import org.forester.protein.Domain;
import org.forester.protein.Protein;
import org.forester.species.Species;
+import org.forester.surfacing.DomainSimilarity.PRINT_OPTION;
import org.forester.surfacing.DomainSimilarityCalculator.Detailedness;
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 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 final static Map<String, String> _TAXCODE_TAXGROUP_MAP = new HashMap<String, String>();
-
-
+ private final static Map<String, String> _TAXCODE_TAXGROUP_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 );
- }
- }
- };
+ @Override
+ public int compare( final Domain d1,
+ final Domain d2 ) {
+ if ( d1.getPerDomainEvalue() < d2
+ .getPerDomainEvalue() ) {
+ return -1;
+ }
+ else if ( d1.getPerDomainEvalue() > d2
+ .getPerDomainEvalue() ) {
+ return 1;
+ }
+ else {
+ return d1.compareTo( d2 );
+ }
+ }
+ };
private final static NumberFormat FORMATTER_3 = new DecimalFormat( "0.000" );
private SurfacingUtil() {
}
}
- public static void checkWriteabilityForPairwiseComparisons( final PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option,
+ public static void checkWriteabilityForPairwiseComparisons( final DomainSimilarity.PRINT_OPTION domain_similarity_print_option,
final String[][] input_file_properties,
final String automated_pairwise_comparison_suffix,
final File outdir ) {
|| ( !get_gains && ( matrix.getState( id, c ) == CharacterStateMatrix.GainLossStates.LOSS ) ) ) {
if ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) {
all_binary_domains_combination_gained.add( AdjactantDirectedBinaryDomainCombination
- .createInstance( matrix.getCharacter( c ) ) );
+ .obtainInstance( matrix.getCharacter( c ) ) );
}
else if ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED ) {
all_binary_domains_combination_gained.add( DirectedBinaryDomainCombination
- .createInstance( matrix.getCharacter( c ) ) );
+ .obtainInstance( matrix.getCharacter( c ) ) );
}
else {
- all_binary_domains_combination_gained.add( BasicBinaryDomainCombination.createInstance( matrix
- .getCharacter( c ) ) );
+ all_binary_domains_combination_gained.add( BasicBinaryDomainCombination.obtainInstance( matrix
+ .getCharacter( c ) ) );
}
}
}
}
public static StringBuilder createParametersAsString( final boolean ignore_dufs,
- final double e_value_max,
+ final double ie_value_max,
+ final double fs_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 );
+ parameters_sb.append( "iE-value: " + ie_value_max );
+ parameters_sb.append( ", FS E-value: " + fs_e_value_max );
if ( cutoff_scores_file != null ) {
parameters_sb.append( ", Cutoff-scores-file: " + cutoff_scores_file );
}
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" ) ) );
+ + "_domains_A.html" ) ) );
split_writers.put( 'b', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_B.html" ) ) );
+ + "_domains_B.html" ) ) );
split_writers.put( 'c', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_C.html" ) ) );
+ + "_domains_C.html" ) ) );
split_writers.put( 'd', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_D.html" ) ) );
+ + "_domains_D.html" ) ) );
split_writers.put( 'e', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_E.html" ) ) );
+ + "_domains_E.html" ) ) );
split_writers.put( 'f', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_F.html" ) ) );
+ + "_domains_F.html" ) ) );
split_writers.put( 'g', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_G.html" ) ) );
+ + "_domains_G.html" ) ) );
split_writers.put( 'h', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_H.html" ) ) );
+ + "_domains_H.html" ) ) );
split_writers.put( 'i', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_I.html" ) ) );
+ + "_domains_I.html" ) ) );
split_writers.put( 'j', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_J.html" ) ) );
+ + "_domains_J.html" ) ) );
split_writers.put( 'k', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_K.html" ) ) );
+ + "_domains_K.html" ) ) );
split_writers.put( 'l', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_L.html" ) ) );
