import org.forester.application.surfacing;
import org.forester.phylogeny.Phylogeny;
+import org.forester.phylogeny.PhylogenyMethods;
import org.forester.phylogeny.PhylogenyNode;
import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
import org.forester.protein.Domain;
public final class MinimalDomainomeCalculator {
- static final public void calcOme( final boolean use_domain_architectures,
- final Phylogeny tre,
- final SortedMap<Species, List<Protein>> protein_lists_per_species,
- final String separator,
- final double ie_cutoff,
- final String outfile_base )
+ public final static void calc( final boolean use_domain_architectures,
+ final Phylogeny tre,
+ final int target_level,
+ final SortedMap<Species, List<Protein>> protein_lists_per_species,
+ final String separator,
+ final double ie_cutoff,
+ final String outfile_base,
+ final boolean write_protein_files )
throws IOException {
final SortedMap<String, SortedSet<String>> species_to_features_map = new TreeMap<String, SortedSet<String>>();
if ( protein_lists_per_species == null || tre == null ) {
final BufferedWriter out_table = new BufferedWriter( new FileWriter( outfile_table ) );
out.write( "SPECIES\tCOMMON NAME\tCODE\tRANK\t#EXT NODES\tEXT NODE CODES\t#" + x + "\t" + x + "" );
out.write( ForesterUtil.LINE_SEPARATOR );
+ ///////////
+ //////////
+ SortedMap<String, List<Protein>> protein_lists_per_quasi_species = null;
+ if ( target_level >= 1 ) {
+ protein_lists_per_quasi_species = makeProteinListsPerQuasiSpecies( tre,
+ target_level,
+ protein_lists_per_species );
+
+ }
+ /////////
+ ///////////
for( final PhylogenyNodeIterator iter = tre.iteratorPostorder(); iter.hasNext(); ) {
final PhylogenyNode node = iter.next();
+ final int node_level = PhylogenyMethods.calculateLevel( node );
final String species_name = node.getNodeData().isHasTaxonomy()
? node.getNodeData().getTaxonomy().getScientificName() : node.getName();
final String common = node.getNodeData().isHasTaxonomy() ? node.getNodeData().getTaxonomy().getCommonName()
final String tcode = node.getNodeData().isHasTaxonomy() ? node.getNodeData().getTaxonomy().getTaxonomyCode()
: "";
final String rank = node.getNodeData().isHasTaxonomy() ? node.getNodeData().getTaxonomy().getRank() : "";
- out.write( species_name );
- if ( !ForesterUtil.isEmpty( common ) ) {
- out.write( "\t" + common );
- }
- else {
- out.write( "\t" );
- }
- if ( !ForesterUtil.isEmpty( tcode ) ) {
- out.write( "\t" + tcode );
- }
- else {
- out.write( "\t" );
- }
- if ( !ForesterUtil.isEmpty( rank ) ) {
- out.write( "\t" + rank );
- }
- else {
- out.write( "\t" );
- }
final List<PhylogenyNode> external_descs = node.getAllExternalDescendants();
- if ( node.isInternal() ) {
- out.write( "\t" + external_descs.size() + "\t" );
- }
- else {
- out.write( "\t\t" );
+ if ( ( target_level < 1 ) || ( node_level >= target_level ) ) {
+ out.write( species_name );
+ if ( !ForesterUtil.isEmpty( common ) ) {
+ out.write( "\t" + common );
+ }
+ else {
+ out.write( "\t" );
+ }
+ if ( !ForesterUtil.isEmpty( tcode ) ) {
+ out.write( "\t" + tcode );
+ }
+ else {
+ out.write( "\t" );
+ }
+ if ( !ForesterUtil.isEmpty( rank ) ) {
+ out.write( "\t" + rank );
+ }
+ else {
+ out.write( "\t" );
+ }
+ if ( node.isInternal() ) {
+ out.write( "\t" + external_descs.size() + "\t" );
+ }
+ else {
+ out.write( "\t\t" );
+ }
}
final List<Set<String>> features_per_genome_list = new ArrayList<Set<String>>();
boolean first = true;
- for( final PhylogenyNode external_desc : external_descs ) {
- final String code = external_desc.getNodeData().getTaxonomy().getTaxonomyCode();
- if ( node.isInternal() ) {
- if ( first ) {
- first = false;
- }
- else {
- out.write( ", " );
+ if ( target_level >= 1 ) {
+ ////////////
+ ////////////
+ if ( node_level >= target_level ) {
+ final List<PhylogenyNode> given_level_descs = PhylogenyMethods
+ .getAllDescendantsOfGivenLevel( node, target_level );
+ for( final PhylogenyNode given_level_desc : given_level_descs ) {
+ final String spec_name = given_level_desc.getNodeData().isHasTaxonomy()
+ ? given_level_desc.getNodeData().getTaxonomy().getScientificName()
