import org.forester.io.parsers.phyloxml.PhyloXmlParser;
import org.forester.io.parsers.tol.TolParser;
import org.forester.io.writers.PhylogenyWriter;
+import org.forester.msa.BasicMsa;
import org.forester.msa.Mafft;
import org.forester.msa.Msa;
import org.forester.msa.MsaInferrer;
+import org.forester.msa.MsaMethods;
import org.forester.pccx.TestPccx;
import org.forester.phylogeny.Phylogeny;
import org.forester.phylogeny.PhylogenyBranch;
import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
import org.forester.phylogeny.factories.PhylogenyFactory;
import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
+import org.forester.protein.Protein;
import org.forester.sdi.SDI;
import org.forester.sdi.SDIR;
import org.forester.sdi.SDIse;
import org.forester.sdi.TestGSDI;
import org.forester.sequence.BasicSequence;
import org.forester.sequence.Sequence;
-import org.forester.surfacing.Protein;
import org.forester.surfacing.TestSurfacing;
import org.forester.tools.ConfidenceAssessor;
import org.forester.tools.SupportCount;
import org.forester.util.ForesterConstants;
import org.forester.util.ForesterUtil;
import org.forester.util.GeneralTable;
+import org.forester.util.SequenceIdParser;
import org.forester.ws.uniprot.DatabaseTools;
import org.forester.ws.uniprot.SequenceDatabaseEntry;
import org.forester.ws.uniprot.UniProtTaxonomy;
System.exit( -1 );
}
final long start_time = new Date().getTime();
+
+
+
+ System.out.print( "Sequence id parsing: " );
+ if ( testSequenceIdParsing() ) {
+ System.out.println( "OK." );
+ succeeded++;
+ }
+ else {
+ System.out.println( "failed." );
+ System.exit( -1 ); //TODO FIXME remove me!! ~
+ failed++;
+ }
System.out.print( "Hmmscan output parser: " );
if ( testHmmscanOutputParser() ) {
System.out.println( "OK." );
System.out.println( "failed." );
failed++;
}
+ System.out.print( "Simple MSA quality: " );
+ if ( Test.testMsaQualityMethod() ) {
+ System.out.println( "OK." );
+ succeeded++;
+ }
+ else {
+ System.out.println( "failed." );
+ failed++;
+ }
// System.out.print( "WABI TxSearch: " );
// if ( Test.testWabiTxSearch() ) {
// System.out.println( "OK." );
dss3.addValue( 10 );
final AsciiHistogram histo = new AsciiHistogram( dss3 );
histo.toStringBuffer( 10, '=', 40, 5 );
- histo.toStringBuffer( 3, 8, 10, '=', 40, 5 );
+ histo.toStringBuffer( 3, 8, 10, '=', 40, 5, null );
}
catch ( final Exception e ) {
e.printStackTrace( System.out );
if ( p1.getNumberOfProteinDomains() != 15 ) {
return false;
}
+ if ( p1.getLength() != 850 ) {
+ return false;
+ }
final Protein p2 = proteins.get( 1 );
if ( p2.getNumberOfProteinDomains() != 51 ) {
return false;
}
+ if ( p2.getLength() != 1291 ) {
+ return false;
+ }
final Protein p3 = proteins.get( 2 );
if ( p3.getNumberOfProteinDomains() != 2 ) {
return false;
if ( p53.getNode( "B (x (a' ,b) f(x);" ) == null ) {
return false;
}
+ //
