import java.text.DecimalFormat;
import java.text.NumberFormat;
import java.util.ArrayList;
+import java.util.Arrays;
import java.util.Collections;
import java.util.Comparator;
import java.util.HashMap;
import java.util.HashSet;
import java.util.List;
import java.util.Map;
+import java.util.PriorityQueue;
import java.util.Set;
import java.util.SortedMap;
import java.util.SortedSet;
import org.forester.go.GoId;
import org.forester.go.GoNameSpace;
import org.forester.go.GoTerm;
-import org.forester.go.GoUtils;
import org.forester.go.PfamToGoMapping;
import org.forester.io.parsers.nexus.NexusConstants;
import org.forester.io.writers.PhylogenyWriter;
import org.forester.phylogeny.Phylogeny;
import org.forester.phylogeny.PhylogenyMethods;
import org.forester.phylogeny.PhylogenyNode;
+import org.forester.phylogeny.PhylogenyNodeI.NH_CONVERSION_SUPPORT_VALUE_STYLE;
import org.forester.phylogeny.data.BinaryCharacters;
import org.forester.phylogeny.data.Confidence;
import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
return stats;
}
+ private static void calculateIndependentDomainCombinationGains( final Phylogeny local_phylogeny_l,
+ final String outfilename_for_counts,
+ final String outfilename_for_dc,
+ final String outfilename_for_dc_for_go_mapping,
+ final String outfilename_for_dc_for_go_mapping_unique,
+ final String outfilename_for_rank_counts,
+ final String outfilename_for_ancestor_species_counts ) {
+ try {
+ final BufferedWriter out_counts = new BufferedWriter( new FileWriter( outfilename_for_counts ) );
+ final BufferedWriter out_dc = new BufferedWriter( new FileWriter( outfilename_for_dc ) );
+ final BufferedWriter out_dc_for_go_mapping = new BufferedWriter( new FileWriter( outfilename_for_dc_for_go_mapping ) );
+ final BufferedWriter out_dc_for_go_mapping_unique = new BufferedWriter( new FileWriter( outfilename_for_dc_for_go_mapping_unique ) );
+ final SortedMap<String, Integer> dc_gain_counts = new TreeMap<String, Integer>();
+ for( final PhylogenyNodeIterator it = local_phylogeny_l.iteratorPostorder(); it.hasNext(); ) {
+ final PhylogenyNode n = it.next();
+ final Set<String> gained_dc = n.getNodeData().getBinaryCharacters().getGainedCharacters();
+ for( final String dc : gained_dc ) {
+ if ( dc_gain_counts.containsKey( dc ) ) {
+ dc_gain_counts.put( dc, dc_gain_counts.get( dc ) + 1 );
+ }
+ else {
+ dc_gain_counts.put( dc, 1 );
+ }
+ }
+ }
+ final SortedMap<Integer, Integer> histogram = new TreeMap<Integer, Integer>();
+ final SortedMap<Integer, StringBuilder> domain_lists = new TreeMap<Integer, StringBuilder>();
+ final SortedMap<Integer, PriorityQueue<String>> domain_lists_go = new TreeMap<Integer, PriorityQueue<String>>();
+ final SortedMap<Integer, SortedSet<String>> domain_lists_go_unique = new TreeMap<Integer, SortedSet<String>>();
+ final Set<String> dcs = dc_gain_counts.keySet();
+ final SortedSet<String> more_than_once = new TreeSet<String>();
+ for( final String dc : dcs ) {
+ final int count = dc_gain_counts.get( dc );
+ if ( histogram.containsKey( count ) ) {
+ histogram.put( count, histogram.get( count ) + 1 );
+ domain_lists.get( count ).append( ", " + dc );
+ domain_lists_go.get( count ).addAll( splitDomainCombination( dc ) );
+ domain_lists_go_unique.get( count ).addAll( splitDomainCombination( dc ) );
+ }
+ else {
+ histogram.put( count, 1 );
+ domain_lists.put( count, new StringBuilder( dc ) );
+ final PriorityQueue<String> q = new PriorityQueue<String>();
+ q.addAll( splitDomainCombination( dc ) );
+ domain_lists_go.put( count, q );
+ final SortedSet<String> set = new TreeSet<String>();
+ set.addAll( splitDomainCombination( dc ) );
+ domain_lists_go_unique.put( count, set );
+ }
+ if ( count > 1 ) {
+ more_than_once.add( dc );
+ }
+ }
+ final Set<Integer> histogram_keys = histogram.keySet();
+ for( final Integer histogram_key : histogram_keys ) {
+ final int count = histogram.get( histogram_key );
+ final StringBuilder dc = domain_lists.get( histogram_key );
+ out_counts.write( histogram_key + "\t" + count + ForesterUtil.LINE_SEPARATOR );
+ out_dc.write( histogram_key + "\t" + dc + ForesterUtil.LINE_SEPARATOR );
+ out_dc_for_go_mapping.write( "#" + histogram_key + ForesterUtil.LINE_SEPARATOR );
+ final Object[] sorted = domain_lists_go.get( histogram_key ).toArray();
+ Arrays.sort( sorted );
+ for( final Object domain : sorted ) {
+ out_dc_for_go_mapping.write( domain + ForesterUtil.LINE_SEPARATOR );
+ }
+ out_dc_for_go_mapping_unique.write( "#" + histogram_key + ForesterUtil.LINE_SEPARATOR );
+ for( final String domain : domain_lists_go_unique.get( histogram_key ) ) {
+ out_dc_for_go_mapping_unique.write( domain + ForesterUtil.LINE_SEPARATOR );
+ }
+ }
+ out_counts.close();
+ out_dc.close();
+ out_dc_for_go_mapping.close();
+ out_dc_for_go_mapping_unique.close();
+ //
+ final SortedMap<String, Integer> lca_rank_counts = new TreeMap<String, Integer>();
+ final SortedMap<String, Integer> lca_ancestor_species_counts = new TreeMap<String, Integer>();
+ for( final String dc : more_than_once ) {
+ final List<PhylogenyNode> nodes = new ArrayList<PhylogenyNode>();
+ for( final PhylogenyNodeIterator it = local_phylogeny_l.iteratorExternalForward(); it.hasNext(); ) {
