package org.forester.surfacing;
+import java.awt.Color;
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileWriter;
import org.forester.go.GoTerm;
import org.forester.go.PfamToGoMapping;
import org.forester.io.parsers.nexus.NexusConstants;
+import org.forester.io.parsers.phyloxml.PhyloXmlUtil;
+import org.forester.io.parsers.util.ParserUtils;
import org.forester.io.writers.PhylogenyWriter;
import org.forester.phylogeny.Phylogeny;
import org.forester.phylogeny.PhylogenyMethods;
import org.forester.phylogeny.data.BinaryCharacters;
import org.forester.phylogeny.data.Confidence;
import org.forester.phylogeny.data.Taxonomy;
+import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
import org.forester.protein.BasicDomain;
import org.forester.protein.BasicProtein;
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;
import org.forester.util.BasicTableParser;
+import org.forester.util.CommandLineArguments;
import org.forester.util.DescriptiveStatistics;
import org.forester.util.ForesterUtil;
+import org.forester.util.TaxonomyColors;
public final class SurfacingUtil {
- private final static NumberFormat FORMATTER_3 = new DecimalFormat( "0.000" );
- private static final Comparator<Domain> ASCENDING_CONFIDENCE_VALUE_ORDER = new Comparator<Domain>() {
-
- @Override
- public int compare( final Domain d1,
- final Domain d2 ) {
- if ( d1.getPerSequenceEvalue() < d2
- .getPerSequenceEvalue() ) {
- return -1;
- }
- else if ( d1
- .getPerSequenceEvalue() > d2
- .getPerSequenceEvalue() ) {
- return 1;
- }
- else {
- return d1.compareTo( d2 );
- }
- }
- };
- public final static Pattern PATTERN_SP_STYLE_TAXONOMY = Pattern.compile( "^[A-Z0-9]{3,5}$" );
+ public final static Pattern PATTERN_SP_STYLE_TAXONOMY = Pattern.compile( "^[A-Z0-9]{3,5}$" );
+ private final static Map<String, String> _TAXCODE_HEXCOLORSTRING_MAP = new HashMap<String, String>();
+ private static final Comparator<Domain> ASCENDING_CONFIDENCE_VALUE_ORDER = new Comparator<Domain>() {
+
+ @Override
+ public int compare( final Domain d1,
+ final Domain d2 ) {
+ if ( d1.getPerSequenceEvalue() < d2
+ .getPerSequenceEvalue() ) {
+ return -1;
+ }
+ else if ( d1
+ .getPerSequenceEvalue() > d2
+ .getPerSequenceEvalue() ) {
+ return 1;
+ }
+ else {
+ return d1.compareTo( d2 );
+ }
+ }
+ };
+ private final static NumberFormat FORMATTER_3 = new DecimalFormat( "0.000" );
private SurfacingUtil() {
// Hidden constructor.
}
}
- public static void addHtmlHead( final Writer w, final String title ) throws IOException {
- w.write( SurfacingConstants.NL );
- w.write( "<head>" );
- w.write( "<title>" );
- w.write( title );
- w.write( "</title>" );
- w.write( SurfacingConstants.NL );
- w.write( "<style>" );
- w.write( SurfacingConstants.NL );
- w.write( "a:visited { color : #6633FF; text-decoration : none; }" );
- w.write( SurfacingConstants.NL );
- w.write( "a:link { color : #6633FF; text-decoration : none; }" );
- w.write( SurfacingConstants.NL );
- w.write( "a:active { color : #99FF00; text-decoration : none; }" );
- w.write( SurfacingConstants.NL );
- w.write( "a:hover { color : #FFFFFF; background-color : #99FF00; text-decoration : none; }" );
- 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 }" );
- w.write( SurfacingConstants.NL );
- w.write( "h2 { color : #0000FF; font-family: Verdana, Arial, Helvetica; font-size: 16pt; font-weight: bold }" );
- w.write( SurfacingConstants.NL );
- w.write( "</style>" );
- w.write( SurfacingConstants.NL );
- w.write( "</head>" );
- w.write( SurfacingConstants.NL );
- }
-
public static DescriptiveStatistics calculateDescriptiveStatisticsForMeanValues( final Set<DomainSimilarity> similarities ) {
final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
for( final DomainSimilarity similarity : similarities ) {
return stats;
}
- public static int calculateOverlap( final Domain domain, final List<Boolean> covered_positions ) {
- int overlap_count = 0;
- for( int i = domain.getFrom(); i <= domain.getTo(); ++i ) {
- if ( ( i < covered_positions.size() ) && ( covered_positions.get( i ) == true ) ) {
- ++overlap_count;
- }
- }
- return overlap_count;
- }
-
public static void checkForOutputFileWriteability( final File outfile ) {
final String error = ForesterUtil.isWritableFile( outfile );
if ( !ForesterUtil.isEmpty( error ) ) {
}
}
+ public static void checkWriteabilityForPairwiseComparisons( final PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option,
+ final String[][] input_file_properties,
+ final String automated_pairwise_comparison_suffix,
+ final File outdir ) {
+ for( int i = 0; i < input_file_properties.length; ++i ) {
+ for( int j = 0; j < i; ++j ) {
+ final String species_i = input_file_properties[ i ][ 1 ];
+ final String species_j = input_file_properties[ j ][ 1 ];
+ String pairwise_similarities_output_file_str = surfacing.PAIRWISE_DOMAIN_COMPARISONS_PREFIX + species_i
+ + "_" + species_j + automated_pairwise_comparison_suffix;
+ switch ( domain_similarity_print_option ) {
+ case HTML:
+ if ( !pairwise_similarities_output_file_str.endsWith( ".html" ) ) {
+ pairwise_similarities_output_file_str += ".html";
+ }
+ break;
+ }
+ final String error = ForesterUtil
+ .isWritableFile( new File( outdir == null ? pairwise_similarities_output_file_str : outdir
+ + ForesterUtil.FILE_SEPARATOR + pairwise_similarities_output_file_str ) );
+ if ( !ForesterUtil.isEmpty( error ) ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, error );
+ }
+ }
+ }
+ }
+
public static void collectChangedDomainCombinationsFromBinaryStatesMatrixAsListToFile( final CharacterStateMatrix<CharacterStateMatrix.GainLossStates> matrix,
final BinaryDomainCombination.DomainCombinationType dc_type,
