X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=forester%2Fjava%2Fsrc%2Forg%2Fforester%2Fphylogeny%2Fdata%2FSequence.java;h=3561edcecaee812a3d451acdbb8491a3e3f58c37;hb=c31fca8b235625db6186410c2244ffcef10efa1c;hp=ac4be9e79070405861d0bc25cc45fff42f22cc42;hpb=a648fae3c8d0402dbdafa379ff3d42bbea96633d;p=jalview.git diff --git a/forester/java/src/org/forester/phylogeny/data/Sequence.java b/forester/java/src/org/forester/phylogeny/data/Sequence.java index ac4be9e..3561edc 100644 --- a/forester/java/src/org/forester/phylogeny/data/Sequence.java +++ b/forester/java/src/org/forester/phylogeny/data/Sequence.java @@ -37,54 +37,69 @@ import org.forester.io.parsers.phyloxml.PhyloXmlDataFormatException; import org.forester.io.parsers.phyloxml.PhyloXmlMapping; import org.forester.io.parsers.phyloxml.PhyloXmlUtil; import org.forester.io.writers.PhylogenyWriter; +import org.forester.sequence.MolecularSequence; +import org.forester.sequence.MolecularSequence.TYPE; import org.forester.util.ForesterUtil; -public class Sequence implements PhylogenyData, MultipleUris { +public class Sequence implements PhylogenyData, MultipleUris, Comparable { + private Accession _accession; + private SortedSet _annotations; + private DomainArchitecture _da; + private String _gene_name; + private String _location; private String _mol_sequence; private boolean _mol_sequence_is_aligned; private String _name; + private List _seq_relations; private String _source_id; - private Accession _accession; private String _symbol; - private String _location; private String _type; - private SortedSet _annotations; - private DomainArchitecture _da; private List _uris; - private List _seq_relations; private SortedSet _xrefs; public Sequence() { init(); } - public boolean isEmpty() { - return ( getAccession() == null ) && ForesterUtil.isEmpty( getName() ) && ForesterUtil.isEmpty( getSymbol() ) - && ForesterUtil.isEmpty( getType() ) && ForesterUtil.isEmpty( getLocation() ) - && ForesterUtil.isEmpty( getSourceId() ) && ForesterUtil.isEmpty( getMolecularSequence() ) - && ( getDomainArchitecture() == null ) && ForesterUtil.isEmpty( _annotations ) - && ForesterUtil.isEmpty( _uris ) && ForesterUtil.isEmpty( _seq_relations ) - && ( getCrossReferences() == null || getCrossReferences().isEmpty() ); + public Sequence( final MolecularSequence mol_seq ) { + init(); + setMolecularSequence( mol_seq.getMolecularSequenceAsString() ); + setName( mol_seq.getIdentifier() ); + String type; + if ( mol_seq.getType() == TYPE.AA ) { + type = "protein"; + } + else if ( mol_seq.getType() == TYPE.DNA ) { + type = "dna"; + } + else if ( mol_seq.getType() == TYPE.RNA ) { + type = "rna"; + } + else { + throw new IllegalArgumentException( "unknown sequence type " + mol_seq.getType() ); + } + try { + setType( type ); + } + catch ( final PhyloXmlDataFormatException e ) { + throw new IllegalArgumentException( "don't know how to handle type " + mol_seq.getType() ); + } } public void addAnnotation( final Annotation annotation ) { getAnnotations().add( annotation ); } - - public void addCrossReference( Accession cross_reference ) { + + public void addCrossReference( final Accession cross_reference ) { if ( getCrossReferences() == null ) { setCrossReferences( new TreeSet() ); } - getCrossReferences().add( cross_reference ); - } - - public SortedSet getCrossReferences() { - return _xrefs; + getCrossReferences().add( cross_reference ); } - - private void setCrossReferences( TreeSet cross_references ) { - _xrefs = cross_references; + + public void addSequenceRelation( final SequenceRelation sr ) { + getSequenceRelations().add( sr ); } @Override @@ -95,10 +110,6 @@ public class Sequence implements PhylogenyData, MultipleUris { getUris().add( uri ); } - public void addSequenceRelation( final SequenceRelation sr ) { - _seq_relations.add( sr ); - } - @Override public StringBuffer asSimpleText() { final StringBuffer sb = new StringBuffer(); @@ -122,15 +133,39 @@ public class Sequence implements PhylogenyData, MultipleUris { return asSimpleText(); } + @Override + public int