public void TestReadSampleGenbankFileAsTextReaderObj () {
using ( reader = new BioPatMBF_Reader() ) {
System.Diagnostics.Debug.WriteLine( reader.Read(
Global.GetResourceReader( _sampleGenBankFile1 )
) );
}
}
public void TestMotifPattern_Motif () {
BiopatMLFilePath = "BioPaperTestData/MotifPattern/Motif.xml";
using ( BioPatMBF_Reader gbReader = new BioPatMBF_Reader() ) {
BioList = gbReader.Read( Global.GetResourceReader( _singleDnaSeqGenBankFilename ) );
}
MyPatterns = DefinitionIO.Read( Global.GetResourceReader( BiopatMLFilePath ) );
FeatureList Matches = BioList[0].Search( SearchPosition, BioList[0].Length, MyPatterns.Pattern );
//According to Jacobi library total matches should be 57
Assert.AreEqual( 57, Matches.Count );
Assert.AreEqual( "Pribnow-box", Matches.Name );
//Perform some random checks from the 57 list
Match matched = (Match) Matches[10]; //try get the 11th matched
Assert.AreEqual( 0.66, matched.Similarity, 1e-2 );
Assert.AreEqual( 6, matched.Length );
Assert.AreEqual( "ttttat", matched.Letters() );
//try the first match
matched = (Match) Matches[0];
Assert.AreEqual( AlphabetFactory.Instance( AlphabetType.DNA ), matched.Alphabet );
Assert.AreEqual( 6, matched.Length );
Assert.AreEqual( 0.5, matched.Similarity, 1e-2 );
// Check the last match
matched = (Match) Matches[56];
Assert.AreEqual( 0.5, matched.Similarity, 1e-2 );
Assert.AreEqual( "tttctt", matched.Letters() );
}
public void TestStructuredPattern_SeriesAll()
{
BiopatMLFilePath = "BioPaperTestData/StructuredPattern/SeriesAll.xml";
using (BioPatMBF_Reader gbReader = new BioPatMBF_Reader())
{
BioList = gbReader.Read( Global.GetResourceReader( _singleDnaSeqGenBankFilename ) );
}
MyPatterns = DefinitionIO.Read( Global.GetResourceReader( BiopatMLFilePath ) );
FeatureList Matches = BioList[0].Search( SearchPosition, BioList[0].Length, MyPatterns.Pattern );
//expecting 49 matches based on the old jacobi result
Assert.AreEqual(49, Matches.Count);
Match matched = (Match)Matches[0]; //Query the 1st matched from the list of matches
Assert.AreEqual(3, matched.SubMatches.Count); //should have 3 sub matches
Assert.AreEqual("aattt", matched.SubMatches[0].Letters());
Assert.AreEqual("tataagtg", matched.SubMatches[1].Letters());
Assert.AreEqual("ttcaa", matched.SubMatches[2].Letters());
//And finally the main matched
Assert.AreEqual("aattttataagtgttcaa", matched.Letters());
}
public void TestReadSampleGenbankFileAsFilePath () {
using ( reader = new BioPatMBF_Reader() ) {
// TODO: this is not a unit test. We need some way of automatically determining if it worked.
System.Diagnostics.Debug.WriteLine( reader.Read(
Global.GetResourceReader( _sampleGenBankFile2 )
) );
}
}
public void TestRegionalPattern_Gap () {
BiopatMLFilePath = "BioPaperTestData/RegionalPattern/RegionalGap.xml";
BioPatMBF_Reader gbReader = new BioPatMBF_Reader();
BioList = gbReader.Read( Global.GetResourceReader( _singleProteinSeqGenBankFilename ) );
MyPatterns = DefinitionIO.Read( Global.GetResourceReader( BiopatMLFilePath ) );
FeatureList Matches = BioList[0].Search( SearchPosition, BioList[0].Length, MyPatterns.Pattern );
//Total matches according to old jacobi is 309
Assert.AreEqual( 410, Matches.Count );
//Checks the first match
Assert.AreEqual( "MT", Matches[0].MainSequence.Letters( Matches[0].Start, Matches[0].End ) );
//Checks if the last Match is in correect start and end pos
Assert.AreEqual( "CE", Matches[409].MainSequence.Letters( Matches[409].Start, Matches[409].End ) );
}
public SequenceContract ParseGenbankFile(string gbContent)
{
StringReader sr = new StringReader(gbContent);
SequenceContract sequence = new SequenceContract();
SequenceList bioSeqList = null; //BioPatML's data structure
using (ReaderBase reader = new BioPatMBF_Reader())
{
bioSeqList = reader.Read(sr);
}
//for now we only always use the first sequence SequenceName
sequence.Name = bioSeqList[0].Annotations("SequenceName").AnnotationValue as string;
//sequence.Name = bioSeqList[0].Name;
sequence.AlphabetName = bioSeqList[0].Alphabet.Name;
sequence.Characters = bioSeqList[0].Letters();
return sequence;
}
