+ ForesterConstants.PHYLO_XML_VERSION + "/"
+ ForesterConstants.PHYLO_XML_XSD;
+ public static boolean testOverlapRemoval() {
+ try {
+ final Domain d0 = new BasicDomain( "d0", ( short ) 2, ( short ) 5, ( short ) 1, ( short ) 1, 0.1, 1 );
+ final Domain d1 = new BasicDomain( "d1", ( short ) 7, ( short ) 10, ( short ) 1, ( short ) 1, 0.1, 1 );
+ final Domain d2 = new BasicDomain( "d2", ( short ) 0, ( short ) 20, ( short ) 1, ( short ) 1, 0.1, 1 );
+ final Domain d3 = new BasicDomain( "d3", ( short ) 9, ( short ) 10, ( short ) 1, ( short ) 1, 0.1, 1 );
+ final Domain d4 = new BasicDomain( "d4", ( short ) 7, ( short ) 8, ( short ) 1, ( short ) 1, 0.1, 1 );
+ final List<Boolean> covered = new ArrayList<Boolean>();
+ covered.add( true ); // 0
+ covered.add( false ); // 1
+ covered.add( true ); // 2
+ covered.add( false ); // 3
+ covered.add( true ); // 4
+ covered.add( true ); // 5
+ covered.add( false ); // 6
+ covered.add( true ); // 7
+ covered.add( true ); // 8
+ if ( ForesterUtil.calculateOverlap( d0, covered ) != 3 ) {
+ return false;
+ }
+ if ( ForesterUtil.calculateOverlap( d1, covered ) != 2 ) {
+ return false;
+ }
+ if ( ForesterUtil.calculateOverlap( d2, covered ) != 6 ) {
+ return false;
+ }
+ if ( ForesterUtil.calculateOverlap( d3, covered ) != 0 ) {
+ return false;
+ }
+ if ( ForesterUtil.calculateOverlap( d4, covered ) != 2 ) {
+ return false;
+ }
+ final Domain a = new BasicDomain( "a", ( short ) 2, ( short ) 5, ( short ) 1, ( short ) 1, 0.01, 1 );
+ final Domain b = new BasicDomain( "b", ( short ) 2, ( short ) 10, ( short ) 1, ( short ) 1, 0.1, 1 );
+ final Protein ab = new BasicProtein( "ab", "varanus", 0 );
+ ab.addProteinDomain( a );
+ ab.addProteinDomain( b );
+ final Protein ab_s0 = ForesterUtil.removeOverlappingDomains( 3, false, ab );
+ if ( ab.getNumberOfProteinDomains() != 2 ) {
+ return false;
+ }
+ if ( ab_s0.getNumberOfProteinDomains() != 1 ) {
+ return false;
+ }
+ if ( !ab_s0.getProteinDomain( 0 ).getDomainId().equals( "a" ) ) {
+ return false;
+ }
+ final Protein ab_s1 = ForesterUtil.removeOverlappingDomains( 4, false, ab );
+ if ( ab.getNumberOfProteinDomains() != 2 ) {
+ return false;
+ }
+ if ( ab_s1.getNumberOfProteinDomains() != 2 ) {
+ return false;
+ }
+ final Domain c = new BasicDomain( "c", ( short ) 20000, ( short ) 20500, ( short ) 1, ( short ) 1, 10, 1 );
+ final Domain d = new BasicDomain( "d",
+ ( short ) 10000,
+ ( short ) 10500,
+ ( short ) 1,
+ ( short ) 1,
+ 0.0000001,
+ 1 );
+ final Domain e = new BasicDomain( "e", ( short ) 5000, ( short ) 5500, ( short ) 1, ( short ) 1, 0.0001, 1 );
+ final Protein cde = new BasicProtein( "cde", "varanus", 0 );
+ cde.addProteinDomain( c );
+ cde.addProteinDomain( d );
+ cde.addProteinDomain( e );
+ final Protein cde_s0 = ForesterUtil.removeOverlappingDomains( 0, false, cde );
+ if ( cde.getNumberOfProteinDomains() != 3 ) {
+ return false;
