org.forester.surfacing
Class SurfacingUtil
java.lang.Object
org.forester.surfacing.SurfacingUtil
public final class SurfacingUtil
- extends java.lang.Object
|
Method Summary |
static void |
addAllBinaryDomainCombinationToSet(GenomeWideCombinableDomains genome,
java.util.SortedSet<BinaryDomainCombination> binary_domain_combinations)
|
static void |
addAllDomainIdsToSet(GenomeWideCombinableDomains genome,
java.util.SortedSet<DomainId> domain_ids)
|
static void |
addHtmlHead(java.io.Writer w,
java.lang.String title)
|
static DescriptiveStatistics |
calculateDescriptiveStatisticsForMeanValues(java.util.Set<DomainSimilarity> similarities)
|
static int |
calculateOverlap(Domain domain,
java.util.List<java.lang.Boolean> covered_positions)
|
static void |
checkForOutputFileWriteability(java.io.File outfile)
|
static void |
collectChangedDomainCombinationsFromBinaryStatesMatrixAsListToFile(CharacterStateMatrix<CharacterStateMatrix.GainLossStates> matrix,
BinaryDomainCombination.DomainCombinationType dc_type,
java.util.List<BinaryDomainCombination> all_binary_domains_combination_gained,
boolean get_gains)
|
static java.util.Map<DomainId,java.util.List<GoId>> |
createDomainIdToGoIdMap(java.util.List<PfamToGoMapping> pfam_to_go_mappings)
|
static java.util.Map<DomainId,java.util.Set<java.lang.String>> |
createDomainIdToSecondaryFeaturesMap(java.io.File secondary_features_map_file)
|
static Phylogeny |
createNjTreeBasedOnMatrixToFile(java.io.File nj_tree_outfile,
DistanceMatrix distance)
|
static void |
decoratePrintableDomainSimilarities(java.util.SortedSet<DomainSimilarity> domain_similarities,
DomainSimilarityCalculator.Detailedness detailedness,
DomainSimilarityCalculator.GoAnnotationOutput go_annotation_output,
java.util.Map<GoId,GoTerm> go_id_to_term_map,
GoNameSpace go_namespace_limit)
|
static void |
doit(java.util.List<Protein> proteins,
java.util.List<DomainId> query_domain_ids_nc_order,
java.io.Writer out,
java.lang.String separator,
java.lang.String limit_to_species,
java.util.Map<java.lang.String,java.util.List<java.lang.Integer>> average_protein_lengths_by_dc)
|
static void |
domainsPerProteinsStatistics(java.lang.String genome,
java.util.List<Protein> protein_list,
DescriptiveStatistics all_genomes_domains_per_potein_stats,
java.util.SortedMap<java.lang.Integer,java.lang.Integer> all_genomes_domains_per_potein_histo,
java.util.SortedSet<java.lang.String> domains_which_are_always_single,
java.util.SortedSet<java.lang.String> domains_which_are_sometimes_single_sometimes_not,
java.util.SortedSet<java.lang.String> domains_which_never_single,
java.io.Writer writer)
|
static void |
executeDomainLengthAnalysis(java.lang.String[][] input_file_properties,
int number_of_genomes,
DomainLengthsTable domain_lengths_table,
java.io.File outfile)
|
static void |
executeParsimonyAnalysis(long random_number_seed_for_fitch_parsimony,
boolean radomize_fitch_parsimony,
java.lang.String outfile_name,
DomainParsimonyCalculator domain_parsimony,
Phylogeny phylogeny,
java.util.Map<DomainId,java.util.List<GoId>> domain_id_to_go_ids_map,
java.util.Map<GoId,GoTerm> go_id_to_term_map,
GoNameSpace go_namespace_limit,
java.lang.String parameters_str,
java.util.Map<DomainId,java.util.Set<java.lang.String>>[] domain_id_to_secondary_features_maps,
java.util.SortedSet<DomainId> positive_filter,
boolean output_binary_domain_combinations_for_graphs,
java.util.List<BinaryDomainCombination> all_binary_domains_combination_gained_fitch,
java.util.List<BinaryDomainCombination> all_binary_domains_combination_lost_fitch,
BinaryDomainCombination.DomainCombinationType dc_type,
java.util.Map<java.lang.String,DescriptiveStatistics> protein_length_stats_by_dc,
java.util.Map<java.lang.String,DescriptiveStatistics> domain_number_stats_by_dc,
java.util.Map<java.lang.String,DescriptiveStatistics> domain_length_stats_by_domain)
|
static void |
executeParsimonyAnalysisForSecondaryFeatures(java.lang.String outfile_name,
DomainParsimonyCalculator secondary_features_parsimony,
Phylogeny phylogeny,
java.lang.String parameters_str,
java.util.Map<Species,MappingResults> mapping_results_map)
|
static void |
extractProteinNames(java.util.List<Protein> proteins,
java.util.List<DomainId> query_domain_ids_nc_order,
java.io.Writer out,