final List<BinaryDomainCombination> all_binary_domains_combination_gained,
return phylogeny;
}
+ public static StringBuilder createParametersAsString( final boolean ignore_dufs,
+ final double e_value_max,
+ final int max_allowed_overlap,
+ final boolean no_engulfing_overlaps,
+ final File cutoff_scores_file,
+ final BinaryDomainCombination.DomainCombinationType dc_type ) {
+ final StringBuilder parameters_sb = new StringBuilder();
+ parameters_sb.append( "E-value: " + e_value_max );
+ if ( cutoff_scores_file != null ) {
+ parameters_sb.append( ", Cutoff-scores-file: " + cutoff_scores_file );
+ }
+ else {
+ parameters_sb.append( ", Cutoff-scores-file: not-set" );
+ }
+ if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
+ parameters_sb.append( ", Max-overlap: " + max_allowed_overlap );
+ }
+ else {
+ parameters_sb.append( ", Max-overlap: not-set" );
+ }
+ if ( no_engulfing_overlaps ) {
+ parameters_sb.append( ", Engulfing-overlaps: not-allowed" );
+ }
+ else {
+ parameters_sb.append( ", Engulfing-overlaps: allowed" );
+ }
+ if ( ignore_dufs ) {
+ parameters_sb.append( ", Ignore-dufs: true" );
+ }
+ else {
+ parameters_sb.append( ", Ignore-dufs: false" );
+ }
+ parameters_sb.append( ", DC type (if applicable): " + dc_type );
+ return parameters_sb;
+ }
+
+ public static void createSplitWriters( final File out_dir,
+ final String my_outfile,
+ final Map<Character, Writer> split_writers ) throws IOException {
+ split_writers.put( 'a', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_A.html" ) ) );
+ split_writers.put( 'b', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_B.html" ) ) );
+ split_writers.put( 'c', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_C.html" ) ) );
+ split_writers.put( 'd', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_D.html" ) ) );
+ split_writers.put( 'e', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_E.html" ) ) );
+ split_writers.put( 'f', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_F.html" ) ) );
+ split_writers.put( 'g', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_G.html" ) ) );
+ split_writers.put( 'h', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_H.html" ) ) );
+ split_writers.put( 'i', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_I.html" ) ) );
+ split_writers.put( 'j', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_J.html" ) ) );
+ split_writers.put( 'k', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_K.html" ) ) );
+ split_writers.put( 'l', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_L.html" ) ) );
+ split_writers.put( 'm', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_M.html" ) ) );
+ split_writers.put( 'n', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_N.html" ) ) );
+ split_writers.put( 'o', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_O.html" ) ) );
+ split_writers.put( 'p', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_P.html" ) ) );
+ split_writers.put( 'q', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_Q.html" ) ) );
+ split_writers.put( 'r', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_R.html" ) ) );
+ split_writers.put( 's', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_S.html" ) ) );
+ split_writers.put( 't', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_T.html" ) ) );
+ split_writers.put( 'u', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_U.html" ) ) );
+ split_writers.put( 'v', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_V.html" ) ) );
+ split_writers.put( 'w', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_W.html" ) ) );
+ split_writers.put( 'x', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_X.html" ) ) );
+ split_writers.put( 'y', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_Y.html" ) ) );
+ split_writers.put( 'z', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_Z.html" ) ) );
+ split_writers.put( '0', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_0.html" ) ) );
+ }
+
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(); ) {
}
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 );
}
}
}
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();
}
/**
+ * Warning: This side-effects 'all_bin_domain_combinations_encountered'!
+ *
+ *
+ * @param output_file
+ * @param all_bin_domain_combinations_changed
+ * @param sum_of_all_domains_encountered
+ * @param all_bin_domain_combinations_encountered
+ * @param is_gains_analysis
+ * @param protein_length_stats_by_dc
+ * @throws IOException
+ */
+ public static void executeFitchGainsAnalysis( final File output_file,
+ final List<BinaryDomainCombination> all_bin_domain_combinations_changed,
+ final int sum_of_all_domains_encountered,
+ final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered,
+ final boolean is_gains_analysis ) throws IOException {
+ checkForOutputFileWriteability( output_file );
+ final Writer out = ForesterUtil.createBufferedWriter( output_file );
+ final SortedMap<Object, Integer> bdc_to_counts = ForesterUtil
+ .listToSortedCountsMap( all_bin_domain_combinations_changed );
+ final SortedSet<String> all_domains_in_combination_changed_more_than_once = new TreeSet<String>();
+ final SortedSet<String> all_domains_in_combination_changed_only_once = new TreeSet<String>();
+ int above_one = 0;
+ int one = 0;
+ for( final Object bdc_object : bdc_to_counts.keySet() ) {
+ final BinaryDomainCombination bdc = ( BinaryDomainCombination ) bdc_object;
+ final int count = bdc_to_counts.get( bdc_object );
+ if ( count < 1 ) {
+ ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "count < 1 " );
+ }
+ out.write( bdc + "\t" + count + ForesterUtil.LINE_SEPARATOR );
+ if ( count > 1 ) {