+ }
+ if ( cde_s0.getNumberOfProteinDomains() != 3 ) {
+ return false;
+ }
+ final Domain f = new BasicDomain( "f", ( short ) 10, ( short ) 20, ( short ) 1, ( short ) 1, 10, 1 );
+ final Domain g = new BasicDomain( "g", ( short ) 10, ( short ) 20, ( short ) 1, ( short ) 1, 0.01, 1 );
+ final Domain h = new BasicDomain( "h", ( short ) 10, ( short ) 20, ( short ) 1, ( short ) 1, 0.0001, 1 );
+ final Domain i = new BasicDomain( "i", ( short ) 10, ( short ) 20, ( short ) 1, ( short ) 1, 0.5, 1 );
+ final Domain i2 = new BasicDomain( "i", ( short ) 5, ( short ) 30, ( short ) 1, ( short ) 1, 0.5, 10 );
+ final Protein fghi = new BasicProtein( "fghi", "varanus", 0 );
+ fghi.addProteinDomain( f );
+ fghi.addProteinDomain( g );
+ fghi.addProteinDomain( h );
+ fghi.addProteinDomain( i );
+ fghi.addProteinDomain( i );
+ fghi.addProteinDomain( i );
+ fghi.addProteinDomain( i2 );
+ final Protein fghi_s0 = ForesterUtil.removeOverlappingDomains( 10, false, fghi );
+ if ( fghi.getNumberOfProteinDomains() != 7 ) {
+ return false;
+ }
+ if ( fghi_s0.getNumberOfProteinDomains() != 1 ) {
+ return false;
+ }
+ if ( !fghi_s0.getProteinDomain( 0 ).getDomainId().equals( "h" ) ) {
+ return false;
+ }
+ final Protein fghi_s1 = ForesterUtil.removeOverlappingDomains( 11, false, fghi );
+ if ( fghi.getNumberOfProteinDomains() != 7 ) {
+ return false;
+ }
+ if ( fghi_s1.getNumberOfProteinDomains() != 7 ) {
+ return false;
+ }
+ final Domain j = new BasicDomain( "j", ( short ) 10, ( short ) 20, ( short ) 1, ( short ) 1, 10, 1 );
+ final Domain k = new BasicDomain( "k", ( short ) 10, ( short ) 20, ( short ) 1, ( short ) 1, 0.01, 1 );
+ final Domain l = new BasicDomain( "l", ( short ) 10, ( short ) 20, ( short ) 1, ( short ) 1, 0.0001, 1 );
+ final Domain m = new BasicDomain( "m", ( short ) 10, ( short ) 20, ( short ) 1, ( short ) 4, 0.5, 1 );
+ final Domain m0 = new BasicDomain( "m", ( short ) 10, ( short ) 20, ( short ) 2, ( short ) 4, 0.5, 1 );
+ final Domain m1 = new BasicDomain( "m", ( short ) 10, ( short ) 20, ( short ) 3, ( short ) 4, 0.5, 1 );
+ final Domain m2 = new BasicDomain( "m", ( short ) 5, ( short ) 30, ( short ) 4, ( short ) 4, 0.5, 10 );
+ final Protein jklm = new BasicProtein( "jklm", "varanus", 0 );
+ jklm.addProteinDomain( j );
+ jklm.addProteinDomain( k );
+ jklm.addProteinDomain( l );
+ jklm.addProteinDomain( m );
+ jklm.addProteinDomain( m0 );
+ jklm.addProteinDomain( m1 );
+ jklm.addProteinDomain( m2 );
+ final Protein jklm_s0 = ForesterUtil.removeOverlappingDomains( 10, false, jklm );
+ if ( jklm.getNumberOfProteinDomains() != 7 ) {
+ return false;
+ }
+ if ( jklm_s0.getNumberOfProteinDomains() != 1 ) {
+ return false;
+ }
+ if ( !jklm_s0.getProteinDomain( 0 ).getDomainId().equals( "l" ) ) {
+ return false;
+ }
+ final Protein jklm_s1 = ForesterUtil.removeOverlappingDomains( 11, false, jklm );
