public void TestMatch1 () {
Sequence seq = new Sequence( AlphabetType.DNA, "taaacc" );
SeriesAll series = new SeriesAll();
FeatureList matches;
series.Add( new Motif( "motif1", AlphabetType.DNA, "aa", 0.5 ) );
matches = seq.Search( 1, seq.Length, series );
Assert.AreEqual( 4, matches.Count );
Assert.AreEqual( "ta", matches[ 0 ].Letters() ); //There might be some error with data structure
Assert.AreEqual( 1, matches[ 0 ].Start );
Assert.AreEqual( "aa", matches[ 1 ].Letters() );
Assert.AreEqual( 2, matches[ 1 ].Start );
Assert.AreEqual( "aa", matches[ 2 ].Letters() );
Assert.AreEqual( 3, matches[ 2 ].Start );
Assert.AreEqual( "ac", matches[ 3 ].Letters() );
Assert.AreEqual( 4, matches[ 3 ].Start );
series.Add( new Gap( "gap1", 1, 2, 1 ) );
series.Add( new Motif( "motif2", AlphabetType.DNA, "cc", 0.5 ) );
matches = seq.Search( 1, seq.Length, series );
Assert.AreEqual( 3, matches.Count() );
Assert.AreEqual( "taaac", matches[ 0 ].Letters() );
Assert.AreEqual( 0.666, ( (Match) matches[ 0 ] ).Similarity, 1e-3 );
Assert.AreEqual( "taaacc", matches[ 1 ].Letters() );
Assert.AreEqual( 0.833, ( (Match) matches[ 1 ] ).Similarity, 1e-3 );
Assert.AreEqual( "aaacc", matches[ 2 ].Letters() );
Assert.AreEqual( 1.000, ( (Match) matches[ 2 ] ).Similarity, 1e-3 );
}
/** Tests the match method of a series of patterns with a weighted gap */
public void TestMatchWeightedGap () {
Sequence seq = new Sequence( AlphabetType.DNA, "taaacc" );
SeriesAll series = new SeriesAll();
series.Add( new Motif( "motif1", AlphabetType.DNA, "ta", 1.0 ) );
series.Add( new Gap( "gap", 1, 2, 1, new double[] { 0, 1 }, 0.0 ) );
series.Add( new Motif( "motif2", AlphabetType.DNA, "cc", 0.5 ) );
FeatureList matches = seq.Search( 1, seq.Length, series );
Assert.AreEqual( "taaac", matches[ 0 ].Letters() );
Assert.AreEqual( 0.500, ( (Match) matches[ 0 ] ).Similarity, 1e-3 );
Assert.AreEqual( "taaacc", matches[ 1 ].Letters() );
Assert.AreEqual( 1.000, ( (Match) matches[ 1 ] ).Similarity, 1e-3 );
}
/** Tests the match method of a series of patterns with two gaps */
public void TestMatchTwoGaps () {
Sequence seq = new Sequence( AlphabetType.DNA, "taaaagccc" );
SeriesAll series = new SeriesAll();
series.Add( new Motif( "motif1", AlphabetType.DNA, "ta", 1.0 ) );
series.Add( new Gap( "gap1", 1, 2, 1 ) );
series.Add( new Motif( "motif2", AlphabetType.DNA, "aa", 0.5 ) );
series.Add( new Gap( "gap2", 1, 2, 1 ) );
series.Add( new Motif( "motif3", AlphabetType.DNA, "cc", 1.0 ) );
FeatureList matches = seq.Search( 1, seq.Length, series );
Assert.AreEqual( 3, 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 );
}
/// <summary>
///
/// Reads a pattern from a starting specified node. This method
/// recursivly calls the reading methods of the different patterns.
/// </summary>
/// <param name="node">Node of the pattern the reading starts with.</param>
/// <param name="definition">Pattern definition which pattern list will be extended
/// with the pattern and all its sub-patterns read.
/// </param>
/// <returns>The read pattern or null if there is no pattern to read.</returns>
/// <exception cref="System.SystemException">Thrown when unknown pattern was found</exception>
public static IPattern ReadPattern
(XmlNode node, Definition definition)
{
while (node != null
&& node.NodeType != XmlNodeType.Element)
node = node.NextSibling; //Iterate thru the list of nodes until it is an element
IPattern pattern = null;
String mode = XMLHelper.GetAttrValueString(node, "mode");
switch (node.Name)
{
case "Any":
pattern = new Any();
break;
case "Alignment":
pattern = new Alignment();
break;
case "Composition" :
pattern = new Composition();
break;
case "Constraint":
pattern = new Constraint();
break;
case "Iteration":
pattern = new Iteration();
break;
case "Logic":
pattern = new Logic();
break;
case "Motif":
pattern = new Motif();
break;
case "PWM":
pattern = new PWM();
break;
case "Regex":
pattern = new RegularExp();
break;
case "Prosite":
pattern = new Prosite();
break;
case "Block":
pattern = new Block();
break;
case "Gap":
pattern = new Gap();
break;
case "Repeat":
pattern = new Repeat();
break;
case "Series":
pattern = mode.Equals("ALL") ?
pattern = new SeriesAll() : pattern = new SeriesBest();
break;
case "Set":
pattern = mode.Equals("ALL") ?
pattern = new SetAll() : pattern = new SetBest();
break;
case "Void":
pattern = new VoidPattern();
break;
case "Use":
pattern = new Use();
break;
throw new SystemException
("Unknown pattern found: " + node.Name);
}
pattern.ReadNode(node, definition); // read the node data and initialize the pattern
definition.Patterns.Add
(0, pattern); //Always adding the element to last index
return pattern;
}
/** Tests the match method of a series of patterns with two gaps */
public void TestMatchSigma70 () {
Sequence seq = new Sequence( AlphabetType.DNA, "cgagagagcg attatatcga ctaaacagaa aatgtcaaac aacttgtcaa aaaacagaag" );
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( 2, matches.Count );
System.Diagnostics.Debug.WriteLine( series.ToXml().ToString() );
//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 );
}
/** 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 );
}