/// <summary>
/// Default constructor
/// </summary>
protected PairwiseSequenceAligner()
{
SimilarityMatrix = new DiagonalSimilarityMatrix(2, -2);
GapOpenCost = -8;
GapExtensionCost = -1;
IncludeScoreTable = false;
}
public void PairwiseOverlapProteinSeqWithZeroOverlap()
{
Sequence sequence1 = new Sequence(Alphabets.Protein, "ACDEF");
Sequence sequence2 = new Sequence(Alphabets.Protein, "TUVWY");
SimilarityMatrix sm = new DiagonalSimilarityMatrix(5, -5);
int gapPenalty = -10;
PairwiseOverlapAligner overlap = new PairwiseOverlapAligner();
overlap.SimilarityMatrix = sm;
overlap.GapOpenCost = gapPenalty;
overlap.GapExtensionCost = -1;
IList <IPairwiseSequenceAlignment> result = overlap.Align(sequence1, sequence2);
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"{0}, Simple; Matrix {1}; GapOpenCost {2}", overlap.Name, overlap.SimilarityMatrix.Name, overlap.GapOpenCost));
foreach (IPairwiseSequenceAlignment sequenceResult in result)
{
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"score {0}", sequenceResult.PairwiseAlignedSequences[0].Score));
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"input 0 {0}", sequenceResult.FirstSequence.ToString()));
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"input 1 {0}", sequenceResult.SecondSequence.ToString()));
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"result 0 {0}", sequenceResult.PairwiseAlignedSequences[0].FirstSequence.ToString()));
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"result 1 {0}", sequenceResult.PairwiseAlignedSequences[0].SecondSequence.ToString()));
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"consesus {0}", sequenceResult.PairwiseAlignedSequences[0].Consensus.ToString()));
}
IList <IPairwiseSequenceAlignment> expectedOutput = new List <IPairwiseSequenceAlignment>();
Assert.IsTrue(CompareAlignment(result, expectedOutput));
}
public void SmithWatermanAlignerMultipleAlignments2()
{
Sequence sequence1 = new Sequence(Alphabets.DNA, "AAAAGGGGGGCCCC");
Sequence sequence2 = new Sequence(Alphabets.DNA, "AAAATTTTTTTCCCC");
SimilarityMatrix sm = new DiagonalSimilarityMatrix(5, -4);
int gapPenalty = -10;
SmithWatermanAligner sw = new SmithWatermanAligner();
sw.SimilarityMatrix = sm;
sw.GapOpenCost = gapPenalty;
IList <IPairwiseSequenceAlignment> result = sw.AlignSimple(sequence1, sequence2);
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"{0}, Simple; Matrix {1}; GapOpenCost {2}", sw.Name, sw.SimilarityMatrix.Name, sw.GapOpenCost));
foreach (IPairwiseSequenceAlignment sequenceResult in result)
{
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"score {0}", sequenceResult.PairwiseAlignedSequences[0].Score));
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"input 0 {0}", sequenceResult.FirstSequence.ToString()));
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"input 1 {0}", sequenceResult.SecondSequence.ToString()));
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"result 0 {0}", sequenceResult.PairwiseAlignedSequences[0].FirstSequence.ToString()));
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"result 1 {0}", sequenceResult.PairwiseAlignedSequences[0].SecondSequence.ToString()));
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"consesus {0}", sequenceResult.PairwiseAlignedSequences[0].Consensus.ToString()));
}
IList <IPairwiseSequenceAlignment> expectedOutput = new List <IPairwiseSequenceAlignment>();
IPairwiseSequenceAlignment align = new PairwiseSequenceAlignment(sequence1, sequence2);
// First alignment
PairwiseAlignedSequence alignedSeq = new PairwiseAlignedSequence();
