import java.util.ArrayList;
import java.util.Date;
import java.util.HashMap;
-import java.util.HashSet;
import java.util.List;
import java.util.Map;
-import java.util.Map.Entry;
import java.util.Set;
import java.util.SortedMap;
import java.util.SortedSet;
import java.util.TreeMap;
import java.util.TreeSet;
-import org.forester.evoinference.matrix.character.CharacterStateMatrix.Format;
import org.forester.go.GoId;
import org.forester.go.GoNameSpace;
import org.forester.go.GoTerm;
import org.forester.go.PfamToGoParser;
import org.forester.io.parsers.HmmscanPerDomainTableParser;
import org.forester.io.parsers.HmmscanPerDomainTableParser.INDIVIDUAL_SCORE_CUTOFF;
-import org.forester.io.parsers.phyloxml.PhyloXmlUtil;
-import org.forester.io.parsers.util.ParserUtils;
import org.forester.phylogeny.Phylogeny;
-import org.forester.phylogeny.PhylogenyMethods;
-import org.forester.phylogeny.PhylogenyNode;
-import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
-import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
import org.forester.protein.BinaryDomainCombination;
import org.forester.protein.Domain;
import org.forester.protein.Protein;
import org.forester.surfacing.BasicGenomeWideCombinableDomains;
import org.forester.surfacing.CombinationsBasedPairwiseDomainSimilarityCalculator;
import org.forester.surfacing.DomainCountsBasedPairwiseSimilarityCalculator;
-import org.forester.surfacing.DomainCountsDifferenceUtil;
import org.forester.surfacing.DomainLengthsTable;
import org.forester.surfacing.DomainParsimonyCalculator;
import org.forester.surfacing.DomainSimilarity;
import org.forester.surfacing.DomainSimilarity.DomainSimilarityScoring;
-import org.forester.surfacing.DomainSimilarity.DomainSimilaritySortField;
+import org.forester.surfacing.DomainSimilarity.PRINT_OPTION;
import org.forester.surfacing.DomainSimilarityCalculator;
import org.forester.surfacing.DomainSimilarityCalculator.Detailedness;
import org.forester.surfacing.GenomeWideCombinableDomains;
import org.forester.surfacing.MappingResults;
import org.forester.surfacing.PairwiseDomainSimilarityCalculator;
import org.forester.surfacing.PairwiseGenomeComparator;
-import org.forester.surfacing.PrintableDomainSimilarity;
-import org.forester.surfacing.PrintableDomainSimilarity.PRINT_OPTION;
import org.forester.surfacing.ProteinCountsBasedPairwiseDomainSimilarityCalculator;
import org.forester.surfacing.SurfacingUtil;
import org.forester.util.BasicDescriptiveStatistics;
public class surfacing {
- private static final int MINIMAL_NUMBER_OF_SIMILARITIES_FOR_SPLITTING = 1000;
- public final static String DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS = "graph_analysis_out";
- public final static String DOMAIN_COMBINITONS_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_dc.dot";
- public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_BC_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_fitch_present_dc.dot";
- public final static String DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX = ".dcc";
+ private static final int MINIMAL_NUMBER_OF_SIMILARITIES_FOR_SPLITTING = 1000;
+ public final static String DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS = "graph_analysis_out";
+ public final static String DOMAIN_COMBINITONS_COUNTS_OUTPUT_OPTION = "dcc";
+ public final static String DOMAIN_COMBINITONS_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_dc.dot";
+ public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_BC_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_fitch_present_dc.dot";
+ public final static String DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX = ".dcc";
// gain/loss:
- public final static String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_DOMAINS = "_dollo_gl_d";
- public final static String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_BINARY_COMBINATIONS = "_dollo_gl_dc";
- public final static String PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_DOMAINS = "_fitch_gl_d";
- public final static String PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_BINARY_COMBINATIONS = "_fitch_gl_dc";
+ public final static String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_DOMAINS = "_dollo_gl_d";
+ public final static String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_BINARY_COMBINATIONS = "_dollo_gl_dc";
+ public final static String PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_DOMAINS = "_fitch_gl_d";
+ public final static String PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_BINARY_COMBINATIONS = "_fitch_gl_dc";
// gain/loss counts:
- public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_DOMAINS = "_dollo_glc_d";
- public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_BINARY_COMBINATIONS = "_dollo_glc_dc";
- public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_DOMAINS = "_fitch_glc_d";
- public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_BINARY_COMBINATIONS = "_fitch_glc_dc";
+ public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_DOMAINS = "_dollo_glc_d";
+ public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_BINARY_COMBINATIONS = "_dollo_glc_dc";
+ public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_DOMAINS = "_fitch_glc_d";
+ public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_BINARY_COMBINATIONS = "_fitch_glc_dc";
// tables:
- public final static String PARSIMONY_OUTPUT_FITCH_GAINS_BC = "_fitch_gains_dc";
- public final static String PARSIMONY_OUTPUT_FITCH_GAINS_HTML_BC = "_fitch_gains_dc.html";
- public final static String PARSIMONY_OUTPUT_FITCH_LOSSES_BC = "_fitch_losses_dc";
- public final static String PARSIMONY_OUTPUT_FITCH_LOSSES_HTML_BC = "_fitch_losses_dc.html";
- public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_BC = "_fitch_present_dc";
- public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_HTML_BC = "_fitch_present_dc.html";
- public final static String PARSIMONY_OUTPUT_DOLLO_GAINS_D = "_dollo_gains_d";
- public final static String PARSIMONY_OUTPUT_DOLLO_GAINS_HTML_D = "_dollo_gains_d.html";
- public final static String PARSIMONY_OUTPUT_DOLLO_LOSSES_D = "_dollo_losses_d";
- public final static String PARSIMONY_OUTPUT_DOLLO_LOSSES_HTML_D = "_dollo_losses_d.html";
- public final static String PARSIMONY_OUTPUT_DOLLO_PRESENT_D = "_dollo_present_d";
- public final static String PARSIMONY_OUTPUT_DOLLO_PRESENT_HTML_D = "_dollo_present_d.html";
- public final static String DOMAINS_PRESENT_NEXUS = "_dom.nex";
- public final static String BDC_PRESENT_NEXUS = "_dc.nex";
+ public final static String PARSIMONY_OUTPUT_FITCH_GAINS_BC = "_fitch_gains_dc";
+ public final static String PARSIMONY_OUTPUT_FITCH_GAINS_HTML_BC = "_fitch_gains_dc.html";
+ public final static String PARSIMONY_OUTPUT_FITCH_LOSSES_BC = "_fitch_losses_dc";
+ public final static String PARSIMONY_OUTPUT_FITCH_LOSSES_HTML_BC = "_fitch_losses_dc.html";
+ public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_BC = "_fitch_present_dc";
+ public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_HTML_BC = "_fitch_present_dc.html";
+ public final static String PARSIMONY_OUTPUT_DOLLO_GAINS_D = "_dollo_gains_d";
+ public final static String PARSIMONY_OUTPUT_DOLLO_GAINS_HTML_D = "_dollo_gains_d.html";
+ public final static String PARSIMONY_OUTPUT_DOLLO_LOSSES_D = "_dollo_losses_d";
+ public final static String PARSIMONY_OUTPUT_DOLLO_LOSSES_HTML_D = "_dollo_losses_d.html";
+ public final static String PARSIMONY_OUTPUT_DOLLO_PRESENT_D = "_dollo_present_d";
+ public final static String PARSIMONY_OUTPUT_DOLLO_PRESENT_HTML_D = "_dollo_present_d.html";
+ public final static String DOMAINS_PRESENT_NEXUS = "_dom.nex";
+ public final static String BDC_PRESENT_NEXUS = "_dc.nex";
// ---
- public final static String PRG_NAME = "surfacing";
- public static final String DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_d_dollo"
- + ForesterConstants.PHYLO_XML_SUFFIX;
- public static final String DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH = "_d_fitch"
- + ForesterConstants.PHYLO_XML_SUFFIX;
- public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_dc_dollo"
- + ForesterConstants.PHYLO_XML_SUFFIX;
- public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH = "_dc_fitch"
- + ForesterConstants.PHYLO_XML_SUFFIX;
- public static final String NEXUS_EXTERNAL_DOMAINS = "_dom.nex";
- public static final String NEXUS_EXTERNAL_DOMAIN_COMBINATIONS = "_dc.nex";
- public static final String NEXUS_SECONDARY_FEATURES = "_secondary_features.nex";
- public static final String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_SECONDARY_FEATURES = "_dollo_gl_secondary_features";
- public static final String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_SECONDARY_FEATURES = "_dollo_glc_secondary_features";
- public static final String PARSIMONY_OUTPUT_DOLLO_GAINS_SECONDARY_FEATURES = "_dollo_gains_secondary_features";
- public static final String PARSIMONY_OUTPUT_DOLLO_LOSSES_SECONDARY_FEATURES = "_dollo_losses_secondary_features";
- public static final String PARSIMONY_OUTPUT_DOLLO_PRESENT_SECONDARY_FEATURES = "_dollo_present_secondary_features";
- public static final String SECONDARY_FEATURES_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_secondary_features_dollo"
- + ForesterConstants.PHYLO_XML_SUFFIX;
- public static final String PARSIMONY_OUTPUT_DOLLO_ALL_GOID_D_ALL_NAMESPACES = "_dollo_goid_d";
- public static final String PARSIMONY_OUTPUT_FITCH_ALL_GOID_BC_ALL_NAMESPACES = "_fitch_goid_dc";
- final static private String HELP_OPTION_1 = "help";
- final static private String HELP_OPTION_2 = "h";
- final static private String OUTPUT_DIR_OPTION = "out_dir";
- final static private String SCORING_OPTION = "scoring";
- private static final DomainSimilarityScoring SCORING_DEFAULT = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
- final static private String SCORING_DOMAIN_COUNT_BASED = "domains";
- final static private String SCORING_PROTEIN_COUNT_BASED = "proteins";
- final static private String SCORING_COMBINATION_BASED = "combinations";
- final static private String DETAILEDNESS_OPTION = "detail";
- private final static Detailedness DETAILEDNESS_DEFAULT = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
- final static private String SPECIES_MATRIX_OPTION = "smatrix";
- final static private String DETAILEDNESS_BASIC = "basic";
- final static private String DETAILEDNESS_LIST_IDS = "list_ids";
- final static private String DETAILEDNESS_PUNCTILIOUS = "punctilious";
- final static private String DOMAIN_SIMILARITY_SORT_OPTION = "sort";
- private static final DomainSimilaritySortField DOMAIN_SORT_FILD_DEFAULT = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
- final static private String DOMAIN_SIMILARITY_SORT_MIN = "min";
- final static private String DOMAIN_SIMILARITY_SORT_MAX = "max";
- final static private String DOMAIN_SIMILARITY_SORT_SD = "sd";
- final static private String DOMAIN_SIMILARITY_SORT_MEAN = "mean";
- final static private String DOMAIN_SIMILARITY_SORT_DIFF = "diff";
- final static private String DOMAIN_SIMILARITY_SORT_COUNTS_DIFF = "count_diff";
- final static private String DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF = "abs_count_diff";
- final static private String DOMAIN_SIMILARITY_SORT_SPECIES_COUNT = "species";