+ all_domains_in_combination_changed_more_than_once.add( bdc.getId0() );
+ all_domains_in_combination_changed_more_than_once.add( bdc.getId1() );
+ above_one++;
+ }
+ else if ( count == 1 ) {
+ all_domains_in_combination_changed_only_once.add( bdc.getId0() );
+ all_domains_in_combination_changed_only_once.add( bdc.getId1() );
+ one++;
+ }
+ }
+ final int all = all_bin_domain_combinations_encountered.size();
+ int never_lost = -1;
+ if ( !is_gains_analysis ) {
+ all_bin_domain_combinations_encountered.removeAll( all_bin_domain_combinations_changed );
+ never_lost = all_bin_domain_combinations_encountered.size();
+ for( final BinaryDomainCombination bdc : all_bin_domain_combinations_encountered ) {
+ out.write( bdc + "\t" + "0" + ForesterUtil.LINE_SEPARATOR );
+ }
+ }
+ if ( is_gains_analysis ) {
+ out.write( "Sum of all distinct domain combinations appearing once : " + one
+ + ForesterUtil.LINE_SEPARATOR );
+ out.write( "Sum of all distinct domain combinations appearing more than once : " + above_one
+ + ForesterUtil.LINE_SEPARATOR );
+ out.write( "Sum of all distinct domains in combinations apppearing only once : "
+ + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR );
+ out.write( "Sum of all distinct domains in combinations apppearing more than once: "
+ + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR );
+ }
+ else {
+ out.write( "Sum of all distinct domain combinations never lost : " + never_lost
+ + ForesterUtil.LINE_SEPARATOR );
+ out.write( "Sum of all distinct domain combinations lost once : " + one
+ + ForesterUtil.LINE_SEPARATOR );
+ out.write( "Sum of all distinct domain combinations lost more than once : " + above_one
+ + ForesterUtil.LINE_SEPARATOR );
+ out.write( "Sum of all distinct domains in combinations lost only once : "
+ + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR );
+ out.write( "Sum of all distinct domains in combinations lost more than once: "
+ + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR );
+ }
+ out.write( "All binary combinations : " + all
+ + ForesterUtil.LINE_SEPARATOR );
+ out.write( "All domains : "
+ + sum_of_all_domains_encountered );
+ out.close();
+ ForesterUtil.programMessage( surfacing.PRG_NAME,
+ "Wrote fitch domain combination dynamics counts analysis to \"" + output_file
+ + "\"" );
+ }
+
+ /**
*
* @param all_binary_domains_combination_lost_fitch
* @param use_last_in_fitch_parsimony
+ "_MAPPED_indep_dc_gains_fitch_lca_taxonomies.txt", null, null, null, null );
}
+ public static void executePlusMinusAnalysis( final File output_file,
+ final List<String> plus_minus_analysis_high_copy_base,
+ final List<String> plus_minus_analysis_high_copy_target,
+ final List<String> plus_minus_analysis_low_copy,
+ final List<GenomeWideCombinableDomains> gwcd_list,
+ final SortedMap<Species, List<Protein>> protein_lists_per_species,
+ final Map<String, List<GoId>> domain_id_to_go_ids_map,
+ final Map<GoId, GoTerm> go_id_to_term_map,
+ final List<Object> plus_minus_analysis_numbers ) {
+ final Set<String> all_spec = new HashSet<String>();
+ for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
+ all_spec.add( gwcd.getSpecies().getSpeciesId() );
+ }
+ final File html_out_dom = new File( output_file + surfacing.PLUS_MINUS_DOM_SUFFIX_HTML );
+ final File plain_out_dom = new File( output_file + surfacing.PLUS_MINUS_DOM_SUFFIX );
+ final File html_out_dc = new File( output_file + surfacing.PLUS_MINUS_DC_SUFFIX_HTML );
+ final File all_domains_go_ids_out_dom = new File( output_file + surfacing.PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX );
+ final File passing_domains_go_ids_out_dom = new File( output_file
+ + surfacing.PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX );
+ final File proteins_file_base = new File( output_file + "" );
+ final int min_diff = ( ( Integer ) plus_minus_analysis_numbers.get( 0 ) ).intValue();
+ final double factor = ( ( Double ) plus_minus_analysis_numbers.get( 1 ) ).doubleValue();
+ try {
+ DomainCountsDifferenceUtil.calculateCopyNumberDifferences( gwcd_list,
+ protein_lists_per_species,
+ plus_minus_analysis_high_copy_base,
+ plus_minus_analysis_high_copy_target,
+ plus_minus_analysis_low_copy,
+ min_diff,
+ factor,
+ plain_out_dom,
+ html_out_dom,
+ html_out_dc,
+ domain_id_to_go_ids_map,
+ go_id_to_term_map,
+ all_domains_go_ids_out_dom,
+ passing_domains_go_ids_out_dom,
+ proteins_file_base );
+ }
+ catch ( final IOException e ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
+ }
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \""
+ + html_out_dom + "\"" );
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \""
+ + plain_out_dom + "\"" );
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \"" + html_out_dc
+ + "\"" );
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based passing GO ids to \""
+ + passing_domains_go_ids_out_dom + "\"" );
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based all GO ids to \""
+ + all_domains_go_ids_out_dom + "\"" );
+ }
+
public static void extractProteinNames( final List<Protein> proteins,
final List<String> query_domain_ids_nc_order,
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 );
+ //System.out.println( "Per domain E-value: " + domain_e_cutoff );
for( final Species species : protein_lists_per_species.keySet() ) {
- System.out.println( species + ":" );
+ //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 ) ) {
out.write( domain.getFrom() + "-" + domain.getTo() );
if ( prev_to >= 0 ) {
final int l = domain.getFrom() - prev_to;
- System.out.println( l );
+ // System.out.println( l );
}
prev_to = domain.getTo();
}
return c;
}
- /**
- * Returns true is Domain domain falls in an uninterrupted stretch of
- * covered positions.
