// Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
//
// Contact: phylosoft @ gmail . com
-// WWW: www.phylosoft.org/forester
+// WWW: https://sites.google.com/site/cmzmasek/home/software/forester
package org.forester.surfacing;
import java.util.Comparator;
import java.util.HashMap;
import java.util.HashSet;
+import java.util.Iterator;
import java.util.List;
import java.util.Map;
+import java.util.Map.Entry;
import java.util.PriorityQueue;
import java.util.Set;
import java.util.SortedMap;
import org.forester.evoinference.matrix.character.CharacterStateMatrix.BinaryStates;
import org.forester.evoinference.matrix.character.CharacterStateMatrix.Format;
import org.forester.evoinference.matrix.character.CharacterStateMatrix.GainLossStates;
+import org.forester.evoinference.matrix.distance.BasicSymmetricalDistanceMatrix;
import org.forester.evoinference.matrix.distance.DistanceMatrix;
import org.forester.go.GoId;
import org.forester.go.GoNameSpace;
import org.forester.phylogeny.Phylogeny;
import org.forester.phylogeny.PhylogenyMethods;
import org.forester.phylogeny.PhylogenyNode;
+import org.forester.phylogeny.PhylogenyNode.NH_CONVERSION_SUPPORT_VALUE_STYLE;
import org.forester.phylogeny.data.BinaryCharacters;
import org.forester.phylogeny.data.Confidence;
+import org.forester.phylogeny.data.Taxonomy;
import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
+import org.forester.protein.BasicDomain;
+import org.forester.protein.BasicProtein;
+import org.forester.protein.BinaryDomainCombination;
+import org.forester.protein.Domain;
+import org.forester.protein.Protein;
+import org.forester.species.Species;
import org.forester.surfacing.DomainSimilarityCalculator.Detailedness;
-import org.forester.surfacing.DomainSimilarityCalculator.GoAnnotationOutput;
import org.forester.surfacing.GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder;
+import org.forester.surfacing.PrintableDomainSimilarity.PRINT_OPTION;
import org.forester.util.AsciiHistogram;
import org.forester.util.BasicDescriptiveStatistics;
import org.forester.util.BasicTable;
public final class SurfacingUtil {
- private final static NumberFormat FORMATTER = new DecimalFormat( "0.0E0" );
private final static NumberFormat FORMATTER_3 = new DecimalFormat( "0.000" );
private static final Comparator<Domain> ASCENDING_CONFIDENCE_VALUE_ORDER = new Comparator<Domain>() {
public static void addAllBinaryDomainCombinationToSet( final GenomeWideCombinableDomains genome,
final SortedSet<BinaryDomainCombination> binary_domain_combinations ) {
- final SortedMap<DomainId, CombinableDomains> all_cd = genome.getAllCombinableDomainsIds();
- for( final DomainId domain_id : all_cd.keySet() ) {
+ final SortedMap<String, CombinableDomains> all_cd = genome.getAllCombinableDomainsIds();
+ for( final String domain_id : all_cd.keySet() ) {
binary_domain_combinations.addAll( all_cd.get( domain_id ).toBinaryDomainCombinations() );
}
}
public static void addAllDomainIdsToSet( final GenomeWideCombinableDomains genome,
- final SortedSet<DomainId> domain_ids ) {
- final SortedSet<DomainId> domains = genome.getAllDomainIds();
- for( final DomainId domain : domains ) {
+ final SortedSet<String> domain_ids ) {
+ final SortedSet<String> domains = genome.getAllDomainIds();
+ for( final String domain : domains ) {
domain_ids.add( domain );
}
}
w.write( SurfacingConstants.NL );
w.write( "a:hover { color : #FFFFFF; background-color : #99FF00; text-decoration : none; }" );
w.write( SurfacingConstants.NL );
+ //
+ w.write( "a.pl:visited { color : #505050; text-decoration : none; font-size: 7pt;}" );
+ w.write( SurfacingConstants.NL );
+ w.write( "a.pl:link { color : #505050; text-decoration : none; font-size: 7pt;}" );
+ w.write( SurfacingConstants.NL );
+ w.write( "a.pl:active { color : #505050; text-decoration : none; font-size: 7pt;}" );
+ w.write( SurfacingConstants.NL );
+ w.write( "a.pl:hover { color : #FFFFFF; background-color : #99FF00; text-decoration : none; font-size: 7pt;}" );
+ w.write( SurfacingConstants.NL );
+ //
+ w.write( "a.ps:visited { color : #707070; text-decoration : none; font-size: 7pt;}" );
+ w.write( SurfacingConstants.NL );
+ w.write( "a.ps:link { color : #707070; text-decoration : none; font-size: 7pt;}" );
+ w.write( SurfacingConstants.NL );
+ w.write( "a.ps:active { color : #707070; text-decoration : none; font-size: 7pt;}" );
+ w.write( SurfacingConstants.NL );
+ w.write( "a.ps:hover { color : #FFFFFF; background-color : #99FF00; text-decoration : none; font-size: 7pt;}" );
+ w.write( SurfacingConstants.NL );
+ //
w.write( "td { text-align: left; vertical-align: top; font-family: Verdana, Arial, Helvetica; font-size: 8pt}" );
w.write( SurfacingConstants.NL );
w.write( "h1 { color : #0000FF; font-family: Verdana, Arial, Helvetica; font-size: 18pt; font-weight: bold }" );
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 ) {
- 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();
- 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 );
- }
- }
- 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();
- }
- 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 + "]" );
- }
-
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 ) {
}
}
- private static SortedSet<String> collectAllDomainsChangedOnSubtree( final PhylogenyNode subtree_root,
- final boolean get_gains ) {
- final SortedSet<String> domains = new TreeSet<String>();
- for( final PhylogenyNode descendant : PhylogenyMethods.getAllDescendants( subtree_root ) ) {
- final BinaryCharacters chars = descendant.getNodeData().getBinaryCharacters();
- if ( get_gains ) {
- domains.addAll( chars.getGainedCharacters() );
- }
- else {
- domains.addAll( chars.getLostCharacters() );
- }
- }
- return domains;
- }
-
public static void collectChangedDomainCombinationsFromBinaryStatesMatrixAsListToFile( final CharacterStateMatrix<CharacterStateMatrix.GainLossStates> matrix,
final BinaryDomainCombination.DomainCombinationType dc_type,
final List<BinaryDomainCombination> all_binary_domains_combination_gained,
}
}
- private static File createBaseDirForPerNodeDomainFiles( final String base_dir,
- final boolean domain_combinations,
- final CharacterStateMatrix.GainLossStates state,
- final String outfile ) {
- File per_node_go_mapped_domain_gain_loss_files_base_dir = new File( new File( outfile ).getParent()
- + ForesterUtil.FILE_SEPARATOR + base_dir );
- if ( !per_node_go_mapped_domain_gain_loss_files_base_dir.exists() ) {
- per_node_go_mapped_domain_gain_loss_files_base_dir.mkdir();
- }
- if ( domain_combinations ) {
- per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir
- + ForesterUtil.FILE_SEPARATOR + "DC" );
- }
- else {
- per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir
- + ForesterUtil.FILE_SEPARATOR + "DOMAINS" );
- }
- if ( !per_node_go_mapped_domain_gain_loss_files_base_dir.exists() ) {
- per_node_go_mapped_domain_gain_loss_files_base_dir.mkdir();
- }
- if ( state == GainLossStates.GAIN ) {
- per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir
- + ForesterUtil.FILE_SEPARATOR + "GAINS" );
- }
- else if ( state == GainLossStates.LOSS ) {
- per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir
- + ForesterUtil.FILE_SEPARATOR + "LOSSES" );
- }
- else {
- per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir
- + ForesterUtil.FILE_SEPARATOR + "PRESENT" );
- }
- if ( !per_node_go_mapped_domain_gain_loss_files_base_dir.exists() ) {
- per_node_go_mapped_domain_gain_loss_files_base_dir.mkdir();
- }
- return per_node_go_mapped_domain_gain_loss_files_base_dir;
- }
-
- public static Map<DomainId, List<GoId>> createDomainIdToGoIdMap( final List<PfamToGoMapping> pfam_to_go_mappings ) {
- final Map<DomainId, List<GoId>> domain_id_to_go_ids_map = new HashMap<DomainId, List<GoId>>( pfam_to_go_mappings
- .size() );
+ public static Map<String, List<GoId>> createDomainIdToGoIdMap( final List<PfamToGoMapping> pfam_to_go_mappings ) {
+ final Map<String, List<GoId>> domain_id_to_go_ids_map = new HashMap<String, List<GoId>>( pfam_to_go_mappings.size() );
for( final PfamToGoMapping pfam_to_go : pfam_to_go_mappings ) {
if ( !domain_id_to_go_ids_map.containsKey( pfam_to_go.getKey() ) ) {
domain_id_to_go_ids_map.put( pfam_to_go.getKey(), new ArrayList<GoId>() );
return domain_id_to_go_ids_map;
}
- public static Map<DomainId, Set<String>> createDomainIdToSecondaryFeaturesMap( final File secondary_features_map_file )
+ public static Map<String, Set<String>> createDomainIdToSecondaryFeaturesMap( final File secondary_features_map_file )
throws IOException {
- final BasicTable<String> primary_table = BasicTableParser.parse( secondary_features_map_file, "\t" );
- final Map<DomainId, Set<String>> map = new TreeMap<DomainId, Set<String>>();
+ final BasicTable<String> primary_table = BasicTableParser.parse( secondary_features_map_file, '\t' );
+ final Map<String, Set<String>> map = new TreeMap<String, Set<String>>();
for( int r = 0; r < primary_table.getNumberOfRows(); ++r ) {
- final DomainId domain_id = new DomainId( primary_table.getValue( 0, r ) );
+ final String domain_id = primary_table.getValue( 0, r );
if ( !map.containsKey( domain_id ) ) {
map.put( domain_id, new HashSet<String>() );
}
public static Phylogeny createNjTreeBasedOnMatrixToFile( final File nj_tree_outfile, final DistanceMatrix distance ) {
checkForOutputFileWriteability( nj_tree_outfile );
final NeighborJoining nj = NeighborJoining.createInstance();
- final Phylogeny phylogeny = nj.execute( distance );
+ final Phylogeny phylogeny = nj.execute( ( BasicSymmetricalDistanceMatrix ) distance );
phylogeny.setName( nj_tree_outfile.getName() );
writePhylogenyToFile( phylogeny, nj_tree_outfile.toString() );
return phylogeny;
}
- private static SortedSet<BinaryDomainCombination> createSetOfAllBinaryDomainCombinationsPerGenome( final GenomeWideCombinableDomains gwcd ) {
- final SortedMap<DomainId, CombinableDomains> cds = gwcd.getAllCombinableDomainsIds();
- final SortedSet<BinaryDomainCombination> binary_combinations = new TreeSet<BinaryDomainCombination>();
- for( final DomainId domain_id : cds.keySet() ) {
- final CombinableDomains cd = cds.get( domain_id );
- binary_combinations.addAll( cd.toBinaryDomainCombinations() );
+ public static Map<String, Integer> createTaxCodeToIdMap( final Phylogeny phy ) {
+ final Map<String, Integer> m = new HashMap<String, Integer>();
+ for( final PhylogenyNodeIterator iter = phy.iteratorExternalForward(); iter.hasNext(); ) {
+ final PhylogenyNode n = iter.next();
+ if ( n.getNodeData().isHasTaxonomy() ) {
+ final Taxonomy t = n.getNodeData().getTaxonomy();
+ final String c = t.getTaxonomyCode();
+ if ( !ForesterUtil.isEmpty( c ) ) {
+ if ( n.getNodeData().getTaxonomy() == null ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "no taxonomy id for node " + n );