- final static private String DOMAIN_SIMILARITY_SORT_ALPHA = "alpha";
- final static private String DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION = "species_first";
- final static private String DOMAIN_COUNT_SORT_OPTION = "dc_sort";
- private static final GenomeWideCombinableDomainsSortOrder DOMAINS_SORT_ORDER_DEFAULT = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
- final static private String DOMAIN_COUNT_SORT_ALPHA = "alpha";
- final static private String DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT = "dom";
- final static private String DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT = "prot";
- final static private String DOMAIN_COUNT_SORT_COMBINATIONS_COUNT = "comb";
- final static private String CUTOFF_SCORE_FILE_OPTION = "cos";
- final static private String NOT_IGNORE_DUFS_OPTION = "dufs";
- final static private String MAX_E_VALUE_OPTION = "e";
- final static private String MAX_ALLOWED_OVERLAP_OPTION = "mo";
- final static private String NO_ENGULFING_OVERLAP_OPTION = "no_eo";
- final static private String IGNORE_COMBINATION_WITH_SAME_OPTION = "ignore_self_comb";
- final static private String PERFORM_DC_REGAIN_PROTEINS_STATS_OPTION = "dc_regain_stats";
- final static private String DA_ANALYSIS_OPTION = "DA_analyis";
- final static private String USE_LAST_IN_FITCH_OPTION = "last";
- final static private String PAIRWISE_DOMAIN_COMPARISONS_PREFIX = "pwc_";
- final static private String PAIRWISE_DOMAIN_COMPARISONS_OPTION = "pwc";
- final static private String OUTPUT_FILE_OPTION = "o";
- final static private String PFAM_TO_GO_FILE_USE_OPTION = "p2g";
- final static private String GO_OBO_FILE_USE_OPTION = "obo";
- final static private String GO_NAMESPACE_LIMIT_OPTION = "go_namespace";
- final static private String GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION = "molecular_function";
- final static private String GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS = "biological_process";
- final static private String GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT = "cellular_component";
- final static private String SECONDARY_FEATURES_PARSIMONY_MAP_FILE = "secondary";
- final static private String DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED = "simple_tab";
- final static private String DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML = "simple_html";
- final static private String DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML = "detailed_html";
- final static private String DOMAIN_SIMILARITY_PRINT_OPTION = "ds_output";
- private static final PRINT_OPTION DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT = PrintableDomainSimilarity.PRINT_OPTION.HTML;
- final static private String IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION = "ignore_singlet_domains";
- final static private String IGNORE_VIRAL_IDS = "ignore_viral_ids";
- final static private boolean IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_DEFAULT = false;
- final static private String IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION = "ignore_species_specific_domains";
- final static private boolean IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION_DEFAULT = false;
- final static private String MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX = "_mean_score.pwd";
- final static private String MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX = "_domains.pwd";
- final static private String MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX = "_bin_combinations.pwd";
- final static private String NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX = "_mean_score_NJ"
- + ForesterConstants.PHYLO_XML_SUFFIX;
- final static private String NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX = "_domains_NJ"
- + ForesterConstants.PHYLO_XML_SUFFIX;
- final static private String NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX = "_bin_combinations_NJ"
- + ForesterConstants.PHYLO_XML_SUFFIX;
- final static private String FILTER_POSITIVE_OPTION = "pos_filter";
- final static private String FILTER_NEGATIVE_OPTION = "neg_filter";
- final static private String FILTER_NEGATIVE_DOMAINS_OPTION = "neg_dom_filter";
- final static private String INPUT_GENOMES_FILE_OPTION = "genomes";
- final static private String INPUT_SPECIES_TREE_OPTION = "species_tree";
- final static private String SEQ_EXTRACT_OPTION = "prot_extract";
- final static private String PRG_VERSION = "2.290";
- final static private String PRG_DATE = "130709";
- final static private String E_MAIL = "czmasek@burnham.org";
- final static private String WWW = "https://sites.google.com/site/cmzmasek/home/software/forester/surfacing";
- final static private boolean IGNORE_DUFS_DEFAULT = true;
- final static private boolean IGNORE_COMBINATION_WITH_SAME_DEFAULLT = false;
- final static private double MAX_E_VALUE_DEFAULT = -1;
- final static private int MAX_ALLOWED_OVERLAP_DEFAULT = -1;
- private static final String RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION = "random_seed";
- private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS = "consider_bdc_direction";
- private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY = "consider_bdc_adj";
- private static final String SEQ_EXTRACT_SUFFIX = ".prot";
- private static final String PLUS_MINUS_ANALYSIS_OPTION = "plus_minus";
- private static final String PLUS_MINUS_DOM_SUFFIX = "_plus_minus_dom.txt";
- private static final String PLUS_MINUS_DOM_SUFFIX_HTML = "_plus_minus_dom.html";
- private static final String PLUS_MINUS_DC_SUFFIX_HTML = "_plus_minus_dc.html";
- private static final int PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT = 0;
- private static final double PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT = 1.0;
- private static final String PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_all.txt";
- private static final String PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_passing.txt";
- private static final String OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS = "all_prot";
- final static private String OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION = "all_prot_e";
- private static final boolean VERBOSE = false;
- private static final String OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_gains_counts";
- private static final String OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_losses_counts";
- private static final String DOMAIN_LENGTHS_ANALYSIS_SUFFIX = "_domain_lengths_analysis";
- private static final boolean PERFORM_DOMAIN_LENGTH_ANALYSIS = true;
- public static final String ALL_PFAMS_ENCOUNTERED_SUFFIX = "_all_encountered_pfams";
- public static final String ALL_PFAMS_ENCOUNTERED_WITH_GO_ANNOTATION_SUFFIX = "_all_encountered_pfams_with_go_annotation";
- public static final String ENCOUNTERED_PFAMS_SUMMARY_SUFFIX = "_encountered_pfams_summary";
- public static final String ALL_PFAMS_GAINED_AS_DOMAINS_SUFFIX = "_all_pfams_gained_as_domains";
- public static final String ALL_PFAMS_LOST_AS_DOMAINS_SUFFIX = "_all_pfams_lost_as_domains";
- public static final String ALL_PFAMS_GAINED_AS_DC_SUFFIX = "_all_pfams_gained_as_dc";
- public static final String ALL_PFAMS_LOST_AS_DC_SUFFIX = "_all_pfams_lost_as_dc";
- public static final String BASE_DIRECTORY_PER_NODE_DOMAIN_GAIN_LOSS_FILES = "PER_NODE_EVENTS";
- public static final String BASE_DIRECTORY_PER_SUBTREE_DOMAIN_GAIN_LOSS_FILES = "PER_SUBTREE_EVENTS";
- public static final String D_PROMISCUITY_FILE_SUFFIX = "_domain_promiscuities";
- private static final String LOG_FILE_SUFFIX = "_log.txt";
- private static final String DATA_FILE_SUFFIX = "_domain_combination_data.txt";
- private static final String DATA_FILE_DESC = "#SPECIES\tPRTEIN_ID\tN_TERM_DOMAIN\tC_TERM_DOMAIN\tN_TERM_DOMAIN_PER_DOMAIN_E_VALUE\tC_TERM_DOMAIN_PER_DOMAIN_E_VALUE\tN_TERM_DOMAIN_COUNTS_PER_PROTEIN\tC_TERM_DOMAIN_COUNTS_PER_PROTEIN";
- private static final String WRITE_TO_NEXUS_OPTION = "nexus";
- private static final INDIVIDUAL_SCORE_CUTOFF INDIVIDUAL_SCORE_CUTOFF_DEFAULT = INDIVIDUAL_SCORE_CUTOFF.FULL_SEQUENCE; //TODO look at me! change?
- public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts.txt";
- public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists.txt";
- public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping.txt";
- public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_UNIQUE_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping_unique.txt";
- public static final String LIMIT_SPEC_FOR_PROT_EX = null; // e.g. "HUMAN"; set to null for not using this feature (default).
- public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH_MAPPED = "_dc_MAPPED_secondary_features_fitch"
- + ForesterConstants.PHYLO_XML_SUFFIX;
- public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts_MAPPED.txt";
- public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_MAPPED.txt";
- public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping_MAPPED.txt";
- public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_MAPPED_OUTPUT_UNIQUE_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping_unique_MAPPED.txt";
-
- private 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 = 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 );
- }
- }
- }
- }
-
- private 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;
- }
-
- /**
- * 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
- */
- private 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 {
- SurfacingUtil.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( 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
- + "\"" );
- }
-
- private 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 + PLUS_MINUS_DOM_SUFFIX_HTML );
- final File plain_out_dom = new File( output_file + PLUS_MINUS_DOM_SUFFIX );
- final File html_out_dc = new File( output_file + PLUS_MINUS_DC_SUFFIX_HTML );
- final File all_domains_go_ids_out_dom = new File( output_file + PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX );
- final File passing_domains_go_ids_out_dom = new File( output_file + 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 + "\"" );
- }
-
- private static Phylogeny[] getIntrees( 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 = SurfacingUtil.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 intrees;
- }
-
- private 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 final static String PRG_NAME = "surfacing";
+ public static final String DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_d_dollo"
+ + ForesterConstants.PHYLO_XML_SUFFIX;
+ public static final String DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH = "_d_fitch"
+ + ForesterConstants.PHYLO_XML_SUFFIX;
+ public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_dc_dollo"
+ + ForesterConstants.PHYLO_XML_SUFFIX;
+ public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH = "_dc_fitch"
+ + ForesterConstants.PHYLO_XML_SUFFIX;
+ public static final String NEXUS_EXTERNAL_DOMAINS = "_dom.nex";
+ public static final String NEXUS_EXTERNAL_DOMAIN_COMBINATIONS = "_dc.nex";
+ public static final String NEXUS_SECONDARY_FEATURES = "_secondary_features.nex";
+ public static final String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_SECONDARY_FEATURES = "_dollo_gl_secondary_features";
