// Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
//
// Contact: phylosoft @ gmail . com
-// WWW: www.phylosoft.org/forester
+// WWW: https://sites.google.com/site/cmzmasek/home/software/forester
package org.forester.ws.seqdb;
import java.net.URLEncoder;
import java.util.ArrayList;
import java.util.List;
-import java.util.regex.Matcher;
-import java.util.regex.Pattern;
+import java.util.SortedSet;
+import java.util.TreeSet;
+import org.forester.phylogeny.Phylogeny;
+import org.forester.phylogeny.PhylogenyNode;
+import org.forester.phylogeny.data.Accession;
import org.forester.phylogeny.data.Identifier;
+import org.forester.phylogeny.data.Sequence;
+import org.forester.phylogeny.data.Taxonomy;
+import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
import org.forester.util.ForesterUtil;
+import org.forester.util.SequenceIdParser;
public final class SequenceDbWsTools {
- private static final boolean ALLOW_TAXONOMY_CODE_HACKS = true; //TODO turn off for final realease!
-
- public enum Db {
- UNKNOWN, UNIPROT;
- }
- public final static String BASE_UNIPROT_URL = "http://www.uniprot.org/";
- public final static String BASE_EMBL_DB_URL = "http://www.ebi.ac.uk/Tools/dbfetch/dbfetch/";
- public final static String EMBL_DBS_EMBL = "embl";
- public final static String EMBL_DBS_REFSEQ_P = "refseqp";
- public final static String EMBL_DBS_REFSEQ_N = "refseqn";
- private final static String URL_ENC = "UTF-8";
- // uniprot/expasy accession number format (6 chars):
- // letter digit letter-or-digit letter-or-digit letter-or-digit digit
- // ?: => no back-reference
- // \A => begin of String
- // \Z => end of String
- private final static Pattern UNIPROT_AC_PATTERN = Pattern
- .compile( "(?:\\A|.*[^a-zA-Z0-9])([A-Z]\\d[A-Z0-9]{3}\\d)(?:[^a-zA-Z0-9]|\\Z)" );
- private final static boolean DEBUG = false;
-
- private static String encode( final String str ) throws UnsupportedEncodingException {
- return URLEncoder.encode( str.trim(), URL_ENC );
- }
-
- /**
- * Returns null if no match.
- *
- * @param query
- * @param db
- * @return
- */
- static public String parseUniProtAccessor( final String query ) {
- final Matcher m = UNIPROT_AC_PATTERN.matcher( query );
- if ( m.lookingAt() ) {
- return m.group( 1 );
- }
- else {
- return null;
- }
- }
+ private static final boolean ALLOW_TAXONOMY_CODE_HACKS = true; //TODO turn off for final realease!
+ public final static String BASE_UNIPROT_URL = "http://www.uniprot.org/";
+ public final static String BASE_EMBL_DB_URL = "http://www.ebi.ac.uk/Tools/dbfetch/dbfetch/";
+ public final static String EMBL_DBS_EMBL = "embl";
+ public final static String EMBL_DBS_REFSEQ_P = "refseqp";
+ public final static String EMBL_DBS_REFSEQ_N = "refseqn";
+ private final static String URL_ENC = "UTF-8";
+ private final static boolean DEBUG = false;
public static List<UniProtTaxonomy> getTaxonomiesFromCommonName( final String cn, final int max_taxonomies_return )
throws IOException {
return null;
}
+ public static SequenceDatabaseEntry obtainEmblEntry( final Identifier id, final int max_lines_to_return )
+ throws IOException {
+ final List<String> lines = queryEmblDb( id, max_lines_to_return );
+ return EbiDbEntry.createInstanceFromPlainText( lines );
+ }
+
+ public static SequenceDatabaseEntry obtainRefSeqEntryFromEmbl( final Identifier id, final int max_lines_to_return )
+ throws IOException {
+ final List<String> lines = queryEmblDb( id, max_lines_to_return );
+ return EbiDbEntry.createInstanceFromPlainTextForRefSeq( lines );
+ }
+
+ public static SortedSet<String> obtainSeqInformation( final Phylogeny phy,
+ final boolean ext_nodes_only,
+ final boolean allow_to_set_taxonomic_data,
+ final int lines_to_return ) 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;
+ }
+ 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 = ForesterUtil.extractUniProtKbProteinSeqIdentifier( node ) ) != 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 = obtainUniProtEntry( query, lines_to_return );
+ }
+ if ( ( db == Db.EMBL ) || ( ( db == Db.UNIPROT ) && ( db_entry == null ) ) ) {
+ if ( DEBUG ) {
+ System.out.println( "embl: " + query );
+ }
+ db_entry = obtainEmblEntry( new Identifier( query ), lines_to_return );
+ if ( ( db == Db.UNIPROT ) && ( db_entry != null ) ) {
+ db = Db.EMBL;
+ }
+ }
+ }
+ else if ( ( db == Db.REFSEQ ) && ( id != null ) ) {
+ db_entry = obtainRefSeqEntryFromEmbl( id, lines_to_return );
+ }
+ else if ( ( db == Db.NCBI ) && ( id != null ) ) {
+ db_entry = obtainEmblEntry( id, lines_to_return ); //TODO ?