+ }
+ final String id = n.getNodeData().getTaxonomy().getIdentifier().getValue();
+ if ( ForesterUtil.isEmpty( id ) ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "no taxonomy id for node " + n );
+ }
+ if ( m.containsKey( c ) ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "taxonomy code " + c + " is not unique" );
+ }
+ final int iid = Integer.valueOf( id );
+ if ( m.containsValue( iid ) ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "taxonomy id " + iid + " is not unique" );
+ }
+ m.put( c, iid );
+ }
+ }
+ else {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "no taxonomy for node " + n );
+ }
}
- return binary_combinations;
+ return m;
}
public static void decoratePrintableDomainSimilarities( final SortedSet<DomainSimilarity> domain_similarities,
- final Detailedness detailedness,
- final GoAnnotationOutput go_annotation_output,
- final Map<GoId, GoTerm> go_id_to_term_map,
- final GoNameSpace go_namespace_limit ) {
- if ( ( go_namespace_limit != null ) && ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) ) {
- throw new IllegalArgumentException( "attempt to use a GO namespace limit without a GO id to term map" );
- }
+ final Detailedness detailedness ) {
for( final DomainSimilarity domain_similarity : domain_similarities ) {
if ( domain_similarity instanceof PrintableDomainSimilarity ) {
final PrintableDomainSimilarity printable_domain_similarity = ( PrintableDomainSimilarity ) domain_similarity;
printable_domain_similarity.setDetailedness( detailedness );
- printable_domain_similarity.setGoAnnotationOutput( go_annotation_output );
- printable_domain_similarity.setGoIdToTermMap( go_id_to_term_map );
- printable_domain_similarity.setGoNamespaceLimit( go_namespace_limit );
}
}
}
+ public static void doit( final List<Protein> proteins,
+ final List<String> query_domain_ids_nc_order,
+ final Writer out,
+ final String separator,
+ final String limit_to_species,
+ final Map<String, List<Integer>> average_protein_lengths_by_dc ) throws IOException {
+ for( final Protein protein : proteins ) {
+ if ( ForesterUtil.isEmpty( limit_to_species )
+ || protein.getSpecies().getSpeciesId().equalsIgnoreCase( limit_to_species ) ) {
+ if ( protein.contains( query_domain_ids_nc_order, true ) ) {
+ out.write( protein.getSpecies().getSpeciesId() );
+ out.write( separator );
+ out.write( protein.getProteinId().getId() );
+ out.write( separator );
+ out.write( "[" );
+ final Set<String> visited_domain_ids = new HashSet<String>();
+ boolean first = true;
+ for( final Domain domain : protein.getProteinDomains() ) {
+ if ( !visited_domain_ids.contains( domain.getDomainId() ) ) {
+ visited_domain_ids.add( domain.getDomainId() );
+ if ( first ) {
+ first = false;
+ }
+ else {
+ out.write( " " );
+ }
+ out.write( domain.getDomainId() );
+ out.write( " {" );
+ out.write( "" + domain.getTotalCount() );
+ out.write( "}" );
+ }
+ }
+ out.write( "]" );
+ out.write( separator );
+ if ( !( ForesterUtil.isEmpty( protein.getDescription() ) || protein.getDescription()
+ .equals( SurfacingConstants.NONE ) ) ) {
+ out.write( protein.getDescription() );
+ }
+ out.write( separator );
+ if ( !( ForesterUtil.isEmpty( protein.getAccession() ) || protein.getAccession()
+ .equals( SurfacingConstants.NONE ) ) ) {
+ out.write( protein.getAccession() );
+ }
+ out.write( SurfacingConstants.NL );
+ }
+ }
+ }
+ out.flush();
+ }
+
+ 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();
+ 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();
+ // 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();
+ }
+ }
+
public static void executeDomainLengthAnalysis( final String[][] input_file_properties,
final int number_of_genomes,
final DomainLengthsTable domain_lengths_table,
out.write( species + "\t" );
}
out.write( ForesterUtil.LINE_SEPARATOR );
- // DescriptiveStatistics stats_for_domain = domain_lengths
- // .calculateMeanBasedStatistics();
- //AsciiHistogram histo = new AsciiHistogram( stats_for_domain );
- //System.out.println( histo.toStringBuffer( 40, '=', 60, 4 ).toString() );
}
}
out.write( ForesterUtil.LINE_SEPARATOR );
}
}
out.close();
- // final List<HistogramData> histogram_datas = new ArrayList<HistogramData>();
- // for( int i = 0; i < number_of_genomes; ++i ) {
- // final Species species = new BasicSpecies( input_file_properties[ i ][ 0 ] );
- // histogram_datas
- // .add( new HistogramData( species.toString(), domain_lengths_table
- // .calculateMeanBasedStatisticsForSpecies( species )
- // .getDataAsDoubleArray(), 5, 600, null, 60 ) );
- // }
- // final HistogramsFrame hf = new HistogramsFrame( histogram_datas );
- // hf.setVisible( true );
System.gc();
}
/**
*
* @param all_binary_domains_combination_lost_fitch
+ * @param use_last_in_fitch_parsimony
* @param consider_directedness_and_adjacency_for_bin_combinations
* @param all_binary_domains_combination_gained if null ignored, otherwise this is to list all binary domain combinations
* which were gained under unweighted (Fitch) parsimony.
final String outfile_name,
final DomainParsimonyCalculator domain_parsimony,
final Phylogeny phylogeny,
- final Map<DomainId, List<GoId>> domain_id_to_go_ids_map,
+ final Map<String, List<GoId>> domain_id_to_go_ids_map,
final Map<GoId, GoTerm> go_id_to_term_map,
final GoNameSpace go_namespace_limit,
final String parameters_str,
- final Map<DomainId, Set<String>>[] domain_id_to_secondary_features_maps,
- final SortedSet<DomainId> positive_filter,
+ final Map<String, Set<String>>[] domain_id_to_secondary_features_maps,
+ final SortedSet<String> positive_filter,
final boolean output_binary_domain_combinations_for_graphs,
final List<BinaryDomainCombination> all_binary_domains_combination_gained_fitch,
final List<BinaryDomainCombination> all_binary_domains_combination_lost_fitch,
- final BinaryDomainCombination.DomainCombinationType dc_type ) {
+ final BinaryDomainCombination.DomainCombinationType dc_type,
+ final Map<String, DescriptiveStatistics> protein_length_stats_by_dc,
+ final Map<String, DescriptiveStatistics> domain_number_stats_by_dc,
+ final Map<String, DescriptiveStatistics> domain_length_stats_by_domain,
+ final Map<String, Integer> tax_code_to_id_map,
+ final boolean write_to_nexus,
+ final boolean use_last_in_fitch_parsimony ) {
final String sep = ForesterUtil.LINE_SEPARATOR + "###################" + ForesterUtil.LINE_SEPARATOR;
final String date_time = ForesterUtil.getCurrentDateTime();
final SortedSet<String> all_pfams_encountered = new TreeSet<String>();
final SortedSet<String> all_pfams_lost_as_domains = new TreeSet<String>();
final SortedSet<String> all_pfams_gained_as_dom_combinations = new TreeSet<String>();
final SortedSet<String> all_pfams_lost_as_dom_combinations = new TreeSet<String>();
- writeToNexus( outfile_name, domain_parsimony, phylogeny );
+ if ( write_to_nexus ) {
+ writeToNexus( outfile_name, domain_parsimony, phylogeny );
+ }
// DOLLO DOMAINS
// -------------
Phylogeny local_phylogeny_l = phylogeny.copy();
domain_id_to_secondary_features_maps,
all_pfams_encountered,
all_pfams_gained_as_domains,
- "_dollo_gains_d" );
+ "_dollo_gains_d",
+ tax_code_to_id_map );
writeBinaryStatesMatrixToList( domain_id_to_go_ids_map,
go_id_to_term_map,
go_namespace_limit,
domain_id_to_secondary_features_maps,
all_pfams_encountered,
all_pfams_lost_as_domains,
- "_dollo_losses_d" );
- writeBinaryStatesMatrixToList( domain_id_to_go_ids_map,
- go_id_to_term_map,
- go_namespace_limit,
- false,
- domain_parsimony.getGainLossMatrix(),
- null,
- outfile_name + surfacing.PARSIMONY_OUTPUT_DOLLO_PRESENT_HTML_D,
- sep,
- ForesterUtil.LINE_SEPARATOR,
- "Dollo Parsimony | Present | Domains",
- "",
- domain_id_to_secondary_features_maps,
- all_pfams_encountered,
- null,
- "_dollo_present_d" );
+ "_dollo_losses_d",
+ tax_code_to_id_map );
+ // writeBinaryStatesMatrixToList( domain_id_to_go_ids_map,
+ // go_id_to_term_map,
+ // go_namespace_limit,
+ // false,
+ // domain_parsimony.getGainLossMatrix(),
+ // null,
+ // outfile_name + surfacing.PARSIMONY_OUTPUT_DOLLO_PRESENT_HTML_D,
+ // sep,
+ // ForesterUtil.LINE_SEPARATOR,
+ // "Dollo Parsimony | Present | Domains",
+ // "",
+ // domain_id_to_secondary_features_maps,
+ // all_pfams_encountered,
+ // null,
+ // "_dollo_present_d",
+ // tax_code_to_id_map );
preparePhylogeny( local_phylogeny_l,
domain_parsimony,
date_time,
randomization = "yes, seed = " + random_number_seed_for_fitch_parsimony;
}
else {
- domain_parsimony.executeFitchParsimonyOnBinaryDomainCombintion( false );
+ domain_parsimony.executeFitchParsimonyOnBinaryDomainCombintion( use_last_in_fitch_parsimony );
}
SurfacingUtil.writeMatrixToFile( domain_parsimony.getGainLossMatrix(), outfile_name
+ surfacing.PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_BINARY_COMBINATIONS, Format.FORESTER );
null,
all_pfams_encountered,
all_pfams_gained_as_dom_combinations,
- "_fitch_gains_dc" );
+ "_fitch_gains_dc",
+ tax_code_to_id_map );
writeBinaryStatesMatrixToList( domain_id_to_go_ids_map,
go_id_to_term_map,
go_namespace_limit,
null,
all_pfams_encountered,
all_pfams_lost_as_dom_combinations,
- "_fitch_losses_dc" );
- writeBinaryStatesMatrixToList( domain_id_to_go_ids_map,
- go_id_to_term_map,
- go_namespace_limit,
- true,
- domain_parsimony.getGainLossMatrix(),
- null,
- outfile_name + surfacing.PARSIMONY_OUTPUT_FITCH_PRESENT_HTML_BC,
- sep,
- ForesterUtil.LINE_SEPARATOR,
- "Fitch Parsimony | Present | Domain Combinations",
- "",
- null,
- all_pfams_encountered,
- null,
- "_fitch_present_dc" );
+ "_fitch_losses_dc",
+ tax_code_to_id_map );
+ // writeBinaryStatesMatrixToList( domain_id_to_go_ids_map,
+ // go_id_to_term_map,
+ // go_namespace_limit,
+ // true,
+ // domain_parsimony.getGainLossMatrix(),
+ // null,
+ // outfile_name + surfacing.PARSIMONY_OUTPUT_FITCH_PRESENT_HTML_BC,
+ // sep,
+ // ForesterUtil.LINE_SEPARATOR,
+ // "Fitch Parsimony | Present | Domain Combinations",
+ // "",
+ // null,
+ // all_pfams_encountered,
+ // null,
+ // "_fitch_present_dc",
+ // tax_code_to_id_map );
writeAllEncounteredPfamsToFile( domain_id_to_go_ids_map,
go_id_to_term_map,
outfile_name,
parameters_str );
SurfacingUtil.writePhylogenyToFile( local_phylogeny_l, outfile_name
+ 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, 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 );
+ 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,
+ 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",
+ outfile_name + "_indep_dc_gains_fitch_protein_statistics.txt",
+ protein_length_stats_by_dc,
+ domain_number_stats_by_dc,
+ domain_length_stats_by_domain );
}
}
final DomainParsimonyCalculator secondary_features_parsimony,
final Phylogeny phylogeny,
final String parameters_str,
- final Map<Species, MappingResults> mapping_results_map ) {
