// Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
//
// Contact: phylosoft @ gmail . com
-// WWW: www.phylosoft.org/forester
+// WWW: https://sites.google.com/site/cmzmasek/home/software/forester
package org.forester.application;
import java.util.TreeMap;
import java.util.TreeSet;
-import org.forester.evoinference.distance.NeighborJoining;
import org.forester.evoinference.matrix.character.CharacterStateMatrix.Format;
-import org.forester.evoinference.matrix.distance.DistanceMatrix;
import org.forester.go.GoId;
import org.forester.go.GoNameSpace;
import org.forester.go.GoTerm;
import org.forester.go.PfamToGoParser;
import org.forester.io.parsers.HmmscanPerDomainTableParser;
import org.forester.io.parsers.HmmscanPerDomainTableParser.INDIVIDUAL_SCORE_CUTOFF;
+import org.forester.io.parsers.phyloxml.PhyloXmlUtil;
import org.forester.io.parsers.util.ParserUtils;
-import org.forester.io.writers.PhylogenyWriter;
import org.forester.phylogeny.Phylogeny;
import org.forester.phylogeny.PhylogenyMethods;
import org.forester.phylogeny.PhylogenyNode;
import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
import org.forester.protein.BinaryDomainCombination;
-import org.forester.protein.DomainId;
+import org.forester.protein.Domain;
import org.forester.protein.Protein;
import org.forester.species.BasicSpecies;
import org.forester.species.Species;
final static private String MAX_ALLOWED_OVERLAP_OPTION = "mo";
final static private String NO_ENGULFING_OVERLAP_OPTION = "no_eo";
final static private String IGNORE_COMBINATION_WITH_SAME_OPTION = "ignore_self_comb";
+ final static private String PERFORM_DC_REGAIN_PROTEINS_STATS_OPTION = "dc_regain_stats";
+ final static private String DA_ANALYSIS_OPTION = "DA_analyis";
+ final static private String USE_LAST_IN_FITCH_OPTION = "last";
final static private String PAIRWISE_DOMAIN_COMPARISONS_PREFIX = "pwc_";
final static private String PAIRWISE_DOMAIN_COMPARISONS_OPTION = "pwc";
final static private String OUTPUT_FILE_OPTION = "o";
+ 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 JACKNIFE_OPTION = "jack";
- final static private String JACKNIFE_RANDOM_SEED_OPTION = "seed";
- final static private String JACKNIFE_RATIO_OPTION = "jack_ratio";
- private static final int JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT = 100;
- final static private long JACKNIFE_RANDOM_SEED_DEFAULT = 19;
- final static private double JACKNIFE_RATIO_DEFAULT = 0.5;
- //final static private String INFER_SPECIES_TREES_OPTION = "species_tree_inference";
- final static private String INFERRED_SD_BASED_NJ_SPECIES_TREE_SUFFIX = "_sd_nj.nh";
- final static private String INFERRED_SBC_BASED_NJ_SPECIES_TREE_SUFFIX = "_sbc_nj.nh";
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_FILES_FROM_FILE_OPTION = "input";
+ 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 char SEPARATOR_FOR_INPUT_VALUES = '#';
- final static private String PRG_VERSION = "2.240";
- final static private String PRG_DATE = "2012.05.04";
+ final static private String PRG_VERSION = "2.280";
+ final static private String PRG_DATE = "130701";
final static private String E_MAIL = "czmasek@burnham.org";
final static private String WWW = "www.phylosoft.org/forester/applications/surfacing";
final static private boolean IGNORE_DUFS_DEFAULT = true;
private static final String PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_all.txt";
private static final String PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_passing.txt";
private static final String OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS = "all_prot";
+ final static private String OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION = "all_prot_e";
private static final boolean VERBOSE = false;
private static final String OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_gains_counts";
private static final String OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_losses_counts";
private static final String 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 INDIVIDUAL_SCORE_CUTOFF INDIVIDUAL_SCORE_CUTOFF_DEFAULT = INDIVIDUAL_SCORE_CUTOFF.FULL_SEQUENCE;
+ 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";
final Writer out = ForesterUtil.createBufferedWriter( output_file );
final SortedMap<Object, Integer> bdc_to_counts = ForesterUtil
.listToSortedCountsMap( all_bin_domain_combinations_changed );
- final SortedSet<DomainId> all_domains_in_combination_changed_more_than_once = new TreeSet<DomainId>();
- final SortedSet<DomainId> all_domains_in_combination_changed_only_once = new TreeSet<DomainId>();
+ final SortedSet<String> all_domains_in_combination_changed_more_than_once = new TreeSet<String>();
+ final SortedSet<String> all_domains_in_combination_changed_only_once = new TreeSet<String>();
int above_one = 0;
int one = 0;
for( final Object bdc_object : bdc_to_counts.keySet() ) {
final List<String> plus_minus_analysis_low_copy,
final List<GenomeWideCombinableDomains> gwcd_list,
final SortedMap<Species, List<Protein>> protein_lists_per_species,
- final Map<DomainId, List<GoId>> domain_id_to_go_ids_map,
+ final Map<String, List<GoId>> domain_id_to_go_ids_map,
final Map<GoId, GoTerm> go_id_to_term_map,
final List<Object> plus_minus_analysis_numbers ) {
final Set<String> all_spec = new HashSet<String>();
return intrees;
}
- private static List<Phylogeny> inferSpeciesTrees( final File outfile, final List<DistanceMatrix> distances_list ) {
- final NeighborJoining nj = NeighborJoining.createInstance();
- final List<Phylogeny> phylogenies = nj.execute( distances_list );
- final PhylogenyWriter w = new PhylogenyWriter();
- try {
- w.toNewHampshire( phylogenies, true, true, outfile, ";" );
