X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=forester%2Fjava%2Fsrc%2Forg%2Fforester%2Fapplication%2Fsurfacing.java;h=fc87a9686df8ee10eca0cf2d1d47e2e947b7c211;hb=eb22dac14771c467104f57362e3a624d0140f897;hp=616135a2c6cf93ed16a54f12f55b0503df42f6be;hpb=0fc3bc32fc5be907e3f91a780af68c6baff79db1;p=jalview.git diff --git a/forester/java/src/org/forester/application/surfacing.java b/forester/java/src/org/forester/application/surfacing.java index 616135a..fc87a96 100644 --- a/forester/java/src/org/forester/application/surfacing.java +++ b/forester/java/src/org/forester/application/surfacing.java @@ -65,16 +65,15 @@ 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.GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder; import org.forester.surfacing.MappingResults; +import org.forester.surfacing.MinimalDomainomeCalculator; 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; @@ -87,189 +86,195 @@ import org.forester.util.ForesterUtil; 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"; - 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 = 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 = "2.303"; - final static private String PRG_DATE = "131022"; - 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 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 final boolean CALC_SIMILARITY_SCORES = false; + 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 MIN_REL_ENV_LENGTH_RATIO_OPTION = "mrel"; + 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 = "2.503"; + final static private String PRG_DATE = "170518"; + final static private String E_MAIL = "phyloxml@gmail.com"; + 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; + private static final String SEPARATOR_FOR_DA = "--"; + @SuppressWarnings( "unchecked") public static void main( final String args[] ) { final long start_time = new Date().getTime(); // final StringBuffer log = new StringBuffer(); @@ -303,7 +308,9 @@ public class surfacing { } final List allowed_options = new ArrayList(); 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.MIN_REL_ENV_LENGTH_RATIO_OPTION ); allowed_options.add( surfacing.DETAILEDNESS_OPTION ); allowed_options.add( surfacing.OUTPUT_FILE_OPTION ); allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ); @@ -335,15 +342,20 @@ public class surfacing { 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; + double rel_env_length_ratio_cutoff = -1; int max_allowed_overlap = surfacing.MAX_ALLOWED_OVERLAP_DEFAULT; final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options ); if ( dissallowed_options.length() > 0 ) { @@ -357,6 +369,10 @@ public class surfacing { 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; @@ -369,9 +385,29 @@ public class surfacing { 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 { - e_value_max = cla.getOptionValueAsDouble( surfacing.MAX_E_VALUE_OPTION ); + 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.MIN_REL_ENV_LENGTH_RATIO_OPTION ) ) { + try { + rel_env_length_ratio_cutoff = cla.getOptionValueAsDouble( surfacing.MIN_REL_ENV_LENGTH_RATIO_OPTION ); + } + catch ( final Exception e ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for min rel env length ratio" ); + } + } + if ( cla.isOptionSet( surfacing.MAX_I_E_VALUE_OPTION ) ) { + try { + 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" ); @@ -399,6 +435,10 @@ public class surfacing { 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; @@ -407,17 +447,11 @@ public class surfacing { 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 + "=" ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "no input species tree file given: " + surfacing.INPUT_SPECIES_TREE_OPTION + + "=" ); } - - - - File output_file = null; if ( cla.isOptionSet( surfacing.OUTPUT_FILE_OPTION ) ) { if ( !cla.isOptionValueSet( surfacing.OUTPUT_FILE_OPTION ) ) { @@ -432,14 +466,15 @@ public class surfacing { Map individual_score_cutoffs = null; if ( cla.isOptionSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) { if ( !cla.isOptionValueSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for individual domain score cutoffs file: -" - + surfacing.CUTOFF_SCORE_FILE_OPTION + "=" ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "no value for individual domain score cutoffs file: -" + + surfacing.CUTOFF_SCORE_FILE_OPTION + "=" ); } cutoff_scores_file = new File( cla.getOptionValue( surfacing.CUTOFF_SCORE_FILE_OPTION ) ); final String error = ForesterUtil.isReadableFile( cutoff_scores_file ); if ( !ForesterUtil.isEmpty( error ) ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read individual domain score cutoffs file: " - + error ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "cannot read individual domain score cutoffs file: " + error ); } try { final BasicTable scores_table = BasicTableParser.parse( cutoff_scores_file, ' ' ); @@ -459,8 +494,8 @@ public class surfacing { File out_dir = null; if ( cla.isOptionSet( surfacing.OUTPUT_DIR_OPTION ) ) { if ( !cla.isOptionValueSet( surfacing.OUTPUT_DIR_OPTION ) ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for output directory: -" - + surfacing.OUTPUT_DIR_OPTION + "=" ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "no value for output directory: -" + surfacing.OUTPUT_DIR_OPTION + "=" ); } out_dir = new File( cla.getOptionValue( surfacing.OUTPUT_DIR_OPTION ) ); if ( out_dir.exists() && ( out_dir.listFiles().length > 0 ) ) { @@ -479,50 +514,54 @@ public class surfacing { File positive_filter_file = null; File negative_filter_file = null; File negative_domains_filter_file = null; - if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) && cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) { + if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) + && cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) { ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use both negative and positive protein filter" ); } if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) - && ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) || cla - .isOptionSet( surfacing.FILTER_POSITIVE_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" ); } if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) ) { if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_OPTION ) ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative filter: -" - + surfacing.FILTER_NEGATIVE_OPTION + "=" ); + ForesterUtil + .fatalError( surfacing.PRG_NAME, + "no value for negative filter: -" + surfacing.FILTER_NEGATIVE_OPTION + "=" ); } negative_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_OPTION ) ); final String msg = ForesterUtil.isReadableFile( negative_filter_file ); if ( !ForesterUtil.isEmpty( msg ) ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_filter_file + "\": " - + msg ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "can not read from \"" + negative_filter_file + "\": " + msg ); } } else if ( cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) { if ( !cla.isOptionValueSet( surfacing.FILTER_POSITIVE_OPTION ) ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for positive filter: -" - + surfacing.FILTER_POSITIVE_OPTION + "=" ); + ForesterUtil + .fatalError( surfacing.PRG_NAME, + "no value for positive filter: -" + surfacing.FILTER_POSITIVE_OPTION + "=" ); } positive_filter_file = new File( cla.getOptionValue( surfacing.FILTER_POSITIVE_OPTION ) ); final String msg = ForesterUtil.isReadableFile( positive_filter_file ); if ( !ForesterUtil.isEmpty( msg ) ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + positive_filter_file + "\": " - + msg ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "can not read from \"" + positive_filter_file + "\": " + msg ); } } else if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) { if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative domains filter: -" - + surfacing.FILTER_NEGATIVE_DOMAINS_OPTION + "=" ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "no value for negative domains filter: -" + + surfacing.FILTER_NEGATIVE_DOMAINS_OPTION + "=" ); } negative_domains_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_DOMAINS_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 ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "can not read from \"" + negative_domains_filter_file + "\": " + msg ); } } final List plus_minus_analysis_high_copy_base_species = new ArrayList(); @@ -530,39 +569,38 @@ public class surfacing { final List plus_minus_analysis_high_low_copy_species = new ArrayList(); final List plus_minus_analysis_numbers = new ArrayList(); 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 ); + 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 ) ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input genomes file: -" - + surfacing.INPUT_GENOMES_FILE_OPTION + "=" ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "no value for input genomes file: -" + surfacing.INPUT_GENOMES_FILE_OPTION + + "=" ); } input_genomes_file = new File( cla.getOptionValue( 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 ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "can not read from \"" + input_genomes_file + "\": " + msg ); } } else { - ForesterUtil.fatalError( surfacing.PRG_NAME, "no input genomes file given: " - + surfacing.INPUT_GENOMES_FILE_OPTION + "=" ); + ForesterUtil + .fatalError( surfacing.PRG_NAME, + "no input genomes file given: " + surfacing.INPUT_GENOMES_FILE_OPTION + "=" ); } - - - DomainSimilarity.DomainSimilarityScoring scoring = SCORING_DEFAULT; if ( cla.isOptionSet( surfacing.SCORING_OPTION ) ) { if ( !cla.isOptionValueSet( surfacing.SCORING_OPTION ) ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, - "no value 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 + ">\"" ); + ForesterUtil + .fatalError( surfacing.PRG_NAME, + "no value 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 + ">\"" ); } final String scoring_str = cla.getOptionValue( surfacing.SCORING_OPTION ); if ( scoring_str.equals( surfacing.SCORING_DOMAIN_COUNT_BASED ) ) { @@ -575,10 +613,13 @@ public class surfacing { scoring = DomainSimilarity.DomainSimilarityScoring.PROTEINS; } 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 + ">\"" ); + 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 + ">\"" ); } } boolean sort_by_species_count_first = false; @@ -606,9 +647,10 @@ public class surfacing { Detailedness detailedness = DETAILEDNESS_DEFAULT; if ( cla.isOptionSet( surfacing.DETAILEDNESS_OPTION ) ) { if ( !cla.isOptionValueSet( surfacing.DETAILEDNESS_OPTION ) ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for -" + surfacing.DETAILEDNESS_OPTION + "=<" - + surfacing.DETAILEDNESS_BASIC + "|" + surfacing.DETAILEDNESS_LIST_IDS + "|" - + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "no value for -" + surfacing.DETAILEDNESS_OPTION + "=<" + + surfacing.DETAILEDNESS_BASIC + "|" + surfacing.DETAILEDNESS_LIST_IDS + + "|" + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" ); } final String detness = cla.getOptionValue( surfacing.DETAILEDNESS_OPTION ).toLowerCase(); if ( detness.equals( surfacing.DETAILEDNESS_BASIC ) ) { @@ -621,9 +663,11 @@ public class surfacing { detailedness = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS; } else { - ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + detness + "\" for detailedness: \"-" - + surfacing.DETAILEDNESS_OPTION + "=<" + surfacing.DETAILEDNESS_BASIC + "|" - + surfacing.DETAILEDNESS_LIST_IDS + "|" + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "unknown