+ public static final String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_SECONDARY_FEATURES = "_dollo_glc_secondary_features";
+ public static final String PARSIMONY_OUTPUT_DOLLO_GAINS_SECONDARY_FEATURES = "_dollo_gains_secondary_features";
+ public static final String PARSIMONY_OUTPUT_DOLLO_LOSSES_SECONDARY_FEATURES = "_dollo_losses_secondary_features";
+ public static final String PARSIMONY_OUTPUT_DOLLO_PRESENT_SECONDARY_FEATURES = "_dollo_present_secondary_features";
+ public static final String SECONDARY_FEATURES_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_secondary_features_dollo"
+ + ForesterConstants.PHYLO_XML_SUFFIX;
+ public static final String PARSIMONY_OUTPUT_DOLLO_ALL_GOID_D_ALL_NAMESPACES = "_dollo_goid_d";
+ public static final String PARSIMONY_OUTPUT_FITCH_ALL_GOID_BC_ALL_NAMESPACES = "_fitch_goid_dc";
+ final static private String HELP_OPTION_1 = "help";
+ final static private String HELP_OPTION_2 = "h";
+ final static private String OUTPUT_DIR_OPTION = "out_dir";
+ final static private String SCORING_OPTION = "scoring";
+ private static final DomainSimilarityScoring SCORING_DEFAULT = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
+ final static private String SCORING_DOMAIN_COUNT_BASED = "domains";
+ final static private String SCORING_PROTEIN_COUNT_BASED = "proteins";
+ final static private String SCORING_COMBINATION_BASED = "combinations";
+ final static private String DETAILEDNESS_OPTION = "detail";
+ private final static Detailedness DETAILEDNESS_DEFAULT = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
+ final static private String SPECIES_MATRIX_OPTION = "smatrix";
+ final static private String DETAILEDNESS_BASIC = "basic";
+ final static private String DETAILEDNESS_LIST_IDS = "list_ids";
+ final static private String DETAILEDNESS_PUNCTILIOUS = "punctilious";
+ final static private String DOMAIN_SIMILARITY_SORT_OPTION = "sort";
+ private static final DomainSimilarity.DomainSimilaritySortField DOMAIN_SORT_FILD_DEFAULT = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
+ final static private String DOMAIN_SIMILARITY_SORT_MIN = "min";
+ final static private String DOMAIN_SIMILARITY_SORT_MAX = "max";
+ final static private String DOMAIN_SIMILARITY_SORT_SD = "sd";
+ final static private String DOMAIN_SIMILARITY_SORT_MEAN = "mean";
+ final static private String DOMAIN_SIMILARITY_SORT_DIFF = "diff";
+ final static private String DOMAIN_SIMILARITY_SORT_COUNTS_DIFF = "count_diff";
+ final static private String DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF = "abs_count_diff";
+ final static private String DOMAIN_SIMILARITY_SORT_SPECIES_COUNT = "species";
+ final static private String DOMAIN_SIMILARITY_SORT_ALPHA = "alpha";
+ final static private String DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION = "species_first";
+ final static private String DOMAIN_COUNT_SORT_OPTION = "dc_sort";
+ private static final GenomeWideCombinableDomainsSortOrder DOMAINS_SORT_ORDER_DEFAULT = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
+ final static private String DOMAIN_COUNT_SORT_ALPHA = "alpha";
+ final static private String DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT = "dom";
+ final static private String DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT = "prot";
+ final static private String DOMAIN_COUNT_SORT_COMBINATIONS_COUNT = "comb";
+ final static private String CUTOFF_SCORE_FILE_OPTION = "cos";
+ final static private String NOT_IGNORE_DUFS_OPTION = "dufs";
+ final static private String MAX_FS_E_VALUE_OPTION = "fs_e";
+ final static private String MAX_I_E_VALUE_OPTION = "ie";
+ final static private String MAX_ALLOWED_OVERLAP_OPTION = "mo";
+ final static private String NO_ENGULFING_OVERLAP_OPTION = "no_eo";
+ final static private String IGNORE_COMBINATION_WITH_SAME_OPTION = "ignore_self_comb";
+ final static private String PERFORM_DC_REGAIN_PROTEINS_STATS_OPTION = "dc_regain_stats";
+ final static private String DA_ANALYSIS_OPTION = "da_analyis";
+ final static private String USE_LAST_IN_FITCH_OPTION = "last";
+ public final static String PAIRWISE_DOMAIN_COMPARISONS_PREFIX = "pwc_";
+ final static private String PAIRWISE_DOMAIN_COMPARISONS_OPTION = "pwc";
+ final static private String OUTPUT_FILE_OPTION = "o";
+ final static private String PFAM_TO_GO_FILE_USE_OPTION = "p2g";
+ final static private String GO_OBO_FILE_USE_OPTION = "obo";
+ final static private String GO_NAMESPACE_LIMIT_OPTION = "go_namespace";
+ final static private String GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION = "molecular_function";
+ final static private String GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS = "biological_process";
+ final static private String GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT = "cellular_component";
+ final static private String SECONDARY_FEATURES_PARSIMONY_MAP_FILE = "secondary";
+ final static private String DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED = "simple_tab";
+ final static private String DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML = "simple_html";
+ final static private String DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML = "detailed_html";
+ final static private String DOMAIN_SIMILARITY_PRINT_OPTION = "ds_output";
+ private static final PRINT_OPTION DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT = DomainSimilarity.PRINT_OPTION.HTML;
+ final static private String IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION = "ignore_singlet_domains";
+ final static private String IGNORE_VIRAL_IDS = "ignore_viral_ids";
+ final static private boolean IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_DEFAULT = false;
+ final static private String IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION = "ignore_species_specific_domains";
+ final static private boolean IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION_DEFAULT = false;
+ final static private String MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX = "_mean_score.pwd";
+ final static private String MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX = "_domains.pwd";
+ final static private String MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX = "_bin_combinations.pwd";
+ final static private String NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX = "_mean_score_NJ"
+ + ForesterConstants.PHYLO_XML_SUFFIX;
+ final static private String NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX = "_domains_NJ"
+ + ForesterConstants.PHYLO_XML_SUFFIX;
+ final static private String NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX = "_bin_combinations_NJ"
+ + ForesterConstants.PHYLO_XML_SUFFIX;
+ final static private String FILTER_POSITIVE_OPTION = "pos_filter";
+ final static private String FILTER_NEGATIVE_OPTION = "neg_filter";
+ final static private String FILTER_NEGATIVE_DOMAINS_OPTION = "neg_dom_filter";
+ final static private String INPUT_GENOMES_FILE_OPTION = "genomes";
+ final static private String INPUT_SPECIES_TREE_OPTION = "species_tree";
+ final static private String SEQ_EXTRACT_OPTION = "prot_extract";
+ final static private String PRG_VERSION = "2.404";
+ final static private String PRG_DATE = "140709";
+ final static private String E_MAIL = "czmasek@burnham.org";
+ final static private String WWW = "https://sites.google.com/site/cmzmasek/home/software/forester/surfacing";
+ final static private boolean IGNORE_DUFS_DEFAULT = true;
+ final static private boolean IGNORE_COMBINATION_WITH_SAME_DEFAULLT = false;
+ final static private double MAX_E_VALUE_DEFAULT = -1;
+ public final static int MAX_ALLOWED_OVERLAP_DEFAULT = -1;
+ private static final String RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION = "random_seed";
+ private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS = "consider_bdc_direction";
+ private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY = "consider_bdc_adj";
+ public static final String SEQ_EXTRACT_SUFFIX = ".prot";
+ public static final String PLUS_MINUS_ANALYSIS_OPTION = "plus_minus";
+ public static final String PLUS_MINUS_DOM_SUFFIX = "_plus_minus_dom.txt";
+ public static final String PLUS_MINUS_DOM_SUFFIX_HTML = "_plus_minus_dom.html";
+ public static final String PLUS_MINUS_DC_SUFFIX_HTML = "_plus_minus_dc.html";
+ public static final int PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT = 0;
+ public static final double PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT = 1.0;
+ public static final String PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_all.txt";
+ public static final String PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_passing.txt";
+ private static final String OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS = "all_prot";
+ final static private String OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION = "all_prot_e";
+ public static final boolean VERBOSE = false;
+ private static final String OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_gains_counts";
+ private static final String OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_losses_counts";
+ private static final String DOMAIN_LENGTHS_ANALYSIS_SUFFIX = "_domain_lengths_analysis";
+ private static final String PERFORM_DOMAIN_LENGTH_ANALYSIS_OPTION = "dla";
+ public static final String ALL_PFAMS_ENCOUNTERED_SUFFIX = "_all_encountered_pfams";
+ public static final String ALL_PFAMS_ENCOUNTERED_WITH_GO_ANNOTATION_SUFFIX = "_all_encountered_pfams_with_go_annotation";
+ public static final String ENCOUNTERED_PFAMS_SUMMARY_SUFFIX = "_encountered_pfams_summary";
+ public static final String ALL_PFAMS_GAINED_AS_DOMAINS_SUFFIX = "_all_pfams_gained_as_domains";
+ public static final String ALL_PFAMS_LOST_AS_DOMAINS_SUFFIX = "_all_pfams_lost_as_domains";
+ public static final String ALL_PFAMS_GAINED_AS_DC_SUFFIX = "_all_pfams_gained_as_dc";
+ public static final String ALL_PFAMS_LOST_AS_DC_SUFFIX = "_all_pfams_lost_as_dc";
+ public static final String BASE_DIRECTORY_PER_NODE_DOMAIN_GAIN_LOSS_FILES = "PER_NODE_EVENTS";
+ public static final String BASE_DIRECTORY_PER_SUBTREE_DOMAIN_GAIN_LOSS_FILES = "PER_SUBTREE_EVENTS";
+ public static final String D_PROMISCUITY_FILE_SUFFIX = "_domain_promiscuities";
+ private static final String LOG_FILE_SUFFIX = "_log.txt";
+ private static final String DATA_FILE_SUFFIX = "_domain_combination_data.txt";
+ private static final String DATA_FILE_DESC = "#SPECIES\tPRTEIN_ID\tN_TERM_DOMAIN\tC_TERM_DOMAIN\tN_TERM_DOMAIN_PER_DOMAIN_E_VALUE\tC_TERM_DOMAIN_PER_DOMAIN_E_VALUE\tN_TERM_DOMAIN_COUNTS_PER_PROTEIN\tC_TERM_DOMAIN_COUNTS_PER_PROTEIN";
+ private static final String WRITE_TO_NEXUS_OPTION = "nexus";
+ private static final String PERFORM_DC_FITCH = "dc_pars";
+ private static final INDIVIDUAL_SCORE_CUTOFF INDIVIDUAL_SCORE_CUTOFF_DEFAULT = INDIVIDUAL_SCORE_CUTOFF.FULL_SEQUENCE; //TODO look at me! change?
+ public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts.txt";
+ public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists.txt";
+ public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping.txt";
+ public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_UNIQUE_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping_unique.txt";
+ public static final String LIMIT_SPEC_FOR_PROT_EX = null; // e.g. "HUMAN"; set to null for not using this feature (default).
