import java.util.TreeMap;
import java.util.TreeSet;
+import org.forester.phylogeny.Phylogeny;
import org.forester.species.Species;
import org.forester.surfacing.DomainSimilarityCalculator.Detailedness;
import org.forester.util.ForesterUtil;
public class PrintableDomainSimilarity implements DomainSimilarity {
- final public static String SPECIES_SEPARATOR = " ";
- final private static int EQUAL = 0;
- final private static String NO_SPECIES = " ";
- private static final boolean PRINT_MORE_INFO = false;
- final private double _min;
- final private double _max;
- final private double _mean;
- final private double _sd;
- final private int _n;
- private final int _max_difference_in_counts;
- private final int _max_difference;
- final private CombinableDomains _combinable_domains;
- final private SortedMap<Species, SpeciesSpecificDomainSimilariyData> _species_data;
- private List<Species> _species_order;
- private DomainSimilarityCalculator.Detailedness _detailedness;
- private final boolean _treat_as_binary_comparison;
+ final public static String SPECIES_SEPARATOR = " ";
+ final private static int EQUAL = 0;
+ final private static String NO_SPECIES = " ";
+ final private CombinableDomains _combinable_domains;
+ private DomainSimilarityCalculator.Detailedness _detailedness;
+ final private double _max;
+ private final int _max_difference;
+ private final int _max_difference_in_counts;
+ final private double _mean;
+ final private double _min;
+ final private int _n;
+ final private double _sd;
+ final private SortedMap<Species, SpeciesSpecificDcData> _species_data;
+ private List<Species> _species_order;
+ private final boolean _treat_as_binary_comparison;
public PrintableDomainSimilarity( final CombinableDomains combinable_domains,
final double min,
final int n,
final int max_difference_in_counts,
final int max_difference,
- final SortedMap<Species, SpeciesSpecificDomainSimilariyData> species_data,
+ final SortedMap<Species, SpeciesSpecificDcData> species_data,
final boolean sort_by_species_count_first,
final boolean treat_as_binary_comparison ) {
if ( combinable_domains == null ) {
}
}
- private void addSpeciesSpecificDomainData( final StringBuffer sb,
- final Species species,
- final boolean html,
- final Map<String, Integer> tax_code_to_id_map ) {
- if ( html ) {
- addTaxWithLink( sb, species.getSpeciesId(), tax_code_to_id_map );
- }
- else {
- sb.append( species.getSpeciesId() );
- }
- if ( getDetaildness() != DomainSimilarityCalculator.Detailedness.BASIC ) {
- sb.append( ":" );
- sb.append( getSpeciesData().get( species ).toStringBuffer( getDetaildness(), html ) );
- }
- if ( html ) {
- sb.append( "<br>" );
+ public PrintableDomainSimilarity( final CombinableDomains combinable_domains,
+ final int max_difference_in_counts,
+ final int max_difference,
+ final SortedMap<Species, SpeciesSpecificDcData> species_data,
+ final boolean sort_by_species_count_first,
+ final boolean treat_as_binary_comparison ) {
+ if ( combinable_domains == null ) {
+ throw new IllegalArgumentException( "attempt to use null combinable domains" );
}
- else {
- sb.append( PrintableDomainSimilarity.SPECIES_SEPARATOR );
+ if ( species_data == null ) {
+ throw new IllegalArgumentException( "attempt to use null species data" );
}
- }
-
- private void addTaxWithLink( final StringBuffer sb,
- final String tax_code,
- final Map<String, Integer> tax_code_to_id_map ) {
- sb.append( "<b>" );
- if ( !ForesterUtil.isEmpty( tax_code )
- && ( ( tax_code_to_id_map != null ) && tax_code_to_id_map.containsKey( tax_code ) ) ) {