value \"" + detness + "\" for detailedness: \"-" + + surfacing.DETAILEDNESS_OPTION + "=<" + surfacing.DETAILEDNESS_BASIC + + "|" + surfacing.DETAILEDNESS_LIST_IDS + "|" + + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" ); } } String automated_pairwise_comparison_suffix = null; @@ -655,14 +699,18 @@ public class surfacing { DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field_for_automated_pwc = DOMAIN_SORT_FILD_DEFAULT; if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) { if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "no value 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 - + ">\"" ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "no value 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 + ">\"" ); } final String sort_str = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ).toLowerCase(); if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ALPHA ) ) { @@ -702,50 +750,59 @@ public class surfacing { domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE; } 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 - + ">\"" ); - } - } - PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option = DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT; + 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 + ">\"" ); + } + } + 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: -" - + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|" - + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|" - + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" ); + ForesterUtil + .fatalError( surfacing.PRG_NAME, + "no value for print option: -" + + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|" + + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|" + + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" ); } 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: -" - + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|" - + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|" - + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" ); + ForesterUtil + .fatalError( surfacing.PRG_NAME, + "unknown value \"" + sort + "\" for print option: -" + + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|" + + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|" + + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" ); } } GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder dc_sort_order = DOMAINS_SORT_ORDER_DEFAULT; if ( cla.isOptionSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) { if ( !cla.isOptionValueSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "no value 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 + ">\"" ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "no value 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 sort = cla.getOptionValue( surfacing.DOMAIN_COUNT_SORT_OPTION ).toLowerCase(); if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_ALPHA ) ) { @@ -761,11 +818,13 @@ public class surfacing { dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.COMBINATIONS_COUNT; } 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 + ">\"" ); + 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 + ">\"" ); } } final String[][] input_file_properties = SurfacingUtil.processInputGenomesFile( input_genomes_file ); @@ -774,14 +833,15 @@ public class surfacing { ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot analyze less than two files" ); } if ( ( number_of_genomes < 3 ) && perform_pwc ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use : -" - + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION - + "= to turn on pairwise analyses with less than three input files" ); + ForesterUtil + .fatalError( surfacing.PRG_NAME, + "cannot use : -" + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION + + "= to turn on pairwise analyses with less than three input files" ); } SurfacingUtil.checkWriteabilityForPairwiseComparisons( domain_similarity_print_option, - input_file_properties, - automated_pairwise_comparison_suffix, - out_dir ); + 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 ); @@ -790,62 +850,57 @@ public class surfacing { } SurfacingUtil.checkForOutputFileWriteability( dcc_outfile ); } - File pfam_to_go_file = null; - Map> 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 + "=" ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "no value for Pfam to GO mapping file: -" + + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=" ); } 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 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> 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 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 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 + "=" ); - } - 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 + "=) without Pfam to GO mapping file (" - + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=)" ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "no value for GO OBO file: -" + surfacing.GO_OBO_FILE_USE_OPTION + "=" ); } 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 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 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 ) ) ) { @@ -854,17 +909,18 @@ public class surfacing { GoNameSpace go_namespace_limit = null; if ( cla.isOptionSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) { if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO namespace limit (-" - + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=) without Pfam to GO mapping file (" - + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=) and GO OBO file (-" - + surfacing.GO_OBO_FILE_USE_OPTION + "=)" ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "cannot use GO namespace