public void PairwiseOverlapMultipleAlignments()
{
Sequence sequence1 = new Sequence(Alphabets.DNA, "CCCAACCC");
Sequence sequence2 = new Sequence(Alphabets.DNA, "CCC");
SimilarityMatrix sm = new DiagonalSimilarityMatrix(5, -20);
int gapPenalty = -10;
PairwiseOverlapAligner overlap = new PairwiseOverlapAligner();
overlap.SimilarityMatrix = sm;
overlap.GapOpenCost = gapPenalty;
IList <IPairwiseSequenceAlignment> result = overlap.AlignSimple(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>();
IPairwiseSequenceAlignment align = new PairwiseSequenceAlignment();
// First alignment
PairwiseAlignedSequence alignedSeq = new PairwiseAlignedSequence();
alignedSeq.FirstSequence = new Sequence(Alphabets.DNA, "CCC");
alignedSeq.SecondSequence = new Sequence(Alphabets.DNA, "CCC");
alignedSeq.Consensus = new Sequence(Alphabets.DNA, "CCC");
alignedSeq.Score = 15;
alignedSeq.FirstOffset = 0;
alignedSeq.SecondOffset = 0;
align.PairwiseAlignedSequences.Add(alignedSeq);
// Second alignment
alignedSeq = new PairwiseAlignedSequence();
alignedSeq.FirstSequence = new Sequence(Alphabets.DNA, "CCC");
alignedSeq.SecondSequence = new Sequence(Alphabets.DNA, "CCC");
alignedSeq.Consensus = new Sequence(Alphabets.DNA, "CCC");
alignedSeq.Score = 15;
alignedSeq.FirstOffset = 0;
alignedSeq.SecondOffset = 5;
align.PairwiseAlignedSequences.Add(alignedSeq);
expectedOutput.Add(align);
Assert.IsTrue(CompareAlignment(result, expectedOutput));
}
public void PairwiseOverlapProteinSeqSimpleGapUseEarthToFillMatrix()
{
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;
PairwiseOverlapAligner overlap = new PairwiseOverlapAligner();
overlap.UseEARTHToFillMatrix = true;
overlap.SimilarityMatrix = sm;
overlap.GapOpenCost = gapPenalty;
IList <IPairwiseSequenceAlignment> result = overlap.AlignSimple(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>();
IPairwiseSequenceAlignment align = new PairwiseSequenceAlignment();
PairwiseAlignedSequence alignedSeq = new PairwiseAlignedSequence();
alignedSeq.FirstSequence = new Sequence(Alphabets.Protein, "GAWGHEE");
alignedSeq.SecondSequence = new Sequence(Alphabets.Protein, "PAW-HEA");
alignedSeq.Consensus = new Sequence(Alphabets.AmbiguousProtein, "XAWGHEX");
alignedSeq.Score = 25;
alignedSeq.FirstOffset = 0;
alignedSeq.SecondOffset = 3;
align.PairwiseAlignedSequences.Add(alignedSeq);
expectedOutput.Add(align);
Assert.IsTrue(CompareAlignment(result, expectedOutput));
}
void ValidatePairwiseOverlapAlignment(bool isTextFile, AlignmentParamType alignParam,
AlignmentType alignType)
{
ISequence aInput = null;
ISequence bInput = null;
IAlphabet alphabet = Utility.GetAlphabet(utilityObj.xmlUtil.GetTextValue(
Constants.PairwiseOverlapAlignAlgorithmNodeName,
Constants.AlphabetNameNode));
if (isTextFile)
{
// Read the xml file for getting both the files for aligning.
string filePath1 = utilityObj.xmlUtil.GetTextValue(
Constants.PairwiseOverlapAlignAlgorithmNodeName,
Constants.FilePathNode1);
string filePath2 = utilityObj.xmlUtil.GetTextValue(
Constants.PairwiseOverlapAlignAlgorithmNodeName,
Constants.FilePathNode2);
//Parse the files and get the sequence.
using (FastAParser parser1 = new FastAParser(filePath1))
{
parser1.Alphabet = alphabet;
aInput = parser1.Parse().ElementAt(0);
}
using (FastAParser parser2 = new FastAParser(filePath2))
{
parser2.Alphabet = alphabet;
bInput = parser2.Parse().ElementAt(0);
}
}
else
{
// Read the xml file for getting both the files for aligning.
