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;
31 import org.forester.sequence.BasicSequence;
32 import org.forester.sequence.Sequence;
33 import org.forester.util.BasicDescriptiveStatistics;
34 import org.forester.util.DescriptiveStatistics;
36 public final class MsaTools {
38 private ArrayList<String> _ignored_seqs_ids;
40 synchronized public ArrayList<String> getIgnoredSequenceIds() {
41 return _ignored_seqs_ids;
44 synchronized public static MsaTools createInstance() {
45 return new MsaTools();
52 synchronized private void init() {
53 _ignored_seqs_ids = new ArrayList<String>();
57 public Object clone() {
58 throw new NoSuchMethodError();
61 public static int calcGapSumPerColumn( final Msa msa, final int col ) {
63 for( int j = 0; j < msa.getNumberOfSequences(); ++j ) {
64 if ( msa.getResidueAt( j, col ) == Sequence.GAP ) {
71 synchronized public Msa removeGapColumns( final double max_allowed_gap_ratio,
72 final int min_allowed_length,
75 if ( ( max_allowed_gap_ratio < 0 ) || ( max_allowed_gap_ratio > 1 ) ) {
76 throw new IllegalArgumentException( "max allowed gap ration is out of range: " + max_allowed_gap_ratio );
78 final boolean ignore_too_short_seqs = min_allowed_length > 0;
79 final boolean[] delete_cols = new boolean[ msa.getLength() ];
81 for( int col = 0; col < msa.getLength(); ++col ) {
82 delete_cols[ col ] = ( ( double ) calcGapSumPerColumn( msa, col ) / msa.getNumberOfSequences() ) > max_allowed_gap_ratio;
83 if ( !delete_cols[ col ] ) {
87 final List<Sequence> seqs = new ArrayList<Sequence>( msa.getNumberOfSequences() );
88 for( int row = 0; row < msa.getNumberOfSequences(); ++row ) {
89 final char[] mol_seq = new char[ new_length ];
91 int non_gap_cols_sum = 0;
92 for( int col = 0; col < msa.getLength(); ++col ) {
93 if ( !delete_cols[ col ] ) {
94 final char residue = msa.getResidueAt( row, col );
95 mol_seq[ new_col++ ] = ( residue );
96 if ( residue != Sequence.GAP ) {
101 if ( ignore_too_short_seqs ) {
102 if ( non_gap_cols_sum >= min_allowed_length ) {
103 seqs.add( new BasicSequence( msa.getIdentifier( row ), mol_seq, msa.getType() ) );
106 _ignored_seqs_ids.add( msa.getIdentifier( row ).toString() );
110 seqs.add( new BasicSequence( msa.getIdentifier( row ), mol_seq, msa.getType() ) );
113 if ( seqs.size() < 1 ) {
116 return BasicMsa.createInstance( seqs );
119 public static DescriptiveStatistics calcBasicGapinessStatistics( final Msa msa ) {
120 final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
121 for( int i = 0; i < msa.getLength(); ++i ) {
122 stats.addValue( ( double ) calcGapSumPerColumn( msa, i ) / msa.getNumberOfSequences() );