+ final PhylogenyNode n = it.next();
+ if ( n.getNodeData().getBinaryCharacters().getGainedCharacters().contains( dc ) ) {
+ nodes.add( n );
+ }
+ }
+ for( int i = 0; i < nodes.size() - 1; ++i ) {
+ for( int j = i + 1; j < nodes.size(); ++j ) {
+ final PhylogenyNode lca = PhylogenyMethods.getInstance().obtainLCA( nodes.get( i ),
+ nodes.get( j ) );
+ String rank = "unknown";
+ if ( lca.getNodeData().isHasTaxonomy()
+ && !ForesterUtil.isEmpty( lca.getNodeData().getTaxonomy().getRank() ) ) {
+ rank = lca.getNodeData().getTaxonomy().getRank();
+ }
+ addToCountMap( lca_rank_counts, rank );
+ String lca_species;
+ if ( lca.getNodeData().isHasTaxonomy()
+ && !ForesterUtil.isEmpty( lca.getNodeData().getTaxonomy().getScientificName() ) ) {
+ lca_species = lca.getNodeData().getTaxonomy().getScientificName();
+ }
+ else if ( lca.getNodeData().isHasTaxonomy()
+ && !ForesterUtil.isEmpty( lca.getNodeData().getTaxonomy().getCommonName() ) ) {
+ lca_species = lca.getNodeData().getTaxonomy().getCommonName();
+ }
+ else {
+ lca_species = lca.getName();
+ }
+ addToCountMap( lca_ancestor_species_counts, lca_species );
+ }
+ }
+ }
+ final BufferedWriter out_for_rank_counts = new BufferedWriter( new FileWriter( outfilename_for_rank_counts ) );
+ final BufferedWriter out_for_ancestor_species_counts = new BufferedWriter( new FileWriter( outfilename_for_ancestor_species_counts ) );
+ ForesterUtil.map2writer( out_for_rank_counts, lca_rank_counts, "\t", ForesterUtil.LINE_SEPARATOR );
+ ForesterUtil.map2writer( out_for_ancestor_species_counts,
+ lca_ancestor_species_counts,
+ "\t",
+ ForesterUtil.LINE_SEPARATOR );
+ out_for_rank_counts.close();
+ out_for_ancestor_species_counts.close();
+ }
+ catch ( final IOException e ) {
+ ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "Failure to write: " + e );
+ }
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote independent domain combination gains fitch counts to ["
+ + outfilename_for_counts + "]" );
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote independent domain combination gains fitch lists to ["
+ + outfilename_for_dc + "]" );
+ ForesterUtil.programMessage( surfacing.PRG_NAME,
+ "Wrote independent domain combination gains fitch lists to (for GO mapping) ["
+ + outfilename_for_dc_for_go_mapping + "]" );
+ ForesterUtil.programMessage( surfacing.PRG_NAME,
+ "Wrote independent domain combination gains fitch lists to (for GO mapping, unique) ["
+ + outfilename_for_dc_for_go_mapping_unique + "]" );
+ }
+
+ private final static void addToCountMap( final Map<String, Integer> map, final String s ) {
+ if ( map.containsKey( s ) ) {
+ map.put( s, map.get( s ) + 1 );
+ }
+ else {
+ map.put( s, 1 );
+ }
+ }
+
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 ) {
randomization = "yes, seed = " + random_number_seed_for_fitch_parsimony;
}
else {
- domain_parsimony.executeFitchParsimonyOnBinaryDomainCombintion( false );
+ domain_parsimony.executeFitchParsimonyOnBinaryDomainCombintion( true );
}
SurfacingUtil.writeMatrixToFile( domain_parsimony.getGainLossMatrix(), outfile_name
+ surfacing.PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_BINARY_COMBINATIONS, Format.FORESTER );
+ surfacing.BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH );
calculateIndependentDomainCombinationGains( local_phylogeny_l, outfile_name
+ surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_OUTPUT_SUFFIX, outfile_name
- + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_OUTPUT_SUFFIX );
- }
- }
-
- private static void calculateIndependentDomainCombinationGains( final Phylogeny local_phylogeny_l,
- final String outfilename_for_counts,
- final String outfilename_for_dc ) {
- try {
- final BufferedWriter out_counts = new BufferedWriter( new FileWriter( outfilename_for_counts ) );
- final BufferedWriter out_dc = new BufferedWriter( new FileWriter( outfilename_for_dc ) );
- final SortedMap<String, Integer> dc_gain_counts = new TreeMap<String, Integer>();
- for( final PhylogenyNodeIterator it = local_phylogeny_l.iteratorPostorder(); it.hasNext(); ) {
- final PhylogenyNode n = it.next();
- final Set<String> gained_dc = n.getNodeData().getBinaryCharacters().getGainedCharacters();
- for( final String dc : gained_dc ) {
- if ( dc_gain_counts.containsKey( dc ) ) {
- dc_gain_counts.put( dc, dc_gain_counts.get( dc ) + 1 );
- }
- else {
- dc_gain_counts.put( dc, 1 );
- }
- }
- }
- final SortedMap<Integer, Integer> histogram = new TreeMap<Integer, Integer>();
- final SortedMap<Integer, StringBuilder> domain_lists = new TreeMap<Integer, StringBuilder>();
- final Set<String> dcs = dc_gain_counts.keySet();
- for( final String dc : dcs ) {
- final int count = dc_gain_counts.get( dc );
- if ( histogram.containsKey( count ) ) {
- histogram.put( count, histogram.get( count ) + 1 );
- domain_lists.put( count, domain_lists.get( count ).append( ", " + dc ) );
- }
- else {
- histogram.put( count, 1 );
- domain_lists.put( count, new StringBuilder( dc ) );
- }
- }
- final Set<Integer> histogram_keys = histogram.keySet();
- for( final Integer histogram_key : histogram_keys ) {
- final int count = histogram.get( histogram_key );