+ final Map<Species, MappingResults> mapping_results_map,
+ final boolean use_last_in_fitch_parsimony ) {
final String sep = ForesterUtil.LINE_SEPARATOR + "###################" + ForesterUtil.LINE_SEPARATOR;
final String date_time = ForesterUtil.getCurrentDateTime();
System.out.println();
writeToNexus( outfile_name + surfacing.NEXUS_SECONDARY_FEATURES,
secondary_features_parsimony.createMatrixOfSecondaryFeaturePresenceOrAbsence( null ),
phylogeny );
- final Phylogeny local_phylogeny_copy = phylogeny.copy();
+ Phylogeny local_phylogeny_copy = phylogeny.copy();
secondary_features_parsimony.executeDolloParsimonyOnSecondaryFeatures( mapping_results_map );
SurfacingUtil.writeMatrixToFile( secondary_features_parsimony.getGainLossMatrix(), outfile_name
+ surfacing.PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_SECONDARY_FEATURES, Format.FORESTER );
parameters_str );
SurfacingUtil.writePhylogenyToFile( local_phylogeny_copy, outfile_name
+ surfacing.SECONDARY_FEATURES_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO );
+ // FITCH DOMAIN COMBINATIONS
+ // -------------------------
+ local_phylogeny_copy = phylogeny.copy();
+ final String randomization = "no";
+ secondary_features_parsimony
+ .executeFitchParsimonyOnBinaryDomainCombintionOnSecondaryFeatures( use_last_in_fitch_parsimony );
+ preparePhylogeny( local_phylogeny_copy,
+ secondary_features_parsimony,
+ date_time,
+ "Fitch parsimony on secondary binary domain combination presence/absence randomization: "
+ + randomization,
+ "fitch_on_binary_domain_combinations_" + outfile_name,
+ parameters_str );
+ SurfacingUtil.writePhylogenyToFile( local_phylogeny_copy, outfile_name
+ + surfacing.BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH_MAPPED );
+ calculateIndependentDomainCombinationGains( local_phylogeny_copy, outfile_name
+ + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_MAPPED_OUTPUT_SUFFIX, outfile_name
+ + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_MAPPED_OUTPUT_SUFFIX, outfile_name
+ + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_MAPPED_OUTPUT_SUFFIX, outfile_name
+ + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_MAPPED_OUTPUT_UNIQUE_SUFFIX, outfile_name
+ + "_MAPPED_indep_dc_gains_fitch_lca_ranks.txt", outfile_name
+ + "_MAPPED_indep_dc_gains_fitch_lca_taxonomies.txt", null, null, null, null );
}
public static void extractProteinNames( final List<Protein> proteins,
- final List<DomainId> query_domain_ids_nc_order,
+ final List<String> query_domain_ids_nc_order,
final Writer out,
- final String separator ) throws IOException {
+ final String separator,
+ final String limit_to_species ) throws IOException {
for( final Protein protein : proteins ) {
- if ( protein.contains( query_domain_ids_nc_order, true ) ) {
- out.write( protein.getSpecies().getSpeciesId() );
- out.write( separator );
- out.write( protein.getProteinId().getId() );
- out.write( separator );
- out.write( "[" );
- final Set<DomainId> visited_domain_ids = new HashSet<DomainId>();
- boolean first = true;
- for( final Domain domain : protein.getProteinDomains() ) {
- if ( !visited_domain_ids.contains( domain.getDomainId() ) ) {
- visited_domain_ids.add( domain.getDomainId() );
- if ( first ) {
- first = false;
- }
- else {
- out.write( " " );
- }
- out.write( domain.getDomainId().getId() );
- out.write( " {" );
- out.write( "" + domain.getTotalCount() );
- out.write( "}" );
- }
- }
- out.write( "]" );
- out.write( separator );
- if ( !( ForesterUtil.isEmpty( protein.getDescription() ) || protein.getDescription()
- .equals( SurfacingConstants.NONE ) ) ) {
- out.write( protein.getDescription() );
- }
- out.write( separator );
- if ( !( ForesterUtil.isEmpty( protein.getAccession() ) || protein.getAccession()
- .equals( SurfacingConstants.NONE ) ) ) {
- out.write( protein.getAccession() );
- }
- out.write( SurfacingConstants.NL );
- }
- }
- out.flush();
- }
-
- public static void extractProteinNames( final SortedMap<Species, List<Protein>> protein_lists_per_species,
- final DomainId domain_id,
- final Writer out,
- final String separator ) throws IOException {
- for( final Species species : protein_lists_per_species.keySet() ) {
- for( final Protein protein : protein_lists_per_species.get( species ) ) {
- final List<Domain> domains = protein.getProteinDomains( domain_id );
- if ( domains.size() > 0 ) {
- final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
- for( final Domain domain : domains ) {
- stats.addValue( domain.getPerSequenceEvalue() );
- }
+ if ( ForesterUtil.isEmpty( limit_to_species )
+ || protein.getSpecies().getSpeciesId().equalsIgnoreCase( limit_to_species ) ) {
+ if ( protein.contains( query_domain_ids_nc_order, true ) ) {
out.write( protein.getSpecies().getSpeciesId() );
out.write( separator );
out.write( protein.getProteinId().getId() );
out.write( separator );
- out.write( "[" + FORMATTER.format( stats.median() ) + "]" );
+ out.write( "[" );
+ final Set<String> visited_domain_ids = new HashSet<String>();
+ boolean first = true;
+ for( final Domain domain : protein.getProteinDomains() ) {
+ if ( !visited_domain_ids.contains( domain.getDomainId() ) ) {
+ visited_domain_ids.add( domain.getDomainId() );
+ if ( first ) {
+ first = false;
+ }
+ else {
+ out.write( " " );
+ }
+ out.write( domain.getDomainId() );
+ out.write( " {" );
+ out.write( "" + domain.getTotalCount() );
+ out.write( "}" );
+ }
+ }
+ out.write( "]" );
out.write( separator );
if ( !( ForesterUtil.isEmpty( protein.getDescription() ) || protein.getDescription()
.equals( SurfacingConstants.NONE ) ) ) {
out.flush();
}
- public static SortedSet<DomainId> getAllDomainIds( final List<GenomeWideCombinableDomains> gwcd_list ) {
- final SortedSet<DomainId> all_domains_ids = new TreeSet<DomainId>();
+ public static void extractProteinNames( final SortedMap<Species, List<Protein>> protein_lists_per_species,
+ final String domain_id,
+ final Writer out,
+ final String separator,
+ final String limit_to_species,
+ final double domain_e_cutoff ) throws IOException {
+ System.out.println( "Per domain E-value: " + domain_e_cutoff );
+ for( final Species species : protein_lists_per_species.keySet() ) {
+ System.out.println( species + ":" );
+ for( final Protein protein : protein_lists_per_species.get( species ) ) {
+ if ( ForesterUtil.isEmpty( limit_to_species )
+ || protein.getSpecies().getSpeciesId().equalsIgnoreCase( limit_to_species ) ) {
+ final List<Domain> domains = protein.getProteinDomains( domain_id );
+ if ( domains.size() > 0 ) {
+ out.write( protein.getSpecies().getSpeciesId() );
+ out.write( separator );
+ out.write( protein.getProteinId().getId() );
+ out.write( separator );
+ out.write( domain_id.toString() );
+ out.write( separator );
+ int prev_to = -1;
+ for( final Domain domain : domains ) {
+ if ( ( domain_e_cutoff < 0 ) || ( domain.getPerDomainEvalue() <= domain_e_cutoff ) ) {
+ out.write( "/" );
+ out.write( domain.getFrom() + "-" + domain.getTo() );
+ if ( prev_to >= 0 ) {
+ final int l = domain.getFrom() - prev_to;
+ System.out.println( l );
+ }
+ prev_to = domain.getTo();
+ }
+ }
+ out.write( "/" );
+ out.write( separator );
+ final List<Domain> domain_list = new ArrayList<Domain>();
+ for( final Domain domain : protein.getProteinDomains() ) {
+ if ( ( domain_e_cutoff < 0 ) || ( domain.getPerDomainEvalue() <= domain_e_cutoff ) ) {
+ domain_list.add( domain );
+ }
+ }
+ final Domain domain_ary[] = new Domain[ domain_list.size() ];
+ for( int i = 0; i < domain_list.size(); ++i ) {
+ domain_ary[ i ] = domain_list.get( i );
+ }
+ Arrays.sort( domain_ary, new DomainComparator( true ) );
+ out.write( "{" );
+ boolean first = true;
+ for( final Domain domain : domain_ary ) {
+ if ( first ) {
+ first = false;
+ }
+ else {
+ out.write( "," );
+ }
+ out.write( domain.getDomainId().toString() );
+ out.write( ":" + domain.getFrom() + "-" + domain.getTo() );
+ out.write( ":" + domain.getPerDomainEvalue() );
+ }
+ out.write( "}" );
+ if ( !( ForesterUtil.isEmpty( protein.getDescription() ) || protein.getDescription()
+ .equals( SurfacingConstants.NONE ) ) ) {
+ out.write( protein.getDescription() );
+ }
+ out.write( separator );
+ if ( !( ForesterUtil.isEmpty( protein.getAccession() ) || protein.getAccession()
+ .equals( SurfacingConstants.NONE ) ) ) {
+ out.write( protein.getAccession() );
+ }
+ out.write( SurfacingConstants.NL );
+ }
+ }
+ }
+ }
+ out.flush();
+ }
+
+ public static SortedSet<String> getAllDomainIds( final List<GenomeWideCombinableDomains> gwcd_list ) {
+ final SortedSet<String> all_domains_ids = new TreeSet<String>();
for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
- final Set<DomainId> all_domains = gwcd.getAllDomainIds();
+ final Set<String> all_domains = gwcd.getAllDomainIds();
// for( final Domain domain : all_domains ) {
all_domains_ids.addAll( all_domains );
// }
for( final Protein protein_domain_collection : protein_domain_collections ) {
for( final Object name : protein_domain_collection.getProteinDomains() ) {
final BasicDomain protein_domain = ( BasicDomain ) name;
- final String id = protein_domain.getDomainId().getId();
+ final String id = protein_domain.getDomainId();
if ( map.containsKey( id ) ) {
map.put( id, map.get( id ) + 1 );
}
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;
}
}
return true;
}
+ public static void performDomainArchitectureAnalysis( final SortedMap<String, Set<String>> domain_architecutures,
+ final SortedMap<String, Integer> domain_architecuture_counts,
+ final int min_count,
+ final File da_counts_outfile,
+ final File unique_da_outfile ) {
+ checkForOutputFileWriteability( da_counts_outfile );
+ checkForOutputFileWriteability( unique_da_outfile );
+ try {
+ final BufferedWriter da_counts_out = new BufferedWriter( new FileWriter( da_counts_outfile ) );
+ final BufferedWriter unique_da_out = new BufferedWriter( new FileWriter( unique_da_outfile ) );
+ final Iterator<Entry<String, Integer>> it = domain_architecuture_counts.entrySet().iterator();
+ while ( it.hasNext() ) {
+ final Map.Entry<String, Integer> e = it.next();
+ final String da = e.getKey();
+ final int count = e.getValue();
+ if ( count >= min_count ) {
+ da_counts_out.write( da );
+ da_counts_out.write( "\t" );
+ da_counts_out.write( String.valueOf( count ) );
+ da_counts_out.write( ForesterUtil.LINE_SEPARATOR );
+ }
+ if ( count == 1 ) {
+ final Iterator<Entry<String, Set<String>>> it2 = domain_architecutures.entrySet().iterator();
+ while ( it2.hasNext() ) {
+ final Map.Entry<String, Set<String>> e2 = it2.next();
+ final String genome = e2.getKey();
+ final Set<String> das = e2.getValue();
+ if ( das.contains( da ) ) {
+ unique_da_out.write( genome );
+ unique_da_out.write( "\t" );
+ unique_da_out.write( da );
+ unique_da_out.write( ForesterUtil.LINE_SEPARATOR );
+ }
+ }
+ }
+ }