+ + "_domains_L.html" ) ) );
split_writers.put( 'm', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_M.html" ) ) );
+ + "_domains_M.html" ) ) );
split_writers.put( 'n', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_N.html" ) ) );
+ + "_domains_N.html" ) ) );
split_writers.put( 'o', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_O.html" ) ) );
+ + "_domains_O.html" ) ) );
split_writers.put( 'p', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_P.html" ) ) );
+ + "_domains_P.html" ) ) );
split_writers.put( 'q', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_Q.html" ) ) );
+ + "_domains_Q.html" ) ) );
split_writers.put( 'r', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_R.html" ) ) );
+ + "_domains_R.html" ) ) );
split_writers.put( 's', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_S.html" ) ) );
+ + "_domains_S.html" ) ) );
split_writers.put( 't', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_T.html" ) ) );
+ + "_domains_T.html" ) ) );
split_writers.put( 'u', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_U.html" ) ) );
+ + "_domains_U.html" ) ) );
split_writers.put( 'v', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_V.html" ) ) );
+ + "_domains_V.html" ) ) );
split_writers.put( 'w', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_W.html" ) ) );
+ + "_domains_W.html" ) ) );
split_writers.put( 'x', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_X.html" ) ) );
+ + "_domains_X.html" ) ) );
split_writers.put( 'y', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_Y.html" ) ) );
+ + "_domains_Y.html" ) ) );
split_writers.put( 'z', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_Z.html" ) ) );
+ + "_domains_Z.html" ) ) );
split_writers.put( '0', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_0.html" ) ) );
+ + "_domains_0.html" ) ) );
}
public static Map<String, Integer> createTaxCodeToIdMap( final Phylogeny phy ) {
public static void decoratePrintableDomainSimilarities( final SortedSet<DomainSimilarity> domain_similarities,
final Detailedness detailedness ) {
for( final DomainSimilarity domain_similarity : domain_similarities ) {
- if ( domain_similarity instanceof PrintableDomainSimilarity ) {
- final PrintableDomainSimilarity printable_domain_similarity = ( PrintableDomainSimilarity ) domain_similarity;
+ if ( domain_similarity instanceof DomainSimilarity ) {
+ final DomainSimilarity printable_domain_similarity = domain_similarity;
printable_domain_similarity.setDetailedness( detailedness );
}
}
/**
* 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
+ * @param protein_length_stats_by_dc
* @throws IOException
*/
public static void executeFitchGainsAnalysis( final File output_file,
}
if ( is_gains_analysis ) {
out.write( "Sum of all distinct domain combinations appearing once : " + one
- + ForesterUtil.LINE_SEPARATOR );
+ + ForesterUtil.LINE_SEPARATOR );
out.write( "Sum of all distinct domain combinations appearing more than once : " + above_one
- + ForesterUtil.LINE_SEPARATOR );
+ + 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: "
}
else {
out.write( "Sum of all distinct domain combinations never lost : " + never_lost
- + ForesterUtil.LINE_SEPARATOR );
+ + ForesterUtil.LINE_SEPARATOR );
out.write( "Sum of all distinct domain combinations lost once : " + one
- + ForesterUtil.LINE_SEPARATOR );
+ + ForesterUtil.LINE_SEPARATOR );
out.write( "Sum of all distinct domain combinations lost more than once : " + above_one
- + ForesterUtil.LINE_SEPARATOR );
+ + 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 );
+ + 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
- * @param consider_directedness_and_adjacency_for_bin_combinations
+ *
+ * @param all_binary_domains_combination_lost_fitch
+ * @param use_last_in_fitch_parsimony
+ * @param perform_dc_fich
+ * @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 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 boolean use_last_in_fitch_parsimony,