java.lang.String separator,
java.lang.String limit_to_species)
|
static void |
extractProteinNames(java.util.SortedMap<Species,java.util.List<Protein>> protein_lists_per_species,
DomainId domain_id,
java.io.Writer out,
java.lang.String separator,
java.lang.String limit_to_species)
|
static java.util.SortedSet<DomainId> |
getAllDomainIds(java.util.List<GenomeWideCombinableDomains> gwcd_list)
|
static java.util.SortedMap<java.lang.String,java.lang.Integer> |
getDomainCounts(java.util.List<Protein> protein_domain_collections)
|
static int |
getNumberOfNodesLackingName(Phylogeny p,
java.lang.StringBuilder names)
|
static boolean |
isEngulfed(Domain domain,
java.util.List<java.lang.Boolean> covered_positions)
Returns true is Domain domain falls in an uninterrupted stretch of
covered positions. |
static void |
preparePhylogeny(Phylogeny p,
DomainParsimonyCalculator domain_parsimony,
java.lang.String date_time,
java.lang.String method,
java.lang.String name,
java.lang.String parameters_str)
|
static java.lang.StringBuffer |
proteinToDomainCombinations(Protein protein,
java.lang.String protein_id,
java.lang.String separator)
|
static Protein |
removeOverlappingDomains(int max_allowed_overlap,
boolean remove_engulfed_domains,
Protein protein)
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 |
static java.util.List<Domain> |
sortDomainsWithAscendingConfidenceValues(Protein protein)
|
static void |
writeAllDomainsChangedOnAllSubtrees(Phylogeny p,
boolean get_gains,
java.lang.String outdir,
java.lang.String suffix_for_filename)
|
static void |
writeBinaryDomainCombinationsFileForGraphAnalysis(java.lang.String[][] input_file_properties,
java.io.File output_dir,
GenomeWideCombinableDomains gwcd,
int i,
GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder dc_sort_order)
|
static void |
writeBinaryStatesMatrixAsListToFile(CharacterStateMatrix<CharacterStateMatrix.GainLossStates> matrix,
CharacterStateMatrix.GainLossStates state,
java.lang.String filename,
java.lang.String indentifier_characters_separator,
java.lang.String character_separator,
java.util.Map<java.lang.String,java.lang.String> descriptions)
|
static void |
writeBinaryStatesMatrixAsListToFileForBinaryCombinationsForGraphAnalysis(CharacterStateMatrix<CharacterStateMatrix.GainLossStates> matrix,
CharacterStateMatrix.GainLossStates state,
java.lang.String filename,
java.lang.String indentifier_characters_separator,
java.lang.String character_separator,
BinaryDomainCombination.OutputFormat bc_output_format)
|
static void |
writeBinaryStatesMatrixToList(java.util.Map<DomainId,java.util.List<GoId>> domain_id_to_go_ids_map,
java.util.Map<GoId,GoTerm> go_id_to_term_map,
GoNameSpace go_namespace_limit,
boolean domain_combinations,
CharacterStateMatrix<CharacterStateMatrix.GainLossStates> matrix,
CharacterStateMatrix.GainLossStates state,
java.lang.String filename,
java.lang.String indentifier_characters_separator,
java.lang.String character_separator,
java.lang.String title_for_html,
java.lang.String prefix_for_html,
java.util.Map<DomainId,java.util.Set<java.lang.String>>[] domain_id_to_secondary_features_maps,
java.util.SortedSet<java.lang.String> all_pfams_encountered,
java.util.SortedSet<java.lang.String> pfams_gained_or_lost,
java.lang.String suffix_for_per_node_events_file)
|
static void |
writeDomainCombinationsCountsFile(java.lang.String[][] input_file_properties,
java.io.File output_dir,
java.io.Writer per_genome_domain_promiscuity_statistics_writer,
GenomeWideCombinableDomains gwcd,
int i,
GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder dc_sort_order)
|
static DescriptiveStatistics |
writeDomainSimilaritiesToFile(java.lang.StringBuilder html_desc,
java.lang.StringBuilder html_title,
java.io.Writer single_writer,
java.util.Map<java.lang.Character,java.io.Writer> split_writers,
java.util.SortedSet<DomainSimilarity> similarities,
boolean treat_as_binary,
java.util.List<Species> species_order,
PrintableDomainSimilarity.PRINT_OPTION print_option,
DomainSimilarity.DomainSimilaritySortField sort_field,
DomainSimilarity.DomainSimilarityScoring scoring,
boolean verbose)
|
static void |
writeMatrixToFile(CharacterStateMatrix<?> matrix,
java.lang.String filename,
CharacterStateMatrix.Format format)
|