+ unique_da_out.close();
+ da_counts_out.close();
+ }
+ catch ( final IOException e ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
+ }
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote distance matrices to \"" + da_counts_outfile + "\"" );
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote distance matrices to \"" + unique_da_outfile + "\"" );
+ //
+ }
+
public static void preparePhylogeny( final Phylogeny p,
final DomainParsimonyCalculator domain_parsimony,
final String date_time,
if ( domains.size() > 1 ) {
final Map<String, Integer> counts = new HashMap<String, Integer>();
for( final Domain domain : domains ) {
- final String id = domain.getDomainId().getId();
+ final String id = domain.getDomainId();
if ( counts.containsKey( id ) ) {
counts.put( id, counts.get( id ) + 1 );
}
domain_n = domains.get( j );
domain_c = domains.get( i );
}
- final String dc = domain_n.getDomainId().getId() + domain_c.getDomainId().getId();
+ final String dc = domain_n.getDomainId() + domain_c.getDomainId();
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( domain_n.getDomainId() );
sb.append( separator );
- sb.append( domain_c.getDomainId().getId() );
+ sb.append( domain_c.getDomainId() );
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( counts.get( domain_n.getDomainId() ) );
sb.append( separator );
- sb.append( counts.get( domain_c.getDomainId().getId() ) );
+ sb.append( counts.get( domain_c.getDomainId() ) );
sb.append( ForesterUtil.LINE_SEPARATOR );
}
}
sb.append( separator );
sb.append( protein_id );
sb.append( separator );
- sb.append( domains.get( 0 ).getDomainId().getId() );
+ sb.append( domains.get( 0 ).getDomainId() );
sb.append( separator );
sb.append( separator );
sb.append( domains.get( 0 ).getPerDomainEvalue() );
final boolean remove_engulfed_domains,
final Protein protein ) {
final Protein pruned_protein = new BasicProtein( protein.getProteinId().getId(), protein.getSpecies()
- .getSpeciesId() );
+ .getSpeciesId(), protein.getLength() );
final List<Domain> sorted = SurfacingUtil.sortDomainsWithAscendingConfidenceValues( protein );
final List<Boolean> covered_positions = new ArrayList<Boolean>();
for( final Domain domain : sorted ) {
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 );
+ public static int storeDomainArchitectures( final String genome,
+ final SortedMap<String, Set<String>> domain_architecutures,
+ final List<Protein> protein_list,
+ final Map<String, Integer> distinct_domain_architecuture_counts ) {
+ final Set<String> da = new HashSet<String>();
+ domain_architecutures.put( genome, da );
+ for( final Protein protein : protein_list ) {
+ final String da_str = ( ( BasicProtein ) protein ).toDomainArchitectureString( "~", 3, "=" );
+ if ( !da.contains( da_str ) ) {
+ if ( !distinct_domain_architecuture_counts.containsKey( da_str ) ) {
+ distinct_domain_architecuture_counts.put( da_str, 1 );
+ }
+ else {
+ distinct_domain_architecuture_counts.put( da_str,
+ distinct_domain_architecuture_counts.get( da_str ) + 1 );
+ }
+ da.add( da_str );
+ }
}
- final List<String> l = new ArrayList<String>( 2 );
- l.add( s[ 0 ] );
- l.add( s[ 1 ] );
- return l;
+ return da.size();
}
public static void writeAllDomainsChangedOnAllSubtrees( final Phylogeny p,
}
}
- private static void writeAllEncounteredPfamsToFile( final Map<DomainId, List<GoId>> domain_id_to_go_ids_map,
- final Map<GoId, GoTerm> go_id_to_term_map,
- final String outfile_name,
- final SortedSet<String> all_pfams_encountered ) {
- final File all_pfams_encountered_file = new File( outfile_name + surfacing.ALL_PFAMS_ENCOUNTERED_SUFFIX );
- final File all_pfams_encountered_with_go_annotation_file = new File( outfile_name
- + surfacing.ALL_PFAMS_ENCOUNTERED_WITH_GO_ANNOTATION_SUFFIX );
- final File encountered_pfams_summary_file = new File( outfile_name + surfacing.ENCOUNTERED_PFAMS_SUMMARY_SUFFIX );
- int biological_process_counter = 0;
- int cellular_component_counter = 0;
- int molecular_function_counter = 0;
- int pfams_with_mappings_counter = 0;
- int pfams_without_mappings_counter = 0;
- int pfams_without_mappings_to_bp_or_mf_counter = 0;
- int pfams_with_mappings_to_bp_or_mf_counter = 0;
- try {
- final Writer all_pfams_encountered_writer = new BufferedWriter( new FileWriter( all_pfams_encountered_file ) );
- final Writer all_pfams_encountered_with_go_annotation_writer = new BufferedWriter( new FileWriter( all_pfams_encountered_with_go_annotation_file ) );
- final Writer summary_writer = new BufferedWriter( new FileWriter( encountered_pfams_summary_file ) );
- summary_writer.write( "# Pfam to GO mapping summary" );
- summary_writer.write( ForesterUtil.LINE_SEPARATOR );
- summary_writer.write( "# Actual summary is at the end of this file." );
- summary_writer.write( ForesterUtil.LINE_SEPARATOR );
- summary_writer.write( "# Encountered Pfams without a GO mapping:" );
- summary_writer.write( ForesterUtil.LINE_SEPARATOR );
- for( final String pfam : all_pfams_encountered ) {
- all_pfams_encountered_writer.write( pfam );
- all_pfams_encountered_writer.write( ForesterUtil.LINE_SEPARATOR );
- final DomainId domain_id = new DomainId( pfam );
- if ( domain_id_to_go_ids_map.containsKey( domain_id ) ) {
- ++pfams_with_mappings_counter;
- all_pfams_encountered_with_go_annotation_writer.write( pfam );
- all_pfams_encountered_with_go_annotation_writer.write( ForesterUtil.LINE_SEPARATOR );
- final List<GoId> go_ids = domain_id_to_go_ids_map.get( domain_id );
- boolean maps_to_bp = false;
- boolean maps_to_cc = false;
- boolean maps_to_mf = false;
- for( final GoId go_id : go_ids ) {
- final GoTerm go_term = go_id_to_term_map.get( go_id );
- if ( go_term.getGoNameSpace().isBiologicalProcess() ) {
- maps_to_bp = true;
- }
- else if ( go_term.getGoNameSpace().isCellularComponent() ) {
- maps_to_cc = true;
- }
- else if ( go_term.getGoNameSpace().isMolecularFunction() ) {
- maps_to_mf = true;
- }
- }
- if ( maps_to_bp ) {
- ++biological_process_counter;
- }
- if ( maps_to_cc ) {
- ++cellular_component_counter;
- }
- if ( maps_to_mf ) {
- ++molecular_function_counter;
- }
- if ( maps_to_bp || maps_to_mf ) {
- ++pfams_with_mappings_to_bp_or_mf_counter;
- }
- else {
- ++pfams_without_mappings_to_bp_or_mf_counter;
- }
- }
- else {
- ++pfams_without_mappings_to_bp_or_mf_counter;
- ++pfams_without_mappings_counter;
- summary_writer.write( pfam );
- summary_writer.write( ForesterUtil.LINE_SEPARATOR );
- }
- }
- all_pfams_encountered_writer.close();
- all_pfams_encountered_with_go_annotation_writer.close();
- ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote all [" + all_pfams_encountered.size()
- + "] encountered Pfams to: \"" + all_pfams_encountered_file + "\"" );
- ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote all [" + pfams_with_mappings_counter
- + "] encountered Pfams with GO mappings to: \"" + all_pfams_encountered_with_go_annotation_file
- + "\"" );
- ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote summary (including all ["
- + pfams_without_mappings_counter + "] encountered Pfams without GO mappings) to: \""
- + encountered_pfams_summary_file + "\"" );
- ForesterUtil.programMessage( surfacing.PRG_NAME, "Sum of Pfams encountered : "
- + all_pfams_encountered.size() );
- ForesterUtil.programMessage( surfacing.PRG_NAME, "Pfams without a mapping : "
- + pfams_without_mappings_counter + " ["
- + ( 100 * pfams_without_mappings_counter / all_pfams_encountered.size() ) + "%]" );
- ForesterUtil.programMessage( surfacing.PRG_NAME, "Pfams without mapping to proc. or func. : "
- + pfams_without_mappings_to_bp_or_mf_counter + " ["
- + ( 100 * pfams_without_mappings_to_bp_or_mf_counter / all_pfams_encountered.size() ) + "%]" );
- ForesterUtil.programMessage( surfacing.PRG_NAME,
- "Pfams with a mapping : " + pfams_with_mappings_counter
- + " ["
- + ( 100 * pfams_with_mappings_counter / all_pfams_encountered.size() )
- + "%]" );
- ForesterUtil.programMessage( surfacing.PRG_NAME, "Pfams with a mapping to proc. or func. : "
- + pfams_with_mappings_to_bp_or_mf_counter + " ["
- + ( 100 * pfams_with_mappings_to_bp_or_mf_counter / all_pfams_encountered.size() ) + "%]" );
- ForesterUtil.programMessage( surfacing.PRG_NAME,
- "Pfams with mapping to biological process: " + biological_process_counter
- + " ["
- + ( 100 * biological_process_counter / all_pfams_encountered.size() )
- + "%]" );
- ForesterUtil.programMessage( surfacing.PRG_NAME,
- "Pfams with mapping to molecular function: " + molecular_function_counter
- + " ["
- + ( 100 * molecular_function_counter / all_pfams_encountered.size() )
- + "%]" );
- ForesterUtil.programMessage( surfacing.PRG_NAME,
- "Pfams with mapping to cellular component: " + cellular_component_counter
- + " ["
- + ( 100 * cellular_component_counter / all_pfams_encountered.size() )
- + "%]" );
- summary_writer.write( ForesterUtil.LINE_SEPARATOR );
- summary_writer.write( "# Sum of Pfams encountered : " + all_pfams_encountered.size() );
- summary_writer.write( ForesterUtil.LINE_SEPARATOR );
- summary_writer.write( "# Pfams without a mapping : " + pfams_without_mappings_counter
- + " [" + ( 100 * pfams_without_mappings_counter / all_pfams_encountered.size() ) + "%]" );
- summary_writer.write( ForesterUtil.LINE_SEPARATOR );
- summary_writer.write( "# Pfams without mapping to proc. or func. : "
- + pfams_without_mappings_to_bp_or_mf_counter + " ["
- + ( 100 * pfams_without_mappings_to_bp_or_mf_counter / all_pfams_encountered.size() ) + "%]" );
- summary_writer.write( ForesterUtil.LINE_SEPARATOR );
- summary_writer.write( "# Pfams with a mapping : " + pfams_with_mappings_counter + " ["
- + ( 100 * pfams_with_mappings_counter / all_pfams_encountered.size() ) + "%]" );
- summary_writer.write( ForesterUtil.LINE_SEPARATOR );
- summary_writer.write( "# Pfams with a mapping to proc. or func. : "
- + pfams_with_mappings_to_bp_or_mf_counter + " ["
- + ( 100 * pfams_with_mappings_to_bp_or_mf_counter / all_pfams_encountered.size() ) + "%]" );
- summary_writer.write( ForesterUtil.LINE_SEPARATOR );
- summary_writer.write( "# Pfams with mapping to biological process: " + biological_process_counter + " ["
- + ( 100 * biological_process_counter / all_pfams_encountered.size() ) + "%]" );
- summary_writer.write( ForesterUtil.LINE_SEPARATOR );
- summary_writer.write( "# Pfams with mapping to molecular function: " + molecular_function_counter + " ["
- + ( 100 * molecular_function_counter / all_pfams_encountered.size() ) + "%]" );
- summary_writer.write( ForesterUtil.LINE_SEPARATOR );
- summary_writer.write( "# Pfams with mapping to cellular component: " + cellular_component_counter + " ["
- + ( 100 * cellular_component_counter / all_pfams_encountered.size() ) + "%]" );
- summary_writer.write( ForesterUtil.LINE_SEPARATOR );
- summary_writer.close();
- }
