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
140
141
142
143
144
145
146
|
/*
* 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/
*
*/
package demo;
import java.io.ByteArrayInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.UnsupportedEncodingException;
import org.biojava.nbio.core.sequence.ProteinSequence;
import org.biojava.nbio.core.sequence.compound.AminoAcidCompound;
import org.biojava.nbio.core.sequence.compound.AminoAcidCompoundSet;
import org.biojava.nbio.core.sequence.io.CasePreservingProteinSequenceCreator;
import org.biojava.nbio.core.sequence.io.GenericFastaHeaderParser;
import org.biojava.nbio.core.sequence.io.template.SequenceCreatorInterface;
import org.biojava.nbio.core.sequence.io.template.SequenceHeaderParserInterface;
import org.biojava.nbio.structure.Atom;
import org.biojava.nbio.structure.ResidueNumber;
import org.biojava.nbio.structure.Structure;
import org.biojava.nbio.structure.StructureException;
import org.biojava.nbio.structure.StructureTools;
import org.biojava.nbio.structure.align.gui.StructureAlignmentDisplay;
import org.biojava.nbio.structure.align.model.AFPChain;
import org.biojava.nbio.structure.align.util.AlignmentTools;
import org.biojava.nbio.structure.align.util.AtomCache;
import org.biojava.nbio.structure.io.FastaStructureParser;
import org.biojava.nbio.structure.io.StructureSequenceMatcher;
import org.biojava.nbio.structure.StructureException;
import org.biojava.nbio.structure.Structure;
import org.biojava.nbio.structure.StructureTools;
import org.biojava.nbio.structure.Atom;
import org.biojava.nbio.structure.ResidueNumber;
/**
* Demo of how to use the {@link FastaStructureParser} class to read protein
* structures from a FASTA file.
*
* @author Spencer Bliven
*
*/
public class DemoAlignmentFromFasta {
public static void getAlignmentFromFasta() throws StructureException {
// Load a test sequence
// Normally this would come from a file, eg
// File fasta = new File("/path/to/file.fa");
String fastaStr =
"> 1KQ1.A\n" +
"mianeniqdkalenfkanqtevtvfflngFQ.MKGVIEEYDK.....YVVSLNsqgkQHLIYKh......\n" +
".......................AISTYTVetegqastesee\n" +
"> 1C4Q.D\n" +
"............................tPDcVTGKVEYTKYndddtFTVKVG....DKELATnranlqs\n" +
"lllsaqitgmtvtiktnachnggGFSEVIFr...........\n";
InputStream fasta;
try {
fasta = new ByteArrayInputStream(fastaStr.getBytes("UTF-8"));
} catch (UnsupportedEncodingException e) {
e.printStackTrace();
return;
}
// Create a header parser to parse the header lines into valid structure accessions.
// The resulting accession can be anything interpretable by AtomCache.getStructure.
// Possible Examples: "4HHB" (whole structure), "d4hhba_" (SCOP domain),
// "4HHB.A:1-15" (residue range)
// For this example, the built-in fasta parser will extract the correct accession.
SequenceHeaderParserInterface<ProteinSequence, AminoAcidCompound> headerParser;
headerParser = new GenericFastaHeaderParser<ProteinSequence, AminoAcidCompound>();
// Create AtomCache to fetch structures from the PDB
AtomCache cache = new AtomCache();
// Create SequenceCreator. This converts a String to a ProteinSequence
AminoAcidCompoundSet aaSet = AminoAcidCompoundSet.getAminoAcidCompoundSet();
SequenceCreatorInterface<AminoAcidCompound> creator;
creator = new CasePreservingProteinSequenceCreator(aaSet);
// parse file
FastaStructureParser parser = new FastaStructureParser(
fasta, headerParser, creator, cache);
try {
parser.process();
} catch (IOException e) {
e.printStackTrace();
return;
} catch (StructureException e) {
e.printStackTrace();
return;
}
ResidueNumber[][] residues = parser.getResidues();
ProteinSequence[] sequences = parser.getSequences();
Structure[] structures = parser.getStructures();
// Set lowercase residues to null too
for(int structNum = 0; structNum<sequences.length;structNum++) {
CasePreservingProteinSequenceCreator.setLowercaseToNull(
sequences[structNum],residues[structNum]);
}
// Remove alignment columns with a gap
residues = StructureSequenceMatcher.removeGaps(residues);
// Create AFPChain from the alignment
Atom[] ca1 = StructureTools.getAtomCAArray(structures[0]);
Atom[] ca2 = StructureTools.getAtomCAArray(structures[1]);
AFPChain afp = AlignmentTools.createAFPChain(ca1, ca2, residues[0], residues[1]);
try {
StructureAlignmentDisplay.display(afp, ca1, ca2);
} catch (StructureException e) {
e.printStackTrace();
return;
}
}
public static void main(String[] args) throws StructureException {
getAlignmentFromFasta();
}
}
|