- }
- catch ( final IOException e ) {
- ForesterUtil.fatalError( PRG_NAME, "failed to write to outfile [" + outfile + "]: " + e.getMessage() );
- }
- return phylogenies;
- }
-
private static void log( final String msg, final Writer w ) {
try {
w.write( msg );
allowed_options.add( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
allowed_options.add( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION );
allowed_options.add( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS );
- allowed_options.add( JACKNIFE_OPTION );
- allowed_options.add( JACKNIFE_RANDOM_SEED_OPTION );
- allowed_options.add( JACKNIFE_RATIO_OPTION );
+ //allowed_options.add( JACKNIFE_OPTION );
+ // allowed_options.add( JACKNIFE_RANDOM_SEED_OPTION );
+ // allowed_options.add( JACKNIFE_RATIO_OPTION );
allowed_options.add( INPUT_SPECIES_TREE_OPTION );
- //allowed_options.add( INFER_SPECIES_TREES_OPTION );
allowed_options.add( FILTER_POSITIVE_OPTION );
allowed_options.add( FILTER_NEGATIVE_OPTION );
- allowed_options.add( INPUT_FILES_FROM_FILE_OPTION );
+ allowed_options.add( INPUT_GENOMES_FILE_OPTION );
allowed_options.add( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
allowed_options.add( FILTER_NEGATIVE_DOMAINS_OPTION );
allowed_options.add( IGNORE_VIRAL_IDS );
allowed_options.add( SEQ_EXTRACT_OPTION );
+ allowed_options.add( OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION );
allowed_options.add( SECONDARY_FEATURES_PARSIMONY_MAP_FILE );
allowed_options.add( PLUS_MINUS_ANALYSIS_OPTION );
allowed_options.add( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS );
allowed_options.add( 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 );
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;
if ( dissallowed_options.length() > 0 ) {
ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown option(s): " + dissallowed_options );
}
+ boolean use_last_in_fitch_parsimony = false;
+ if ( cla.isOptionSet( USE_LAST_IN_FITCH_OPTION ) ) {
+ use_last_in_fitch_parsimony = true;
+ }
+ boolean write_to_nexus = false;
+ if ( cla.isOptionSet( WRITE_TO_NEXUS_OPTION ) ) {
+ write_to_nexus = true;
+ }
+ boolean perform_dc_regain_proteins_stats = false;
+ if ( cla.isOptionSet( PERFORM_DC_REGAIN_PROTEINS_STATS_OPTION ) ) {
+ perform_dc_regain_proteins_stats = true;
+ }
+ boolean da_analysis = false;
+ if ( cla.isOptionSet( DA_ANALYSIS_OPTION ) ) {
+ da_analysis = true;
+ }
boolean output_binary_domain_combinationsfor_graph_analysis = false;
if ( cla.isOptionSet( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS ) ) {
output_binary_domain_combinationsfor_graph_analysis = true;
+ error );
}
try {
- final BasicTable<String> scores_table = BasicTableParser.parse( cutoff_scores_file, " " );
+ final BasicTable<String> scores_table = BasicTableParser.parse( cutoff_scores_file, ' ' );
individual_score_cutoffs = scores_table.getColumnsAsMapDouble( 0, 1 );
}
catch ( final IOException e ) {
plus_minus_analysis_high_copy_target_species,
plus_minus_analysis_high_low_copy_species,
plus_minus_analysis_numbers );
- File input_files_file = null;
- String[] input_file_names_from_file = null;
- if ( cla.isOptionSet( surfacing.INPUT_FILES_FROM_FILE_OPTION ) ) {
- if ( !cla.isOptionValueSet( surfacing.INPUT_FILES_FROM_FILE_OPTION ) ) {
- ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input files file: -"
- + surfacing.INPUT_FILES_FROM_FILE_OPTION + "=<file>" );
- }
- input_files_file = new File( cla.getOptionValue( surfacing.INPUT_FILES_FROM_FILE_OPTION ) );
- final String msg = ForesterUtil.isReadableFile( input_files_file );
+ 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 + "=<file>" );
+ }
+ 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_files_file + "\": " + msg );
- }
- try {
- input_file_names_from_file = ForesterUtil.file2array( input_files_file );
- }
- catch ( final IOException e ) {
- ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to read from \"" + input_files_file + "\": " + e );
+ ForesterUtil
+ .fatalError( surfacing.PRG_NAME, "can not read from \"" + input_genomes_file + "\": " + msg );
}
}
- if ( ( cla.getNumberOfNames() < 1 )
- && ( ( input_file_names_from_file == null ) || ( input_file_names_from_file.length < 1 ) ) ) {
- ForesterUtil.fatalError( surfacing.PRG_NAME,
- "No hmmpfam output file indicated is input: use comand line directly or "
- + surfacing.INPUT_FILES_FROM_FILE_OPTION + "=<file>" );
+ else {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "no input genomes file given: "
+ + surfacing.INPUT_GENOMES_FILE_OPTION + "=<file>" );
}
DomainSimilarity.DomainSimilarityScoring scoring = SCORING_DEFAULT;
if ( cla.isOptionSet( surfacing.SCORING_OPTION ) ) {
species_matrix = true;
}
boolean output_protein_lists_for_all_domains = false;
+ double output_list_of_all_proteins_per_domain_e_value_max = -1;
if ( cla.isOptionSet( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS ) ) {
output_protein_lists_for_all_domains = true;
+ if ( cla.isOptionSet( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION ) ) {
+ try {
+ output_list_of_all_proteins_per_domain_e_value_max = cla
+ .getOptionValueAsDouble( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION );
+ }
+ catch ( final Exception e ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for per domain E-value maximum" );
+ }
+ }
}
Detailedness detailedness = DETAILEDNESS_DEFAULT;
if ( cla.isOptionSet( surfacing.DETAILEDNESS_OPTION ) ) {
domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.HTML;
}
else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML ) ) {
- // domain_similarity_print_option =
- // DomainSimilarity.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 ) ) {
+ surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
}
}
- String[][] input_file_properties = null;
- if ( input_file_names_from_file != null ) {
- input_file_properties = surfacing.processInputFileNames( input_file_names_from_file );
- }
- else {
- input_file_properties = surfacing.processInputFileNames( cla.getNames() );
- }
+ final String[][] input_file_properties = processInputGenomesFile( input_genomes_file );
final int number_of_genomes = input_file_properties.length;
if ( number_of_genomes < 2 ) {
ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot analyze less than two files" );
automated_pairwise_comparison_suffix,
out_dir );
for( int i = 0; i < number_of_genomes; i++ ) {
- File dcc_outfile = new File( input_file_properties[ i ][ 0 ]
+ File dcc_outfile = new File( input_file_properties[ i ][ 1 ]
+ surfacing.DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX );
if ( out_dir != null ) {
dcc_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + dcc_outfile );
SurfacingUtil.checkForOutputFileWriteability( dcc_outfile );
}
File pfam_to_go_file = null;
- Map<DomainId, List<GoId>> domain_id_to_go_ids_map = null;
+ Map<String, List<GoId>> domain_id_to_go_ids_map = null;
int domain_id_to_go_ids_count = 0;
if ( cla.isOptionSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
if ( !cla.isOptionValueSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
&& ( number_of_genomes > 2 ) ) {
domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
}
- boolean jacknifed_distances = false;
- int jacknife_resamplings = JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT;
- double jacknife_ratio = JACKNIFE_RATIO_DEFAULT;
- long random_seed = JACKNIFE_RANDOM_SEED_DEFAULT;
- if ( cla.isOptionSet( surfacing.JACKNIFE_OPTION ) ) {
- if ( ( number_of_genomes < 3 ) || !perform_pwc ) {
- ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use jacknife resampling analysis (-"
- + surfacing.JACKNIFE_OPTION + "[=<number of resamplings>]) without pairwise analyses ("
- + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
- + "=<suffix for pairwise comparison output files>)" );
- }
- jacknifed_distances = true;
- if ( cla.isOptionHasAValue( surfacing.JACKNIFE_OPTION ) ) {
- try {
- jacknife_resamplings = cla.getOptionValueAsInt( surfacing.JACKNIFE_OPTION );
- }
- catch ( final IOException e ) {
- ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for number of resamplings" );
- }
- if ( jacknife_resamplings < 2 ) {
- ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use less than 2 resamplings" );
- }
- }
- if ( cla.isOptionSet( surfacing.JACKNIFE_RATIO_OPTION )
- && cla.isOptionHasAValue( surfacing.JACKNIFE_RATIO_OPTION ) ) {
- try {
- jacknife_ratio = cla.getOptionValueAsDouble( surfacing.JACKNIFE_RATIO_OPTION );
- }
- catch ( final IOException e ) {
- ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for jacknife ratio" );
- }
- if ( ( jacknife_ratio <= 0.0 ) || ( jacknife_ratio >= 1.0 ) ) {
- ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use illegal value for jacknife ratio: "
- + jacknife_ratio );
- }
- }
- if ( cla.isOptionSet( surfacing.JACKNIFE_RANDOM_SEED_OPTION )
- && cla.isOptionHasAValue( surfacing.JACKNIFE_RANDOM_SEED_OPTION ) ) {
- try {
- random_seed = cla.getOptionValueAsLong( surfacing.JACKNIFE_RANDOM_SEED_OPTION );
- }
- catch ( final IOException e ) {
- ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for random generator seed" );
- }
- }
- }
- // boolean infer_species_trees = false;
- // if ( cla.isOptionSet( surfacing.INFER_SPECIES_TREES_OPTION ) ) {
- // if ( ( output_file == null ) || ( number_of_genomes < 3 )
- // || ForesterUtil.isEmpty( automated_pairwise_comparison_suffix ) ) {
- // ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot infer species trees (-"
- // + surfacing.INFER_SPECIES_TREES_OPTION + " without pairwise analyses ("
- // + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
- // + "=<suffix for pairwise comparison output files>)" );
- // }
- // infer_species_trees = true;
- // }
File[] intree_files = null;
Phylogeny[] intrees = null;
if ( cla.isOptionSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
- // TODO FIXME if jacknife.... maybe not
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 ("
}
radomize_fitch_parsimony = true;
}
- SortedSet<DomainId> filter = null;
+ SortedSet<String> filter = null;
if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
|| ( negative_domains_filter_file != null ) ) {
- filter = new TreeSet<DomainId>();
+ filter = new TreeSet<String>();
if ( positive_filter_file != null ) {
processFilter( positive_filter_file, filter );
}
processFilter( negative_domains_filter_file, filter );
}
}
- Map<DomainId, Set<String>>[] domain_id_to_secondary_features_maps = null;
+ Map<String, Set<String>>[] domain_id_to_secondary_features_maps = null;
File[] secondary_features_map_files = null;
final File domain_lengths_analysis_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
+ DOMAIN_LENGTHS_ANALYSIS_SUFFIX );
+ surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
}
System.out.println( "Output directory : " + out_dir );
- if ( input_file_names_from_file != null ) {
- System.out.println( "Input files names from : " + input_files_file + " ["
- + input_file_names_from_file.length + " input files]" );
- html_desc.append( "<tr><td>Input files names from:</td><td>" + input_files_file + " ["
- + input_file_names_from_file.length + " input files]</td></tr>" + nl );
- }
+ System.out.println( "Input genomes from : " + input_genomes_file );
+ html_desc.append( "<tr><td>Input genomes from:</td><td>" + input_genomes_file + "</td></tr>" + nl );