public void TestRegionalPattern_Composition () {
BiopatMLFilePath = "BioPaperTestData/RegionalPattern/RegionalComposition.xml";
using ( BioPatMBF_Reader gbReader = new BioPatMBF_Reader() ) {
BioList = gbReader.Read( Global.GetResourceReader( _singleProteinSeqGenBankFilename ) );
}
MyPatterns = DefinitionIO.Read( Global.GetResourceReader( BiopatMLFilePath ) );
FeatureList Matches = BioList[0].Search( SearchPosition, BioList[0].Length, MyPatterns.Pattern );
//Total matches according to old jacobi is 309
Assert.AreEqual( 49, Matches.Count );
//Checks the first match
Assert.AreEqual( "GATLFKTRCLQCHTV", Matches[0].MainSequence.Letters( Matches[0].Start, Matches[0].End ) );
//Check see if the pattern used to match has the correct name for its matches
Assert.AreEqual( "transmembrane domain", Matches.Name );
Assert.AreEqual( 12, Matches[0].Start );
Assert.AreEqual( 26, Matches[0].End );
//Checks if the last Match is in correect start and end pos
Assert.AreEqual( "KDRNDLITYLKKACE", Matches[48].MainSequence.Letters( Matches[48].Start, Matches[48].End ) );
}
/** Tests the match method of a series of patterns with two gaps */
public void TestMatchSigma70InChlamydia () {
SequenceList sequences = null;
using ( BioPatMBF_Reader reader = new BioPatMBF_Reader() ) {
sequences = reader.Read(
Global.GetResourceReader( "data/GenBank/NC_000117-Chlamydia trachomatis D-UW-3CX.gbk" )
);
}
Sequence seq = sequences[0];
SeriesAll series = new SeriesAll();
series.Add( new Motif( "", AlphabetType.DNA, "attata", 1.0 ) );
series.Add( new Gap( "", 1, 200, 1 ) );
series.Add( new Motif( "", AlphabetType.DNA, "tgtcaa", 1.0 ) );
FeatureList matches = seq.Search( 2, seq.Length, series );
Assert.AreEqual( 11, matches.Count );
//Assert.AreEqual( "taaaagcc", matches[0].Letters() );
//Assert.AreEqual( 1.0, ( (Match) matches[0] ).Similarity, 1e-1 );
//Assert.AreEqual( "taaaagccc", matches[1].Letters() );
//Assert.AreEqual( 1.0, ( (Match) matches[1] ).Similarity, 1e-1 );
//Assert.AreEqual( "taaaagccc", matches[2].Letters() );
//Assert.AreEqual( 0.9, ( (Match) matches[2] ).Similarity, 1e-1 );
}
public void TestMotifPattern_PWM () {
BiopatMLFilePath = "BioPaperTestData/MotifPattern/PWM.xml";
using ( BioPatMBF_Reader gbReader = new BioPatMBF_Reader() ) {
BioList = gbReader.Read( Global.GetResourceReader( _sampleGenBankFile2 ) );
}
MyPatterns = DefinitionIO.Read( Global.GetResourceReader( BiopatMLFilePath ) );
FeatureList Matches = BioList[0].Search( SearchPosition, BioList[0].Length, MyPatterns.Pattern );
Assert.AreEqual( 14, Matches.Count );
Assert.AreEqual( "Pribnow-box", Matches.Name );
Match matched = (Match) Matches[0];
Assert.AreEqual( 17, matched.Start );
Assert.AreEqual( 22, matched.End );
Assert.AreEqual( 0.67, matched.Similarity, 1e-2 );
Assert.AreEqual( "tctcct", matched.Letters() );
matched = (Match) Matches[1];
Assert.AreEqual( 25, matched.Start );
Assert.AreEqual( 30, matched.End );
Assert.AreEqual( 0.61, matched.Similarity, 1e-2 );
Assert.AreEqual( "ttggct", matched.Letters() );
matched = (Match) Matches[13];
Assert.AreEqual( 268, matched.Start );
Assert.AreEqual( 273, matched.End );
Assert.AreEqual( 0.67, matched.Similarity, 1e-2 );
Assert.AreEqual( "tgtgct", matched.Letters() );
}
public void TestMotifPattern_Block () {
BiopatMLFilePath = "BioPaperTestData/MotifPattern/Block.xml";
BioPatMBF_Reader gbReader = new BioPatMBF_Reader();
BioList = gbReader.Read( Global.GetResourceReader( _sampleGenBankFile2 ) );
MyPatterns = DefinitionIO.Read( Global.GetResourceReader( BiopatMLFilePath ) );
FeatureList Matches = BioList[0].Search( SearchPosition, BioList[0].Length, MyPatterns.Pattern );
Assert.AreEqual( 3, Matches.Count );
Assert.AreEqual( "Pribnow-box", Matches.Name );
Match matched = (Match) Matches[0];
Assert.AreEqual( 0.83, matched.Similarity, 1e-2 );
Assert.AreEqual( "tataac", matched.Letters() );
matched = (Match) Matches[1];
Assert.AreEqual( 0.76, matched.Similarity, 1e-2 );
Assert.AreEqual( "taacat", matched.Letters() );
matched = (Match) Matches[2];
Assert.AreEqual( 0.72, matched.Similarity, 1e-2 );
Assert.AreEqual( "cataaa", matched.Letters() );
}