public void ValidateNUCmerGetClusters()
{
// NOTE: Nigel ran this test with the same data through mmummer and mgaps and got the same result.
// Gets the reference sequence from the FastA file
string filePath = this.utilityObj.xmlUtil.GetTextValue(Constants.MediumSizeSequenceNodeName,
Constants.FilePathNode);
// Gets the query sequence from the FastA file
string queryFilePath = this.utilityObj.xmlUtil.GetTextValue(Constants.MediumSizeSequenceNodeName,
Constants.SearchSequenceFilePathNode);
FastAParser parser = new FastAParser();
IEnumerable <ISequence> seqs1 = parser.Parse(filePath);
IEnumerable <ISequence> seqs2 = parser.Parse(queryFilePath);
var nuc = new Bio.Algorithms.Alignment.NUCmer(seqs1.First())
{
LengthOfMUM = 5,
MinimumScore = 0,
};
var clusts = nuc.GetClusters(seqs2.First());
string clustCount1 = this.utilityObj.xmlUtil.GetTextValue(
Constants.MediumSizeSequenceNodeName, Constants.ClustCount1Node);
Assert.AreEqual(clustCount1, clusts.Count.ToString(CultureInfo.InvariantCulture));
}
/// <summary>
/// Gets the Delta for list of query sequences.
/// </summary>
/// <param name="referenceSequence">The reference sequence.</param>
/// <param name="originalQuerySequences">The query sequence.</param>
/// <returns>Returns list of IEnumerable Delta Alignment.</returns>
private IEnumerable<IEnumerable<DeltaAlignment>> GetDelta(IEnumerable<ISequence> referenceSequence, IEnumerable<ISequence> originalQuerySequences)
{
IEnumerable<ISequence> querySequences =
Forward ? originalQuerySequences
: (Reverse
? ReverseComplementSequenceList(originalQuerySequences)
: AddReverseComplementsToSequenceList(originalQuerySequences));
foreach (ISequence refSeq in referenceSequence)
{
NUCmer nucmer = new NUCmer(refSeq)
{
FixedSeparation = FixedSeparation,
BreakLength = BreakLength,
LengthOfMUM = MinMatch,
MaximumSeparation = MaxGap,
MinimumScore = MinCluster,
SeparationFactor = (float) DiagFactor
};
foreach (ISequence qs in querySequences)
{
_queryCount++;
yield return nucmer.GetDeltaAlignments(qs, !MaxMatch, qs.IsMarkedAsReverseComplement());
}
}
}
/// <summary>
/// Returns the cluster.
/// </summary>
/// <param name="referenceSequence">The Reference sequences.</param>
/// <param name="originalQuerySequences">The Query sequences.</param>
/// <returns>Returns list of clusters.</returns>
private IList<List<IList<Cluster>>> GetCluster(IEnumerable<ISequence> referenceSequence, IEnumerable<ISequence> originalQuerySequences)
{
var clusters = new List<List<IList<Cluster>>>();
var clusters1 = new List<IList<Cluster>>();
IEnumerable<ISequence> querySequences =
Forward ? originalQuerySequences
: (Reverse
? ReverseComplementSequenceList(originalQuerySequences)
: AddReverseComplementsToSequenceList(originalQuerySequences));
_queryCount += querySequences.Count();
foreach (var sequence in referenceSequence)
{
NUCmer nucmer = new NUCmer(sequence)
{
FixedSeparation = FixedSeparation,
BreakLength = BreakLength,
LengthOfMUM = MinMatch,
MaximumSeparation = MaxGap,
MinimumScore = MinCluster,
SeparationFactor = (float) DiagFactor
};
clusters1.AddRange(querySequences.Select(qs => nucmer.GetClusters(qs, !MaxMatch, qs.IsMarkedAsReverseComplement())));
}
clusters.Add(clusters1);
return clusters;
}
/// <summary>
/// This method is considered as main execute method which defines the
/// step by step algorithm. Derived class flows the defined flow by this
/// method.
