3 // forester -- software libraries and applications
4 // for genomics and evolutionary biology research.
6 // Copyright (C) 2010 Christian M Zmasek
7 // Copyright (C) 2010 Sanford-Burnham Medical Research Institute
10 // This library is free software; you can redistribute it and/or
11 // modify it under the terms of the GNU Lesser General Public
12 // License as published by the Free Software Foundation; either
13 // version 2.1 of the License, or (at your option) any later version.
15 // This library is distributed in the hope that it will be useful,
16 // but WITHOUT ANY WARRANTY; without even the implied warranty of
17 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
18 // Lesser General Public License for more details.
20 // You should have received a copy of the GNU Lesser General Public
21 // License along with this library; if not, write to the Free Software
22 // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
24 // Contact: phylosoft @ gmail . com
25 // WWW: www.phylosoft.org/forester
27 package org.forester.io.parsers;
29 import java.io.BufferedReader;
30 import java.io.ByteArrayInputStream;
31 import java.io.IOException;
32 import java.io.InputStream;
33 import java.io.InputStreamReader;
34 import java.util.ArrayList;
35 import java.util.List;
36 import java.util.regex.Matcher;
37 import java.util.regex.Pattern;
39 import org.forester.msa.BasicMsa;
40 import org.forester.msa.Msa;
41 import org.forester.msa.MsaFormatException;
42 import org.forester.phylogeny.Phylogeny;
43 import org.forester.phylogeny.PhylogenyNode;
44 import org.forester.phylogeny.data.Accession;
45 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
46 import org.forester.sequence.BasicSequence;
47 import org.forester.sequence.Sequence;
48 import org.forester.util.ForesterUtil;
50 public class FastaParser {
52 private static final Pattern NAME_REGEX = Pattern.compile( "^\\s*>\\s*(.+)" );
53 private static final Pattern SEQ_REGEX = Pattern.compile( "^\\s*(.+)" );
54 private static final Pattern ANYTHING_REGEX = Pattern.compile( "[\\d\\s]+" );
55 //>gi|71834668|ref|NP_001025424.1| Bcl2 [Danio rerio]
56 private static final Pattern FASTA_DESC_LINE = Pattern
57 .compile( ">?\\s*([^|]+)\\|([^|]+)\\S*\\s+(.+)\\s+\\[(.+)\\]" );
59 public static void main( final String[] args ) {
60 final String a = ">gi|71834668|ref|NP_001025424.1| Bcl2 [Danio rerio]";
61 final Matcher name_m = FASTA_DESC_LINE.matcher( a );
62 if ( name_m.lookingAt() ) {
64 System.out.println( name_m.group( 1 ) );
65 System.out.println( name_m.group( 2 ) );
66 System.out.println( name_m.group( 3 ) );
67 System.out.println( name_m.group( 4 ) );
70 System.out.println( "Does not match." );
74 static public boolean isLikelyFasta( final InputStream is ) throws IOException {
75 final BufferedReader reader = new BufferedReader( new InputStreamReader( is, "UTF-8" ) );
77 while ( ( line = reader.readLine() ) != null ) {
78 final boolean is_name_line = NAME_REGEX.matcher( line ).lookingAt();
79 if ( canIgnore( line, true, false ) ) {
82 else if ( is_name_line ) {
86 else if ( SEQ_REGEX.matcher( line ).lookingAt() ) {
95 static public Msa parseMsa( final InputStream is ) throws IOException {
96 return BasicMsa.createInstance( parse( is ) );
99 static public Msa parseMsa( final String s ) throws IOException {
100 return parseMsa( s.getBytes() );
103 static public Msa parseMsa( final byte[] bytes ) throws IOException {
104 return parseMsa( new ByteArrayInputStream( bytes ) );