string origSequence1 = utilityObj.xmlUtil.GetTextValue(
Constants.PairwiseOverlapAlignAlgorithmNodeName,
Constants.SequenceNode1);
string origSequence2 = utilityObj.xmlUtil.GetTextValue(
Constants.PairwiseOverlapAlignAlgorithmNodeName,
Constants.SequenceNode2);
aInput = new Sequence(alphabet, origSequence1);
bInput = new Sequence(alphabet, origSequence2);
}
string aInputString = new string(aInput.Select(a => (char)a).ToArray());
string bInputString = new string(bInput.Select(a => (char)a).ToArray());
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"PairwiseOverlapAligner BVT : First sequence used is '{0}'.",
aInputString));
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"PairwiseOverlapAligner BVT : Second sequence used is '{0}'.",
bInputString));
Console.WriteLine(string.Format((IFormatProvider)null,
"PairwiseOverlapAligner BVT : First sequence used is '{0}'.",
aInputString));
Console.WriteLine(string.Format((IFormatProvider)null,
"PairwiseOverlapAligner BVT : Second sequence used is '{0}'.",
bInputString));
string blosumFilePath = utilityObj.xmlUtil.GetTextValue(
Constants.PairwiseOverlapAlignAlgorithmNodeName,
Constants.BlosumFilePathNode);
SimilarityMatrix sm = new SimilarityMatrix(blosumFilePath);
int gapOpenCost = int.Parse(utilityObj.xmlUtil.GetTextValue(
Constants.PairwiseOverlapAlignAlgorithmNodeName,
Constants.GapOpenCostNode), (IFormatProvider)null);
int gapExtensionCost = int.Parse(utilityObj.xmlUtil.GetTextValue(
Constants.PairwiseOverlapAlignAlgorithmNodeName,
Constants.GapExtensionCostNode), (IFormatProvider)null);
PairwiseOverlapAligner pairwiseOverlapObj = new PairwiseOverlapAligner();
if (AlignmentParamType.AllParam != alignParam)
{
pairwiseOverlapObj.SimilarityMatrix = sm;
pairwiseOverlapObj.GapOpenCost = gapOpenCost;
}
IList <IPairwiseSequenceAlignment> result = null;
switch (alignParam)
{
case AlignmentParamType.AlignList:
List <ISequence> sequences = new List <ISequence>();
sequences.Add(aInput);
sequences.Add(bInput);
switch (alignType)
{
case AlignmentType.Align:
result = pairwiseOverlapObj.Align(sequences);
break;
default:
result = pairwiseOverlapObj.AlignSimple(sequences);
break;
}
break;
case AlignmentParamType.AlignTwo:
switch (alignType)
{
case AlignmentType.Align:
result = pairwiseOverlapObj.Align(aInput, bInput);
break;
default:
result = pairwiseOverlapObj.AlignSimple(aInput, bInput);
break;
}
break;
case AlignmentParamType.AllParam:
switch (alignType)
{
case AlignmentType.Align:
result = pairwiseOverlapObj.Align(sm, gapOpenCost,
gapExtensionCost, aInput, bInput);
break;
default:
result = pairwiseOverlapObj.AlignSimple(sm, gapOpenCost, aInput, bInput);
break;
}
break;
default:
break;
}
pairwiseOverlapObj = null;
aInput = null;
bInput = null;
sm = null;
// Read the xml file for getting both the files for aligning.
