import java.util.ArrayList;
import java.util.Collection;
import java.util.Date;
-import java.util.Iterator;
import java.util.List;
import java.util.Map;
import java.util.Map.Entry;
import org.forester.phylogeny.data.Distribution;
import org.forester.phylogeny.data.Sequence;
import org.forester.phylogeny.data.Taxonomy;
+import org.forester.protein.BasicProtein;
+import org.forester.protein.Domain;
+import org.forester.protein.Protein;
+import org.forester.surfacing.SurfacingUtil;
public final class ForesterUtil {
public static final String NCBI_PROTEIN = "http://www.ncbi.nlm.nih.gov/protein/";
public static final String NCBI_NUCCORE = "http://www.ncbi.nlm.nih.gov/nuccore/";
public final static String UNIPROT_KB = "http://www.uniprot.org/uniprot/";
- public final static Pattern UNIPROT_KB_PATTERN_1 = Pattern
- .compile( "(?:\\b|_)(?:sp|tr)[\\.|\\-_=/\\\\]([A-Z][0-9][A-Z0-9]{3}[0-9])(?:\\b|_)" );
- public final static Pattern UNIPROT_KB_PATTERN_2 = Pattern
- .compile( "\\b(?:[A-Z0-9]{2,5}|(?:[A-Z][0-9][A-Z0-9]{3}[0-9]))_(([A-Z9][A-Z]{2}[A-Z0-9]{2})|RAT|PIG|PEA)\\b" );
public static final String NCBI_GI = "http://www.ncbi.nlm.nih.gov/protein/gi:";
static {
final DecimalFormatSymbols dfs = new DecimalFormatSymbols();
private ForesterUtil() {
}
- public static String extractRefSeqAccessorAccessor( final PhylogenyNode node ) {
- String v = null;
- if ( node.getNodeData().isHasSequence() ) {
- final Sequence seq = node.getNodeData().getSequence();
- if ( !isEmpty( seq.getSymbol() ) ) {
- v = SequenceIdParser.parseRefSeqAccessor( seq.getSymbol() );
- }
- if ( isEmpty( v ) && !isEmpty( seq.getName() ) ) {
- v = SequenceIdParser.parseRefSeqAccessor( seq.getName() );
- }
- if ( isEmpty( v ) && ( node.getNodeData().getSequence().getAccession() != null )
- && !isEmpty( seq.getAccession().getValue() ) ) {
- v = SequenceIdParser.parseRefSeqAccessor( seq.getAccession().getValue() );
+ public static int calculateOverlap( final Domain domain, final List<Boolean> covered_positions ) {
+ int overlap_count = 0;
+ for( int i = domain.getFrom(); i <= domain.getTo(); ++i ) {
+ if ( ( i < covered_positions.size() ) && ( covered_positions.get( i ) == true ) ) {
+ ++overlap_count;
}
}
- if ( isEmpty( v ) && !isEmpty( node.getName() ) ) {
- v = SequenceIdParser.parseRefSeqAccessor( node.getName() );
- }
- return v;
+ return overlap_count;
}
- public static String extractGenbankAccessor( final PhylogenyNode node ) {
- String v = null;
- if ( node.getNodeData().isHasSequence() ) {
- final Sequence seq = node.getNodeData().getSequence();
- if ( !isEmpty( seq.getSymbol() ) ) {
- v = SequenceIdParser.parseGenbankAccessor( seq.getSymbol() );
- }
- if ( isEmpty( v ) && !isEmpty( seq.getName() ) ) {
- v = SequenceIdParser.parseGenbankAccessor( seq.getName() );
- }
- if ( isEmpty( v ) && ( node.getNodeData().getSequence().getAccession() != null )
- && !isEmpty( seq.getAccession().getValue() ) ) {
- v = SequenceIdParser.parseGenbankAccessor( seq.getAccession().getValue() );
- }
- }
- if ( isEmpty( v ) && !isEmpty( node.getName() ) ) {
- v = SequenceIdParser.parseGenbankAccessor( node.getName() );
- }
- return v;
- }
-
- public static String extractGInumber( final PhylogenyNode node ) {
- String v = null;
- if ( node.getNodeData().isHasSequence() ) {
- final Sequence seq = node.getNodeData().getSequence();
- if ( isEmpty( v ) && !isEmpty( seq.getName() ) ) {
- v = SequenceIdParser.parseGInumber( seq.getName() );
- }
- if ( isEmpty( v ) && ( node.getNodeData().getSequence().getAccession() != null )
- && !isEmpty( seq.getAccession().getValue() ) ) {
- v = SequenceIdParser.parseGInumber( seq.getAccession().getValue() );
- }
- }
- if ( isEmpty( v ) && !isEmpty( node.getName() ) ) {
