PageRenderTime 22ms CodeModel.GetById 10ms app.highlight 9ms RepoModel.GetById 1ms app.codeStats 0ms

/lib/galaxy_utils/sequence/transform.py

https://bitbucket.org/cistrome/cistrome-harvard/
Python | 73 lines | 62 code | 3 blank | 8 comment | 12 complexity | 6dadf556302e3f7a9a49da564e2adada MD5 | raw file
 1#Dan Blankenberg
 2#Contains methods to tranform sequence strings
 3import string
 4
 5#Translation table for reverse Complement, with ambiguity codes
 6DNA_COMPLEMENT = string.maketrans( "ACGTRYKMBDHVacgtrykmbdhv", "TGCAYRMKVHDBtgcayrmkvhdb" )
 7RNA_COMPLEMENT = string.maketrans( "ACGURYKMBDHVacgurykmbdhv", "UGCAYRMKVHDBugcayrmkvhdb" )
 8#Translation table for DNA <--> RNA
 9DNA_TO_RNA = string.maketrans( "Tt", "Uu" )
10RNA_TO_DNA = string.maketrans( "Uu", "Tt" )
11
12#reverse sequence string
13def reverse( sequence ):
14    return sequence[::-1]
15#complement DNA sequence string
16def DNA_complement( sequence ):
17    return sequence.translate( DNA_COMPLEMENT )
18#complement RNA sequence string
19def RNA_complement( sequence ):
20    return sequence.translate( RNA_COMPLEMENT )
21#returns the reverse complement of the sequence
22def DNA_reverse_complement( sequence ):
23    sequence = reverse( sequence )
24    return DNA_complement( sequence )
25def RNA_reverse_complement( sequence ):
26    sequence = reverse( sequence )
27    return RNA_complement( sequence )
28def to_DNA( sequence ):
29    return sequence.translate( DNA_TO_RNA )
30def to_RNA( sequence ):
31    return sequence.translate( RNA_TO_DNA )
32
33class ColorSpaceConverter( object ):
34    unknown_base = 'N'
35    unknown_color = '.'
36    color_to_base_dict = {}
37    color_to_base_dict[ 'A' ] = { '0':'A', '1':'C', '2':'G', '3':'T', '4':'N', '5':'N', '6':'N', '.':'N' }
38    color_to_base_dict[ 'C' ] = { '0':'C', '1':'A', '2':'T', '3':'G', '4':'N', '5':'N', '6':'N', '.':'N' }
39    color_to_base_dict[ 'G' ] = { '0':'G', '1':'T', '2':'A', '3':'C', '4':'N', '5':'N', '6':'N', '.':'N' }
40    color_to_base_dict[ 'T' ] = { '0':'T', '1':'G', '2':'C', '3':'A', '4':'N', '5':'N', '6':'N', '.':'N' }
41    color_to_base_dict[ 'N' ] = { '0':'N', '1':'N', '2':'N', '3':'N', '4':'N', '5':'N', '6':'N', '.':'N' }
42    base_to_color_dict = {}
43    for base, color_dict in color_to_base_dict.iteritems():
44        base_to_color_dict[ base ] = {}
45        for key, value in color_dict.iteritems():
46            base_to_color_dict[ base ][ value ] = key
47        base_to_color_dict[ base ][ 'N' ] = '4' #force ACGT followed by N to be '4', because this is now 'processed' data; we could force to '.' (non-processed data) also
48    base_to_color_dict[ 'N' ].update( { 'A':'5', 'C':'5', 'G':'5', 'T':'5', 'N':'6' } )
49    def __init__( self, fake_adapter_base = 'G' ):
50        assert fake_adapter_base in self.base_to_color_dict, 'A bad fake adapter base was provided: %s.' % fake_adapter_base
51        self.fake_adapter_base = fake_adapter_base
52    def to_color_space( self, sequence, adapter_base = None ):
53        if adapter_base is None:
54            adapter_base = self.fake_adapter_base
55        last_base = adapter_base #we add a fake adapter base so that the sequence can be decoded properly again
56        rval = last_base
57        for base in sequence:
58            rval += self.base_to_color_dict.get( last_base, self.base_to_color_dict[ self.unknown_base ] ).get( base, self.unknown_color )
59            last_base = base
60        return rval
61    def to_base_space( self, sequence ):
62        if not isinstance( sequence, list ):
63            sequence = list( sequence )
64        if sequence:
65            last_base = sequence.pop( 0 )
66        else:
67            last_base = None
68        assert last_base in self.color_to_base_dict, 'A valid adapter base must be included when converting to base space from color space. Found: %s' % last_base
69        rval = ''
70        for color_val in sequence:
71            last_base = self.color_to_base_dict[ last_base ].get( color_val, self.unknown_base )
72            rval += last_base
73        return rval