- sb.append( "<a href=\"" + SurfacingConstants.UNIPROT_TAXONOMY_ID_LINK + tax_code_to_id_map.get( tax_code )
- + "\" target=\"taxonomy_window\">" + tax_code + "</a>" );
+ if ( species_data.size() < 1 ) {
+ throw new IllegalArgumentException( "attempt to use empty species data" );
}
- else {
- sb.append( tax_code );
+ init();
+ _combinable_domains = combinable_domains;
+ _min = -1;
+ _max = -1;
+ _mean = -1;
+ _sd = -1;
+ _n = -1;
+ _max_difference_in_counts = max_difference_in_counts;
+ _max_difference = max_difference;
+ _species_data = species_data;
+ _treat_as_binary_comparison = treat_as_binary_comparison;
+ final int s = species_data.size();
+ if ( s > 2 ) {
+ if ( getMaximalDifferenceInCounts() < 0 ) {
+ throw new IllegalArgumentException( "attempt to use negative max difference in counts with more than two species" );
+ }
+ if ( getMaximalDifference() < 0 ) {
+ throw new IllegalArgumentException( "attempt to use negative max difference with more than two species" );
+ }
}
- sb.append( "</b>" );
- }
-
- private int compareByDomainId( final DomainSimilarity other ) {
- return getDomainId().compareToIgnoreCase( other.getDomainId() );
}
@Override
return sorted_ids;
}
- private CombinableDomains getCombinableDomains() {
- return _combinable_domains;
- }
-
- private DomainSimilarityCalculator.Detailedness getDetaildness() {
- return _detailedness;
- }
-
@Override
public String getDomainId() {
return getCombinableDomains().getKeyDomain();
}
@Override
- public SortedMap<Species, SpeciesSpecificDomainSimilariyData> getSpeciesData() {
+ public SortedMap<Species, SpeciesSpecificDcData> getSpeciesData() {
return _species_data;
}
- private StringBuffer getSpeciesDataInAlphabeticalOrder( final boolean html,
- final Map<String, Integer> tax_code_to_id_map ) {
- final StringBuffer sb = new StringBuffer();
- for( final Species species : getSpeciesData().keySet() ) {
- addSpeciesSpecificDomainData( sb, species, html, tax_code_to_id_map );
+ @Override
+ public double getStandardDeviationOfSimilarityScore() {
+ return _sd;
+ }
+
+ public void setDetailedness( final Detailedness detailedness ) {
+ _detailedness = detailedness;
+ }
+
+ public void setSpeciesOrder( final List<Species> species_order ) {
+ if ( !species_order.containsAll( getSpeciesData().keySet() ) ) {
+ throw new IllegalArgumentException( "list to order species must contain all species of multiple combinable domains similarity" );
}
- return sb;
+ _species_order = species_order;
+ }
+
+ @Override
+ public StringBuffer toStringBuffer( final PrintableDomainSimilarity.PRINT_OPTION print_option,
+ final Map<String, Integer> tax_code_to_id_map,
+ final Phylogeny phy ) {
+ switch ( print_option ) {
+ case SIMPLE_TAB_DELIMITED:
+ return toStringBufferSimpleTabDelimited();
+ case HTML:
+ return toStringBufferDetailedHTML( tax_code_to_id_map, phy );
+ default:
+ throw new AssertionError( "Unknown print option: " + print_option );
+ }
+ }
+
+ private void addSpeciesSpecificDomainData( final StringBuffer sb,
+ final Species species,
+ final boolean html,
+ final Map<String, Integer> tax_code_to_id_map,
+ final Phylogeny phy ) {
+ if ( html ) {
+ addTaxWithLink( sb, species.getSpeciesId(), tax_code_to_id_map, phy );
+ }
+ else {
+ sb.append( species.getSpeciesId() );
+ }
+ if ( getDetaildness() != DomainSimilarityCalculator.Detailedness.BASIC ) {
+ if ( html ) {
+ sb.append( ":" );
+ }
+ else {
+ sb.append( "\t" );
+ }
+ sb.append( getSpeciesData().get( species ).toStringBuffer( getDetaildness(), html ) );
+ }
+ if ( html ) {
