import java.io.Writer;
import java.util.ArrayList;
import java.util.Date;
+import java.util.HashMap;
import java.util.HashSet;
import java.util.List;
import java.util.Map;
public class surfacing {
+ private static final int MINIMAL_NUMBER_OF_SIMILARITIES_FOR_SPLITTING = 1000;
public final static String DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS = "graph_analysis_out";
public final static String DOMAIN_COMBINITONS_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_dc.dot";
public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_BC_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_fitch_present_dc.dot";
final static private String SEQ_EXTRACT_OPTION = "prot_extract";
final static private char SEPARATOR_FOR_INPUT_VALUES = '#';
final static private String PRG_VERSION = "2.210";
- final static private String PRG_DATE = "2011.11.25";
+ final static private String PRG_DATE = "2012.02.21";
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;
public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists.txt";
public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping.txt";
public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_UNIQUE_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping_unique.txt";
+ public static final String LIMIT_SPEC_FOR_PROT_EX = null; // e.g. "HUMAN"; set to null for not using this feature (default).
+ public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH_MAPPED = "_dc_MAPPED_secondary_features_fitch"
+ + ForesterConstants.PHYLO_XML_SUFFIX;
+ public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts_MAPPED.txt";
+ public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_MAPPED.txt";
+ public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping_MAPPED.txt";
+ public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_MAPPED_OUTPUT_UNIQUE_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping_unique_MAPPED.txt";
private static void checkWriteabilityForPairwiseComparisons( final PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option,
final String[][] input_file_properties,
SurfacingUtil.extractProteinNames( protein_list,
query_domain_ids_array[ j ],
query_domains_writer_ary[ j ],
- "\t" );
+ "\t",
+ LIMIT_SPEC_FOR_PROT_EX );
query_domains_writer_ary[ j ].flush();
}
catch ( final IOException e ) {
DescriptiveStatistics pw_stats = null;
try {
String my_outfile = output_file.toString();
- if ( !my_outfile.endsWith( ".html" ) ) {
+ Map<Character, Writer> split_writers = null;
+ Writer writer = null;
+ if ( similarities.size() > MINIMAL_NUMBER_OF_SIMILARITIES_FOR_SPLITTING ) {
+ if ( my_outfile.endsWith( ".html" ) ) {
+ my_outfile = my_outfile.substring( 0, my_outfile.length() - 5 );
+ }
+ split_writers = new HashMap<Character, Writer>();
+ createSplitWriters( out_dir, my_outfile, split_writers );
+ }
+ else if ( !my_outfile.endsWith( ".html" ) ) {
my_outfile += ".html";
+ writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) );
}
- final Writer writer = new BufferedWriter( new FileWriter( out_dir == null ? my_outfile : out_dir
- + ForesterUtil.FILE_SEPARATOR + my_outfile ) );
List<Species> species_order = null;
if ( species_matrix ) {
species_order = new ArrayList<Species>();
.writeDomainSimilaritiesToFile( html_desc,
new StringBuilder( number_of_genomes + " genomes" ),
writer,
+ split_writers,
similarities,
number_of_genomes == 2,
species_order,
System.out.println();
}
+ private static void createSplitWriters( final File out_dir,
+ final String my_outfile,
+ final Map<Character, Writer> split_writers ) throws IOException {
+ split_writers.put( 'a', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_A.html" ) ) );
+ split_writers.put( 'b', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_B.html" ) ) );
+ split_writers.put( 'c', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_C.html" ) ) );
+ split_writers.put( 'd', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_D.html" ) ) );
+ split_writers.put( 'e', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_E.html" ) ) );
+ split_writers.put( 'f', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_F.html" ) ) );
+ split_writers.put( 'g', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_G.html" ) ) );
+ split_writers.put( 'h', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_H.html" ) ) );
+ split_writers.put( 'i', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_I.html" ) ) );
+ split_writers.put( 'j', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_J.html" ) ) );
+ split_writers.put( 'k', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_K.html" ) ) );
+ split_writers.put( 'l', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_L.html" ) ) );
+ split_writers.put( 'm', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_M.html" ) ) );
+ split_writers.put( 'n', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_N.html" ) ) );
+ split_writers.put( 'o', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_O.html" ) ) );
+ split_writers.put( 'p', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_P.html" ) ) );
+ split_writers.put( 'q', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_Q.html" ) ) );
+ split_writers.put( 'r', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_R.html" ) ) );
+ split_writers.put( 's', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_S.html" ) ) );
+ split_writers.put( 't', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_T.html" ) ) );
+ split_writers.put( 'u', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_U.html" ) ) );
+ split_writers.put( 'v', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_V.html" ) ) );
+ split_writers.put( 'w', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_W.html" ) ) );
+ split_writers.put( 'x', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_X.html" ) ) );
+ split_writers.put( 'y', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_Y.html" ) ) );
+ split_writers.put( 'z', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_Z.html" ) ) );
+ split_writers.put( '0', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
+ + "_domains_0.html" ) ) );
+ }
+
private static void printOutPercentageOfMultidomainProteins( final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo,
final Writer log_writer ) {
int sum = 0;
SurfacingUtil.checkForOutputFileWriteability( out );
try {
final Writer proteins_file_writer = new BufferedWriter( new FileWriter( out ) );
- SurfacingUtil.extractProteinNames( protein_lists_per_species, domain, proteins_file_writer, "\t" );
+ SurfacingUtil.extractProteinNames( protein_lists_per_species,
+ domain,
+ proteins_file_writer,
+ "\t",
+ LIMIT_SPEC_FOR_PROT_EX );
proteins_file_writer.close();
}
catch ( final IOException e ) {
git://source.jalview.org / jalview.git / blobdiff