- final StringBuilder dc = domain_lists.get( histogram_key );
- out_counts.write( histogram_key + "\t" + count + ForesterUtil.LINE_SEPARATOR );
- out_dc.write( histogram_key + "\t" + dc + ForesterUtil.LINE_SEPARATOR );
- }
- out_counts.close();
- out_dc.close();
- }
- catch ( final IOException e ) {
- ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "Failure to write: " + e );
+ + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_OUTPUT_SUFFIX, outfile_name
+ + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_SUFFIX, outfile_name
+ + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_UNIQUE_SUFFIX, outfile_name
+ + "_indep_dc_gains_fitch_lca_ranks.txt", outfile_name + "_indep_dc_gains_fitch_lca_taxonomies.txt" );
}
- ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote independent domain combination gains fitch counts to ["
- + outfilename_for_counts + "]" );
- ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote independent domain combination gains fitch lists to ["
- + outfilename_for_dc + "]" );
}
public static void executeParsimonyAnalysisForSecondaryFeatures( final String outfile_name,
final PhylogenyNode n = it.next();
if ( ForesterUtil.isEmpty( n.getName() )
&& ( !n.getNodeData().isHasTaxonomy() || ForesterUtil.isEmpty( n.getNodeData().getTaxonomy()
- .getScientificName() ) ) ) {
+ .getScientificName() ) )
+ && ( !n.getNodeData().isHasTaxonomy() || ForesterUtil.isEmpty( n.getNodeData().getTaxonomy()
+ .getCommonName() ) ) ) {
if ( n.getParent() != null ) {
names.append( " " );
names.append( n.getParent().getName() );
}
+ final List l = n.getAllExternalDescendants();
+ for( final Object object : l ) {
+ System.out.println( l.toString() );
+ }
++c;
}
}
p.setRooted( true );
}
+ /*
+ * species | protein id | n-terminal domain | c-terminal domain | n-terminal domain per domain E-value | c-terminal domain per domain E-value
+ *
+ *
+ */
+ static public StringBuffer proteinToDomainCombinations( final Protein protein,
+ final String protein_id,
+ final String separator ) {
+ final StringBuffer sb = new StringBuffer();
+ if ( protein.getSpecies() == null ) {
+ throw new IllegalArgumentException( "species must not be null" );
+ }
+ if ( ForesterUtil.isEmpty( protein.getSpecies().getSpeciesId() ) ) {
+ throw new IllegalArgumentException( "species id must not be empty" );
+ }
+ final List<Domain> domains = protein.getProteinDomains();
+ if ( domains.size() > 1 ) {
+ final Map<String, Integer> counts = new HashMap<String, Integer>();
+ for( final Domain domain : domains ) {
+ final String id = domain.getDomainId().getId();
+ if ( counts.containsKey( id ) ) {
+ counts.put( id, counts.get( id ) + 1 );
+ }
+ else {
+ counts.put( id, 1 );
+ }
+ }
+ final Set<String> dcs = new HashSet<String>();
+ for( int i = 1; i < domains.size(); ++i ) {
+ for( int j = 0; j < i; ++j ) {
+ Domain domain_n = domains.get( i );
+ Domain domain_c = domains.get( j );
+ if ( domain_n.getFrom() > domain_c.getFrom() ) {
+ domain_n = domains.get( j );
+ domain_c = domains.get( i );
+ }
+ final String dc = domain_n.getDomainId().getId() + domain_c.getDomainId().getId();
+ if ( !dcs.contains( dc ) ) {
+ dcs.add( dc );
+ sb.append( protein.getSpecies() );
+ sb.append( separator );
+ sb.append( protein_id );
+ sb.append( separator );
+ sb.append( domain_n.getDomainId().getId() );
+ sb.append( separator );
+ sb.append( domain_c.getDomainId().getId() );
+ sb.append( separator );
+ sb.append( domain_n.getPerDomainEvalue() );
+ sb.append( separator );
+ sb.append( domain_c.getPerDomainEvalue() );
+ sb.append( separator );
+ sb.append( counts.get( domain_n.getDomainId().getId() ) );
+ sb.append( separator );
+ sb.append( counts.get( domain_c.getDomainId().getId() ) );
+ sb.append( ForesterUtil.LINE_SEPARATOR );
+ }
+ }
+ }
+ }
+ else if ( domains.size() == 1 ) {
+ sb.append( protein.getSpecies() );
+ sb.append( separator );
+ sb.append( protein_id );
+ sb.append( separator );
+ sb.append( domains.get( 0 ).getDomainId().getId() );
+ sb.append( separator );
+ sb.append( separator );
+ sb.append( domains.get( 0 ).getPerDomainEvalue() );
+ sb.append( separator );
+ sb.append( separator );
+ sb.append( 1 );
+ sb.append( separator );
+ sb.append( ForesterUtil.LINE_SEPARATOR );
+ }
+ else {
+ sb.append( protein.getSpecies() );
+ sb.append( separator );
+ sb.append( protein_id );
+ sb.append( separator );
+ sb.append( separator );
+ sb.append( separator );
+ sb.append( separator );
+ sb.append( separator );
+ sb.append( separator );
+ sb.append( ForesterUtil.LINE_SEPARATOR );
+ }
+ return sb;
+ }
+
/**
*
* Example regarding engulfment: ------------0.1 ----------0.2 --0.3 =>
return pruned_protein;
}
- static List<Domain> sortDomainsWithAscendingConfidenceValues( final Protein protein ) {
+ public static List<Domain> sortDomainsWithAscendingConfidenceValues( final Protein protein ) {
final List<Domain> domains = new ArrayList<Domain>();
for( final Domain d : protein.getProteinDomains() ) {
domains.add( d );
return domains;
}
+ private static List<String> splitDomainCombination( final String dc ) {
+ final String[] s = dc.split( "=" );
+ if ( s.length != 2 ) {