static void |
writeMatrixToFile(java.io.File matrix_outfile,
java.util.List<DistanceMatrix> matrices)
|
static void |
writePhylogenyToFile(Phylogeny phylogeny,
java.lang.String filename)
|
static void |
writeTaxonomyLinks(java.io.Writer writer,
java.lang.String species)
|
| Methods inherited from class java.lang.Object |
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
PATTERN_SP_STYLE_TAXONOMY
public static final java.util.regex.Pattern PATTERN_SP_STYLE_TAXONOMY
addAllBinaryDomainCombinationToSet
public static void addAllBinaryDomainCombinationToSet(GenomeWideCombinableDomains genome,
java.util.SortedSet<BinaryDomainCombination> binary_domain_combinations)
addAllDomainIdsToSet
public static void addAllDomainIdsToSet(GenomeWideCombinableDomains genome,
java.util.SortedSet<DomainId> domain_ids)
addHtmlHead
public static void addHtmlHead(java.io.Writer w,
java.lang.String title)
throws java.io.IOException
- Throws:
java.io.IOException
calculateDescriptiveStatisticsForMeanValues
public static DescriptiveStatistics calculateDescriptiveStatisticsForMeanValues(java.util.Set<DomainSimilarity> similarities)
calculateOverlap
public static int calculateOverlap(Domain domain,
java.util.List<java.lang.Boolean> covered_positions)
checkForOutputFileWriteability
public static void checkForOutputFileWriteability(java.io.File outfile)
collectChangedDomainCombinationsFromBinaryStatesMatrixAsListToFile
public static void collectChangedDomainCombinationsFromBinaryStatesMatrixAsListToFile(CharacterStateMatrix<CharacterStateMatrix.GainLossStates> matrix,
BinaryDomainCombination.DomainCombinationType dc_type,
java.util.List<BinaryDomainCombination> all_binary_domains_combination_gained,
boolean get_gains)
createDomainIdToGoIdMap
public static java.util.Map<DomainId,java.util.List<GoId>> createDomainIdToGoIdMap(java.util.List<PfamToGoMapping> pfam_to_go_mappings)
createDomainIdToSecondaryFeaturesMap
public static java.util.Map<DomainId,java.util.Set<java.lang.String>> createDomainIdToSecondaryFeaturesMap(java.io.File secondary_features_map_file)
throws java.io.IOException
- Throws:
java.io.IOException
createNjTreeBasedOnMatrixToFile
public static Phylogeny createNjTreeBasedOnMatrixToFile(java.io.File nj_tree_outfile,
DistanceMatrix distance)
decoratePrintableDomainSimilarities
public static void decoratePrintableDomainSimilarities(java.util.SortedSet<DomainSimilarity> domain_similarities,
DomainSimilarityCalculator.Detailedness detailedness,
DomainSimilarityCalculator.GoAnnotationOutput go_annotation_output,
java.util.Map<GoId,GoTerm> go_id_to_term_map,
GoNameSpace go_namespace_limit)
executeDomainLengthAnalysis
public static void executeDomainLengthAnalysis(java.lang.String[][] input_file_properties,
int number_of_genomes,
DomainLengthsTable domain_lengths_table,
java.io.File outfile)
throws java.io.IOException
- Throws:
java.io.IOException
executeParsimonyAnalysis
public static void executeParsimonyAnalysis(long random_number_seed_for_fitch_parsimony,
boolean radomize_fitch_parsimony,
java.lang.String outfile_name,
DomainParsimonyCalculator domain_parsimony,
Phylogeny phylogeny,
java.util.Map<DomainId,java.util.List<GoId>> domain_id_to_go_ids_map,
java.util.Map<GoId,GoTerm> go_id_to_term_map,
GoNameSpace go_namespace_limit,
java.lang.String parameters_str,
java.util.Map<DomainId,java.util.Set<java.lang.String>>[] domain_id_to_secondary_features_maps,
java.util.SortedSet<DomainId> positive_filter,
boolean output_binary_domain_combinations_for_graphs,
java.util.List<BinaryDomainCombination> all_binary_domains_combination_gained_fitch,
java.util.List<BinaryDomainCombination> all_binary_domains_combination_lost_fitch,
BinaryDomainCombination.DomainCombinationType dc_type,
java.util.Map<java.lang.String,DescriptiveStatistics> protein_length_stats_by_dc,
java.util.Map<java.lang.String,DescriptiveStatistics> domain_number_stats_by_dc,
java.util.Map<java.lang.String,DescriptiveStatistics> domain_length_stats_by_domain)
- Parameters:
all_binary_domains_combination_lost_fitch - consider_directedness_and_adjacency_for_bin_combinations - all_binary_domains_combination_gained - if null ignored, otherwise this is to list all binary domain combinations
which were gained under unweighted (Fitch) parsimony.