if ( positive_filter_file != null ) {
final int filter_size = filter.size();
System.out.println( "Positive protein filter : " + positive_filter_file + " [" + filter_size
System.out.println( "E-value maximum (inclusive) : " + e_value_max );
html_desc.append( "<tr><td>E-value maximum (inclusive):</td><td>" + e_value_max + "</td></tr>" + nl );
}
+ if ( output_protein_lists_for_all_domains ) {
+ System.out.println( "Domain E-value max : " + output_list_of_all_proteins_per_domain_e_value_max );
+ html_desc.append( "<tr><td>Protein lists: E-value maximum per domain (inclusive):</td><td>"
+ + output_list_of_all_proteins_per_domain_e_value_max + "</td></tr>" + nl );
+ }
System.out.println( "Ignore DUFs : " + ignore_dufs );
if ( ignore_virus_like_ids ) {
System.out.println( "Ignore virus like ids : " + ignore_virus_like_ids );
+ ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) + "</td></tr>"
+ nl );
}
+ System.out.println( "Use last in Fitch parimony : " + use_last_in_fitch_parsimony );
+ html_desc.append( "<tr><td>Use last in Fitch parimon:</td><td>" + use_last_in_fitch_parsimony + "</td></tr>"
+ + nl );
+ System.out.println( "Write to Nexus files : " + write_to_nexus );
+ html_desc.append( "<tr><td>Write to Nexus files:</td><td>" + write_to_nexus + "</td></tr>" + nl );
+ System.out.println( "DC regain prot stats : " + perform_dc_regain_proteins_stats );
+ html_desc.append( "<tr><td>DC regain prot stats:</td><td>" + perform_dc_regain_proteins_stats + "</td></tr>"
+ + nl );
+ System.out.println( "DA analysis : " + da_analysis );
+ html_desc.append( "<tr><td>DA analysis :</td><td>" + da_analysis + "</td></tr>" + nl );
System.out.print( "Domain counts sort order : " );
+ html_desc.append( "<tr><td>Domain counts sort order:</td><td>" );
switch ( dc_sort_order ) {
case ALPHABETICAL_KEY_ID:
System.out.println( "alphabetical" );
+ html_desc.append( "alphabetical" + "</td></tr>" + nl );
break;
case KEY_DOMAIN_COUNT:
System.out.println( "domain count" );
+ html_desc.append( "domain count" + "</td></tr>" + nl );
break;
case KEY_DOMAIN_PROTEINS_COUNT:
System.out.println( "domain proteins count" );
+ html_desc.append( "domain proteins count" + "</td></tr>" + nl );
break;
case COMBINATIONS_COUNT:
System.out.println( "domain combinations count" );
+ html_desc.append( "domain combinations count" + "</td></tr>" + nl );
break;
default:
ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for dc sort order" );
}
System.out.println();
html_desc.append( "</td></tr>" + nl );
- if ( jacknifed_distances ) {
- html_desc.append( "<tr><td>Jacknife:</td><td>" + jacknife_resamplings + " resamplings</td></tr>" + nl );
- html_desc.append( "<tr><td>Jacknife ratio:</td><td>" + ForesterUtil.round( jacknife_ratio, 2 )
- + "</td></tr>" + nl );
- html_desc.append( "<tr><td>Jacknife random number seed:</td><td>" + random_seed + "</td></tr>" + nl );
- System.out.println( " Jacknife : " + jacknife_resamplings + " resamplings" );
- System.out.println( " Ratio : " + ForesterUtil.round( jacknife_ratio, 2 ) );
- System.out.println( " Random number seed : " + random_seed );
- }
- // if ( infer_species_trees ) {
- // html_desc.append( "<tr><td>Infer species trees:</td><td>true</td></tr>" + nl );
- // System.out.println( " Infer species trees : true" );
- // }
if ( ( intrees != null ) && ( intrees.length > 0 ) ) {
for( final File intree_file : intree_files ) {
html_desc.append( "<tr><td>Intree for gain/loss parsimony analysis:</td><td>" + intree_file
if ( VERBOSE ) {
System.out.println();
System.out.println( "Domain ids to secondary features map:" );
- for( final DomainId domain_id : domain_id_to_secondary_features_maps[ i ].keySet() ) {
- System.out.print( domain_id.getId() );
+ for( final String domain_id : domain_id_to_secondary_features_maps[ i ].keySet() ) {
+ System.out.print( domain_id );
System.out.print( " => " );
for( final String sec : domain_id_to_secondary_features_maps[ i ].get( domain_id ) ) {
System.out.print( sec );
html_desc.append( "<tr><td>Command line:</td><td>\n" + cla.getCommandLineArgsAsString() + "\n</td></tr>" + nl );
System.out.println( "Command line : " + cla.getCommandLineArgsAsString() );
BufferedWriter[] query_domains_writer_ary = null;
- List<DomainId>[] query_domain_ids_array = null;
+ List<String>[] query_domain_ids_array = null;
if ( query_domain_ids != null ) {
final String[] query_domain_ids_str_array = query_domain_ids.split( "#" );
query_domain_ids_array = new ArrayList[ query_domain_ids_str_array.length ];
for( int i = 0; i < query_domain_ids_str_array.length; i++ ) {
String query_domain_ids_str = query_domain_ids_str_array[ i ];
final String[] query_domain_ids_str_ary = query_domain_ids_str.split( "~" );
- final List<DomainId> query = new ArrayList<DomainId>();
+ final List<String> query = new ArrayList<String>();
for( final String element : query_domain_ids_str_ary ) {
- query.add( new DomainId( element ) );
+ query.add( element );
}
query_domain_ids_array[ i ] = query;
query_domain_ids_str = query_domain_ids_str.replace( '~', '_' );
if ( need_protein_lists_per_species ) {
protein_lists_per_species = new TreeMap<Species, List<Protein>>();
}
- final List<GenomeWideCombinableDomains> gwcd_list = new ArrayList<GenomeWideCombinableDomains>( number_of_genomes );
- final SortedSet<DomainId> all_domains_encountered = new TreeSet<DomainId>();
+ List<GenomeWideCombinableDomains> gwcd_list = new ArrayList<GenomeWideCombinableDomains>( number_of_genomes );
+ final SortedSet<String> all_domains_encountered = new TreeSet<String>();
final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered = new TreeSet<BinaryDomainCombination>();
List<BinaryDomainCombination> all_bin_domain_combinations_gained_fitch = null;