+ sb.append( "<br>" );
+ }
+ else {
+ sb.append( "\n\t" );
+ }
+ }
+
+ private void addTaxWithLink( final StringBuffer sb,
+ final String tax_code,
+ final Map<String, Integer> tax_code_to_id_map,
+ final Phylogeny phy ) {
+ String hex = null;
+ if ( ( phy != null ) && !phy.isEmpty() ) {
+ hex = SurfacingUtil.obtainHexColorStringDependingOnTaxonomyGroup( tax_code, phy );
+ }
+ sb.append( "<b>" );
+ if ( !ForesterUtil.isEmpty( tax_code )
+ && ( ( tax_code_to_id_map != null ) && tax_code_to_id_map.containsKey( tax_code ) ) ) {
+ if ( !ForesterUtil.isEmpty( hex ) ) {
+ sb.append( "<a href=\"" );
+ sb.append( SurfacingConstants.UNIPROT_TAXONOMY_ID_LINK );
+ sb.append( tax_code_to_id_map.get( tax_code ) );
+ sb.append( "\" target=\"tw\"><span style=\"color:" );
+ sb.append( hex );
+ sb.append( "\">" );
+ sb.append( tax_code );
+ sb.append( "</span></a>" );
+ }
+ else {
+ sb.append( "<a href=\"" );
+ sb.append( SurfacingConstants.UNIPROT_TAXONOMY_ID_LINK );
+ sb.append( tax_code_to_id_map.get( tax_code ) );
+ sb.append( "\" target=\"tw\">" );
+ sb.append( tax_code );
+ sb.append( "</a>" );
+ }
+ }
+ else {
+ sb.append( tax_code );
+ }
+ sb.append( "</b>" );
+ }
+
+ private int compareByDomainId( final DomainSimilarity other ) {
+ return getDomainId().compareToIgnoreCase( other.getDomainId() );
+ }
+
+ private CombinableDomains getCombinableDomains() {
+ return _combinable_domains;
+ }
+
+ private DomainSimilarityCalculator.Detailedness getDetaildness() {
+ return _detailedness;
}
private StringBuffer getDomainDataInAlphabeticalOrder() {
for( final Map.Entry<String, SortedSet<String>> e : m.entrySet() ) {
sb.append( "<a href=\"" + SurfacingConstants.PFAM_FAMILY_ID_LINK + e.getKey() + "\">" + e.getKey() + "</a>" );
sb.append( ": " );
- for( final String s : e.getValue() ) {
- sb.append( s );
+ sb.append( "<span style=\"font-size:7px\">" );
+ for( final String tax : e.getValue() ) {
+ final String hex = SurfacingUtil.obtainHexColorStringDependingOnTaxonomyGroup( tax, null );
+ if ( !ForesterUtil.isEmpty( hex ) ) {
+ sb.append( "<span style=\"color:" );
+ sb.append( hex );
+ sb.append( "\">" );
+ sb.append( tax );
+ sb.append( "</span>" );
+ }
+ else {
+ sb.append( tax );
+ }
sb.append( " " );
}
- sb.append( "<br>" );
+ sb.append( "</span>" );
+ sb.append( "<br>\n" );
}
return sb;
}
- private StringBuffer getSpeciesDataInCustomOrder( final boolean html, final Map<String, Integer> tax_code_to_id_map ) {
+ private StringBuffer getSpeciesDataInAlphabeticalOrder( final boolean html,
+ final Map<String, Integer> tax_code_to_id_map,
+ final Phylogeny phy ) {
+ final StringBuffer sb = new StringBuffer();
+ for( final Species species : getSpeciesData().keySet() ) {
+ addSpeciesSpecificDomainData( sb, species, html, tax_code_to_id_map, phy );
+ }
+ return sb;
+ }
+
+ private StringBuffer getSpeciesDataInCustomOrder( final boolean html,
+ final Map<String, Integer> tax_code_to_id_map,
+ final Phylogeny phy ) {
final StringBuffer sb = new StringBuffer();
for( final Species order_species : getSpeciesCustomOrder() ) {
if ( getSpeciesData().keySet().contains( order_species ) ) {
- addSpeciesSpecificDomainData( sb, order_species, html, tax_code_to_id_map );
+ addSpeciesSpecificDomainData( sb, order_species, html, tax_code_to_id_map, phy );
}
else {
sb.append( PrintableDomainSimilarity.NO_SPECIES );
return sb;
}
- @Override
- public double getStandardDeviationOfSimilarityScore() {
- return _sd;
- }
-
private void init() {
_detailedness = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
}
return _treat_as_binary_comparison;
