public void TestMatch1 () {
Sequence seq = new Sequence( AlphabetType.DNA, "taaacc" );
SeriesBest series = new SeriesBest();
Match match;
series.Add( new Motif( "Motif1", AlphabetType.DNA, "aa", 0.5 ) );
match = seq.SearchBest( 1, seq.Length, series );
Assert.AreEqual( "aa", match.Letters() );
Assert.AreEqual( 2, match.Position() );
Assert.AreEqual( 1.00, match.Similarity, 1e-2 );
series.Add( new Gap( "Gap", 0, 2, 1 ) );
series.Add( new Motif( "motif2", AlphabetType.DNA, "cc", 0.5 ) );
match = seq.SearchBest( 1, seq.Length, series );
Assert.AreEqual( "aaacc", match.Letters() );
Assert.AreEqual( 2, match.Start );
Assert.AreEqual( 1.00, match.Similarity, 1e-2 );
}
public void TestMatch2 () {
Sequence seq = new Sequence( AlphabetType.DNA, "taaaccc" );
SeriesBest series = new SeriesBest();
Match match;
series.Add( new Motif( "motif1", AlphabetType.DNA, "ta", 0.5 ) );
series.Add( new Gap( "gap", 1, 3, 1, new double[] { 1, 2, 1 }, 0.0 ) );
series.Add( new Motif( "motif2", AlphabetType.DNA, "cc", 0.5 ) );
match = seq.SearchBest( 1, seq.Length, series );
Assert.AreEqual( "taaacc", match.Letters() );
Assert.AreEqual( 1.00, match.Similarity, 1e-2 );
}
public void TestMatchStart()
{
Sequence seq = new Sequence(AlphabetType.DNA, "atgcatgc");
Series series = new SeriesBest("test", 1.0);
series.Add(new Constraint("test", "START", +1));
series.Add(new Motif("motif", AlphabetType.DNA, "nnnn", 0.0));
Match match = series.Match(seq, 2);
Assert.AreEqual("tgca", match.Letters());
match = series.Match(seq, 1);
Assert.AreEqual(null, match);
match = seq.SearchBest(0, 0, series);
Assert.AreEqual("tgca", match.Letters());
}
public void TestMatchCenter()
{
Sequence seq = new Sequence(AlphabetType.DNA, "atgcatg");
Series series = new SeriesBest("test", 1.0);
series.Add(new Constraint("test", "CENTER", -1));
series.Add(new Motif("motif", AlphabetType.DNA, "nnnn", 1.0));
Match match = series.Match(seq, 3);
Assert.AreEqual("gcat", match.Letters());
match = series.Match(seq, 2);
Assert.AreEqual(null, match);
match = series.Match(seq, 4);
Assert.AreEqual(null, match);
match = seq.SearchBest(0, 0, series);
Assert.AreEqual("gcat", match.Letters());
}
/** Tests the a match for an inverted repeat pattern */
public void TestMatchInverted()
{
Sequence seq = new Sequence(AlphabetType.DNA, "ttaccgtttgcaattt");
Repeat repeat = new Repeat("repeat", motif, Repeat.RepeatType.INVERTED, 0.5);
series.Add(repeat);
Match match = series.Match(seq, 3);
Assert.AreEqual(0.875, match.Similarity);
Assert.AreEqual("accgtttgcaa", match.Letters());
Assert.AreEqual("gcaa", match.SubMatches[2].Letters());
Assert.AreEqual(0.75, match.SubMatches[2].Similarity);
Assert.AreEqual(10, match.SubMatches[2].Start);
Assert.AreEqual(4, match.SubMatches[2].Length);
Assert.AreEqual(1, match.SubMatches[2].Strand);
match = seq.SearchBest(0, 0, series);
Assert.AreEqual("accgtttgcaa", match.Letters());
}
public List<Matched> PerformSearch(string BioPatMLContent, SequenceContract sequence)
{
List<Matched> matchedList = new List<Matched>();
StringReader sr = new StringReader(BioPatMLContent);
Definition MyPatterns = null;
using (BioPatMLPatternReader reader = new BioPatMLPatternReader())
{
MyPatterns = reader.ReadBioPatML(sr);
}
Sequence targetSequence = new Sequence(sequence.AlphabetName, sequence.Characters);
SequenceList matches = new FeatureList();
IPattern MatchingPattern = MyPatterns.MainPattern;
#region If bioPatML pattern is SeriesBest OR SetBest : Search by best
if (MatchingPattern is SeriesBest
|| MatchingPattern is SetBest)
{
Match match = targetSequence.SearchBest(0, 0, MatchingPattern);
matches.Add(match);
}
#endregion
#region Else, pattern is Motif, Any, Anchor, Prosite, RegularEx : Search by normal
else
//The rest
{
matches = targetSequence.Search(1, targetSequence.Length, MatchingPattern);
}
#endregion
for (int i = 0; i < matches.Count; i++)
{
Match matched = matches[i] as Match;
matchedList.Add(new Matched
(matched.Similarity,
matched.Start, matched.End,
matched.Length, matched.Letters(), sequence.Name));
}
return matchedList;
}
/** Tests a weighted repeat */
public void TestMatchWeighted()
{
Sequence seq = new Sequence(AlphabetType.DNA, "ttaccgtttaacgttt");
Repeat repeat = new Repeat("repeat", motif, Repeat.RepeatType.DIRECT, 0.1);
series.Add(repeat);
repeat.Weight('a', 'a', 0.3);
repeat.Weight('c', 'a', 1.0);
repeat.Weight('g', 'g', 0.7);
Match match = series.Match(seq, 3);
Assert.AreEqual(0.75, match.Similarity);
Assert.AreEqual("accgtttaacg", match.Letters());
Assert.AreEqual("aacg", match.SubMatches[2].Letters());
Assert.AreEqual(0.5, match.SubMatches[2].Similarity, 1e-3);
match = seq.SearchBest(0, 0, series);
Assert.AreEqual("accgtttaacg", match.Letters());
}
public void TestMatchSubMatches()
{
Sequence seq = new Sequence(AlphabetType.DNA, "tttaagaacaagttt");
Motif motif = new Motif("motif", AlphabetType.DNA, "aag", 0.5);
Iteration iteration = new Iteration("test", motif, 1, 3, 0.0);
Match match = seq.SearchBest(0, 0, iteration);
Assert.AreEqual("aag", match.Letters());
Assert.AreEqual(10, match.Start);
Assert.AreEqual(1.0, match.Similarity);
Assert.AreEqual("aag", match.SubMatches[0].Letters()); //sub match to properties?
