in progress

[jalview.git] / forester / java / src / org / forester / io / parsers / HmmscanPerDomainTableParser.java

diff --git a/forester/java/src/org/forester/io/parsers/HmmscanPerDomainTableParser.java b/forester/java/src/org/forester/io/parsers/HmmscanPerDomainTableParser.java
index b5d1bc1..f595349 100644 (file)
--- a/forester/java/src/org/forester/io/parsers/HmmscanPerDomainTableParser.java
+++ b/forester/java/src/org/forester/io/parsers/HmmscanPerDomainTableParser.java
@@ -23,7 +23,7 @@
 // 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;
 
@@ -44,9 +44,7 @@ import java.util.TreeSet;
 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;
 
 public final class HmmscanPerDomainTableParser {
@@ -65,7 +63,8 @@ public final class HmmscanPerDomainTableParser {
     private static final boolean          IGNORE_DUFS_DEFAULT         = false;
     private static final int              MAX_ALLOWED_OVERLAP_DEFAULT = -1;
     private static final boolean          IGNORE_REPLACED_RRMS        = false;
-    private final Set<DomainId>           _filter;
+    private static final boolean          IGNORE_hGDE_amylase         = true;                                                      //TODO eventually remove me, added 10/22/13
+    private final Set<String>             _filter;
     private final FilterType              _filter_type;
     private final File                    _input_file;
     private final String                  _species;
@@ -85,7 +84,7 @@ public final class HmmscanPerDomainTableParser {
     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;
@@ -121,7 +120,7 @@ public final class HmmscanPerDomainTableParser {
 
     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;
@@ -135,7 +134,7 @@ public final class HmmscanPerDomainTableParser {
 
     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 ) {
@@ -165,15 +164,15 @@ public final class HmmscanPerDomainTableParser {
         if ( ( getMaxAllowedOverlap() != HmmscanPerDomainTableParser.MAX_ALLOWED_OVERLAP_DEFAULT )
                 || isIgnoreEngulfedDomains() ) {
             final int domains_count = current_protein.getNumberOfProteinDomains();
-            current_protein = SurfacingUtil.removeOverlappingDomains( getMaxAllowedOverlap(),
-                                                                      isIgnoreEngulfedDomains(),
-                                                                      current_protein );
+            current_protein = ForesterUtil.removeOverlappingDomains( getMaxAllowedOverlap(),
+                                                                     isIgnoreEngulfedDomains(),
+                                                                     current_protein );
             final int domains_removed = domains_count - current_protein.getNumberOfProteinDomains();
             _domains_stored -= domains_removed;
             _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() );
             }
@@ -240,7 +239,7 @@ public final class HmmscanPerDomainTableParser {
         return _domains_stored;
     }
 
-    public SortedSet<DomainId> getDomainsStoredSet() {
+    public SortedSet<String> getDomainsStoredSet() {
         return _domains_stored_set;
     }
 
@@ -248,7 +247,7 @@ public final class HmmscanPerDomainTableParser {
         return _e_value_maximum;
     }
 
-    private Set<DomainId> getFilter() {
+    private Set<String> getFilter() {
         return _filter;
     }
 
@@ -308,7 +307,7 @@ public final class HmmscanPerDomainTableParser {
     }
 
     private void intitCounts() {
-        setDomainsStoredSet( new TreeSet<DomainId>() );
+        setDomainsStoredSet( new TreeSet<String>() );
         setDomainsEncountered( 0 );
         setProteinsEncountered( 0 );
         setProteinsIgnoredDueToFilter( 0 );
@@ -452,6 +451,8 @@ public final class HmmscanPerDomainTableParser {
                     && ( uc_id.contains( "RRM_1" ) || uc_id.contains( "RRM_3" ) || uc_id.contains( "RRM_5" ) || uc_id
                             .contains( "RRM_6" ) ) ) {
             }
+            else if ( IGNORE_hGDE_amylase && ( uc_id.equals( "hGDE_amylase" ) ) ) {
+            }
             else if ( isIgnoreVirusLikeIds()
                     && ( uc_id.contains( VIR ) || uc_id.contains( PHAGE ) || uc_id.contains( RETRO )
                             || uc_id.contains( TRANSPOS ) || uc_id.startsWith( RV ) || uc_id.startsWith( GAG )
@@ -459,8 +460,7 @@ public final class HmmscanPerDomainTableParser {
                 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 );
             }
@@ -556,7 +556,7 @@ public final class HmmscanPerDomainTableParser {
         _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;
     }