File: kabat_format.py

package info (click to toggle)
python-biopython 1.42-2
  • links: PTS
  • area: main
  • in suites: etch, etch-m68k
  • size: 17,584 kB
  • ctags: 12,272
  • sloc: python: 80,461; xml: 13,834; ansic: 7,902; cpp: 1,855; sql: 1,144; makefile: 203
file content (139 lines) | stat: -rw-r--r-- 5,473 bytes parent folder | download | duplicates (2)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
# Copyright 2001 by Katharine Lindner.  All rights reserved.
# This code is part of the Biopython distribution and governed by its
# license.  Please see the LICENSE file that should have been included
# as part of this package.

"""Martel based parser to read Kabat formatted files.

This is a huge regular regular expression for Kabat, built using
the 'regular expressiona on steroids' capabilities of Martel.

http://immuno.bme.nwu.edu/

Notes:
Just so I remember -- the new end of line syntax is:
  New regexp syntax - \R
     \R    means "\n|\r\n?"
     [\R]  means "[\n\r]"

This helps us have endlines be consistent across platforms.

"""
# standard library
#http://immuno.bme.nwu.edu/seqhunt.html
import string

# Martel
import Martel
from Martel import RecordReader

# - useful constants for dealing with the blank space in GenBank documents
# this is useful since blank space can be significant in GenBank flat files.
INDENT = 12
FEATURE_KEY_INDENT = 5
FEATURE_QUALIFIER_INDENT = 21

# --- first set up some helper constants and functions
blank_space = Martel.MaxRepeat(Martel.Str(" "), 1, 80 )
lower_alpha = Martel.Any( "abcdefghijklmnopqrstuvwxyz" )
alpha = Martel.NoCase( lower_alpha )
date = Martel.Group("date",
                    Martel.Re("[-\w]+"))
amino_3_letter_codes = [ 'ALA', 'CYS', 'ASP', 'GLU', 'PHE', 'GLY', 'PHE', 'GLY',\
                'HIS', 'ILE', 'LYS', 'LEU', 'MET', 'ASN', 'PRO', 'GLN', \
                'ARG', 'SER','THR', 'VAL', 'TRP', 'TYR', '---' ]
# from http://www.lmb.uni-muenchen.de/groups/bioinformatics/02/ch_02.html

amino_1_letter_codes = 'ACDEFGHIKLMNPQRSTVWY-'

nucleotides = 'gcat-'

amino_alts = map( Martel.Str, amino_3_letter_codes )

codon = Martel.Group( "codon", Martel.MaxRepeat( Martel.Any( nucleotides ), 1, 3 ) )
amino_3_letter_code = reduce( Martel.Alt, amino_alts )
amino_1_letter_code = Martel.Group( "amino_1_letter_code", \
    Martel.Any( amino_1_letter_codes ) )
amino_codes = Martel.Opt( amino_3_letter_code + blank_space + amino_1_letter_code )

residue =   blank_space + codon + blank_space + amino_codes


kabatid = Martel.Group("kabatid",
                    Martel.Rep1(Martel.Integer()))
pubmed_num = Martel.Rep1(Martel.Integer())
residue_num = Martel.Rep1(Martel.Integer())
kabat_num = Martel.Rep1(Martel.Integer()) + Martel.Opt( alpha )
id_line = Martel.Str("KADBID") + \
          blank_space + \
          kabatid + \
          Martel.ToEol()
creation_date_line =  Martel.Str( "CREATD" ) + \
                      blank_space + \
                      Martel.ToEol("creation_date")
last_mod_date_line =  Martel.Str( "LMODIF" ) + \
                      blank_space + \
                      Martel.ToEol("last_mod_date")
definition_line = Martel.Str( "DEFINI" ) + \
                  blank_space + \
                  Martel.ToEol( "definition" )
species_line = Martel.Str( "SPECIE" ) + \
               blank_space + \
               Martel.ToEol( "species" )
amino_acid_sequence_name_line = Martel.Str( "AANAME" ) + \
                                blank_space + \
                                Martel.ToEol( "amino_acid_sequence_name" )

nucleotide_sequence_name_line = Martel.Str( "NNNAME" ) + \
                                blank_space + \
                                Martel.ToEol( "nucleotide_sequence_name" )
amino_acid_ref_author_line = Martel.Str( "AAREFA" ) + \
                             Martel.ToEol( "amino_acid_ref_author" )
amino_acid_ref_journal_line = Martel.Str( "AAREFJ" ) + \
                              Martel.ToEol( "amino_acid_ref_journal" )
amino_acid_ref_pubmed_line = Martel.Str( "AAPUBM" ) +  \
                             Martel.ToEol( "amino_acid_ref_pubmed" )
nucleotide_ref_author_line = Martel.Str( "NNREFA" ) +  \
                             Martel.ToEol( "nucleotide_ref_author" )
nucleotide_ref_journal_line = Martel.Str( "NNREFJ" ) + \
                              Martel.ToEol( "nucleotide_ref_journal" )
nucleotide_ref_pubmed_line = Martel.Str( "NNPUBM" ) +  \
                             Martel.ToEol("nucleotide_ref_pubmed")
annotation_key = Martel.Group( "annotation_key", Martel.RepN( Martel.Re( "\w" ), 4 ) )
annotation_val = Martel.Group( "annotation_val", Martel.ToEol() )
annotation_item = annotation_key + \
                  blank_space + \
                  annotation_val

annotation_line = Martel.Str( "ANNOTA" ) + \
                  blank_space + annotation_item
residue_line = Martel.Str( "SEQTPA" ) + \
               blank_space + \
               residue_num + \
               blank_space + \
               kabat_num + \
               Martel.Opt( residue ) + \
               Martel.ToEol( )
kabat_record_end_line = Martel.Str( "RECEND" ) + \
                        Martel.ToEol()
amino_acid_ref = amino_acid_ref_author_line + \
                 amino_acid_ref_journal_line + \
                 amino_acid_ref_pubmed_line
nucleotide_ref = nucleotide_ref_author_line + \
                 nucleotide_ref_journal_line + \
                 nucleotide_ref_pubmed_line
residue_lines = Martel.Rep( residue_line )
annotation = Martel.Group( "annotation", Martel.Rep( annotation_line ) )
refs = Martel.Rep1( amino_acid_ref | nucleotide_ref )
kabat_record = id_line + creation_date_line + last_mod_date_line + \
               definition_line + species_line + amino_acid_sequence_name_line + \
               nucleotide_sequence_name_line + refs + annotation +  \
               residue_lines + kabat_record_end_line