+ if ( jklm.getNumberOfProteinDomains() != 7 ) {
+ return false;
+ }
+ if ( jklm_s1.getNumberOfProteinDomains() != 7 ) {
+ return false;
+ }
+ final Domain only = new BasicDomain( "only", ( short ) 5, ( short ) 30, ( short ) 4, ( short ) 4, 0.5, 10 );
+ final Protein od = new BasicProtein( "od", "varanus", 0 );
+ od.addProteinDomain( only );
+ final Protein od_s0 = ForesterUtil.removeOverlappingDomains( 0, false, od );
+ if ( od.getNumberOfProteinDomains() != 1 ) {
+ return false;
+ }
+ if ( od_s0.getNumberOfProteinDomains() != 1 ) {
+ return false;
+ }
+ }
+ catch ( final Exception e ) {
+ e.printStackTrace( System.out );
+ return false;
+ }
+ return true;
+ }
+
+ public static boolean testEngulfingOverlapRemoval() {
+ try {
+ final Domain d0 = new BasicDomain( "d0", 0, 8, ( short ) 1, ( short ) 1, 0.1, 1 );
+ final Domain d1 = new BasicDomain( "d1", 0, 1, ( short ) 1, ( short ) 1, 0.1, 1 );
+ final Domain d2 = new BasicDomain( "d2", 0, 2, ( short ) 1, ( short ) 1, 0.1, 1 );
+ final Domain d3 = new BasicDomain( "d3", 7, 8, ( short ) 1, ( short ) 1, 0.1, 1 );
+ final Domain d4 = new BasicDomain( "d4", 7, 9, ( short ) 1, ( short ) 1, 0.1, 1 );
+ final Domain d5 = new BasicDomain( "d4", 0, 9, ( short ) 1, ( short ) 1, 0.1, 1 );
+ final Domain d6 = new BasicDomain( "d4", 4, 5, ( short ) 1, ( short ) 1, 0.1, 1 );
+ final List<Boolean> covered = new ArrayList<Boolean>();
+ covered.add( true ); // 0
+ covered.add( false ); // 1
+ covered.add( true ); // 2
+ covered.add( false ); // 3
+ covered.add( true ); // 4
+ covered.add( true ); // 5
+ covered.add( false ); // 6
+ covered.add( true ); // 7
+ covered.add( true ); // 8
+ if ( ForesterUtil.isEngulfed( d0, covered ) ) {
+ return false;
+ }
+ if ( ForesterUtil.isEngulfed( d1, covered ) ) {
+ return false;
+ }
+ if ( ForesterUtil.isEngulfed( d2, covered ) ) {
+ return false;
+ }
+ if ( !ForesterUtil.isEngulfed( d3, covered ) ) {
+ return false;
+ }
+ if ( ForesterUtil.isEngulfed( d4, covered ) ) {
+ return false;
+ }
+ if ( ForesterUtil.isEngulfed( d5, covered ) ) {
+ return false;
+ }
+ if ( !ForesterUtil.isEngulfed( d6, covered ) ) {
+ return false;
+ }
+ final Domain a = new BasicDomain( "a", 0, 10, ( short ) 1, ( short ) 1, 0.1, 1 );
+ final Domain b = new BasicDomain( "b", 8, 20, ( short ) 1, ( short ) 1, 0.2, 1 );
+ final Domain c = new BasicDomain( "c", 15, 16, ( short ) 1, ( short ) 1, 0.3, 1 );
+ final Protein abc = new BasicProtein( "abc", "nemve", 0 );
+ abc.addProteinDomain( a );
+ abc.addProteinDomain( b );
+ abc.addProteinDomain( c );
+ final Protein abc_r1 = ForesterUtil.removeOverlappingDomains( 3, false, abc );
+ final Protein abc_r2 = ForesterUtil.removeOverlappingDomains( 3, true, abc );
+ if ( abc.getNumberOfProteinDomains() != 3 ) {
+ return false;
+ }
+ if ( abc_r1.getNumberOfProteinDomains() != 3 ) {
+ return false;
+ }
+ if ( abc_r2.getNumberOfProteinDomains() != 2 ) {
