Repository navigation
Expand file tree
/
Copy pathCDSSequence.java
More file actions
106 lines (95 loc) · 3.19 KB
/
Copy pathCDSSequence.java
File metadata and controls
106 lines (95 loc) · 3.19 KB
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
/*
* BioJava development code
*
* This code may be freely distributed and modified under the
* terms of the GNU Lesser General Public Licence. This should
* be distributed with the code. If you do not have a copy,
* see:
*
* http://www.gnu.org/copyleft/lesser.html
*
* Copyright for this code is held jointly by the individual
* authors. These should be listed in @author doc comments.
*
* For more information on the BioJava project and its aims,
* or to join the biojava-l mailing list, visit the home page
* at:
*
* http://www.biojava.org/
*
* Created on DATE
*
*/
package org.biojava.nbio.core.sequence;
import org.biojava.nbio.core.sequence.compound.DNACompoundSet;
import org.biojava.nbio.core.sequence.compound.NucleotideCompound;
import org.biojava.nbio.core.sequence.template.CompoundSet;
/**
* Represents a exon or coding sequence in a gene. It has a parent {@link TranscriptSequence}
* where a TranscriptSequence is the child of a GeneSequence
* Not important for protein construction but the phase is used if outputting the gene
* to a gff3 file. {@link http://www.sequenceontology.org/gff3.shtml}
* @author Scooter Willis
*/
public class CDSSequence extends DNASequence {
//private static final Logger log = Logger.getLogger(CDSSequence.class.getName());
Integer phase = 0; // 0, 1, 2
TranscriptSequence parentTranscriptSequence;
/**
*
* @param parentSequence
* @param bioBegin
* @param bioEnd
* @param phase
*/
public CDSSequence(TranscriptSequence parentSequence, int bioBegin, int bioEnd, int phase) {
parentTranscriptSequence = parentSequence;
this.setParentSequence(parentTranscriptSequence);
setBioBegin(bioBegin);
setBioEnd(bioEnd);
this.phase = phase;
this.setCompoundSet(DNACompoundSet.getDNACompoundSet());
}
@Override
public int getLength() {
return Math.abs(this.getBioEnd() - this.getBioBegin()) + 1;
}
/**
*
* @return get the phase
*/
public Integer getPhase() {
return phase;
}
/**
*
* @return get the strand
*/
public Strand getStrand() {
return parentTranscriptSequence.getStrand();
}
/**
* A CDS sequence if negative stranded needs to be reverse complement
* to represent the actual coding sequence. When getting a ProteinSequence
* from a TranscriptSequence this method is callled for each CDSSequence
* {@link http://www.sequenceontology.org/gff3.shtml}
* {@link http://biowiki.org/~yam/bioe131/GFF.ppt}
* @return coding sequence
*/
public String getCodingSequence() {
String sequence = this.getSequenceAsString(getBioBegin(), getBioEnd(), getStrand());
if (getStrand() == Strand.NEGATIVE) {
//need to take complement of sequence because it is negative and we are returning a coding sequence
StringBuilder b = new StringBuilder(getLength());
CompoundSet<NucleotideCompound> compoundSet = this.getCompoundSet();
for (int i = 0; i < sequence.length(); i++) {
String nucleotide = String.valueOf(sequence.charAt(i));
NucleotideCompound nucleotideCompound = compoundSet.getCompoundForString(nucleotide);
b.append(nucleotideCompound.getComplement().getShortName());
}
sequence = b.toString();
}
// sequence = sequence.substring(phase);
return sequence;
}
}