X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=forester%2Fjava%2Fsrc%2Forg%2Fforester%2Fapplication%2Fsurfacing.java;h=fc87a9686df8ee10eca0cf2d1d47e2e947b7c211;hb=8298cc0323b6f4d4a905f31512f0b3adcc76f925;hp=2b5c7c4de89636f694bb760dbfd42224190fed21;hpb=10297bd8b8a4b4ab198a17a42fc6ff24ae2ed49b;p=jalview.git diff --git a/forester/java/src/org/forester/application/surfacing.java b/forester/java/src/org/forester/application/surfacing.java index 2b5c7c4..fc87a96 100644 --- a/forester/java/src/org/forester/application/surfacing.java +++ b/forester/java/src/org/forester/application/surfacing.java @@ -71,6 +71,7 @@ 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.ProteinCountsBasedPairwiseDomainSimilarityCalculator; @@ -174,6 +175,7 @@ public class surfacing { 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"; @@ -215,9 +217,9 @@ public class surfacing { final static private String INPUT_GENOMES_FILE_OPTION = "genomes"; final static private String INPUT_SPECIES_TREE_OPTION = "species_tree"; final static private String SEQ_EXTRACT_OPTION = "prot_extract"; - final static private String PRG_VERSION = "2.404"; - final static private String PRG_DATE = "140709"; - final static private String E_MAIL = "czmasek@burnham.org"; + final static private String 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; @@ -270,7 +272,9 @@ public class surfacing { 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(); @@ -306,6 +310,7 @@ public class surfacing { allowed_options.add( surfacing.NOT_IGNORE_DUFS_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 ); @@ -350,6 +355,7 @@ public class surfacing { boolean ignore_combination_with_same = surfacing.IGNORE_COMBINATION_WITH_SAME_DEFAULLT; 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 ) { @@ -391,6 +397,14 @@ public class surfacing { 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 ); @@ -434,8 +448,9 @@ public class surfacing { 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 ) ) { @@ -451,14 +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, ' ' ); @@ -478,8 +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 ) ) { @@ -498,50 +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" ); + .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(); @@ -556,29 +576,31 @@ public class surfacing { 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 ) ) { @@ -591,10 +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; @@ -622,9 +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 ) ) { @@ -637,9 +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; @@ -660,10 +688,10 @@ public class surfacing { if ( cla.isOptionSet( surfacing.SEQ_EXTRACT_OPTION ) ) { if ( !cla.isOptionValueSet( surfacing.SEQ_EXTRACT_OPTION ) ) { ForesterUtil - .fatalError( surfacing.PRG_NAME, - "no domain ids given for sequences with given domains to be extracted : -" - + surfacing.SEQ_EXTRACT_OPTION - + "=" ); + .fatalError( surfacing.PRG_NAME, + "no domain ids given for sequences with given domains to be extracted : -" + + surfacing.SEQ_EXTRACT_OPTION + + "=" ); } query_domain_ids = cla.getOptionValue( surfacing.SEQ_EXTRACT_OPTION ); } @@ -671,14 +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 ) ) { @@ -718,24 +750,30 @@ 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 - + ">\"" ); + 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 ) ) { @@ -748,20 +786,23 @@ public class surfacing { 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 ) ) { @@ -777,11 +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 ); @@ -790,9 +833,10 @@ 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, @@ -809,8 +853,9 @@ public class surfacing { 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 ) ); } @@ -826,7 +871,7 @@ public class surfacing { 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()" ); + "parser.getMappingCount() < domain_id_to_go_ids_map.size()" ); } domain_id_to_go_ids_count = parser.getMappingCount(); } @@ -836,8 +881,8 @@ public class surfacing { 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 + "=" ); + 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 ) ); } @@ -864,17 +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(); @@ -888,11 +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 ) @@ -903,14 +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 ) { @@ -925,15 +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 ] ); 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 @@ -961,14 +1013,15 @@ public class surfacing { Map>[] domain_id_to_secondary_features_maps = null; File[] secondary_features_map_files = null; final File domain_lengths_analysis_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file - + DOMAIN_LENGTHS_ANALYSIS_SUFFIX ); + + DOMAIN_LENGTHS_ANALYSIS_SUFFIX ); 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( "#" ); @@ -990,19 +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, @@ -1020,21 +1075,21 @@ public class surfacing { if ( positive_filter_file != null ) { final int filter_size = filter.size(); System.out.println( "Positive protein filter : " + positive_filter_file + " [" + filter_size - + " domain