+ public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH_MAPPED = "_dc_MAPPED_secondary_features_fitch"
+ + ForesterConstants.PHYLO_XML_SUFFIX;
+ public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts_MAPPED.txt";
+ public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_MAPPED.txt";
+ public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping_MAPPED.txt";
+ public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_MAPPED_OUTPUT_UNIQUE_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping_unique_MAPPED.txt";
+ private static final boolean CALC_SIMILARITY_SCORES = false;
public static void main( final String args[] ) {
final long start_time = new Date().getTime();
}
final List<String> allowed_options = new ArrayList<String>();
allowed_options.add( surfacing.NOT_IGNORE_DUFS_OPTION );
- allowed_options.add( surfacing.MAX_E_VALUE_OPTION );
+ allowed_options.add( surfacing.MAX_FS_E_VALUE_OPTION );
+ allowed_options.add( surfacing.MAX_I_E_VALUE_OPTION );
allowed_options.add( surfacing.DETAILEDNESS_OPTION );
allowed_options.add( surfacing.OUTPUT_FILE_OPTION );
allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_OPTION );
allowed_options.add( SECONDARY_FEATURES_PARSIMONY_MAP_FILE );
allowed_options.add( PLUS_MINUS_ANALYSIS_OPTION );
allowed_options.add( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS );
+ allowed_options.add( DOMAIN_COMBINITONS_COUNTS_OUTPUT_OPTION );
allowed_options.add( OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS );
allowed_options.add( CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY );
allowed_options.add( WRITE_TO_NEXUS_OPTION );
allowed_options.add( PERFORM_DC_REGAIN_PROTEINS_STATS_OPTION );
allowed_options.add( DA_ANALYSIS_OPTION );
allowed_options.add( USE_LAST_IN_FITCH_OPTION );
+ allowed_options.add( PERFORM_DC_FITCH );
+ allowed_options.add( PERFORM_DOMAIN_LENGTH_ANALYSIS_OPTION );
boolean ignore_dufs = surfacing.IGNORE_DUFS_DEFAULT;
boolean ignore_combination_with_same = surfacing.IGNORE_COMBINATION_WITH_SAME_DEFAULLT;
- double e_value_max = surfacing.MAX_E_VALUE_DEFAULT;
+ double fs_e_value_max = surfacing.MAX_E_VALUE_DEFAULT;
+ double ie_value_max = surfacing.MAX_E_VALUE_DEFAULT;
int max_allowed_overlap = surfacing.MAX_ALLOWED_OVERLAP_DEFAULT;
final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
if ( dissallowed_options.length() > 0 ) {
if ( cla.isOptionSet( WRITE_TO_NEXUS_OPTION ) ) {
write_to_nexus = true;
}
+ boolean perform_dc_fich = false;
+ if ( cla.isOptionSet( PERFORM_DC_FITCH ) ) {
+ perform_dc_fich = true;
+ }
boolean perform_dc_regain_proteins_stats = false;
if ( cla.isOptionSet( PERFORM_DC_REGAIN_PROTEINS_STATS_OPTION ) ) {
perform_dc_regain_proteins_stats = true;
if ( cla.isOptionSet( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS ) ) {
output_binary_domain_combinationsfor_graph_analysis = true;
}
- if ( cla.isOptionSet( surfacing.MAX_E_VALUE_OPTION ) ) {
+ boolean output_binary_domain_combinationsfor_counts = false;
+ if ( cla.isOptionSet( DOMAIN_COMBINITONS_COUNTS_OUTPUT_OPTION ) ) {
+ output_binary_domain_combinationsfor_counts = true;
+ }
+ if ( cla.isOptionSet( surfacing.MAX_FS_E_VALUE_OPTION ) ) {
+ try {
+ fs_e_value_max = cla.getOptionValueAsDouble( surfacing.MAX_FS_E_VALUE_OPTION );
+ }
+ catch ( final Exception e ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for E-value maximum" );
+ }
+ }
+ if ( cla.isOptionSet( surfacing.MAX_I_E_VALUE_OPTION ) ) {
try {
- e_value_max = cla.getOptionValueAsDouble( surfacing.MAX_E_VALUE_OPTION );
+ ie_value_max = cla.getOptionValueAsDouble( surfacing.MAX_I_E_VALUE_OPTION );
}
catch ( final Exception e ) {
ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for E-value maximum" );
if ( cla.isOptionSet( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION ) ) {
ignore_combination_with_same = true;
}
+ boolean domain_length_analysis = false;
+ if ( cla.isOptionSet( surfacing.PERFORM_DOMAIN_LENGTH_ANALYSIS_OPTION ) ) {
+ domain_length_analysis = true;
+ }
boolean ignore_domains_without_combs_in_all_spec = IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_DEFAULT;
if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION ) ) {
ignore_domains_without_combs_in_all_spec = true;
if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION ) ) {
ignore_species_specific_domains = true;
}
+ if ( !cla.isOptionValueSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "no input species tree file given: "
+ + surfacing.INPUT_SPECIES_TREE_OPTION + "=<file>" );
+ }
File output_file = null;
if ( cla.isOptionSet( surfacing.OUTPUT_FILE_OPTION ) ) {
if ( !cla.isOptionValueSet( surfacing.OUTPUT_FILE_OPTION ) ) {
&& ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) || cla
.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) ) {
ForesterUtil
- .fatalError( surfacing.PRG_NAME,
- "attempt to use both negative or positive protein filter together wirh a negative domains filter" );
+ .fatalError( surfacing.PRG_NAME,
+ "attempt to use both negative or positive protein filter together wirh a negative domains filter" );
}
if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
final String msg = ForesterUtil.isReadableFile( negative_domains_filter_file );
if ( !ForesterUtil.isEmpty( msg ) ) {
ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_domains_filter_file
- + "\": " + msg );
+ + "\": " + msg );
}
}
final List<String> plus_minus_analysis_high_copy_base_species = new ArrayList<String>();
final List<String> plus_minus_analysis_high_copy_target_species = new ArrayList<String>();
final List<String> plus_minus_analysis_high_low_copy_species = new ArrayList<String>();
final List<Object> plus_minus_analysis_numbers = new ArrayList<Object>();
- processPlusMinusAnalysisOption( cla,
- plus_minus_analysis_high_copy_base_species,
- plus_minus_analysis_high_copy_target_species,
- plus_minus_analysis_high_low_copy_species,
- plus_minus_analysis_numbers );
+ SurfacingUtil.processPlusMinusAnalysisOption( cla,
+ plus_minus_analysis_high_copy_base_species,
+ plus_minus_analysis_high_copy_target_species,
+ plus_minus_analysis_high_low_copy_species,
+ plus_minus_analysis_numbers );
File input_genomes_file = null;
if ( cla.isOptionSet( surfacing.INPUT_GENOMES_FILE_OPTION ) ) {
if ( !cla.isOptionValueSet( surfacing.INPUT_GENOMES_FILE_OPTION ) ) {
final String msg = ForesterUtil.isReadableFile( input_genomes_file );
if ( !ForesterUtil.isEmpty( msg ) ) {
ForesterUtil
- .fatalError( surfacing.PRG_NAME, "can not read from \"" + input_genomes_file + "\": " + msg );
+ .fatalError( surfacing.PRG_NAME, "can not read from \"" + input_genomes_file + "\": " + msg );
}
}
else {
}
else {
ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + scoring_str
- + "\" for scoring method for domain combinations similarity calculation: \"-"
- + surfacing.SCORING_OPTION + "=<" + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
- + surfacing.SCORING_PROTEIN_COUNT_BASED + "|" + surfacing.SCORING_COMBINATION_BASED + ">\"" );
+ + "\" for scoring method for domain combinations similarity calculation: \"-"
+ + surfacing.SCORING_OPTION + "=<" + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
+ + surfacing.SCORING_PROTEIN_COUNT_BASED + "|" + surfacing.SCORING_COMBINATION_BASED + ">\"" );
}
}
boolean sort_by_species_count_first = false;
if ( cla.isOptionSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
if ( !cla.isOptionValueSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
ForesterUtil
- .fatalError( surfacing.PRG_NAME,
- "no domain ids given for sequences with given domains to be extracted : -"
- + surfacing.SEQ_EXTRACT_OPTION
- + "=<ordered domain sequences, domain ids separated by '~', sequences separated by '#'>" );
+ .fatalError( surfacing.PRG_NAME,
+ "no domain ids given for sequences with given domains to be extracted : -"
+ + surfacing.SEQ_EXTRACT_OPTION
+ + "=<ordered domain sequences, domain ids separated by '~', sequences separated by '#'>" );
}
query_domain_ids = cla.getOptionValue( surfacing.SEQ_EXTRACT_OPTION );
}
}
else {
ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort_str
- + "\" for domain combinations similarities sorting: \"-"
- + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
- + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
- + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
- + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
- + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|" + "|"
- + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
- + ">\"" );
+ + "\" for domain combinations similarities sorting: \"-"
+ + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
+ + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
+ + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
+ + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
+ + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|" + "|"
+ + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
+ + ">\"" );
}
}
- PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option = DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT;
+ DomainSimilarity.PRINT_OPTION domain_similarity_print_option = DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT;
if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for print option: -"
}
final String sort = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ).toLowerCase();
if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML ) ) {
- domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.HTML;
+ domain_similarity_print_option = DomainSimilarity.PRINT_OPTION.HTML;
}
else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML ) ) {
ForesterUtil.fatalError( surfacing.PRG_NAME, "simple HTML output not implemented yet :(" );
}
else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED ) ) {
- domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.SIMPLE_TAB_DELIMITED;
+ domain_similarity_print_option = DomainSimilarity.PRINT_OPTION.SIMPLE_TAB_DELIMITED;
}
else {
ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort + "\" for print option: -"
}
else {
ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort
- + "\" for sorting of domain counts: \"-" + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<"
- + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|" + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
- + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
- + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
+ + "\" for sorting of domain counts: \"-" + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<"
+ + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|" + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
+ + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
+ + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
}
}
- final String[][] input_file_properties = processInputGenomesFile( input_genomes_file );
+ final String[][] input_file_properties = SurfacingUtil.processInputGenomesFile( input_genomes_file );
final int number_of_genomes = input_file_properties.length;
if ( number_of_genomes < 2 ) {
ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot analyze less than two files" );
+ surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
+ "=<suffix> to turn on pairwise analyses with less than three input files" );
}
- checkWriteabilityForPairwiseComparisons( domain_similarity_print_option,
- input_file_properties,
- automated_pairwise_comparison_suffix,
- out_dir );
+ SurfacingUtil.checkWriteabilityForPairwiseComparisons( domain_similarity_print_option,
+ input_file_properties,
+ automated_pairwise_comparison_suffix,
+ out_dir );
for( int i = 0; i < number_of_genomes; i++ ) {
File dcc_outfile = new File( input_file_properties[ i ][ 1 ]
+ surfacing.DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX );
}
SurfacingUtil.checkForOutputFileWriteability( dcc_outfile );
}
- File pfam_to_go_file = null;
- Map<String, List<GoId>> domain_id_to_go_ids_map = null;
- int domain_id_to_go_ids_count = 0;
+ File pfam_to_go_file = new File( "pfam2go.txt" );
if ( cla.isOptionSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
if ( !cla.isOptionValueSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for Pfam to GO mapping file: -"
+ surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>" );
}
pfam_to_go_file = new File( cla.getOptionValue( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) );
- final String error = ForesterUtil.isReadableFile( pfam_to_go_file );
- if ( !ForesterUtil.isEmpty( error ) ) {
- ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read Pfam to GO mapping file: " + error );
- }
- try {
- final PfamToGoParser parser = new PfamToGoParser( pfam_to_go_file );
- final List<PfamToGoMapping> pfam_to_go_mappings = parser.parse();
- domain_id_to_go_ids_map = SurfacingUtil.createDomainIdToGoIdMap( pfam_to_go_mappings );
- if ( parser.getMappingCount() < domain_id_to_go_ids_map.size() ) {
- ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME,
- "parser.getMappingCount() < domain_id_to_go_ids_map.size()" );
- }
- domain_id_to_go_ids_count = parser.getMappingCount();
- }
- catch ( final IOException e ) {
- ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from Pfam to GO mapping file: " + e );
+ }
+ final String error1 = ForesterUtil.isReadableFile( pfam_to_go_file );
+ if ( !ForesterUtil.isEmpty( error1 ) ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read Pfam to GO mapping file: " + error1 );
+ }
+ Map<String, List<GoId>> domain_id_to_go_ids_map = null;
+ int domain_id_to_go_ids_count = 0;
+ try {
+ final PfamToGoParser parser = new PfamToGoParser( pfam_to_go_file );
+ final List<PfamToGoMapping> pfam_to_go_mappings = parser.parse();
+ domain_id_to_go_ids_map = SurfacingUtil.createDomainIdToGoIdMap( pfam_to_go_mappings );
+ if ( parser.getMappingCount() < domain_id_to_go_ids_map.size() ) {
+ ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME,
+ "parser.getMappingCount() < domain_id_to_go_ids_map.size()" );
}
+ domain_id_to_go_ids_count = parser.getMappingCount();
}
- File go_obo_file = null;
- List<GoTerm> go_terms = null;
+ catch ( final IOException e ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from Pfam to GO mapping file: " + e );
+ }
+ File go_obo_file = new File( "go.obo" );
if ( cla.isOptionSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
if ( !cla.isOptionValueSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO OBO file: -"
+ surfacing.GO_OBO_FILE_USE_OPTION + "=<file>" );
}
- if ( ( domain_id_to_go_ids_map == null ) || ( domain_id_to_go_ids_map.size() < 1 ) ) {
- ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO OBO file (-"
- + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>) without Pfam to GO mapping file ("
- + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
- }
go_obo_file = new File( cla.getOptionValue( surfacing.GO_OBO_FILE_USE_OPTION ) );
- final String error = ForesterUtil.isReadableFile( go_obo_file );
- if ( !ForesterUtil.isEmpty( error ) ) {
- ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read GO OBO file: " + error );
- }
- try {
- final OBOparser parser = new OBOparser( go_obo_file, OBOparser.ReturnType.BASIC_GO_TERM );
- go_terms = parser.parse();
- if ( parser.getGoTermCount() != go_terms.size() ) {
- ForesterUtil
- .unexpectedFatalError( surfacing.PRG_NAME, "parser.getGoTermCount() != go_terms.size()" );
- }
- }
- catch ( final IOException e ) {
- ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from GO OBO file: " + e );
+ }
+ final String error2 = ForesterUtil.isReadableFile( go_obo_file );
+ if ( !ForesterUtil.isEmpty( error2 ) ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read GO OBO file: " + error2 );
+ }
+ List<GoTerm> go_terms = null;
+ try {
+ final OBOparser parser = new OBOparser( go_obo_file, OBOparser.ReturnType.BASIC_GO_TERM );
+ go_terms = parser.parse();
+ if ( parser.getGoTermCount() != go_terms.size() ) {
+ ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "parser.getGoTermCount() != go_terms.size()" );
}
}
+ catch ( final IOException e ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from GO OBO file: " + e );
+ }
Map<GoId, GoTerm> go_id_to_term_map = null;
if ( ( ( domain_id_to_go_ids_map != null ) && ( domain_id_to_go_ids_map.size() > 0 ) )
&& ( ( go_terms != null ) && ( go_terms.size() > 0 ) ) ) {
}
else {
ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + go_namespace_limit_str
- + "\" for GO namespace limit: \"-" + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
- + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
- + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
- + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
+ + "\" for GO namespace limit: \"-" + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
+ + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
+ + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
+ + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
}
}
if ( ( domain_similarity_sort_field == DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE )
intree_files = new File[ 1 ];
intree_files[ 0 ] = new File( intrees_str );
}
- intrees = getIntrees( intree_files, number_of_genomes, input_file_properties );
+ intrees = SurfacingUtil.obtainAndPreProcessIntrees( intree_files, number_of_genomes, input_file_properties );
}
+ final Phylogeny intree_0_orig = SurfacingUtil.obtainFirstIntree( intree_files[ 0 ] );
long random_number_seed_for_fitch_parsimony = 0l;
boolean radomize_fitch_parsimony = false;
if ( cla.isOptionSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
|| ( negative_domains_filter_file != null ) ) {
filter = new TreeSet<String>();
if ( positive_filter_file != null ) {
- processFilter( positive_filter_file, filter );
+ SurfacingUtil.processFilter( positive_filter_file, filter );
}
else if ( negative_filter_file != null ) {
- processFilter( negative_filter_file, filter );
+ SurfacingUtil.processFilter( negative_filter_file, filter );
}
else if ( negative_domains_filter_file != null ) {
- processFilter( negative_domains_filter_file, filter );
+ SurfacingUtil.processFilter( negative_domains_filter_file, filter );
}
}
Map<String, Set<String>>[] domain_id_to_secondary_features_maps = null;
File[] secondary_features_map_files = null;
final File domain_lengths_analysis_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
- + DOMAIN_LENGTHS_ANALYSIS_SUFFIX );
- if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
+ + DOMAIN_LENGTHS_ANALYSIS_SUFFIX );
+ if ( domain_length_analysis ) {
SurfacingUtil.checkForOutputFileWriteability( domain_lengths_analysis_outfile );
}
if ( cla.isOptionSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
if ( positive_filter_file != null ) {
final int filter_size = filter.size();
System.out.println( "Positive protein filter : " + positive_filter_file + " [" + filter_size
- + " domain ids]" );
+ + " domain ids]" );
html_desc.append( "<tr><td>Positive protein filter:</td><td>" + positive_filter_file + " [" + filter_size
- + " domain ids]</td></tr>" + nl );
+ + " domain ids]</td></tr>" + nl );
}
if ( negative_filter_file != null ) {
final int filter_size = filter.size();
System.out.println( "Negative protein filter : " + negative_filter_file + " [" + filter_size
- + " domain ids]" );
+ + " domain ids]" );
html_desc.append( "<tr><td>Negative protein filter:</td><td>" + negative_filter_file + " [" + filter_size
- + " domain ids]</td></tr>" + nl );
+ + " domain ids]</td></tr>" + nl );
}
if ( negative_domains_filter_file != null ) {
final int filter_size = filter.size();
System.out.println( "Negative domain filter : " + negative_domains_filter_file + " [" + filter_size
- + " domain ids]" );
+ + " domain ids]" );
html_desc.append( "<tr><td>Negative domain filter:</td><td>" + negative_domains_filter_file + " ["
+ filter_size + " domain ids]</td></tr>" + nl );
}
}
System.out.println( "Plus-minus analysis : " + plus1 + "&& " + plus0 + "&& " + minus );
html_desc.append( "<tr><td>Plus-minus analysis:</td><td>" + plus1 + "&& " + plus0 + "&& " + minus
- + "</td></tr>" + nl );
+ + "</td></tr>" + nl );
}
if ( cutoff_scores_file != null ) {
System.out.println( "Cutoff scores file : " + cutoff_scores_file );
html_desc.append( "<tr><td>Cutoff scores file:</td><td>" + cutoff_scores_file + "</td></tr>" + nl );
}
- if ( e_value_max >= 0.0 ) {
- System.out.println( "E-value maximum (inclusive) : " + e_value_max );
- html_desc.append( "<tr><td>E-value maximum (inclusive):</td><td>" + e_value_max + "</td></tr>" + nl );
+ if ( ie_value_max >= 0.0 ) {
+ System.out.println( "iE-value maximum (incl) : " + ie_value_max );
+ html_desc.append( "<tr><td>iE-value maximum (inclusive):</td><td>" + ie_value_max + "</td></tr>" + nl );
+ }
+ if ( fs_e_value_max >= 0.0 ) {
+ System.out.println( "FS E-value maximum (incl) : " + fs_e_value_max );
+ html_desc.append( "<tr><td>FS E-value maximum (inclusive):</td><td>" + fs_e_value_max + "</td></tr>" + nl );
}
if ( output_protein_lists_for_all_domains ) {
System.out.println( "Domain E-value max : " + output_list_of_all_proteins_per_domain_e_value_max );
if ( no_engulfing_overlaps ) {
System.out.println( "Ignore engulfed domains : " + no_engulfing_overlaps );
html_desc.append( "<tr><td>Ignore (lower confidence) engulfed domains:</td><td>" + no_engulfing_overlaps
- + "</td></tr>" + nl );
+ + "</td></tr>" + nl );
}
System.out.println( "Ignore singlet domains : " + ignore_domains_without_combs_in_all_spec );
html_desc
- .append( "<tr><td>Ignore singlet domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
- + ignore_domains_without_combs_in_all_spec + "</td></tr>" + nl );
+ .append( "<tr><td>Ignore singlet domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
+ + ignore_domains_without_combs_in_all_spec + "</td></tr>" + nl );
System.out.println( "Ignore species specific doms: " + ignore_species_specific_domains );
html_desc
- .append( "<tr><td>Ignore species specific domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
- + ignore_species_specific_domains + "</td></tr>" + nl );
+ .append( "<tr><td>Ignore species specific domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
+ + ignore_species_specific_domains + "</td></tr>" + nl );
System.out.println( "Ignore combination with self: " + ignore_combination_with_same );
html_desc.append( "<tr><td>Ignore combination with self for domain combination similarity analyses:</td><td>"
+ ignore_combination_with_same + "</td></tr>" + nl );
+ ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) + "</td></tr>"
+ nl );
}
- System.out.println( "Use last in Fitch parimony : " + use_last_in_fitch_parsimony );
- html_desc.append( "<tr><td>Use last in Fitch parimon:</td><td>" + use_last_in_fitch_parsimony + "</td></tr>"
- + nl );
+ System.out.println( "Fitch parsimony of DCs : " + perform_dc_fich );
+ html_desc.append( "<tr><td>Fitch parsimony of DCs:</td><td>" + perform_dc_fich + "</td></tr>" + nl );
+ if ( perform_dc_fich ) {
+ System.out.println( "Use last in Fitch parsimony : " + use_last_in_fitch_parsimony );
+ html_desc.append( "<tr><td>Use last in Fitch parsimony:</td><td>" + use_last_in_fitch_parsimony
+ + "</td></tr>" + nl );
+ }
System.out.println( "Write to Nexus files : " + write_to_nexus );
html_desc.append( "<tr><td>Write to Nexus files:</td><td>" + write_to_nexus + "</td></tr>" + nl );
- System.out.println( "DC regain prot stats : " + perform_dc_regain_proteins_stats );
- html_desc.append( "<tr><td>DC regain prot stats:</td><td>" + perform_dc_regain_proteins_stats + "</td></tr>"
- + nl );
+ if ( perform_dc_fich ) {
+ System.out.println( "DC regain prot stats : " + perform_dc_regain_proteins_stats );
+ html_desc.append( "<tr><td>DC regain prot stats:</td><td>" + perform_dc_regain_proteins_stats
+ + "</td></tr>" + nl );
+ }
System.out.println( "DA analysis : " + da_analysis );
html_desc.append( "<tr><td>DA analysis :</td><td>" + da_analysis + "</td></tr>" + nl );
System.out.print( "Domain counts sort order : " );
}
if ( domain_id_to_go_ids_map != null ) {
System.out.println( "Pfam to GO mappings from : " + pfam_to_go_file + " [" + domain_id_to_go_ids_count
- + " mappings]" );
+ + " mappings]" );
html_desc.append( "<tr><td>Pfam to GO mappings from:</td><td>" + pfam_to_go_file + " ["
+ domain_id_to_go_ids_count + " mappings]" + "</td></tr>" + nl );
}
if ( perform_pwc ) {
System.out.println( "Suffix for PWC files : " + automated_pairwise_comparison_suffix );
html_desc.append( "<tr><td>Suffix for PWC files</td><td>" + automated_pairwise_comparison_suffix
- + "</td></tr>" + nl );
+ + "</td></tr>" + nl );
}
if ( out_dir != null ) {
System.out.println( "Output directory : " + out_dir );
break;
default:
ForesterUtil
- .unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
+ .unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
}
System.out.println();
html_desc.append( "</td></tr>" + nl );
if ( ( intrees != null ) && ( intrees.length > 0 ) ) {
for( final File intree_file : intree_files ) {