+ }
+ if ( ( db_entry != null ) && !db_entry.isEmpty() ) {
+ final Sequence seq = node.getNodeData().isHasSequence() ? node.getNodeData().getSequence()
+ : new Sequence();
+ 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() );
+ }
+ final Taxonomy tax = node.getNodeData().isHasTaxonomy() ? node.getNodeData().getTaxonomy()
+ : new Taxonomy();
+ 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;
+ }
+
+ public static SequenceDatabaseEntry obtainUniProtEntry( final String query, final int max_lines_to_return )
+ throws IOException {
+ final List<String> lines = queryUniprot( "uniprot/" + query + ".txt", max_lines_to_return );
+ return UniProtEntry.createInstanceFromPlainText( lines );
+ }
+
+ public static List<String> queryDb( final String query, int max_lines_to_return, final String base_url )
+ throws IOException {
+ if ( ForesterUtil.isEmpty( query ) ) {
+ throw new IllegalArgumentException( "illegal attempt to use empty query " );
+ }
+ if ( max_lines_to_return < 1 ) {
+ max_lines_to_return = 1;
+ }
+ final URL url = new URL( base_url + query );
+ if ( DEBUG ) {
+ System.out.println( "url: " + url.toString() );
+ }
+ final URLConnection urlc = url.openConnection();
+ final BufferedReader in = new BufferedReader( new InputStreamReader( urlc.getInputStream() ) );
+ String line;
+ final List<String> result = new ArrayList<String>();
+ while ( ( line = in.readLine() ) != null ) {
+ if ( DEBUG ) {
+ System.out.println( line );
+ }
+ result.add( line );
+ if ( result.size() > max_lines_to_return ) {
+ break;
+ }
+ }
+ in.close();
+ try {
+ // To prevent accessing online dbs in too quick succession.
+ Thread.sleep( 20 );
+ }
+ catch ( final InterruptedException e ) {
+ e.printStackTrace();
+ }
+ return result;
+ }
+
+ public static List<String> queryEmblDb( final Identifier id, final int max_lines_to_return ) throws IOException {
+ final StringBuilder url_sb = new StringBuilder();
+ url_sb.append( BASE_EMBL_DB_URL );
+ if ( ForesterUtil.isEmpty( id.getProvider() ) || id.getProvider().equalsIgnoreCase( Identifier.NCBI ) ) {
+ url_sb.append( SequenceDbWsTools.EMBL_DBS_EMBL );
+ url_sb.append( '/' );
+ }
+ else if ( id.getProvider().equalsIgnoreCase( Identifier.REFSEQ ) ) {
+ if ( id.getValue().toUpperCase().indexOf( 'P' ) == 1 ) {
+ url_sb.append( SequenceDbWsTools.EMBL_DBS_REFSEQ_P );
+ url_sb.append( '/' );
+ }
+ else {
+ url_sb.append( SequenceDbWsTools.EMBL_DBS_REFSEQ_N );
+ url_sb.append( '/' );
+ }
+ }
+ return queryDb( id.getValue(), max_lines_to_return, url_sb.toString() );
+ }
+
+ public static List<String> queryUniprot( final String query, final int max_lines_to_return ) throws IOException {
+ return queryDb( query, max_lines_to_return, BASE_UNIPROT_URL );
+ }
+
+ private static String encode( final String str ) throws UnsupportedEncodingException {
+ return URLEncoder.encode( str.trim(), URL_ENC );
+ }
+
+ private static List<String> getTaxonomyStringFromCommonName( final String cn, final int max_lines_to_return )
+ throws IOException {
+ return queryUniprot( "taxonomy/?query=common%3a%22" + encode( cn ) + "%22&format=tab", max_lines_to_return );
+ }
+
+ private static List<String> getTaxonomyStringFromId( final String id, final int max_lines_to_return )
+ throws IOException {