- catch ( final IOException e ) {
- ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "Failure to write: " + e );
- }
- }
-
public static void writeBinaryDomainCombinationsFileForGraphAnalysis( final String[][] input_file_properties,
final File output_dir,
final GenomeWideCombinableDomains gwcd,
final int i,
final GenomeWideCombinableDomainsSortOrder dc_sort_order ) {
- File dc_outfile_dot = new File( input_file_properties[ i ][ 0 ]
+ File dc_outfile_dot = new File( input_file_properties[ i ][ 1 ]
+ surfacing.DOMAIN_COMBINITONS_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS );
if ( output_dir != null ) {
dc_outfile_dot = new File( output_dir + ForesterUtil.FILE_SEPARATOR + dc_outfile_dot );
ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote characters list: \"" + filename + "\"" );
}
- public static void writeBinaryStatesMatrixToList( final Map<DomainId, List<GoId>> domain_id_to_go_ids_map,
+ public static void writeBinaryStatesMatrixToList( final Map<String, List<GoId>> domain_id_to_go_ids_map,
final Map<GoId, GoTerm> go_id_to_term_map,
final GoNameSpace go_namespace_limit,
final boolean domain_combinations,
final String character_separator,
final String title_for_html,
final String prefix_for_html,
- final Map<DomainId, Set<String>>[] domain_id_to_secondary_features_maps,
+ final Map<String, Set<String>>[] domain_id_to_secondary_features_maps,
final SortedSet<String> all_pfams_encountered,
final SortedSet<String> pfams_gained_or_lost,
- final String suffix_for_per_node_events_file ) {
+ final String suffix_for_per_node_events_file,
+ final Map<String, Integer> tax_code_to_id_map ) {
if ( ( go_namespace_limit != null ) && ( ( go_id_to_term_map == null ) || ( go_id_to_term_map.size() < 1 ) ) ) {
throw new IllegalArgumentException( "attempt to use GO namespace limit without a GO-id to term map" );
}
out.write( SurfacingConstants.NL );
out.write( "<h2>" );
out.write( "<a name=\"" + id + "\">" + id + "</a>" );
- writeTaxonomyLinks( out, id );
+ writeTaxonomyLinks( out, id, tax_code_to_id_map );
out.write( "</h2>" );
out.write( SurfacingConstants.NL );
out.write( "<table>" );
ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote characters detailed HTML list: \"" + filename + "\"" );
}
- public static void writeBinaryStatesMatrixToListORIGIG( 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 boolean domain_combinations,
- final CharacterStateMatrix<CharacterStateMatrix.GainLossStates> matrix,
- final CharacterStateMatrix.GainLossStates state,
- final String filename,
- final String indentifier_characters_separator,
- final String character_separator,
- final String title_for_html,
- final String prefix_for_html,
- final Map<DomainId, Set<String>>[] domain_id_to_secondary_features_maps,
- final SortedSet<String> all_pfams_encountered,
- final SortedSet<String> pfams_gained_or_lost,
- final String suffix_for_per_node_events_file ) {
- if ( ( go_namespace_limit != null ) && ( ( go_id_to_term_map == null ) || ( go_id_to_term_map.size() < 1 ) ) ) {
- throw new IllegalArgumentException( "attempt to use GO namespace limit without a GO-id to term map" );
- }
- else if ( ( ( domain_id_to_go_ids_map == null ) || ( domain_id_to_go_ids_map.size() < 1 ) ) ) {
- throw new IllegalArgumentException( "attempt to output detailed HTML without a Pfam to GO map" );
+ public static void writeDomainCombinationsCountsFile( final String[][] input_file_properties,
+ final File output_dir,
+ final Writer per_genome_domain_promiscuity_statistics_writer,
+ final GenomeWideCombinableDomains gwcd,
+ final int i,
+ final GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder dc_sort_order ) {
+ File dc_outfile = new File( input_file_properties[ i ][ 1 ]
+ + surfacing.DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX );
+ if ( output_dir != null ) {
+ dc_outfile = new File( output_dir + ForesterUtil.FILE_SEPARATOR + dc_outfile );
}
- else if ( ( ( go_id_to_term_map == null ) || ( go_id_to_term_map.size() < 1 ) ) ) {
- throw new IllegalArgumentException( "attempt to output detailed HTML without a GO-id to term map" );
+ checkForOutputFileWriteability( dc_outfile );
+ try {
+ final BufferedWriter out = new BufferedWriter( new FileWriter( dc_outfile ) );
+ out.write( gwcd.toStringBuilder( dc_sort_order ).toString() );
+ out.close();
}
- 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 ) );
+ catch ( final IOException e ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
}
+ final DescriptiveStatistics stats = gwcd.getPerGenomeDomainPromiscuityStatistics();
try {
- final Writer out = new BufferedWriter( new FileWriter( outfile ) );
- final File per_node_go_mapped_domain_gain_loss_files_base_dir = createBaseDirForPerNodeDomainFiles( surfacing.BASE_DIRECTORY_PER_NODE_DOMAIN_GAIN_LOSS_FILES,
- domain_combinations,
- state,
- filename );
- Writer per_node_go_mapped_domain_gain_loss_outfile_writer = null;
- File per_node_go_mapped_domain_gain_loss_outfile = null;
- int per_node_counter = 0;
- out.write( "<html>" );
- out.write( SurfacingConstants.NL );
- addHtmlHead( out, title_for_html );
- out.write( SurfacingConstants.NL );
- out.write( "<body>" );
- out.write( SurfacingConstants.NL );
- out.write( "<h1>" );
- out.write( SurfacingConstants.NL );
- out.write( title_for_html );
- out.write( SurfacingConstants.NL );
- out.write( "</h1>" );
- out.write( SurfacingConstants.NL );
- out.write( "<table>" );
- out.write( SurfacingConstants.NL );
- for( final String id : sorted_ids ) {
- out.write( "<tr>" );
- out.write( "<td>" );
- out.write( "<a href=\"#" + id + "\">" + id + "</a>" );
- writeTaxonomyLinks( out, id );
- out.write( "</td>" );
- out.write( "</tr>" );
- out.write( SurfacingConstants.NL );
+ per_genome_domain_promiscuity_statistics_writer.write( input_file_properties[ i ][ 1 ] + "\t" );
+ per_genome_domain_promiscuity_statistics_writer.write( FORMATTER_3.format( stats.arithmeticMean() ) + "\t" );
+ if ( stats.getN() < 2 ) {
+ per_genome_domain_promiscuity_statistics_writer.write( "n/a" + "\t" );
}
- out.write( "</table>" );
- out.write( SurfacingConstants.NL );
- for( final String id : sorted_ids ) {
- out.write( SurfacingConstants.NL );
- out.write( "<h2>" );
- out.write( "<a name=\"" + id + "\">" + id + "</a>" );
- writeTaxonomyLinks( out, id );
- out.write( "</h2>" );
- out.write( SurfacingConstants.NL );
- out.write( "<table>" );
- out.write( SurfacingConstants.NL );
- out.write( "<tr>" );
- out.write( "<td><b>" );
- out.write( "Pfam domain(s)" );
- out.write( "</b></td><td><b>" );
- out.write( "GO term acc" );
- out.write( "</b></td><td><b>" );
- out.write( "GO term" );
- out.write( "</b></td><td><b>" );
- out.write( "Penultimate GO term" );
- out.write( "</b></td><td><b>" );
- out.write( "GO namespace" );
- out.write( "</b></td>" );
- out.write( "</tr>" );
- out.write( SurfacingConstants.NL );
- out.write( "</tr>" );
- out.write( SurfacingConstants.NL );
- per_node_counter = 0;
- if ( matrix.getNumberOfCharacters() > 0 ) {
- per_node_go_mapped_domain_gain_loss_outfile = new File( per_node_go_mapped_domain_gain_loss_files_base_dir
- + ForesterUtil.FILE_SEPARATOR + id + suffix_for_per_node_events_file );
- SurfacingUtil.checkForOutputFileWriteability( per_node_go_mapped_domain_gain_loss_outfile );
- per_node_go_mapped_domain_gain_loss_outfile_writer = ForesterUtil
- .createBufferedWriter( per_node_go_mapped_domain_gain_loss_outfile );
+ else {
+ per_genome_domain_promiscuity_statistics_writer.write( FORMATTER_3.format( stats
+ .sampleStandardDeviation() ) + "\t" );
+ }
+ per_genome_domain_promiscuity_statistics_writer.write( FORMATTER_3.format( stats.median() ) + "\t" );
+ per_genome_domain_promiscuity_statistics_writer.write( ( int ) stats.getMin() + "\t" );
+ per_genome_domain_promiscuity_statistics_writer.write( ( int ) stats.getMax() + "\t" );
+ per_genome_domain_promiscuity_statistics_writer.write( stats.getN() + "\t" );
+ final SortedSet<String> mpds = gwcd.getMostPromiscuosDomain();
+ for( final String mpd : mpds ) {
+ per_genome_domain_promiscuity_statistics_writer.write( mpd + " " );
+ }
+ per_genome_domain_promiscuity_statistics_writer.write( ForesterUtil.LINE_SEPARATOR );
+ }
+ catch ( final IOException e ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
+ }
+ if ( input_file_properties[ i ].length == 3 ) {
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote domain combination counts for \""
+ + input_file_properties[ i ][ 0 ] + "\" (" + input_file_properties[ i ][ 1 ] + ", "
+ + input_file_properties[ i ][ 2 ] + ") to: \"" + dc_outfile + "\"" );
+ }
+ else {
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote domain combination counts for \""
+ + input_file_properties[ i ][ 0 ] + "\" (" + input_file_properties[ i ][ 1 ] + ") to: \""
+ + dc_outfile + "\"" );
+ }
+ }
+
+ public static void writeDomainSimilaritiesToFile( final StringBuilder html_desc,
+ final StringBuilder html_title,
+ final Writer simple_tab_writer,
+ final Writer single_writer,
+ Map<Character, Writer> split_writers,
+ final SortedSet<DomainSimilarity> similarities,
+ final boolean treat_as_binary,
+ final List<Species> species_order,
+ final PrintableDomainSimilarity.PRINT_OPTION print_option,
+ final DomainSimilarity.DomainSimilarityScoring scoring,
+ final boolean verbose,
+ final Map<String, Integer> tax_code_to_id_map )
+ throws IOException {
+ 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:
+ 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, "DC analysis (" + html_title + ") " + key.toString().toUpperCase() );
+ }
+ else {
+ addHtmlHead( w, "DC analysis (" + 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( SurfacingConstants.NL );
+ w.write( "<br>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<table>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<tr><td><b>Domains:</b></td></tr>" );
+ w.write( SurfacingConstants.NL );
}
- else {
- per_node_go_mapped_domain_gain_loss_outfile = null;
- per_node_go_mapped_domain_gain_loss_outfile_writer = null;
+ break;
+ }
+ //
+ for( final DomainSimilarity similarity : similarities ) {
+ if ( ( species_order != null ) && !species_order.isEmpty() ) {
+ ( ( PrintableDomainSimilarity ) similarity ).setSpeciesOrder( species_order );
+ }
+ if ( single_writer != null ) {
+ single_writer.write( "<tr><td><b><a href=\"#" + similarity.getDomainId() + "\">"
+ + similarity.getDomainId() + "</a></b></td></tr>" );
+ single_writer.write( SurfacingConstants.NL );
+ }
+ else {
+ Writer local_writer = split_writers.get( ( similarity.getDomainId().charAt( 0 ) + "" ).toLowerCase()
+ .charAt( 0 ) );
+ if ( local_writer == null ) {
+ local_writer = split_writers.get( '0' );
}
- for( int c = 0; c < matrix.getNumberOfCharacters(); ++c ) {
- // Not nice:
- // using null to indicate either UNCHANGED_PRESENT or GAIN.