+ return false;
+ }
+ if ( !abc_r2.getProteinDomain( 0 ).getDomainId().equals( "a" ) ) {
+ return false;
+ }
+ if ( !abc_r2.getProteinDomain( 1 ).getDomainId().equals( "b" ) ) {
+ return false;
+ }
+ final Domain d = new BasicDomain( "d", 0, 10, ( short ) 1, ( short ) 1, 0.1, 1 );
+ final Domain e = new BasicDomain( "e", 8, 20, ( short ) 1, ( short ) 1, 0.3, 1 );
+ final Domain f = new BasicDomain( "f", 15, 16, ( short ) 1, ( short ) 1, 0.2, 1 );
+ final Protein def = new BasicProtein( "def", "nemve", 0 );
+ def.addProteinDomain( d );
+ def.addProteinDomain( e );
+ def.addProteinDomain( f );
+ final Protein def_r1 = ForesterUtil.removeOverlappingDomains( 5, false, def );
+ final Protein def_r2 = ForesterUtil.removeOverlappingDomains( 5, true, def );
+ if ( def.getNumberOfProteinDomains() != 3 ) {
+ return false;
+ }
+ if ( def_r1.getNumberOfProteinDomains() != 3 ) {
+ return false;
+ }
+ if ( def_r2.getNumberOfProteinDomains() != 3 ) {
+ return false;
+ }
+ if ( !def_r2.getProteinDomain( 0 ).getDomainId().equals( "d" ) ) {
+ return false;
+ }
+ if ( !def_r2.getProteinDomain( 1 ).getDomainId().equals( "f" ) ) {
+ return false;
+ }
+ if ( !def_r2.getProteinDomain( 2 ).getDomainId().equals( "e" ) ) {
+ return false;
+ }
+ }
+ catch ( final Exception e ) {
+ e.printStackTrace( System.out );
+ return false;
+ }
+ return true;
+ }
+
public static boolean isEqual( final double a, final double b ) {
return ( ( Math.abs( a - b ) ) < Test.ZERO_DIFF );
}
System.out.println( "failed." );
failed++;
}
- if ( PERFORM_DB_TESTS ) {
- System.out.print( "Ebi Entry Retrieval: " );
- if ( Test.testEbiEntryRetrieval() ) {
- System.out.println( "OK." );
- succeeded++;
- }
- else {
- System.out.println( "failed." );
- failed++;
- }
- }
- System.exit( 0 );
System.out.print( "UniProtKB id extraction: " );
if ( Test.testExtractUniProtKbProteinSeqIdentifier() ) {
System.out.println( "OK." );
failed++;
}
if ( PERFORM_DB_TESTS ) {
+ System.out.print( "Ebi Entry Retrieval: " );
+ if ( Test.testEbiEntryRetrieval() ) {
+ System.out.println( "OK." );
+ succeeded++;
+ }
+ else {
+ System.out.println( "failed." );
+ failed++;
+ }
+ }
+ // System.exit( 0 );
+ if ( PERFORM_DB_TESTS ) {
System.out.print( "Sequence DB tools 2: " );
if ( testSequenceDbWsTools2() ) {
System.out.println( "OK." );
System.exit( -1 );
}
}
+ // System.exit( 0 );
System.out.print( "Hmmscan output parser: " );
if ( testHmmscanOutputParser() ) {
System.out.println( "OK." );
System.out.println( "failed." );
failed++;
}
+ //
+ System.out.print( "Overlap removal: " );
+ if ( !org.forester.test.Test.testOverlapRemoval() ) {
+ System.out.println( "failed." );
+ failed++;
+ }
+ else {
+ succeeded++;
+ }
+ System.out.println( "OK." );
+ System.out.print( "Engulfing overlap removal: " );
+ if ( !Test.testEngulfingOverlapRemoval() ) {
+ System.out.println( "failed." );
+ failed++;
+ }
+ else {