+ return queryUniprot( "taxonomy/?query=id%3a%22" + encode( id ) + "%22&format=tab", max_lines_to_return );
+ }
+
+ private static List<String> getTaxonomyStringFromScientificName( final String sn, final int max_lines_to_return )
+ throws IOException {
+ return queryUniprot( "taxonomy/?query=scientific%3a%22" + encode( sn ) + "%22&format=tab", max_lines_to_return );
+ }
+
+ private static List<String> getTaxonomyStringFromTaxonomyCode( final String code, final int max_lines_to_return )
+ throws IOException {
+ return queryUniprot( "taxonomy/?query=mnemonic%3a%22" + encode( code ) + "%22&format=tab", max_lines_to_return );
+ }
+
+ private static List<UniProtTaxonomy> parseUniProtTaxonomy( final List<String> result ) throws IOException {
+ final List<UniProtTaxonomy> taxonomies = new ArrayList<UniProtTaxonomy>();
+ for( final String line : result ) {
+ if ( ForesterUtil.isEmpty( line ) ) {
+ // Ignore empty lines.
+ }
+ else if ( line.startsWith( "Taxon" ) ) {
+ final String[] items = line.split( "\t" );
+ if ( !( items[ 1 ].equalsIgnoreCase( "Mnemonic" ) && items[ 2 ].equalsIgnoreCase( "Scientific name" )
+ && items[ 3 ].equalsIgnoreCase( "Common name" ) && items[ 4 ].equalsIgnoreCase( "Synonym" )
+ && items[ 5 ].equalsIgnoreCase( "Other Names" ) && items[ 6 ].equalsIgnoreCase( "Reviewed" )
+ && items[ 7 ].equalsIgnoreCase( "Rank" ) && items[ 8 ].equalsIgnoreCase( "Lineage" ) ) ) {
+ throw new IOException( "Unreconized UniProt Taxonomy format: " + line );
+ }
+ }
+ else {
+ if ( line.split( "\t" ).length > 4 ) {
+ taxonomies.add( new UniProtTaxonomy( line ) );
+ }
+ }
+ }
+ return taxonomies;
+ }
+
private static List<UniProtTaxonomy> resolveFakeTaxonomyCodes( final int max_taxonomies_return, final String code )
throws IOException {
if ( code.equals( "CAP" ) ) {
}
}
- private static List<String> getTaxonomyStringFromCommonName( final String cn, final int max_lines_to_return )
- throws IOException {
- return queryUniprot( "taxonomy/?query=common%3a%22" + encode( cn ) + "%22&format=tab", max_lines_to_return );
- }
-
- private static List<String> getTaxonomyStringFromId( final String id, final int max_lines_to_return )
- throws IOException {
- return queryUniprot( "taxonomy/?query=id%3a%22" + encode( id ) + "%22&format=tab", max_lines_to_return );
- }
-
- private static List<String> getTaxonomyStringFromScientificName( final String sn, final int max_lines_to_return )
- throws IOException {
- return queryUniprot( "taxonomy/?query=scientific%3a%22" + encode( sn ) + "%22&format=tab", max_lines_to_return );
- }
-
- private static List<String> getTaxonomyStringFromTaxonomyCode( final String code, final int max_lines_to_return )
- throws IOException {
- return queryUniprot( "taxonomy/?query=mnemonic%3a%22" + encode( code ) + "%22&format=tab", max_lines_to_return );
- }
-
private static List<UniProtTaxonomy> uniProtTaxonomyToList( final UniProtTaxonomy tax ) {
final List<UniProtTaxonomy> l = new ArrayList<UniProtTaxonomy>();
l.add( tax );
return l;
}
- private static List<UniProtTaxonomy> parseUniProtTaxonomy( final List<String> result ) throws IOException {
- final List<UniProtTaxonomy> taxonomies = new ArrayList<UniProtTaxonomy>();
- for( final String line : result ) {
- if ( ForesterUtil.isEmpty( line ) ) {
- // Ignore empty lines.