- *
- * @param domain
- * @param covered_positions
- * @return
- */
- public static boolean isEngulfed( final Domain domain, final List<Boolean> covered_positions ) {
- for( int i = domain.getFrom(); i <= domain.getTo(); ++i ) {
- if ( ( i >= covered_positions.size() ) || ( covered_positions.get( i ) != true ) ) {
- return false;
+ public static void log( final String msg, final Writer w ) {
+ try {
+ w.write( msg );
+ w.write( ForesterUtil.LINE_SEPARATOR );
+ }
+ catch ( final IOException e ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
+ }
+ }
+
+ public static Phylogeny[] obtainAndPreProcessIntrees( final File[] intree_files,
+ final int number_of_genomes,
+ final String[][] input_file_properties ) {
+ final Phylogeny[] intrees = new Phylogeny[ intree_files.length ];
+ int i = 0;
+ for( final File intree_file : intree_files ) {
+ Phylogeny intree = null;
+ final String error = ForesterUtil.isReadableFile( intree_file );
+ if ( !ForesterUtil.isEmpty( error ) ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read input tree file [" + intree_file + "]: "
+ + error );
+ }
+ try {
+ final Phylogeny[] p_array = ParserBasedPhylogenyFactory.getInstance()
+ .create( intree_file, ParserUtils.createParserDependingOnFileType( intree_file, true ) );
+ if ( p_array.length < 1 ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
+ + "] does not contain any phylogeny in phyloXML format" );
+ }
+ else if ( p_array.length > 1 ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
+ + "] contains more than one phylogeny in phyloXML format" );
+ }
+ intree = p_array[ 0 ];
+ }
+ catch ( final Exception e ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to read input tree from file [" + intree_file
+ + "]: " + error );
+ }
+ if ( ( intree == null ) || intree.isEmpty() ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is empty" );
+ }
+ if ( !intree.isRooted() ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is not rooted" );
+ }
+ if ( intree.getNumberOfExternalNodes() < number_of_genomes ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME,
+ "number of external nodes [" + intree.getNumberOfExternalNodes()
+ + "] of input tree [" + intree_file
+ + "] is smaller than the number of genomes the be analyzed ["
+ + number_of_genomes + "]" );
+ }
+ final StringBuilder parent_names = new StringBuilder();
+ final int nodes_lacking_name = getNumberOfNodesLackingName( intree, parent_names );
+ if ( nodes_lacking_name > 0 ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] has "
+ + nodes_lacking_name + " node(s) lacking a name [parent names:" + parent_names + "]" );
+ }
+ preparePhylogenyForParsimonyAnalyses( intree, input_file_properties );
+ if ( !intree.isCompletelyBinary() ) {
+ ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "input tree [" + intree_file
+ + "] is not completely binary" );
}
+ intrees[ i++ ] = intree;
}
- return true;
+ return intrees;
+ }
+
+ public static Phylogeny obtainFirstIntree( final File intree_file ) {
+ Phylogeny intree = null;
+ final String error = ForesterUtil.isReadableFile( intree_file );
+ if ( !ForesterUtil.isEmpty( error ) ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read input tree file [" + intree_file + "]: " + error );
+ }
+ try {
+ final Phylogeny[] phys = ParserBasedPhylogenyFactory.getInstance()
+ .create( intree_file, ParserUtils.createParserDependingOnFileType( intree_file, true ) );
+ if ( phys.length < 1 ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
+ + "] does not contain any phylogeny in phyloXML format" );
+ }
+ else if ( phys.length > 1 ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
+ + "] contains more than one phylogeny in phyloXML format" );
+ }
+ intree = phys[ 0 ];
+ }
+ catch ( final Exception e ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to read input tree from file [" + intree_file + "]: "
+ + error );
+ }
+ if ( ( intree == null ) || intree.isEmpty() ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is empty" );
+ }
+ if ( !intree.isRooted() ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is not rooted" );
+ }
+ return intree;
+ }
+
+ public static String obtainHexColorStringDependingOnTaxonomyGroup( final String tax_code, final Phylogeny phy )
+ throws IllegalArgumentException {
+ if ( !_TAXCODE_HEXCOLORSTRING_MAP.containsKey( tax_code ) ) {
+ if ( ( phy != null ) && !phy.isEmpty() ) {
+ final List<PhylogenyNode> nodes = phy.getNodesViaTaxonomyCode( tax_code );
+ Color c = null;
+ if ( ( nodes == null ) || nodes.isEmpty() ) {
+ throw new IllegalArgumentException( "code " + tax_code + " is not found" );
+ }
+ if ( nodes.size() != 1 ) {
+ throw new IllegalArgumentException( "code " + tax_code + " is not unique" );
+ }
+ PhylogenyNode n = nodes.get( 0 );
+ while ( n != null ) {
+ if ( n.getNodeData().isHasTaxonomy()
+ && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getScientificName() ) ) {
+ c = ForesterUtil.obtainColorDependingOnTaxonomyGroup( n.getNodeData().getTaxonomy()
+ .getScientificName(), tax_code );
+ }
+ if ( ( c == null ) && !ForesterUtil.isEmpty( n.getName() ) ) {
+ c = ForesterUtil.obtainColorDependingOnTaxonomyGroup( n.getName(), tax_code );
+ }
+ if ( c != null ) {
+ break;
+ }
+ n = n.getParent();
+ }
+ if ( c == null ) {
+ throw new IllegalArgumentException( "no color found for taxonomy code \"" + tax_code + "\"" );
+ }
+ final String hex = String.format( "#%02x%02x%02x", c.getRed(), c.getGreen(), c.getBlue() );
+ _TAXCODE_HEXCOLORSTRING_MAP.put( tax_code, hex );
+ }
+ else {
+ throw new IllegalArgumentException( "unable to obtain color for code " + tax_code
+ + " (tree is null or empty and code is not in map)" );
+ }
+ }
+ return _TAXCODE_HEXCOLORSTRING_MAP.get( tax_code );
}