- if ( ( matrix.getState( id, c ) == state )
- || ( ( state == null ) && ( ( matrix.getState( id, c ) == CharacterStateMatrix.GainLossStates.UNCHANGED_PRESENT ) || ( matrix
- .getState( id, c ) == CharacterStateMatrix.GainLossStates.GAIN ) ) ) ) {
- final String character = matrix.getCharacter( c );
- String domain_0 = "";
- String domain_1 = "";
- if ( character.indexOf( BinaryDomainCombination.SEPARATOR ) > 0 ) {
- final String[] s = character.split( BinaryDomainCombination.SEPARATOR );
- if ( s.length != 2 ) {
- throw new AssertionError( "this should not have happened: unexpected format for domain combination: ["
- + character + "]" );
- }
- domain_0 = s[ 0 ];
- domain_1 = s[ 1 ];
- }
- else {
- domain_0 = character;
- }
- writeDomainData( domain_id_to_go_ids_map,
- go_id_to_term_map,
- go_namespace_limit,
- out,
- domain_0,
- domain_1,
- prefix_for_html,
- character_separator,
- domain_id_to_secondary_features_maps,
- null );
- all_pfams_encountered.add( domain_0 );
- if ( pfams_gained_or_lost != null ) {
- pfams_gained_or_lost.add( domain_0 );
- }
- if ( !ForesterUtil.isEmpty( domain_1 ) ) {
- all_pfams_encountered.add( domain_1 );
- if ( pfams_gained_or_lost != null ) {
- pfams_gained_or_lost.add( domain_1 );
- }
- }
- if ( per_node_go_mapped_domain_gain_loss_outfile_writer != null ) {
- writeDomainsToIndividualFilePerTreeNode( per_node_go_mapped_domain_gain_loss_outfile_writer,
- domain_0,
- domain_1 );
- per_node_counter++;
- }
- }
+ local_writer.write( "<tr><td><b><a href=\"#" + similarity.getDomainId() + "\">"
+ + similarity.getDomainId() + "</a></b></td></tr>" );
+ local_writer.write( SurfacingConstants.NL );
+ }
+ }
+ for( final Writer w : split_writers.values() ) {
+ w.write( "</table>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<hr>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<table>" );
+ w.write( SurfacingConstants.NL );
+ }
+ //
+ for( final DomainSimilarity similarity : similarities ) {
+ if ( ( species_order != null ) && !species_order.isEmpty() ) {
+ ( ( PrintableDomainSimilarity ) similarity ).setSpeciesOrder( species_order );
+ }
+ if ( simple_tab_writer != null ) {
+ simple_tab_writer.write( similarity.toStringBuffer( PRINT_OPTION.SIMPLE_TAB_DELIMITED,
+ tax_code_to_id_map ).toString() );
+ }
+ if ( single_writer != null ) {
+ single_writer.write( similarity.toStringBuffer( print_option, tax_code_to_id_map ).toString() );
+ single_writer.write( SurfacingConstants.NL );
+ }
+ else {
+ Writer local_writer = split_writers.get( ( similarity.getDomainId().charAt( 0 ) + "" ).toLowerCase()
+ .charAt( 0 ) );
+ if ( local_writer == null ) {
+ local_writer = split_writers.get( '0' );
}
- if ( per_node_go_mapped_domain_gain_loss_outfile_writer != null ) {
- per_node_go_mapped_domain_gain_loss_outfile_writer.close();
- if ( per_node_counter < 1 ) {
- per_node_go_mapped_domain_gain_loss_outfile.delete();
- }
- per_node_counter = 0;
+ local_writer.write( similarity.toStringBuffer( print_option, tax_code_to_id_map ).toString() );
+ local_writer.write( SurfacingConstants.NL );
+ }
+ }
+ switch ( print_option ) {
+ case HTML:
+ 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 );
}
- out.write( "</table>" );
- out.write( SurfacingConstants.NL );
- out.write( "<hr>" );
- out.write( SurfacingConstants.NL );
- } // for( final String id : sorted_ids ) {
- out.write( "</body>" );
- out.write( SurfacingConstants.NL );
- out.write( "</html>" );
- out.write( SurfacingConstants.NL );
+ break;
+ }
+ for( final Writer w : split_writers.values() ) {
+ w.close();
+ }
+ }
+
+ private static void printSomeStats( final DescriptiveStatistics stats, final AsciiHistogram histo, final Writer w )
+ throws IOException {
+ 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( "</table>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<br>" );
+ w.write( SurfacingConstants.NL );
+ }
+
+ public static void writeMatrixToFile( final CharacterStateMatrix<?> matrix,
+ final String filename,
+ final Format format ) {
+ final File outfile = new File( filename );
+ checkForOutputFileWriteability( outfile );
+ try {
+ final BufferedWriter out = new BufferedWriter( new FileWriter( outfile ) );
+ matrix.toWriter( out, format );
out.flush();
out.close();
}
catch ( final IOException e ) {
ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
}
- ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote characters detailed HTML list: \"" + filename + "\"" );
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote matrix: \"" + filename + "\"" );
}
- public static void writeDomainCombinationsCountsFile( final String[][] input_file_properties,
- final File output_dir,
- final Writer per_genome_domain_promiscuity_statistics_writer,
- final GenomeWideCombinableDomains gwcd,
- final int i,
- final GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder dc_sort_order ) {
- File dc_outfile = new File( input_file_properties[ i ][ 0 ]
- + surfacing.DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX );
- if ( output_dir != null ) {
- dc_outfile = new File( output_dir + ForesterUtil.FILE_SEPARATOR + dc_outfile );
- }
- checkForOutputFileWriteability( dc_outfile );
+ public static void writeMatrixToFile( final File matrix_outfile, final List<DistanceMatrix> matrices ) {
+ checkForOutputFileWriteability( matrix_outfile );
try {
- final BufferedWriter out = new BufferedWriter( new FileWriter( dc_outfile ) );
- out.write( gwcd.toStringBuilder( dc_sort_order ).toString() );
+ final BufferedWriter out = new BufferedWriter( new FileWriter( matrix_outfile ) );
+ for( final DistanceMatrix distance_matrix : matrices ) {
+ out.write( distance_matrix.toStringBuffer( DistanceMatrix.Format.PHYLIP ).toString() );
+ out.write( ForesterUtil.LINE_SEPARATOR );
+ out.flush();
+ }
out.close();
}
catch ( final IOException e ) {
ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
}
- final DescriptiveStatistics stats = gwcd.getPerGenomeDomainPromiscuityStatistics();
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote distance matrices to \"" + matrix_outfile + "\"" );
+ }
+
+ public static void writePhylogenyToFile( final Phylogeny phylogeny, final String filename ) {
+ final PhylogenyWriter writer = new PhylogenyWriter();
try {
- per_genome_domain_promiscuity_statistics_writer.write( input_file_properties[ i ][ 0 ] + "\t" );
- per_genome_domain_promiscuity_statistics_writer.write( FORMATTER_3.format( stats.arithmeticMean() ) + "\t" );
- if ( stats.getN() < 2 ) {
- per_genome_domain_promiscuity_statistics_writer.write( "n/a" + "\t" );
+ writer.toPhyloXML( new File( filename ), phylogeny, 1 );
+ }
+ catch ( final IOException e ) {
+ ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "failed to write phylogeny to \"" + filename + "\": "
+ + e );
+ }
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote phylogeny to \"" + filename + "\"" );
+ }
+
+ public static void writeTaxonomyLinks( final Writer writer,
+ final String species,
+ final Map<String, Integer> tax_code_to_id_map ) throws IOException {
+ if ( ( species.length() > 1 ) && ( species.indexOf( '_' ) < 1 ) ) {
+ writer.write( " [" );
+ if ( ( tax_code_to_id_map != null ) && tax_code_to_id_map.containsKey( species ) ) {
+ writer.write( "<a href=\"" + SurfacingConstants.UNIPROT_TAXONOMY_ID_LINK
+ + tax_code_to_id_map.get( species ) + "\" target=\"taxonomy_window\">uniprot</a>" );
}
else {
- per_genome_domain_promiscuity_statistics_writer.write( FORMATTER_3.format( stats
- .sampleStandardDeviation() ) + "\t" );
+ writer.write( "<a href=\"" + SurfacingConstants.EOL_LINK + species
+ + "\" target=\"taxonomy_window\">eol</a>" );
+ writer.write( "|" );
+ writer.write( "<a href=\"" + SurfacingConstants.GOOGLE_SCHOLAR_SEARCH + species
+ + "\" target=\"taxonomy_window\">scholar</a>" );
+ writer.write( "|" );
+ writer.write( "<a href=\"" + SurfacingConstants.GOOGLE_WEB_SEARCH_LINK + species
+ + "\" target=\"taxonomy_window\">google</a>" );
}
- per_genome_domain_promiscuity_statistics_writer.write( FORMATTER_3.format( stats.median() ) + "\t" );
- per_genome_domain_promiscuity_statistics_writer.write( ( int ) stats.getMin() + "\t" );
- per_genome_domain_promiscuity_statistics_writer.write( ( int ) stats.getMax() + "\t" );
- per_genome_domain_promiscuity_statistics_writer.write( stats.getN() + "\t" );
- final SortedSet<DomainId> mpds = gwcd.getMostPromiscuosDomain();
- for( final DomainId mpd : mpds ) {
- per_genome_domain_promiscuity_statistics_writer.write( mpd.getId() + " " );
+ writer.write( "]" );
+ }
+ }
+
+ 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 );
+ }
+ }
+
+ 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,
+ final String outfilename_for_protein_stats,
+ final Map<String, DescriptiveStatistics> protein_length_stats_by_dc,
+ final Map<String, DescriptiveStatistics> domain_number_stats_by_dc,
+ final Map<String, DescriptiveStatistics> domain_length_stats_by_domain ) {
+ try {
+ //
+ // if ( protein_length_stats_by_dc != null ) {
+ // for( final Entry<?, DescriptiveStatistics> entry : protein_length_stats_by_dc.entrySet() ) {
+ // System.out.print( entry.getKey().toString() );
+ // System.out.print( ": " );
+ // double[] a = entry.getValue().getDataAsDoubleArray();
+ // for( int i = 0; i < a.length; i++ ) {
+ // System.out.print( a[ i ] + " " );
+ // }
+ // System.out.println();
+ // }
+ // }
+ // if ( domain_number_stats_by_dc != null ) {
+ // for( final Entry<?, DescriptiveStatistics> entry : domain_number_stats_by_dc.entrySet() ) {
+ // System.out.print( entry.getKey().toString() );
+ // System.out.print( ": " );
+ // double[] a = entry.getValue().getDataAsDoubleArray();
+ // for( int i = 0; i < a.length; i++ ) {
+ // System.out.print( a[ i ] + " " );
+ // }
+ // System.out.println();
+ // }
+ // }
+ //
+ 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, DescriptiveStatistics> dc_reapp_counts_to_protein_length_stats = new TreeMap<Integer, DescriptiveStatistics>();
+ final SortedMap<Integer, DescriptiveStatistics> dc_reapp_counts_to_domain_number_stats = new TreeMap<Integer, DescriptiveStatistics>();
+ final SortedMap<Integer, DescriptiveStatistics> dc_reapp_counts_to_domain_lengths_stats = new TreeMap<Integer, DescriptiveStatistics>();
+ 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>();
+ DescriptiveStatistics gained_once_lengths_stats = new BasicDescriptiveStatistics();
+ DescriptiveStatistics gained_once_domain_count_stats = new BasicDescriptiveStatistics();
+ DescriptiveStatistics gained_multiple_times_lengths_stats = new BasicDescriptiveStatistics();
+ final DescriptiveStatistics gained_multiple_times_domain_count_stats = new BasicDescriptiveStatistics();
+ long gained_multiple_times_domain_length_sum = 0;
+ long gained_once_domain_length_sum = 0;
+ long gained_multiple_times_domain_length_count = 0;
+ long gained_once_domain_length_count = 0;
+ 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 ( protein_length_stats_by_dc != null ) {
+ if ( !dc_reapp_counts_to_protein_length_stats.containsKey( count ) ) {
+ dc_reapp_counts_to_protein_length_stats.put( count, new BasicDescriptiveStatistics() );
+ }
+ dc_reapp_counts_to_protein_length_stats.get( count ).addValue( protein_length_stats_by_dc.get( dc )
+ .arithmeticMean() );
+ }
+ if ( domain_number_stats_by_dc != null ) {
+ if ( !dc_reapp_counts_to_domain_number_stats.containsKey( count ) ) {
+ dc_reapp_counts_to_domain_number_stats.put( count, new BasicDescriptiveStatistics() );
+ }
+ dc_reapp_counts_to_domain_number_stats.get( count ).addValue( domain_number_stats_by_dc.get( dc )
+ .arithmeticMean() );
+ }
+ if ( domain_length_stats_by_domain != null ) {
+ if ( !dc_reapp_counts_to_domain_lengths_stats.containsKey( count ) ) {
+ dc_reapp_counts_to_domain_lengths_stats.put( count, new BasicDescriptiveStatistics() );
+ }
+ final String[] ds = dc.split( "=" );
+ dc_reapp_counts_to_domain_lengths_stats.get( count ).addValue( domain_length_stats_by_domain
+ .get( ds[ 0 ] ).arithmeticMean() );
+ dc_reapp_counts_to_domain_lengths_stats.get( count ).addValue( domain_length_stats_by_domain
+ .get( ds[ 1 ] ).arithmeticMean() );
+ }
+ if ( count > 1 ) {
+ more_than_once.add( dc );
+ if ( protein_length_stats_by_dc != null ) {
+ final DescriptiveStatistics s = protein_length_stats_by_dc.get( dc );
+ for( final double element : s.getData() ) {
+ gained_multiple_times_lengths_stats.addValue( element );
+ }
+ }