+ : given_level_desc.getName();
+ if ( node.isInternal() ) {
+ if ( first ) {
+ first = false;
+ }
+ else {
+ out.write( ", " );
+ }
+ out.write( "sp_n=" + spec_name );
+ }
+ final List<Protein> proteins_per_species = protein_lists_per_quasi_species.get( spec_name );
+ if ( proteins_per_species != null ) {
+ final SortedSet<String> features_per_genome = new TreeSet<String>();
+ for( final Protein protein : proteins_per_species ) {
+ if ( use_domain_architectures ) {
+ final String da = protein.toDomainArchitectureString( separator, ie_cutoff );
+ features_per_genome.add( da );
+ }
+ else {
+ List<Domain> domains = protein.getProteinDomains();
+ for( final Domain domain : domains ) {
+ if ( ( ie_cutoff <= -1 ) || ( domain.getPerDomainEvalue() <= ie_cutoff ) ) {
+ features_per_genome.add( domain.getDomainId() );
+ }
+ }
+ }
+ }
+ System.out.println( ">>>>>>>>>>>>>> features_per_genome.size()=" + features_per_genome.size() );
+ if ( features_per_genome.size() > 0 ) {
+ features_per_genome_list.add( features_per_genome );
+ }
+ else {
+ System.out.println( "error!" );
+ System.exit( -1 );
+ }
+ }
+ else {
+ System.out.println( "error!" );
+ System.exit( -1 );
+ }
}
- out.write( code );
}
- final List<Protein> proteins_per_species = protein_lists_per_species.get( new BasicSpecies( code ) );
- if ( proteins_per_species != null ) {
- final SortedSet<String> features_per_genome = new TreeSet<String>();
- for( final Protein protein : proteins_per_species ) {
- if ( use_domain_architectures ) {
- final String da = protein.toDomainArchitectureString( separator, ie_cutoff );
- features_per_genome.add( da );
+ ///////////
+ ///////////
+ }
+ else {
+ for( final PhylogenyNode external_desc : external_descs ) {
+ final String code = external_desc.getNodeData().getTaxonomy().getTaxonomyCode();
+ if ( node.isInternal() ) {
+ if ( first ) {
+ first = false;
}
else {
- List<Domain> domains = protein.getProteinDomains();
- for( final Domain domain : domains ) {
- if ( ( ie_cutoff <= -1 ) || ( domain.getPerDomainEvalue() <= ie_cutoff ) ) {
- features_per_genome.add( domain.getDomainId() );
+ out.write( ", " );
+ }
+ out.write( code );
+ }
+ final List<Protein> proteins_per_species = protein_lists_per_species
+ .get( new BasicSpecies( code ) );
+ if ( proteins_per_species != null ) {
+ final SortedSet<String> features_per_genome = new TreeSet<String>();
+ for( final Protein protein : proteins_per_species ) {
+ if ( use_domain_architectures ) {
+ final String da = protein.toDomainArchitectureString( separator, ie_cutoff );
+ features_per_genome.add( da );
+ }
+ else {
+ List<Domain> domains = protein.getProteinDomains();
+ for( final Domain domain : domains ) {
+ if ( ( ie_cutoff <= -1 ) || ( domain.getPerDomainEvalue() <= ie_cutoff ) ) {
+ features_per_genome.add( domain.getDomainId() );
+ }
}
}
}
+ if ( features_per_genome.size() > 0 ) {
+ features_per_genome_list.add( features_per_genome );
+ }
}
- if ( features_per_genome.size() > 0 ) {
- features_per_genome_list.add( features_per_genome );
- }
- }
- }
+ } // for( final PhylogenyNode external_desc : external_descs )
+ } // else
if ( features_per_genome_list.size() > 0 ) {
SortedSet<String> intersection = calcIntersection( features_per_genome_list );
out.write( "\t" + intersection.size() + "\t" );
out_table.close();
ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote minimal DAome data to : " + outfile );
ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote minimal DAome data to (as table): " + outfile_table );
- for( String f : all_features ) {
+ if ( write_protein_files ) {
+ final String protdirname;
final String a;
+ final String b;
if ( use_domain_architectures ) {
- a = "DA_";
+ a = "_DA";
+ b = "domain architectures (DAs)";
+ protdirname = "_DAS";
}
else {
- a = "domain_";
+ a = "_domain";
+ b = "domains";
+ protdirname = "_DOMAINS";
+ }
+ final File prot_dir = new File( outfile_base + protdirname );
+ final boolean success = prot_dir.mkdir();
+ if ( !success ) {
+ throw new IOException( "failed to create dir " + prot_dir );
+ }
+ int total = 0;
+ final String dir = outfile_base + protdirname + "/";
