode": ["xml"], "db": [variables["db"]], **QUERY_DEFAULTS}
         )
 
     def test_construct_cgi_einfo(self):
@@ -170,7 +170,7 @@ def test_construct_cgi_epost1(self):
 
         self.assertEqual(result_url, URL_HEAD + "epost.fcgi")  # Params in POST data
         self.assertDictEqual(
-            query, {"db": [variables["db"]], "id": [variables["id"]], **QUERY_DEFAULTS},
+            query, {"db": [variables["db"]], "id": [variables["id"]], **QUERY_DEFAULTS}
         )
 
     def test_construct_cgi_epost2(self):
@@ -185,9 +185,7 @@ def test_construct_cgi_epost2(self):
         self.assertEqual(result_url, URL_HEAD + "epost.fcgi")  # Params in POST data
         # Compare IDs up to reordering:
         self.assertCountEqual(query.pop("id"), variables["id"])
-        self.assertDictEqual(
-            query, {"db": [variables["db"]], **QUERY_DEFAULTS},
-        )
+        self.assertDictEqual(query, {"db": [variables["db"]], **QUERY_DEFAULTS})
 
     def test_construct_cgi_elink1(self):
         variables = {
@@ -320,10 +318,10 @@ def test_custom_directory(self):
 
         # Confirm that the two temp directories are named what we want.
         self.assertEqual(
-            handler.local_dtd_dir, os.path.join(tmpdir, "Bio", "Entrez", "DTDs"),
+            handler.local_dtd_dir, os.path.join(tmpdir, "Bio", "Entrez", "DTDs")
         )
         self.assertEqual(
-            handler.local_xsd_dir, os.path.join(tmpdir, "Bio", "Entrez", "XSDs"),
+            handler.local_xsd_dir, os.path.join(tmpdir, "Bio", "Entrez", "XSDs")
         )
 
         # And that they were created.

Tests/test_GenBank.py

@@ -7512,7 +7512,7 @@ def test_implicit_orign_wrap_extract_and_translate(self):
             "MPYKTQGCLGKGATPTPSSRGI*",
         )
         self.assertEqual(
-            seq_features[2].extract(seq_record).seq.translate(), "MPRLEGVGVAPFPRQPWVL*",
+            seq_features[2].extract(seq_record).seq.translate(), "MPRLEGVGVAPFPRQPWVL*"
         )
 
     def test_fuzzy_origin_wrap(self):

Tests/test_GenomeDiagram.py

@@ -303,7 +303,7 @@ def test_slicing(self):
 
         self.assertEqual(
             gd[4:16],
-            [(5, 15), (10, 20),],  # noqa 231
+            [(5, 15), (10, 20)],  # noqa 231
             "Unable to insert and retrieve points correctly",
         )
 

Tests/test_HMMGeneral.py

@@ -122,9 +122,7 @@ def test_set_equal_probabilities(self):
         self.mm_builder.allow_transition("2", "1", 0.95)
         self.mm_builder.set_equal_probabilities()
 
-        self.assertEqual(
-            self.mm_builder.initial_prob, {"1": 0.5, "2": 0.5},
-        )
+        self.assertEqual(self.mm_builder.initial_prob, {"1": 0.5, "2": 0.5})
         self.assertEqual(
             self.mm_builder.transition_prob, {("1", "2"): 0.5, ("2", "1"): 0.5}
         )