html_desc.append( "<tr><td>Intree for gain/loss parsimony analysis:</td><td>" + intree_file
- + "</td></tr>" + nl );
+ + "</td></tr>" + nl );
System.out.println( " Intree for gain/loss pars.: " + intree_file );
}
}
}
} // if ( perform_pwc ) {
System.out.println();
- html_desc.append( "<tr><td>Command line:</td><td>\n" + cla.getCommandLineArgsAsString() + "\n</td></tr>" + nl );
+ html_desc.append( "<tr><td>Command line:</td><td>" + nl + nl + cla.getCommandLineArgsAsString() + nl + nl
+ + "</td></tr>" + nl );
System.out.println( "Command line : " + cla.getCommandLineArgsAsString() );
BufferedWriter[] query_domains_writer_ary = null;
List<String>[] query_domain_ids_array = null;
all_bin_domain_combinations_gained_fitch = new ArrayList<BinaryDomainCombination>();
all_bin_domain_combinations_lost_fitch = new ArrayList<BinaryDomainCombination>();
}
- final DomainLengthsTable domain_lengths_table = new DomainLengthsTable();
final File per_genome_domain_promiscuity_statistics_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR
- + output_file + D_PROMISCUITY_FILE_SUFFIX );
+ + output_file + D_PROMISCUITY_FILE_SUFFIX );
BufferedWriter per_genome_domain_promiscuity_statistics_writer = null;
try {
per_genome_domain_promiscuity_statistics_writer = new BufferedWriter( new FileWriter( per_genome_domain_promiscuity_statistics_file ) );
catch ( final IOException e2 ) {
ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
}
- final DescriptiveStatistics protein_coverage_stats = new BasicDescriptiveStatistics();
- final DescriptiveStatistics all_genomes_domains_per_potein_stats = new BasicDescriptiveStatistics();
+ DescriptiveStatistics protein_coverage_stats = new BasicDescriptiveStatistics();
+ DescriptiveStatistics all_genomes_domains_per_potein_stats = new BasicDescriptiveStatistics();
final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo = new TreeMap<Integer, Integer>();
final SortedSet<String> domains_which_are_always_single = new TreeSet<String>();
final SortedSet<String> domains_which_are_sometimes_single_sometimes_not = new TreeSet<String>();
BufferedWriter domains_per_potein_stats_writer = null;
try {
domains_per_potein_stats_writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR
- + output_file + "_domains_per_potein_stats.txt" ) );
+ + output_file + "_domains_per_potein_stats.txt" ) );
domains_per_potein_stats_writer.write( "Genome" );
domains_per_potein_stats_writer.write( "\t" );
domains_per_potein_stats_writer.write( "Mean" );
protein_length_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
domain_number_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
}
+ DomainLengthsTable domain_lengths_table = null;
+ if ( domain_length_analysis ) {
+ domain_lengths_table = new DomainLengthsTable();
+ }
// Main loop:
final SortedMap<String, Set<String>> distinct_domain_architecutures_per_genome = new TreeMap<String, Set<String>>();
final SortedMap<String, Integer> distinct_domain_architecuture_counts = new TreeMap<String, Integer>();
for( int i = 0; i < number_of_genomes; ++i ) {
System.out.println();
System.out.println( ( i + 1 ) + "/" + number_of_genomes );
- log( ( i + 1 ) + "/" + number_of_genomes, log_writer );
+ SurfacingUtil.log( ( i + 1 ) + "/" + number_of_genomes, log_writer );
System.out.println( "Processing : " + input_file_properties[ i ][ 1 ]
+ " [" + input_file_properties[ i ][ 0 ] + "]" );
- log( "Genome : " + input_file_properties[ i ][ 1 ] + " ["
- + input_file_properties[ i ][ 0 ] + "]", log_writer );
+ SurfacingUtil.log( "Genome : " + input_file_properties[ i ][ 1 ]
+ + " [" + input_file_properties[ i ][ 0 ] + "]", log_writer );
HmmscanPerDomainTableParser parser = null;
INDIVIDUAL_SCORE_CUTOFF ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF.NONE;
if ( individual_score_cutoffs != null ) {
ind_score_cutoff,
true );
}
- if ( e_value_max >= 0.0 ) {
- parser.setEValueMaximum( e_value_max );
+ if ( fs_e_value_max >= 0.0 ) {
+ parser.setFsEValueMaximum( fs_e_value_max );
+ }
+ if ( ie_value_max >= 0.0 ) {
+ parser.setIEValueMaximum( ie_value_max );
}
parser.setIgnoreDufs( ignore_dufs );
parser.setIgnoreVirusLikeIds( ignore_virus_like_ids );
distinct_domain_architecuture_counts );
}
System.out.println( "Number of proteins encountered : " + parser.getProteinsEncountered() );
- log( "Number of proteins encountered : " + parser.getProteinsEncountered(), log_writer );
+ SurfacingUtil.log( "Number of proteins encountered : " + parser.getProteinsEncountered(),
+ log_writer );
System.out.println( "Number of proteins stored : " + protein_list.size() );
- log( "Number of proteins stored : " + protein_list.size(), log_writer );
+ SurfacingUtil.log( "Number of proteins stored : " + protein_list.size(), log_writer );
System.out.println( "Coverage : "
+ ForesterUtil.roundToInt( 100.0 * coverage ) + "%" );
- log( "Coverage : " + ForesterUtil.roundToInt( 100.0 * coverage )
- + "%", log_writer );
+ SurfacingUtil.log( "Coverage : "
+ + ForesterUtil.roundToInt( 100.0 * coverage ) + "%",
+ log_writer );
System.out.println( "Domains encountered : " + parser.getDomainsEncountered() );
- log( "Domains encountered : " + parser.getDomainsEncountered(), log_writer );
+ SurfacingUtil.log( "Domains encountered : " + parser.getDomainsEncountered(),
+ log_writer );
System.out.println( "Domains stored : " + parser.getDomainsStored() );
- log( "Domains stored : " + parser.getDomainsStored(), log_writer );
+ SurfacingUtil.log( "Domains stored : " + parser.getDomainsStored(),
+ log_writer );
System.out.println( "Distinct domains stored : "
+ parser.getDomainsStoredSet().size() );
- log( "Distinct domains stored : " + parser.getDomainsStoredSet().size(), log_writer );
+ SurfacingUtil.log( "Distinct domains stored : "
+ + parser.getDomainsStoredSet().size(), log_writer );
System.out.println( "Domains ignored due to individual score cutoffs: "
+ parser.getDomainsIgnoredDueToIndividualScoreCutoff() );
- log( "Domains ignored due to individual score cutoffs: "
- + parser.getDomainsIgnoredDueToIndividualScoreCutoff(),
- log_writer );
- System.out.println( "Domains ignored due to E-value : "
- + parser.getDomainsIgnoredDueToEval() );
- log( "Domains ignored due to E-value : " + parser.getDomainsIgnoredDueToEval(), log_writer );
+ SurfacingUtil.log( "Domains ignored due to individual score cutoffs: "
+ + parser.getDomainsIgnoredDueToIndividualScoreCutoff(),
+ log_writer );
+ System.out.println( "Domains ignored due to FS E-value : "
+ + parser.getDomainsIgnoredDueToFsEval() );
+ SurfacingUtil.log( "Domains ignored due to FS E-value : "
+ + parser.getDomainsIgnoredDueToFsEval(),
+ log_writer );
+ System.out.println( "Domains ignored due to iE-value : "
+ + parser.getDomainsIgnoredDueToIEval() );
+ SurfacingUtil.log( "Domains ignored due to iE-value : "
+ + parser.getDomainsIgnoredDueToIEval(),
+ log_writer );
System.out.println( "Domains ignored due to DUF designation : "
+ parser.getDomainsIgnoredDueToDuf() );
- log( "Domains ignored due to DUF designation : " + parser.getDomainsIgnoredDueToDuf(), log_writer );
+ SurfacingUtil
+ .log( "Domains ignored due to DUF designation : " + parser.getDomainsIgnoredDueToDuf(),
+ log_writer );
if ( ignore_virus_like_ids ) {
System.out.println( "Domains ignored due virus like ids : "
+ parser.getDomainsIgnoredDueToVirusLikeIds() );
- log( "Domains ignored due virus like ids : " + parser.getDomainsIgnoredDueToVirusLikeIds(),
- log_writer );
+ SurfacingUtil.log( "Domains ignored due virus like ids : "
+ + parser.getDomainsIgnoredDueToVirusLikeIds(),
+ log_writer );
}
System.out.println( "Domains ignored due negative domain filter : "
+ parser.getDomainsIgnoredDueToNegativeDomainFilter() );
- log( "Domains ignored due negative domain filter : "
- + parser.getDomainsIgnoredDueToNegativeDomainFilter(),
- log_writer );
+ SurfacingUtil.log( "Domains ignored due negative domain filter : "
+ + parser.getDomainsIgnoredDueToNegativeDomainFilter(),
+ log_writer );
System.out.println( "Domains ignored due to overlap : "
+ parser.getDomainsIgnoredDueToOverlap() );
- log( "Domains ignored due to overlap : " + parser.getDomainsIgnoredDueToOverlap(),
- log_writer );
+ SurfacingUtil.log( "Domains ignored due to overlap : "
+ + parser.getDomainsIgnoredDueToOverlap(),
+ log_writer );
if ( negative_filter_file != null ) {
System.out.println( "Proteins ignored due to negative filter : "
+ parser.getProteinsIgnoredDueToFilter() );
- log( "Proteins ignored due to negative filter : " + parser.getProteinsIgnoredDueToFilter(),
- log_writer );
+ SurfacingUtil.log( "Proteins ignored due to negative filter : "
+ + parser.getProteinsIgnoredDueToFilter(),
+ log_writer );
}
if ( positive_filter_file != null ) {
System.out.println( "Proteins ignored due to positive filter : "
+ parser.getProteinsIgnoredDueToFilter() );
- log( "Proteins ignored due to positive filter : " + parser.getProteinsIgnoredDueToFilter(),
- log_writer );
+ SurfacingUtil.log( "Proteins ignored due to positive filter : "
+ + parser.getProteinsIgnoredDueToFilter(),
+ log_writer );
}
if ( da_analysis ) {
System.out.println( "Distinct domain architectures stored : " + distinct_das );
- log( "Distinct domain architectures stored : " + distinct_das, log_writer );
+ SurfacingUtil.log( "Distinct domain architectures stored : " + distinct_das, log_writer );
}
System.out.println( "Time for processing : " + parser.getTime() + "ms" );
- log( "", log_writer );
+ SurfacingUtil.log( "", log_writer );
try {
int count = 0;
for( final Protein protein : protein_list ) {
dc_data_writer.write( SurfacingUtil.proteinToDomainCombinations( protein, count + "", "\t" )
- .toString() );
+ .toString() );
++count;
for( final Domain d : protein.getProteinDomains() ) {
final String d_str = d.getDomainId().toString();
domains_which_are_sometimes_single_sometimes_not,
domains_which_never_single,
domains_per_potein_stats_writer );
- domain_lengths_table.addLengths( protein_list );
+ if ( domain_length_analysis ) {
+ domain_lengths_table.addLengths( protein_list );
+ }
if ( !da_analysis ) {
gwcd_list.add( BasicGenomeWideCombinableDomains
- .createInstance( protein_list,
- ignore_combination_with_same,
- new BasicSpecies( input_file_properties[ i ][ 1 ] ),
- domain_id_to_go_ids_map,
- dc_type,
- protein_length_stats_by_dc,
- domain_number_stats_by_dc ) );
+ .createInstance( protein_list,
+ ignore_combination_with_same,
+ new BasicSpecies( input_file_properties[ i ][ 1 ] ),
+ domain_id_to_go_ids_map,
+ dc_type,
+ protein_length_stats_by_dc,
+ domain_number_stats_by_dc ) );
if ( gwcd_list.get( i ).getSize() > 0 ) {
- SurfacingUtil.writeDomainCombinationsCountsFile( input_file_properties,
- out_dir,
- per_genome_domain_promiscuity_statistics_writer,
- gwcd_list.get( i ),
- i,
- dc_sort_order );
+ if ( output_binary_domain_combinationsfor_counts ) {
+ SurfacingUtil
+ .writeDomainCombinationsCountsFile( input_file_properties,
+ out_dir,
+ per_genome_domain_promiscuity_statistics_writer,
+ gwcd_list.get( i ),
+ i,
+ dc_sort_order );
+ }
if ( output_binary_domain_combinationsfor_graph_analysis ) {
SurfacingUtil.writeBinaryDomainCombinationsFileForGraphAnalysis( input_file_properties,
out_dir,
distinct_domain_architecuture_counts,
10,
new File( out_dir.toString() + "/" + output_file
- + "_DA_counts.txt" ),
- new File( out_dir.toString() + "/" + output_file
- + "_unique_DAs.txt" ) );
+ + "_DA_counts.txt" ),
+ new File( out_dir.toString() + "/" + output_file
+ + "_unique_DAs.txt" ) );
distinct_domain_architecutures_per_genome.clear();
distinct_domain_architecuture_counts.clear();
System.gc();
domains_per_potein_stats_writer.write( "\t" );
domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.sampleStandardDeviation() + "" );
domains_per_potein_stats_writer.write( "\t" );
- domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.median() + "" );
- domains_per_potein_stats_writer.write( "\t" );
+ if ( all_genomes_domains_per_potein_stats.getN() <= 300 ) {
+ domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.median() + "" );
+ domains_per_potein_stats_writer.write( "\t" );
+ }
domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getN() + "" );
domains_per_potein_stats_writer.write( "\t" );
domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMin() + "" );
domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMax() + "" );
domains_per_potein_stats_writer.write( "\n" );
domains_per_potein_stats_writer.close();
- printOutPercentageOfMultidomainProteins( all_genomes_domains_per_potein_histo, log_writer );
+ all_genomes_domains_per_potein_stats = null;