+ ForesterUtil.printErrorMessage( surfacing.PRG_NAME, "Stringyfied domain combination has illegal format: "
+ + dc );
+ System.exit( -1 );
+ }
+ final List<String> l = new ArrayList<String>( 2 );
+ l.add( s[ 0 ] );
+ l.add( s[ 1 ] );
+ return l;
+ }
+
public static void writeAllDomainsChangedOnAllSubtrees( final Phylogeny p,
final boolean get_gains,
final String outdir,
+ input_file_properties[ i ][ 2 ] + ") to: \"" + dc_outfile_dot + "\"" );
}
- /*
- * species | protein id | n-terminal domain | c-terminal domain | n-terminal domain per domain E-value | c-terminal domain per domain E-value
- *
- *
- */
- static public StringBuffer proteinToDomainCombinations( final Protein protein,
- final String protein_id,
- final String separator ) {
- final StringBuffer sb = new StringBuffer();
- if ( protein.getSpecies() == null ) {
- throw new IllegalArgumentException( "species must not be null" );
- }
- if ( ForesterUtil.isEmpty( protein.getSpecies().getSpeciesId() ) ) {
- throw new IllegalArgumentException( "species id must not be empty" );
- }
- final List<Domain> domains = protein.getProteinDomains();
- if ( domains.size() > 1 ) {
- final Map<String, Integer> counts = new HashMap<String, Integer>();
- for( final Domain domain : domains ) {
- final String id = domain.getDomainId().getId();
- if ( counts.containsKey( id ) ) {
- counts.put( id, counts.get( id ) + 1 );
- }
- else {
- counts.put( id, 1 );
- }
- }
- final Set<String> dcs = new HashSet<String>();
- for( int i = 1; i < domains.size(); ++i ) {
- for( int j = 0; j < i; ++j ) {
- Domain domain_n = domains.get( i );
- Domain domain_c = domains.get( j );
- if ( domain_n.getFrom() > domain_c.getFrom() ) {
- domain_n = domains.get( j );
- domain_c = domains.get( i );
- }
- final String dc = domain_n.getDomainId().getId() + domain_c.getDomainId().getId();
- if ( !dcs.contains( dc ) ) {
- dcs.add( dc );
- sb.append( protein.getSpecies() );
- sb.append( separator );
- sb.append( protein_id );
- sb.append( separator );
- sb.append( domain_n.getDomainId().getId() );
- sb.append( separator );
- sb.append( domain_c.getDomainId().getId() );
- sb.append( separator );
- sb.append( domain_n.getPerDomainEvalue() );
- sb.append( separator );
- sb.append( domain_c.getPerDomainEvalue() );
- sb.append( separator );
- sb.append( counts.get( domain_n.getDomainId().getId() ) );
- sb.append( separator );
- sb.append( counts.get( domain_c.getDomainId().getId() ) );
- sb.append( ForesterUtil.LINE_SEPARATOR );
- }
- }
- }
- }
- else if ( domains.size() == 1 ) {
- sb.append( protein.getSpecies() );
- sb.append( separator );
- sb.append( protein_id );
- sb.append( separator );
- sb.append( domains.get( 0 ).getDomainId().getId() );
- sb.append( separator );
- sb.append( separator );
- sb.append( domains.get( 0 ).getPerDomainEvalue() );
- sb.append( separator );
- sb.append( separator );
- sb.append( 1 );
- sb.append( separator );
- sb.append( ForesterUtil.LINE_SEPARATOR );
- }
- else {
- sb.append( protein.getSpecies() );
- sb.append( separator );
- sb.append( protein_id );
- sb.append( separator );
- sb.append( separator );
- sb.append( separator );
- sb.append( separator );
- sb.append( separator );
- sb.append( separator );
- sb.append( ForesterUtil.LINE_SEPARATOR );
- }
- return sb;
- }
-
- public static void writeBinaryStatesMatrixAsListToFile( final CharacterStateMatrix<CharacterStateMatrix.GainLossStates> matrix,
- final CharacterStateMatrix.GainLossStates state,
- final String filename,
- final String indentifier_characters_separator,
- final String character_separator,
- final Map<String, String> descriptions ) {
- final File outfile = new File( filename );
- checkForOutputFileWriteability( outfile );
- final SortedSet<String> sorted_ids = new TreeSet<String>();
- for( int i = 0; i < matrix.getNumberOfIdentifiers(); ++i ) {
- sorted_ids.add( matrix.getIdentifier( i ) );
+ public static void writeBinaryStatesMatrixAsListToFile( final CharacterStateMatrix<CharacterStateMatrix.GainLossStates> matrix,
+ final CharacterStateMatrix.GainLossStates state,
+ final String filename,
+ final String indentifier_characters_separator,
+ final String character_separator,
+ final Map<String, String> descriptions ) {
+ final File outfile = new File( filename );
+ checkForOutputFileWriteability( outfile );
+ final SortedSet<String> sorted_ids = new TreeSet<String>();
+ for( int i = 0; i < matrix.getNumberOfIdentifiers(); ++i ) {
+ sorted_ids.add( matrix.getIdentifier( i ) );
}
try {
final BufferedWriter out = new BufferedWriter( new FileWriter( outfile ) );
}
}
- private static void writeDomainDataORIG( final Map<DomainId, List<GoId>> domain_id_to_go_ids_map,
- final Map<GoId, GoTerm> go_id_to_term_map,
- final GoNameSpace go_namespace_limit,
- final Writer out,
- final String domain_0,
- final String domain_1,
- final String prefix_for_html,
- final String character_separator_for_non_html_output,
- final Map<DomainId, Set<String>>[] domain_id_to_secondary_features_maps,
- final Set<GoId> all_go_ids ) throws IOException {
- boolean any_go_annotation_present = false;
- boolean first_has_no_go = false;
- int domain_count = 2; // To distinguish between domains and binary domain combinations.