+ if ( domain_number_stats_by_dc != null ) {
+ final DescriptiveStatistics s = domain_number_stats_by_dc.get( dc );
+ for( final double element : s.getData() ) {
+ gained_multiple_times_domain_count_stats.addValue( element );
+ }
+ }
+ if ( domain_length_stats_by_domain != null ) {
+ final String[] ds = dc.split( "=" );
+ final DescriptiveStatistics s0 = domain_length_stats_by_domain.get( ds[ 0 ] );
+ final DescriptiveStatistics s1 = domain_length_stats_by_domain.get( ds[ 1 ] );
+ for( final double element : s0.getData() ) {
+ gained_multiple_times_domain_length_sum += element;
+ ++gained_multiple_times_domain_length_count;
+ }
+ for( final double element : s1.getData() ) {
+ gained_multiple_times_domain_length_sum += element;
+ ++gained_multiple_times_domain_length_count;
+ }
+ }
+ }
+ else {
+ if ( protein_length_stats_by_dc != null ) {
+ final DescriptiveStatistics s = protein_length_stats_by_dc.get( dc );
+ for( final double element : s.getData() ) {
+ gained_once_lengths_stats.addValue( element );
+ }
+ }
+ if ( domain_number_stats_by_dc != null ) {
+ final DescriptiveStatistics s = domain_number_stats_by_dc.get( dc );
+ for( final double element : s.getData() ) {
+ gained_once_domain_count_stats.addValue( element );
+ }
+ }
+ if ( domain_length_stats_by_domain != null ) {
+ final String[] ds = dc.split( "=" );
+ final DescriptiveStatistics s0 = domain_length_stats_by_domain.get( ds[ 0 ] );
+ final DescriptiveStatistics s1 = domain_length_stats_by_domain.get( ds[ 1 ] );
+ for( final double element : s0.getData() ) {
+ gained_once_domain_length_sum += element;
+ ++gained_once_domain_length_count;
+ }
+ for( final double element : s1.getData() ) {
+ gained_once_domain_length_sum += element;
+ ++gained_once_domain_length_count;
+ }
+ }
+ }
+ }
+ 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.calculateLCA( 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();
+ if ( !ForesterUtil.isEmpty( outfilename_for_protein_stats )
+ && ( ( domain_length_stats_by_domain != null ) || ( protein_length_stats_by_dc != null ) || ( domain_number_stats_by_dc != null ) ) ) {
+ final BufferedWriter w = new BufferedWriter( new FileWriter( outfilename_for_protein_stats ) );
+ w.write( "Domain Lengths: " );
+ w.write( "\n" );
+ if ( domain_length_stats_by_domain != null ) {
+ for( final Entry<Integer, DescriptiveStatistics> entry : dc_reapp_counts_to_domain_lengths_stats
+ .entrySet() ) {
+ w.write( entry.getKey().toString() );
+ w.write( "\t" + entry.getValue().arithmeticMean() );
+ w.write( "\t" + entry.getValue().median() );
+ w.write( "\n" );
+ }
+ }
+ w.flush();
+ w.write( "\n" );
+ w.write( "\n" );
+ w.write( "Protein Lengths: " );
+ w.write( "\n" );
+ if ( protein_length_stats_by_dc != null ) {
+ for( final Entry<Integer, DescriptiveStatistics> entry : dc_reapp_counts_to_protein_length_stats
+ .entrySet() ) {
+ w.write( entry.getKey().toString() );
+ w.write( "\t" + entry.getValue().arithmeticMean() );
+ w.write( "\t" + entry.getValue().median() );
+ w.write( "\n" );
+ }
+ }
+ w.flush();
+ w.write( "\n" );
+ w.write( "\n" );
+ w.write( "Number of domains: " );
+ w.write( "\n" );
+ if ( domain_number_stats_by_dc != null ) {
+ for( final Entry<Integer, DescriptiveStatistics> entry : dc_reapp_counts_to_domain_number_stats
+ .entrySet() ) {
+ w.write( entry.getKey().toString() );
+ w.write( "\t" + entry.getValue().arithmeticMean() );
+ w.write( "\t" + entry.getValue().median() );
+ w.write( "\n" );
+ }
+ }
+ w.flush();
+ w.write( "\n" );
+ w.write( "\n" );
+ w.write( "Gained once, domain lengths:" );
+ w.write( "\n" );
+ w.write( "N: " + gained_once_domain_length_count );
+ w.write( "\n" );
+ w.write( "Avg: " + ( ( double ) gained_once_domain_length_sum / gained_once_domain_length_count ) );
+ w.write( "\n" );
+ w.write( "\n" );
+ w.write( "Gained multiple times, domain lengths:" );
+ w.write( "\n" );
+ w.write( "N: " + gained_multiple_times_domain_length_count );
+ w.write( "\n" );
+ w.write( "Avg: "
+ + ( ( double ) gained_multiple_times_domain_length_sum / gained_multiple_times_domain_length_count ) );
+ w.write( "\n" );
+ w.write( "\n" );
+ w.write( "\n" );
+ w.write( "\n" );
+ w.write( "Gained once, protein lengths:" );
+ w.write( "\n" );
+ w.write( gained_once_lengths_stats.toString() );
+ gained_once_lengths_stats = null;
+ w.write( "\n" );
+ w.write( "\n" );
+ w.write( "Gained once, domain counts:" );
+ w.write( "\n" );
+ w.write( gained_once_domain_count_stats.toString() );
+ gained_once_domain_count_stats = null;
+ w.write( "\n" );
+ w.write( "\n" );
+ w.write( "Gained multiple times, protein lengths:" );
+ w.write( "\n" );
+ w.write( gained_multiple_times_lengths_stats.toString() );
+ gained_multiple_times_lengths_stats = null;
+ w.write( "\n" );
+ w.write( "\n" );
+ w.write( "Gained multiple times, domain counts:" );
+ w.write( "\n" );
+ w.write( gained_multiple_times_domain_count_stats.toString() );
+ w.flush();
+ w.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 static SortedSet<String> collectAllDomainsChangedOnSubtree( final PhylogenyNode subtree_root,
+ final boolean get_gains ) {
+ final SortedSet<String> domains = new TreeSet<String>();
+ for( final PhylogenyNode descendant : PhylogenyMethods.getAllDescendants( subtree_root ) ) {
+ final BinaryCharacters chars = descendant.getNodeData().getBinaryCharacters();
+ if ( get_gains ) {
+ domains.addAll( chars.getGainedCharacters() );
+ }
+ else {
+ domains.addAll( chars.getLostCharacters() );
+ }
+ }
+ return domains;
+ }
+
+ private static File createBaseDirForPerNodeDomainFiles( final String base_dir,
+ final boolean domain_combinations,
+ final CharacterStateMatrix.GainLossStates state,
+ final String outfile ) {
+ File per_node_go_mapped_domain_gain_loss_files_base_dir = new File( new File( outfile ).getParent()
+ + ForesterUtil.FILE_SEPARATOR + base_dir );
+ if ( !per_node_go_mapped_domain_gain_loss_files_base_dir.exists() ) {
+ per_node_go_mapped_domain_gain_loss_files_base_dir.mkdir();
+ }
+ if ( domain_combinations ) {
+ per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir
+ + ForesterUtil.FILE_SEPARATOR + "DC" );
+ }
+ else {
+ per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir
+ + ForesterUtil.FILE_SEPARATOR + "DOMAINS" );
+ }
+ if ( !per_node_go_mapped_domain_gain_loss_files_base_dir.exists() ) {
+ per_node_go_mapped_domain_gain_loss_files_base_dir.mkdir();
+ }
+ if ( state == GainLossStates.GAIN ) {
+ per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir
+ + ForesterUtil.FILE_SEPARATOR + "GAINS" );
+ }
+ else if ( state == GainLossStates.LOSS ) {
+ per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir
+ + ForesterUtil.FILE_SEPARATOR + "LOSSES" );
+ }
+ else {
+ per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir
+ + ForesterUtil.FILE_SEPARATOR + "PRESENT" );
+ }
+ if ( !per_node_go_mapped_domain_gain_loss_files_base_dir.exists() ) {
+ per_node_go_mapped_domain_gain_loss_files_base_dir.mkdir();
+ }
+ return per_node_go_mapped_domain_gain_loss_files_base_dir;
+ }
+
+ private static SortedSet<BinaryDomainCombination> createSetOfAllBinaryDomainCombinationsPerGenome( final GenomeWideCombinableDomains gwcd ) {
+ final SortedMap<String, CombinableDomains> cds = gwcd.getAllCombinableDomainsIds();
+ final SortedSet<BinaryDomainCombination> binary_combinations = new TreeSet<BinaryDomainCombination>();
+ for( final String domain_id : cds.keySet() ) {
+ final CombinableDomains cd = cds.get( domain_id );
+ binary_combinations.addAll( cd.toBinaryDomainCombinations() );
+ }
+ return binary_combinations;
+ }
+
+ 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;
+ }
+
+ private static void writeAllEncounteredPfamsToFile( final Map<String, List<GoId>> domain_id_to_go_ids_map,
+ final Map<GoId, GoTerm> go_id_to_term_map,
+ final String outfile_name,
+ final SortedSet<String> all_pfams_encountered ) {
+ final File all_pfams_encountered_file = new File( outfile_name + surfacing.ALL_PFAMS_ENCOUNTERED_SUFFIX );
+ final File all_pfams_encountered_with_go_annotation_file = new File( outfile_name
+ + surfacing.ALL_PFAMS_ENCOUNTERED_WITH_GO_ANNOTATION_SUFFIX );
+ final File encountered_pfams_summary_file = new File( outfile_name + surfacing.ENCOUNTERED_PFAMS_SUMMARY_SUFFIX );
+ int biological_process_counter = 0;
+ int cellular_component_counter = 0;
+ int molecular_function_counter = 0;
+ int pfams_with_mappings_counter = 0;
+ int pfams_without_mappings_counter = 0;
+ int pfams_without_mappings_to_bp_or_mf_counter = 0;
+ int pfams_with_mappings_to_bp_or_mf_counter = 0;
+ try {
+ final Writer all_pfams_encountered_writer = new BufferedWriter( new FileWriter( all_pfams_encountered_file ) );
+ final Writer all_pfams_encountered_with_go_annotation_writer = new BufferedWriter( new FileWriter( all_pfams_encountered_with_go_annotation_file ) );
+ final Writer summary_writer = new BufferedWriter( new FileWriter( encountered_pfams_summary_file ) );
+ summary_writer.write( "# Pfam to GO mapping summary" );
+ summary_writer.write( ForesterUtil.LINE_SEPARATOR );
+ summary_writer.write( "# Actual summary is at the end of this file." );
+ summary_writer.write( ForesterUtil.LINE_SEPARATOR );
+ summary_writer.write( "# Encountered Pfams without a GO mapping:" );
+ summary_writer.write( ForesterUtil.LINE_SEPARATOR );
+ for( final String pfam : all_pfams_encountered ) {
+ all_pfams_encountered_writer.write( pfam );
+ all_pfams_encountered_writer.write( ForesterUtil.LINE_SEPARATOR );
+ final String domain_id = new String( pfam );
+ if ( domain_id_to_go_ids_map.containsKey( domain_id ) ) {
+ ++pfams_with_mappings_counter;
+ all_pfams_encountered_with_go_annotation_writer.write( pfam );
+ all_pfams_encountered_with_go_annotation_writer.write( ForesterUtil.LINE_SEPARATOR );
+ final List<GoId> go_ids = domain_id_to_go_ids_map.get( domain_id );
+ boolean maps_to_bp = false;
+ boolean maps_to_cc = false;
+ boolean maps_to_mf = false;
+ for( final GoId go_id : go_ids ) {
+ final GoTerm go_term = go_id_to_term_map.get( go_id );
+ if ( go_term.getGoNameSpace().isBiologicalProcess() ) {
+ maps_to_bp = true;
+ }
+ else if ( go_term.getGoNameSpace().isCellularComponent() ) {
+ maps_to_cc = true;
+ }
+ else if ( go_term.getGoNameSpace().isMolecularFunction() ) {
+ maps_to_mf = true;
+ }
+ }
+ if ( maps_to_bp ) {
+ ++biological_process_counter;
+ }
+ if ( maps_to_cc ) {
+ ++cellular_component_counter;
+ }
+ if ( maps_to_mf ) {
+ ++molecular_function_counter;
+ }
+ if ( maps_to_bp || maps_to_mf ) {
+ ++pfams_with_mappings_to_bp_or_mf_counter;
+ }
+ else {
+ ++pfams_without_mappings_to_bp_or_mf_counter;
+ }
+ }
+ else {
+ ++pfams_without_mappings_to_bp_or_mf_counter;
+ ++pfams_without_mappings_counter;
+ summary_writer.write( pfam );
+ summary_writer.write( ForesterUtil.LINE_SEPARATOR );
+ }
}
- per_genome_domain_promiscuity_statistics_writer.write( ForesterUtil.LINE_SEPARATOR );
+ all_pfams_encountered_writer.close();
+ all_pfams_encountered_with_go_annotation_writer.close();
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote all [" + all_pfams_encountered.size()
+ + "] encountered Pfams to: \"" + all_pfams_encountered_file + "\"" );
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote all [" + pfams_with_mappings_counter
+ + "] encountered Pfams with GO mappings to: \"" + all_pfams_encountered_with_go_annotation_file
+ + "\"" );
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote summary (including all ["
+ + pfams_without_mappings_counter + "] encountered Pfams without GO mappings) to: \""
+ + encountered_pfams_summary_file + "\"" );
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Sum of Pfams encountered : "
+ + all_pfams_encountered.size() );
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Pfams without a mapping : "
+ + pfams_without_mappings_counter + " ["
+ + ( ( 100 * pfams_without_mappings_counter ) / all_pfams_encountered.size() ) + "%]" );
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Pfams without mapping to proc. or func. : "
+ + pfams_without_mappings_to_bp_or_mf_counter + " ["
+ + ( ( 100 * pfams_without_mappings_to_bp_or_mf_counter ) / all_pfams_encountered.size() ) + "%]" );
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Pfams with a mapping : "
+ + pfams_with_mappings_counter + " ["
+ + ( ( 100 * pfams_with_mappings_counter ) / all_pfams_encountered.size() ) + "%]" );