+ for( final String feat : all_features ) {
+ final File extract_outfile = new File( dir + feat + a + surfacing.SEQ_EXTRACT_SUFFIX );
+ SurfacingUtil.checkForOutputFileWriteability( extract_outfile );
+ final Writer proteins_file_writer = new BufferedWriter( new FileWriter( extract_outfile ) );
+ final int counter = extractProteinFeatures( use_domain_architectures,
+ protein_lists_per_species,
+ feat,
+ proteins_file_writer,
+ ie_cutoff,
+ separator );
+ if ( counter < 1 ) {
+ ForesterUtil.printWarningMessage( "surfacing", feat + " not present (in " + b + " extraction)" );
+ }
+ total += counter;
+ proteins_file_writer.close();
+ }
+ ForesterUtil.programMessage( "surfacing",
+ "Wrote " + total + " individual " + b + " from a total of "
+ + all_features.size() + " into: " + dir );
+ }
+ }
+
+ private final static SortedMap<String, List<Protein>> makeProteinListsPerQuasiSpecies( final Phylogeny tre,
+ final int level,
+ final SortedMap<Species, List<Protein>> protein_lists_per_species ) {
+ final SortedMap<String, List<Protein>> protein_lists_per_quasi_species = new TreeMap<String, List<Protein>>();
+ System.out.println( "---------------------------------" );
+ System.out.println( "level=" + level );
+ for( final PhylogenyNodeIterator iter = tre.iteratorPostorder(); iter.hasNext(); ) {
+ final PhylogenyNode node = iter.next();
+ final int node_level = PhylogenyMethods.calculateLevel( node );
+ if ( node_level == level ) {
+ System.out.println( "level=" + level );
+ final List<PhylogenyNode> external_descs = node.getAllExternalDescendants();
+ final List<Protein> protein_list_per_quasi_species = new ArrayList<Protein>();
+ for( final PhylogenyNode external_desc : external_descs ) {
+ final String code = external_desc.getNodeData().getTaxonomy().getTaxonomyCode();
+ final List<Protein> proteins_per_species = protein_lists_per_species
+ .get( new BasicSpecies( code ) );
+ //System.out.println( code );
+ for( Protein protein : proteins_per_species ) {
+ protein_list_per_quasi_species.add( protein );
+ }
+ }
+ final String species_name = node.getNodeData().isHasTaxonomy()
+ ? node.getNodeData().getTaxonomy().getScientificName() : node.getName();
+ System.out.println( "species_name=" + species_name );
+ protein_lists_per_quasi_species.put( species_name, protein_list_per_quasi_species );
+ System.out.println( ">>>>" + protein_list_per_quasi_species.size() );
}
- final File prot_dir = new File( outfile_base + "_prot" );
- prot_dir.mkdir();
- final File outt = new File( outfile_base + "_prot/" + a + f + surfacing.SEQ_EXTRACT_SUFFIX );
- final Writer proteins_file_writer = new BufferedWriter( new FileWriter( outt ) );
- extractProteinFeatures( use_domain_architectures,
- protein_lists_per_species,
- f,
- proteins_file_writer,
- ie_cutoff,
- separator );
- proteins_file_writer.close();
}
+
+ return protein_lists_per_quasi_species;
}
private final static SortedSet<String> calcIntersection( final List<Set<String>> features_per_genome_list ) {
return my_first;
}
- public static void extractProteinFeatures( final boolean use_domain_architectures,
- final SortedMap<Species, List<Protein>> protein_lists_per_species,
- final String domain_id,
- final Writer out,
- final double ie_cutoff,
- final String domain_separator )
+ private final static int extractProteinFeatures( final boolean use_domain_architectures,
+ final SortedMap<Species, List<Protein>> protein_lists_per_species,
+ final String domain_id,
+ final Writer out,
+ final double ie_cutoff,
+ final String domain_separator )
throws IOException {
+ int counter = 0;
final String separator_for_output = "\t";
for( final Species species : protein_lists_per_species.keySet() ) {
final List<Protein> proteins_per_species = protein_lists_per_species.get( species );
out.write( from + "-" + to );
out.write( "/" );
out.write( SurfacingConstants.NL );
+ ++counter;
}
}
else {
out.write( protein.getAccession() );
}
out.write( SurfacingConstants.NL );
+ ++counter;
}
}
}
}
out.flush();
+ return counter;
}
public static void main( final String[] args ) {
git://source.jalview.org / jalview.git / blobdiff