- if ( ForesterUtil.isEmpty( domain_1 ) ) {
- domain_count = 1;
- }
- // The following has a difficult to understand logic.
- for( int d = 0; d < domain_count; ++d ) {
- List<GoId> go_ids = null;
- boolean go_annotation_present = false;
- if ( d == 0 ) {
- final DomainId domain_id = new DomainId( domain_0 );
- if ( domain_id_to_go_ids_map.containsKey( domain_id ) ) {
- go_annotation_present = true;
- any_go_annotation_present = true;
- go_ids = domain_id_to_go_ids_map.get( domain_id );
- }
- else {
- first_has_no_go = true;
- }
- }
- else {
- final DomainId domain_id = new DomainId( domain_1 );
- if ( domain_id_to_go_ids_map.containsKey( domain_id ) ) {
- go_annotation_present = true;
- any_go_annotation_present = true;
- go_ids = domain_id_to_go_ids_map.get( domain_id );
- }
- }
- if ( go_annotation_present ) {
- boolean first = ( ( d == 0 ) || ( ( d == 1 ) && first_has_no_go ) );
- for( final GoId go_id : go_ids ) {
- out.write( "<tr>" );
- if ( first ) {
- first = false;
- writeDomainIdsToHtml( out,
- domain_0,
- domain_1,
- prefix_for_html,
- domain_id_to_secondary_features_maps );
- }
- else {
- out.write( "<td></td>" );
- }
- if ( !go_id_to_term_map.containsKey( go_id ) ) {
- throw new IllegalArgumentException( "GO-id [" + go_id + "] not found in GO-id to GO-term map" );
- }
- final GoTerm go_term = go_id_to_term_map.get( go_id );
- if ( ( go_namespace_limit == null ) || go_namespace_limit.equals( go_term.getGoNameSpace() ) ) {
- final String top = GoUtils.getPenultimateGoTerm( go_term, go_id_to_term_map ).getName();
- final String go_id_str = go_id.getId();
- out.write( "<td>" );
- out.write( "<a href=\"" + SurfacingConstants.AMIGO_LINK + go_id_str
- + "\" target=\"amigo_window\">" + go_id_str + "</a>" );
- out.write( "</td><td>" );
- out.write( go_term.getName() );
- if ( domain_count == 2 ) {
- out.write( " (" + d + ")" );
- }
- out.write( "</td><td>" );
- out.write( top );
- out.write( "</td><td>" );
- out.write( "[" );
- out.write( go_term.getGoNameSpace().toShortString() );
- out.write( "]" );
- out.write( "</td>" );
- if ( all_go_ids != null ) {
- all_go_ids.add( go_id );
- }
- }
- else {
- out.write( "<td>" );
- out.write( "</td><td>" );
- out.write( "</td><td>" );
- out.write( "</td><td>" );
- out.write( "</td>" );
- }
- out.write( "</tr>" );
- out.write( SurfacingConstants.NL );
- }
- }
- } // for( int d = 0; d < domain_count; ++d )
- if ( !any_go_annotation_present ) {
- out.write( "<tr>" );
- writeDomainIdsToHtml( out, domain_0, domain_1, prefix_for_html, domain_id_to_secondary_features_maps );
- out.write( "<td>" );
- out.write( "</td><td>" );
- out.write( "</td><td>" );
- out.write( "</td><td>" );
- out.write( "</td>" );
- out.write( "</tr>" );
- out.write( SurfacingConstants.NL );
- }
- }
-
private static void writeDomainIdsToHtml( final Writer out,
final String domain_0,
final String domain_1,
out.write( " " );
}
out.write( "<a href=\"" + SurfacingConstants.PFAM_FAMILY_ID_LINK + domain_0 + "\">" + domain_0 + "</a>" );
- //if ( ForesterUtil.isEmpty( domain_1 ) ) {
- // out.write( " <a href=\"" + SurfacingConstants.GOOGLE_SCHOLAR_LINK + domain_0
- // + SurfacingConstants.GOOGLE_SCHOLAR_LIMITS + "\">[gs]</a>" );
- //}
- // if ( !ForesterUtil.isEmpty( domain_1 ) ) {
- // out.write( "=" );
- // out.write( "<a href=\"" + SurfacingConstants.PFAM_FAMILY_ID_LINK + domain_1 + "\">" + domain_1 + "</a>" );
- //}
- // else if ( ( domain_id_to_secondary_features_maps != null )
- // && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
- // out.write( " [" );
- // boolean first = true;
- // for( final Map<DomainId, Set<String>> domain_id_to_secondary_features_map : domain_id_to_secondary_features_maps ) {
- // final Set<String> sec_features = domain_id_to_secondary_features_map.get( new DomainId( domain_0 ) );
- // if ( ( sec_features != null ) && ( sec_features.size() > 0 ) ) {
- // for( final String sec_feature : sec_features ) {
- // if ( first ) {
- // first = false;
- // }
- // else {
- // out.write( ", " );
- // }
- // if ( SurfacingConstants.SECONDARY_FEATURES_ARE_SCOP
- // && ( SurfacingConstants.SECONDARY_FEATURES_SCOP_LINK != null ) ) {
- // out.write( "<a href=\"" + SurfacingConstants.SECONDARY_FEATURES_SCOP_LINK + sec_feature
- // + "\" target=\"scop_window\">" + sec_feature + "</a>" );
- // }
- // else {
- // out.write( sec_feature );
- // }
- // }
- // }
- // }
- // out.write( "]" );
- // }
- out.write( "</td>" );
- }
-
- private static void writeDomainIdsToHtmlORIG( final Writer out,
- final String domain_0,
- final String domain_1,
- final String prefix_for_detailed_html,
- final Map<DomainId, Set<String>>[] domain_id_to_secondary_features_maps )
- throws IOException {