- v = SequenceIdParser.parseGInumber( node.getName() );
+ final public static void appendSeparatorIfNotEmpty( final StringBuffer sb, final char separator ) {
+ if ( sb.length() > 0 ) {
+ sb.append( separator );
}
- return v;
}
- public static String extractUniProtKbProteinSeqIdentifier( final PhylogenyNode node ) {
- String upkb = null;
- if ( node.getNodeData().isHasSequence() ) {
- final Sequence seq = node.getNodeData().getSequence();
- Matcher m;
- if ( !isEmpty( seq.getSymbol() ) ) {
- m = UNIPROT_KB_PATTERN_1.matcher( seq.getSymbol() );
- if ( m.find() ) {
- upkb = m.group( 1 );
- }
- else {
- m = UNIPROT_KB_PATTERN_2.matcher( seq.getSymbol() );
- if ( m.find() ) {
- upkb = m.group();
- }
- }
- }
- if ( isEmpty( upkb ) && !isEmpty( seq.getName() ) ) {
- m = UNIPROT_KB_PATTERN_1.matcher( seq.getName() );
- if ( m.find() ) {
- upkb = m.group( 1 );
+ /**
+ *
+ * Example regarding engulfment: ------------0.1 ----------0.2 --0.3 =>
+ * domain with 0.3 is ignored
+ *
+ * -----------0.1 ----------0.2 --0.3 => domain with 0.3 is ignored
+ *
+ *
+ * ------------0.1 ----------0.3 --0.2 => domains with 0.3 and 0.2 are _not_
+ * ignored
+ *
+ * @param max_allowed_overlap
+ * maximal allowed overlap (inclusive) to be still considered not
+ * overlapping (zero or negative value to allow any overlap)
+ * @param remove_engulfed_domains
+ * to remove domains which are completely engulfed by coverage of
+ * domains with better support
+ * @param protein
+ * @return
+ */
+ public static Protein removeOverlappingDomains( final int max_allowed_overlap,
+ final boolean remove_engulfed_domains,
+ final Protein protein ) {
+ final Protein pruned_protein = new BasicProtein( protein.getProteinId().getId(), protein.getSpecies()
+ .getSpeciesId(), protein.getLength() );
+ final List<Domain> sorted = SurfacingUtil.sortDomainsWithAscendingConfidenceValues( protein );
+ final List<Boolean> covered_positions = new ArrayList<Boolean>();
+ for( final Domain domain : sorted ) {
+ if ( ( ( max_allowed_overlap < 0 ) || ( ForesterUtil.calculateOverlap( domain, covered_positions ) <= max_allowed_overlap ) )
+ && ( !remove_engulfed_domains || !isEngulfed( domain, covered_positions ) ) ) {
+ final int covered_positions_size = covered_positions.size();
+ for( int i = covered_positions_size; i < domain.getFrom(); ++i ) {
+ covered_positions.add( false );
}
- else {
- m = UNIPROT_KB_PATTERN_2.matcher( seq.getName() );
- if ( m.find() ) {
- upkb = m.group();
+ final int new_covered_positions_size = covered_positions.size();
+ for( int i = domain.getFrom(); i <= domain.getTo(); ++i ) {
+ if ( i < new_covered_positions_size ) {
+ covered_positions.set( i, true );
}
- }
- }
- if ( isEmpty( upkb ) && ( node.getNodeData().getSequence().getAccession() != null )
- && !isEmpty( seq.getAccession().getValue() ) ) {
- m = UNIPROT_KB_PATTERN_1.matcher( seq.getAccession().getValue() );
- if ( m.find() ) {
- upkb = m.group( 1 );
- }
- else {
- m = UNIPROT_KB_PATTERN_2.matcher( seq.getAccession().getValue() );
- if ( m.find() ) {
- upkb = m.group();
+ else {
+ covered_positions.add( true );
}
}
+ pruned_protein.addProteinDomain( domain );
}
}
- if ( isEmpty( upkb ) && !isEmpty( node.getName() ) ) {
- final Matcher m1 = UNIPROT_KB_PATTERN_1.matcher( node.getName() );
- if ( m1.find() ) {
- upkb = m1.group( 1 );
- }
- else {
- final Matcher m2 = UNIPROT_KB_PATTERN_2.matcher( node.getName() );
- if ( m2.find() ) {
- upkb = m2.group();
- }
- }
- }
- return upkb;
+ return pruned_protein;
}
- final public static void appendSeparatorIfNotEmpty( final StringBuffer sb, final char separator ) {
- if ( sb.length() > 0 ) {
- sb.append( separator );
+ /**
+ * Returns true is Domain domain falls in an uninterrupted stretch of
+ * covered positions.