+ succeeded++;
+ }
+ System.out.println( "OK." );
+ //
System.out.print( "Taxonomy code extraction: " );
if ( Test.testExtractTaxonomyCodeFromNodeName() ) {
System.out.println( "OK." );
System.out.println( "failed." );
failed++;
}
+ System.out.print( "Tree copy: " );
+ if ( Test.testTreeCopy() ) {
+ System.out.println( "OK." );
+ succeeded++;
+ }
+ else {
+ System.out.println( "failed." );
+ failed++;
+ }
System.out.print( "Basic tree methods: " );
if ( Test.testBasicTreeMethods() ) {
System.out.println( "OK." );
private static boolean testBasicPhyloXMLparsing() {
try {
final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
- final PhyloXmlParser xml_parser = new PhyloXmlParser();
+ final PhyloXmlParser xml_parser = PhyloXmlParser.createPhyloXmlParser();
final Phylogeny[] phylogenies_0 = factory.create( Test.PATH_TO_TEST_DATA + "phyloxml_test_t1.xml",
xml_parser );
if ( xml_parser.getErrorCount() > 0 ) {
private static boolean testBasicPhyloXMLparsingRoundtrip() {
try {
final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
- final PhyloXmlParser xml_parser = new PhyloXmlParser();
+ final PhyloXmlParser xml_parser = PhyloXmlParser.createPhyloXmlParser();
if ( USE_LOCAL_PHYLOXML_SCHEMA ) {
xml_parser.setValidateAgainstSchema( PHYLOXML_LOCAL_XSD );
}
// Do nothing -- means were not running from jar.
}
if ( xml_parser == null ) {
- xml_parser = new PhyloXmlParser();
+ xml_parser = PhyloXmlParser.createPhyloXmlParser();
if ( USE_LOCAL_PHYLOXML_SCHEMA ) {
xml_parser.setValidateAgainstSchema( PHYLOXML_LOCAL_XSD );
}
return true;
}
+ private static boolean testTreeCopy() {
+ try {
+ final String str_0 = "((((a,b),c),d)[&&NHX:S=lizards],e[&&NHX:S=reptiles])r[&&NHX:S=animals]";
+ final Phylogeny t0 = Phylogeny.createInstanceFromNhxString( str_0 );
+ final Phylogeny t1 = t0.copy();
+ if ( !t1.toNewHampshireX().equals( t0.toNewHampshireX() ) ) {
+ return false;
+ }
+ if ( !t1.toNewHampshireX().equals( str_0 ) ) {
+ return false;
+ }
+ t0.deleteSubtree( t0.getNode( "c" ), true );
+ t0.deleteSubtree( t0.getNode( "a" ), true );
+ t0.getRoot().getNodeData().getTaxonomy().setScientificName( "metazoa" );
+ t0.getNode( "b" ).setName( "Bee" );
+ if ( !t0.toNewHampshireX().equals( "((Bee,d)[&&NHX:S=lizards],e[&&NHX:S=reptiles])r[&&NHX:S=metazoa]" ) ) {
+ return false;
+ }
+ if ( !t1.toNewHampshireX().equals( str_0 ) ) {
+ return false;
+ }
+ t0.deleteSubtree( t0.getNode( "e" ), true );
+ t0.deleteSubtree( t0.getNode( "Bee" ), true );
+ t0.deleteSubtree( t0.getNode( "d" ), true );
+ if ( !t1.toNewHampshireX().equals( str_0 ) ) {
+ return false;
+ }
+ }
+ catch ( final Exception e ) {
+ e.printStackTrace();
+ return false;
+ }
+ return true;
+ }
+
private static boolean testCreateBalancedPhylogeny() {
try {
final Phylogeny p0 = DevelopmentTools.createBalancedPhylogeny( 6, 5 );
// Do nothing -- means were not running from jar.