executeParsimonyAnalysisForSecondaryFeatures
public static void executeParsimonyAnalysisForSecondaryFeatures(java.lang.String outfile_name,
DomainParsimonyCalculator secondary_features_parsimony,
Phylogeny phylogeny,
java.lang.String parameters_str,
java.util.Map<Species,MappingResults> mapping_results_map)
doit
public static void doit(java.util.List<Protein> proteins,
java.util.List<DomainId> query_domain_ids_nc_order,
java.io.Writer out,
java.lang.String separator,
java.lang.String limit_to_species,
java.util.Map<java.lang.String,java.util.List<java.lang.Integer>> average_protein_lengths_by_dc)
throws java.io.IOException
- Throws:
java.io.IOException
extractProteinNames
public static void extractProteinNames(java.util.List<Protein> proteins,
java.util.List<DomainId> query_domain_ids_nc_order,
java.io.Writer out,
java.lang.String separator,
java.lang.String limit_to_species)
throws java.io.IOException
- Throws:
java.io.IOException
extractProteinNames
public static void extractProteinNames(java.util.SortedMap<Species,java.util.List<Protein>> protein_lists_per_species,
DomainId domain_id,
java.io.Writer out,
java.lang.String separator,
java.lang.String limit_to_species)
throws java.io.IOException
- Throws:
java.io.IOException
getAllDomainIds
public static java.util.SortedSet<DomainId> getAllDomainIds(java.util.List<GenomeWideCombinableDomains> gwcd_list)
getDomainCounts
public static java.util.SortedMap<java.lang.String,java.lang.Integer> getDomainCounts(java.util.List<Protein> protein_domain_collections)
getNumberOfNodesLackingName
public static int getNumberOfNodesLackingName(Phylogeny p,
java.lang.StringBuilder names)
isEngulfed
public static boolean isEngulfed(Domain domain,
java.util.List<java.lang.Boolean> covered_positions)
- Returns true is Domain domain falls in an uninterrupted stretch of
covered positions.
