// 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.io.parsers;
import org.forester.protein.BasicDomain;
import org.forester.protein.BasicProtein;
import org.forester.protein.Domain;
-import org.forester.protein.DomainId;
import org.forester.protein.Protein;
import org.forester.surfacing.SurfacingUtil;
import org.forester.util.ForesterUtil;
private static final ReturnType RETURN_TYPE_DEFAULT = ReturnType.UNORDERED_PROTEIN_DOMAIN_COLLECTION_PER_PROTEIN;
private static final boolean IGNORE_DUFS_DEFAULT = false;
private static final int MAX_ALLOWED_OVERLAP_DEFAULT = -1;
- private static final boolean IGNORE_REPLACED_RRMS = true;
- private final Set<DomainId> _filter;
+ private static final boolean IGNORE_REPLACED_RRMS = false;
+ private final Set<String> _filter;
private final FilterType _filter_type;
private final File _input_file;
private final String _species;
private int _domains_ignored_due_to_e_value;
private int _domains_ignored_due_to_individual_score_cutoff;
private int _domains_stored;
- private SortedSet<DomainId> _domains_stored_set;
+ private SortedSet<String> _domains_stored_set;
private long _time;
private int _domains_ignored_due_to_negative_domain_filter;
private Map<String, Integer> _domains_ignored_due_to_negative_domain_filter_counts_map;
public HmmscanPerDomainTableParser( final File input_file,
final String species,
- final Set<DomainId> filter,
+ final Set<String> filter,
final FilterType filter_type,
final INDIVIDUAL_SCORE_CUTOFF individual_cutoff_applies_to ) {
_input_file = input_file;
public HmmscanPerDomainTableParser( final File input_file,
final String species,
- final Set<DomainId> filter,
+ final Set<String> filter,
final FilterType filter_type,
final INDIVIDUAL_SCORE_CUTOFF individual_cutoff_applies_to,
final boolean allow_proteins_with_same_name ) {
_domains_ignored_due_to_overlap += domains_removed;
}
if ( ( getFilterType() == FilterType.POSITIVE_PROTEIN ) || ( getFilterType() == FilterType.NEGATIVE_PROTEIN ) ) {
- final Set<DomainId> domain_ids_in_protein = new HashSet<DomainId>();
+ final Set<String> domain_ids_in_protein = new HashSet<String>();
for( final Domain d : current_protein.getProteinDomains() ) {
domain_ids_in_protein.add( d.getDomainId() );
}
return _domains_stored;
}
- public SortedSet<DomainId> getDomainsStoredSet() {
+ public SortedSet<String> getDomainsStoredSet() {
return _domains_stored_set;
}
return _e_value_maximum;
}
- private Set<DomainId> getFilter() {
+ private Set<String> getFilter() {
return _filter;
}
}
private void intitCounts() {
- setDomainsStoredSet( new TreeSet<DomainId>() );
+ setDomainsStoredSet( new TreeSet<String>() );
setDomainsEncountered( 0 );
setProteinsEncountered( 0 );
setProteinsIgnoredDueToFilter( 0 );
ForesterUtil.increaseCountingMap( getDomainsIgnoredDueToVirusLikeIdCountsMap(), target_id );
++_domains_ignored_due_to_virus_like_id;
}
- else if ( ( getFilterType() == FilterType.NEGATIVE_DOMAIN )
- && getFilter().contains( new DomainId( target_id ) ) ) {
+ else if ( ( getFilterType() == FilterType.NEGATIVE_DOMAIN ) && getFilter().contains( target_id ) ) {
++_domains_ignored_due_to_negative_domain_filter;
ForesterUtil.increaseCountingMap( getDomainsIgnoredDueToNegativeDomainFilterCountsMap(), target_id );
}
_domains_stored = domains_stored;
}
- private void setDomainsStoredSet( final SortedSet<DomainId> _storeddomains_stored ) {
+ private void setDomainsStoredSet( final SortedSet<String> _storeddomains_stored ) {
_domains_stored_set = _storeddomains_stored;
}