public void SmithWatermanProteinSeqAffineGap()
{
IPairwiseSequenceAligner sw = new SmithWatermanAligner
{
SimilarityMatrix = new SimilarityMatrix(SimilarityMatrix.StandardSimilarityMatrix.Blosum62),
GapOpenCost = -8,
GapExtensionCost = -1,
};
ISequence sequence1 = new Sequence(Alphabets.Protein, "HEAGAWGHEE");
ISequence sequence2 = new Sequence(Alphabets.Protein, "PAWHEAE");
IList <IPairwiseSequenceAlignment> result = sw.Align(sequence1, sequence2);
AlignmentHelpers.LogResult(sw, result);
IList <IPairwiseSequenceAlignment> expectedOutput = new List <IPairwiseSequenceAlignment>();
IPairwiseSequenceAlignment align = new PairwiseSequenceAlignment();
PairwiseAlignedSequence alignedSeq = new PairwiseAlignedSequence
{
FirstSequence = new Sequence(Alphabets.Protein, "AWGHE"),
SecondSequence = new Sequence(Alphabets.Protein, "AW-HE"),
Consensus = new Sequence(Alphabets.AmbiguousProtein, "AWGHE"),
Score = 20,
FirstOffset = 0,
SecondOffset = 3
};
align.PairwiseAlignedSequences.Add(alignedSeq);
expectedOutput.Add(align);
Assert.IsTrue(AlignmentHelpers.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));
}
protected override ActivityExecutionStatus Execute(ActivityExecutionContext executionContext)
{
SmithWatermanAligner SWA = new SmithWatermanAligner();
Result = SWA.AlignSimple(SimilarityMatrix, GapPenalty, Sequence1, Sequence2);
if (Result.Count >= 1 && Result[0].PairwiseAlignedSequences.Count >= 1)
{
Result1 = Result[0].PairwiseAlignedSequences[0].FirstSequence;
Result2 = Result[0].PairwiseAlignedSequences[0].SecondSequence;
Consensus = Result[0].PairwiseAlignedSequences[0].Consensus;
}
return(ActivityExecutionStatus.Closed);
}
public void SmithWatermanProteinSeqAffineGap()
{
string sequenceString1 = "HEAGAWGHEE";
string sequenceString2 = "PAWHEAE";
Sequence sequence1 = new Sequence(Alphabets.Protein, sequenceString1);
Sequence sequence2 = new Sequence(Alphabets.Protein, sequenceString2);
SimilarityMatrix sm = new SimilarityMatrix(SimilarityMatrix.StandardSimilarityMatrix.Blosum50);
int gapPenalty = -8;
SmithWatermanAligner sw = new SmithWatermanAligner();
sw.SimilarityMatrix = sm;
sw.GapOpenCost = gapPenalty;
sw.GapExtensionCost = -1;
IList <IPairwiseSequenceAlignment> result = sw.Align(sequence1, sequence2);
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"{0}, Affine; Matrix {1}; GapOpenCost {2}; GapExtenstionCost {3}", sw.Name, sw.SimilarityMatrix.Name, sw.GapOpenCost, sw.GapExtensionCost));
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();
PairwiseAlignedSequence alignedSeq = new PairwiseAlignedSequence();
alignedSeq.FirstSequence = new Sequence(Alphabets.Protein, "AWGHE");
alignedSeq.SecondSequence = new Sequence(Alphabets.Protein, "AW-HE");
alignedSeq.Consensus = new Sequence(Alphabets.Protein, "AWGHE");
alignedSeq.Score = 28;
alignedSeq.FirstOffset = 0;
alignedSeq.SecondOffset = 3;
align.PairwiseAlignedSequences.Add(alignedSeq);
expectedOutput.Add(align);
Assert.IsTrue(CompareAlignment(result, expectedOutput));
}
public void SmithWatermanAlignerMultipleAlignments2()
{
IPairwiseSequenceAligner sw = new SmithWatermanAligner
{
SimilarityMatrix = new DiagonalSimilarityMatrix(5, -4),
GapOpenCost = -5
};
ISequence sequence1 = new Sequence(Alphabets.DNA, "AAAAGGGGGGCCCC");
ISequence sequence2 = new Sequence(Alphabets.DNA, "AAAATTTTTTTCCCC");
IList <IPairwiseSequenceAlignment> result = sw.AlignSimple(sequence1, sequence2);
AlignmentHelpers.LogResult(sw, result);
IList <IPairwiseSequenceAlignment> expectedOutput = new List <IPairwiseSequenceAlignment>();
// First alignment
IPairwiseSequenceAlignment align = new PairwiseSequenceAlignment(sequence1, sequence2);
align.PairwiseAlignedSequences.Add(new PairwiseAlignedSequence
{
FirstSequence = new Sequence(Alphabets.DNA, "AAAA"),
SecondSequence = new Sequence(Alphabets.DNA, "AAAA"),
Consensus = new Sequence(Alphabets.DNA, "AAAA"),
Score = 20,
FirstOffset = 0,
SecondOffset = 0
});
// Second alignment
align.PairwiseAlignedSequences.Add(new PairwiseAlignedSequence
{
FirstSequence = new Sequence(Alphabets.DNA, "CCCC"),