+ final boolean perform_dc_fich ) {
final String sep = ForesterUtil.LINE_SEPARATOR + "###################" + ForesterUtil.LINE_SEPARATOR;
final String date_time = ForesterUtil.getCurrentDateTime();
final SortedSet<String> all_pfams_encountered = new TreeSet<String>();
domain_parsimony.executeDolloParsimonyOnDomainPresence();
}
SurfacingUtil.writeMatrixToFile( domain_parsimony.getGainLossMatrix(), outfile_name
- + surfacing.PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_DOMAINS, Format.FORESTER );
+ + surfacing.PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_DOMAINS, Format.FORESTER );
SurfacingUtil.writeMatrixToFile( domain_parsimony.getGainLossCountsMatrix(), outfile_name
- + surfacing.PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_DOMAINS, Format.FORESTER );
+ + surfacing.PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_DOMAINS, Format.FORESTER );
SurfacingUtil.writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(),
CharacterStateMatrix.GainLossStates.GAIN,
outfile_name + surfacing.PARSIMONY_OUTPUT_DOLLO_GAINS_D,
ForesterUtil.LINE_SEPARATOR,
null );
SurfacingUtil.writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(), null, outfile_name
- + surfacing.PARSIMONY_OUTPUT_DOLLO_PRESENT_D, sep, ForesterUtil.LINE_SEPARATOR, null );
+ + surfacing.PARSIMONY_OUTPUT_DOLLO_PRESENT_D, sep, ForesterUtil.LINE_SEPARATOR, null );
//HTML:
writeBinaryStatesMatrixToList( domain_id_to_go_ids_map,
go_id_to_term_map,
"dollo_on_domains_" + outfile_name,
parameters_str );
SurfacingUtil.writePhylogenyToFile( local_phylogeny_l, outfile_name
- + surfacing.DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO );
+ + surfacing.DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO );
try {
writeAllDomainsChangedOnAllSubtrees( local_phylogeny_l, true, outfile_name, "_dollo_all_gains_d" );
writeAllDomainsChangedOnAllSubtrees( local_phylogeny_l, false, outfile_name, "_dollo_all_losses_d" );
e.printStackTrace();
ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
}
- if ( domain_parsimony.calculateNumberOfBinaryDomainCombination() > 0 ) {
+ if ( perform_dc_fich && ( domain_parsimony.calculateNumberOfBinaryDomainCombination() > 0 ) ) {
// FITCH DOMAIN COMBINATIONS
// -------------------------
local_phylogeny_l = phylogeny.copy();
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 );
+ + surfacing.PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_BINARY_COMBINATIONS, Format.FORESTER );
SurfacingUtil.writeMatrixToFile( domain_parsimony.getGainLossCountsMatrix(), outfile_name
- + surfacing.PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_BINARY_COMBINATIONS, Format.FORESTER );
+ + surfacing.PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_BINARY_COMBINATIONS, Format.FORESTER );
SurfacingUtil
- .writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(),
- CharacterStateMatrix.GainLossStates.GAIN,
- outfile_name + surfacing.PARSIMONY_OUTPUT_FITCH_GAINS_BC,
- sep,
- ForesterUtil.LINE_SEPARATOR,
- null );
+ .writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(),
+ CharacterStateMatrix.GainLossStates.GAIN,
+ outfile_name + surfacing.PARSIMONY_OUTPUT_FITCH_GAINS_BC,
+ sep,
+ ForesterUtil.LINE_SEPARATOR,
+ null );
SurfacingUtil.writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(),
CharacterStateMatrix.GainLossStates.LOSS,
outfile_name
- + surfacing.PARSIMONY_OUTPUT_FITCH_LOSSES_BC,
+ + surfacing.PARSIMONY_OUTPUT_FITCH_LOSSES_BC,
sep,
ForesterUtil.LINE_SEPARATOR,
null );
SurfacingUtil.writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(), null, outfile_name
- + surfacing.PARSIMONY_OUTPUT_FITCH_PRESENT_BC, sep, ForesterUtil.LINE_SEPARATOR, null );
+ + surfacing.PARSIMONY_OUTPUT_FITCH_PRESENT_BC, sep, ForesterUtil.LINE_SEPARATOR, null );
if ( all_binary_domains_combination_gained_fitch != null ) {
collectChangedDomainCombinationsFromBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(),
dc_type,
}
if ( output_binary_domain_combinations_for_graphs ) {
SurfacingUtil