ids]" ); + + " domain ids]" ); html_desc.append( "Positive protein filter:" + positive_filter_file + " [" + filter_size - + " domain ids]" + nl ); + + " domain ids]" + nl ); } if ( negative_filter_file != null ) { final int filter_size = filter.size(); System.out.println( "Negative protein filter : " + negative_filter_file + " [" + filter_size - + " domain ids]" ); + + " domain ids]" ); html_desc.append( "Negative protein filter:" + negative_filter_file + " [" + filter_size - + " domain ids]" + nl ); + + " domain ids]" + nl ); } if ( negative_domains_filter_file != null ) { final int filter_size = filter.size(); System.out.println( "Negative domain filter : " + negative_domains_filter_file + " [" + filter_size - + " domain ids]" ); + + " domain ids]" ); html_desc.append( "Negative domain filter:" + negative_domains_filter_file + " [" + filter_size + " domain ids]" + nl ); } @@ -1053,7 +1108,7 @@ public class surfacing { } System.out.println( "Plus-minus analysis : " + plus1 + "&& " + plus0 + "&& " + minus ); html_desc.append( "Plus-minus analysis:" + plus1 + "&& " + plus0 + "&& " + minus - + "" + nl ); + + "" + nl ); } if ( cutoff_scores_file != null ) { System.out.println( "Cutoff scores file : " + cutoff_scores_file ); @@ -1063,6 +1118,11 @@ public class surfacing { 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 ); @@ -1075,27 +1135,28 @@ 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 ); html_desc.append( "Ignore (lower confidence) engulfed domains:" + no_engulfing_overlaps - + "" + nl ); + + "" + nl ); } System.out.println( "Ignore singlet domains : " + ignore_domains_without_combs_in_all_spec ); html_desc - .append( "Ignore singlet domains for domain combination similarity analyses (not for parsimony analyses):" - + ignore_domains_without_combs_in_all_spec + "" + nl ); + .append( "Ignore singlet domains for domain combination similarity analyses (not for parsimony analyses):" + + ignore_domains_without_combs_in_all_spec + "" + nl ); System.out.println( "Ignore species specific doms: " + ignore_species_specific_domains ); html_desc - .append( "Ignore species specific domains for domain combination similarity analyses (not for parsimony analyses):" - + ignore_species_specific_domains + "" + nl ); + .append( "Ignore species specific domains for domain combination similarity analyses (not for parsimony analyses):" + + ignore_species_specific_domains + "" + nl ); System.out.println( "Ignore combination with self: " + ignore_combination_with_same ); html_desc.append( "Ignore combination with self for domain combination similarity analyses:" + ignore_combination_with_same + "" + nl ); @@ -1115,14 +1176,14 @@ public class surfacing { 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 ); + + "" + nl ); } System.out.println( "Write to Nexus files : " + write_to_nexus ); html_desc.append( "Write to Nexus files:" + write_to_nexus + "" + 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 ); + 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 ); @@ -1150,7 +1211,7 @@ public class surfacing { } if ( domain_id_to_go_ids_map != null ) { System.out.println( "Pfam to GO mappings from : " + pfam_to_go_file + " [" + domain_id_to_go_ids_count - + " mappings]" ); + + " mappings]" ); html_desc.append( "Pfam to GO mappings from:" + pfam_to_go_file + " [" + domain_id_to_go_ids_count + " mappings]" + "" + nl ); } @@ -1166,7 +1227,7 @@ public class surfacing { if ( perform_pwc ) { System.out.println( "Suffix for PWC files : " + automated_pairwise_comparison_suffix ); html_desc.append( "Suffix for PWC files" + automated_pairwise_comparison_suffix - + "" + nl ); + + "" + nl ); } if ( out_dir != null ) { System.out.println( "Output directory : " + out_dir ); @@ -1302,15 +1363,15 @@ 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 ); if ( ( intrees != null ) && ( intrees.length > 0 ) ) { for( final File intree_file : intree_files ) { html_desc.append( "Intree for gain/loss parsimony analysis:" + intree_file - + "" + nl ); + + "" + nl ); System.out.println( " Intree for gain/loss pars.: " + intree_file ); } } @@ -1319,7 +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 ); @@ -1343,7 +1405,7 @@ public class surfacing { } // if ( perform_pwc ) { System.out.println(); html_desc.append( "Command line:" + nl + nl + cla.getCommandLineArgsAsString() + nl + nl - + "" + nl ); + + "" + nl ); System.out.println( "Command line : " + cla.getCommandLineArgsAsString() ); BufferedWriter[] query_domains_writer_ary = null; List[] query_domain_ids_array = null; @@ -1368,14 +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 ) { @@ -1391,7 +1455,7 @@ public class surfacing { all_bin_domain_combinations_lost_fitch = new ArrayList(); } final File per_genome_domain_promiscuity_statistics_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR - + output_file + D_PROMISCUITY_FILE_SUFFIX ); + + output_file + D_PROMISCUITY_FILE_SUFFIX ); BufferedWriter per_genome_domain_promiscuity_statistics_writer = null; try { per_genome_domain_promiscuity_statistics_writer = new BufferedWriter( new FileWriter( per_genome_domain_promiscuity_statistics_file ) ); @@ -1402,8 +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() ); @@ -1434,7 +1498,7 @@ public class surfacing { BufferedWriter domains_per_potein_stats_writer = null; try { domains_per_potein_stats_writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR - + output_file + "_domains_per_potein_stats.txt" ) ); + + output_file + "_domains_per_potein_stats.txt" ) ); domains_per_potein_stats_writer.write( "Genome" ); domains_per_potein_stats_writer.write( "\t" ); domains_per_potein_stats_writer.write( "Mean" ); @@ -1511,6 +1575,9 @@ public class surfacing { 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 ); parser.setIgnoreEngulfedDomains( no_engulfing_overlaps ); @@ -1555,8 +1622,7 @@ public class surfacing { System.out.println( "Coverage : " + ForesterUtil.roundToInt( 100.0 * coverage ) + "%" ); SurfacingUtil.log( "Coverage : " - + ForesterUtil.roundToInt( 100.0 * coverage ) + "%", - log_writer ); + + ForesterUtil.roundToInt( 100.0 * coverage ) + "%", log_writer ); System.out.println( "Domains encountered : " + parser.getDomainsEncountered() ); SurfacingUtil.log( "Domains encountered : " + parser.getDomainsEncountered(), log_writer ); @@ -1565,58 +1631,57 @@ public class surfacing { 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 ); + + 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 ); + 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 ); + 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 ); + + 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 ); + + 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 ); + + parser.getProteinsIgnoredDueToFilter(), log_writer ); } if ( da_analysis ) { System.out.println( "Distinct domain architectures stored : " + distinct_das ); @@ -1627,8 +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(); @@ -1654,23 +1719,21 @@ public class surfacing { 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 ) { 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 ); + 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, @@ -1710,17 +1773,44 @@ 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, 10, new File( out_dir.toString() + "/" + output_file - + "_DA_counts.txt" ), - new File( out_dir.toString() + "/" + output_file - + "_unique_DAs.txt" ) ); + + "_DA_counts.txt" ), + new File( out_dir.toString() + "/" + output_file + + "_unique_DAs.txt" ) ); distinct_domain_architecutures_per_genome.clear(); distinct_domain_architecuture_counts.clear(); System.gc(); @@ -1730,7 +1820,8 @@ 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( 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() + "" ); @@ -1745,29 +1836,43 @@ public class surfacing { 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: " - + ( 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 ); + 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() ) + "%", - log_writer ); + + ( 100 * protein_coverage_stats.getMin() ) + "%-" + ( 100 * protein_coverage_stats.getMax() ) + + "%", log_writer ); protein_coverage_stats = null; } catch ( final IOException e2 ) { @@ -1830,11 +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 { @@ -1862,13 +1966,13 @@ public class surfacing { html_desc.append( "Sum of all distinct binary combinations:" + all_bin_domain_combinations_encountered.size() + "" + nl ); html_desc.append( "Sum of all distinct domains:" + all_domains_encountered.size() - + "" + nl ); + + "" + nl ); html_desc.append( "Analysis date/time:" + new java.text.SimpleDateFormat( "yyyy.MM.dd HH:mm:ss" ).format( new java.util.Date() ) + "" + 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, @@ -1884,12 +1988,16 @@ public class surfacing { 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 ]; @@ -1931,24 +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 - + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ), - pwgc.getSharedDomainsBasedDistances() ); + 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 ); @@ -1976,8 +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, @@ -1989,17 +2105,17 @@ public class surfacing { parameters_sb.toString(), domain_id_to_secondary_features_maps, positive_filter_file == null ? null : filter, - output_binary_domain_combinationsfor_graph_analysis, - all_bin_domain_combinations_gained_fitch, - all_bin_domain_combinations_lost_fitch, - dc_type, - protein_length_stats_by_dc, - domain_number_stats_by_dc, - domain_length_stats_by_domain, - tax_code_to_id_map, - write_to_nexus, - use_last_in_fitch_parsimony, - perform_dc_fich ); + output_binary_domain_combinationsfor_graph_analysis, + all_bin_domain_combinations_gained_fitch, + all_bin_domain_combinations_lost_fitch, + dc_type, + protein_length_stats_by_dc, + domain_number_stats_by_dc, + domain_length_stats_by_domain, + tax_code_to_id_map, + write_to_nexus, + use_last_in_fitch_parsimony, + perform_dc_fich ); // Listing of all domain combinations gained is only done if only one input tree is used. if ( ( domain_id_to_secondary_features_maps != null ) && ( domain_id_to_secondary_features_maps.length > 0 ) ) { @@ -2008,15 +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:" ); @@ -2062,13 +2176,13 @@ public class surfacing { 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() ); @@ -2076,13 +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() ); @@ -2091,13 +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(); } @@ -2107,33 +2225,32 @@ public class surfacing { System.out.println( "Usage:" ); System.out.println(); System.out.println( "% java -Xms256m -Xmx512m -cp forester.jar org.forester.applications." + surfacing.PRG_NAME - + " [options] [external node name 1] [name 2] ... [name n]" ); + + " [options] [external node name 1] [name 2] ... [name n]" ); System.out.println(); System.out.println( " Note: This software might need a significant amount of memory (heap space);" ); System.out - .println( " hence use \"-Xms128m -Xmx512m\" (or more) to prevent a \"java.lang.OutOfMemoryError\"." ); + .println( " hence use \"-Xms128m -Xmx512m\" (or more) to prevent a \"java.lang.OutOfMemoryError\"." ); System.out.println(); System.out.println( " Options: " ); System.out.println( surfacing.DETAILEDNESS_OPTION + ": level of detail for similarities output file (default:" + DETAILEDNESS_DEFAULT + ")" ); System.out.println( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION - + ": to ignore combinations with self (default: not to ignore)" ); - 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)" ); + + ": 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.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_'" ); + + ": 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.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_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" ); @@ -2144,45 +2261,42 @@ public class surfacing { + DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT + ")" ); System.out.println( surfacing.CUTOFF_SCORE_FILE_OPTION + ": cutoff score file" ); System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION - + ": sort by species count first" ); + + ": sort by species count first" ); System.out.println( surfacing.OUTPUT_DIR_OPTION + ": output directory" ); System.out.println( surfacing.PFAM_TO_GO_FILE_USE_OPTION + ": Pfam to GO mapping file" ); System.out.println( surfacing.GO_OBO_FILE_USE_OPTION + ": GO terms file (OBO format)" ); System.out.println( surfacing.GO_NAMESPACE_LIMIT_OPTION + ": limit GO term to one GO namespace" ); System.out.println( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION - + "[=]: to perform pairwise comparison based analyses" ); + + "[=]: 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" ); + + ": 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.FILTER_POSITIVE_OPTION - + "=: to filter out proteins not containing at least one domain listed in " ); + + "=: to filter out proteins not containing at least one domain listed in " ); System.out.println( surfacing.FILTER_NEGATIVE_OPTION - + "=: to filter out proteins containing at least one domain listed in " ); + + "=: to filter out proteins containing at least one domain listed in " ); System.out.println( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION - + "=: to filter out (ignore) domains listed in " ); + + "=: 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" ); + + ": 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')" ); + + ": 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.SECONDARY_FEATURES_PARSIMONY_MAP_FILE - + "=: to perfom parsimony analysis on secondary features" ); + + "=: 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)" ); + + ": to output binary domain counts (as individual files)" ); System.out.println( surfacing.DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS - + ": to output binary domain combinations for (downstream) graph analysis" ); + + ": to output binary domain combinations for (downstream) graph analysis" ); System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS + ": to output all proteins per domain" ); System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION - + ": e value max per domain for output of all proteins per domain" ); + + ": e value max per domain for output of all proteins per domain" ); System.out.println( surfacing.USE_LAST_IN_FITCH_OPTION + ": to use last in Fitch parsimony" ); System.out.println( surfacing.WRITE_TO_NEXUS_OPTION + ": to output in Nexus format" ); System.out.println( PERFORM_DC_FITCH + ": to perform DC Fitch parsimony" ); @@ -2192,10 +2306,16 @@ public class surfacing { 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" ); + .println( "Example 1: surfacing -p2g=pfam2go.txt -obo=go.obo -species_tree=tol_156.xml -no_eo -ie=0.01 -dufs -genomes=genomes_all.txt -pos_filter=tf_1.txt -out_dir=_tf1 -o=tf1" ); + System.out.println(); + System.out + .println( "Example 2: surfacing -p2g=pfam2go.txt -obo=go.obo -species_tree=tol_156.xml -last -ignore_viral_ids -no_eo -ie=0.1 -dufs -genomes=genomes_all.txt -pos_filter=tf_1.txt -all_prot -all_prot_e=0.1 -out_dir=_tf1_e01_ape01 -o=tf1_e01_ape01" ); + System.out.println(); + 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: 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" ); + .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(); } }