SecondSequence = new Sequence(Alphabets.DNA, "CCCC"),
Consensus = new Sequence(Alphabets.DNA, "CCCC"),
Score = 20,
FirstOffset = 1,
SecondOffset = 0
});
expectedOutput.Add(align);
Assert.IsTrue(AlignmentHelpers.CompareAlignment(result, expectedOutput));
}
public void ValidateSequenceAlignersAll()
{
MUMmer mumobj = new MUMmer3();
Assert.AreEqual(mumobj.ToString(), SequenceAligners.MUMmer.ToString());
NeedlemanWunschAligner nwAlignerobj = new NeedlemanWunschAligner();
Assert.AreEqual(nwAlignerobj.ToString(), SequenceAligners.NeedlemanWunsch.ToString());
NUCmer nucobj = new NUCmer3();
Assert.AreEqual(nucobj.ToString(), SequenceAligners.NUCmer.ToString());
PairwiseOverlapAligner poAlignerobj = new PairwiseOverlapAligner();
Assert.AreEqual(poAlignerobj.ToString(), SequenceAligners.PairwiseOverlap.ToString());
SmithWatermanAligner swAlignerobj = new SmithWatermanAligner();
Assert.AreEqual(swAlignerobj.ToString(), SequenceAligners.SmithWaterman.ToString());
Assert.IsNotNull(SequenceAligners.All);
Console.Write("Successfully created all the objects in Sequence Aligners");
ApplicationLog.Write("Successfully created all the objects in Sequence Aligners");
}
public void PerformSmithWatermanPerf()
{
// Get Sequence file path.
string refPath =
Utility._xmlUtil.GetTextValue(Constants.AlignmentAlgorithmNodeName,
Constants.RefFilePathNode);
string queryPath =
Utility._xmlUtil.GetTextValue(Constants.AlignmentAlgorithmNodeName,
Constants.QueryFilePathNode);
string smFilePath =
Utility._xmlUtil.GetTextValue(Constants.AlignmentAlgorithmNodeName,
Constants.SMFilePathNode);
// Create a List for input files.
List <string> lstInputFiles = new List <string>();
lstInputFiles.Add(refPath);
lstInputFiles.Add(queryPath);
FastaParser parserObj = new FastaParser();
IList <ISequence> seqs1 = parserObj.Parse(refPath);
parserObj = new FastaParser();
IList <ISequence> seqs2 = parserObj.Parse(queryPath);
IAlphabet alphabet = Alphabets.DNA;
ISequence originalSequence1 = seqs1[0];
ISequence originalSequence2 = seqs2[0];
ISequence aInput = new Sequence(alphabet, originalSequence1.ToString());
ISequence bInput = new Sequence(alphabet, originalSequence2.ToString());
SimilarityMatrix sm = new SimilarityMatrix(smFilePath);
swObj = new SmithWatermanAligner();
swObj.GapOpenCost = -10;
swObj.GapExtensionCost = -10;
swObj.SimilarityMatrix = sm;
_watchObj = new Stopwatch();
_watchObj.Reset();
_watchObj.Start();
long memoryStart = GC.GetTotalMemory(false);
// Align sequences using smith water man algorithm.
IList <IPairwiseSequenceAlignment> alignment = swObj.AlignSimple(aInput, bInput);
_watchObj.Stop();
long memoryEnd = GC.GetTotalMemory(false);
string memoryUsed = (memoryEnd - memoryStart).ToString();
// Display SmithWaterman perf test case execution details.
DisplayTestCaseHeader(lstInputFiles, _watchObj, memoryUsed,
"SmithWaterman");
Console.WriteLine(string.Format(
"Smith Waterman AlignSimple() method, Alignment Score is : {0}",
alignment[0].PairwiseAlignedSequences[0].Score.ToString()));
// Dispose SmithWaterman object
swObj = null;
}
private void ValidateSmithWatermanAlignment(bool isTextFile, AlignmentParamType alignParam,
AlignmentType alignType)
{
ISequence aInput, bInput;
IAlphabet alphabet =
Utility.GetAlphabet(this.utilityObj.xmlUtil.GetTextValue(Constants.SmithWatermanAlignAlgorithmNodeName,
Constants.AlphabetNameNode));
if (isTextFile)
{
// Read the xml file for getting both the files for aligning.
string filePath1 = this.utilityObj.xmlUtil.GetTextValue(Constants.SmithWatermanAlignAlgorithmNodeName,
Constants.FilePathNode1);
string filePath2 = this.utilityObj.xmlUtil.GetTextValue(Constants.SmithWatermanAlignAlgorithmNodeName,
Constants.FilePathNode2);
// Parse the files and get the sequence.
var parseObjectForFile1 = new FastAParser();
{
parseObjectForFile1.Alphabet = alphabet;
aInput = parseObjectForFile1.Parse(filePath1).First();
}
var parseObjectForFile2 = new FastAParser();
{
parseObjectForFile2.Alphabet = alphabet;
bInput = parseObjectForFile2.Parse(filePath2).First();
}
}
else
{
// Read the xml file for getting both the files for aligning.