- .writeBinaryStatesMatrixAsListToFileForBinaryCombinationsForGraphAnalysis( domain_parsimony
- .getGainLossMatrix(),
- null,
- outfile_name
- + surfacing.PARSIMONY_OUTPUT_FITCH_PRESENT_BC_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS,
- sep,
- ForesterUtil.LINE_SEPARATOR,
- BinaryDomainCombination.OutputFormat.DOT );
+ .writeBinaryStatesMatrixAsListToFileForBinaryCombinationsForGraphAnalysis( domain_parsimony
+ .getGainLossMatrix(),
+ null,
+ outfile_name
+ + surfacing.PARSIMONY_OUTPUT_FITCH_PRESENT_BC_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS,
+ sep,
+ ForesterUtil.LINE_SEPARATOR,
+ BinaryDomainCombination.OutputFormat.DOT );
}
// HTML:
writeBinaryStatesMatrixToList( domain_id_to_go_ids_map,
date_time,
"Fitch parsimony on binary domain combination presence/absence randomization: "
+ randomization,
- "fitch_on_binary_domain_combinations_" + outfile_name,
- parameters_str );
+ "fitch_on_binary_domain_combinations_" + outfile_name,
+ parameters_str );
SurfacingUtil.writePhylogenyToFile( local_phylogeny_l, outfile_name
- + surfacing.BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH );
+ + surfacing.BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH );
calculateIndependentDomainCombinationGains( local_phylogeny_l,
outfile_name
- + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_OUTPUT_SUFFIX,
+ + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_OUTPUT_SUFFIX,
outfile_name
- + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_OUTPUT_SUFFIX,
+ + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_OUTPUT_SUFFIX,
outfile_name
- + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_SUFFIX,
+ + 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,
+ + 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",
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 );
+ + surfacing.PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_SECONDARY_FEATURES, Format.FORESTER );
SurfacingUtil.writeMatrixToFile( secondary_features_parsimony.getGainLossCountsMatrix(), outfile_name
- + surfacing.PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_SECONDARY_FEATURES, Format.FORESTER );
+ + surfacing.PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_SECONDARY_FEATURES, Format.FORESTER );
SurfacingUtil
- .writeBinaryStatesMatrixAsListToFile( secondary_features_parsimony.getGainLossMatrix(),
- CharacterStateMatrix.GainLossStates.GAIN,
- outfile_name
- + surfacing.PARSIMONY_OUTPUT_DOLLO_GAINS_SECONDARY_FEATURES,
- sep,
- ForesterUtil.LINE_SEPARATOR,
- null );
+ .writeBinaryStatesMatrixAsListToFile( secondary_features_parsimony.getGainLossMatrix(),
+ CharacterStateMatrix.GainLossStates.GAIN,
+ outfile_name
+ + surfacing.PARSIMONY_OUTPUT_DOLLO_GAINS_SECONDARY_FEATURES,
+ sep,
+ ForesterUtil.LINE_SEPARATOR,
+ null );
SurfacingUtil
- .writeBinaryStatesMatrixAsListToFile( secondary_features_parsimony.getGainLossMatrix(),
- CharacterStateMatrix.GainLossStates.LOSS,
- outfile_name
- + surfacing.PARSIMONY_OUTPUT_DOLLO_LOSSES_SECONDARY_FEATURES,
- sep,
- ForesterUtil.LINE_SEPARATOR,
- null );
+ .writeBinaryStatesMatrixAsListToFile( secondary_features_parsimony.getGainLossMatrix(),
+ CharacterStateMatrix.GainLossStates.LOSS,
+ outfile_name
+ + surfacing.PARSIMONY_OUTPUT_DOLLO_LOSSES_SECONDARY_FEATURES,
+ sep,
+ ForesterUtil.LINE_SEPARATOR,
+ null );
SurfacingUtil
- .writeBinaryStatesMatrixAsListToFile( secondary_features_parsimony.getGainLossMatrix(),
- null,
- outfile_name
- + surfacing.PARSIMONY_OUTPUT_DOLLO_PRESENT_SECONDARY_FEATURES,
- sep,
- ForesterUtil.LINE_SEPARATOR,
- null );
+ .writeBinaryStatesMatrixAsListToFile( secondary_features_parsimony.getGainLossMatrix(),
+ null,
+ outfile_name
+ + surfacing.PARSIMONY_OUTPUT_DOLLO_PRESENT_SECONDARY_FEATURES,
+ sep,
+ ForesterUtil.LINE_SEPARATOR,
+ null );
preparePhylogeny( local_phylogeny_copy,
secondary_features_parsimony,
date_time,
"dollo_on_secondary_features_" + outfile_name,
parameters_str );
SurfacingUtil.writePhylogenyToFile( local_phylogeny_copy, outfile_name