List<BinaryDomainCombination> all_bin_domain_combinations_lost_fitch = null;
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" );
catch ( final IOException e3 ) {
e3.printStackTrace();
}
- final Map<String, DescriptiveStatistics> protein_length_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
- final Map<String, DescriptiveStatistics> domain_number_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
+ Map<String, DescriptiveStatistics> protein_length_stats_by_dc = null;
+ Map<String, DescriptiveStatistics> domain_number_stats_by_dc = null;
+ final Map<String, DescriptiveStatistics> domain_length_stats_by_domain = new HashMap<String, DescriptiveStatistics>();
+ if ( perform_dc_regain_proteins_stats ) {
+ protein_length_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
+ domain_number_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
+ }
// Main loop:
+ final SortedMap<String, Set<String>> distinct_domain_architecutures_per_genome = new TreeMap<String, Set<String>>();
+ final SortedMap<String, Integer> distinct_domain_architecuture_counts = new TreeMap<String, Integer>();
for( int i = 0; i < number_of_genomes; ++i ) {
System.out.println();
System.out.println( ( i + 1 ) + "/" + number_of_genomes );
log( ( i + 1 ) + "/" + number_of_genomes, log_writer );
- System.out.println( "Processing : " + input_file_properties[ i ][ 0 ] );
- log( "Genome : " + input_file_properties[ i ][ 0 ], log_writer );
+ System.out.println( "Processing : " + input_file_properties[ i ][ 1 ]
+ + " [" + input_file_properties[ i ][ 0 ] + "]" );
+ log( "Genome : " + input_file_properties[ i ][ 1 ] + " ["
+ + input_file_properties[ i ][ 0 ] + "]", log_writer );
HmmscanPerDomainTableParser parser = null;
INDIVIDUAL_SCORE_CUTOFF ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF.NONE;
if ( individual_score_cutoffs != null ) {
}
final double coverage = ( double ) protein_list.size() / parser.getProteinsEncountered();
protein_coverage_stats.addValue( coverage );
+ int distinct_das = -1;
+ if ( da_analysis ) {
+ final String genome = input_file_properties[ i ][ 0 ];
+ distinct_das = SurfacingUtil.storeDomainArchitectures( genome,
+ distinct_domain_architecutures_per_genome,
+ protein_list,
+ distinct_domain_architecuture_counts );
+ }
System.out.println( "Number of proteins encountered : " + parser.getProteinsEncountered() );
log( "Number of proteins encountered : " + parser.getProteinsEncountered(), log_writer );
System.out.println( "Number of proteins stored : " + protein_list.size() );
log( "Proteins ignored due to positive filter : " + parser.getProteinsIgnoredDueToFilter(),
log_writer );
}
+ if ( da_analysis ) {
+ System.out.println( "Distinct domain architectures stored : " + distinct_das );
+ log( "Distinct domain architectures stored : " + distinct_das, log_writer );
+ }
System.out.println( "Time for processing : " + parser.getTime() + "ms" );
log( "", log_writer );
html_desc.append( "<tr><td>" + input_file_properties[ i ][ 0 ] + " [species: "
+ parser.getProteinsIgnoredDueToFilter() );
}
html_desc.append( "</td></tr>" + nl );
- // domain_partner_counts_array[ i ] =
- // Methods.getDomainPartnerCounts( protein_domain_collections_array[
- // i ],
- // false, input_file_properties[ i ][ 1 ] );
try {
int count = 0;
for( final Protein protein : protein_list ) {
dc_data_writer.write( SurfacingUtil.proteinToDomainCombinations( protein, count + "", "\t" )
.toString() );
++count;
+ for( final Domain d : protein.getProteinDomains() ) {
+ final String d_str = d.getDomainId().toString();
+ if ( !domain_length_stats_by_domain.containsKey( d_str ) ) {
+ domain_length_stats_by_domain.put( d_str, new BasicDescriptiveStatistics() );
+ }
+ domain_length_stats_by_domain.get( d_str ).addValue( d.getLength() );
+ }
}
}
catch ( final IOException e ) {
domains_which_are_sometimes_single_sometimes_not,
domains_which_never_single,
domains_per_potein_stats_writer );
- 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 ) );
domain_lengths_table.addLengths( protein_list );
- 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_graph_analysis ) {
- SurfacingUtil.writeBinaryDomainCombinationsFileForGraphAnalysis( input_file_properties,
- out_dir,
- gwcd_list.get( i ),
- i,
- dc_sort_order );
+ 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 ) );
+ 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_graph_analysis ) {
+ SurfacingUtil.writeBinaryDomainCombinationsFileForGraphAnalysis( input_file_properties,
+ out_dir,
+ gwcd_list.get( i ),
+ i,
+ dc_sort_order );
+ }
+ SurfacingUtil.addAllDomainIdsToSet( gwcd_list.get( i ), all_domains_encountered );
+ SurfacingUtil.addAllBinaryDomainCombinationToSet( gwcd_list.get( i ),
+ all_bin_domain_combinations_encountered );
}
- SurfacingUtil.addAllDomainIdsToSet( gwcd_list.get( i ), all_domains_encountered );
- SurfacingUtil.addAllBinaryDomainCombinationToSet( gwcd_list.get( i ),
- all_bin_domain_combinations_encountered );
}
if ( query_domains_writer_ary != null ) {
for( int j = 0; j < query_domain_ids_array.length; j++ ) {
ForesterUtil.programMessage( PRG_NAME, "Wrote domain promiscuities to: "
+ per_genome_domain_promiscuity_statistics_file );
//
+ 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" ) );
+ distinct_domain_architecutures_per_genome.clear();
+ distinct_domain_architecuture_counts.clear();
+ System.gc();
+ }
try {
domains_per_potein_stats_writer.write( "ALL" );
domains_per_potein_stats_writer.write( "\t" );
domains_per_potein_stats_writer.close();
printOutPercentageOfMultidomainProteins( all_genomes_domains_per_potein_histo, log_writer );
ForesterUtil.map2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