/// </summary>
/// <param name="referenceSequenceList">Reference sequence.</param>
/// <param name="querySequenceList">List of input sequences.</param>
/// <returns>A list of sequence alignment.</returns>
private IEnumerable <IPairwiseSequenceAlignment> Alignment(IEnumerable <ISequence> referenceSequenceList, IEnumerable <ISequence> querySequenceList)
{
ConsensusResolver = new SimpleConsensusResolver(referenceSequenceList.ElementAt(0).Alphabet);
IList <IPairwiseSequenceAlignment> results = new List <IPairwiseSequenceAlignment>();
IPairwiseSequenceAlignment sequenceAlignment;
IList <PairwiseAlignedSequence> alignments;
List <DeltaAlignment> deltas = new List <DeltaAlignment>();
foreach (ISequence refSequence in referenceSequenceList)
{
this.nucmerAlgo = new NUCmer((Sequence)refSequence);
if (GapOpenCost != DefaultGapOpenCost)
{
this.nucmerAlgo.GapOpenCost = GapOpenCost;
}
if (GapExtensionCost != DefaultGapExtensionCost)
{
this.nucmerAlgo.GapExtensionCost = GapExtensionCost;
}
if (LengthOfMUM != DefaultLengthOfMUM)
{
this.nucmerAlgo.LengthOfMUM = LengthOfMUM;
}
// Set the ClusterBuilder properties to defaults
if (FixedSeparation != ClusterBuilder.DefaultFixedSeparation)
{
this.nucmerAlgo.FixedSeparation = FixedSeparation;
}
if (MaximumSeparation != ClusterBuilder.DefaultMaximumSeparation)
{
this.nucmerAlgo.MaximumSeparation = MaximumSeparation;
}
if (MinimumScore != ClusterBuilder.DefaultMinimumScore)
{
this.nucmerAlgo.MinimumScore = MinimumScore;
}
if (SeparationFactor != ClusterBuilder.DefaultSeparationFactor)
{
this.nucmerAlgo.SeparationFactor = SeparationFactor;
}
if (BreakLength != ModifiedSmithWaterman.DefaultBreakLength)
{
this.nucmerAlgo.BreakLength = BreakLength;
}
this.nucmerAlgo.ConsensusResolver = ConsensusResolver;
if (SimilarityMatrix != null)
{
this.nucmerAlgo.SimilarityMatrix = SimilarityMatrix;
}
foreach (ISequence querySequence in querySequenceList)
{
IEnumerable <DeltaAlignment> deltaAlignment = this.nucmerAlgo.GetDeltaAlignments(querySequence);
deltas.AddRange(deltaAlignment);
}
}
if (deltas.Count > 0)
{
ISequence concatReference = referenceSequenceList.ElementAt(0);
//// concat all the sequences into one sequence
if (referenceSequenceList.Count() > 1)
{
concatReference = ConcatSequence(referenceSequenceList);
}
foreach (ISequence querySequence in querySequenceList)
{
List <DeltaAlignment> qDelta = deltas.Where(d => d.QuerySequence.Equals(querySequence)).ToList();
sequenceAlignment = new PairwiseSequenceAlignment(concatReference, querySequence);
// Convert delta alignments to sequence alignments
alignments = ConvertDeltaToAlignment(qDelta);
if (alignments.Count > 0)
{
foreach (PairwiseAlignedSequence align in alignments)
{
// Calculate the score of alignment
align.Score = CalculateScore(
align.FirstSequence,
align.SecondSequence);
// Make Consensus
align.Consensus = MakeConsensus(
align.FirstSequence,
align.SecondSequence);
sequenceAlignment.PairwiseAlignedSequences.Add(align);
}
}
results.Add(sequenceAlignment);
}
}
return(results);
}
/// <summary>
/// This method is considered as main execute method which defines the
/// step by step algorithm. Derived class flows the defined flow by this
/// method.