limit (-" + surfacing.GO_NAMESPACE_LIMIT_OPTION + + "=) without Pfam to GO mapping file (" + + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=) and GO OBO file (-" + + surfacing.GO_OBO_FILE_USE_OPTION + "=)" ); } if ( !cla.isOptionValueSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "no value 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 + ">\"" ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "no value 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 + ">\"" ); } final String go_namespace_limit_str = cla.getOptionValue( surfacing.GO_NAMESPACE_LIMIT_OPTION ) .toLowerCase(); @@ -878,11 +934,12 @@ public class surfacing { go_namespace_limit = GoNameSpace.createCellularComponent(); } 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 + ">\"" ); + 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 + ">\"" ); } } if ( ( domain_similarity_sort_field == DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE ) @@ -893,14 +950,16 @@ public class surfacing { Phylogeny[] intrees = null; if ( cla.isOptionSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) { if ( number_of_genomes < 3 ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot infer gains and losses on input species trees (-" - + surfacing.INPUT_SPECIES_TREE_OPTION + " without pairwise analyses (" - + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION - + "=)" ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "cannot infer gains and losses on input species trees (-" + + surfacing.INPUT_SPECIES_TREE_OPTION + " without pairwise analyses (" + + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION + + "=)" ); } if ( !cla.isOptionValueSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input tree: -" - + surfacing.INPUT_SPECIES_TREE_OPTION + "=" ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "no value for input tree: -" + surfacing.INPUT_SPECIES_TREE_OPTION + + "=" ); } final String intrees_str = cla.getOptionValue( surfacing.INPUT_SPECIES_TREE_OPTION ); if ( intrees_str.indexOf( "#" ) > 0 ) { @@ -915,16 +974,18 @@ public class surfacing { intree_files = new File[ 1 ]; intree_files[ 0 ] = new File( intrees_str ); } - intrees = SurfacingUtil.obtainAndPreProcessIntrees( 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 ]); + 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 ) ) { if ( !cla.isOptionValueSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for random number seed: -" - + surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION + "=" ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "no value for random number seed: -" + + surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION + "=" ); } try { random_number_seed_for_fitch_parsimony = cla @@ -953,13 +1014,14 @@ public class surfacing { 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 ) { + if ( domain_length_analysis ) { SurfacingUtil.checkForOutputFileWriteability( domain_lengths_analysis_outfile ); } if ( cla.isOptionSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) { if ( !cla.isOptionValueSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for secondary features map file: -" - + surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE + "=" ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "no value for secondary features map file: -" + + surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE + "=" ); } final String[] secondary_features_map_files_strs = cla .getOptionValue( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ).split( "#" ); @@ -981,19 +1043,21 @@ public class surfacing { "cannot read secondary features map file: " + e.getMessage() ); } catch ( final Exception e ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "problem with contents of features map file [" - + secondary_features_map_files[ i ] + "]: " + e.getMessage() ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "problem with contents of features map file [" + + secondary_features_map_files[ i ] + "]: " + e.getMessage() ); } i++; } } if ( out_dir == null ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "no output directory indicated (-" - + surfacing.OUTPUT_DIR_OPTION + "=)" ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "no output directory indicated (-" + surfacing.OUTPUT_DIR_OPTION + "=)" ); } if ( output_file == null ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "no name for (main) output file indicated (-" - + surfacing.OUTPUT_FILE_OPTION + "=)" ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "no name for (main) output file indicated (-" + surfacing.OUTPUT_FILE_OPTION + + "=)" ); } if ( ( domain_id_to_go_ids_map == null ) || domain_id_to_go_ids_map.isEmpty() ) { ForesterUtil.fatalError( surfacing.PRG_NAME, @@ -1050,9 +1114,18 @@ public class surfacing { System.out.println( "Cutoff scores file : " + cutoff_scores_file ); html_desc.append( "Cutoff scores file:" + cutoff_scores_file + "" + nl ); } - if ( e_value_max >= 0.0 ) { - System.out.println( "E-value maximum (inclusive) : " + e_value_max ); - html_desc.append( "E-value maximum (inclusive):" + e_value_max + "" + nl ); + if ( ie_value_max >= 0.0 ) { + System.out.println( "iE-value maximum (incl) : " + ie_value_max ); + html_desc.append( "iE-value maximum (inclusive):" + ie_value_max + "" + nl ); + } + if ( rel_env_length_ratio_cutoff > 0.0 ) { + System.out.println( "Rel env length ratio min : " + rel_env_length_ratio_cutoff ); + html_desc.append( "Relative hmm envelope length ratio min (inclusive):" + + rel_env_length_ratio_cutoff + "" + nl ); + } + if ( fs_e_value_max >= 0.0 ) { + System.out.println( "FS E-value maximum (incl) : " + fs_e_value_max ); + html_desc.append( "FS E-value maximum (inclusive):" + fs_e_value_max + "" + 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 ); @@ -1062,13 +1135,14 @@ public class surfacing { System.out.println( "Ignore DUFs : " + ignore_dufs ); if ( ignore_virus_like_ids ) { System.out.println( "Ignore virus like ids : " + ignore_virus_like_ids ); - html_desc.append( "Ignore virus, phage, transposition related ids:" - + ignore_virus_like_ids + "" + nl ); + html_desc.append( "Ignore virus, phage, transposition related ids:" + ignore_virus_like_ids + + "" + nl ); } html_desc.append( "Ignore DUFs:" + ignore_dufs + "" + nl ); if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) { System.out.println( "Max allowed domain overlap : " + max_allowed_overlap ); - html_desc.append( "Max allowed domain overlap:" + max_allowed_overlap + "" + nl ); + html_desc + .append( "Max allowed domain overlap:" + max_allowed_overlap + "" + nl ); } if ( no_engulfing_overlaps ) { System.out.println( "Ignore engulfed domains : " + no_engulfing_overlaps ); @@ -1097,14 +1171,20 @@ public class surfacing { + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) + "" + nl ); } - System.out.println( "Use last in Fitch parimony : " + use_last_in_fitch_parsimony ); - html_desc.append( "Use last in Fitch parimon:" + use_last_in_fitch_parsimony + "" - + nl ); + System.out.println( "Fitch parsimony of DCs : " + perform_dc_fich ); + html_desc.append( "Fitch parsimony of DCs:" + perform_dc_fich + "" + nl ); + if ( perform_dc_fich ) { + System.out.println( "Use last in Fitch parsimony : " + use_last_in_fitch_parsimony ); + html_desc.append( "Use last in Fitch parsimony:" + use_last_in_fitch_parsimony + + "" + nl ); + } System.out.println( "Write to Nexus files : " + write_to_nexus ); html_desc.append( "Write to Nexus files:" + write_to_nexus + "" + nl ); - System.out.println( "DC regain prot stats : " + perform_dc_regain_proteins_stats ); - html_desc.append( "DC regain prot stats:" + perform_dc_regain_proteins_stats + "" - + nl ); + if ( perform_dc_fich ) { + System.out.println( "DC regain prot stats : " + perform_dc_regain_proteins_stats ); + html_desc.append( "DC regain prot stats:" + perform_dc_regain_proteins_stats + "" + + nl ); + } System.out.println( "DA analysis : " + da_analysis ); html_desc.append( "DA analysis :" + da_analysis + "" + nl ); System.out.print( "Domain counts sort order : " ); @@ -1283,8 +1363,8 @@ public class surfacing { html_desc.append( "counts difference" ); break; default: - ForesterUtil - .unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" ); + ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, + "unknown value for sorting for similarities" ); } System.out.println(); html_desc.append( "" + nl ); @@ -1300,7 +1380,8 @@ public class surfacing { + random_number_seed_for_fitch_parsimony + "" + nl ); System.out.println( " Random number seed : " + random_number_seed_for_fitch_parsimony ); } - if ( ( domain_id_to_secondary_features_maps != null ) && ( domain_id_to_secondary_features_maps.length > 0 ) ) { + if ( ( domain_id_to_secondary_features_maps != null ) + && ( domain_id_to_secondary_features_maps.length > 0 ) ) { for( int i = 0; i < secondary_features_map_files.length; i++ ) { html_desc.append( "Secondary features map file:" + secondary_features_map_files[ i ] + "" + nl ); @@ -1323,7 +1404,8 @@ public class surfacing { } } // if ( perform_pwc ) { System.out.println(); - html_desc.append( "Command line:\n" + cla.getCommandLineArgsAsString() + "\n" + nl ); + html_desc.append( "Command line:" + nl + nl + cla.getCommandLineArgsAsString() + nl + nl + + "" + nl ); System.out.println( "Command line : " + cla.getCommandLineArgsAsString() ); BufferedWriter[] query_domains_writer_ary = null; List[] query_domain_ids_array = null; @@ -1348,14 +1430,16 @@ public class surfacing { query_domains_writer_ary[ i ] = new BufferedWriter( new FileWriter( protein_names_writer_str ) ); } catch ( final IOException e ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "Could not open [" + protein_names_writer_str + "]: " - + e.getLocalizedMessage() ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "Could not open [" + protein_names_writer_str + "]: " + + e.getLocalizedMessage() ); } } } - SortedMap> protein_lists_per_species = null; //This will only be created if neede. + SortedMap> protein_lists_per_species = null; //This will only be created if needed. boolean need_protein_lists_per_species = false; - if ( ( plus_minus_analysis_high_copy_base_species.size() > 0 ) || output_protein_lists_for_all_domains ) { + if ( ( plus_minus_analysis_high_copy_base_species.size() > 0 ) || output_protein_lists_for_all_domains + || true ) { //TODO need_protein_lists_per_species = true; } if ( need_protein_lists_per_species ) { @@ -1370,7 +1454,6 @@ public class surfacing { all_bin_domain_combinations_gained_fitch = new ArrayList(); all_bin_domain_combinations_lost_fitch = new ArrayList(); } - 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 ); BufferedWriter per_genome_domain_promiscuity_statistics_writer = null; @@ -1383,8 +1466,8 @@ public class surfacing { per_genome_domain_promiscuity_statistics_writer.write( "Min:\t" ); per_genome_domain_promiscuity_statistics_writer.write( "Max:\t" ); per_genome_domain_promiscuity_statistics_writer.write( "N:\t" ); - per_genome_domain_promiscuity_statistics_writer.write( "Max Promiscuous Domains:" - + ForesterUtil.LINE_SEPARATOR ); + per_genome_domain_promiscuity_statistics_writer + .write( "Max Promiscuous Domains:" + ForesterUtil.LINE_SEPARATOR ); } catch ( final IOException e2 ) { ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() ); @@ -1406,8 +1489,8 @@ public class surfacing { 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 all_genomes_domains_per_potein_histo = new TreeMap(); final SortedSet domains_which_are_always_single = new TreeSet(); final SortedSet domains_which_are_sometimes_single_sometimes_not = new TreeSet(); @@ -1441,6 +1524,10 @@ public class surfacing { protein_length_stats_by_dc = new HashMap(); domain_number_stats_by_dc = new HashMap(); } + DomainLengthsTable domain_lengths_table = null; + if ( domain_length_analysis ) { + domain_lengths_table = new DomainLengthsTable(); + } // Main loop: final SortedMap> distinct_domain_architecutures_per_genome = new TreeMap>(); final SortedMap distinct_domain_architecuture_counts = new TreeMap(); @@ -1450,8 +1537,8 @@ public class surfacing { SurfacingUtil.log( ( i + 1 ) + "/" + number_of_genomes, log_writer ); System.out.println( "Processing : " + input_file_properties[ i ][ 1 ] + " [" + input_file_properties[ i ][ 0 ] + "]" ); - SurfacingUtil.