- + "__all_genomes_domains_per_potein_histo.txt" ), all_genomes_domains_per_potein_histo, "\t", "\n" );
+ + "_all_genomes_domains_per_potein_histo.txt" ), all_genomes_domains_per_potein_histo, "\t", "\n" );
ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
- + "__domains_always_single_.txt" ), domains_which_are_always_single, "\n" );
+ + "_domains_always_single_.txt" ), domains_which_are_always_single, "\n" );
ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
- + "__domains_single_or_combined.txt" ), domains_which_are_sometimes_single_sometimes_not, "\n" );
+ + "_domains_single_or_combined.txt" ), domains_which_are_sometimes_single_sometimes_not, "\n" );
ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
- + "__domains_always_combined.txt" ), domains_which_never_single, "\n" );
+ + "_domains_always_combined.txt" ), domains_which_never_single, "\n" );
ForesterUtil.programMessage( PRG_NAME,
"Average of proteins with a least one domain assigned: "
+ ( 100 * protein_coverage_stats.arithmeticMean() ) + "% (+/-"
+ ( 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() + "%" );
+ ForesterUtil.programMessage( PRG_NAME, "Range of proteins with a least one domain assigned: "
+ + ( 100 * protein_coverage_stats.getMin() ) + "%-" + ( 100 * protein_coverage_stats.getMax() )
+ + "%" );
log( "Average of prot with a least one dom assigned : " + ( 100 * protein_coverage_stats.arithmeticMean() )
+ "% (+/-" + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)", log_writer );
- log( "Range of prot with a least one dom assigned : " + 100 * protein_coverage_stats.getMin() + "%-"
- + 100 * protein_coverage_stats.getMax() + "%", log_writer );
+ log( "Range of prot with a least one dom assigned : " + ( 100 * protein_coverage_stats.getMin() ) + "%-"
+ + ( 100 * protein_coverage_stats.getMax() ) + "%", log_writer );
}
catch ( final IOException e2 ) {
ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
go_annotation_output,
go_id_to_term_map,
go_namespace_limit );
- DescriptiveStatistics pw_stats = null;
+ final Map<String, Integer> tax_code_to_id_map = SurfacingUtil.createTaxCodeToIdMap( intrees[ 0 ] );
try {
String my_outfile = output_file.toString();
Map<Character, Writer> split_writers = null;
+ new java.text.SimpleDateFormat( "yyyy.MM.dd HH:mm:ss" ).format( new java.util.Date() )
+ "</td></tr>" + nl );
html_desc.append( "</table>" + nl );
- pw_stats = SurfacingUtil
+ final DescriptiveStatistics pw_stats = SurfacingUtil
.writeDomainSimilaritiesToFile( html_desc,
new StringBuilder( number_of_genomes + " genomes" ),
writer,
domain_similarity_print_option,
domain_similarity_sort_field,
scoring,
- true );
+ true,
+ tax_code_to_id_map );
ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote main output (includes domain similarities) to: \""
+ ( out_dir == null ? my_outfile : out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) + "\"" );
}
+ e.getMessage() + "]" );
}
System.out.println();
- // values_for_all_scores_histogram = pw_stats.getDataAsDoubleArray();
final Species[] species = new Species[ number_of_genomes ];
for( int i = 0; i < number_of_genomes; ++i ) {
species[ i ] = new BasicSpecies( input_file_properties[ i ][ 1 ] );
surfacing.PAIRWISE_DOMAIN_COMPARISONS_PREFIX,
surfacing.PRG_NAME,
out_dir,
- write_pwc_files );
+ write_pwc_files,
+ tax_code_to_id_map );
String matrix_output_file = new String( output_file.toString() );
if ( matrix_output_file.indexOf( '.' ) > 1 ) {
matrix_output_file = matrix_output_file.substring( 0, matrix_output_file.indexOf( '.' ) );
inferred_trees.add( nj_gd );
inferred_trees.add( nj_bc );
inferred_trees.add( nj_d );
- if ( jacknifed_distances ) {
- pwgc.performPairwiseComparisonsJacknifed( species,
- number_of_genomes,
- gwcd_list,
- true,
- jacknife_resamplings,
- jacknife_ratio,
- random_seed );
- SurfacingUtil
- .writeMatrixToFile( new File( matrix_output_file
- + "_"
- + ForesterUtil.round( jacknife_ratio, 2 )
- + "_"
- + jacknife_resamplings
- + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
- pwgc.getSharedBinaryCombinationsBasedDistances() );
- SurfacingUtil
- .writeMatrixToFile( new File( matrix_output_file + "_" + ForesterUtil.round( jacknife_ratio, 2 )
- + "_" + jacknife_resamplings
- + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
- pwgc.getSharedDomainsBasedDistances() );
- // if ( infer_species_trees ) {
- // inferSpeciesTrees( new File( output_file + "_" + jacknife_resamplings
- // + INFERRED_SBC_BASED_NJ_SPECIES_TREE_SUFFIX ), pwgc
- // .getSharedBinaryCombinationsBasedDistances() );
- // inferSpeciesTrees( new File( output_file + "_" + jacknife_resamplings
- // + INFERRED_SD_BASED_NJ_SPECIES_TREE_SUFFIX ), pwgc.getSharedDomainsBasedDistances() );
- // }
- }
} // if ( ( output_file != null ) && ( number_of_genomes > 2 ) && !isEmpty( automated_pairwise_comparison_suffix ) )
if ( ( out_dir != null ) && ( !perform_pwc ) ) {
output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
}
- writePresentToNexus( output_file, positive_filter_file, filter, gwcd_list );
+ if ( write_to_nexus ) {
+ writePresentToNexus( output_file, positive_filter_file, filter, gwcd_list );
+ }
if ( ( ( intrees != null ) && ( intrees.length > 0 ) ) && ( number_of_genomes > 2 ) ) {
final StringBuilder parameters_sb = createParametersAsString( ignore_dufs,
e_value_max,
all_bin_domain_combinations_lost_fitch,
dc_type,
protein_length_stats_by_dc,
- domain_number_stats_by_dc );
+ domain_number_stats_by_dc,
+ domain_length_stats_by_domain,
+ tax_code_to_id_map,
+ write_to_nexus,
+ use_last_in_fitch_parsimony );
// Listing of all domain combinations gained is only done if only one input tree is used.