/// </summary>
/// <param name="referenceSequenceList">Reference sequence.</param>
/// <param name="originalQuerySequences">List of input sequences.</param>
/// <returns>A list of sequence alignment.</returns>
private IEnumerable <IPairwiseSequenceAlignment> Alignment(IEnumerable <ISequence> referenceSequenceList, IEnumerable <ISequence> originalQuerySequences)
{
ConsensusResolver = new SimpleConsensusResolver(referenceSequenceList.ElementAt(0).Alphabet);
IEnumerable <ISequence> querySequenceList =
ForwardOnly ? originalQuerySequences
: (ReverseOnly
? ReverseComplementSequenceList(originalQuerySequences)
: AddReverseComplementsToSequenceList(originalQuerySequences));
IList <IPairwiseSequenceAlignment> results = new List <IPairwiseSequenceAlignment>();
var deltas = new List <DeltaAlignment>();
foreach (ISequence refSequence in referenceSequenceList)
{
this.nucmerAlgo = new NUCmer(refSequence);
if (GapOpenCost != DefaultGapOpenCost)
{
this.nucmerAlgo.GapOpenCost = GapOpenCost;
}
if (GapExtensionCost != DefaultGapExtensionCost)
{
this.nucmerAlgo.GapExtensionCost = GapExtensionCost;
}
if (LengthOfMUM != DefaultLengthOfMUM)
{
this.nucmerAlgo.LengthOfMUM = LengthOfMUM;
}
// Set the ClusterBuilder properties to defaults
if (FixedSeparation != ClusterBuilder.DefaultFixedSeparation)
{
this.nucmerAlgo.FixedSeparation = FixedSeparation;
}
if (MaximumSeparation != ClusterBuilder.DefaultMaximumSeparation)
{
this.nucmerAlgo.MaximumSeparation = MaximumSeparation;
}
if (MinimumScore != ClusterBuilder.DefaultMinimumScore)
{
this.nucmerAlgo.MinimumScore = MinimumScore;
}
if (SeparationFactor != ClusterBuilder.DefaultSeparationFactor)
{
this.nucmerAlgo.SeparationFactor = SeparationFactor;
}
if (BreakLength != ModifiedSmithWaterman.DefaultBreakLength)
{
this.nucmerAlgo.BreakLength = BreakLength;
}
this.nucmerAlgo.ConsensusResolver = ConsensusResolver;
if (SimilarityMatrix != null)
{
this.nucmerAlgo.SimilarityMatrix = SimilarityMatrix;
}
foreach (ISequence querySequence in querySequenceList)
{
// Check for parameters that would prevent an alignment from being returned.
if (Math.Min(querySequence.Count, refSequence.Count) < MinimumScore)
{
var msg = "Bad parameter settings for NucmerPairwiseAligner. " +
"Tried to align a reference of length " + refSequence.Count.ToString() +
" to a sequence of length " + querySequence.Count.ToString() +
" while requiring a minimum score of MinimumScore = " + MinimumScore +
". This will prevent any alignments from being returned.";
throw new ArgumentException(msg);
}
IEnumerable <DeltaAlignment> deltaAlignment = this.nucmerAlgo.GetDeltaAlignments(querySequence, !MaxMatch, querySequence.IsMarkedAsReverseComplement());
deltas.AddRange(deltaAlignment);
}
}
if (deltas.Count > 0)
{
ISequence concatReference = referenceSequenceList.ElementAt(0);
//// concat all the sequences into one sequence
if (referenceSequenceList.Count() > 1)
{
concatReference = ConcatSequence(referenceSequenceList);
}
foreach (ISequence querySequence in querySequenceList)
{
List <DeltaAlignment> qDelta = deltas.Where(d => d.QuerySequence.Equals(querySequence)).ToList();
IPairwiseSequenceAlignment sequenceAlignment = new PairwiseSequenceAlignment(concatReference, querySequence);
// Convert delta alignments to sequence alignments
IList <PairwiseAlignedSequence> alignments = ConvertDeltaToAlignment(qDelta);
if (alignments.Count > 0)
{
foreach (PairwiseAlignedSequence align in alignments)
{
// Calculate the score of alignment
align.Score = CalculateScore(
align.FirstSequence,
align.SecondSequence);
// Make Consensus
align.Consensus = MakeConsensus(
align.FirstSequence,
align.SecondSequence);
sequenceAlignment.PairwiseAlignedSequences.Add(align);
}
}
results.Add(sequenceAlignment);
}
}
return(results);
}
public void ValidateNUCmerGetClusters()
{
// NOTE: Nigel ran this test with the same data through mmummer and mgaps and got the same result.