public static void performDomainArchitectureAnalysis( final SortedMap<String, Set<String>> domain_architecutures,
p.setRooted( true );
}
+ public static void preparePhylogenyForParsimonyAnalyses( final Phylogeny intree,
+ final String[][] input_file_properties ) {
+ final String[] genomes = new String[ input_file_properties.length ];
+ for( int i = 0; i < input_file_properties.length; ++i ) {
+ if ( intree.getNodes( input_file_properties[ i ][ 1 ] ).size() > 1 ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_properties[ i ][ 1 ]
+ + "] is not unique in input tree " + intree.getName() );
+ }
+ genomes[ i ] = input_file_properties[ i ][ 1 ];
+ }
+ //
+ final PhylogenyNodeIterator it = intree.iteratorPostorder();
+ while ( it.hasNext() ) {
+ final PhylogenyNode n = it.next();
+ if ( ForesterUtil.isEmpty( n.getName() ) ) {
+ if ( n.getNodeData().isHasTaxonomy()
+ && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getTaxonomyCode() ) ) {
+ n.setName( n.getNodeData().getTaxonomy().getTaxonomyCode() );
+ }
+ else if ( n.getNodeData().isHasTaxonomy()
+ && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getScientificName() ) ) {
+ n.setName( n.getNodeData().getTaxonomy().getScientificName() );
+ }
+ else if ( n.getNodeData().isHasTaxonomy()
+ && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getCommonName() ) ) {
+ n.setName( n.getNodeData().getTaxonomy().getCommonName() );
+ }
+ else {
+ ForesterUtil
+ .fatalError( surfacing.PRG_NAME,
+ "node with no name, scientific name, common name, or taxonomy code present" );
+ }
+ }
+ }
+ //
+ final List<String> igns = PhylogenyMethods.deleteExternalNodesPositiveSelection( genomes, intree );
+ if ( igns.size() > 0 ) {
+ System.out.println( "Not using the following " + igns.size() + " nodes:" );
+ for( int i = 0; i < igns.size(); ++i ) {
+ System.out.println( " " + i + ": " + igns.get( i ) );
+ }
+ System.out.println( "--" );
+ }
+ for( final String[] input_file_propertie : input_file_properties ) {
+ try {
+ intree.getNode( input_file_propertie[ 1 ] );
+ }
+ catch ( final IllegalArgumentException e ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_propertie[ 1 ]
+ + "] not present/not unique in input tree" );
+ }
+ }
+ }
+
+ public static void printOutPercentageOfMultidomainProteins( final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo,
+ final Writer log_writer ) {
+ int sum = 0;
+ for( final Entry<Integer, Integer> entry : all_genomes_domains_per_potein_histo.entrySet() ) {
+ sum += entry.getValue();
+ }
+ final double percentage = ( 100.0 * ( sum - all_genomes_domains_per_potein_histo.get( 1 ) ) ) / sum;
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Percentage of multidomain proteins: " + percentage + "%" );
+ log( "Percentage of multidomain proteins: : " + percentage + "%", log_writer );
+ }
+
+ public static void processFilter( final File filter_file, final SortedSet<String> filter ) {
+ SortedSet<String> filter_str = null;
+ try {
+ filter_str = ForesterUtil.file2set( filter_file );
+ }
+ catch ( final IOException e ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
+ }
+ if ( filter_str != null ) {
+ for( final String string : filter_str ) {
+ filter.add( string );
+ }
+ }
+ if ( surfacing.VERBOSE ) {
+ System.out.println( "Filter:" );
+ for( final String domainId : filter ) {
+ System.out.println( domainId );
+ }
+ }
+ }
+
+ public static String[][] processInputGenomesFile( final File input_genomes ) {
+ String[][] input_file_properties = null;
+ try {
+ input_file_properties = ForesterUtil.file22dArray( input_genomes );
+ }
+ catch ( final IOException e ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME,
+ "genomes files is to be in the following format \"<hmmpfam output file> <species>\": "
+ + e.getLocalizedMessage() );
+ }
+ final Set<String> specs = new HashSet<String>();
+ final Set<String> paths = new HashSet<String>();
+ for( int i = 0; i < input_file_properties.length; ++i ) {
+ if ( !PhyloXmlUtil.TAXOMONY_CODE_PATTERN.matcher( input_file_properties[ i ][ 1 ] ).matches() ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for species code: "
+ + input_file_properties[ i ][ 1 ] );
+ }
+ if ( specs.contains( input_file_properties[ i ][ 1 ] ) ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "species code " + input_file_properties[ i ][ 1 ]
+ + " is not unique" );
+ }
+ specs.add( input_file_properties[ i ][ 1 ] );
+ if ( paths.contains( input_file_properties[ i ][ 0 ] ) ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "path " + input_file_properties[ i ][ 0 ]
+ + " is not unique" );
+ }
+ paths.add( input_file_properties[ i ][ 0 ] );
+ final String error = ForesterUtil.isReadableFile( new File( input_file_properties[ i ][ 0 ] ) );
+ if ( !ForesterUtil.isEmpty( error ) ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, error );
+ }
+ }
+ return input_file_properties;
+ }
+
+ public static void processPlusMinusAnalysisOption( final CommandLineArguments cla,
+ final List<String> high_copy_base,
+ final List<String> high_copy_target,
+ final List<String> low_copy,
+ final List<Object> numbers ) {
+ if ( cla.isOptionSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) {
+ if ( !cla.isOptionValueSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for 'plus-minus' file: -"
+ + surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>" );
+ }
+ final File plus_minus_file = new File( cla.getOptionValue( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) );
+ final String msg = ForesterUtil.isReadableFile( plus_minus_file );
+ if ( !ForesterUtil.isEmpty( msg ) ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + plus_minus_file + "\": " + msg );
+ }
+ processPlusMinusFile( plus_minus_file, high_copy_base, high_copy_target, low_copy, numbers );
+ }
+ }
+
+ // First numbers is minimal difference, second is factor.