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Pfams with a mapping to proc. or func. : "
+ + pfams_with_mappings_to_bp_or_mf_counter + " ["
+ + ( ( 100 * pfams_with_mappings_to_bp_or_mf_counter ) / all_pfams_encountered.size() ) + "%]" );
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Pfams with mapping to biological process: "
+ + biological_process_counter + " ["
+ + ( ( 100 * biological_process_counter ) / all_pfams_encountered.size() ) + "%]" );
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Pfams with mapping to molecular function: "
+ + molecular_function_counter + " ["
+ + ( ( 100 * molecular_function_counter ) / all_pfams_encountered.size() ) + "%]" );
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Pfams with mapping to cellular component: "
+ + cellular_component_counter + " ["
+ + ( ( 100 * cellular_component_counter ) / all_pfams_encountered.size() ) + "%]" );
+ summary_writer.write( ForesterUtil.LINE_SEPARATOR );
+ summary_writer.write( "# Sum of Pfams encountered : " + all_pfams_encountered.size() );
+ summary_writer.write( ForesterUtil.LINE_SEPARATOR );
+ summary_writer.write( "# Pfams without a mapping : " + pfams_without_mappings_counter
+ + " [" + ( ( 100 * pfams_without_mappings_counter ) / all_pfams_encountered.size() ) + "%]" );
+ summary_writer.write( ForesterUtil.LINE_SEPARATOR );
+ summary_writer.write( "# Pfams without mapping to proc. or func. : "
+ + pfams_without_mappings_to_bp_or_mf_counter + " ["
+ + ( ( 100 * pfams_without_mappings_to_bp_or_mf_counter ) / all_pfams_encountered.size() ) + "%]" );
+ summary_writer.write( ForesterUtil.LINE_SEPARATOR );
+ summary_writer.write( "# Pfams with a mapping : " + pfams_with_mappings_counter + " ["
+ + ( ( 100 * pfams_with_mappings_counter ) / all_pfams_encountered.size() ) + "%]" );
+ summary_writer.write( ForesterUtil.LINE_SEPARATOR );
+ summary_writer.write( "# Pfams with a mapping to proc. or func. : "
+ + pfams_with_mappings_to_bp_or_mf_counter + " ["
+ + ( ( 100 * pfams_with_mappings_to_bp_or_mf_counter ) / all_pfams_encountered.size() ) + "%]" );
+ summary_writer.write( ForesterUtil.LINE_SEPARATOR );
+ summary_writer.write( "# Pfams with mapping to biological process: " + biological_process_counter + " ["
+ + ( ( 100 * biological_process_counter ) / all_pfams_encountered.size() ) + "%]" );
+ summary_writer.write( ForesterUtil.LINE_SEPARATOR );
+ summary_writer.write( "# Pfams with mapping to molecular function: " + molecular_function_counter + " ["
+ + ( ( 100 * molecular_function_counter ) / all_pfams_encountered.size() ) + "%]" );
+ summary_writer.write( ForesterUtil.LINE_SEPARATOR );
+ summary_writer.write( "# Pfams with mapping to cellular component: " + cellular_component_counter + " ["
+ + ( ( 100 * cellular_component_counter ) / all_pfams_encountered.size() ) + "%]" );
+ summary_writer.write( ForesterUtil.LINE_SEPARATOR );
+ summary_writer.close();
}
catch ( final IOException e ) {
- ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
- }
- if ( input_file_properties[ i ].length == 3 ) {
- ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote domain combination counts for \""
- + input_file_properties[ i ][ 0 ] + "\" (" + input_file_properties[ i ][ 1 ] + ", "
- + input_file_properties[ i ][ 2 ] + ") to: \"" + dc_outfile + "\"" );
- }
- else {
- ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote domain combination counts for \""
- + input_file_properties[ i ][ 0 ] + "\" (" + input_file_properties[ i ][ 1 ] + ") to: \""
- + dc_outfile + "\"" );
+ ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "Failure to write: " + e );
}
}
- private static void writeDomainData( final Map<DomainId, List<GoId>> domain_id_to_go_ids_map,
+ private static void writeDomainData( final Map<String, 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_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 Map<String, 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;
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 ) ) {
+ if ( domain_id_to_go_ids_map.containsKey( domain_0 ) ) {
go_annotation_present = true;
any_go_annotation_present = true;
- go_ids = domain_id_to_go_ids_map.get( domain_id );
+ go_ids = domain_id_to_go_ids_map.get( domain_0 );
}
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 ) ) {
+ if ( domain_id_to_go_ids_map.containsKey( domain_1 ) ) {
go_annotation_present = true;
any_go_annotation_present = true;
- go_ids = domain_id_to_go_ids_map.get( domain_id );
+ go_ids = domain_id_to_go_ids_map.get( domain_1 );
}
}
if ( go_annotation_present ) {
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 )
+ final Map<String, Set<String>>[] domain_id_to_secondary_features_maps )
throws IOException {
out.write( "<td>" );
if ( !ForesterUtil.isEmpty( prefix_for_detailed_html ) ) {
out.write( "</td>" );
}
- public static DescriptiveStatistics writeDomainSimilaritiesToFile( final StringBuilder html_desc,
- final StringBuilder html_title,
- final Writer w,
- final SortedSet<DomainSimilarity> similarities,
- final boolean treat_as_binary,
- final List<Species> species_order,
- final PrintableDomainSimilarity.PRINT_OPTION print_option,
- final DomainSimilarity.DomainSimilaritySortField sort_field,
- final DomainSimilarity.DomainSimilarityScoring scoring,
- final boolean verbose ) throws IOException {
- final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
- String histogram_title = null;
- switch ( sort_field ) {
- case ABS_MAX_COUNTS_DIFFERENCE:
- if ( treat_as_binary ) {
- histogram_title = "absolute counts difference:";
- }
- else {
- histogram_title = "absolute (maximal) counts difference:";
- }
- break;
- case MAX_COUNTS_DIFFERENCE:
- if ( treat_as_binary ) {
- histogram_title = "counts difference:";
- }
- else {
- histogram_title = "(maximal) counts difference:";
- }
- break;
- case DOMAIN_ID:
- histogram_title = "score mean:";
- break;
- case MIN:
- histogram_title = "score minimum:";
- break;
- case MAX:
- histogram_title = "score maximum:";
- break;
- case MAX_DIFFERENCE:
- if ( treat_as_binary ) {
- histogram_title = "difference:";
- }
- else {
- histogram_title = "(maximal) difference:";
- }
- break;
- case MEAN:
- histogram_title = "score mean:";
- break;
- case SD:
- histogram_title = "score standard deviation:";
- break;
- case SPECIES_COUNT:
- histogram_title = "species number:";
- break;
- default:
- throw new AssertionError( "Unknown sort field: " + sort_field );
- }
- for( final DomainSimilarity similarity : similarities ) {
- switch ( sort_field ) {
- case ABS_MAX_COUNTS_DIFFERENCE:
- stats.addValue( Math.abs( similarity.getMaximalDifferenceInCounts() ) );
- break;
- case MAX_COUNTS_DIFFERENCE:
- stats.addValue( similarity.getMaximalDifferenceInCounts() );
- break;
- case DOMAIN_ID:
- stats.addValue( similarity.getMeanSimilarityScore() );
- break;
- case MIN:
- stats.addValue( similarity.getMinimalSimilarityScore() );
- break;
- case MAX:
- stats.addValue( similarity.getMaximalSimilarityScore() );
- break;
- case MAX_DIFFERENCE:
- stats.addValue( similarity.getMaximalDifference() );
- break;
- case MEAN:
- stats.addValue( similarity.getMeanSimilarityScore() );
- break;
- case SD:
- stats.addValue( similarity.getStandardDeviationOfSimilarityScore() );
- break;
- case SPECIES_COUNT:
- stats.addValue( similarity.getSpecies().size() );
- break;
- default:
- throw new AssertionError( "Unknown sort field: " + sort_field );
- }
- }
- //
- // final HistogramData[] hists = new HistogramData[ 1 ];
- //
- //
- // List<HistogramDataItem> data_items = new
- // ArrayList<HistogramDataItem>();
- // double[] values = stats.getDataAsDoubleArray();
- // for( int i = 0; i < values.length; i++ ) {
- // HistogramDataItem data_item = new BasicHistogramDataItem( "", values[
- // i ] );
- // data_items.add( data_item );
- // }
- //
- //
- // HistogramData hd0 = new HistogramData( "name",
- // data_items,
- // null, 20,
- // 40 );
- //
- //
- //
- //
- // hists[ 0 ] = hd0;
- //
- // final HistogramsFrame hf = new HistogramsFrame( hists );
- // hf.setVisible( true );
- //
- AsciiHistogram histo = null;
- if ( stats.getMin() < stats.getMin() ) {
- histo = new AsciiHistogram( stats, histogram_title );
- }
- if ( verbose ) {
- if ( histo != null ) {
- System.out.println( histo.toStringBuffer( 20, '|', 40, 5 ) );
- }
- System.out.println();
- System.out.println( "N : " + stats.getN() );
- System.out.println( "Min : " + stats.getMin() );
- System.out.println( "Max : " + stats.getMax() );
- System.out.println( "Mean : " + stats.arithmeticMean() );
- if ( stats.getN() > 1 ) {
- System.out.println( "SD : " + stats.sampleStandardDeviation() );
- }
- else {
- System.out.println( "SD : n/a" );
- }
- System.out.println( "Median : " + stats.median() );
- if ( stats.getN() > 1 ) {
- System.out.println( "Pearsonian skewness : " + stats.pearsonianSkewness() );
- }
- else {
- System.out.println( "Pearsonian skewness : n/a" );
- }
- }
- 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() );
- 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 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 );
- }
- 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 );
- break;
- }
- w.flush();
- w.close();
- return stats;
- }
-
private static void writeDomainsToIndividualFilePerTreeNode( final Writer individual_files_writer,
final String domain_0,
final String domain_1 ) throws IOException {
}
}
- public static void writeMatrixToFile( final CharacterStateMatrix<?> matrix,
- final String filename,
- final Format format ) {
- final File outfile = new File( filename );
- checkForOutputFileWriteability( outfile );
- try {
- final BufferedWriter out = new BufferedWriter( new FileWriter( outfile ) );
- matrix.toWriter( out, format );
- out.flush();
- out.close();
- }
- catch ( final IOException e ) {
- ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
- }
- ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote matrix: \"" + filename + "\"" );
- }
-
- public static void writeMatrixToFile( final File matrix_outfile, final List<DistanceMatrix> matrices ) {
- checkForOutputFileWriteability( matrix_outfile );
- try {
- final BufferedWriter out = new BufferedWriter( new FileWriter( matrix_outfile ) );
- for( final DistanceMatrix distance_matrix : matrices ) {
- out.write( distance_matrix.toStringBuffer( DistanceMatrix.Format.PHYLIP ).toString() );
- out.write( ForesterUtil.LINE_SEPARATOR );
- out.flush();
- }
- out.close();
- }
- catch ( final IOException e ) {
- ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
- }
- ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote distance matrices to \"" + matrix_outfile + "\"" );
- }
-
private static void writePfamsToFile( final String outfile_name, final SortedSet<String> pfams ) {
try {
final Writer writer = new BufferedWriter( new FileWriter( new File( outfile_name ) ) );
}
}
- public static void writePhylogenyToFile( final Phylogeny phylogeny, final String filename ) {
- final PhylogenyWriter writer = new PhylogenyWriter();
- try {
- writer.toPhyloXML( new File( filename ), phylogeny, 1 );
- }
- catch ( final IOException e ) {
- ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "failed to write phylogeny to \"" + filename + "\": "
- + e );
- }
- ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote phylogeny to \"" + filename + "\"" );
- }
-
- public static void writeTaxonomyLinks( 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( "]" );
- }
- }
-
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 + "\"" );
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 );
- }
- }
+ final static class DomainComparator implements Comparator<Domain> {
+
+ final private boolean _ascending;
+
+ public DomainComparator( final boolean ascending ) {
+ _ascending = ascending;
+ }
+
+ @Override
+ public final int compare( final Domain d0, final Domain d1 ) {
+ if ( d0.getFrom() < d1.getFrom() ) {
+ return _ascending ? -1 : 1;
}
- 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 );
- }
- }
- }
+ else if ( d0.getFrom() > d1.getFrom() ) {
+ return _ascending ? 1 : -1;
}
- }
- try {
- writer.write( genome );
- writer.write( "\t" );
- writer.write( stats.arithmeticMean() + "" );
- writer.write( "\t" );
- writer.write( stats.sampleStandardDeviation() + "" );
- 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() + "" );
- writer.write( "\n" );
- }
- catch ( final IOException e ) {
- e.printStackTrace();
+ return 0;
}
}
}