+ *
+ * @param domain
+ * @param covered_positions
+ * @return
+ */
+ public static boolean isEngulfed( final Domain domain, final List<Boolean> covered_positions ) {
+ for( int i = domain.getFrom(); i <= domain.getTo(); ++i ) {
+ if ( ( i >= covered_positions.size() ) || ( covered_positions.get( i ) != true ) ) {
+ return false;
+ }
}
+ return true;
}
/**
return i;
}
- final public static SortedMap<Object, Integer> listToSortedCountsMap( final List list ) {
+ final public static SortedMap<Object, Integer> listToSortedCountsMap( final List<?> list ) {
final SortedMap<Object, Integer> map = new TreeMap<Object, Integer>();
for( final Object key : list ) {
if ( !map.containsKey( key ) ) {
}
}
- final public static StringBuffer mapToStringBuffer( final Map map, final String key_value_separator ) {
+ final public static StringBuffer mapToStringBuffer( final Map<Object, Object> map, final String key_value_separator ) {
final StringBuffer sb = new StringBuffer();
- for( final Iterator iter = map.keySet().iterator(); iter.hasNext(); ) {
- final Object key = iter.next();
+ for( final Object key : map.keySet() ) {
sb.append( key.toString() );
sb.append( key_value_separator );
sb.append( map.get( key ).toString() );
System.err.println();
System.exit( -1 );
}
+
+ public final static Color obtainColorDependingOnTaxonomyGroup( final String tax_group ) {
+ if ( !ForesterUtil.isEmpty( tax_group ) ) {
+ if ( tax_group.equals( "deuterostomia" ) ) {
+ return TaxonomyColors.DEUTEROSTOMIA_COLOR;
+ }
+ else if ( tax_group.equals( "protostomia" ) ) {
+ return TaxonomyColors.PROTOSTOMIA_COLOR;
+ }
+ else if ( tax_group.equals( "cnidaria" ) ) {
+ return TaxonomyColors.CNIDARIA_COLOR;
+ }
+ else if ( tax_group.equals( "placozoa" ) ) {
+ return TaxonomyColors.PLACOZOA_COLOR;
+ }
+ else if ( tax_group.equals( "ctenophora" ) ) {
+ return TaxonomyColors.CTENOPHORA_COLOR;
+ }
+ else if ( tax_group.equals( "porifera" ) ) {
+ return TaxonomyColors.PORIFERA_COLOR;
+ }
+ else if ( tax_group.equals( "choanoflagellida" ) ) {
+ return TaxonomyColors.CHOANOFLAGELLIDA;
+ }
+ else if ( tax_group.equals( "ichthyophonida & filasterea" ) ) {
+ return TaxonomyColors.ICHTHYOSPOREA_AND_FILASTEREA;
+ }
+ else if ( tax_group.equals( "dikarya" ) ) {
+ return TaxonomyColors.DIKARYA_COLOR;
+ }
+ else if ( tax_group.equalsIgnoreCase( "fungi" ) || tax_group.equalsIgnoreCase( "other fungi" ) ) {
+ return TaxonomyColors.OTHER_FUNGI_COLOR;
+ }
+ else if ( tax_group.equals( "nucleariidae and fonticula" ) ) {
+ return TaxonomyColors.NUCLEARIIDAE_AND_FONTICULA_GROUP_COLOR;
+ }
+ else if ( tax_group.equals( "amoebozoa" ) ) {
+ return TaxonomyColors.AMOEBOZOA_COLOR;
+ }
+ else if ( tax_group.equals( "embryophyta" ) ) {
+ return TaxonomyColors.EMBRYOPHYTA_COLOR;
+ }
+ else if ( tax_group.equals( "chlorophyta" ) ) {
+ return TaxonomyColors.CHLOROPHYTA_COLOR;
+ }
+ else if ( tax_group.equals( "rhodophyta" ) ) {
+ return TaxonomyColors.RHODOPHYTA_COLOR;
+ }
+ else if ( tax_group.equals( "hacrobia" ) ) {
+ return TaxonomyColors.HACROBIA_COLOR;
+ }
+ else if ( tax_group.equals( "glaucocystophyceae" ) ) {
+ return TaxonomyColors.GLAUCOPHYTA_COLOR;
+ }
+ else if ( tax_group.equals( "stramenopiles" ) ) {
