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;
return false;
}
if ( !p50.toNewHampshire( false, NH_CONVERSION_SUPPORT_VALUE_STYLE.IN_SQUARE_BRACKETS )
- .equals( "((A,B)ab:2.0[88.0],C);" ) ) {
+ .equals( "((A,B)ab:2.0[88],C);" ) ) {
return false;
}
if ( !p50.toNewHampshire( false, NH_CONVERSION_SUPPORT_VALUE_STYLE.NONE ).equals( "((A,B)ab:2.0,C);" ) ) {
return false;
}
if ( !p50.toNewHampshire( false, NH_CONVERSION_SUPPORT_VALUE_STYLE.AS_INTERNAL_NODE_NAMES )
- .equals( "((A,B)88.0:2.0,C);" ) ) {
+ .equals( "((A,B)88:2.0,C);" ) ) {
return false;
}
final Phylogeny p51 = factory.create( new StringBuffer( "((\"A(A\",B)ab:2[88],C)" ), new NHXParser() )[ 0 ];
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 );
return false;
}
if ( !n5.toNewHampshireX()
- .equals( "n5:0.1[&&NHX:T=1:S=Ecoli:D=Y:XN=S=tag1=value1=unit1:B=56.0:W=2.0:C=10.20.30]" ) ) {
+ .equals( "n5:0.1[&&NHX:T=1:S=Ecoli:D=Y:XN=S=tag1=value1=unit1:B=56:W=2.0:C=10.20.30]" ) ) {
return false;
}
- if ( !n6.toNewHampshireX()
- .equals( "n6:1.0E-6[&&NHX:T=1:S=Ecoli:D=N:XN=B=bool_tag=T:B=100.0:W=2.0:C=0.0.0]" ) ) {
+ if ( !n6.toNewHampshireX().equals( "n6:1.0E-6[&&NHX:T=1:S=Ecoli:D=N:XN=B=bool_tag=T:B=100:W=2.0:C=0.0.0]" ) ) {
return false;
}
}
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
return false;
}
final Phylogeny p9 = factory.create( "((A:0.2,B:0.3):0.5[91],C:0.1)root:0.1[100]", new NHXParser() )[ 0 ];
- if ( !p9.toNewHampshireX().equals( "((A:0.2,B:0.3):0.5[&&NHX:B=91.0],C:0.1)root:0.1[&&NHX:B=100.0]" ) ) {
+ if ( !p9.toNewHampshireX().equals( "((A:0.2,B:0.3):0.5[&&NHX:B=91],C:0.1)root:0.1[&&NHX:B=100]" ) ) {
return false;
}
final Phylogeny p10 = factory
.create( " [79] ( (A [co mment] :0 .2[comment],B:0.3[com])[com ment]: 0. 5 \t[ 9 1 ][ comment],C: 0.1)[comment]root:0.1[100] [comment]",
new NHXParser() )[ 0 ];
- if ( !p10.toNewHampshireX().equals( "((A:0.2,B:0.3):0.5[&&NHX:B=91.0],C:0.1)root:0.1[&&NHX:B=100.0]" ) ) {
+ if ( !p10.toNewHampshireX().equals( "((A:0.2,B:0.3):0.5[&&NHX:B=91],C:0.1)root:0.1[&&NHX:B=100]" ) ) {
return false;
}
}
final Phylogeny p10 = factory
.create( " [79] ( (\"A \n\tB \" [co mment] :0 .2[comment],'B':0.3[com])[com ment]: 0. 5 \t[ 9 1 ][ comment],'C (or D?\\//;,))': 0.1)[comment]'\nroot is here (cool, was! ) ':0.1[100] [comment]",
new NHXParser() )[ 0 ];
- final String p10_clean_str = "(('A B':0.2,B:0.3):0.5[&&NHX:B=91.0],'C (or D?\\//;,))':0.1)'root is here (cool, was! )':0.1[&&NHX:B=100.0]";
+ final String p10_clean_str = "(('A B':0.2,B:0.3):0.5[&&NHX:B=91],'C (or D?\\//;,))':0.1)'root is here (cool, was! )':0.1[&&NHX:B=100]";
if ( !p10.toNewHampshireX().equals( p10_clean_str ) ) {
return false;
}
final Phylogeny p12 = factory
.create( " [79] ( (\"A \n\tB \" [[][] :0 .2[comment][\t&\t&\n N\tH\tX:S=mo\tnkey !],'\tB\t\b\t\n\f\rB B ':0.0\b3[])\t[com ment]: 0. 5 \t[ 9 1 ][ \ncomment],'C\t (or D?\\//;,))': 0.\b1)[comment]'\nroot \tis here (cool, \b\t\n\f\r was! ) ':0.1[100] [comment]",
new NHXParser() )[ 0 ];
- final String p12_clean_str = "(('A B':0.2[&&NHX:S=monkey!],'BB B':0.03):0.5[&&NHX:B=91.0],'C (or D?\\//;,))':0.1)'root is here (cool, was! )':0.1[&&NHX:B=100.0]";
+ final String p12_clean_str = "(('A B':0.2[&&NHX:S=monkey!],'BB B':0.03):0.5[&&NHX:B=91],'C (or D?\\//;,))':0.1)'root is here (cool, was! )':0.1[&&NHX:B=100]";
if ( !p12.toNewHampshireX().equals( p12_clean_str ) ) {
return false;
}
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( "mites|ref_XP_002434188_1" );
+ if ( id == null || ForesterUtil.isEmpty( id.getValue() ) || !id.getValue().equals( "002434188_1" ) ) {
+ return false;
+ }
+ }
+ catch ( final Exception e ) {
+ e.printStackTrace( System.out );
+ return false;
+ }
+ return true;
+ }
}