-
- public static SortedSet<String> obtainSeqInformation( final Phylogeny phy, final boolean ext_nodes_only ) throws IOException {
- final SortedSet<String> not_found = new TreeSet<String>();
- for( final PhylogenyNodeIterator iter = phy.iteratorPostorder(); iter.hasNext(); ) {
- final PhylogenyNode node = iter.next();
- if ( ext_nodes_only && node.isInternal() ) {
- continue;
- }
- final Sequence seq = node.getNodeData().isHasSequence() ? node.getNodeData().getSequence() : new Sequence();
- final Taxonomy tax = node.getNodeData().isHasTaxonomy() ? node.getNodeData().getTaxonomy() : new Taxonomy();
- String query = null;
- Identifier id = null;
- Db db = Db.NONE;
- if ( node.getNodeData().isHasSequence() && ( node.getNodeData().getSequence().getAccession() != null )
- && !ForesterUtil.isEmpty( node.getNodeData().getSequence().getAccession().getSource() )
- && !ForesterUtil.isEmpty( node.getNodeData().getSequence().getAccession().getValue() )
- && node.getNodeData().getSequence().getAccession().getValue().toLowerCase().startsWith( "uniprot" ) ) {
- query = node.getNodeData().getSequence().getAccession().getValue();
- db = Db.UNIPROT;
- }
- else if ( node.getNodeData().isHasSequence()
- && ( node.getNodeData().getSequence().getAccession() != null )
- && !ForesterUtil.isEmpty( node.getNodeData().getSequence().getAccession().getSource() )
- && !ForesterUtil.isEmpty( node.getNodeData().getSequence().getAccession().getValue() )
- && ( node.getNodeData().getSequence().getAccession().getValue().toLowerCase().startsWith( "embl" ) || node
- .getNodeData().getSequence().getAccession().getValue().toLowerCase().startsWith( "ebi" ) ) ) {
- query = node.getNodeData().getSequence().getAccession().getValue();
- db = Db.EMBL;
- }
- else if ( !ForesterUtil.isEmpty( node.getName() ) ) {
- if ( ( query = SequenceDbWsTools.parseUniProtAccessor( node.getName() ) ) != null ) {
- db = Db.UNIPROT;
- }
- else if ( ( id = SequenceIdParser.parse( node.getName() ) ) != null ) {
- if ( id.getProvider().equalsIgnoreCase( Identifier.NCBI ) ) {
- db = Db.NCBI;
- }
- else if ( id.getProvider().equalsIgnoreCase( Identifier.REFSEQ ) ) {
- db = Db.REFSEQ;
- }
- }
- }
-
- if ( db == Db.NONE ) {
- not_found.add( node.getName() );
- }
-
- SequenceDatabaseEntry db_entry = null;
- if ( !ForesterUtil.isEmpty( query ) ) {
- if ( db == Db.UNIPROT ) {
- if ( DEBUG ) {
- System.out.println( "uniprot: " + query );
- }
- db_entry = SequenceDbWsTools.obtainUniProtEntry( query, DEFAULT_LINES_TO_RETURN );
- }
- if ( ( db == Db.EMBL ) || ( ( db == Db.UNIPROT ) && ( db_entry == null ) ) ) {
- if ( DEBUG ) {
- System.out.println( "embl: " + query );
- }
- db_entry = SequenceDbWsTools.obtainEmblEntry( new Identifier( query ), DEFAULT_LINES_TO_RETURN );
- if ( ( db == Db.UNIPROT ) && ( db_entry != null ) ) {
- db = Db.EMBL;
- }
- }
- }
- else if ( ( db == Db.REFSEQ ) && ( id != null ) ) {
- db_entry = SequenceDbWsTools.obtainRefSeqEntryFromEmbl( id, DEFAULT_LINES_TO_RETURN );
- }
- else if ( ( db == Db.NCBI ) && ( id != null ) ) {
- db_entry = SequenceDbWsTools.obtainEmblEntry( id, DEFAULT_LINES_TO_RETURN );
- }
-
- if ( ( db_entry != null ) && !db_entry.isEmpty() ) {
- if ( !ForesterUtil.isEmpty( db_entry.getAccession() ) ) {
- String type = null;
- if ( db == Db.EMBL ) {
- type = "embl";
- }
- else if ( db == Db.UNIPROT ) {
- type = "uniprot";
- }
- else if ( db == Db.NCBI ) {
- type = "ncbi";
- }
- else if ( db == Db.REFSEQ ) {
- type = "refseq";
- }
- seq.setAccession( new Accession( db_entry.getAccession(), type ) );
- }
- if ( !ForesterUtil.isEmpty( db_entry.getSequenceName() ) ) {
- seq.setName( db_entry.getSequenceName() );
- }
- if ( !ForesterUtil.isEmpty( db_entry.getSequenceSymbol() ) ) {
- seq.setSymbol( db_entry.getSequenceSymbol() );
- }
- if ( !ForesterUtil.isEmpty( db_entry.getTaxonomyScientificName() ) ) {
- tax.setScientificName( db_entry.getTaxonomyScientificName() );
- }
- if ( !ForesterUtil.isEmpty( db_entry.getTaxonomyIdentifier() ) ) {
- tax.setIdentifier( new Identifier( db_entry.getTaxonomyIdentifier(), "uniprot" ) );
- }
- node.getNodeData().setTaxonomy( tax );
- node.getNodeData().setSequence( seq );
- }
- else if ( db != Db.NONE ) {
- not_found.add( node.getName() );
- }
- }
- return not_found;
- }
-
- @Override
- public void run() {
- execute();
- }