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.List;
30 import java.util.SortedMap;
31 import java.util.TreeMap;
33 import org.forester.sequence.BasicSequence;
34 import org.forester.sequence.Sequence;
35 import org.forester.util.BasicDescriptiveStatistics;
36 import org.forester.util.DescriptiveStatistics;
38 public final class MsaMethods {
40 private ArrayList<String> _ignored_seqs_ids;
42 synchronized public ArrayList<String> getIgnoredSequenceIds() {
43 return _ignored_seqs_ids;
46 synchronized public static MsaMethods createInstance() {
47 return new MsaMethods();
50 private MsaMethods() {
54 synchronized private void init() {
55 _ignored_seqs_ids = new ArrayList<String>();
59 public Object clone() {
60 throw new NoSuchMethodError();
63 public static int calcGapSumPerColumn( final Msa msa, final int col ) {
65 for( int j = 0; j < msa.getNumberOfSequences(); ++j ) {
66 if ( msa.getResidueAt( j, col ) == Sequence.GAP ) {
73 synchronized public Msa removeGapColumns( final double max_allowed_gap_ratio,
74 final int min_allowed_length,
77 if ( ( max_allowed_gap_ratio < 0 ) || ( max_allowed_gap_ratio > 1 ) ) {
78 throw new IllegalArgumentException( "max allowed gap ration is out of range: " + max_allowed_gap_ratio );
80 final boolean ignore_too_short_seqs = min_allowed_length > 0;
81 final boolean[] delete_cols = new boolean[ msa.getLength() ];
83 for( int col = 0; col < msa.getLength(); ++col ) {
84 delete_cols[ col ] = ( ( double ) calcGapSumPerColumn( msa, col ) / msa.getNumberOfSequences() ) > max_allowed_gap_ratio;
85 if ( !delete_cols[ col ] ) {
89 final List<Sequence> seqs = new ArrayList<Sequence>( msa.getNumberOfSequences() );
90 for( int row = 0; row < msa.getNumberOfSequences(); ++row ) {
91 final char[] mol_seq = new char[ new_length ];
93 int non_gap_cols_sum = 0;
94 for( int col = 0; col < msa.getLength(); ++col ) {
95 if ( !delete_cols[ col ] ) {
96 final char residue = msa.getResidueAt( row, col );
97 mol_seq[ new_col++ ] = ( residue );
98 if ( residue != Sequence.GAP ) {
103 if ( ignore_too_short_seqs ) {
104 if ( non_gap_cols_sum >= min_allowed_length ) {
105 seqs.add( new BasicSequence( msa.getIdentifier( row ), mol_seq, msa.getType() ) );
108 _ignored_seqs_ids.add( msa.getIdentifier( row ).toString() );
112 seqs.add( new BasicSequence( msa.getIdentifier( row ), mol_seq, msa.getType() ) );
115 if ( seqs.size() < 1 ) {
118 return BasicMsa.createInstance( seqs );
121 public static SortedMap<Character, Integer> calculateResidueDestributionPerColumn( final Msa msa, final int c ) {
122 final SortedMap<Character, Integer> map = new TreeMap<Character, Integer>();
123 for( final Character r : msa.getColumnAt( c ) ) {
124 if ( !map.containsKey( r ) ) {
128 map.put( r, map.get( r ) + 1 );
134 public static DescriptiveStatistics calcBasicGapinessStatistics( final Msa msa ) {
135 final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
136 for( int i = 0; i < msa.getLength(); ++i ) {
137 stats.addValue( ( double ) calcGapSumPerColumn( msa, i ) / msa.getNumberOfSequences() );