package org.forester.ws.seqdb;
-import java.util.ArrayList;
import java.util.List;
+import java.util.SortedSet;
+import java.util.TreeSet;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public final class EbiDbEntry implements SequenceDatabaseEntry {
- public static SequenceDatabaseEntry createInstanceFromPlainText( final List<String> lines ) {
- final EbiDbEntry e = new EbiDbEntry();
- for( final String line : lines ) {
- if ( line.startsWith( "PA" ) ) {
- e.setPA( SequenceDbWsTools.extractFrom( line, "PA" ) );
- }
- else if ( line.startsWith( "DE" ) ) {
- e.setDe( SequenceDbWsTools.extractFrom( line, "DE" ) );
- }
- else if ( line.startsWith( "OS" ) ) {
- if ( line.indexOf( "(" ) > 0 ) {
- e.setOs( SequenceDbWsTools.extractFromTo( line, "OS", "(" ) );
- }
- else {
- e.setOs( SequenceDbWsTools.extractFrom( line, "OS" ) );
- }
- }
- else if ( line.startsWith( "OX" ) ) {
- if ( line.indexOf( "NCBI_TaxID=" ) > 0 ) {
- e.setTaxId( SequenceDbWsTools.extractFromTo( line, "NCBI_TaxID=", ";" ) );
- }
- }
- }
- return e;
- }
-
+ // public static SequenceDatabaseEntry createInstanceFromPlainText( final List<String> lines ) {
+ // final EbiDbEntry e = new EbiDbEntry();
+ // for( final String line : lines ) {
+ // if ( line.startsWith( "PA" ) ) {
+ // e.setPA( SequenceDbWsTools.extractFrom( line, "PA" ) );
+ // }
+ // else if ( line.startsWith( "DE" ) ) {
+ // e.setDe( SequenceDbWsTools.extractFrom( line, "DE" ) );
+ // }
+ // else if ( line.startsWith( "OS" ) ) {
+ // if ( line.indexOf( "(" ) > 0 ) {
+ // e.setOs( SequenceDbWsTools.extractFromTo( line, "OS", "(" ) );
+ // }
+ // else {
+ // e.setOs( SequenceDbWsTools.extractFrom( line, "OS" ) );
+ // }
+ // }
+ // else if ( line.startsWith( "OX" ) ) {
+ // if ( line.indexOf( "NCBI_TaxID=" ) > 0 ) {
+ // e.setTaxId( SequenceDbWsTools.extractFromTo( line, "NCBI_TaxID=", ";" ) );
+ // }
+ // }
+ // }
+ // return e;
+ // }
public static SequenceDatabaseEntry createInstanceFromPlainTextForRefSeq( final List<String> lines ) {
final Pattern X_PATTERN = Pattern.compile( "^[A-Z]+" );
final Pattern chromosome_PATTERN = Pattern.compile( "\\s+/chromosome=\"(\\w+)\"" );
final Pattern map_PATTERN = Pattern.compile( "\\s+/map=\"([\\w+\\.])\"" );
final Pattern gene_PATTERN = Pattern.compile( "\\s+/gene=\"(.+)\"" );
- final Pattern mim_xref_PATTERN = Pattern.compile( "\\s+/db_xref=\"MIM:(\\d+)\"" );
- final Pattern taxon_xref_PATTERN = Pattern.compile( "\\s+/db_xref=\"taxon:(\\d+)\"" );
- final Pattern interpro_PATTERN = Pattern.compile( "\\s+/db_xref=\"InterPro:(IP\\d+)\"" );
- final Pattern uniprot_PATTERN = Pattern.compile( "\\s+/db_xref=\"UniProtKB/TrEMBL:(\\w+)\"" );
- final Pattern ec_PATTERN = Pattern.compile( "\\s+/EC_number=\"[\\.\\-\\d]+\"" );
+ 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/[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();
final StringBuilder def = new StringBuilder();
boolean in_definition = false;
boolean in_source = false;
boolean in_gene = false;
boolean in_cds = false;
+ boolean in_mrna = false;
boolean in_protein = false;
for( final String line : lines ) {
if ( line.startsWith( "ACCESSION " ) ) {
- e.setPA( SequenceDbWsTools.extractFrom( line, "ACCESSION" ) );
+ e.setAccession( SequenceDbWsTools.extractFrom( line, "ACCESSION" ) );
in_definition = false;
}
else if ( line.startsWith( "ID " ) ) {
- e.setPA( SequenceDbWsTools.extractFromTo( line, "ID", ";" ) );
+ e.setAccession( SequenceDbWsTools.extractFromTo( line, "ID", ";" ) );
in_definition = false;
}