- + surfacing.SECONDARY_FEATURES_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO );
+ + 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 );
+ .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 );
+ "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 );
+ + 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 );
+ + 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 executePlusMinusAnalysis( final File output_file,
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 );
+ + 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();
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 \""
final PhylogenyNode n = it.next();
if ( ForesterUtil.isEmpty( n.getName() )
&& ( !n.getNodeData().isHasTaxonomy() || ForesterUtil.isEmpty( n.getNodeData().getTaxonomy()
- .getScientificName() ) )
- && ( !n.getNodeData().isHasTaxonomy() || ForesterUtil.isEmpty( n.getNodeData().getTaxonomy()
- .getCommonName() ) ) ) {
+ .getScientificName() ) )
+ && ( !n.getNodeData().isHasTaxonomy() || ForesterUtil.isEmpty( n.getNodeData().getTaxonomy()
+ .getCommonName() ) ) ) {
if ( n.getParent() != null ) {
names.append( " " );
names.append( n.getParent().getName() );
.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" );
+ + "] 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" );
+ + "] 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 );
+ + "]: " + error );
}
if ( ( intree == null ) || intree.isEmpty() ) {
ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is empty" );
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 + "]" );
+ + "] 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 );
preparePhylogenyForParsimonyAnalyses( intree, input_file_properties );
if ( !intree.isCompletelyBinary() ) {
ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "input tree [" + intree_file
- + "] is not completely binary" );
+ + "] is not completely binary" );
}
intrees[ i++ ] = intree;
}
.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" );
+ + "] 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" );
+ + "] contains more than one phylogeny in phyloXML format" );
}
intree = phys[ 0 ];
}
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();
-// }
+ // 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();
+ // }
final String group = obtainTaxonomyGroup( tax_code, phy );
- Color c = ForesterUtil.obtainColorDependingOnTaxonomyGroup( group );
+ final Color c = ForesterUtil.obtainColorDependingOnTaxonomyGroup( group );
if ( c == null ) {
- throw new IllegalArgumentException( "no color found for taxonomy code \"" + tax_code + "\"" );
- }
+ throw new IllegalArgumentException( "no color found for taxonomy group \"" + group
+ + "\" for 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)" );
+ + " (tree is null or empty and code is not in map)" );
}
}
return _TAXCODE_HEXCOLORSTRING_MAP.get( tax_code );
}
-
-
+
public static String obtainTaxonomyGroup( final String tax_code, final Phylogeny species_tree )
throws IllegalArgumentException {
if ( !_TAXCODE_TAXGROUP_MAP.containsKey( tax_code ) ) {
if ( ( species_tree != null ) && !species_tree.isEmpty() ) {
final List<PhylogenyNode> nodes = species_tree.getNodesViaTaxonomyCode( tax_code );
-
if ( ( nodes == null ) || nodes.isEmpty() ) {
throw new IllegalArgumentException( "code " + tax_code + " is not found" );
}
}
PhylogenyNode n = nodes.get( 0 );
String group = null;
-
while ( n != null ) {
if ( n.getNodeData().isHasTaxonomy()
&& !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getScientificName() ) ) {
group = ForesterUtil.obtainNormalizedTaxonomyGroup( n.getNodeData().getTaxonomy()
- .getScientificName() );
-
+ .getScientificName() );
}
- if ( ForesterUtil.isEmpty( group ) && !ForesterUtil.isEmpty( n.getName() ) ) {
+ if ( ForesterUtil.isEmpty( group ) && !ForesterUtil.isEmpty( n.getName() ) ) {
group = ForesterUtil.obtainNormalizedTaxonomyGroup( n.getName() );
-
}
- if ( !ForesterUtil.isEmpty( group ) ) {
+ if ( !ForesterUtil.isEmpty( group ) ) {
