Mercurial > repos > cpt > cpt_gbk_to_5col

comparison BIO_FIX_TOPO.py @ 1:1bdd481d5c25 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
author cpt
date Mon, 05 Jun 2023 02:42:57 +0000
parents
children
comparison
equal deleted inserted replaced
0:66143811fe8a 1:1bdd481d5c25
1 import Bio.GenBank
2
3
4 def record_end(self, content):
5 """Clean up when we've finished the record."""
6 # from Bio import Alphabet
7 # from Bio.Alphabet import IUPAC
8 from Bio.Seq import Seq, UnknownSeq
9
10 # Try and append the version number to the accession for the full id
11 if not self.data.id:
12 assert "accessions" not in self.data.annotations, self.data.annotations[
13 "accessions"
14 ]
15 self.data.id = self.data.name # Good fall back?
16 elif self.data.id.count(".") == 0:
17 try:
18 self.data.id += ".%i" % self.data.annotations["sequence_version"]
19 except KeyError:
20 pass
21
22 # add the sequence information
23 # first, determine the alphabet
24 # we default to an generic alphabet if we don't have a
25 # seq type or have strange sequence information.
26
27 # seq_alphabet = Alphabet.generic_alphabet
28
29 # now set the sequence
30 sequence = "".join(self._seq_data)
31
32 if (
33 self._expected_size is not None
34 and len(sequence) != 0
35 and self._expected_size != len(sequence)
36 ):
37 import warnings
38 from Bio import BiopythonParserWarning
39
40 warnings.warn(
41 "Expected sequence length %i, found %i (%s)."
42 % (self._expected_size, len(sequence), self.data.id),
43 BiopythonParserWarning,
44 )
45 """
46 if self._seq_type:
47 # mRNA is really also DNA, since it is actually cDNA
48 if "DNA" in self._seq_type.upper() or "MRNA" in self._seq_type.upper():
49 seq_alphabet = IUPAC.ambiguous_dna
50 # are there ever really RNA sequences in GenBank?
51 elif "RNA" in self._seq_type.upper():
52 # Even for data which was from RNA, the sequence string
53 # is usually given as DNA (T not U). Bug 2408
54 if "T" in sequence and "U" not in sequence:
55 seq_alphabet = IUPAC.ambiguous_dna
56 else:
57 seq_alphabet = IUPAC.ambiguous_rna
58 elif (
59 "PROTEIN" in self._seq_type.upper() or self._seq_type == "PRT"
60 ): # PRT is used in EMBL-bank for patents
61 seq_alphabet = IUPAC.protein # or extended protein?
62 # work around ugly GenBank records which have circular or
63 # linear but no indication of sequence type
64 elif self._seq_type in ["circular", "linear", "unspecified"]:
65 pass
66 # we have a bug if we get here
67 else:
68 raise ValueError(
69 "Could not determine alphabet for seq_type %s" % self._seq_type
70 )
71
72 # Also save the chomosome layout
73 if "circular" in self._seq_type.lower():
74 self.data.annotations["topology"] = "circular"
75 elif "linear" in self._seq_type.lower():
76 self.data.annotations["topology"] = "linear"
77 """
78 if not sequence and self.__expected_size:
79 self.data.seq = UnknownSeq(self._expected_size) # , seq_alphabet)
80 else:
81 self.data.seq = Seq(sequence) # , seq_alphabet)
82
83
84 Bio.GenBank._FeatureConsumer.record_end = record_end