+ final Phylogeny p54 = factory.create( new StringBuffer( "((A,B):[88],C)" ), new NHXParser() )[ 0 ];
+ if ( p54.getNode( "A" ) == null ) {
+ return false;
+ }
+ if ( !p54.toNewHampshire( false, NH_CONVERSION_SUPPORT_VALUE_STYLE.IN_SQUARE_BRACKETS )
+ .equals( "((A,B)[88],C);" ) ) {
+ return false;
+ }
}
catch ( final Exception e ) {
e.printStackTrace( System.out );
if ( !b.getName().equals( "n10_ECOLI1/1-2" ) ) {
return false;
}
- if ( !PhylogenyMethods.getSpecies( b ).equals( "ECOLI" ) ) {
+ if ( !PhylogenyMethods.getSpecies( b ).equals( "" ) ) {
return false;
}
final PhylogenyNode c = PhylogenyNode
if ( !c.getName().equals( "n10_RATAF12/1000-2000" ) ) {
return false;
}
- if ( !PhylogenyMethods.getSpecies( c ).equals( "RATAF" ) ) {
+ if ( !PhylogenyMethods.getSpecies( c ).equals( "" ) ) {
+ return false;
+ }
+ final PhylogenyNode c1 = PhylogenyNode
+ .createInstanceFromNhxString( "n10_BOVIN_1/1000-2000",
+ PhylogenyMethods.TAXONOMY_EXTRACTION.PFAM_STYLE_ONLY );
+ if ( !c1.getName().equals( "n10_BOVIN_1/1000-2000" ) ) {
+ return false;
+ }
+ if ( !PhylogenyMethods.getSpecies( c1 ).equals( "BOVIN" ) ) {
+ return false;
+ }
+ final PhylogenyNode c2 = PhylogenyNode
+ .createInstanceFromNhxString( "n10_Bovin_1/1000-2000",
+ PhylogenyMethods.TAXONOMY_EXTRACTION.PFAM_STYLE_ONLY );
+ if ( !c2.getName().equals( "n10_Bovin_1/1000-2000" ) ) {
+ return false;
+ }
+ if ( !PhylogenyMethods.getSpecies( c2 ).equals( "" ) ) {
return false;
}
final PhylogenyNode d = PhylogenyNode
try {
final String msa_str_0 = "seq1 abcd\n\nseq2 efgh\n";
final Msa msa_0 = GeneralMsaParser.parse( new ByteArrayInputStream( msa_str_0.getBytes() ) );
- final String msa_str_1 = "seq_1 abc\nseq2 ghi\nseq_1 def\nseq2 jkm\n";
+ final String msa_str_1 = "seq1 abc\nseq2 ghi\nseq1 def\nseq2 jkm\n";
final Msa msa_1 = GeneralMsaParser.parse( new ByteArrayInputStream( msa_str_1.getBytes() ) );
final String msa_str_2 = "seq1 abc\nseq2 ghi\n\ndef\njkm\n";
final Msa msa_2 = GeneralMsaParser.parse( new ByteArrayInputStream( msa_str_2.getBytes() ) );
final String msa_str_3 = "seq1 abc\n def\nseq2 ghi\n jkm\n";
final Msa msa_3 = GeneralMsaParser.parse( new ByteArrayInputStream( msa_str_3.getBytes() ) );
+ if ( !msa_1.getSequenceAsString( 0 ).toString().equalsIgnoreCase( "abcdef" ) ) {
+ return false;
+ }
+ if ( !msa_1.getSequenceAsString( 1 ).toString().equalsIgnoreCase( "ghixkm" ) ) {
+ return false;
+ }
+ if ( !msa_1.getIdentifier( 0 ).toString().equals( "seq1" ) ) {
+ return false;
+ }
+ if ( !msa_1.getIdentifier( 1 ).toString().equals( "seq2" ) ) {
+ return false;
+ }
+ if ( !msa_2.getSequenceAsString( 0 ).toString().equalsIgnoreCase( "abcdef" ) ) {
+ return false;
+ }
+ if ( !msa_2.getSequenceAsString( 1 ).toString().equalsIgnoreCase( "ghixkm" ) ) {
+ return false;
+ }
+ if ( !msa_2.getIdentifier( 0 ).toString().equals( "seq1" ) ) {
+ return false;
+ }
+ if ( !msa_2.getIdentifier( 1 ).toString().equals( "seq2" ) ) {