string expectedSequence1 = string.Empty;
string expectedSequence2 = string.Empty;
string expectedScore = string.Empty;
aInput = null;
bInput = null;
sm = null;
switch (alignType)
{
case AlignmentType.Align:
expectedScore = utilityObj.xmlUtil.GetTextValue(
Constants.PairwiseOverlapAlignAlgorithmNodeName,
Constants.ExpectedGapExtensionScoreNode);
expectedSequence1 = utilityObj.xmlUtil.GetTextValue(
Constants.PairwiseOverlapAlignAlgorithmNodeName,
Constants.ExpectedGapExtensionSequence1Node);
expectedSequence2 = utilityObj.xmlUtil.GetTextValue(
Constants.PairwiseOverlapAlignAlgorithmNodeName,
Constants.ExpectedGapExtensionSequence2Node);
break;
default:
expectedScore = utilityObj.xmlUtil.GetTextValue(
Constants.PairwiseOverlapAlignAlgorithmNodeName,
Constants.ExpectedScoreNode);
expectedSequence1 = utilityObj.xmlUtil.GetTextValue(
Constants.PairwiseOverlapAlignAlgorithmNodeName,
Constants.ExpectedSequenceNode1);
expectedSequence2 = utilityObj.xmlUtil.GetTextValue(
Constants.PairwiseOverlapAlignAlgorithmNodeName,
Constants.ExpectedSequenceNode2);
break;
}
IList <IPairwiseSequenceAlignment> expectedOutput = new List <IPairwiseSequenceAlignment>();
string[] expectedSequences1, expectedSequences2;
char[] seperators = new char[1] {
';'
};
expectedSequences1 = expectedSequence1.Split(seperators);
expectedSequences2 = expectedSequence2.Split(seperators);
IPairwiseSequenceAlignment align = new PairwiseSequenceAlignment();
PairwiseAlignedSequence alignedSeq;
for (int i = 0; i < expectedSequences1.Length; i++)
{
alignedSeq = new PairwiseAlignedSequence();
alignedSeq.FirstSequence = new Sequence(alphabet, expectedSequences1[i]);
alignedSeq.SecondSequence = new Sequence(alphabet, expectedSequences2[i]);
alignedSeq.Score = Convert.ToInt32(expectedScore, (IFormatProvider)null);
align.PairwiseAlignedSequences.Add(alignedSeq);
}
expectedOutput.Add(align);
Assert.IsTrue(CompareAlignment(result, expectedOutput));
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"PairwiseOverlapAligner BVT : Final Score '{0}'.", expectedScore));
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"PairwiseOverlapAligner BVT : Aligned First Sequence is '{0}'.",
expectedSequence1));
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"PairwiseOverlapAligner BVT : Aligned Second Sequence is '{0}'.",
expectedSequence2));
Console.WriteLine(string.Format((IFormatProvider)null,
"PairwiseOverlapAligner BVT : Final Score '{0}'.", expectedScore));
Console.WriteLine(string.Format((IFormatProvider)null,
"PairwiseOverlapAligner BVT : Aligned First Sequence is '{0}'.",
expectedSequence1));
Console.WriteLine(string.Format((IFormatProvider)null,
"PairwiseOverlapAligner BVT : Aligned Second Sequence is '{0}'.",
expectedSequence2));
}
/// <summary>
/// Validates PairwiseOverlapAlignment algorithm for the parameters passed.
/// </summary>
/// <param name="isTextFile">Is text file an input.</param>
/// <param name="alignParam">parameter based on which certain validations are done.</param>
/// <param name="alignType">Is the Align type Simple or Align with Gap Extension cost?</param>
private void ValidatePairwiseOverlapAlignment(bool isTextFile, AlignmentParamType alignParam, AlignmentType alignType)
{
ISequence aInput;
ISequence bInput;
IAlphabet alphabet = Utility.GetAlphabet(this.utilityObj.xmlUtil.GetTextValue(Constants.PairwiseOverlapAlignAlgorithmNodeName, Constants.AlphabetNameNode));
if (isTextFile)
{
// Read the xml file for getting both the files for aligning.
string filePath1 = this.utilityObj.xmlUtil.GetTextValue(Constants.PairwiseOverlapAlignAlgorithmNodeName, Constants.FilePathNode1).TestDir();
string filePath2 = this.utilityObj.xmlUtil.GetTextValue(Constants.PairwiseOverlapAlignAlgorithmNodeName, Constants.FilePathNode2).TestDir();
//Parse the files and get the sequence.
var parser = new FastAParser {
Alphabet = alphabet
};
aInput = parser.Parse(filePath1).ElementAt(0);
bInput = parser.Parse(filePath2).ElementAt(0);
}
else
{
// Read the xml file for getting both the files for aligning.