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 ) { @@ -1482,8 +1569,14 @@ public class surfacing { 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 ); + } + if ( rel_env_length_ratio_cutoff > 0.0 ) { + parser.setRelEnvLengthRatioCutoff( rel_env_length_ratio_cutoff ); } parser.setIgnoreDufs( ignore_dufs ); parser.setIgnoreVirusLikeIds( ignore_virus_like_ids ); @@ -1522,57 +1615,73 @@ public class surfacing { distinct_domain_architecuture_counts ); } System.out.println( "Number of proteins encountered : " + parser.getProteinsEncountered() ); - SurfacingUtil.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() ); SurfacingUtil.log( "Number of proteins stored : " + protein_list.size(), log_writer ); System.out.println( "Coverage : " + ForesterUtil.roundToInt( 100.0 * coverage ) + "%" ); - SurfacingUtil.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() ); - SurfacingUtil.log( "Domains encountered : " + parser.getDomainsEncountered(), log_writer ); + SurfacingUtil.log( "Domains encountered : " + parser.getDomainsEncountered(), + log_writer ); System.out.println( "Domains stored : " + parser.getDomainsStored() ); - SurfacingUtil.log( "Domains stored : " + parser.getDomainsStored(), log_writer ); + SurfacingUtil.log( "Domains stored : " + parser.getDomainsStored(), + log_writer ); System.out.println( "Distinct domains stored : " + parser.getDomainsStoredSet().size() ); - SurfacingUtil.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() ); SurfacingUtil.log( "Domains ignored due to individual score cutoffs: " - + parser.getDomainsIgnoredDueToIndividualScoreCutoff(), - log_writer ); - System.out.println( "Domains ignored due to E-value : " - + parser.getDomainsIgnoredDueToEval() ); - SurfacingUtil.log( "Domains ignored due to E-value : " + parser.getDomainsIgnoredDueToEval(), log_writer ); + + 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 rel env length ratio : " + + parser.getDomainsIgnoredDueToRelEnvLengthRatioCutoff() ); + SurfacingUtil.log( "Domains ignored due to rel env length ratio : " + + parser.getDomainsIgnoredDueToRelEnvLengthRatioCutoff(), log_writer ); System.out.println( "Domains ignored due to DUF designation : " + parser.getDomainsIgnoredDueToDuf() ); - SurfacingUtil.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() ); - SurfacingUtil.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() ); SurfacingUtil.log( "Domains ignored due negative domain filter : " - + parser.getDomainsIgnoredDueToNegativeDomainFilter(), - log_writer ); + + parser.getDomainsIgnoredDueToNegativeDomainFilter(), log_writer ); System.out.println( "Domains ignored due to overlap : " + parser.getDomainsIgnoredDueToOverlap() ); - SurfacingUtil.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() ); - SurfacingUtil.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() ); - SurfacingUtil.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 ); @@ -1583,8 +1692,8 @@ public class surfacing { try { int count = 0; for( final Protein protein : protein_list ) { - dc_data_writer.write( SurfacingUtil.proteinToDomainCombinations( protein, count + "", "\t" ) - .toString() ); + dc_data_writer + .write( SurfacingUtil.proteinToDomainCombinations( protein, count + "", "\t" ).toString() ); ++count; for( final Domain d : protein.getProteinDomains() ) { final String d_str = d.getDomainId().toString(); @@ -1606,23 +1715,26 @@ public class surfacing { 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 ) ); + 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 ) ); 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, @@ -1661,9 +1773,36 @@ public class surfacing { } System.gc(); } // for( int i = 0; i < number_of_genomes; ++i ) { - ForesterUtil.programMessage( PRG_NAME, "Wrote domain promiscuities to: " - + per_genome_domain_promiscuity_statistics_file ); - // + ForesterUtil + .programMessage( PRG_NAME, + "Wrote domain promiscuities to: " + per_genome_domain_promiscuity_statistics_file ); + final int LEVEL = 0; + try { + MinimalDomainomeCalculator.calc( false, + intrees[ 0 ], + LEVEL, + protein_lists_per_species, + SEPARATOR_FOR_DA, + -1, + out_dir.toString() + "/" + output_file, + true ); + } + catch ( IOException e ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() ); + } + try { + MinimalDomainomeCalculator.calc( true, + intrees[ 0 ], + LEVEL, + protein_lists_per_species, + SEPARATOR_FOR_DA, + -1, + out_dir.toString() + "/" + output_file, + true ); + } + catch ( IOException e ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() ); + } if ( da_analysis ) { SurfacingUtil.performDomainArchitectureAnalysis( distinct_domain_architecutures_per_genome, distinct_domain_architecuture_counts, @@ -1681,10 +1820,13 @@ public class surfacing { domains_per_potein_stats_writer.write( "\t" ); domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.arithmeticMean() + "" ); 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( all_genomes_domains_per_potein_stats.sampleStandardDeviation() + "" ); 