+ public static void processPlusMinusFile( final File plus_minus_file,
+ final List<String> high_copy_base,
+ final List<String> high_copy_target,
+ final List<String> low_copy,
+ final List<Object> numbers ) {
+ Set<String> species_set = null;
+ int min_diff = surfacing.PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT;
+ double factor = surfacing.PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT;
+ try {
+ species_set = ForesterUtil.file2set( plus_minus_file );
+ }
+ catch ( final IOException e ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
+ }
+ if ( species_set != null ) {
+ for( final String species : species_set ) {
+ final String species_trimmed = species.substring( 1 );
+ if ( species.startsWith( "+" ) ) {
+ if ( low_copy.contains( species_trimmed ) ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME,
+ "species/genome names can not appear with both '+' and '-' suffix, as appears the case for: \""
+ + species_trimmed + "\"" );
+ }
+ high_copy_base.add( species_trimmed );
+ }
+ else if ( species.startsWith( "*" ) ) {
+ if ( low_copy.contains( species_trimmed ) ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME,
+ "species/genome names can not appear with both '*' and '-' suffix, as appears the case for: \""
+ + species_trimmed + "\"" );
+ }
+ high_copy_target.add( species_trimmed );
+ }
+ else if ( species.startsWith( "-" ) ) {
+ if ( high_copy_base.contains( species_trimmed ) || high_copy_target.contains( species_trimmed ) ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME,
+ "species/genome names can not appear with both '+' or '*' and '-' suffix, as appears the case for: \""
+ + species_trimmed + "\"" );
+ }
+ low_copy.add( species_trimmed );
+ }
+ else if ( species.startsWith( "$D" ) ) {
+ try {
+ min_diff = Integer.parseInt( species.substring( 3 ) );
+ }
+ catch ( final NumberFormatException e ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME,
+ "could not parse integer value for minimal difference from: \""
+ + species.substring( 3 ) + "\"" );
+ }
+ }
+ else if ( species.startsWith( "$F" ) ) {
+ try {
+ factor = Double.parseDouble( species.substring( 3 ) );
+ }
+ catch ( final NumberFormatException e ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "could not parse double value for factor from: \""
+ + species.substring( 3 ) + "\"" );
+ }
+ }
+ else if ( species.startsWith( "#" ) ) {
+ // Comment, ignore.
+ }
+ else {
+ ForesterUtil
+ .fatalError( surfacing.PRG_NAME,
+ "species/genome names in 'plus minus' file must begin with '*' (high copy target genome), '+' (high copy base genomes), '-' (low copy genomes), '$D=<integer>' minimal Difference (default is 1), '$F=<double>' factor (default is 1.0), double), or '#' (ignore) suffix, encountered: \""
+ + species + "\"" );
+ }
+ numbers.add( new Integer( min_diff + "" ) );
+ numbers.add( new Double( factor + "" ) );
+ }
+ }
+ else {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "'plus minus' file [" + plus_minus_file + "] appears empty" );
+ }
+ }
+
/*
* species | protein id | n-terminal domain | c-terminal domain | n-terminal domain per domain E-value | c-terminal domain per domain E-value
*
return sb;
}
- /**
- *
- * Example regarding engulfment: ------------0.1 ----------0.2 --0.3 =>
- * domain with 0.3 is ignored
- *
- * -----------0.1 ----------0.2 --0.3 => domain with 0.3 is ignored
- *
- *
- * ------------0.1 ----------0.3 --0.2 => domains with 0.3 and 0.2 are _not_
- * ignored
- *
- * @param max_allowed_overlap
- * maximal allowed overlap (inclusive) to be still considered not
- * overlapping (zero or negative value to allow any overlap)
- * @param remove_engulfed_domains
- * to remove domains which are completely engulfed by coverage of
- * domains with better support
- * @param protein
- * @return
- */
- public static Protein removeOverlappingDomains( final int max_allowed_overlap,
- final boolean remove_engulfed_domains,
- final Protein protein ) {
- final Protein pruned_protein = new BasicProtein( protein.getProteinId().getId(), protein.getSpecies()
- .getSpeciesId(), protein.getLength() );
- final List<Domain> sorted = SurfacingUtil.sortDomainsWithAscendingConfidenceValues( protein );
- final List<Boolean> covered_positions = new ArrayList<Boolean>();
- for( final Domain domain : sorted ) {
- if ( ( ( max_allowed_overlap < 0 ) || ( SurfacingUtil.calculateOverlap( domain, covered_positions ) <= max_allowed_overlap ) )
- && ( !remove_engulfed_domains || !isEngulfed( domain, covered_positions ) ) ) {
- final int covered_positions_size = covered_positions.size();
- for( int i = covered_positions_size; i < domain.getFrom(); ++i ) {
- covered_positions.add( false );
- }
- final int new_covered_positions_size = covered_positions.size();
- for( int i = domain.getFrom(); i <= domain.getTo(); ++i ) {
- if ( i < new_covered_positions_size ) {
- covered_positions.set( i, true );
- }
- else {
- covered_positions.add( true );
- }
- }
- pruned_protein.addProteinDomain( domain );
- }
- }
- return pruned_protein;
- }
-
public static List<Domain> sortDomainsWithAscendingConfidenceValues( final Protein protein ) {
final List<Domain> domains = new ArrayList<Domain>();
for( final Domain d : protein.getProteinDomains() ) {
int per_node_counter = 0;
out.write( "<html>" );
out.write( SurfacingConstants.NL );
- addHtmlHead( out, title_for_html );
+ writeHtmlHead( out, title_for_html );
out.write( SurfacingConstants.NL );
out.write( "<body>" );
out.write( SurfacingConstants.NL );
}
}