else if ( line.startsWith( "DEFINITION " ) || ( line.startsWith( "DE " ) ) ) {
}
else if ( line.startsWith( " ORGANISM " ) ) {
if ( line.indexOf( "(" ) > 0 ) {
- e.setOs( SequenceDbWsTools.extractFromTo( line, " ORGANISM", "(" ) );
+ e.setTaxonomyScientificName( SequenceDbWsTools.extractFromTo( line, " ORGANISM", "(" ) );
}
else {
- e.setOs( SequenceDbWsTools.extractFrom( line, " ORGANISM" ) );
+ e.setTaxonomyScientificName( SequenceDbWsTools.extractFrom( line, " ORGANISM" ) );
}
// in_def = false;
}
else if ( line.startsWith( "OS " ) ) {
if ( line.indexOf( "(" ) > 0 ) {
- e.setOs( SequenceDbWsTools.extractFromTo( line, "OS", "(" ) );
+ e.setTaxonomyScientificName( SequenceDbWsTools.extractFromTo( line, "OS", "(" ) );
}
else {
- e.setOs( SequenceDbWsTools.extractFrom( line, "OS" ) );
+ e.setTaxonomyScientificName( SequenceDbWsTools.extractFrom( line, "OS" ) );
}
}
else if ( line.startsWith( " " ) && in_definition ) {
else {
in_definition = false;
}
- if ( X_PATTERN.matcher( line ).find() ) {
+ if ( !line.startsWith( "FT " ) && X_PATTERN.matcher( line ).find() ) {
in_features = false;
in_source = false;
in_gene = false;
in_cds = false;
+ in_mrna = false;
in_protein = false;
// in_def = false;
}
- if ( line.startsWith( "FEATURES " ) ) {
+ if ( line.startsWith( "FEATURES " ) || line.startsWith( "FT " ) ) {
in_features = true;
}
- if ( in_features && line.startsWith( " source " ) ) {
+ if ( in_features && ( line.startsWith( " source " ) || line.startsWith( "FT source " ) ) ) {
in_source = true;
in_gene = false;
in_cds = false;
+ in_mrna = false;
in_protein = false;
}
- if ( in_features && line.startsWith( " gene " ) ) {
+ if ( in_features && ( line.startsWith( " gene " ) || line.startsWith( "FT gene " ) ) ) {
in_source = false;
in_gene = true;
in_cds = false;
+ in_mrna = false;
in_protein = false;
}
- if ( in_features && line.startsWith( " CDS " ) ) {
+ if ( in_features && ( line.startsWith( " CDS " ) || line.startsWith( "FT CDS " ) ) ) {
in_source = false;
in_gene = false;
in_cds = true;
+ in_mrna = false;
in_protein = false;
}
- if ( in_features && line.startsWith( " Protein " ) ) {
+ if ( in_features && ( line.startsWith( " Protein " ) || line.startsWith( "FT Protein " ) ) ) {
in_source = false;
in_gene = false;
in_cds = false;
+ in_mrna = false;
in_protein = true;
}
- if ( in_protein || in_cds ) {
- final Matcher m = ec_PATTERN.matcher( line );
- if ( m.find() ) {
- e.addAnnotation( new Annotation( "EC", m.group( 1 ) ) );
+ if ( in_features && ( line.startsWith( " mRNA " ) || line.startsWith( "FT mRNA " ) ) ) {
+ in_source = false;
+ in_gene = false;
+ in_cds = false;
+ in_mrna = true;
+ in_protein = false;
+ }
+ if ( in_source ) {
+ final Matcher ti = taxon_PATTERN.matcher( line );
+ if ( ti.find() ) {
+ e.setTaxId( ti.group( 1 ) );
+ }
+ final Matcher chr = chromosome_PATTERN.matcher( line );
+ if ( chr.find() ) {
+ e.setChromosome( chr.group( 1 ) );
+ }
+ final Matcher map = map_PATTERN.matcher( line );
+ if ( map.find() ) {
+ e.setMap( map.group( 1 ) );
+ }
+ }
+ if ( in_cds || in_gene ) {
+ final Matcher hgnc = hgnc_PATTERN.matcher( line );
+ if ( hgnc.find() ) {
+ e.addCrossReference( new Accession( hgnc.group( 1 ), "hgnc" ) );
+ }
+ final Matcher geneid = geneid_PATTERN.matcher( line );
+ if ( geneid.find() ) {
+ e.addCrossReference( new Accession( geneid.group( 1 ), "geneid" ) );
+ }
+ }
+ if ( in_protein || in_cds || in_gene || in_mrna ) {
+ final Matcher ec = ec_PATTERN.matcher( line );
+ if ( ec.find() ) {
+ e.addAnnotation( new Annotation( "EC", ec.group( 1 ) ) );