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() + "" ); @@ -1692,26 +1834,46 @@ public class surfacing { 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(); + 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" ); - ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file - + "_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" ); - ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file - + "_domains_always_combined.txt" ), domains_which_never_single, "\n" ); + 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" ); + ForesterUtil.collection2file( + new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + + "_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" ); + ForesterUtil.collection2file( + new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + + "_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() ) + "% (+/-" + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)" ); - ForesterUtil.programMessage( PRG_NAME, "Range of proteins with a least one domain assigned: " + ForesterUtil.programMessage( PRG_NAME, + "Range of proteins with a least one domain assigned: " + + ( 100 * protein_coverage_stats.getMin() ) + "%-" + + ( 100 * protein_coverage_stats.getMax() ) + "%" ); + 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() ) - + "%" ); - 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 ); + + "%", log_writer ); + protein_coverage_stats = null; } catch ( final IOException e2 ) { ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() ); @@ -1734,7 +1896,7 @@ public class surfacing { 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, @@ -1754,7 +1916,8 @@ public class surfacing { final DomainSimilarityCalculator calc = new BasicDomainSimilarityCalculator( domain_similarity_sort_field, sort_by_species_count_first, number_of_genomes == 2, - CALC_SIMILARITY_SCORES ); + CALC_SIMILARITY_SCORES, + true ); switch ( scoring ) { case COMBINATIONS: pw_calc = new CombinationsBasedPairwiseDomainSimilarityCalculator(); @@ -1772,11 +1935,10 @@ public class surfacing { if ( domain_id_to_go_ids_map != null ) { go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.ALL; } - final SortedSet similarities = calc - .calculateSimilarities( pw_calc, - gwcd_list, - ignore_domains_without_combs_in_all_spec, - ignore_species_specific_domains ); + final SortedSet similarities = calc.calculateSimilarities( pw_calc, + gwcd_list, + ignore_domains_without_combs_in_all_spec, + ignore_species_specific_domains ); SurfacingUtil.decoratePrintableDomainSimilarities( similarities, detailedness ); final Map tax_code_to_id_map = SurfacingUtil.createTaxCodeToIdMap( intrees[ 0 ] ); try { @@ -1810,7 +1972,7 @@ public class surfacing { + "" + nl ); html_desc.append( "" + nl ); final Writer simple_tab_writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR - + my_outfile + ".tsv" ) ); + + my_outfile.replaceFirst( ".html", ".tsv" ) ) ); SurfacingUtil.writeDomainSimilaritiesToFile( html_desc, new StringBuilder( number_of_genomes + " genomes" ), simple_tab_writer, @@ -1823,14 +1985,19 @@ public class surfacing { scoring, true, tax_code_to_id_map, - intree_0_orig ); + 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 ) + "\"" ); + ForesterUtil.programMessage( surfacing.PRG_NAME, + "Wrote main output (includes domain similarities) to: \"" + + ( out_dir == null ? my_outfile + : out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) + + "\"" ); } catch ( final IOException e ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "Failed to write similarites to: \"" + output_file + "\" [" - + e.getMessage() + "]" ); + ForesterUtil + .fatalError( surfacing.PRG_NAME, + "Failed to write similarites to: \"" + output_file + "\" [" + e.getMessage() + "]" ); } System.out.println(); final Species[] species = new Species[ number_of_genomes ]; @@ -1872,24 +2039,32 @@ public class surfacing { matrix_output_file = out_dir + ForesterUtil.FILE_SEPARATOR + matrix_output_file; 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() ); - SurfacingUtil - .writeMatrixToFile( new File( matrix_output_file - + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ), - pwgc.getSharedBinaryCombinationsBasedDistances() ); - SurfacingUtil.writeMatrixToFile( new File( matrix_output_file + SurfacingUtil.writeMatrixToFile( + new File( matrix_output_file + + 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() ); + SurfacingUtil.writeMatrixToFile( + new File( matrix_output_file + 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 ) ); - 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 ) ); - 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_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 ) ); + final Phylogeny nj_d = SurfacingUtil.createNjTreeBasedOnMatrixToFile( + new File( matrix_output_file + + surfacing.NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ), + pwgc.getSharedDomainsBasedDistances() + .get( 0 ) ); inferred_trees = new ArrayList(); inferred_trees.add( nj_gd ); inferred_trees.add( nj_bc ); @@ -1903,11 +2078,12 @@ public class surfacing { } if ( ( ( intrees != null ) && ( intrees.length > 0 ) ) && ( number_of_genomes > 2 ) ) { final StringBuilder parameters_sb = SurfacingUtil.createParametersAsString( ignore_dufs, - e_value_max, - max_allowed_overlap, - no_engulfing_overlaps, - cutoff_scores_file, - dc_type ); + 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 + "_"; @@ -1916,8 +2092,8 @@ public class surfacing { for( final Phylogeny intree : intrees ) { final String outfile_name = ForesterUtil.removeSuffix( output_file.toString() ) + s + ForesterUtil.removeSuffix( intree_files[ i ].toString() ); - final DomainParsimonyCalculator domain_parsimony = DomainParsimonyCalculator.createInstance( intree, - gwcd_list ); + final DomainParsimonyCalculator domain_parsimony = DomainParsimonyCalculator + .createInstance( intree, gwcd_list ); SurfacingUtil.executeParsimonyAnalysis( random_number_seed_for_fitch_parsimony, radomize_fitch_parsimony, outfile_name, @@ -1938,8 +2114,9 @@ public class surfacing { 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. + 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; @@ -1947,15 +2124,13 @@ public class surfacing { final Map mapping_results_map = new TreeMap(); 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 ); + SurfacingUtil.