+ return false;
+ }
+ if ( !msa_3.getSequenceAsString( 0 ).toString().equalsIgnoreCase( "abcdef" ) ) {
+ return false;
+ }
+ if ( !msa_3.getSequenceAsString( 1 ).toString().equalsIgnoreCase( "ghixkm" ) ) {
+ return false;
+ }
+ if ( !msa_3.getIdentifier( 0 ).toString().equals( "seq1" ) ) {
+ return false;
+ }
+ if ( !msa_3.getIdentifier( 1 ).toString().equals( "seq2" ) ) {
+ return false;
+ }
final Msa msa_4 = GeneralMsaParser.parse( new FileInputStream( PATH_TO_TEST_DATA + "msa_1.txt" ) );
if ( !msa_4.getSequenceAsString( 0 ).toString().equalsIgnoreCase( "abcdefeeeeeeeexx" ) ) {
return false;
opts.add( "--quiet" );
Msa msa = null;
final MsaInferrer mafft = Mafft.createInstance();
- msa = mafft.infer( new File( PATH_TO_TEST_DATA + "ncbi.fasta" ), opts );
- if ( ( msa == null ) || ( msa.getLength() < 10 ) || ( msa.getNumberOfSequences() != 19 ) ) {
+ msa = mafft.infer( new File( PATH_TO_TEST_DATA + "ncbi_sn.fasta" ), opts );
+ if ( ( msa == null ) || ( msa.getLength() < 20 ) || ( msa.getNumberOfSequences() != 19 ) ) {
+ return false;
+ }
+ if ( !msa.getIdentifier( 0 ).toString().equals( "a" ) ) {
return false;
}
}
}
return true;
}
+
+ private static boolean testMsaQualityMethod() {
+ try {
+ final Sequence s0 = BasicSequence.createAaSequence( "a", "ABAXEFGHIJ" );
+ final Sequence s1 = BasicSequence.createAaSequence( "a", "ABBXEFGHIJ" );
+ final Sequence s2 = BasicSequence.createAaSequence( "a", "AXCXEFGHIJ" );
+ final Sequence s3 = BasicSequence.createAaSequence( "a", "AXDDEFGHIJ" );
+ final List<Sequence> l = new ArrayList<Sequence>();
+ l.add( s0 );
+ l.add( s1 );
+ l.add( s2 );
+ l.add( s3 );
+ final Msa msa = BasicMsa.createInstance( l );
+ if ( !isEqual( 1, MsaMethods.calculateIdentityRatio( msa, 0 ) ) ) {
+ return false;
+ }
+ if ( !isEqual( 0.5, MsaMethods.calculateIdentityRatio( msa, 1 ) ) ) {
+ return false;
+ }
+ if ( !isEqual( 0.25, MsaMethods.calculateIdentityRatio( msa, 2 ) ) ) {
+ return false;
+ }
+ if ( !isEqual( 0.75, MsaMethods.calculateIdentityRatio( msa, 3 ) ) ) {
+ return false;
+ }
+ }
+ catch ( final Exception e ) {
+ e.printStackTrace( System.out );
+ return false;
+ }
+ return true;
+ }
+
+ private static boolean testSequenceIdParsing() {
+ try {
+ Identifier id = SequenceIdParser.parse( "gb_ADF31344_segmented_worms_" );
+ if ( id == null
+ || ForesterUtil.isEmpty( id.getValue() )
+ || ForesterUtil.isEmpty( id.getProvider() )
+ || !id.getValue().equals( "ADF31344" )
+ || !id.getProvider().equals( "genbank" ) ) {
+ if ( id != null ) {
+ System.out.println( "value =" + id.getValue() );
+ System.out.println( "provider=" + id.getProvider() );
+ }
+ return false;
+ }
+ //
+ id = SequenceIdParser.parse( "segmented worms|gb_ADF31344" );
+ if ( id == null
+ || ForesterUtil.isEmpty( id.getValue() )
+ || ForesterUtil.isEmpty( id.getProvider() )
+ || !id.getValue().equals( "ADF31344" )