string origSequence1 = this.utilityObj.xmlUtil.GetTextValue(Constants.SmithWatermanAlignAlgorithmNodeName,
Constants.SequenceNode1);
string origSequence2 = this.utilityObj.xmlUtil.GetTextValue(Constants.SmithWatermanAlignAlgorithmNodeName,
Constants.SequenceNode2);
aInput = new Sequence(alphabet, origSequence1);
bInput = new Sequence(alphabet, origSequence2);
}
string blosumFilePath = this.utilityObj.xmlUtil.GetTextValue(Constants.SmithWatermanAlignAlgorithmNodeName,
Constants.BlosumFilePathNode);
var sm = new SimilarityMatrix(new StreamReader(blosumFilePath));
int gapOpenCost =
int.Parse(
this.utilityObj.xmlUtil.GetTextValue(Constants.SmithWatermanAlignAlgorithmNodeName,
Constants.GapOpenCostNode), null);
int gapExtensionCost =
int.Parse(
this.utilityObj.xmlUtil.GetTextValue(Constants.SmithWatermanAlignAlgorithmNodeName,
Constants.GapExtensionCostNode), null);
var smithWatermanObj = new SmithWatermanAligner();
if (AlignmentParamType.AllParam != alignParam)
{
smithWatermanObj.SimilarityMatrix = sm;
smithWatermanObj.GapOpenCost = gapOpenCost;
}
IList <IPairwiseSequenceAlignment> result = null;
switch (alignParam)
{
case AlignmentParamType.AlignList:
switch (alignType)
{
case AlignmentType.Align:
result = smithWatermanObj.Align(new List <ISequence> {
aInput, bInput
});
break;
default:
result = smithWatermanObj.AlignSimple(new List <ISequence> {
aInput, bInput
});
break;
}
break;
case AlignmentParamType.AlignTwo:
switch (alignType)
{
case AlignmentType.Align:
result = smithWatermanObj.Align(aInput, bInput);
break;
default:
result = smithWatermanObj.AlignSimple(aInput, bInput);
break;
}
break;
case AlignmentParamType.AllParam:
switch (alignType)
{
case AlignmentType.Align:
result = smithWatermanObj.Align(sm, gapOpenCost,
gapExtensionCost, aInput, bInput);
break;
default:
result = smithWatermanObj.AlignSimple(sm, gapOpenCost, aInput, bInput);
break;
}
break;
default:
break;
}
// Read the xml file for getting both the files for aligning.
string expectedSequence1, expectedSequence2, expectedScore;
switch (alignType)
{
case AlignmentType.Align:
expectedScore = this.utilityObj.xmlUtil.GetTextValue(
Constants.SmithWatermanAlignAlgorithmNodeName,
Constants.ExpectedGapExtensionScoreNode);
expectedSequence1 = this.utilityObj.xmlUtil.GetTextValue(
Constants.SmithWatermanAlignAlgorithmNodeName,
Constants.ExpectedGapExtensionSequence1Node);
expectedSequence2 = this.utilityObj.xmlUtil.GetTextValue(
Constants.SmithWatermanAlignAlgorithmNodeName,
Constants.ExpectedGapExtensionSequence2Node);
break;
default:
expectedScore = this.utilityObj.xmlUtil.GetTextValue(
Constants.SmithWatermanAlignAlgorithmNodeName,
Constants.ExpectedScoreNode);
expectedSequence1 = this.utilityObj.xmlUtil.GetTextValue(
Constants.SmithWatermanAlignAlgorithmNodeName,
Constants.ExpectedSequenceNode1);
expectedSequence2 = this.utilityObj.xmlUtil.GetTextValue(
Constants.SmithWatermanAlignAlgorithmNodeName,
Constants.ExpectedSequenceNode2);
break;
}
IList <IPairwiseSequenceAlignment> expectedOutput = new List <IPairwiseSequenceAlignment>();
IPairwiseSequenceAlignment align = new PairwiseSequenceAlignment();
var alignedSeq = new PairwiseAlignedSequence
{
FirstSequence = new Sequence(alphabet, expectedSequence1),
SecondSequence = new Sequence(alphabet, expectedSequence2),
Score = Convert.ToInt32(expectedScore, null),
FirstOffset = Int32.MinValue,
SecondOffset = Int32.MinValue,
};
align.PairwiseAlignedSequences.Add(alignedSeq);
expectedOutput.Add(align);
ApplicationLog.WriteLine(string.Format(null, "SmithWatermanAligner BVT : Final Score '{0}'.", expectedScore));
ApplicationLog.WriteLine(string.Format(null, "SmithWatermanAligner BVT : Aligned First Sequence is '{0}'.",
expectedSequence1));
ApplicationLog.WriteLine(string.Format(null, "SmithWatermanAligner BVT : Aligned Second Sequence is '{0}'.",
expectedSequence2));
Assert.IsTrue(CompareAlignment(result, expectedOutput));
}
public SmithAlignerProvider(ISequenceProvider provider, SmithWatermanAligner aligner)
{
_provider = provider;
_aligner = aligner;
}
