public void NeedlemanWunschDnaSeqSimpleGap()
{
IPairwiseSequenceAligner nw = new NeedlemanWunschAligner
{
SimilarityMatrix = new DiagonalSimilarityMatrix(2, -1),
GapOpenCost = -2
};
ISequence sequence1 = new Sequence(Alphabets.DNA, "GAATTCAGTTA");
ISequence sequence2 = new Sequence(Alphabets.DNA, "GGATCGA");
IList <IPairwiseSequenceAlignment> result = nw.AlignSimple(sequence1, sequence2);
AlignmentHelpers.LogResult(nw, result);
IList <IPairwiseSequenceAlignment> expectedOutput = new List <IPairwiseSequenceAlignment>();
IPairwiseSequenceAlignment align = new PairwiseSequenceAlignment();
align.PairwiseAlignedSequences.Add(new PairwiseAlignedSequence
{
FirstSequence = new Sequence(Alphabets.DNA, "GAATTCAGTTA"),
SecondSequence = new Sequence(Alphabets.DNA, "GGAT-C-G--A"),
Consensus = new Sequence(AmbiguousDnaAlphabet.Instance, "GRATTCAGTTA"),
Score = 3,
FirstOffset = 0,
SecondOffset = 0
});
expectedOutput.Add(align);
Assert.IsTrue(AlignmentHelpers.CompareAlignment(result, expectedOutput));
}
public void NeedlemanWunschProteinSeqSimpleGap()
{
IPairwiseSequenceAligner nw = new NeedlemanWunschAligner
{
SimilarityMatrix = new SimilarityMatrix(SimilarityMatrix.StandardSimilarityMatrix.Blosum62),
GapOpenCost = -8
};
ISequence sequence1 = new Sequence(Alphabets.Protein, "HEAGAWGHEE");
ISequence sequence2 = new Sequence(Alphabets.Protein, "PAWHEAE");
IList <IPairwiseSequenceAlignment> result = nw.AlignSimple(sequence1, sequence2);
AlignmentHelpers.LogResult(nw, result);
IList <IPairwiseSequenceAlignment> expectedOutput = new List <IPairwiseSequenceAlignment>();
IPairwiseSequenceAlignment align = new PairwiseSequenceAlignment();
align.PairwiseAlignedSequences.Add(new PairwiseAlignedSequence
{
FirstSequence = new Sequence(Alphabets.Protein, "HEAGAWGHE-E"),
SecondSequence = new Sequence(Alphabets.Protein, "-PA--W-HEAE"),
Consensus = new Sequence(AmbiguousProteinAlphabet.Instance, "HXAGAWGHEAE"),
Score = -8,
FirstOffset = 0,
SecondOffset = 0
});
expectedOutput.Add(align);
Assert.IsTrue(AlignmentHelpers.CompareAlignment(result, expectedOutput));
}
protected override ActivityExecutionStatus Execute(ActivityExecutionContext executionContext)
{
NeedlemanWunschAligner NWA = new NeedlemanWunschAligner();
Result = NWA.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 static decimal AlignedSequenceSimilarityPercentage(ISequence alignableSequenceA, ISequence alignableSequenceB)
{
if (alignableSequenceA == null || alignableSequenceA.Count == 0 || alignableSequenceB == null || alignableSequenceB.Count == 0)
{
return(0);
}
var firstSequence = alignableSequenceA;
var secondSequence = alignableSequenceB;
var needlemanWunschAligner = new NeedlemanWunschAligner();
try
{
/*
* for (var index = 0; index < alignableSequenceA.Count; index++)
* {
* if (alignableSequenceA[index] == Convert.ToByte('X'))
* {
* alignableSequenceA[index] = Convert.ToByte('L');
*
* }
* }
*/
if (!alignableSequenceA.Contains(Convert.ToByte('X')) && !alignableSequenceB.Contains(Convert.ToByte('X')))
{
IList <IPairwiseSequenceAlignment> alignedList = needlemanWunschAligner.AlignSimple(alignableSequenceA, alignableSequenceB);
if (alignedList != null && alignedList.Count > 0 && alignedList[0].PairwiseAlignedSequences.Count > 0)
{
firstSequence = alignedList[0].PairwiseAlignedSequences[0].FirstSequence;
secondSequence = alignedList[0].PairwiseAlignedSequences[0].SecondSequence;
}
}
}
catch (KeyNotFoundException)
{
}
catch (ArgumentException)
{
}
return(SequenceSimilarityPercentage(firstSequence, secondSequence));
}
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 NeedlemanWunschProteinSeqSimpleGap()
{
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;
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.Protein, "HEAGAWGHE-E");
alignedSeq.SecondSequence = new Sequence(Alphabets.Protein, "--P-AW-HEAE");
alignedSeq.Consensus = new Sequence(AmbiguousProteinAlphabet.Instance, "HEXGAWGHEAE");
alignedSeq.Score = 1;
alignedSeq.FirstOffset = 0;
alignedSeq.SecondOffset = 2;
align.PairwiseAlignedSequences.Add(alignedSeq);
expectedOutput.Add(align);
Assert.IsTrue(CompareAlignment(result, expectedOutput));
}
public void PerformNeedlemanWunschPerf()
{
// 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);
nwObj = new NeedlemanWunschAligner();
nwObj.GapOpenCost = -10;
nwObj.GapExtensionCost = -10;
nwObj.SimilarityMatrix = sm;
_watchObj = new Stopwatch();
_watchObj.Reset();
_watchObj.Start();
long memoryStart = GC.GetTotalMemory(false);
// Align sequences using smith water man algorithm.
IList <IPairwiseSequenceAlignment> alignment = nwObj.AlignSimple(aInput, bInput);
_watchObj.Stop();
long memoryEnd = GC.GetTotalMemory(false);
string memoryUsed = (memoryEnd - memoryStart).ToString();
// Display Needlemanwunsch perf test case execution details.