break;
}
-
n = n.getParent();
}
- if ( ForesterUtil.isEmpty( group ) ) {
+ if ( ForesterUtil.isEmpty( group ) ) {
throw new IllegalArgumentException( "no group found for taxonomy code \"" + tax_code + "\"" );
}
-
_TAXCODE_TAXGROUP_MAP.put( tax_code, group );
}
else {
throw new IllegalArgumentException( "unable to obtain group for code " + tax_code
- + " (tree is null or empty and code is not in map)" );
+ + " (tree is null or empty and code is not in map)" );
}
}
return _TAXCODE_TAXGROUP_MAP.get( tax_code );
}
-
-
-
public static void performDomainArchitectureAnalysis( final SortedMap<String, Set<String>> domain_architecutures,
final SortedMap<String, Integer> domain_architecuture_counts,
}
else {
ForesterUtil
- .fatalError( surfacing.PRG_NAME,
- "node with no name, scientific name, common name, or taxonomy code present" );
+ .fatalError( surfacing.PRG_NAME,
+ "node with no name, scientific name, common name, or taxonomy code present" );
}
}
}
}
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), '$F=<double>' factor (default is 1.0), double), or '#' (ignore) suffix, encountered: \""
- + species + "\"" );
+ .fatalError( surfacing.PRG_NAME,
+ "species/genome names in 'plus minus' file must begin with '*' (high copy target genome), '+' (high copy base genomes), '-' (low copy genomes), '$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 + "" ) );
/*
* species | protein id | n-terminal domain | c-terminal domain | n-terminal domain per domain E-value | c-terminal domain per domain E-value
- *
- *
+ *
+ *
*/
static public StringBuffer proteinToDomainCombinations( final Protein protein,
final String protein_id,
final SortedSet<String> domains = collectAllDomainsChangedOnSubtree( node, get_gains );
if ( domains.size() > 0 ) {
final Writer writer = ForesterUtil.createBufferedWriter( base_dir + ForesterUtil.FILE_SEPARATOR
- + node.getName() + suffix_for_filename );
+ + node.getName() + suffix_for_filename );
for( final String domain : domains ) {
writer.write( domain );
writer.write( ForesterUtil.LINE_SEPARATOR );
final BufferedWriter out_dot = new BufferedWriter( new FileWriter( dc_outfile_dot ) );
for( final BinaryDomainCombination bdc : binary_combinations ) {
out_dot.write( bdc.toGraphDescribingLanguage( BinaryDomainCombination.OutputFormat.DOT, null, null )
- .toString() );
+ .toString() );
out_dot.write( SurfacingConstants.NL );
}
out_dot.close();
catch ( final IOException e ) {
ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
}
- ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote binary domain combination for \""
- + input_file_properties[ i ][ 0 ] + "\" (" + input_file_properties[ i ][ 1 ] + ", "
- + input_file_properties[ i ][ 2 ] + ") to: \"" + dc_outfile_dot + "\"" );
+ if ( input_file_properties[ i ].length == 3 ) {
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote binary domain combination for \""
+ + input_file_properties[ i ][ 0 ] + "\" (" + input_file_properties[ i ][ 1 ] + ", "
+ + input_file_properties[ i ][ 2 ] + ") to: \"" + dc_outfile_dot + "\"" );
+ }
+ else {
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote binary domain combination for \""
+ + input_file_properties[ i ][ 0 ] + "\" (" + input_file_properties[ i ][ 1 ] + ") to: \""
+ + dc_outfile_dot + "\"" );
+ }
}
public static void writeBinaryStatesMatrixAsListToFile( final CharacterStateMatrix<CharacterStateMatrix.GainLossStates> matrix,
.getState( id, c ) == CharacterStateMatrix.GainLossStates.UNCHANGED_PRESENT ) ) ) ) {
BinaryDomainCombination bdc = null;
try {
- bdc = BasicBinaryDomainCombination.createInstance( matrix.getCharacter( c ) );
+ bdc = BasicBinaryDomainCombination.obtainInstance( matrix.getCharacter( c ) );
}
catch ( final Exception e ) {
ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
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 );
+ + 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 );
out.write( SurfacingConstants.NL );
out.write( "<hr>" );
out.write( SurfacingConstants.NL );