- public static DescriptiveStatistics writeDomainSimilaritiesToFile( final StringBuilder html_desc,
- final StringBuilder html_title,
- 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.DomainSimilaritySortField sort_field,
- final DomainSimilarity.DomainSimilarityScoring scoring,
- final boolean verbose,
- final Map<String, Integer> tax_code_to_id_map )
- 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 );
- }
- }
- 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" );
- }
- }
+ 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,
+ final Phylogeny phy ) throws IOException {
if ( ( single_writer != null ) && ( ( split_writers == null ) || split_writers.isEmpty() ) ) {
split_writers = new HashMap<Character, Writer>();
split_writers.put( '_', single_writer );
w.write( "<html>" );
w.write( SurfacingConstants.NL );
if ( key != '_' ) {
- addHtmlHead( w, "DCs (" + html_title + ") " + key.toString().toUpperCase() );
+ writeHtmlHead( w, "DC analysis (" + html_title + ") " + key.toString().toUpperCase() );
}
else {
- addHtmlHead( w, "DCs (" + html_title + ")" );
+ writeHtmlHead( w, "DC analysis (" + html_title + ")" );
}
w.write( SurfacingConstants.NL );
w.write( "<body>" );
w.write( html_desc.toString() );
w.write( SurfacingConstants.NL );
w.write( "<hr>" );
- w.write( "<br>" );
- w.write( SurfacingConstants.NL );
- w.write( "<tt><pre>" );
- w.write( SurfacingConstants.NL );
- if ( histo != null ) {
- w.write( histo.toStringBuffer( 20, '|', 40, 5 ).toString() );
- w.write( SurfacingConstants.NL );
- }
- w.write( "</pre></tt>" );
- w.write( SurfacingConstants.NL );
- w.write( "<table>" );
- w.write( SurfacingConstants.NL );
- w.write( "<tr><td>N: </td><td>" + stats.getN() + "</td></tr>" );
- w.write( SurfacingConstants.NL );
- w.write( "<tr><td>Min: </td><td>" + stats.getMin() + "</td></tr>" );
- w.write( SurfacingConstants.NL );
- w.write( "<tr><td>Max: </td><td>" + stats.getMax() + "</td></tr>" );
- w.write( SurfacingConstants.NL );
- w.write( "<tr><td>Mean: </td><td>" + stats.arithmeticMean() + "</td></tr>" );
- w.write( SurfacingConstants.NL );
- if ( stats.getN() > 1 ) {
- w.write( "<tr><td>SD: </td><td>" + stats.sampleStandardDeviation() + "</td></tr>" );
- }
- else {
- w.write( "<tr><td>SD: </td><td>n/a</td></tr>" );
- }
- w.write( SurfacingConstants.NL );
- w.write( "<tr><td>Median: </td><td>" + stats.median() + "</td></tr>" );
- w.write( SurfacingConstants.NL );
- if ( stats.getN() > 1 ) {
- w.write( "<tr><td>Pearsonian skewness: </td><td>" + stats.pearsonianSkewness() + "</td></tr>" );
- }
- else {
- w.write( "<tr><td>Pearsonian skewness: </td><td>n/a</td></tr>" );
- }
- w.write( SurfacingConstants.NL );
- w.write( "</table>" );
- w.write( SurfacingConstants.NL );
- w.write( "<br>" );
- w.write( SurfacingConstants.NL );
- w.write( "<hr>" );
w.write( SurfacingConstants.NL );
w.write( "<br>" );
w.write( SurfacingConstants.NL );
w.write( "<table>" );
w.write( SurfacingConstants.NL );
+ w.write( "<tr><td><b>Domains:</b></td></tr>" );
+ w.write( SurfacingConstants.NL );
}
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' );
+ }
+ 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 );
+ w.write( "<tr><td><b>" );
+ w.write( "Species group colors:" );
+ w.write( "</b></td></tr>" );
+ w.write( SurfacingConstants.NL );
+ writeColorLabels( "Deuterostomia", TaxonomyColors.DEUTEROSTOMIA_COLOR, w );
+ writeColorLabels( "Protostomia", TaxonomyColors.PROTOSTOMIA_COLOR, w );
+ writeColorLabels( "Cnidaria", TaxonomyColors.CNIDARIA_COLOR, w );
+ writeColorLabels( "Placozoa", TaxonomyColors.PLACOZOA_COLOR, w );
+ writeColorLabels( "Ctenophora (comb jellies)", TaxonomyColors.CTENOPHORA_COLOR, w );
+ writeColorLabels( "Porifera (sponges)", TaxonomyColors.PORIFERA_COLOR, w );
+ writeColorLabels( "Choanoflagellida", TaxonomyColors.CHOANOFLAGELLIDA, w );
+ writeColorLabels( "Ichthyosporea & Filasterea", TaxonomyColors.ICHTHYOSPOREA_AND_FILASTEREA, w );
+ writeColorLabels( "Fungi", TaxonomyColors.FUNGI_COLOR, w );
+ writeColorLabels( "Nucleariidae and Fonticula group",
+ TaxonomyColors.NUCLEARIIDAE_AND_FONTICULA_GROUP_COLOR,
+ w );
+ writeColorLabels( "Amoebozoa", TaxonomyColors.AMOEBOZOA_COLOR, w );
+ writeColorLabels( "Embryophyta (plants)", TaxonomyColors.EMBRYOPHYTA_COLOR, w );
+ writeColorLabels( "Chlorophyta (green algae)", TaxonomyColors.CHLOROPHYTA_COLOR, w );
+ writeColorLabels( "Rhodophyta (red algae)", TaxonomyColors.RHODOPHYTA_COLOR, w );
+ writeColorLabels( "Glaucocystophyce (Glaucophyta)", TaxonomyColors.GLAUCOPHYTA_COLOR, w );
+ writeColorLabels( "Hacrobia (Cryptophyta & Haptophyceae & Centroheliozoa)",
+ TaxonomyColors.HACROBIA_COLOR,
+ w );
+ writeColorLabels( "Stramenopiles (Chromophyta, heterokonts)", TaxonomyColors.STRAMENOPILES_COLOR, w );
+ writeColorLabels( "Alveolata", TaxonomyColors.ALVEOLATA_COLOR, w );
+ writeColorLabels( "Rhizaria", TaxonomyColors.RHIZARIA_COLOR, w );
+ writeColorLabels( "Excavata", TaxonomyColors.EXCAVATA_COLOR, w );
+ writeColorLabels( "Apusozoa", TaxonomyColors.APUSOZOA_COLOR, w );
+ writeColorLabels( "Archaea", TaxonomyColors.ARCHAEA_COLOR, w );
+ writeColorLabels( "Bacteria", TaxonomyColors.BACTERIA_COLOR, w );
+ 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,
+ null ).toString() );
+ }
if ( single_writer != null ) {
- single_writer.write( similarity.toStringBuffer( print_option, tax_code_to_id_map ).toString() );
+ single_writer.write( similarity.toStringBuffer( print_option, tax_code_to_id_map, phy ).toString() );
single_writer.write( SurfacingConstants.NL );
}
else {
if ( local_writer == null ) {
