2 // forester -- software libraries and applications
3 // for genomics and evolutionary biology research.
5 // Copyright (C) 2010 Christian M Zmasek
6 // Copyright (C) 2010 Sanford-Burnham Medical Research Institute
9 // This library is free software; you can redistribute it and/or
10 // modify it under the terms of the GNU Lesser General Public
11 // License as published by the Free Software Foundation; either
12 // version 2.1 of the License, or (at your option) any later version.
14 // This library is distributed in the hope that it will be useful,
15 // but WITHOUT ANY WARRANTY; without even the implied warranty of
16 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
17 // Lesser General Public License for more details.
19 // You should have received a copy of the GNU Lesser General Public
20 // License along with this library; if not, write to the Free Software
21 // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
23 // Contact: phylosoft @ gmail . com
24 // WWW: www.phylosoft.org/forester
26 package org.forester.msa;
28 import java.util.ArrayList;
29 import java.util.Iterator;
30 import java.util.List;
32 import java.util.SortedMap;
33 import java.util.TreeMap;
35 import org.forester.sequence.BasicSequence;
36 import org.forester.sequence.Sequence;
37 import org.forester.util.BasicDescriptiveStatistics;
38 import org.forester.util.DescriptiveStatistics;
40 public final class MsaMethods {
42 private ArrayList<String> _ignored_seqs_ids;
44 synchronized public ArrayList<String> getIgnoredSequenceIds() {
45 return _ignored_seqs_ids;
48 synchronized public static MsaMethods createInstance() {
49 return new MsaMethods();
52 private MsaMethods() {
56 synchronized private void init() {
57 _ignored_seqs_ids = new ArrayList<String>();
61 public Object clone() {
62 throw new NoSuchMethodError();
65 public static int calcGapSumPerColumn( final Msa msa, final int col ) {
67 for( int j = 0; j < msa.getNumberOfSequences(); ++j ) {
68 if ( msa.getResidueAt( j, col ) == Sequence.GAP ) {
75 synchronized public Msa removeGapColumns( final double max_allowed_gap_ratio,
76 final int min_allowed_length,
79 if ( ( max_allowed_gap_ratio < 0 ) || ( max_allowed_gap_ratio > 1 ) ) {
80 throw new IllegalArgumentException( "max allowed gap ration is out of range: " + max_allowed_gap_ratio );
82 final boolean ignore_too_short_seqs = min_allowed_length > 0;
83 final boolean[] delete_cols = new boolean[ msa.getLength() ];
85 for( int col = 0; col < msa.getLength(); ++col ) {
86 delete_cols[ col ] = ( ( double ) calcGapSumPerColumn( msa, col ) / msa.getNumberOfSequences() ) > max_allowed_gap_ratio;
87 if ( !delete_cols[ col ] ) {
91 final List<Sequence> seqs = new ArrayList<Sequence>( msa.getNumberOfSequences() );
92 for( int row = 0; row < msa.getNumberOfSequences(); ++row ) {
93 final char[] mol_seq = new char[ new_length ];
95 int non_gap_cols_sum = 0;
96 for( int col = 0; col < msa.getLength(); ++col ) {
97 if ( !delete_cols[ col ] ) {
98 final char residue = msa.getResidueAt( row, col );
99 mol_seq[ new_col++ ] = ( residue );
100 if ( residue != Sequence.GAP ) {
105 if ( ignore_too_short_seqs ) {
106 if ( non_gap_cols_sum >= min_allowed_length ) {
107 seqs.add( new BasicSequence( msa.getIdentifier( row ), mol_seq, msa.getType() ) );
110 _ignored_seqs_ids.add( msa.getIdentifier( row ).toString() );
114 seqs.add( new BasicSequence( msa.getIdentifier( row ), mol_seq, msa.getType() ) );
117 if ( seqs.size() < 1 ) {
120 return BasicMsa.createInstance( seqs );
123 public static double calculateIdentityRatio( final Msa msa, final int column ) {
124 final SortedMap<Character, Integer> dist = calculateResidueDestributionPerColumn( msa, column );
125 int majority_count = 0;
126 final Iterator<Map.Entry<Character, Integer>> it = dist.entrySet().iterator();
127 while ( it.hasNext() ) {
128 final Map.Entry<Character, Integer> pair = it.next();
129 if ( pair.getValue() > majority_count ) {
130 majority_count = pair.getValue();
133 return ( double ) majority_count / msa.getNumberOfSequences();
136 public static SortedMap<Character, Integer> calculateResidueDestributionPerColumn( final Msa msa, final int column ) {
137 final SortedMap<Character, Integer> map = new TreeMap<Character, Integer>();
138 for( final Character r : msa.getColumnAt( column ) ) {
139 if ( !map.containsKey( r ) ) {
143 map.put( r, map.get( r ) + 1 );
149 public static DescriptiveStatistics calcBasicGapinessStatistics( final Msa msa ) {
150 final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
151 for( int i = 0; i < msa.getLength(); ++i ) {
152 stats.addValue( ( double ) calcGapSumPerColumn( msa, i ) / msa.getNumberOfSequences() );