}
- public void setDetailedness( final Detailedness detailedness ) {
- _detailedness = detailedness;
- }
-
- public void setSpeciesOrder( final List<Species> species_order ) {
- if ( !species_order.containsAll( getSpeciesData().keySet() ) ) {
- throw new IllegalArgumentException( "list to order species must contain all species of multiple combinable domains similarity" );
- }
- _species_order = species_order;
- }
-
- @Override
- public StringBuffer toStringBuffer( final PrintableDomainSimilarity.PRINT_OPTION print_option,
- final Map<String, Integer> tax_code_to_id_map ) {
- switch ( print_option ) {
- case SIMPLE_TAB_DELIMITED:
- return toStringBufferSimpleTabDelimited();
- case HTML:
- return toStringBufferDetailedHTML( tax_code_to_id_map );
- default:
- throw new AssertionError( "Unknown print option: " + print_option );
- }
- }
-
- private StringBuffer toStringBufferDetailedHTML( final Map<String, Integer> tax_code_to_id_map ) {
+ private StringBuffer toStringBufferDetailedHTML( final Map<String, Integer> tax_code_to_id_map, final Phylogeny phy ) {
final StringBuffer sb = new StringBuffer();
sb.append( "<tr>" );
sb.append( "<td>" );
sb.append( "<a href=\"" + SurfacingConstants.GOOGLE_SCHOLAR_SEARCH + getDomainId()
+ "\" target=\"gs_window\">gs</a>" );
sb.append( "</td>" );
- sb.append( "<td>" );
- sb.append( ForesterUtil.round( getMeanSimilarityScore(), 3 ) );
- sb.append( "</td>" );
- if ( PRINT_MORE_INFO ) {
- if ( !isTreatAsBinaryComparison() ) {
- sb.append( "<td>" );
- sb.append( "(" );
- sb.append( ForesterUtil.round( getStandardDeviationOfSimilarityScore(), 3 ) );
- sb.append( ")" );
- sb.append( "</td>" );
- sb.append( "<td>" );
- sb.append( "[" );
- sb.append( ForesterUtil.round( getMinimalSimilarityScore(), 3 ) );
- sb.append( "-" );
- sb.append( ForesterUtil.round( getMaximalSimilarityScore(), 3 ) );
- sb.append( "]" );
- sb.append( "</td>" );
+ if ( getMaximalSimilarityScore() > 0 ) {
+ sb.append( "<td>" );
+ sb.append( ForesterUtil.round( getMeanSimilarityScore(), 3 ) );
+ sb.append( "</td>" );
+ if ( SurfacingConstants.PRINT_MORE_DOM_SIMILARITY_INFO ) {
+ if ( !isTreatAsBinaryComparison() ) {
+ sb.append( "<td>" );
+ sb.append( "(" );
+ sb.append( ForesterUtil.round( getStandardDeviationOfSimilarityScore(), 3 ) );
+ sb.append( ")" );
+ sb.append( "</td>" );
+ sb.append( "<td>" );
+ sb.append( "[" );
+ sb.append( ForesterUtil.round( getMinimalSimilarityScore(), 3 ) );
+ sb.append( "-" );
+ sb.append( ForesterUtil.round( getMaximalSimilarityScore(), 3 ) );
+ sb.append( "]" );
+ sb.append( "</td>" );
+ }
}
}
sb.append( "<td>" );
}
if ( ( getSpeciesCustomOrder() == null ) || getSpeciesCustomOrder().isEmpty() ) {
sb.append( "<td>" );
- sb.append( getSpeciesDataInAlphabeticalOrder( true, tax_code_to_id_map ) );
+ sb.append( getSpeciesDataInAlphabeticalOrder( true, tax_code_to_id_map, phy ) );
sb.append( getDomainDataInAlphabeticalOrder() );
sb.append( "</td>" );
}
else {
sb.append( "<td>" );
- sb.append( getSpeciesDataInCustomOrder( true, tax_code_to_id_map ) );
+ sb.append( getSpeciesDataInCustomOrder( true, tax_code_to_id_map, phy ) );
sb.append( getDomainDataInAlphabeticalOrder() );
sb.append( "</td>" );
}
private StringBuffer toStringBufferSimpleTabDelimited() {
final StringBuffer sb = new StringBuffer();
sb.append( getDomainId() );
+ sb.append( "\t" );
+ sb.append( getSpeciesDataInAlphabeticalOrder( false, null, null ) );
+ sb.append( "\n" );
return sb;
}
public static enum PRINT_OPTION {
- SIMPLE_TAB_DELIMITED, HTML;
+ HTML, SIMPLE_TAB_DELIMITED;
}
}