if ( ( domain_id_to_secondary_features_maps != null )
&& ( domain_id_to_secondary_features_maps.length > 0 ) ) {
int j = 0;
- for( final Map<DomainId, Set<String>> domain_id_to_secondary_features_map : domain_id_to_secondary_features_maps ) {
+ for( final Map<String, Set<String>> domain_id_to_secondary_features_map : domain_id_to_secondary_features_maps ) {
final Map<Species, MappingResults> mapping_results_map = new TreeMap<Species, MappingResults>();
final DomainParsimonyCalculator secondary_features_parsimony = DomainParsimonyCalculator
.createInstance( intree, gwcd_list, domain_id_to_secondary_features_map );
secondary_features_parsimony,
intree,
parameters_sb.toString(),
- mapping_results_map );
+ mapping_results_map,
+ use_last_in_fitch_parsimony );
if ( i == 0 ) {
System.out.println();
System.out.println( "Mapping to secondary features:" );
System.out.print( ", not mapped domains = " + mapping_results.getSumOfFailures() );
if ( total_domains > 0 ) {
System.out.println( ", mapped ratio = "
- + ( 100 * mapping_results.getSumOfSuccesses() / total_domains ) + "%" );
+ + ( ( 100 * mapping_results.getSumOfSuccesses() ) / total_domains ) + "%" );
}
else {
System.out.println( ", mapped ratio = n/a (total domains = 0 )" );
plus_minus_analysis_numbers );
}
if ( output_protein_lists_for_all_domains ) {
- writeProteinListsForAllSpecies( out_dir, protein_lists_per_species, gwcd_list );
- }
- // if ( ( intrees != null ) && ( intrees.length > 0 ) && ( inferred_trees != null ) && ( inferred_trees.size() > 0 ) ) {
- // final StringBuilder parameters_sb = createParametersAsString( ignore_dufs,
- // e_value_max,
- // max_allowed_overlap,
- // no_engulfing_overlaps,
- // cutoff_scores_file );
- // String s = "_";
- // if ( radomize_fitch_parsimony ) {
- // s += random_number_seed_for_fitch_parsimony + "_";
- // }
- // int i = 0;
- // for( final Phylogeny inferred_tree : inferred_trees ) {
- // if ( !inferred_tree.isRooted() ) {
- // intrees[ 0 ].getRoot().getName();
- // inferred_tree.r
- // }
- // final String outfile_name = ForesterUtil.removeSuffix( inferred_tree.getName() ) + s;
- // final DomainParsimonyCalculator domain_parsimony = DomainParsimonyCalculator
- // .createInstance( inferred_tree, gwcd_list );
- // SurfacingUtil.executeParsimonyAnalysis( random_number_seed_for_fitch_parsimony,
- // radomize_fitch_parsimony,
- // outfile_name,
- // domain_parsimony,
- // inferred_tree,
- // domain_id_to_go_ids_map,
- // go_id_to_term_map,
- // go_namespace_limit,
- // parameters_sb.toString() );
- // i++;
- // }
- // }
+ writeProteinListsForAllSpecies( out_dir,
+ protein_lists_per_species,
+ gwcd_list,
+ output_list_of_all_proteins_per_domain_e_value_max );
+ }
+ gwcd_list = null;
if ( all_bin_domain_combinations_gained_fitch != null ) {
try {
executeFitchGainsAnalysis( new File( output_file
for( final Entry<Integer, Integer> entry : all_genomes_domains_per_potein_histo.entrySet() ) {
sum += entry.getValue();
}
- final double percentage = 100.0 * ( sum - all_genomes_domains_per_potein_histo.get( 1 ) ) / sum;
+ final double percentage = ( 100.0 * ( sum - all_genomes_domains_per_potein_histo.get( 1 ) ) ) / sum;
ForesterUtil.programMessage( PRG_NAME, "Percentage of multidomain proteins: " + percentage + "%" );
log( "Percentage of multidomain proteins: : " + percentage + "%", log_writer );
}
}
System.out.println( "--" );
}
- for( int i = 0; i < input_file_properties.length; ++i ) {
+ for( final String[] input_file_propertie : input_file_properties ) {
try {
- intree.getNode( input_file_properties[ i ][ 1 ] );
+ intree.getNode( input_file_propertie[ 1 ] );
}
catch ( final IllegalArgumentException e ) {
- ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_properties[ i ][ 1 ]
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_propertie[ 1 ]
+ "] not present/not unique in input tree" );
}
}
}
- // public static StringBuffer stringCombinableDomainsMapToStringBuffer(
- // final SortedMap<String, CombinableDomains> map ) {
- // final StringBuffer sb = new StringBuffer();
- // for( final Iterator<String> iter = map.keySet().iterator();
- // iter.hasNext(); ) {
- // final Object key = iter.next();
- // sb.append( ForesterUtil.pad( new StringBuffer( key.toString() ), 18, ' ',
- // false ) );
- // final CombinableDomains domain_combination = map.get( key );
- // sb.append( ForesterUtil.pad( new StringBuffer( "" +
- // domain_combination.getNumberOfCombiningDomains() ), 8,
- // ' ', false ) );
- // sb.append( domain_combination.toStringBuffer() );
- // sb.append( ForesterUtil.getLineSeparator() );
- // }
- // return sb;
- // }
private static void printHelp() {
System.out.println();
System.out.println( "Usage:" );
System.out.println( surfacing.INPUT_SPECIES_TREE_OPTION
+ ": species tree, to perform (Dollo, Fitch) parismony analyses" );
System.out
- .println( JACKNIFE_OPTION
- + ": perform jacknife resampling for domain and binary domain combination based distance matrices [default resamplings: "
- + JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT + "]" );
- System.out.println( JACKNIFE_RATIO_OPTION + ": ratio for jacknife resampling [default: "
- + JACKNIFE_RATIO_DEFAULT + "]" );
- System.out.println( JACKNIFE_RANDOM_SEED_OPTION
- + ": seed for random number generator for jacknife resampling [default: "
- + JACKNIFE_RANDOM_SEED_DEFAULT + "]" );
- // System.out.println( surfacing.INFER_SPECIES_TREES_OPTION
- // + ": to infer NJ species trees based on shared domains/binary domain combinations" );
- System.out
.println( surfacing.INPUT_SPECIES_TREE_OPTION
+ "=<treefiles in phyloXML format, separated by #>: to infer domain/binary domain combination gains/losses on given species trees" );
System.out.println( surfacing.FILTER_POSITIVE_OPTION
+ "=<file>: to filter out proteins containing at least one domain listed in <file>" );