- } // for( final String id : sorted_ids ) {
+ } // for( final String id : sorted_ids ) {
out.write( "</body>" );
out.write( SurfacingConstants.NL );
out.write( "</html>" );
}
else {
per_genome_domain_promiscuity_statistics_writer.write( FORMATTER_3.format( stats
- .sampleStandardDeviation() ) + "\t" );
+ .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" );
final SortedSet<DomainSimilarity> similarities,
final boolean treat_as_binary,
final List<Species> species_order,
- final PrintableDomainSimilarity.PRINT_OPTION print_option,
+ final DomainSimilarity.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 {
+ final Phylogeny phy,
+ final Set<String> pos_filter_doms ) throws IOException {
if ( ( single_writer != null ) && ( ( split_writers == null ) || split_writers.isEmpty() ) ) {
split_writers = new HashMap<Character, Writer>();
split_writers.put( '_', single_writer );
//
for( final DomainSimilarity similarity : similarities ) {
if ( ( species_order != null ) && !species_order.isEmpty() ) {
- ( ( PrintableDomainSimilarity ) similarity ).setSpeciesOrder( species_order );
+ ( similarity ).setSpeciesOrder( species_order );
}
if ( single_writer != null ) {
- single_writer.write( "<tr><td><b><a href=\"#" + similarity.getDomainId() + "\">"
- + similarity.getDomainId() + "</a></b></td></tr>" );
+ if ( !ForesterUtil.isEmpty( pos_filter_doms ) && pos_filter_doms.contains( similarity.getDomainId() ) ) {
+ single_writer.write( "<tr><td><b><a href=\"#" + similarity.getDomainId()
+ + "\"><span style=\"color:#00ff00\">" + similarity.getDomainId()
+ + "</span></a></b></td></tr>" );
+ }
+ else {
+ 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 ) );
+ .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>" );
+ if ( !ForesterUtil.isEmpty( pos_filter_doms ) && pos_filter_doms.contains( similarity.getDomainId() ) ) {
+ local_writer.write( "<tr><td><b><a href=\"#" + similarity.getDomainId()
+ + "\"><span style=\"color:#00ff00\">" + similarity.getDomainId()
+ + "</span></a></b></td></tr>" );
+ }
+ else {
+ local_writer.write( "<tr><td><b><a href=\"#" + similarity.getDomainId() + "\">"
+ + similarity.getDomainId() + "</a></b></td></tr>" );
+ }
local_writer.write( SurfacingConstants.NL );
}
}
//
for( final DomainSimilarity similarity : similarities ) {
if ( ( species_order != null ) && !species_order.isEmpty() ) {
- ( ( PrintableDomainSimilarity ) similarity ).setSpeciesOrder( species_order );
+ ( similarity ).setSpeciesOrder( species_order );
}
if ( simple_tab_writer != null ) {
simple_tab_writer.write( similarity.toStringBuffer( PRINT_OPTION.SIMPLE_TAB_DELIMITED,
}
else {
Writer local_writer = split_writers.get( ( similarity.getDomainId().charAt( 0 ) + "" ).toLowerCase()
- .charAt( 0 ) );
+ .charAt( 0 ) );
if ( local_writer == null ) {
local_writer = split_writers.get( '0' );
}
writeMatrixToFile( DomainParsimonyCalculator.createMatrixOfDomainPresenceOrAbsence( gwcd_list,
positive_filter_file == null ? null
: filter ),
- output_file + surfacing.DOMAINS_PRESENT_NEXUS,
- Format.NEXUS_BINARY );
+ output_file + surfacing.DOMAINS_PRESENT_NEXUS,
+ Format.NEXUS_BINARY );
writeMatrixToFile( DomainParsimonyCalculator.createMatrixOfBinaryDomainCombinationPresenceOrAbsence( gwcd_list ),
output_file + surfacing.BDC_PRESENT_NEXUS,
Format.NEXUS_BINARY );
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 double domain_e_cutoff,
+ final Set<String> pos_filter_doms ) {
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 ) {
+ if ( !ForesterUtil.isEmpty( pos_filter_doms ) && !pos_filter_doms.contains( domain ) ) {
+ continue;
+ }
final File out = new File( output_dir + ForesterUtil.FILE_SEPARATOR + domain + surfacing.SEQ_EXTRACT_SUFFIX );
checkForOutputFileWriteability( out );
try {
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>" );
+ + tax_code_to_id_map.get( species ) + "\" target=\"taxonomy_window\">uniprot</a>" );
}
else {
writer.write( "<a href=\"" + SurfacingConstants.EOL_LINK + species
- + "\" target=\"taxonomy_window\">eol</a>" );
