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
|
/////////////////////////////////////////////////////////////////////////////
// File: gnPosSpecificTranslator.cpp
// Purpose: Special case ORF translation
// Description: Used to translate sequences differently based on the position of
// input characters. Useful for tranlating genes because the first
// codon is translated differently
// Changes:
// Version: libGenome 0.5.1
// Author: Aaron Darling
// Modified by:
// Copyright: (c) Aaron Darling
// Licenses: See COPYING file for details
/////////////////////////////////////////////////////////////////////////////
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "libGenome/gnPosSpecificTranslator.h"
using namespace std;
namespace genome {
// static data access, avoids static initialization order fiasco
const gnPosSpecificTranslator *gnPosSpecificTranslator::ProteinDNATranslator(){
const static gnPosSpecificTranslator* t_trans = new gnPosSpecificTranslator(ProteinDNATranslatorType);
return t_trans;
}
const gnPosSpecificTranslator *gnPosSpecificTranslator::DNAProteinTranslator(){
const static gnPosSpecificTranslator* t_trans = new gnPosSpecificTranslator(DNAProteinTranslatorType);
return t_trans;
}
// public:
gnPosSpecificTranslator::gnPosSpecificTranslator()
{
}
gnPosSpecificTranslator::gnPosSpecificTranslator( const gnPosSpecificTranslator &sf )
{
m_name = sf.m_name;
}
gnPosSpecificTranslator::gnPosSpecificTranslator( gnTranslatorType t_type )
{
m_type = t_type;
switch(t_type){
case ProteinDNATranslatorType:
// not special done for this case
filter = gnFastTranslator::ProteinDNATranslator();
break;
case DNAProteinTranslatorType:
filter = gnFastTranslator::DNAProteinTranslator();
break;
}
}
// gnSeqC
gnSeqC gnPosSpecificTranslator::Filter( const gnSeqC ch ) const{
return filter->Filter(ch);
}
void gnPosSpecificTranslator::Filter( gnSeqC** seq, gnSeqI& len ) const{
return filter->Filter(seq, len);
}
// string
void gnPosSpecificTranslator::Filter( string &seq ) const{
switch(m_type){
case ProteinDNATranslatorType:
filter->Filter( seq );
break;
case DNAProteinTranslatorType:
string first_codon = seq.substr(0,3);
string original_sequence = seq;
filter->Filter( seq );
for(int charI = 0; charI < first_codon.length(); charI++ )
first_codon[charI] = tolower(first_codon[charI]);
if( first_codon == "ttg" || first_codon == "gtg" )
seq[0] = 'M';
// replace . with selenocysteine U where appropriate
string::size_type dot_pos = seq.find( "." );
while( dot_pos != string::npos ){
if( dot_pos == seq.size() - 1 )
break; // dont convert the final residue!
string dot_codon = original_sequence.substr( dot_pos * 3, 3 );
dot_codon[0] = tolower( dot_codon[0] );
dot_codon[1] = tolower( dot_codon[1] );
dot_codon[2] = tolower( dot_codon[2] );
if( dot_codon == "tga" )
seq[ dot_pos ] = 'U';
dot_pos = seq.find( ".", dot_pos + 1 );
}
break;
}
}
} // end namespace genome
|