System.out.println( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION
+ "=<file>: to filter out (ignore) domains listed in <file>" );
- System.out.println( surfacing.INPUT_FILES_FROM_FILE_OPTION + "=<file>: to read input files from <file>" );
+ System.out.println( surfacing.INPUT_GENOMES_FILE_OPTION + "=<file>: to read input files from <file>" );
System.out
.println( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION
+ "=<seed>: seed for random number generator for Fitch Parsimony analysis (type: long, default: no randomization - given a choice, prefer absence" );
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" );
+ 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" );
+ 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_REGAIN_PROTEINS_STATS_OPTION + ": to perform DC regain protein statistics" );
+ System.out.println( DA_ANALYSIS_OPTION + ": to do DA analysis" );
System.out.println();
+ System.out.println( "Example 1: java -Xms128m -Xmx512m -cp path/to/forester.jar"
+ + " org.forester.application.surfacing p2g=pfam2go_2012_02_07.txt -dufs -cos=Pfam_260_NC1"
+ + " -no_eo -mo=0 -genomes=eukaryotes.txt -out_dir=out -o=o "
+ + " -species_tree=tol.xml -obo=gene_ontology_2012_02_07.obo -pos_filter=f.txt -all_prot" );
System.out.println();
- System.out.println( "Example: java -Xms128m -Xmx512m -cp path/to/forester.jar"
+ 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 "
- + "-ds_output=detailed_html -scoring=domains -sort=alpha -" + JACKNIFE_OPTION
- + "=50 human mouse brafl strpu" );
+ + "-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();
}
- private static void processFilter( final File filter_file, final SortedSet<DomainId> filter ) {
+ private static void processFilter( final File filter_file, final SortedSet<String> filter ) {
SortedSet<String> filter_str = null;
try {
filter_str = ForesterUtil.file2set( filter_file );
}
if ( filter_str != null ) {
for( final String string : filter_str ) {
- filter.add( new DomainId( string ) );
+ filter.add( string );
}
}
if ( VERBOSE ) {
System.out.println( "Filter:" );
- for( final DomainId domainId : filter ) {
- System.out.println( domainId.getId() );
+ for( final String domainId : filter ) {
+ System.out.println( domainId );
}
}
}
- private static String[][] processInputFileNames( final String[] names ) {
- final String[][] input_file_properties = new String[ names.length ][];
- for( int i = 0; i < names.length; ++i ) {
- if ( names[ i ].indexOf( SEPARATOR_FOR_INPUT_VALUES ) < 0 ) {
- input_file_properties[ i ] = new String[ 2 ];
- input_file_properties[ i ][ 0 ] = names[ i ];
- input_file_properties[ i ][ 1 ] = names[ i ];
+ private static String[][] processInputGenomesFile( final File input_genomes ) {
+ String[][] input_file_properties = null;
+ try {
+ input_file_properties = ForesterUtil.file22dArray( input_genomes );
+ }
+ catch ( final IOException e ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME,
+ "genomes files is to be in the following format \"<hmmpfam output file> <species>\": "
+ + e.getLocalizedMessage() );
+ }
+ final Set<String> specs = new HashSet<String>();
+ final Set<String> paths = new HashSet<String>();
+ for( int i = 0; i < input_file_properties.length; ++i ) {
+ if ( !PhyloXmlUtil.TAXOMONY_CODE_PATTERN.matcher( input_file_properties[ i ][ 1 ] ).matches() ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for species code: "
+ + input_file_properties[ i ][ 1 ] );
}
- else {
- input_file_properties[ i ] = names[ i ].split( surfacing.SEPARATOR_FOR_INPUT_VALUES + "" );
- if ( input_file_properties[ i ].length != 3 ) {
- ForesterUtil
- .fatalError( surfacing.PRG_NAME,
- "properties for the input files (hmmpfam output) are expected "
- + "to be in the following format \"<hmmpfam output file>#<species>\" (or just one word, which is both the filename and the species id), instead received \""
- + names[ i ] + "\"" );
- }
+ if ( specs.contains( input_file_properties[ i ][ 1 ] ) ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "species code " + input_file_properties[ i ][ 1 ]
+ + " is not unique" );
+ }
+ specs.add( input_file_properties[ i ][ 1 ] );
+ if ( paths.contains( input_file_properties[ i ][ 0 ] ) ) {
+ ForesterUtil.fatalError( surfacing.PRG_NAME, "path " + input_file_properties[ i ][ 0 ]
+ + " is not unique" );
}
+ paths.add( input_file_properties[ i ][ 0 ] );
final String error = ForesterUtil.isReadableFile( new File( input_file_properties[ i ][ 0 ] ) );
if ( !ForesterUtil.isEmpty( error ) ) {
ForesterUtil.fatalError( surfacing.PRG_NAME, error );
private static void writePresentToNexus( final File output_file,
final File positive_filter_file,
- final SortedSet<DomainId> filter,
+ final SortedSet<String> filter,
final List<GenomeWideCombinableDomains> gwcd_list ) {
try {
SurfacingUtil
private static void writeProteinListsForAllSpecies( final File output_dir,
final SortedMap<Species, List<Protein>> protein_lists_per_species,
- final List<GenomeWideCombinableDomains> gwcd_list ) {
- final SortedSet<DomainId> all_domains = new TreeSet<DomainId>();
+ final List<GenomeWideCombinableDomains> gwcd_list,
+ final double domain_e_cutoff ) {
+ final SortedSet<String> all_domains = new TreeSet<String>();
for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
all_domains.addAll( gwcd.getAllDomainIds() );
}
- for( final DomainId domain : all_domains ) {
+ for( final String domain : all_domains ) {
final File out = new File( output_dir + ForesterUtil.FILE_SEPARATOR + domain + SEQ_EXTRACT_SUFFIX );
SurfacingUtil.checkForOutputFileWriteability( out );
try {
domain,
proteins_file_writer,
"\t",
- LIMIT_SPEC_FOR_PROT_EX );
+ LIMIT_SPEC_FOR_PROT_EX,
+ domain_e_cutoff );
proteins_file_writer.close();
}
catch ( final IOException e ) {