- out.write( "<td>" );
- if ( !ForesterUtil.isEmpty( prefix_for_detailed_html ) ) {
- out.write( prefix_for_detailed_html );
- out.write( " " );
- }
- out.write( "<a href=\"" + SurfacingConstants.PFAM_FAMILY_ID_LINK + domain_0 + "\">" + domain_0 + "</a>" );
- if ( ForesterUtil.isEmpty( domain_1 ) ) {
- out.write( " <a href=\"" + SurfacingConstants.GOOGLE_SCHOLAR_LINK + domain_0
- + SurfacingConstants.GOOGLE_SCHOLAR_LIMITS + "\">[gs]</a>" );
- }
- if ( !ForesterUtil.isEmpty( domain_1 ) ) {
- out.write( "=" );
- out.write( "<a href=\"" + SurfacingConstants.PFAM_FAMILY_ID_LINK + domain_1 + "\">" + domain_1 + "</a>" );
- }
- else if ( ( domain_id_to_secondary_features_maps != null )
- && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
- out.write( " [" );
- boolean first = true;
- for( final Map<DomainId, Set<String>> domain_id_to_secondary_features_map : domain_id_to_secondary_features_maps ) {
- final Set<String> sec_features = domain_id_to_secondary_features_map.get( new DomainId( domain_0 ) );
- if ( ( sec_features != null ) && ( sec_features.size() > 0 ) ) {
- for( final String sec_feature : sec_features ) {
- if ( first ) {
- first = false;
- }
- else {
- out.write( ", " );
- }
- if ( SurfacingConstants.SECONDARY_FEATURES_ARE_SCOP
- && ( SurfacingConstants.SECONDARY_FEATURES_SCOP_LINK != null ) ) {
- out.write( "<a href=\"" + SurfacingConstants.SECONDARY_FEATURES_SCOP_LINK + sec_feature
- + "\" target=\"scop_window\">" + sec_feature + "</a>" );
- }
- else {
- out.write( sec_feature );
- }
- }
- }
- }
- out.write( "]" );
- }
out.write( "</td>" );
}
public static DescriptiveStatistics writeDomainSimilaritiesToFile( final StringBuilder html_desc,
final StringBuilder html_title,
- final Writer w,
+ final Writer single_writer,
+ Map<Character, Writer> split_writers,
final SortedSet<DomainSimilarity> similarities,
final boolean treat_as_binary,
final List<Species> species_order,
System.out.println( "Pearsonian skewness : n/a" );
}
}
+ if ( ( single_writer != null ) && ( ( split_writers == null ) || split_writers.isEmpty() ) ) {
+ split_writers = new HashMap<Character, Writer>();
+ split_writers.put( '_', single_writer );
+ }
switch ( print_option ) {
case SIMPLE_TAB_DELIMITED:
break;
case HTML:
- w.write( "<html>" );
- w.write( SurfacingConstants.NL );
- addHtmlHead( w, "SURFACING :: " + html_title );
- w.write( SurfacingConstants.NL );
- w.write( "<body>" );
- w.write( SurfacingConstants.NL );
- w.write( html_desc.toString() );
- w.write( SurfacingConstants.NL );
- w.write( "<hr>" );
- w.write( "<br>" );
- w.write( SurfacingConstants.NL );
- w.write( "<tt><pre>" );
- w.write( SurfacingConstants.NL );
- if ( histo != null ) {
- w.write( histo.toStringBuffer( 20, '|', 40, 5 ).toString() );
+ for( final Character key : split_writers.keySet() ) {
+ final Writer w = split_writers.get( key );
+ w.write( "<html>" );
+ w.write( SurfacingConstants.NL );
+ if ( key != '_' ) {
+ addHtmlHead( w, "DCs (" + html_title + ") " + key.toString().toUpperCase() );
+ }
+ else {
+ addHtmlHead( w, "DCs (" + html_title + ")" );
+ }
+ w.write( SurfacingConstants.NL );
+ w.write( "<body>" );
+ w.write( SurfacingConstants.NL );
+ w.write( html_desc.toString() );
+ w.write( SurfacingConstants.NL );
+ w.write( "<hr>" );
+ w.write( "<br>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<tt><pre>" );
+ w.write( SurfacingConstants.NL );
+ if ( histo != null ) {
+ w.write( histo.toStringBuffer( 20, '|', 40, 5 ).toString() );
+ w.write( SurfacingConstants.NL );
+ }
+ w.write( "</pre></tt>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<table>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<tr><td>N: </td><td>" + stats.getN() + "</td></tr>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<tr><td>Min: </td><td>" + stats.getMin() + "</td></tr>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<tr><td>Max: </td><td>" + stats.getMax() + "</td></tr>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<tr><td>Mean: </td><td>" + stats.arithmeticMean() + "</td></tr>" );
+ w.write( SurfacingConstants.NL );
+ if ( stats.getN() > 1 ) {
+ w.write( "<tr><td>SD: </td><td>" + stats.sampleStandardDeviation() + "</td></tr>" );
+ }
+ else {
+ w.write( "<tr><td>SD: </td><td>n/a</td></tr>" );
+ }
+ w.write( SurfacingConstants.NL );
+ w.write( "<tr><td>Median: </td><td>" + stats.median() + "</td></tr>" );
+ w.write( SurfacingConstants.NL );
+ if ( stats.getN() > 1 ) {
+ w.write( "<tr><td>Pearsonian skewness: </td><td>" + stats.pearsonianSkewness() + "</td></tr>" );
+ }
+ else {
+ w.write( "<tr><td>Pearsonian skewness: </td><td>n/a</td></tr>" );
+ }
+ w.write( SurfacingConstants.NL );