+ }
+ final Matcher gene = gene_PATTERN.matcher( line );
+ if ( gene.find() ) {
+ e.setGeneName( gene.group( 1 ) );
+ }
+ final Matcher uniprot = uniprot_PATTERN.matcher( line );
+ if ( uniprot.find() ) {
+ e.addCrossReference( new Accession( uniprot.group( 1 ), "uniprot" ) );
+ }
+ final Matcher interpro = interpro_PATTERN.matcher( line );
+ if ( interpro.find() ) {
+ e.addCrossReference( new Accession( interpro.group( 1 ), "interpro" ) );
+ }
+ final Matcher mim = mim_PATTERN.matcher( line );
+ if ( mim.find() ) {
+ e.addCrossReference( new Accession( mim.group( 1 ), "mim" ) );
+ }
+ final Matcher product = product_PATTERN.matcher( line );
+ 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 ) {
- e.setDe( def.toString().trim() );
+ e.setSequenceName( def.toString().trim() );
}
return e;
}
+ private String _map;
+ private String _chromosome;
+
+ private void setMap( String map ) {
+ _map = map;
+
+ }
+
+ private void setChromosome( String chromosome ) {
+ _chromosome = chromosome;
+
+ }
+ @Override
+ public String getMap( ) {
+ return _map;
+
+ }
+ @Override
+ public String getChromosome() {
+ return _chromosome;
+
+ }
+
+
private static void x( final StringBuilder sb, final String s ) {
if ( sb.length() > 0 ) {
sb.append( " " );
}
// FIXME actually this is NCBI entry
//http://www.ebi.ac.uk/Tools/dbfetch/dbfetch/emb/AAR37336/
- private String _pa;
- private String _de;
- private String _os;
- private String _tax_id;
- private String _symbol;
- private String _provider;
- private List<Accession> _cross_references;
- private List<Annotation> _annotations;
- private String _gene_name;
+ private String _pa;
+ private String _de;
+ private String _os;
+ private String _tax_id;
+ private String _symbol;
+ private String _provider;
+ private SortedSet<Accession> _cross_references;
+ private SortedSet<Annotation> _annotations;
+ private String _gene_name;
// TODO PUBMED 15798186
//TODO (FEATURES)
private void addCrossReference( final Accession accession ) {
if ( _cross_references == null ) {
- _cross_references = new ArrayList<Accession>();
+ _cross_references = new TreeSet<Accession>();
}
System.out.println( "XREF ADDED: " + accession );
_cross_references.add( accession );
}
@Override
- public List<Accession> getCrossReferences() {
+ public SortedSet<Accession> getCrossReferences() {
return _cross_references;
}
}
@Override
- public List<GoTerm> getGoTerms() {
+ public SortedSet<GoTerm> getGoTerms() {
return null;
}
return _symbol;
}
+ private void setSequenceSymbol( final String symbol ) {
+ _symbol = symbol;
+ }
+
@Override
public String getTaxonomyIdentifier() {
return _tax_id;
&& ForesterUtil.isEmpty( getTaxonomyIdentifier() ) && ForesterUtil.isEmpty( getSequenceSymbol() ) );
}
- private void setDe( final String rec_name ) {
+ private void setSequenceName( final String rec_name ) {
if ( _de == null ) {
_de = rec_name;
}
}
}
- private void setOs( final String os ) {
+ private void setTaxonomyScientificName( final String os ) {
if ( _os == null ) {
_os = os;
}
}
- private void setPA( final String pa ) {
+ private void setAccession( final String pa ) {
if ( _pa == null ) {
_pa = pa;
}
}
@Override
- public List<Annotation> getAnnotations() {
+ public SortedSet<Annotation> getAnnotations() {
return _annotations;
}
private void addAnnotation( final Annotation annotation ) {
if ( _annotations == null ) {
- _annotations = new ArrayList<Annotation>();
+ _annotations = new TreeSet<Annotation>();
}
_annotations.add( annotation );
}