+ || !id.getProvider().equals( "genbank" ) ) {
+ if ( id != null ) {
+ System.out.println( "value =" + id.getValue() );
+ System.out.println( "provider=" + id.getProvider() );
+ }
+ return false;
+ }
+ //
+ id = SequenceIdParser.parse( "segmented worms gb_ADF31344 and more" );
+ if ( id == null
+ || ForesterUtil.isEmpty( id.getValue() )
+ || ForesterUtil.isEmpty( id.getProvider() )
+ || !id.getValue().equals( "ADF31344" )
+ || !id.getProvider().equals( "genbank" ) ) {
+ if ( id != null ) {
+ System.out.println( "value =" + id.getValue() );
+ System.out.println( "provider=" + id.getProvider() );
+ }
+ return false;
+ }
+
+ //
+ id = SequenceIdParser.parse( "gb_AAA96518_1" );
+ if ( id == null
+ || ForesterUtil.isEmpty( id.getValue() )
+ || ForesterUtil.isEmpty( id.getProvider() )
+ || !id.getValue().equals( "AAA96518" )
+ || !id.getProvider().equals( "genbank" ) ) {
+ if ( id != null ) {
+ System.out.println( "value =" + id.getValue() );
+ System.out.println( "provider=" + id.getProvider() );
+ }
+ return false;
+ }
+ //
+ id = SequenceIdParser.parse( "gb_EHB07727_1_rodents_" );
+ if ( id == null
+ || ForesterUtil.isEmpty( id.getValue() )
+ || ForesterUtil.isEmpty( id.getProvider() )
+ || !id.getValue().equals( "EHB07727" )
+ || !id.getProvider().equals( "genbank" ) ) {
+ if ( id != null ) {
+ System.out.println( "value =" + id.getValue() );
+ System.out.println( "provider=" + id.getProvider() );
+ }
+ return false;
+ }
+ //
+ id = SequenceIdParser.parse( "dbj_BAF37827_1_turtles_" );
+ if ( id == null
+ || ForesterUtil.isEmpty( id.getValue() )
+ || ForesterUtil.isEmpty( id.getProvider() )
+ || !id.getValue().equals( "BAF37827" )
+ || !id.getProvider().equals( "genbank" ) ) {
+ if ( id != null ) {
+ System.out.println( "value =" + id.getValue() );
+ System.out.println( "provider=" + id.getProvider() );
+ }
+ return false;
+ }
+ //
+ id = SequenceIdParser.parse( "emb_CAA73223_1_primates_" );
+ if ( id == null
+ || ForesterUtil.isEmpty( id.getValue() )
+ || ForesterUtil.isEmpty( id.getProvider() )
+ || !id.getValue().equals( "CAA73223" )
+ || !id.getProvider().equals( "genbank" ) ) {
+ if ( id != null ) {
+ System.out.println( "value =" + id.getValue() );
+ System.out.println( "provider=" + id.getProvider() );
+ }
+ return false;
+ }
+ //
+// id = SequenceIdParser.parse( "mites|ref_XP_002434188_1" );
+// if ( id == null
+// || ForesterUtil.isEmpty( id.getValue() )
+// || ForesterUtil.isEmpty( id.getProvider() )
+// || !id.getValue().equals( "002434188" )
+// || !id.getProvider().equals( "genbank" ) ) {
+// if ( id != null ) {
+// System.out.println( "value =" + id.getValue() );
+// System.out.println( "provider=" + id.getProvider() );
+// }
+// return false;
+// }
+
+ // lcl_91970_unknown_
+ }
+ catch ( final Exception e ) {
+ e.printStackTrace( System.out );
+ return false;
+ }
+ return true;
+ }
}
git://source.jalview.org / jalview.git / blobdiff