+ + "\" target=\"taxonomy_window\">eol</a>" );
writer.write( "|" );
writer.write( "<a href=\"" + SurfacingConstants.GOOGLE_SCHOLAR_SEARCH + species
- + "\" target=\"taxonomy_window\">scholar</a>" );
+ + "\" target=\"taxonomy_window\">scholar</a>" );
writer.write( "|" );
writer.write( "<a href=\"" + SurfacingConstants.GOOGLE_WEB_SEARCH_LINK + species
- + "\" target=\"taxonomy_window\">google</a>" );
+ + "\" target=\"taxonomy_window\">google</a>" );
}
writer.write( "]" );
}
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() );
+ .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() );
+ .arithmeticMean() );
}
if ( domain_length_stats_by_domain != null ) {
if ( !dc_reapp_counts_to_domain_lengths_stats.containsKey( count ) ) {
}
final String[] ds = dc.split( "=" );
dc_reapp_counts_to_domain_lengths_stats.get( count ).addValue( domain_length_stats_by_domain
- .get( ds[ 0 ] ).arithmeticMean() );
+ .get( ds[ 0 ] ).arithmeticMean() );
dc_reapp_counts_to_domain_lengths_stats.get( count ).addValue( domain_length_stats_by_domain
- .get( ds[ 1 ] ).arithmeticMean() );
+ .get( ds[ 1 ] ).arithmeticMean() );
}
if ( count > 1 ) {
more_than_once.add( dc );
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 );
+ + 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" );
+ + 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" );
+ + 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" );
+ + 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" );
+ + 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" );
+ + 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();
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 );
+ + 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;
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 + "\"" );
+ + "] 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
- + "\"" );
+ + "] 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 + "\"" );
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() ) + "%]" );
+ + " [" + ( ( 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 + " ["
if ( ForesterUtil.isEmpty( domain_1 ) ) {
domain_count = 1;
}
- // The following has a difficult to understand logic.
+ // The following has a difficult to understand logic.
for( int d = 0; d < domain_count; ++d ) {
List<GoId> go_ids = null;
boolean go_annotation_present = false;
final String go_id_str = go_id.getId();
out.write( "<td>" );
out.write( "<a href=\"" + SurfacingConstants.AMIGO_LINK + go_id_str
- + "\" target=\"amigo_window\">" + go_id_str + "</a>" );
+ + "\" target=\"amigo_window\">" + go_id_str + "</a>" );
out.write( "</td><td>" );
out.write( go_term.getName() );
if ( domain_count == 2 ) {
out.write( SurfacingConstants.NL );
}
}
- } // for( int d = 0; d < domain_count; ++d )
+ } // for( int d = 0; d < domain_count; ++d )
if ( !any_go_annotation_present ) {
out.write( "<tr>" );
writeDomainIdsToHtml( out, domain_0, domain_1, prefix_for_html, domain_id_to_secondary_features_maps );
final String domain_1,
final String prefix_for_detailed_html,
final Map<String, Set<String>>[] domain_id_to_secondary_features_maps )
- throws IOException {
+ throws IOException {
out.write( "<td>" );
if ( !ForesterUtil.isEmpty( prefix_for_detailed_html ) ) {
out.write( prefix_for_detailed_html );
}
writer.close();
ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote " + pfams.size() + " pfams to [" + outfile_name
- + "]" );
+ + "]" );
}
catch ( final IOException e ) {
ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "Failure to write: " + e );
final Phylogeny phylogeny ) {
if ( !( matrix instanceof BasicCharacterStateMatrix ) ) {
throw new IllegalArgumentException( "can only write matrices of type [" + BasicCharacterStateMatrix.class
- + "] to nexus" );
+ + "] to nexus" );
}
final BasicCharacterStateMatrix<BinaryStates> my_matrix = ( org.forester.evoinference.matrix.character.BasicCharacterStateMatrix<BinaryStates> ) matrix;
final List<Phylogeny> phylogenies = new ArrayList<Phylogeny>( 1 );