+ w.write( "</table>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<br>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<hr>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<br>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<table>" );
w.write( SurfacingConstants.NL );
}
- w.write( "</pre></tt>" );
- w.write( SurfacingConstants.NL );
- w.write( "<table>" );
- w.write( SurfacingConstants.NL );
- w.write( "<tr><td>N: </td><td>" + stats.getN() + "</td></tr>" );
- w.write( SurfacingConstants.NL );
- w.write( "<tr><td>Min: </td><td>" + stats.getMin() + "</td></tr>" );
- w.write( SurfacingConstants.NL );
- w.write( "<tr><td>Max: </td><td>" + stats.getMax() + "</td></tr>" );
- w.write( SurfacingConstants.NL );
- w.write( "<tr><td>Mean: </td><td>" + stats.arithmeticMean() + "</td></tr>" );
- w.write( SurfacingConstants.NL );
- if ( stats.getN() > 1 ) {
- w.write( "<tr><td>SD: </td><td>" + stats.sampleStandardDeviation() + "</td></tr>" );
- }
- else {
- w.write( "<tr><td>SD: </td><td>n/a</td></tr>" );
- }
- w.write( SurfacingConstants.NL );
- w.write( "<tr><td>Median: </td><td>" + stats.median() + "</td></tr>" );
- w.write( SurfacingConstants.NL );
- if ( stats.getN() > 1 ) {
- w.write( "<tr><td>Pearsonian skewness: </td><td>" + stats.pearsonianSkewness() + "</td></tr>" );
- }
- else {
- w.write( "<tr><td>Pearsonian skewness: </td><td>n/a</td></tr>" );
- }
- w.write( SurfacingConstants.NL );
- w.write( "</table>" );
- w.write( SurfacingConstants.NL );
- w.write( "<br>" );
- w.write( SurfacingConstants.NL );
- w.write( "<hr>" );
- w.write( SurfacingConstants.NL );
- w.write( "<br>" );
- w.write( SurfacingConstants.NL );
- w.write( "<table>" );
- w.write( SurfacingConstants.NL );
break;
}
- w.write( SurfacingConstants.NL );
+ for( final Writer w : split_writers.values() ) {
+ w.write( SurfacingConstants.NL );
+ }
for( final DomainSimilarity similarity : similarities ) {
if ( ( species_order != null ) && !species_order.isEmpty() ) {
( ( PrintableDomainSimilarity ) similarity ).setSpeciesOrder( species_order );
}
- w.write( similarity.toStringBuffer( print_option ).toString() );
- w.write( SurfacingConstants.NL );
+ if ( single_writer != null ) {
+ single_writer.write( similarity.toStringBuffer( print_option ).toString() );
+ }
+ else {
+ Writer local_writer = split_writers.get( ( similarity.getDomainId().getId().charAt( 0 ) + "" )
+ .toLowerCase().charAt( 0 ) );
+ if ( local_writer == null ) {
+ local_writer = split_writers.get( '0' );
+ }
+ local_writer.write( similarity.toStringBuffer( print_option ).toString() );
+ }
+ for( final Writer w : split_writers.values() ) {
+ w.write( SurfacingConstants.NL );
+ }
}
switch ( print_option ) {
case HTML:
- w.write( SurfacingConstants.NL );
- w.write( "</table>" );
- w.write( SurfacingConstants.NL );
- w.write( "</font>" );
- w.write( SurfacingConstants.NL );
- w.write( "</body>" );
- w.write( SurfacingConstants.NL );
- w.write( "</html>" );
- w.write( SurfacingConstants.NL );
+ for( final Writer w : split_writers.values() ) {
+ w.write( SurfacingConstants.NL );
+ w.write( "</table>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "</font>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "</body>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "</html>" );
+ w.write( SurfacingConstants.NL );
+ }
break;
}
- w.flush();
- w.close();
+ for( final Writer w : split_writers.values() ) {
+ w.close();
+ }
return stats;
}
}
}
- public static void writeTaxonomyLinksORIG( final Writer writer, final String species ) throws IOException {
- if ( ( species.length() > 1 ) && ( species.indexOf( '_' ) < 1 ) ) {
- final Matcher matcher = PATTERN_SP_STYLE_TAXONOMY.matcher( species );
- writer.write( " [" );
- if ( matcher.matches() ) {
- writer.write( "<a href=\"" + SurfacingConstants.UNIPROT_LINK + species
- + "\" target=\"taxonomy_window\">uniprot</a>" );
- }
- else {
- writer.write( "<a href=\"" + SurfacingConstants.EOL_LINK + species
- + "\" target=\"taxonomy_window\">eol</a>" );
- writer.write( "|" );
- writer.write( "<a href=\"" + SurfacingConstants.TOL_LINK + species
- + "\" target=\"taxonomy_window\">tol</a>" );
- writer.write( "|" );
- writer.write( "<a href=\"" + SurfacingConstants.WIKIPEDIA_LINK + species
- + "\" target=\"taxonomy_window\">wikipedia</a>" );
- writer.write( "|" );
- writer.write( "<a href=\"" + SurfacingConstants.GOOGLE_SCHOLAR_LINK + species
- + "\" target=\"taxonomy_window\">gs</a>" );
- }
- writer.write( "]" );
- }
- }
-
- private static void writeToNexus( final String outfile_name, final CharacterStateMatrix<BinaryStates> matrix ) {
- if ( !( matrix instanceof BasicCharacterStateMatrix ) ) {