// Gets the reference sequence from the FastA file
string filePath = this.utilityObj.xmlUtil.GetTextValue(Constants.MediumSizeSequenceNodeName,
Constants.FilePathNode);
// Gets the query sequence from the FastA file
string queryFilePath = this.utilityObj.xmlUtil.GetTextValue(Constants.MediumSizeSequenceNodeName,
Constants.SearchSequenceFilePathNode);
FastAParser parser = new FastAParser();
IEnumerable<ISequence> seqs1 = parser.Parse(filePath);
IEnumerable<ISequence> seqs2 = parser.Parse(queryFilePath);
var nuc = new Bio.Algorithms.Alignment.NUCmer(seqs1.First()) {
LengthOfMUM = 5,
MinimumScore = 0,
};
var clusts = nuc.GetClusters(seqs2.First());
string clustCount1 = this.utilityObj.xmlUtil.GetTextValue(
Constants.MediumSizeSequenceNodeName, Constants.ClustCount1Node);
Assert.AreEqual(clustCount1, clusts.Count.ToString(CultureInfo.InvariantCulture));
}
/// <summary>
/// This method is considered as main execute method which defines the
/// step by step algorithm. Derived class flows the defined flow by this
/// method.
/// </summary>
/// <param name="referenceSequenceList">Reference sequence.</param>
/// <param name="originalQuerySequences">List of input sequences.</param>
/// <returns>A list of sequence alignment.</returns>
private IEnumerable<IPairwiseSequenceAlignment> Alignment(IEnumerable<ISequence> referenceSequenceList, IEnumerable<ISequence> originalQuerySequences)
{
ConsensusResolver = new SimpleConsensusResolver(referenceSequenceList.ElementAt(0).Alphabet);
IEnumerable<ISequence> querySequenceList =
ForwardOnly ? originalQuerySequences
: (ReverseOnly
? ReverseComplementSequenceList(originalQuerySequences)
: AddReverseComplementsToSequenceList(originalQuerySequences));
IList<IPairwiseSequenceAlignment> results = new List<IPairwiseSequenceAlignment>();
var deltas = new List<DeltaAlignment>();
foreach (ISequence refSequence in referenceSequenceList)
{
this.nucmerAlgo = new NUCmer(refSequence);
if (GapOpenCost != DefaultGapOpenCost) this.nucmerAlgo.GapOpenCost = GapOpenCost;
if (GapExtensionCost != DefaultGapExtensionCost) this.nucmerAlgo.GapExtensionCost = GapExtensionCost;
if (LengthOfMUM != DefaultLengthOfMUM) this.nucmerAlgo.LengthOfMUM = LengthOfMUM;
// Set the ClusterBuilder properties to defaults
if (FixedSeparation != ClusterBuilder.DefaultFixedSeparation) this.nucmerAlgo.FixedSeparation = FixedSeparation;
if (MaximumSeparation != ClusterBuilder.DefaultMaximumSeparation) this.nucmerAlgo.MaximumSeparation = MaximumSeparation;
if (MinimumScore != ClusterBuilder.DefaultMinimumScore) this.nucmerAlgo.MinimumScore = MinimumScore;
if (SeparationFactor != ClusterBuilder.DefaultSeparationFactor) this.nucmerAlgo.SeparationFactor = SeparationFactor;
if (BreakLength != ModifiedSmithWaterman.DefaultBreakLength) this.nucmerAlgo.BreakLength = BreakLength;
this.nucmerAlgo.ConsensusResolver = ConsensusResolver;
if (SimilarityMatrix != null) this.nucmerAlgo.SimilarityMatrix = SimilarityMatrix;
foreach (ISequence querySequence in querySequenceList)
{
// Check for parameters that would prevent an alignment from being returned.