DisplayTestCaseHeader(lstInputFiles, _watchObj, memoryUsed,
"NeedlemanWunsch");
Console.WriteLine(string.Format(
"Needleman Wunsch AlignSimple() method, Alignment Score is : {0}",
alignment[0].PairwiseAlignedSequences[0].Score.ToString()));
// Dispose NeedlemanWunsch object
nwObj = null;
}
private void ValidateNeedlemanWunschAlignment(bool isTextFile, AlignmentParamType alignParam,
AlignmentType alignType)
{
ISequence aInput, bInput;
IAlphabet alphabet = Utility.GetAlphabet(this.utilityObj.xmlUtil.GetTextValue(Constants.NeedlemanWunschAlignAlgorithmNodeName, Constants.AlphabetNameNode));
if (isTextFile)
{
// Read the xml file for getting both the files for aligning.
string filePath1 = this.utilityObj.xmlUtil.GetTextValue(Constants.NeedlemanWunschAlignAlgorithmNodeName, Constants.FilePathNode1);
string filePath2 = this.utilityObj.xmlUtil.GetTextValue(Constants.NeedlemanWunschAlignAlgorithmNodeName, Constants.FilePathNode2);
// Parse the files and get the sequence.
var parseObjectForFile1 = new FastAParser {
Alphabet = alphabet
};
aInput = parseObjectForFile1.Parse(filePath1).First();
var parseObjectForFile2 = new FastAParser {
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.NeedlemanWunschAlignAlgorithmNodeName, Constants.SequenceNode1);
string origSequence2 = this.utilityObj.xmlUtil.GetTextValue(Constants.NeedlemanWunschAlignAlgorithmNodeName, Constants.SequenceNode2);
aInput = new Sequence(alphabet, origSequence1);
bInput = new Sequence(alphabet, origSequence2);
}
string blosumFilePath = this.utilityObj.xmlUtil.GetTextValue(Constants.NeedlemanWunschAlignAlgorithmNodeName, Constants.BlosumFilePathNode);
var sm = new SimilarityMatrix(new StreamReader(blosumFilePath));
int gapOpenCost = int.Parse(this.utilityObj.xmlUtil.GetTextValue(Constants.NeedlemanWunschAlignAlgorithmNodeName, Constants.GapOpenCostNode), null);
int gapExtensionCost = int.Parse(this.utilityObj.xmlUtil.GetTextValue(Constants.NeedlemanWunschAlignAlgorithmNodeName, Constants.GapExtensionCostNode), null);
var needlemanWunschObj = new NeedlemanWunschAligner();
if (AlignmentParamType.AllParam != alignParam)
{
needlemanWunschObj.SimilarityMatrix = sm;
needlemanWunschObj.GapOpenCost = gapOpenCost;
needlemanWunschObj.GapExtensionCost = gapExtensionCost;
}
IList <IPairwiseSequenceAlignment> result = null;
switch (alignParam)
{
case AlignmentParamType.AlignList:
switch (alignType)
{
case AlignmentType.Align:
result = needlemanWunschObj.Align(new List <ISequence> {
aInput, bInput
});
break;
default:
result = needlemanWunschObj.AlignSimple(new List <ISequence> {
aInput, bInput
});
break;
}
break;
case AlignmentParamType.AlignTwo:
switch (alignType)
{
case AlignmentType.Align:
result = needlemanWunschObj.Align(aInput, bInput);
break;
default:
result = needlemanWunschObj.AlignSimple(aInput, bInput);
break;
}
break;
case AlignmentParamType.AllParam:
switch (alignType)
{
case AlignmentType.Align:
result = needlemanWunschObj.Align(
sm, gapOpenCost, gapExtensionCost, aInput, bInput);
break;
default:
result = needlemanWunschObj.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.NeedlemanWunschAlignAlgorithmNodeName,
Constants.ExpectedGapExtensionScoreNode);
expectedSequence1 = this.utilityObj.xmlUtil.GetTextValue(
Constants.NeedlemanWunschAlignAlgorithmNodeName,
Constants.ExpectedGapExtensionSequence1Node);
expectedSequence2 = this.utilityObj.xmlUtil.GetTextValue(
Constants.NeedlemanWunschAlignAlgorithmNodeName,
Constants.ExpectedGapExtensionSequence2Node);
break;
default:
expectedScore = this.utilityObj.xmlUtil.GetTextValue(
Constants.NeedlemanWunschAlignAlgorithmNodeName,
Constants.ExpectedScoreNode);
expectedSequence1 = this.utilityObj.xmlUtil.GetTextValue(
Constants.NeedlemanWunschAlignAlgorithmNodeName,
Constants.ExpectedSequenceNode1);
expectedSequence2 = this.utilityObj.xmlUtil.GetTextValue(
Constants.NeedlemanWunschAlignAlgorithmNodeName,
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, "NeedlemanWunschAligner BVT : Final Score '{0}'.", expectedScore));
ApplicationLog.WriteLine(string.Format(null, "NeedlemanWunschAligner BVT : Aligned First Sequence is '{0}'.", expectedSequence1));
ApplicationLog.WriteLine(string.Format(null, "NeedlemanWunschAligner BVT : Aligned Second Sequence is '{0}'.", expectedSequence2));
Assert.IsTrue(CompareAlignment(result, expectedOutput));
}
public IList <IPairwiseSequenceAlignment> AlignSequencesSimple(SequenceModel[] sequenceData)
{
var sequences = sequenceData.SelectMany(sequence => _provider.Provide(sequence?.FileName, sequence?.Content));
return(_aligner.AlignSimple(sequences));
}