- throw new IllegalArgumentException( "can only write matrices of type [" + BasicCharacterStateMatrix.class
- + "] to nexus" );
- }
- final BasicCharacterStateMatrix<BinaryStates> my_matrix = ( org.forester.evoinference.matrix.character.BasicCharacterStateMatrix<BinaryStates> ) matrix;
- try {
- final BufferedWriter w = new BufferedWriter( new FileWriter( outfile_name ) );
- w.write( NexusConstants.NEXUS );
- w.write( ForesterUtil.LINE_SEPARATOR );
- my_matrix.writeNexusTaxaBlock( w );
- my_matrix.writeNexusBinaryChractersBlock( w );
- w.flush();
- w.close();
- ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote Nexus file: \"" + outfile_name + "\"" );
- }
- catch ( final IOException e ) {
- ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
- }
- }
-
private static void writeToNexus( final String outfile_name,
final CharacterStateMatrix<BinaryStates> matrix,
final Phylogeny phylogeny ) {
w.write( ForesterUtil.LINE_SEPARATOR );
my_matrix.writeNexusTaxaBlock( w );
my_matrix.writeNexusBinaryChractersBlock( w );
- PhylogenyWriter.writeNexusTreesBlock( w, phylogenies );
+ PhylogenyWriter.writeNexusTreesBlock( w, phylogenies, NH_CONVERSION_SUPPORT_VALUE_STYLE.NONE );
w.flush();
w.close();
ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote Nexus file: \"" + outfile_name + "\"" );
}
}
- private static void writeToNexus( final String outfile_name, final DomainParsimonyCalculator domain_parsimony ) {
- writeToNexus( outfile_name + surfacing.NEXUS_EXTERNAL_DOMAINS,
- domain_parsimony.createMatrixOfDomainPresenceOrAbsence() );
- writeToNexus( outfile_name + surfacing.NEXUS_EXTERNAL_DOMAIN_COMBINATIONS,
- domain_parsimony.createMatrixOfBinaryDomainCombinationPresenceOrAbsence() );
- }
-
private static void writeToNexus( final String outfile_name,
final DomainParsimonyCalculator domain_parsimony,
final Phylogeny phylogeny ) {
domain_parsimony.createMatrixOfBinaryDomainCombinationPresenceOrAbsence(),
phylogeny );
}
+
+ public static void domainsPerProteinsStatistics( final String genome,
+ final List<Protein> protein_list,
+ final DescriptiveStatistics all_genomes_domains_per_potein_stats,
+ final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo,
+ final SortedSet<String> domains_which_are_always_single,
+ final SortedSet<String> domains_which_are_sometimes_single_sometimes_not,
+ final SortedSet<String> domains_which_never_single,
+ final Writer writer ) {
+ final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
+ for( final Protein protein : protein_list ) {
+ final int domains = protein.getNumberOfProteinDomains();
+ //System.out.println( domains );
+ stats.addValue( domains );
+ all_genomes_domains_per_potein_stats.addValue( domains );
+ if ( !all_genomes_domains_per_potein_histo.containsKey( domains ) ) {
+ all_genomes_domains_per_potein_histo.put( domains, 1 );
+ }
+ else {
+ all_genomes_domains_per_potein_histo.put( domains,
+ 1 + all_genomes_domains_per_potein_histo.get( domains ) );
+ }
+ if ( domains == 1 ) {
+ final String domain = protein.getProteinDomain( 0 ).getDomainId().getId();
+ if ( !domains_which_are_sometimes_single_sometimes_not.contains( domain ) ) {
+ if ( domains_which_never_single.contains( domain ) ) {
+ domains_which_never_single.remove( domain );
+ domains_which_are_sometimes_single_sometimes_not.add( domain );
+ }
+ else {
+ domains_which_are_always_single.add( domain );
+ }
+ }
+ }
+ else if ( domains > 1 ) {
+ for( final Domain d : protein.getProteinDomains() ) {
+ final String domain = d.getDomainId().getId();
+ // System.out.println( domain );
+ if ( !domains_which_are_sometimes_single_sometimes_not.contains( domain ) ) {
+ if ( domains_which_are_always_single.contains( domain ) ) {
+ domains_which_are_always_single.remove( domain );
+ domains_which_are_sometimes_single_sometimes_not.add( domain );
+ }
+ else {
+ domains_which_never_single.add( domain );
+ }
+ }
+ }
+ }
+ }
+ try {
+ writer.write( genome );
+ writer.write( "\t" );
+ if ( stats.getN() >= 1 ) {
+ writer.write( stats.arithmeticMean() + "" );
+ writer.write( "\t" );
+ if ( stats.getN() >= 2 ) {
+ writer.write( stats.sampleStandardDeviation() + "" );
+ }
+ else {
+ writer.write( "" );
+ }
+ writer.write( "\t" );
+ writer.write( stats.median() + "" );
+ writer.write( "\t" );
+ writer.write( stats.getN() + "" );
+ writer.write( "\t" );
+ writer.write( stats.getMin() + "" );
+ writer.write( "\t" );
+ writer.write( stats.getMax() + "" );
+ }
+ else {
+ writer.write( "\t" );
+ writer.write( "\t" );
+ writer.write( "\t" );
+ writer.write( "0" );
+ writer.write( "\t" );
+ writer.write( "\t" );
+ }
+ writer.write( "\n" );
+ }
+ catch ( final IOException e ) {
+ e.printStackTrace();
+ }
+ }
}
git://source.jalview.org / jalview.git / blobdiff