}
if ( xml_parser == null ) {
- xml_parser = new PhyloXmlParser();
+ xml_parser = PhyloXmlParser.createPhyloXmlParser();
if ( USE_LOCAL_PHYLOXML_SCHEMA ) {
xml_parser.setValidateAgainstSchema( PHYLOXML_LOCAL_XSD );
}
System.out.println( acc.toString() );
return false;
}
+ n.setName( "gi|71845847|1,4-alpha-glucan branching enzyme [Dechloromonas aromatica RCB]" );
+ acc = SequenceDbWsTools.obtainSeqAccession( n );
+ if ( ( acc == null ) || !acc.getSource().equals( Source.GI.toString() )
+ || !acc.getValue().equals( "71845847" ) ) {
+ System.out.println( acc.toString() );
+ return false;
+ }
+ n.setName( "gi|71845847|gb|AAZ45343.1| 1,4-alpha-glucan branching enzyme [Dechloromonas aromatica RCB]" );
+ acc = SequenceDbWsTools.obtainSeqAccession( n );
+ if ( ( acc == null ) || !acc.getSource().equals( Source.NCBI.toString() )
+ || !acc.getValue().equals( "AAZ45343.1" ) ) {
+ System.out.println( acc.toString() );
+ return false;
+ }
}
catch ( final Exception e ) {
return false;
}
final PhylogenyNode n2 = new PhylogenyNode( "NM_001030253" );
SequenceDbWsTools.obtainSeqInformation( n2 );
- System.out.println( n2.toString() );
if ( !n2.getNodeData().getSequence().getName()
.equals( "Danio rerio B-cell leukemia/lymphoma 2 (bcl2), mRNA" ) ) {
return false;
}
final PhylogenyNode n3 = new PhylogenyNode( "NM_184234.2" );
SequenceDbWsTools.obtainSeqInformation( n3 );
- System.out.println( "n=" + n3.toString() );
if ( !n3.getNodeData().getSequence().getName()
.equals( "Homo sapiens RNA binding motif protein 39 (RBM39), transcript variant 1, mRNA" ) ) {
return false;
if ( !entry4.getAccession().equals( "AAA36557" ) ) {
return false;
}
+ if ( !entry4.getTaxonomyScientificName().equals( "Homo sapiens" ) ) {
+ System.out.println( entry4.getTaxonomyScientificName() );
+ return false;
+ }
+ if ( !entry4.getSequenceName().equals( "Homo sapiens (human) ras protein" ) ) {
+ System.out.println( entry4.getSequenceName() );
+ return false;
+ }
+ if ( !entry4.getTaxonomyIdentifier().equals( "9606" ) ) {
+ System.out.println( entry4.getTaxonomyIdentifier() );
+ return false;
+ }
+ if ( !entry4.getGeneName().equals( "ras" ) ) {
+ System.out.println( entry4.getGeneName() );
+ return false;
+ }
+ // if ( !entry4.getChromosome().equals( "ras" ) ) {
+ // System.out.println( entry4.getChromosome() );
+ // return false;
+ // }
+ // if ( !entry4.getMap().equals( "ras" ) ) {
+ // System.out.println( entry4.getMap() );
+ // return false;
+ // }
+ //TODO FIXME gi...
//
- final SequenceDatabaseEntry entry5 = SequenceDbWsTools.obtainEntry( "M30539" );
- if ( !entry5.getAccession().equals( "HM043801" ) ) {
+ //TODO fails:
+ // final SequenceDatabaseEntry entry5 = SequenceDbWsTools.obtainEntry( "M30539" );
+ // if ( !entry5.getAccession().equals( "HM043801" ) ) {
+ // return false;
+ // }
+ final SequenceDatabaseEntry entry5 = SequenceDbWsTools.obtainEntry( "AAZ45343.1" );
+ if ( !entry5.getAccession().equals( "AAZ45343" ) ) {
+ return false;
+ }
+ if ( !entry5.getTaxonomyScientificName().equals( "Dechloromonas aromatica RCB" ) ) {
+ System.out.println( entry5.getTaxonomyScientificName() );
+ return false;
+ }
+ if ( !entry5.getSequenceName().equals( "Dechloromonas aromatica RCB 1,4-alpha-glucan branching enzyme" ) ) {
+ System.out.println( entry5.getSequenceName() );
+ return false;
+ }
+ if ( !entry5.getTaxonomyIdentifier().equals( "159087" ) ) {
+ System.out.println( entry5.getTaxonomyIdentifier() );
return false;
}
}
git://source.jalview.org / jalview.git / blobdiff