alignedSeq.FirstSequence = new Sequence(Alphabets.DNA, "AAAA");
alignedSeq.SecondSequence = new Sequence(Alphabets.DNA, "AAAA");
alignedSeq.Consensus = new Sequence(Alphabets.DNA, "AAAA");
alignedSeq.Score = 20;
alignedSeq.FirstOffset = 0;
alignedSeq.SecondOffset = 0;
align.PairwiseAlignedSequences.Add(alignedSeq);
// Second alignment
alignedSeq = new PairwiseAlignedSequence();
alignedSeq.FirstSequence = new Sequence(Alphabets.DNA, "CCCC");
alignedSeq.SecondSequence = new Sequence(Alphabets.DNA, "CCCC");
alignedSeq.Consensus = new Sequence(Alphabets.DNA, "CCCC");
alignedSeq.Score = 20;
alignedSeq.FirstOffset = 1;
alignedSeq.SecondOffset = 0;
align.PairwiseAlignedSequences.Add(alignedSeq);
expectedOutput.Add(align);
Assert.IsTrue(CompareAlignment(result, expectedOutput));
}
public void NeedlemanWunschDnaSeqSimpleGap()
{
Sequence sequence1 = new Sequence(Alphabets.DNA, "GAATTCAGTTA");
Sequence sequence2 = new Sequence(Alphabets.DNA, "GGATCGA");
SimilarityMatrix sm = new DiagonalSimilarityMatrix(2, -1);
int gapPenalty = -2;
NeedlemanWunschAligner nw = new NeedlemanWunschAligner();
nw.SimilarityMatrix = sm;
nw.GapOpenCost = gapPenalty;
IList <IPairwiseSequenceAlignment> result = nw.AlignSimple(sequence1, sequence2);
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"{0}, Simple; Matrix {1}; GapOpenCost {2}", nw.Name, nw.SimilarityMatrix.Name, nw.GapOpenCost));
ApplicationLog.WriteLine(string.Format(
(IFormatProvider)null, "score {0}", result[0].PairwiseAlignedSequences[0].Score));
ApplicationLog.WriteLine(string.Format(
(IFormatProvider)null, "input 0 {0}", result[0].FirstSequence.ToString()));
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"input 1 {0}", result[0].SecondSequence.ToString()));
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"result 0 {0}", result[0].PairwiseAlignedSequences[0].FirstSequence.ToString()));
ApplicationLog.WriteLine(string.Format((IFormatProvider)null, "result 1 {0}", result[0].PairwiseAlignedSequences[0].SecondSequence.ToString()));
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"consesus {0}", result[0].PairwiseAlignedSequences[0].Consensus));
IList <IPairwiseSequenceAlignment> expectedOutput = new List <IPairwiseSequenceAlignment>();
IPairwiseSequenceAlignment align = new PairwiseSequenceAlignment();
PairwiseAlignedSequence alignedSeq = new PairwiseAlignedSequence();
alignedSeq.FirstSequence = new Sequence(Alphabets.DNA, "GAATTCAGTTA");
alignedSeq.SecondSequence = new Sequence(Alphabets.DNA, "GGA-TC-G--A");
alignedSeq.Consensus = new Sequence(AmbiguousDnaAlphabet.Instance, "GRATTCAGTTA");
alignedSeq.Score = 3;
alignedSeq.FirstOffset = 0;
alignedSeq.SecondOffset = 0;
align.PairwiseAlignedSequences.Add(alignedSeq);
expectedOutput.Add(align);
Assert.IsTrue(CompareAlignment(result, expectedOutput));
}
public void TestMUMmer3MultipleMumWithCustomMatrix()
{
string reference = "ATGCGCATCCCCTT";
string search = "GCGCCCCCTA";
Sequence referenceSeq = null;
Sequence searchSeq = null;
referenceSeq = new Sequence(Alphabets.DNA, reference);
searchSeq = new Sequence(Alphabets.DNA, search);
List <ISequence> searchSeqs = new List <ISequence>();
searchSeqs.Add(searchSeq);
int[,] customMatrix = new int[256, 256];
customMatrix[(byte)'A', (byte)'A'] = 3;
customMatrix[(byte)'A', (byte)'T'] = -2;
customMatrix[(byte)'A', (byte)'G'] = -2;
customMatrix[(byte)'A', (byte)'c'] = -2;
customMatrix[(byte)'G', (byte)'G'] = 3;
customMatrix[(byte)'G', (byte)'A'] = -2;
customMatrix[(byte)'G', (byte)'T'] = -2;
