if ( !entry4.getAccession().equals( "AAA36557" ) ) {
return false;
}
+ if ( !entry4.getTaxonomyScientificName().equals( "Homo sapiens" ) ) {
+ System.out.println( entry4.getTaxonomyScientificName() );
+ return false;
+ }
+ if ( !entry4.getSequenceName().equals( "Homo sapiens (human) ras protein" ) ) {
+ System.out.println( entry4.getSequenceName() );
+ return false;
+ }
+ if ( !entry4.getTaxonomyIdentifier().equals( "9606" ) ) {
+ System.out.println( entry4.getTaxonomyIdentifier() );
+ return false;
+ }
+ if ( !entry4.getGeneName().equals( "ras" ) ) {
+ System.out.println( entry4.getGeneName() );
+ return false;
+ }
//
//TODO fails:
// final SequenceDatabaseEntry entry5 = SequenceDbWsTools.obtainEntry( "M30539" );
final Pattern mim_PATTERN = Pattern.compile( "\\s+/db_xref=\"MIM:(\\d+)\"" );
final Pattern taxon_PATTERN = Pattern.compile( "\\s+/db_xref=\"taxon:(\\d+)\"" );
final Pattern interpro_PATTERN = Pattern.compile( "\\s+/db_xref=\"InterPro:([A-Z0-9]+)\"" );
- final Pattern uniprot_PATTERN = Pattern.compile( "\\s+/db_xref=\"UniProtKB/TrEMBL:(\\w+)\"" );
- final Pattern hgnc_PATTERN = Pattern.compile( "\\s+/db_xref=\"HGNC:(\\d+)\"" );
+ final Pattern uniprot_PATTERN = Pattern.compile( "\\s+/db_xref=\"UniProtKB/[A-Za-z-]*:(\\w+)\"" );
+ final Pattern hgnc_PATTERN = Pattern.compile( "\\s+/db_xref=\"[A-Z:]*HGNC:(\\d+)\"" );
final Pattern geneid_PATTERN = Pattern.compile( "\\s+/db_xref=\"GeneID:(\\d+)\"" );
+ final Pattern pdb_PATTERN = Pattern.compile( "\\s+/db_xref=\"PDB:([A-Z0-9]+)\"" );
+
+
final Pattern ec_PATTERN = Pattern.compile( "\\s+/EC_number=\"([\\.\\-\\d]+)\"" );
final Pattern product_PATTERN = Pattern.compile( "\\s+/product=\"(\\w{1,10})\"" );
final EbiDbEntry e = new EbiDbEntry();
if ( product.find() ) {
e.setSequenceSymbol( product.group( 1 ) );
}
+ final Matcher pdb = pdb_PATTERN.matcher( line );
+ if ( pdb.find() ) {
+ e.addCrossReference( new Accession( pdb.group( 1 ), "pdb" ) );
+ }
}
}
if ( def.length() > 0 ) {