string origSequence1 = this.utilityObj.xmlUtil.GetTextValue(Constants.PairwiseOverlapAlignAlgorithmNodeName, Constants.SequenceNode1);
string origSequence2 = this.utilityObj.xmlUtil.GetTextValue(Constants.PairwiseOverlapAlignAlgorithmNodeName, Constants.SequenceNode2);
aInput = new Sequence(alphabet, origSequence1);
bInput = new Sequence(alphabet, origSequence2);
}
var aInputString = aInput.ConvertToString();
var bInputString = bInput.ConvertToString();
ApplicationLog.WriteLine($"PairwiseOverlapAligner BVT : First sequence used is '{aInputString}'.");
ApplicationLog.WriteLine($"PairwiseOverlapAligner BVT : Second sequence used is '{bInputString}'.");
string blosumFilePath = this.utilityObj.xmlUtil.GetTextValue(Constants.PairwiseOverlapAlignAlgorithmNodeName, Constants.BlosumFilePathNode).TestDir();
var sm = new SimilarityMatrix(new StreamReader(blosumFilePath));
int gapOpenCost = int.Parse(this.utilityObj.xmlUtil.GetTextValue(Constants.PairwiseOverlapAlignAlgorithmNodeName, Constants.GapOpenCostNode), null);
int gapExtensionCost = int.Parse(this.utilityObj.xmlUtil.GetTextValue(Constants.PairwiseOverlapAlignAlgorithmNodeName, Constants.GapExtensionCostNode), null);
var pairwiseOverlapObj = new PairwiseOverlapAligner();
if (AlignmentParamType.AllParam != alignParam)
{
pairwiseOverlapObj.SimilarityMatrix = sm;
pairwiseOverlapObj.GapOpenCost = gapOpenCost;
}
IList <IPairwiseSequenceAlignment> result = null;
switch (alignParam)
{
case AlignmentParamType.AlignList:
var sequences = new List <ISequence> {
aInput, bInput
};
switch (alignType)
{
case AlignmentType.Align:
result = pairwiseOverlapObj.Align(sequences);
break;
default:
result = pairwiseOverlapObj.AlignSimple(sequences);
break;
}
break;
case AlignmentParamType.AlignTwo:
switch (alignType)
{
case AlignmentType.Align:
result = pairwiseOverlapObj.Align(aInput, bInput);
break;
default:
result = pairwiseOverlapObj.AlignSimple(aInput, bInput);
break;
}
break;
case AlignmentParamType.AllParam:
switch (alignType)
{
case AlignmentType.Align:
result = pairwiseOverlapObj.Align(sm, gapOpenCost,
gapExtensionCost, aInput, bInput);
break;
default:
result = pairwiseOverlapObj.AlignSimple(sm, gapOpenCost, aInput, bInput);
break;
}
break;
default:
break;
}
// Read the xml file for getting both the files for aligning.
string expectedSequence1;
string expectedSequence2;
string expectedScore;
switch (alignType)
{
case AlignmentType.Align:
expectedScore = this.utilityObj.xmlUtil.GetTextValue(Constants.PairwiseOverlapAlignAlgorithmNodeName, Constants.ExpectedGapExtensionScoreNode);
expectedSequence1 = this.utilityObj.xmlUtil.GetTextValue(Constants.PairwiseOverlapAlignAlgorithmNodeName, Constants.ExpectedGapExtensionSequence1Node);
expectedSequence2 = this.utilityObj.xmlUtil.GetTextValue(Constants.PairwiseOverlapAlignAlgorithmNodeName, Constants.ExpectedGapExtensionSequence2Node);
break;
default:
expectedScore = this.utilityObj.xmlUtil.GetTextValue(Constants.PairwiseOverlapAlignAlgorithmNodeName, Constants.ExpectedScoreNode);
expectedSequence1 = this.utilityObj.xmlUtil.GetTextValue(Constants.PairwiseOverlapAlignAlgorithmNodeName, Constants.ExpectedSequenceNode1);
expectedSequence2 = this.utilityObj.xmlUtil.GetTextValue(Constants.PairwiseOverlapAlignAlgorithmNodeName, Constants.ExpectedSequenceNode2);
break;
}
IList <IPairwiseSequenceAlignment> expectedOutput = new List <IPairwiseSequenceAlignment>();
var seperators = new[] { ';' };
string[] expectedSequences1 = expectedSequence1.Split(seperators);
string[] expectedSequences2 = expectedSequence2.Split(seperators);
IPairwiseSequenceAlignment align = new PairwiseSequenceAlignment();
for (int i = 0; i < expectedSequences1.Length; i++)
{
PairwiseAlignedSequence alignedSeq = new PairwiseAlignedSequence
{
FirstSequence = new Sequence(alphabet, expectedSequences1[i]),
SecondSequence = new Sequence(alphabet, expectedSequences2[i]),
Score = Convert.ToInt32(expectedScore, null)
};
align.PairwiseAlignedSequences.Add(alignedSeq);
}
expectedOutput.Add(align);
Assert.IsTrue(AlignmentHelpers.CompareAlignment(result, expectedOutput));
ApplicationLog.WriteLine(string.Format(null, "PairwiseOverlapAligner BVT : Final Score '{0}'.", expectedScore));
ApplicationLog.WriteLine(string.Format(null, "PairwiseOverlapAligner BVT : Aligned First Sequence is '{0}'.", expectedSequence1));
ApplicationLog.WriteLine(string.Format(null, "PairwiseOverlapAligner BVT : Aligned Second Sequence is '{0}'.", expectedSequence2));
}