- Parameters:
domain - covered_positions -
- Returns:
preparePhylogeny
public static void preparePhylogeny(Phylogeny p,
DomainParsimonyCalculator domain_parsimony,
java.lang.String date_time,
java.lang.String method,
java.lang.String name,
java.lang.String parameters_str)
proteinToDomainCombinations
public static java.lang.StringBuffer proteinToDomainCombinations(Protein protein,
java.lang.String protein_id,
java.lang.String separator)
removeOverlappingDomains
public static Protein removeOverlappingDomains(int max_allowed_overlap,
boolean remove_engulfed_domains,
Protein protein)
- 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
- Parameters:
max_allowed_overlap - maximal allowed overlap (inclusive) to be still considered not
overlapping (zero or negative value to allow any overlap)remove_engulfed_domains - to remove domains which are completely engulfed by coverage of
domains with better supportprotein -
- Returns:
sortDomainsWithAscendingConfidenceValues
public static java.util.List<Domain> sortDomainsWithAscendingConfidenceValues(Protein protein)
writeAllDomainsChangedOnAllSubtrees
public static void writeAllDomainsChangedOnAllSubtrees(Phylogeny p,
boolean get_gains,
java.lang.String outdir,
java.lang.String suffix_for_filename)
throws java.io.IOException
- Throws:
java.io.IOException
writeBinaryDomainCombinationsFileForGraphAnalysis
public static void writeBinaryDomainCombinationsFileForGraphAnalysis(java.lang.String[][] input_file_properties,
java.io.File output_dir,
GenomeWideCombinableDomains gwcd,
int i,
GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder dc_sort_order)
writeBinaryStatesMatrixAsListToFile
public static void writeBinaryStatesMatrixAsListToFile(CharacterStateMatrix<CharacterStateMatrix.GainLossStates> matrix,
CharacterStateMatrix.GainLossStates state,
java.lang.String filename,
java.lang.String indentifier_characters_separator,
java.lang.String character_separator,
java.util.Map<java.lang.String,java.lang.String> descriptions)
writeBinaryStatesMatrixAsListToFileForBinaryCombinationsForGraphAnalysis
public static void writeBinaryStatesMatrixAsListToFileForBinaryCombinationsForGraphAnalysis(CharacterStateMatrix<CharacterStateMatrix.GainLossStates> matrix,
CharacterStateMatrix.GainLossStates state,
java.lang.String filename,
java.lang.String indentifier_characters_separator,
java.lang.String character_separator,
BinaryDomainCombination.OutputFormat bc_output_format)
writeBinaryStatesMatrixToList
public static void writeBinaryStatesMatrixToList(java.util.Map<DomainId,java.util.List<GoId>> domain_id_to_go_ids_map,
java.util.Map<GoId,GoTerm> go_id_to_term_map,
GoNameSpace go_namespace_limit,
boolean domain_combinations,
CharacterStateMatrix<CharacterStateMatrix.GainLossStates> matrix,
CharacterStateMatrix.GainLossStates state,
java.lang.String filename,
java.lang.String indentifier_characters_separator,
java.lang.String character_separator,
java.lang.String title_for_html,
java.lang.String prefix_for_html,
java.util.Map<DomainId,java.util.Set<java.lang.String>>[] domain_id_to_secondary_features_maps,
java.util.SortedSet<java.lang.String> all_pfams_encountered,
java.util.SortedSet<java.lang.String> pfams_gained_or_lost,
java.lang.String suffix_for_per_node_events_file)
writeDomainCombinationsCountsFile
public static void writeDomainCombinationsCountsFile(java.lang.String[][] input_file_properties,
java.io.File output_dir,
java.io.Writer per_genome_domain_promiscuity_statistics_writer,
GenomeWideCombinableDomains gwcd,
int i,
GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder dc_sort_order)
writeDomainSimilaritiesToFile
public static DescriptiveStatistics writeDomainSimilaritiesToFile(java.lang.StringBuilder html_desc,
java.lang.StringBuilder html_title,
java.io.Writer single_writer,
java.util.Map<java.lang.Character,java.io.Writer> split_writers,
java.util.SortedSet<DomainSimilarity> similarities,
boolean treat_as_binary,
java.util.List<Species> species_order,
PrintableDomainSimilarity.PRINT_OPTION print_option,
DomainSimilarity.DomainSimilaritySortField sort_field,
DomainSimilarity.DomainSimilarityScoring scoring,
boolean verbose)
throws java.io.IOException
- Throws:
java.io.IOException
writeMatrixToFile
public static void writeMatrixToFile(CharacterStateMatrix<?> matrix,
java.lang.String filename,
CharacterStateMatrix.Format format)
writeMatrixToFile
public static void writeMatrixToFile(java.io.File matrix_outfile,
java.util.List<DistanceMatrix> matrices)
writePhylogenyToFile
public static void writePhylogenyToFile(Phylogeny phylogeny,
java.lang.String filename)
writeTaxonomyLinks
public static void writeTaxonomyLinks(java.io.Writer writer,
java.lang.String species)
throws java.io.IOException
- Throws:
java.io.IOException
domainsPerProteinsStatistics
public static void domainsPerProteinsStatistics(java.lang.String genome,
java.util.List<Protein> protein_list,
DescriptiveStatistics all_genomes_domains_per_potein_stats,
java.util.SortedMap<java.lang.Integer,java.lang.Integer> all_genomes_domains_per_potein_histo,
java.util.SortedSet<java.lang.String> domains_which_are_always_single,
java.util.SortedSet<java.lang.String> domains_which_are_sometimes_single_sometimes_not,
java.util.SortedSet<java.lang.String> domains_which_never_single,
java.io.Writer writer)