+ return TaxonomyColors.STRAMENOPILES_COLOR;
+ }
+ else if ( tax_group.equals( "alveolata" ) ) {
+ return TaxonomyColors.ALVEOLATA_COLOR;
+ }
+ else if ( tax_group.equals( "rhizaria" ) ) {
+ return TaxonomyColors.RHIZARIA_COLOR;
+ }
+ else if ( tax_group.equals( "excavata" ) ) {
+ return TaxonomyColors.EXCAVATA_COLOR;
+ }
+ else if ( tax_group.equals( "apusozoa" ) ) {
+ return TaxonomyColors.APUSOZOA_COLOR;
+ }
+ else if ( tax_group.equals( "archaea" ) ) {
+ return TaxonomyColors.ARCHAEA_COLOR;
+ }
+ else if ( tax_group.equals( "bacteria" ) ) {
+ return TaxonomyColors.BACTERIA_COLOR;
+ }
+ }
+ return null;
+ }
+
+ public final static String obtainNormalizedTaxonomyGroup( final String tax ) {
+ if ( tax.equalsIgnoreCase( "deuterostomia" ) ) {
+ return "deuterostomia";
+ }
+ else if ( tax.equalsIgnoreCase( "protostomia" ) ) {
+ return "protostomia";
+ }
+ else if ( tax.equalsIgnoreCase( "cnidaria" ) ) {
+ return "cnidaria";
+ }
+ else if ( tax.toLowerCase().startsWith( "trichoplax" ) || tax.equalsIgnoreCase( "placozoa" ) ) {
+ return "placozoa";
+ }
+ else if ( tax.toLowerCase().startsWith( "mnemiopsis" ) || tax.equalsIgnoreCase( "ctenophora" ) ) {
+ return "ctenophora";
+ }
+ else if ( tax.toLowerCase().startsWith( "amphimedon" ) || tax.equalsIgnoreCase( "porifera" ) ) {
+ return "porifera";
+ }
+ else if ( tax.equalsIgnoreCase( "codonosigidae" ) || tax.equalsIgnoreCase( "choanoflagellida" ) ) {
+ return "choanoflagellida";
+ }
+ else if ( tax.toLowerCase().startsWith( "ichthyophonida & filasterea" )
+ || tax.toLowerCase().startsWith( "ichthyophonida and filasterea" )
+ || tax.toLowerCase().startsWith( "ichthyosporea & filasterea" )
+ || tax.toLowerCase().startsWith( "ichthyosporea and filasterea" ) ) {
+ return "ichthyophonida & filasterea";
+ }
+ else if ( tax.equalsIgnoreCase( "dikarya" ) ) {
+ return "dikarya";
+ }
+ else if ( tax.equalsIgnoreCase( "other fungi" ) ) {
+ return "other fungi";
+ }
+ else if ( tax.toLowerCase().startsWith( "nucleariidae and fonticula" ) ) {
+ return "nucleariidae and fonticula group";
+ }
+ else if ( tax.equalsIgnoreCase( "amoebozoa" ) ) {
+ return "amoebozoa";
+ }
+ else if ( tax.equalsIgnoreCase( "embryophyta" ) ) {
+ return "embryophyta";
+ }
+ else if ( tax.equalsIgnoreCase( "chlorophyta" ) ) {
+ return "chlorophyta";
+ }
+ else if ( tax.equalsIgnoreCase( "rhodophyta" ) ) {
+ return "rhodophyta";
+ }
+ else if ( tax.toLowerCase().startsWith( "hacrobia" ) ) {
+ return "hacrobia";
+ }
+ else if ( tax.equalsIgnoreCase( "glaucocystophyceae" ) || tax.equalsIgnoreCase( "glaucophyta" ) ) {
+ return "glaucocystophyceae";
+ }
+ else if ( tax.equalsIgnoreCase( "stramenopiles" ) ) {
+ return "stramenopiles";
+ }
+ else if ( tax.equalsIgnoreCase( "alveolata" ) ) {
+ return "alveolata";
+ }
+ else if ( tax.equalsIgnoreCase( "rhizaria" ) ) {
+ return "rhizaria";
+ }
+ else if ( tax.equalsIgnoreCase( "excavata" ) ) {
+ return "excavata";
+ }
+ else if ( tax.equalsIgnoreCase( "apusozoa" ) ) {
+ return "apusozoa";
+ }
+ else if ( tax.equalsIgnoreCase( "archaea" ) ) {
+ return "archaea";
+ }
+ else if ( tax.equalsIgnoreCase( "bacteria" ) ) {
+ return "bacteria";
+ }
+ return null;
+ }
}
git://source.jalview.org / jalview.git / blobdiff