if (Math.Min(querySequence.Count, refSequence.Count) < MinimumScore)
{
var msg = "Bad parameter settings for NucmerPairwiseAligner. " +
"Tried to align a reference of length " + refSequence.Count.ToString() +
" to a sequence of length " + querySequence.Count.ToString() +
" while requiring a minimum score of MinimumScore = " + MinimumScore +
". This will prevent any alignments from being returned.";
throw new ArgumentException(msg);
}
IEnumerable<DeltaAlignment> deltaAlignment = this.nucmerAlgo.GetDeltaAlignments(querySequence, !MaxMatch, querySequence.IsMarkedAsReverseComplement());
deltas.AddRange(deltaAlignment);
}
}
if (deltas.Count > 0)
{
ISequence concatReference = referenceSequenceList.ElementAt(0);
//// concat all the sequences into one sequence
if (referenceSequenceList.Count() > 1)
{
concatReference = ConcatSequence(referenceSequenceList);
}
foreach (ISequence querySequence in querySequenceList)
{
List<DeltaAlignment> qDelta = deltas.Where(d => d.QuerySequence.Equals(querySequence)).ToList();
IPairwiseSequenceAlignment sequenceAlignment = new PairwiseSequenceAlignment(concatReference, querySequence);
// Convert delta alignments to sequence alignments
IList<PairwiseAlignedSequence> alignments = ConvertDeltaToAlignment(qDelta);
if (alignments.Count > 0)
{
foreach (PairwiseAlignedSequence align in alignments)
{
// Calculate the score of alignment
align.Score = CalculateScore(
align.FirstSequence,
align.SecondSequence);
// Make Consensus
align.Consensus = MakeConsensus(
align.FirstSequence,
align.SecondSequence);
sequenceAlignment.PairwiseAlignedSequences.Add(align);
}
}
results.Add(sequenceAlignment);
}
}
return results;
}
/// <summary>
/// Aligns reads to reference genome using NUCmer.
/// </summary>
/// <param name="nodeName">Name of parent Node which contains the data in xml.</param>
/// <param name="isFilePath">Represents sequence is in a file or not.</param>
/// <returns>Delta i.e. output from NUCmer</returns>
IList<IEnumerable<DeltaAlignment>> GetDeltaAlignment(string nodeName, bool isFilePath)
{
string[] referenceSequences = null;
string[] searchSequences = null;
List<ISequence> referenceSeqList = new List<ISequence>();
List<ISequence> searchSeqList = new List<ISequence>();
IList<IEnumerable<DeltaAlignment>> results = new List<IEnumerable<DeltaAlignment>>();
if (isFilePath)
{
// Gets the reference sequence from the FastA file
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.FilePathNode1);
Assert.IsNotNull(filePath);
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"Comparative BVT : Successfully validated the File Path '{0}'.", filePath));
using (FastASequencePositionParser parser = new FastASequencePositionParser(filePath))
{
IEnumerable<ISequence> referenceList = parser.Parse();
foreach (ISequence seq in referenceList)
{
referenceSeqList.Add(seq);
}
// Gets the query sequence from the FastA file
string queryFilePath = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.FilePathNode2);
Assert.IsNotNull(queryFilePath);
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"Comparative BVT : Successfully validated the File Path '{0}'.", queryFilePath));
using (FastASequencePositionParser queryParser = new FastASequencePositionParser(queryFilePath))
{
IEnumerable<ISequence> querySeqList = queryParser.Parse();
foreach (ISequence seq in querySeqList)
{
searchSeqList.Add(seq);
}
}
}
}
else
{
// Gets the reference & search sequences from the configurtion file
referenceSequences = utilityObj.xmlUtil.GetTextValues(nodeName,
Constants.ReferenceSequencesNode);
searchSequences = utilityObj.xmlUtil.GetTextValues(nodeName,
Constants.SearchSequencesNode);
IAlphabet seqAlphabet = Utility.GetAlphabet(utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.AlphabetNameNode));
for (int i = 0; i < referenceSequences.Length; i++)
{
ISequence referSeq = new Sequence(seqAlphabet, encodingObj.GetBytes(referenceSequences[i]));
referenceSeqList.Add(referSeq);
}
string[] seqArray = searchSequences.ElementAt(0).Split(',');
searchSeqList.AddRange(seqArray.Select(t => new Sequence(seqAlphabet, encodingObj.GetBytes(t))).Cast<ISequence>());
}
foreach (ISequence reference in referenceSeqList)
{
NUCmer nucmerAligner = new NUCmer((Sequence)reference);
string fixedSeparation = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.FixedSeparationNode);
string minimumScore = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.MinimumScoreNode);
string separationFactor = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.SeparationFactorNode);
string LengthOfMUM = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.MUMLengthNode);
nucmerAligner.FixedSeparation = int.Parse(fixedSeparation);
nucmerAligner.MinimumScore = int.Parse(minimumScore);
nucmerAligner.SeparationFactor = int.Parse(separationFactor);
nucmerAligner.LengthOfMUM = int.Parse(LengthOfMUM);
foreach (ISequence querySeq in searchSeqList)
{
results.Add(nucmerAligner.GetDeltaAlignments(querySeq, true));
}
}
return results;
}