package org.forester.archaeopteryx.tools;
-import java.io.FileNotFoundException;
import java.io.IOException;
import java.net.UnknownHostException;
import java.util.SortedSet;
import org.forester.phylogeny.data.Taxonomy;
import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
import org.forester.util.ForesterUtil;
-import org.forester.ws.uniprot.DatabaseTools;
-import org.forester.ws.uniprot.SequenceDatabaseEntry;
-import org.forester.ws.uniprot.UniProtWsTools;
+import org.forester.util.SequenceIdParser;
+import org.forester.ws.seqdb.SequenceDatabaseEntry;
+import org.forester.ws.seqdb.SequenceDbWsTools;
-public final class SequenceDataRetriver implements Runnable {
+public final class SequenceDataRetriver extends RunnableProcess {
+ public final static int DEFAULT_LINES_TO_RETURN = 50;
private final Phylogeny _phy;
private final MainFrameApplication _mf;
private final TreePanel _treepanel;
- private final static boolean DEBUG = false;
+ private final static boolean DEBUG = false;
private enum Db {
- UNKNOWN, UNIPROT, EMBL;
+ UNIPROT, EMBL, NCBI, NONE, REFSEQ;
}
public SequenceDataRetriver( final MainFrameApplication mf, final TreePanel treepanel, final Phylogeny phy ) {
_treepanel = treepanel;
}
- private String getBaseUrl() {
- return UniProtWsTools.BASE_URL;
- }
-
private void execute() {
- _mf.getMainPanel().getCurrentTreePanel().setWaitCursor();
+ start( _mf, "sequence data" );
SortedSet<String> not_found = null;
try {
- not_found = obtainSeqInformation( _phy );
+ not_found = obtainSeqInformation( _phy, false, true );
}
catch ( final UnknownHostException e ) {
- _mf.getMainPanel().getCurrentTreePanel().setArrowCursor();
+ final String what = "_"; //TODO FIXME
JOptionPane.showMessageDialog( _mf,
- "Could not connect to \"" + getBaseUrl() + "\"",
+ "Could not connect to \"" + what + "\"",
"Network error during taxonomic information gathering",
JOptionPane.ERROR_MESSAGE );
return;
}
catch ( final IOException e ) {
- _mf.getMainPanel().getCurrentTreePanel().setArrowCursor();
e.printStackTrace();
JOptionPane.showMessageDialog( _mf,
e.toString(),
return;
}
finally {
- _mf.getMainPanel().getCurrentTreePanel().setArrowCursor();
+ end( _mf );
}
_treepanel.setTree( _phy );
_mf.showWhole();
else {
try {
JOptionPane.showMessageDialog( _mf,
- "UniProt sequence tool successfully completed",
- "UniProt Sequence Tool Completed",
+ "Sequence tool successfully completed",
+ "Sequence Tool Completed",
JOptionPane.INFORMATION_MESSAGE );
}
catch ( final Exception e ) {
}
}
- public static SortedSet<String> obtainSeqInformation( final Phylogeny phy ) throws IOException {
+ public static SortedSet<String> obtainSeqInformation( final Phylogeny phy,
+ final boolean ext_nodes_only,
+ final boolean allow_to_set_taxonomic_data )
+ throws IOException {
final SortedSet<String> not_found = new TreeSet<String>();
for( final PhylogenyNodeIterator iter = phy.iteratorPostorder(); iter.hasNext(); ) {
final PhylogenyNode node = iter.next();
- Sequence seq = null;
- Taxonomy tax = null;
- if ( node.getNodeData().isHasSequence() ) {
- seq = node.getNodeData().getSequence();
- }
- else {
- seq = new Sequence();
- }
- if ( node.getNodeData().isHasTaxonomy() ) {
- tax = node.getNodeData().getTaxonomy();
- }
- else {
- tax = new Taxonomy();
+ 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;
- Db db = Db.UNKNOWN;
+ 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() )
db = Db.EMBL;
}
else if ( !ForesterUtil.isEmpty( node.getName() ) ) {
- if ( ( query = UniProtWsTools.parseUniProtAccessor( node.getName() ) ) != null ) {
+ if ( ( query = SequenceDbWsTools.parseUniProtAccessor( node.getName() ) ) != null ) {
db = Db.UNIPROT;
}
- else if ( ( query = DatabaseTools.parseGenbankAccessor( node.getName() ) ) != null ) {
- db = Db.EMBL;
+ 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 ) ) {
- SequenceDatabaseEntry db_entry = null;
if ( db == Db.UNIPROT ) {
if ( DEBUG ) {
System.out.println( "uniprot: " + query );
}
- try {
- db_entry = UniProtWsTools.obtainUniProtEntry( query, 200 );
- }
- catch ( final FileNotFoundException e ) {
- // Ignore.
- }
+ 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 );
}
- try {
- db_entry = UniProtWsTools.obtainEmblEntry( query, 200 );
- }
- catch ( final FileNotFoundException e ) {
- // Ignore.
- }
+ db_entry = SequenceDbWsTools.obtainEmblEntry( new Identifier( query ), DEFAULT_LINES_TO_RETURN );
if ( ( db == Db.UNIPROT ) && ( db_entry != null ) ) {
db = Db.EMBL;
}
}
- 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";
- }
- seq.setAccession( new Accession( db_entry.getAccession(), type ) );
- }
- if ( !ForesterUtil.isEmpty( db_entry.getSequenceName() ) ) {
- seq.setName( db_entry.getSequenceName() );
+ }
+ 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";
}
- if ( !ForesterUtil.isEmpty( db_entry.getSequenceSymbol() ) ) {
- seq.setSymbol( db_entry.getSequenceSymbol() );
+ else if ( db == Db.UNIPROT ) {
+ type = "uniprot";
}
- if ( !ForesterUtil.isEmpty( db_entry.getTaxonomyScientificName() ) ) {
- tax.setScientificName( db_entry.getTaxonomyScientificName() );
+ else if ( db == Db.NCBI ) {
+ type = "ncbi";
}
- if ( !ForesterUtil.isEmpty( db_entry.getTaxonomyIdentifier() ) ) {
- tax.setIdentifier( new Identifier( db_entry.getTaxonomyIdentifier(), "uniprot" ) );
+ else if ( db == Db.REFSEQ ) {
+ type = "refseq";
}
- node.getNodeData().setTaxonomy( tax );
- node.getNodeData().setSequence( seq );
+ seq.setAccession( new Accession( db_entry.getAccession(), type ) );
+ }
+ if ( !ForesterUtil.isEmpty( db_entry.getSequenceName() ) ) {
+ seq.setName( db_entry.getSequenceName() );
}
- else {
- not_found.add( node.getName() );
+ if ( !ForesterUtil.isEmpty( db_entry.getSequenceSymbol() ) ) {
+ seq.setSymbol( db_entry.getSequenceSymbol() );
}
+ if ( !ForesterUtil.isEmpty( db_entry.getTaxonomyScientificName() ) ) {
+ tax.setScientificName( db_entry.getTaxonomyScientificName() );
+ }
+ if ( allow_to_set_taxonomic_data && !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() );
+ }
+ try {
+ Thread.sleep( 10 );// Sleep for 10 ms
+ }
+ catch ( final InterruptedException ie ) {
}
}
return not_found;