107 static public List<Sequence> parse( final InputStream is ) throws IOException {
108 final BufferedReader reader = new BufferedReader( new InputStreamReader( is, "UTF-8" ) );
110 int line_counter = 0;
111 boolean saw_first_seq = false;
112 StringBuilder current_seq = null;
113 StringBuilder name = null;
114 final List<StringBuilder[]> temp_msa = new ArrayList<StringBuilder[]>();
115 while ( ( line = reader.readLine() ) != null ) {
117 final Matcher name_m = NAME_REGEX.matcher( line );
118 final boolean is_name_line = name_m.lookingAt();
119 if ( canIgnore( line, saw_first_seq, is_name_line ) ) {
122 final Matcher seq_m = SEQ_REGEX.matcher( line );
123 if ( is_name_line ) {
124 saw_first_seq = true;
125 addSeq( name, current_seq, temp_msa );
126 name = new StringBuilder( name_m.group( 1 ).trim() );
127 current_seq = new StringBuilder();
129 else if ( seq_m.lookingAt() ) {
130 if ( name.length() < 1 ) {
132 throw new MsaFormatException( "illegally formatted fasta msa (line: " + line_counter + "):\n\""
133 + trim( line ) + "\"" );
135 current_seq.append( seq_m.group( 1 ).replaceAll( "\\s+", "" ) );
139 throw new MsaFormatException( "illegally formatted fasta msa (line: " + line_counter + "):\n\""
140 + trim( line ) + "\"" );
143 addSeq( name, current_seq, temp_msa );
145 final List<Sequence> seqs = new ArrayList<Sequence>();
146 for( int i = 0; i < temp_msa.size(); ++i ) {
147 seqs.add( BasicSequence.createAaSequence( temp_msa.get( i )[ 0 ].toString(),
148 temp_msa.get( i )[ 1 ].toString() ) );
153 static private boolean canIgnore( final String line, final boolean saw_first_seq, final boolean is_name_line ) {
154 if ( ( line.length() < 1 ) || ANYTHING_REGEX.matcher( line ).matches() ) {
157 if ( !saw_first_seq && !is_name_line ) {
163 private static void addSeq( final StringBuilder name, final StringBuilder seq, final List<StringBuilder[]> temp_msa ) {
164 if ( ( name != null ) && ( seq != null ) && ( name.length() > 0 ) && ( seq.length() > 0 ) ) {
165 final StringBuilder[] ary = new StringBuilder[ 2 ];
172 private static String trim( final String line ) {
173 if ( line.length() > 100 ) {
174 return line.substring( 0, 100 ) + " ...";
179 public static void extractFastaInformation( final Phylogeny phy ) {
180 for( final PhylogenyNodeIterator iter = phy.iteratorExternalForward(); iter.hasNext(); ) {
181 final PhylogenyNode node = iter.next();
182 if ( !ForesterUtil.isEmpty( node.getName() ) ) {
183 final Matcher name_m = FASTA_DESC_LINE.matcher( node.getName() );
184 if ( name_m.lookingAt() ) {
185 System.out.println();
186 // System.out.println( name_m.group( 1 ) );
187 // System.out.println( name_m.group( 2 ) );
188 // System.out.println( name_m.group( 3 ) );
189 // System.out.println( name_m.group( 4 ) );
190 final String acc_source = name_m.group( 1 );
191 final String acc = name_m.group( 2 );
192 final String seq_name = name_m.group( 3 );
193 final String tax_sn = name_m.group( 4 );
194 if ( !ForesterUtil.isEmpty( acc_source ) && !ForesterUtil.isEmpty( acc ) ) {
195 ForesterUtil.ensurePresenceOfSequence( node );
196 node.getNodeData().getSequence( 0 ).setAccession( new Accession( acc, acc_source ) );
198 if ( !ForesterUtil.isEmpty( seq_name ) ) {
199 ForesterUtil.ensurePresenceOfSequence( node );
200 node.getNodeData().getSequence( 0 ).setName( seq_name );
202 if ( !ForesterUtil.isEmpty( tax_sn ) ) {
203 ForesterUtil.ensurePresenceOfTaxonomy( node );
204 node.getNodeData().getTaxonomy( 0 ).setScientificName( tax_sn );