FeatureList matches = seq.Search(0, 0, iteration);
Assert.AreEqual(3, matches.Count);
Assert.AreEqual("aagaacaag", matches[0].Letters());
Assert.AreEqual(0.88, ((Match)matches[0]).Similarity, 1e-2);
Assert.AreEqual("aacaag", matches[1].Letters());
Assert.AreEqual(0.83, ((Match)matches[1]).Similarity, 1e-2);
Assert.AreEqual("aag", matches[2].Letters());
Assert.AreEqual(1.00, ((Match)matches[2]).Similarity, 1e-2);
}
/** Test for best match searching within a sequence */
public void TestSearchBest () {
Sequence seq = new Sequence( AlphabetType.DNA, "acttacttagttaatt" );
Motif motif = new Motif( "motif1", AlphabetType.DNA, "taga", 0.0 );
Match match = seq.SearchBest( 1, -1, motif );
Assert.AreEqual( "tagt", match.Letters() );
Assert.AreEqual( 8, match.Start );
Assert.AreEqual( 4, match.Length );
Assert.AreEqual( 0.75, match.Similarity, 1e-3 );
motif = new Motif( "motif2", AlphabetType.DNA, "aatt", 0.0 );
match = seq.SearchBest( 1, -1, motif );
Assert.AreEqual( 13, match.Start );
match = seq.SearchBest( 1, seq.Length, motif );
Assert.AreEqual( 13, match.Start );
match = seq.SearchBest( 1, seq.Length - 1, motif );
Assert.AreEqual( 1, match.Start );
}
public void TestMatchBest()
{
Sequence seq = new Sequence(AlphabetType.DNA, "actcctctg");
Composition composition = new Composition("Composition", AlphabetType.DNA, 3, 8, 1.7, Composition.MatchMode.BEST, 0.0);
composition.Add('a', 1.0);
composition.Add('c', 2.0);
composition.Add('t', 3.0);
composition.DefaultWeight = (1.0);
Match match = composition.Match(seq, 1);
Assert.AreEqual(1, match.Start);
Assert.AreEqual(8, match.End);
Assert.AreEqual("actcctct", match.Letters());
Assert.AreEqual(0.75, match.Similarity, 1e-2);
match = seq.SearchBest(0, 0, composition);
Assert.AreEqual(6, match.Start);
Assert.AreEqual("tct", match.Letters());
Assert.AreEqual(0.88, match.Similarity, 1e-2);
}
/** Test for match method from pattern interface */
public void TestMatchAll()
{
Sequence seq = new Sequence(AlphabetType.DNA, "act");
Composition composition = new Composition( "Composition", AlphabetType.DNA, 2, 3, 1, Composition.MatchMode.ALL, 0.0 );
composition.Add('a', 1.0);
composition.Add('c', 2.0);
composition.DefaultWeight = (3.0);
Match match = composition.Match(seq, 1);
Assert.AreEqual(2, match.Length);
Assert.AreEqual(1, match.Start);
Assert.AreEqual(2, match.End);
Assert.AreEqual("ac", match.Letters());
Assert.AreEqual(0.5, match.Similarity, 1e-2);
match = seq.SearchBest(0, 0, composition);
Assert.AreEqual(2, match.Start);
Assert.AreEqual("ct", match.Letters());
Assert.AreEqual(0.83, match.Similarity, 1e-2);
FeatureList matches = seq.Search(0, 0, composition);
Assert.AreEqual(3, matches.Count);
Assert.AreEqual("ac", matches[0].Letters());
Assert.AreEqual("act", matches[1].Letters());
Assert.AreEqual("ct", matches[2].Letters());
}