+ SurfacingUtil.printOutPercentageOfMultidomainProteins( all_genomes_domains_per_potein_histo, log_writer );
ForesterUtil.map2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
- + "_all_genomes_domains_per_potein_histo.txt" ), all_genomes_domains_per_potein_histo, "\t", "\n" );
+ + "_all_genomes_domains_per_potein_histo.txt" ), all_genomes_domains_per_potein_histo, "\t", "\n" );
ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
- + "_domains_always_single_.txt" ), domains_which_are_always_single, "\n" );
+ + "_domains_always_single_.txt" ), domains_which_are_always_single, "\n" );
ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
- + "_domains_single_or_combined.txt" ), domains_which_are_sometimes_single_sometimes_not, "\n" );
+ + "_domains_single_or_combined.txt" ), domains_which_are_sometimes_single_sometimes_not, "\n" );
ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
- + "_domains_always_combined.txt" ), domains_which_never_single, "\n" );
+ + "_domains_always_combined.txt" ), domains_which_never_single, "\n" );
ForesterUtil.programMessage( PRG_NAME,
"Average of proteins with a least one domain assigned: "
+ ( 100 * protein_coverage_stats.arithmeticMean() ) + "% (+/-"
ForesterUtil.programMessage( PRG_NAME, "Range of proteins with a least one domain assigned: "
+ ( 100 * protein_coverage_stats.getMin() ) + "%-" + ( 100 * protein_coverage_stats.getMax() )
+ "%" );
- log( "Average of prot with a least one dom assigned : " + ( 100 * protein_coverage_stats.arithmeticMean() )
- + "% (+/-" + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)", log_writer );
- log( "Range of prot with a least one dom assigned : " + ( 100 * protein_coverage_stats.getMin() ) + "%-"
- + ( 100 * protein_coverage_stats.getMax() ) + "%", log_writer );
+ SurfacingUtil.log( "Average of prot with a least one dom assigned : "
+ + ( 100 * protein_coverage_stats.arithmeticMean() ) + "% (+/-"
+ + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)",
+ log_writer );
+ SurfacingUtil.log( "Range of prot with a least one dom assigned : "
+ + ( 100 * protein_coverage_stats.getMin() ) + "%-"
+ + ( 100 * protein_coverage_stats.getMax() ) + "%",
+ log_writer );
+ protein_coverage_stats = null;
}
catch ( final IOException e2 ) {
ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
catch ( final IOException e2 ) {
ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
}
- if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
+ if ( domain_length_analysis ) {
try {
SurfacingUtil.executeDomainLengthAnalysis( input_file_properties,
number_of_genomes,
ForesterUtil.programMessage( PRG_NAME, "Wrote domain length data to: " + domain_lengths_analysis_outfile );
System.out.println();
}
+ domain_lengths_table = null;
final long analysis_start_time = new Date().getTime();
PairwiseDomainSimilarityCalculator pw_calc = null;
- // double[] values_for_all_scores_histogram = null;
final DomainSimilarityCalculator calc = new BasicDomainSimilarityCalculator( domain_similarity_sort_field,
sort_by_species_count_first,
- number_of_genomes == 2 );
+ number_of_genomes == 2,
+ CALC_SIMILARITY_SCORES,
+ true );
switch ( scoring ) {
case COMBINATIONS:
pw_calc = new CombinationsBasedPairwiseDomainSimilarityCalculator();
my_outfile = my_outfile.substring( 0, my_outfile.length() - 5 );
}
split_writers = new HashMap<Character, Writer>();
- createSplitWriters( out_dir, my_outfile, split_writers );
+ SurfacingUtil.createSplitWriters( out_dir, my_outfile, split_writers );
}
else if ( !my_outfile.endsWith( ".html" ) ) {
my_outfile += ".html";
html_desc.append( "<tr><td>Sum of all distinct binary combinations:</td><td>"
+ all_bin_domain_combinations_encountered.size() + "</td></tr>" + nl );
html_desc.append( "<tr><td>Sum of all distinct domains:</td><td>" + all_domains_encountered.size()
- + "</td></tr>" + nl );
+ + "</td></tr>" + nl );
html_desc.append( "<tr><td>Analysis date/time:</td><td>"
+ new java.text.SimpleDateFormat( "yyyy.MM.dd HH:mm:ss" ).format( new java.util.Date() )
+ "</td></tr>" + nl );
html_desc.append( "</table>" + nl );
- final DescriptiveStatistics pw_stats = SurfacingUtil
- .writeDomainSimilaritiesToFile( html_desc,
- new StringBuilder( number_of_genomes + " genomes" ),
- writer,
- split_writers,
- similarities,
- number_of_genomes == 2,
- species_order,
- domain_similarity_print_option,
- scoring,
- true,
- tax_code_to_id_map,
- false );
+ final Writer simple_tab_writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR
+ + my_outfile + ".tsv" ) );
+ SurfacingUtil.writeDomainSimilaritiesToFile( html_desc,
+ new StringBuilder( number_of_genomes + " genomes" ),
+ simple_tab_writer,
+ writer,
+ split_writers,
+ similarities,
+ number_of_genomes == 2,
+ species_order,
+ domain_similarity_print_option,
+ scoring,
+ true,
+ tax_code_to_id_map,
+ intree_0_orig,
+ positive_filter_file != null ? filter : null );
+ simple_tab_writer.close();
ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote main output (includes domain similarities) to: \""
+ ( out_dir == null ? my_outfile : out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) + "\"" );
}
surfacing.PRG_NAME,
out_dir,
write_pwc_files,
- tax_code_to_id_map );
+ tax_code_to_id_map,
+ CALC_SIMILARITY_SCORES,
+ intree_0_orig );
String matrix_output_file = new String( output_file.toString() );
if ( matrix_output_file.indexOf( '.' ) > 1 ) {
matrix_output_file = matrix_output_file.substring( 0, matrix_output_file.indexOf( '.' ) );
output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
}
SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
- + surfacing.MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans() );
+ + surfacing.MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans() );
SurfacingUtil
- .writeMatrixToFile( new File( matrix_output_file
- + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
- pwgc.getSharedBinaryCombinationsBasedDistances() );
+ .writeMatrixToFile( new File( matrix_output_file
+ + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
+ pwgc.getSharedBinaryCombinationsBasedDistances() );
SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
- + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
- pwgc.getSharedDomainsBasedDistances() );
+ + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
+ pwgc.getSharedDomainsBasedDistances() );
final Phylogeny nj_gd = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
- + surfacing.NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans()
- .get( 0 ) );
+ + surfacing.NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans()
+ .get( 0 ) );
final Phylogeny nj_bc = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
- + surfacing.NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
- .getSharedBinaryCombinationsBasedDistances().get( 0 ) );
+ + surfacing.NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
+ .getSharedBinaryCombinationsBasedDistances().get( 0 ) );
final Phylogeny nj_d = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
- + surfacing.NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
- .getSharedDomainsBasedDistances().get( 0 ) );
+ + surfacing.NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
+ .getSharedDomainsBasedDistances().get( 0 ) );
inferred_trees = new ArrayList<Phylogeny>();
inferred_trees.add( nj_gd );
inferred_trees.add( nj_bc );
output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
}
if ( write_to_nexus ) {
- writePresentToNexus( output_file, positive_filter_file, filter, gwcd_list );
+ SurfacingUtil.writePresentToNexus( output_file, positive_filter_file, filter, gwcd_list );
}
if ( ( ( intrees != null ) && ( intrees.length > 0 ) ) && ( number_of_genomes > 2 ) ) {
- final StringBuilder parameters_sb = createParametersAsString( ignore_dufs,
- e_value_max,
- max_allowed_overlap,
- no_engulfing_overlaps,
- cutoff_scores_file,
- dc_type );
+ final StringBuilder parameters_sb = SurfacingUtil.createParametersAsString( ignore_dufs,
+ ie_value_max,
+ fs_e_value_max,
+ max_allowed_overlap,
+ no_engulfing_overlaps,
+ cutoff_scores_file,
+ dc_type );
String s = "_";
if ( radomize_fitch_parsimony ) {
s += random_number_seed_for_fitch_parsimony + "_";
parameters_sb.toString(),
domain_id_to_secondary_features_maps,
positive_filter_file == null ? null : filter,
- output_binary_domain_combinationsfor_graph_analysis,
- all_bin_domain_combinations_gained_fitch,
- all_bin_domain_combinations_lost_fitch,
- dc_type,
- protein_length_stats_by_dc,
- domain_number_stats_by_dc,
- domain_length_stats_by_domain,
- tax_code_to_id_map,
- write_to_nexus,
- use_last_in_fitch_parsimony );
- // Listing of all domain combinations gained is only done if only one input tree is used.
+ output_binary_domain_combinationsfor_graph_analysis,
+ all_bin_domain_combinations_gained_fitch,
+ all_bin_domain_combinations_lost_fitch,
+ dc_type,
+ protein_length_stats_by_dc,
+ domain_number_stats_by_dc,
+ domain_length_stats_by_domain,
+ tax_code_to_id_map,
+ write_to_nexus,
+ use_last_in_fitch_parsimony,
+ perform_dc_fich );
+ // Listing of all domain combinations gained is only done if only one input tree is used.
if ( ( domain_id_to_secondary_features_maps != null )
&& ( domain_id_to_secondary_features_maps.length > 0 ) ) {
int j = 0;
final DomainParsimonyCalculator secondary_features_parsimony = DomainParsimonyCalculator
.createInstance( intree, gwcd_list, domain_id_to_secondary_features_map );
SurfacingUtil
- .executeParsimonyAnalysisForSecondaryFeatures( outfile_name
- + "_"
- + secondary_features_map_files[ j++ ],
- secondary_features_parsimony,
- intree,
- parameters_sb.toString(),
- mapping_results_map,
- use_last_in_fitch_parsimony );
+ .executeParsimonyAnalysisForSecondaryFeatures( outfile_name
+ + "_"
+ + secondary_features_map_files[ j++ ],
+ secondary_features_parsimony,
+ intree,
+ parameters_sb.toString(),
+ mapping_results_map,
+ use_last_in_fitch_parsimony );
if ( i == 0 ) {
System.out.println();
System.out.println( "Mapping to secondary features:" );
} // for( final Phylogeny intree : intrees ) {
}
if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
- executePlusMinusAnalysis( output_file,
- plus_minus_analysis_high_copy_base_species,
- plus_minus_analysis_high_copy_target_species,
- plus_minus_analysis_high_low_copy_species,
- gwcd_list,
- protein_lists_per_species,
- domain_id_to_go_ids_map,
- go_id_to_term_map,
- plus_minus_analysis_numbers );
+ SurfacingUtil.executePlusMinusAnalysis( output_file,
+ plus_minus_analysis_high_copy_base_species,
+ plus_minus_analysis_high_copy_target_species,
+ plus_minus_analysis_high_low_copy_species,
+ gwcd_list,
+ protein_lists_per_species,
+ domain_id_to_go_ids_map,
+ go_id_to_term_map,
+ plus_minus_analysis_numbers );
}
if ( output_protein_lists_for_all_domains ) {
- writeProteinListsForAllSpecies( out_dir,
- protein_lists_per_species,
- gwcd_list,
- output_list_of_all_proteins_per_domain_e_value_max );
+ SurfacingUtil.writeProteinListsForAllSpecies( out_dir,
+ protein_lists_per_species,
+ gwcd_list,
+ output_list_of_all_proteins_per_domain_e_value_max,
+ positive_filter_file != null ? filter : null );
}
gwcd_list = null;
if ( all_bin_domain_combinations_gained_fitch != null ) {
try {
- executeFitchGainsAnalysis( new File( output_file
- + surfacing.OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
- all_bin_domain_combinations_gained_fitch,
- all_domains_encountered.size(),
- all_bin_domain_combinations_encountered,
- true );
+ SurfacingUtil
+ .executeFitchGainsAnalysis( new File( output_file
+ + surfacing.OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
+ all_bin_domain_combinations_gained_fitch,
+ all_domains_encountered.size(),
+ all_bin_domain_combinations_encountered,
+ true );
}
catch ( final IOException e ) {
ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
}
if ( all_bin_domain_combinations_lost_fitch != null ) {
try {
- executeFitchGainsAnalysis( new File( output_file
- + surfacing.OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
- all_bin_domain_combinations_lost_fitch,
- all_domains_encountered.size(),
- all_bin_domain_combinations_encountered,
- false );
+ SurfacingUtil
+ .executeFitchGainsAnalysis( new File( output_file
+ + surfacing.OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
+ all_bin_domain_combinations_lost_fitch,
+ all_domains_encountered.size(),
+ all_bin_domain_combinations_encountered,
+ false );
}
catch ( final IOException e ) {
ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
