import org.forester.phylogeny.data.BinaryCharacters;
import org.forester.phylogeny.data.Confidence;
import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
+import org.forester.protein.BasicProtein;
+import org.forester.protein.BinaryDomainCombination;
+import org.forester.protein.Domain;
+import org.forester.protein.DomainId;
+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;
}
};
public final static Pattern PATTERN_SP_STYLE_TAXONOMY = Pattern.compile( "^[A-Z0-9]{3,5}$" );
+ private static final boolean USE_LAST = true;
private SurfacingUtil() {
// Hidden constructor.
randomization = "yes, seed = " + random_number_seed_for_fitch_parsimony;
}
else {
- domain_parsimony.executeFitchParsimonyOnBinaryDomainCombintion( false );
+ domain_parsimony.executeFitchParsimonyOnBinaryDomainCombintion( USE_LAST );
}
SurfacingUtil.writeMatrixToFile( domain_parsimony.getGainLossMatrix(), outfile_name
+ surfacing.PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_BINARY_COMBINATIONS, Format.FORESTER );
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 );
+ 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" );
}
public static void extractProteinNames( final List<Protein> proteins,
final List<DomainId> 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<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.flush();
}
+ public static void extractProteinNames( final SortedMap<Species, List<Protein>> protein_lists_per_species,
+ final DomainId domain_id,
+ final Writer out,
+ final String separator,
+ final String limit_to_species ) throws IOException {
+ for( final Species species : protein_lists_per_species.keySet() ) {
+ 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 ) {
+ final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
+ for( final Domain domain : domains ) {
+ stats.addValue( domain.getPerSequenceEvalue() );
+ }
+ out.write( protein.getSpecies().getSpeciesId() );
+ out.write( separator );
+ out.write( protein.getProteinId().getId() );
+ out.write( separator );
+ out.write( "[" + FORMATTER.format( stats.median() ) + "]" );
+ 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 SortedSet<DomainId> getAllDomainIds( final List<GenomeWideCombinableDomains> gwcd_list ) {
final SortedSet<DomainId> all_domains_ids = new TreeSet<DomainId>();
for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
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 ) {
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() + "" );
+ 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 ) {