customMatrix[(byte)'G', (byte)'C'] = -2;
customMatrix[(byte)'T', (byte)'T'] = 3;
customMatrix[(byte)'T', (byte)'A'] = -2;
customMatrix[(byte)'T', (byte)'G'] = -2;
customMatrix[(byte)'T', (byte)'C'] = -2;
customMatrix[(byte)'C', (byte)'C'] = 3;
customMatrix[(byte)'C', (byte)'T'] = -2;
customMatrix[(byte)'C', (byte)'A'] = -2;
customMatrix[(byte)'C', (byte)'G'] = -2;
DiagonalSimilarityMatrix matrix = new DiagonalSimilarityMatrix(3, -2);
int gapOpenCost = -6;
MUMmerAligner mummer = new MUMmerAligner();
mummer.LengthOfMUM = 4;
mummer.PairWiseAlgorithm = new NeedlemanWunschAligner();
mummer.SimilarityMatrix = matrix;
mummer.GapOpenCost = gapOpenCost;
mummer.GapExtensionCost = -2;
IList <IPairwiseSequenceAlignment> result = mummer.AlignSimple(referenceSeq, searchSeqs);
// Check if output is not null
Assert.AreNotEqual(null, result);
IList <IPairwiseSequenceAlignment> expectedOutput = new List <IPairwiseSequenceAlignment>();
IPairwiseSequenceAlignment align = new PairwiseSequenceAlignment();
PairwiseAlignedSequence alignedSeq = new PairwiseAlignedSequence();
alignedSeq.FirstSequence = new Sequence(Alphabets.DNA, "ATGCGCATCCCCTT");
alignedSeq.SecondSequence = new Sequence(Alphabets.DNA, "--GCGC--CCCCTA");
alignedSeq.Consensus = new Sequence(AmbiguousDnaAlphabet.Instance, "ATGCGCATCCCCTW");
alignedSeq.Score = 1;
alignedSeq.FirstOffset = 0;
alignedSeq.SecondOffset = 2;
align.PairwiseAlignedSequences.Add(alignedSeq);
expectedOutput.Add(align);
Assert.IsTrue(CompareAlignment(result, expectedOutput));
}
public void SimilarityMatrixMultiTest()
{
string filename = @"testdata\SimilarityMatrices\SampleCustomMatrix.txt";
Assert.IsTrue(File.Exists(filename));
SimilarityMatrix blosum50 = new SimilarityMatrix(SimilarityMatrix.StandardSimilarityMatrix.Blosum50);
SimilarityMatrix fromFile = new SimilarityMatrix(filename);
SimilarityMatrix fromReader = null;
using (TextReader reader = new StreamReader(filename))
{
fromReader = new SimilarityMatrix(reader);
}
// Custom matrix, clone BLOSUM50 and see if it works.
int[][] customMatrixInput = (int[][])blosum50.Matrix.Clone();
string symbolMap = "ARNDCQEGHILKMFPSTWYVBJZX*";
SimilarityMatrix custom = new SimilarityMatrix(customMatrixInput, symbolMap, "custom matrix, should be BLOSUM50", MoleculeType.Protein);
int[][] matrix = blosum50.Matrix;
int[][] matrixFile = fromFile.Matrix;
int[][] matrixReader = fromReader.Matrix;
int[][] matrixCustom = custom.Matrix;
int i, j;
int iLength = matrix.GetLength(0);
int jLength = matrix[0].GetLength(0);
Assert.AreEqual(iLength, matrixFile.GetLength(0));
Assert.AreEqual(jLength, matrixFile[0].GetLength(0));
Assert.AreEqual(iLength, matrixReader.GetLength(0));
Assert.AreEqual(jLength, matrixReader[0].GetLength(0));
Assert.AreEqual(iLength, matrixCustom.GetLength(0));
Assert.AreEqual(jLength, matrixCustom[0].GetLength(0));
for (i = 0; i < iLength; i++)
{
for (j = 0; j < jLength; j++)
{
int blosum50Value = blosum50.Matrix[i][j];
Assert.AreEqual(blosum50Value, matrixFile[i][j]);
Assert.AreEqual(blosum50Value, matrixReader[i][j]);
Assert.AreEqual(blosum50Value, matrixCustom[i][j]);
}
}
// Diagonal
int matchValue = 10;
int mismatchValue = -5;
DiagonalSimilarityMatrix dsm = new DiagonalSimilarityMatrix(matchValue, mismatchValue, MoleculeType.Protein);
// There is no real matrix here, just a function that returns matchValue for i==j and otherwise mismatchValue.
// Run it 25x25
for (i = 0; i < 25; i++)
{
for (j = 0; j < 25; j++)
{
if (i == j)
{
Assert.AreEqual(matchValue, dsm[i, j]);
}
else
{
Assert.AreEqual(mismatchValue, dsm[i, j]);
}
}
}
}