- }
- else if ( line.startsWith( "Taxon" ) ) {
- final String[] items = line.split( "\t" );
- if ( !( items[ 1 ].equalsIgnoreCase( "Mnemonic" ) && items[ 2 ].equalsIgnoreCase( "Scientific name" )
- && items[ 3 ].equalsIgnoreCase( "Common name" ) && items[ 4 ].equalsIgnoreCase( "Synonym" )
- && items[ 5 ].equalsIgnoreCase( "Other Names" ) && items[ 6 ].equalsIgnoreCase( "Reviewed" )
- && items[ 7 ].equalsIgnoreCase( "Rank" ) && items[ 8 ].equalsIgnoreCase( "Lineage" ) ) ) {
- throw new IOException( "Unreconized UniProt Taxonomy format: " + line );
- }
- }
- else {
- if ( line.split( "\t" ).length > 4 ) {
- taxonomies.add( new UniProtTaxonomy( line ) );
- }
- }
- }
- return taxonomies;
- }
-
- public static List<String> queryEmblDb( final Identifier id, final int max_lines_to_return ) throws IOException {
- final StringBuilder url_sb = new StringBuilder();
- url_sb.append( BASE_EMBL_DB_URL );
- if ( ForesterUtil.isEmpty( id.getProvider() ) || id.getProvider().equalsIgnoreCase( Identifier.NCBI ) ) {
- url_sb.append( SequenceDbWsTools.EMBL_DBS_EMBL );
- url_sb.append( '/' );
- }
- else if ( id.getProvider().equalsIgnoreCase( Identifier.REFSEQ ) ) {
- if ( id.getValue().toUpperCase().indexOf( 'P' ) == 1 ) {
- url_sb.append( SequenceDbWsTools.EMBL_DBS_REFSEQ_P );
- url_sb.append( '/' );
- }
- else {
- url_sb.append( SequenceDbWsTools.EMBL_DBS_REFSEQ_N );
- url_sb.append( '/' );
- }
- }
- return queryDb( id.getValue(), max_lines_to_return, url_sb.toString() );
- }
-
- public static List<String> queryUniprot( final String query, final int max_lines_to_return ) throws IOException {
- return queryDb( query, max_lines_to_return, BASE_UNIPROT_URL );
- }
-
- public static List<String> queryDb( final String query, int max_lines_to_return, final String base_url )
- throws IOException {
- if ( ForesterUtil.isEmpty( query ) ) {
- throw new IllegalArgumentException( "illegal attempt to use empty query " );
- }
- if ( max_lines_to_return < 1 ) {
- max_lines_to_return = 1;
- }
- final URL url = new URL( base_url + query );
- if ( DEBUG ) {
- System.out.println( "url: " + url.toString() );
- }
- final URLConnection urlc = url.openConnection();
- final BufferedReader in = new BufferedReader( new InputStreamReader( urlc.getInputStream() ) );
- String line;
- final List<String> result = new ArrayList<String>();
- while ( ( line = in.readLine() ) != null ) {
- if ( DEBUG ) {
- System.out.println( line );
- }
- result.add( line );
- if ( result.size() > max_lines_to_return ) {
- break;
- }
- }
- in.close();
- return result;
- }
-
- public static SequenceDatabaseEntry obtainUniProtEntry( final String query, final int max_lines_to_return )
- throws IOException {
- final List<String> lines = queryUniprot( "uniprot/" + query + ".txt", max_lines_to_return );
- return UniProtEntry.createInstanceFromPlainText( lines );
- }
-
- public static SequenceDatabaseEntry obtainRefSeqEntryFromEmbl( final Identifier id, final int max_lines_to_return )
- throws IOException {
- final List<String> lines = queryEmblDb( id, max_lines_to_return );
- return EbiDbEntry.createInstanceFromPlainTextForRefSeq( lines );
- }
-
- public static SequenceDatabaseEntry obtainEmblEntry( final Identifier id, final int max_lines_to_return )
- throws IOException {
- final List<String> lines = queryEmblDb( id, max_lines_to_return );
- return EbiDbEntry.createInstanceFromPlainText( lines );
+ public enum Db {
+ UNIPROT, EMBL, NCBI, NONE, REFSEQ;
}
}
git://source.jalview.org / jalview.git / blobdiff