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:" ); @@ -1982,30 +2157,32 @@ public class surfacing { } if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) { 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 ); + 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 ) { SurfacingUtil.writeProteinListsForAllSpecies( out_dir, - protein_lists_per_species, - gwcd_list, - output_list_of_all_proteins_per_domain_e_value_max ); + 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 { - 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 ); + 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() ); @@ -2013,12 +2190,13 @@ public class surfacing { } if ( all_bin_domain_combinations_lost_fitch != null ) { try { - 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 ); + 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() ); @@ -2027,13 +2205,17 @@ public class surfacing { final Runtime rt = java.lang.Runtime.getRuntime(); 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" ); + ForesterUtil.programMessage( PRG_NAME, + "Time for analysis : " + ( new Date().getTime() - analysis_start_time ) + "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" ); + ForesterUtil + .programMessage( PRG_NAME, + "Free memory : " + free_memory + "MB, total memory: " + total_memory + "MB" ); ForesterUtil.programMessage( PRG_NAME, "If this application is useful to you, please cite:" ); ForesterUtil.programMessage( PRG_NAME, surfacing.WWW ); + ForesterUtil + .programMessage( PRG_NAME, + "[next step for phylogenomic analysis pipeline (example, in \"DAS\" dir): % mse.rb .prot . FL_seqs DA_seqs path/to/genome_locations.txt]" ); ForesterUtil.programMessage( PRG_NAME, "OK" ); System.out.println(); } @@ -2054,21 +2236,21 @@ public class surfacing { + DETAILEDNESS_DEFAULT + ")" ); System.out.println( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION + ": 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)" ); - 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)" ); + 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)" ); + 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)" ); System.out.println( surfacing.NOT_IGNORE_DUFS_OPTION + ": 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_'" ); + System.out.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.MIN_REL_ENV_LENGTH_RATIO_OPTION + + ": min (inclusive) relative envelope length ratio" ); 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" ); @@ -2088,9 +2270,8 @@ public class surfacing { + "[=]: to perform pairwise comparison based analyses" ); System.out.println( surfacing.INPUT_SPECIES_TREE_OPTION + ": species tree, to perform (Dollo, Fitch) parismony analyses" ); - System.out - .println( surfacing.INPUT_SPECIES_TREE_OPTION - + "=: to infer domain/binary domain combination gains/losses on given species trees" ); + System.out.println( surfacing.INPUT_SPECIES_TREE_OPTION + + "=: to infer domain/binary domain combination gains/losses on given species trees" ); System.out.println( surfacing.FILTER_POSITIVE_OPTION + "=: to filter out proteins not containing at least one domain listed in " ); System.out.println( surfacing.FILTER_NEGATIVE_OPTION @@ -2098,19 +2279,19 @@ public class surfacing { System.out.println( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION + "=: to filter out (ignore) domains listed in " ); System.out.println( surfacing.INPUT_GENOMES_FILE_OPTION + "=: to read input files from " ); - System.out - .println( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION - + "=: seed for random number generator for Fitch Parsimony analysis (type: long, default: no randomization - given a choice, prefer absence" ); + System.out.println( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION + + "=: 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" ); System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY + ": to consider directedness and adjacency in binary combinations" ); - System.out - .println( surfacing.SEQ_EXTRACT_OPTION - + "=: 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.SEQ_EXTRACT_OPTION + + "=: 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 + "=: to perfom parsimony analysis on secondary features" ); System.out.println( surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=: 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" ); System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS + ": to output all proteins per domain" ); @@ -2118,19 +2299,23 @@ public class surfacing { + ": 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(); + 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 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( "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(); + System.out + .println( "Example 3: surfacing -species_tree=master_tree.xml -no_eo -ie=1e-6 -mrel=0.5 -mo=10 -dufs -genomes=genomes.txt -out_dir=a605 -o=a605" ); 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( "[next step for phylogenomic analysis pipeline (example, in \"DAS\" dir): % mse.rb .prot . FL_seqs DA_seqs path/to/genome_locations.txt]" ); System.out.println(); } }