final long free_memory = rt.freeMemory() / 1000000;
final long total_memory = rt.totalMemory() / 1000000;
ForesterUtil.programMessage( PRG_NAME, "Time for analysis : " + ( new Date().getTime() - analysis_start_time )
- + "ms" );
+ + "ms" );
ForesterUtil.programMessage( PRG_NAME, "Total running time: " + ( new Date().getTime() - start_time ) + "ms " );
ForesterUtil.programMessage( PRG_NAME, "Free memory : " + free_memory + "MB, total memory: "
+ total_memory + "MB" );
System.out.println();
}
- private 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" ) ) );
- }
-
- private 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( PRG_NAME, "Percentage of multidomain proteins: " + percentage + "%" );
- log( "Percentage of multidomain proteins: : " + percentage + "%", log_writer );
- }
-
- private 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" );
- }
- }
- }
-
private static void printHelp() {
System.out.println();
System.out.println( "Usage:" );
System.out.println();
System.out.println( "% java -Xms256m -Xmx512m -cp forester.jar org.forester.applications." + surfacing.PRG_NAME
- + " [options] <phylogen(y|ies) infile> [external node name 1] [name 2] ... [name n]" );
+ + " [options] <phylogen(y|ies) infile> [external node name 1] [name 2] ... [name n]" );
System.out.println();
System.out.println( " Note: This software might need a significant amount of memory (heap space);" );
System.out
- .println( " hence use \"-Xms128m -Xmx512m\" (or more) to prevent a \"java.lang.OutOfMemoryError\"." );
+ .println( " hence use \"-Xms128m -Xmx512m\" (or more) to prevent a \"java.lang.OutOfMemoryError\"." );
System.out.println();
System.out.println( " Options: " );
System.out.println( surfacing.DETAILEDNESS_OPTION + ": level of detail for similarities output file (default:"
+ DETAILEDNESS_DEFAULT + ")" );
System.out.println( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION
- + ": to ignore combinations with self (default: not to ignore)" );
+ + ": to ignore combinations with self (default: not to ignore)" );
System.out
- .println( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION
- + ": to ignore domains without combinations in any species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
+ .println( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION
+ + ": to ignore domains without combinations in any species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
System.out
- .println( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION
- + ": to ignore domains specific to one species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
+ .println( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION
+ + ": to ignore domains specific to one species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
System.out.println( surfacing.NOT_IGNORE_DUFS_OPTION
- + ": to _not_ ignore DUFs (domains with unknown function) (default: ignore DUFs)" );
+ + ": to _not_ ignore DUFs (domains with unknown function) (default: ignore DUFs)" );
System.out
- .println( surfacing.IGNORE_VIRAL_IDS
- + ": to ignore domains with ids containing 'vir', 'retro', 'transpos', 'phage', or starting with 'rv' or 'gag_'" );
+ .println( surfacing.IGNORE_VIRAL_IDS
+ + ": to ignore domains with ids containing 'vir', 'retro', 'transpos', 'phage', or starting with 'rv' or 'gag_'" );
System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_OPTION + ": sorting for similarities (default: "
+ DOMAIN_SORT_FILD_DEFAULT + ")" );
System.out.println( surfacing.OUTPUT_FILE_OPTION + ": name for (main) output file (mandatory)" );
- System.out.println( surfacing.MAX_E_VALUE_OPTION + ": max (inclusive) E-value" );
+ System.out.println( surfacing.MAX_I_E_VALUE_OPTION + ": max (inclusive) iE-value" );
+ System.out.println( surfacing.MAX_FS_E_VALUE_OPTION + ": max (inclusive) FS E-value" );
System.out.println( surfacing.MAX_ALLOWED_OVERLAP_OPTION + ": maximal allowed domain overlap" );
System.out.println( surfacing.NO_ENGULFING_OVERLAP_OPTION + ": to ignore engulfed lower confidence domains" );
System.out.println( surfacing.SPECIES_MATRIX_OPTION + ": species matrix" );
+ DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT + ")" );
System.out.println( surfacing.CUTOFF_SCORE_FILE_OPTION + ": cutoff score file" );
System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION
- + ": sort by species count first" );
+ + ": sort by species count first" );
System.out.println( surfacing.OUTPUT_DIR_OPTION + ": output directory" );
System.out.println( surfacing.PFAM_TO_GO_FILE_USE_OPTION + ": Pfam to GO mapping file" );
System.out.println( surfacing.GO_OBO_FILE_USE_OPTION + ": GO terms file (OBO format)" );
System.out.println( surfacing.GO_NAMESPACE_LIMIT_OPTION + ": limit GO term to one GO namespace" );
System.out.println( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
- + "[=<suffix for pairwise comparison output files>]: to perform pairwise comparison based analyses" );
+ + "[=<suffix for pairwise comparison output files>]: to perform pairwise comparison based analyses" );
System.out.println( surfacing.INPUT_SPECIES_TREE_OPTION
- + ": species tree, to perform (Dollo, Fitch) parismony analyses" );
+ + ": species tree, to perform (Dollo, Fitch) parismony analyses" );
System.out
- .println( surfacing.INPUT_SPECIES_TREE_OPTION
- + "=<treefiles in phyloXML format, separated by #>: to infer domain/binary domain combination gains/losses on given species trees" );
+ .println( surfacing.INPUT_SPECIES_TREE_OPTION
+ + "=<treefiles in phyloXML format, separated by #>: to infer domain/binary domain combination gains/losses on given species trees" );
System.out.println( surfacing.FILTER_POSITIVE_OPTION
- + "=<file>: to filter out proteins not containing at least one domain listed in <file>" );
+ + "=<file>: to filter out proteins not containing at least one domain listed in <file>" );
System.out.println( surfacing.FILTER_NEGATIVE_OPTION
- + "=<file>: to filter out proteins containing at least one domain listed in <file>" );
+ + "=<file>: to filter out proteins containing at least one domain listed in <file>" );
System.out.println( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION
- + "=<file>: to filter out (ignore) domains listed in <file>" );
+ + "=<file>: to filter out (ignore) domains listed in <file>" );
System.out.println( surfacing.INPUT_GENOMES_FILE_OPTION + "=<file>: to read input files from <file>" );
System.out
- .println( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION
- + "=<seed>: seed for random number generator for Fitch Parsimony analysis (type: long, default: no randomization - given a choice, prefer absence" );
+ .println( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION
+ + "=<seed>: seed for random number generator for Fitch Parsimony analysis (type: long, default: no randomization - given a choice, prefer absence" );
System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS
- + ": to consider directedness in binary combinations: e.g. A-B != B-A" );
+ + ": to consider directedness in binary combinations: e.g. A-B != B-A" );
System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY
- + ": to consider directedness and adjacency in binary combinations" );
+ + ": to consider directedness and adjacency in binary combinations" );
System.out
- .println( surfacing.SEQ_EXTRACT_OPTION
- + "=<domain ids (Pfam names)>: to extract sequence names of sequences containing matching domains and/or domain-sequences (order N to C) (domain separator: '~', domain sequences speparator: '#', e.g. 'NACHT#BIR~CARD')" );
+ .println( surfacing.SEQ_EXTRACT_OPTION
+ + "=<domain ids (Pfam names)>: to extract sequence names of sequences containing matching domains and/or domain-sequences (order N to C) (domain separator: '~', domain sequences speparator: '#', e.g. 'NACHT#BIR~CARD')" );
System.out.println( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE
- + "=<file>: to perfom parsimony analysis on secondary features" );
+ + "=<file>: to perfom parsimony analysis on secondary features" );
System.out.println( surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>: to presence/absence genome analysis" );
+ System.out.println( surfacing.DOMAIN_COMBINITONS_COUNTS_OUTPUT_OPTION
+ + ": to output binary domain counts (as individual files)" );
System.out.println( surfacing.DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS
- + ": to output binary domain combinations for (downstream) graph analysis" );
+ + ": to output binary domain combinations for (downstream) graph analysis" );
System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS + ": to output all proteins per domain" );
System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION
- + ": e value max per domain for output of all proteins per domain" );
+ + ": e value max per domain for output of all proteins per domain" );
System.out.println( surfacing.USE_LAST_IN_FITCH_OPTION + ": to use last in Fitch parsimony" );
System.out.println( surfacing.WRITE_TO_NEXUS_OPTION + ": to output in Nexus format" );
+ System.out.println( PERFORM_DC_FITCH + ": to perform DC Fitch parsimony" );
System.out.println( PERFORM_DC_REGAIN_PROTEINS_STATS_OPTION + ": to perform DC regain protein statistics" );
- System.out.println( DA_ANALYSIS_OPTION + ": to do DA analysis" );
+ System.out.println( DA_ANALYSIS_OPTION + ": to perform DA analysis" );
+ System.out.println( PERFORM_DOMAIN_LENGTH_ANALYSIS_OPTION + ": to perform domain length analysis" );
System.out.println();
- System.out.println( "Example 1: java -Xms128m -Xmx512m -cp path/to/forester.jar"
- + " org.forester.application.surfacing p2g=pfam2go_2012_02_07.txt -dufs -cos=Pfam_260_NC1"
- + " -no_eo -mo=0 -genomes=eukaryotes.txt -out_dir=out -o=o "
- + " -species_tree=tol.xml -obo=gene_ontology_2012_02_07.obo -pos_filter=f.txt -all_prot" );
System.out.println();
- System.out.println( "Example 2: java -Xms128m -Xmx512m -cp path/to/forester.jar"
- + " org.forester.application.surfacing -detail=punctilious -o=TEST.html -pwc=TEST"
- + " -cos=Pfam_ls_22_TC2 -p2g=pfam2go -obo=gene_ontology_edit.obo "
- + "-dc_sort=dom -ignore_with_self -no_singles -e=0.001 -mo=1 -no_eo -genomes=eukaryotes.txt "
- + "-ds_output=detailed_html -scoring=domains -sort=alpha " );
+ System.out
+ .println( "Example 1: surfacing -p2g=pfam2go.txt -obo=go.obo -species_tree=tol_156.xml -no_eo -ie=0.01 -dufs -genomes=genomes_all.txt -pos_filter=tf_1.txt -out_dir=_tf1 -o=tf1" );
+ System.out.println();
+ System.out
+ .println( "Example 2: surfacing -p2g=pfam2go.txt -obo=go.obo -species_tree=tol_156.xml -last -ignore_viral_ids -no_eo -ie=0.1 -dufs -genomes=genomes_all.txt -pos_filter=tf_1.txt -all_prot -all_prot_e=0.1 -out_dir=_tf1_e01_ape01 -o=tf1_e01_ape01" );
System.out.println();
- }
-
- private 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 ( VERBOSE ) {
- System.out.println( "Filter:" );
- for( final String domainId : filter ) {
- System.out.println( domainId );
- }
- }
- }
-
- private 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;
- }
-
- private 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.
- private 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 = PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT;
- double factor = 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" );
- }
- }
-
- private static void writePresentToNexus( final File output_file,
- final File positive_filter_file,
- final SortedSet<String> filter,
- final List<GenomeWideCombinableDomains> gwcd_list ) {
- try {
- SurfacingUtil
- .writeMatrixToFile( DomainParsimonyCalculator
- .createMatrixOfDomainPresenceOrAbsence( gwcd_list, positive_filter_file == null ? null
- : filter ), output_file + DOMAINS_PRESENT_NEXUS, Format.NEXUS_BINARY );
- SurfacingUtil.writeMatrixToFile( DomainParsimonyCalculator
- .createMatrixOfBinaryDomainCombinationPresenceOrAbsence( gwcd_list ), output_file
- + BDC_PRESENT_NEXUS, Format.NEXUS_BINARY );
- }
- catch ( final Exception e ) {
- ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
- }
- }
-
- private 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 + SEQ_EXTRACT_SUFFIX );
- SurfacingUtil.checkForOutputFileWriteability( out );
- try {
- final Writer proteins_file_writer = new BufferedWriter( new FileWriter( out ) );
- SurfacingUtil.extractProteinNames( protein_lists_per_species,
- domain,
- proteins_file_writer,
- "\t",
- 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 + "\"" );
- }
}
}
git://source.jalview.org / jalview.git / blobdiff