local_writer = split_writers.get( '0' );
}
- local_writer.write( similarity.toStringBuffer( print_option, tax_code_to_id_map ).toString() );
+ local_writer.write( similarity.toStringBuffer( print_option, tax_code_to_id_map, phy ).toString() );
local_writer.write( SurfacingConstants.NL );
}
- // for( final Writer w : split_writers.values() ) {
- //w.write( SurfacingConstants.NL );
- // }
}
switch ( print_option ) {
case HTML:
w.write( SurfacingConstants.NL );
}
break;
+ default:
+ break;
}
for( final Writer w : split_writers.values() ) {
w.close();
}
- return stats;
+ }
+
+ public static void writeHtmlHead( final Writer w, final String title ) throws IOException {
+ w.write( SurfacingConstants.NL );
+ w.write( "<head>" );
+ w.write( "<title>" );
+ w.write( title );
+ w.write( "</title>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<style>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "a:visited { color : #000066; text-decoration : none; }" );
+ w.write( SurfacingConstants.NL );
+ w.write( "a:link { color : #000066; text-decoration : none; }" );
+ w.write( SurfacingConstants.NL );
+ w.write( "a:active { color : ##000066; text-decoration : none; }" );
+ w.write( SurfacingConstants.NL );
+ w.write( "a:hover { color : #FFFFFF; background-color : #000000; text-decoration : none; }" );
+ w.write( SurfacingConstants.NL );
+ //
+ w.write( "a.pl:visited { color : #505050; text-decoration : none; font-size: 7px;}" );
+ w.write( SurfacingConstants.NL );
+ w.write( "a.pl:link { color : #505050; text-decoration : none; font-size: 7px;}" );
+ w.write( SurfacingConstants.NL );
+ w.write( "a.pl:active { color : #505050; text-decoration : none; font-size: 7px;}" );
+ w.write( SurfacingConstants.NL );
+ w.write( "a.pl:hover { color : #FFFFFF; background-color : #000000; text-decoration : none; font-size: 7px;}" );
+ w.write( SurfacingConstants.NL );
+ //
+ w.write( "a.ps:visited { color : #707070; text-decoration : none; font-size: 7px;}" );
+ w.write( SurfacingConstants.NL );
+ w.write( "a.ps:link { color : #707070; text-decoration : none; font-size: 7px;}" );
+ w.write( SurfacingConstants.NL );
+ w.write( "a.ps:active { color : #707070; text-decoration : none; font-size: 7px;}" );
+ w.write( SurfacingConstants.NL );
+ w.write( "a.ps:hover { color : #FFFFFF; background-color : #000000; text-decoration : none; font-size: 7px;}" );
+ 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 }" );
+ w.write( SurfacingConstants.NL );
+ w.write( "h2 { color : #0000FF; font-family: Verdana, Arial, Helvetica; font-size: 16pt; font-weight: bold }" );
+ w.write( SurfacingConstants.NL );
+ w.write( "</style>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "</head>" );
+ w.write( SurfacingConstants.NL );
}
public static void writeMatrixToFile( final CharacterStateMatrix<?> matrix,
ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote phylogeny to \"" + filename + "\"" );
}
+ public static void writePresentToNexus( final File output_file,
+ final File positive_filter_file,
+ final SortedSet<String> filter,
+ final List<GenomeWideCombinableDomains> gwcd_list ) {
+ try {
+ writeMatrixToFile( DomainParsimonyCalculator.createMatrixOfDomainPresenceOrAbsence( gwcd_list,
+ positive_filter_file == null ? null
+ : filter ),
+ output_file + surfacing.DOMAINS_PRESENT_NEXUS,
+ Format.NEXUS_BINARY );
+ writeMatrixToFile( DomainParsimonyCalculator.createMatrixOfBinaryDomainCombinationPresenceOrAbsence( gwcd_list ),
+ output_file + surfacing.BDC_PRESENT_NEXUS,
+ Format.NEXUS_BINARY );
+ }
+ catch ( final Exception e ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
+ }
+ }
+
+ public static void writeProteinListsForAllSpecies( final File output_dir,
+ final SortedMap<Species, List<Protein>> protein_lists_per_species,
+ final List<GenomeWideCombinableDomains> gwcd_list,
+ final double domain_e_cutoff ) {
+ final SortedSet<String> all_domains = new TreeSet<String>();
+ for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
+ all_domains.addAll( gwcd.getAllDomainIds() );
+ }
+ for( final String domain : all_domains ) {
+ final File out = new File( output_dir + ForesterUtil.FILE_SEPARATOR + domain + surfacing.SEQ_EXTRACT_SUFFIX );
+ checkForOutputFileWriteability( out );
+ try {
+ final Writer proteins_file_writer = new BufferedWriter( new FileWriter( out ) );
+ extractProteinNames( protein_lists_per_species,
+ domain,
+ proteins_file_writer,
+ "\t",
+ surfacing.LIMIT_SPEC_FOR_PROT_EX,
+ domain_e_cutoff );
+ proteins_file_writer.close();
+ }
+ catch ( final IOException e ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
+ }
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote proteins list to \"" + out + "\"" );
+ }
+ }
+
public static void writeTaxonomyLinks( final Writer writer,
final String species,
final Map<String, Integer> tax_code_to_id_map ) throws IOException {
return binary_combinations;
}
+ 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 );
+ }
+
private static List<String> splitDomainCombination( final String dc ) {
final String[] s = dc.split( "=" );
if ( s.length != 2 ) {
}
}
+ private final static void writeColorLabels( final String l, final Color c, final Writer w ) throws IOException {
+ w.write( "<tr><td><b><span style=\"color:" );
+ w.write( String.format( "#%02x%02x%02x", c.getRed(), c.getGreen(), c.getBlue() ) );
+ w.write( "\">" );
+ w.write( l );
+ w.write( "</span></b></td></tr>" );
+ w.write( SurfacingConstants.NL );
+ }
+
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,
git://source.jalview.org / jalview.git / blobdiff