compareTo( final Sequence o ) { + if ( ( !ForesterUtil.isEmpty( getName() ) ) && ( !ForesterUtil.isEmpty( o.getName() ) ) ) { + return getName().compareTo( o.getName() ); + } + if ( ( !ForesterUtil.isEmpty( getSymbol() ) ) && ( !ForesterUtil.isEmpty( o.getSymbol() ) ) ) { + return getSymbol().compareTo( o.getSymbol() ); + } + if ( ( !ForesterUtil.isEmpty( getGeneName() ) ) && ( !ForesterUtil.isEmpty( o.getGeneName() ) ) ) { + return getGeneName().compareTo( o.getGeneName() ); + } + if ( ( getAccession() != null ) && ( o.getAccession() != null ) + && !ForesterUtil.isEmpty( getAccession().getValue() ) + && !ForesterUtil.isEmpty( o.getAccession().getValue() ) ) { + return getAccession().getValue().compareTo( o.getAccession().getValue() ); + } + if ( ( !ForesterUtil.isEmpty( getMolecularSequence() ) ) + && ( !ForesterUtil.isEmpty( o.getMolecularSequence() ) ) ) { + return getMolecularSequence().compareTo( o.getMolecularSequence() ); + } + return 0; + } + /** * Not a deep copy. - * + * */ @Override public PhylogenyData copy() { final Sequence seq = new Sequence(); seq.setAnnotations( getAnnotations() ); seq.setName( getName() ); + seq.setGeneName( getGeneName() ); try { seq.setSymbol( getSymbol() ); } @@ -170,7 +205,7 @@ public class Sequence implements PhylogenyData, MultipleUris { seq.setCrossReferences( new TreeSet() ); for( final Accession x : getCrossReferences() ) { if ( x != null ) { - seq.getCrossReferences().add( x); + seq.getCrossReferences().add( x ); } } } @@ -209,10 +244,18 @@ public class Sequence implements PhylogenyData, MultipleUris { return _annotations; } + public SortedSet getCrossReferences() { + return _xrefs; + } + public DomainArchitecture getDomainArchitecture() { return _da; } + public String getGeneName() { + return _gene_name; + } + public String getLocation() { return _location; } @@ -221,10 +264,6 @@ public class Sequence implements PhylogenyData, MultipleUris { return _mol_sequence; } - public boolean isMolecularSequenceAligned() { - return _mol_sequence_is_aligned; - } - public String getName() { return _name; } @@ -236,10 +275,6 @@ public class Sequence implements PhylogenyData, MultipleUris { return _seq_relations; } - private void setSequenceRelations( final List seq_relations ) { - _seq_relations = seq_relations; - } - public String getSourceId() { return _source_id; } @@ -253,13 +288,13 @@ public class Sequence implements PhylogenyData, MultipleUris { } @Override - public List getUris() { - return _uris; + public Uri getUri( final int index ) { + return getUris().get( index ); } @Override - public Uri getUri( final int index ) { - return getUris().get( index ); + public List getUris() { + return _uris; } @Override @@ -267,23 +302,26 @@ public class Sequence implements PhylogenyData, MultipleUris { if ( getAccession() != null ) { return getAccession().hashCode(); } - int result = getSymbol().hashCode(); - if ( getName().length() > 0 ) { + int result = getName().hashCode(); + if ( getSymbol().length() > 0 ) { result ^= getName().hashCode(); } + if ( getGeneName().length() > 0 ) { + result ^= getGeneName().hashCode(); + } if ( getMolecularSequence().length() > 0 ) { result ^= getMolecularSequence().hashCode(); } return result; } - public boolean hasSequenceRelations() { - return _seq_relations.size() > 0; + public boolean isHasSequenceRelations() { + return _seq_relations != null && _seq_relations.size() > 0; } public void init() { - setAnnotations( null ); setName( "" ); + setGeneName( "" ); setMolecularSequence( "" ); setMolecularSequenceAligned( false ); setLocation( "" ); @@ -304,7 +342,18 @@ public class Sequence implements PhylogenyData, MultipleUris { setUris( null ); setSequenceRelations( null ); setSourceId( null ); - setCrossReferences(null); + setCrossReferences( null ); + setAnnotations( null ); + } + + public boolean isEmpty() { + return ( getAccession() == null ) && ForesterUtil.isEmpty( getName() ) && ForesterUtil.isEmpty( getSymbol() ) + && ForesterUtil.isEmpty( getGeneName() ) && ForesterUtil.isEmpty( getType() ) + && ForesterUtil.isEmpty( getLocation() ) && ForesterUtil.isEmpty( getSourceId() ) + && ForesterUtil.isEmpty( getMolecularSequence() ) && ( getDomainArchitecture() == null ) + && ForesterUtil.isEmpty( _annotations ) && ForesterUtil.isEmpty( _uris ) + && ForesterUtil.isEmpty( _seq_relations ) + && ( ( getCrossReferences() == null ) || getCrossReferences().isEmpty() ); } @Override @@ -317,21 +366,25 @@ public class Sequence implements PhylogenyData, MultipleUris { return getAccession().isEqual( s.getAccession() ); } return s.getMolecularSequence().equals( getMolecularSequence() ) && s.getName().equals( getName() ) - && s.getSymbol().equals( getSymbol() ); + && s.getSymbol().equals( getSymbol() ) && s.getGeneName().equals( getGeneName() ); } - public void setAccession( final Accession accession ) { - _accession = accession; + public boolean isMolecularSequenceAligned() { + return _mol_sequence_is_aligned; } - private void setAnnotations( final SortedSet annotations ) { - _annotations = annotations; + public void setAccession( final Accession accession ) { + _accession = accession; } public void setDomainArchitecture( final DomainArchitecture ds ) { _da = ds; } + public void setGeneName( final String gene_name ) { + _gene_name = gene_name; + } + public void setLocation( final String description ) { _location = description; } @@ -382,9 +435,6 @@ public class Sequence implements PhylogenyData, MultipleUris { if ( getAccession() != null ) { getAccession().toNHX(); } - if ( getDomainArchitecture() != null ) { - sb.append( getDomainArchitecture().toNHX() ); - } return sb; } @@ -406,6 +456,9 @@ public class Sequence implements PhylogenyData, MultipleUris { if ( !ForesterUtil.isEmpty( getName() ) ) { PhylogenyDataUtil.appendElement( writer, PhyloXmlMapping.SEQUENCE_NAME, getName(), indentation ); } + if ( !ForesterUtil.isEmpty( getGeneName() ) ) { + PhylogenyDataUtil.appendElement( writer, PhyloXmlMapping.SEQUENCE_GENE_NAME, getGeneName(), indentation ); + } if ( !ForesterUtil.isEmpty( getLocation() ) ) { PhylogenyDataUtil.appendElement( writer, PhyloXmlMapping.SEQUENCE_LOCATION, getLocation(), indentation ); } @@ -417,22 +470,19 @@ public class Sequence implements PhylogenyData, MultipleUris { String.valueOf( isMolecularSequenceAligned() ), indentation ); } - if ( getUris() != null && !getUris().isEmpty() ) { + if ( ( getUris() != null ) && !getUris().isEmpty() ) { for( final Uri uri : getUris() ) { if ( uri != null ) { uri.toPhyloXML( writer, level, indentation ); } } } - if ( getAnnotations() != null && !getAnnotations().isEmpty() ) { + if ( ( getAnnotations() != null ) && !getAnnotations().isEmpty() ) { for( final PhylogenyData annotation : getAnnotations() ) { annotation.toPhyloXML( writer, level, my_ind ); } } - if ( getDomainArchitecture() != null ) { - getDomainArchitecture().toPhyloXML( writer, level, my_ind ); - } - if ( getCrossReferences() != null && !getCrossReferences().isEmpty() ) { + if ( ( getCrossReferences() != null ) && !getCrossReferences().isEmpty() ) { writer.write( ForesterUtil.LINE_SEPARATOR ); writer.write( my_ind ); PhylogenyDataUtil.appendOpen( writer, PhyloXmlMapping.SEQUENCE_X_REFS ); @@ -442,7 +492,10 @@ public class Sequence implements PhylogenyData, MultipleUris { writer.write( ForesterUtil.LINE_SEPARATOR ); writer.write( my_ind ); PhylogenyDataUtil.appendClose( writer, PhyloXmlMapping.SEQUENCE_X_REFS ); - } + } + if ( getDomainArchitecture() != null ) { + getDomainArchitecture().toPhyloXML( writer, level, my_ind ); + } writer.write( ForesterUtil.LINE_SEPARATOR ); writer.write( indentation ); PhylogenyDataUtil.appendClose( writer, PhyloXmlMapping.SEQUENCE ); @@ -452,4 +505,16 @@ public class Sequence implements PhylogenyData, MultipleUris { public String toString() { return asText().toString(); } + + private void setAnnotations( final SortedSet annotations ) { + _annotations = annotations; + } + + private void setCrossReferences( final TreeSet cross_references ) { + _xrefs = cross_references; + } + + private void setSequenceRelations( final List seq_relations ) { + _seq_relations = seq_relations; + } }