File: locus_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 (128 lines) | stat: -rw-r--r-- 3,110 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



"""Martel based parser to read LocusLink flat files.

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

A description of the format can be found in the 'ligand.doc' file
from the Ligand distribution, available from:

 http://www.ncbi.nih.gov/LocusLink


"""

# Martel
from Martel import Str
from Martel import Str1
from Martel import Alt
from Martel import Rep
from Martel import Group
from Martel import ToEol
from Martel import AnyEol
from Martel import Any
from Martel import Word
from Martel import Opt
from Martel import AssertNot

from Martel import RecordReader

# --- First set up some helper constants and functions
INDENT = 12

blank_spaces = Rep(Str1(" "))
point = Str1(".")

white_space = Rep( Any( " 	" ) )
locus_keys = [ \
        'LOCUSID', \
        'LOCUS_CONFIRMED', \
        'LOCUS_TYPE', \
        'ORGANISM', \
        'STATUS', \
        'NM', \
        'NP', \
        'CDD', \
        'PRODUCT', \
        'ASSEMBLY', \
        'CONTIG', \
        'EVID', \
        'XM', \
        'XP', \
        'ACCNUM', \
        'TYPE', \
        'PROT', \
        'OFFICIAL_SYMBOL', \
        'OFFICIAL_GENE_NAME', \
        'PREFERRED_PRODUCT', \
        'ALIAS_SYMBOL', \
        'SUMMARY', \
        'CHR', \
        'STS', \
        'COMP', \
        'ALIAS_PROT', \
        'UNIGENE', \
        'BUTTON', \
        'LINK', \
        'OMIM', \
        'MAP', \
        'MAPLINK', \
        'ECNUM', \
        'PROTOTYPE', \
        'DB_DESCR', \
        'DB_LINK', \
        'PMID', \
        'GRIF', \
        'SUBFUNC', \
        'GO', \
        'EXTANNOT'
        
        ]

accnum_block_keys = [ \
    'ACCNUM', \
    'TYPE', \
    'PROT' \
    ]
phenotype = Str1( 'PHENOTYPE' )
db = Str1( 'DB' )
accnum_block_key = Str( *accnum_block_keys )



valid_locus_key = Str( *locus_keys )
def define_locus_line( entry_tag ):
    
    return(   white_space + \
             Str1(entry_tag ) + \
             white_space + \
	     Str1( ":" ) + \
	     white_space + \
	     ToEol() )

def define_locus_group( entry_name, entry_tag ):   
    return Group( entry_name, \
                  define_locus_line( entry_tag ))

accnum_block = Group( 'accnum_block', \
                      define_locus_line( 'ACCNUM' ) + \
                      define_locus_line( 'TYPE' ) + \
                      Opt(define_locus_line( 'PROT' ) ) ) 

phenotype_block = Group( 'phenotype_block', \
                      define_locus_line( 'PHENOTYPE' ) + \
                      Opt( define_locus_line( 'PHENOTYPE_ID' ) ) )

db_block = Group( 'db_block', \
                      define_locus_line( 'DB_DESCR' ) + \
                      define_locus_line( 'DB_LINK' ) )

begin_record_line = Str1( '>>' ) + ToEol()
locus_line = Group( 'locus_line', \
                 white_space + AssertNot( accnum_block_key ) + AssertNot( phenotype ) + AssertNot( db ) + Word() + white_space + Str1( ':' ) + ToEol() )

locus_record = begin_record_line + Rep( Alt( locus_line, accnum_block, phenotype_block, db_block ) )
#locus_record = Rep( locus_line )