/// <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()));
}
}
}
public void ValidateNUCmerGetClusters()
{
// Gets the reference sequence from the FastA file
string filePath = utilityObj.xmlUtil.GetTextValue(Constants.MediumSizeSequenceNodeName,
Constants.FilePathNode);
// Gets the query sequence from the FastA file
string queryFilePath = utilityObj.xmlUtil.GetTextValue(Constants.MediumSizeSequenceNodeName,
Constants.SearchSequenceFilePathNode);
using (FastAParser parser1 = new FastAParser(filePath))
{
using (FastAParser parser2 = new FastAParser(queryFilePath))
{
IEnumerable <ISequence> seqs1 = parser1.Parse();
IEnumerable <ISequence> seqs2 = parser2.Parse();
NUCmer nuc = new NUCmer((Sequence)seqs1.ElementAt(0));
nuc.LengthOfMUM = 5;
nuc.MinimumScore = 0;
nuc.BreakLength = 0;
IList <Cluster> clusts = nuc.GetClusters(seqs2.ElementAt(0), true);
string clustCount1 = utilityObj.xmlUtil.GetTextValue(Constants.MediumSizeSequenceNodeName,
Constants.ClustCount1Node);
Assert.AreEqual(clustCount1, clusts.Count.ToString((IFormatProvider)null));
}
}
}
/// <summary>
/// Gets the Delta for list of query sequences.
/// </summary>
/// <param name="referenceSequence">The reference sequence.</param>
/// <param name="querySequence">The query sequence.</param>
/// <returns>Returns list of IEnumerable Delta Alignment.</returns>
private IList<List<IEnumerable<DeltaAlignment>>> GetDelta(IEnumerable<ISequence> referenceSequence, IEnumerable<ISequence> querySequence)
{
IList<List<IEnumerable<DeltaAlignment>>> delta;
if (this.MaxMatch)
{
delta = referenceSequence.AsParallel().Select(sequence =>
{
NUCmer nucmer = new NUCmer();
nucmer.BreakLength = BreakLength;
nucmer.LengthOfMUM = MinMatch;
nucmer.MaximumSeparation = MaxGap;
nucmer.MinimumScore = MinCluster;
nucmer.SeparationFactor = (float)DiagFactor;
return nucmer.GetDeltaAlignments(new List<ISequence> { sequence }, GetSequence(querySequence), false);
}).ToList();
}
else
{
delta = referenceSequence.AsParallel().Select(sequence =>
{
NUCmer nucmer = new NUCmer();
nucmer.BreakLength = BreakLength;
nucmer.LengthOfMUM = MinMatch;
nucmer.MaximumSeparation = MaxGap;
nucmer.MinimumScore = MinCluster;
nucmer.SeparationFactor = (float)DiagFactor;
return nucmer.GetDeltaAlignments(new List<ISequence> { sequence }, GetSequence(querySequence));
}).ToList();
}
return delta;
}
/// <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>
/// Aligns reads to reference genome using NUCmer.
/// </summary>
/// <param name="referenceSequence">Sequence of reference genome.</param>
/// <param name="reads">List of sequence reads.</param>
/// <returns>Delta alignments after read alignment.</returns>
private IList <IEnumerable <DeltaAlignment> > ReadAlignment(IEnumerable <ISequence> referenceSequence, IEnumerable <ISequence> reads)
{
IList <List <IEnumerable <DeltaAlignment> > > delta;
List <IEnumerable <DeltaAlignment> > deltaAlignments = new List <IEnumerable <DeltaAlignment> >();
delta = referenceSequence.AsParallel().Select(sequence =>
{
NUCmer nucmer = new NUCmer();
// TODO: Update these hardcoded values with the onces used in AMOSS while validating functionality with real data.
nucmer.FixedSeparation = 0;
nucmer.MinimumScore = 1;
nucmer.SeparationFactor = 0;
nucmer.MaximumSeparation = 0;
nucmer.BreakLength = BreakLength;
nucmer.LengthOfMUM = LengthOfMum;
return(nucmer.GetDeltaAlignments(new List <ISequence> {
sequence
}, reads, false));
}).ToList();
foreach (var alignment in delta)
{
foreach (var align in alignment)
{
deltaAlignments.Add(align);
}
}
return(deltaAlignments);
}
public NucMerQueryable(Sequence touse)
{
ReferenceSequence = touse;
nucmer = new NUCmer(ReferenceSequence)
{
FixedSeparation = FixedSeparation,
BreakLength = BreakLength,
LengthOfMUM = MinMatch,
MaximumSeparation = MaxGap,
MinimumScore = 22,
SeparationFactor = (float)DiagFactor
};
}
/// <summary>
/// Returns the cluster.
/// </summary>
/// <param name="referenceSequence">The Reference sequence.</param>
/// <param name="querySequence">The Query sequence.</param>
/// <returns>Returns list of clusters.</returns>
private IList <List <IList <Cluster> > > GetCluster(IEnumerable <ISequence> referenceSequence, IEnumerable <ISequence> querySequence)
{
IList <List <IList <Cluster> > > clusters = new List <List <IList <Cluster> > >();
List <IList <Cluster> > clusters1 = new List <IList <Cluster> >();
if (this.MaxMatch)
{
Parallel.ForEach(referenceSequence, sequence =>
{
NUCmer nucmer = new NUCmer((Sequence)sequence);
nucmer.FixedSeparation = FixedSeparation;
nucmer.BreakLength = BreakLength;
nucmer.LengthOfMUM = MinMatch;
nucmer.MaximumSeparation = MaxGap;
nucmer.MinimumScore = MinCluster;
nucmer.SeparationFactor = (float)DiagFactor;
foreach (ISequence qrySequence in querySequence)
{
clusters1.Add(nucmer.GetClusters(qrySequence, false));
}
});
clusters.Add(clusters1);
}
else
{
Parallel.ForEach(referenceSequence, sequence =>
{
NUCmer nucmer = new NUCmer((Sequence)sequence);
nucmer.FixedSeparation = FixedSeparation;
nucmer.BreakLength = BreakLength;
nucmer.LengthOfMUM = MinMatch;
nucmer.MaximumSeparation = MaxGap;
nucmer.MinimumScore = MinCluster;
nucmer.SeparationFactor = (float)DiagFactor;
foreach (ISequence qrySequence in querySequence)
{
clusters1.Add(nucmer.GetClusters(qrySequence));
}
});
clusters.Add(clusters1);
}
return(clusters);
}
/// <summary>
/// Gets the Delta for list of query sequences.
/// </summary>
/// <param name="referenceSequence">The reference sequence.</param>
/// <param name="querySequence">The query sequence.</param>
/// <returns>Returns list of IEnumerable Delta Alignment.</returns>
private IEnumerable <IEnumerable <DeltaAlignment> > GetDelta(IEnumerable <ISequence> referenceSequence, IEnumerable <ISequence> querySequence)
{
if (this.MaxMatch)
{
foreach (ISequence refSeq in referenceSequence)
{
NUCmer nucmer = new NUCmer((Sequence)refSeq);
nucmer.FixedSeparation = FixedSeparation;
nucmer.BreakLength = BreakLength;
nucmer.LengthOfMUM = MinMatch;
nucmer.MaximumSeparation = MaxGap;
nucmer.MinimumScore = MinCluster;
nucmer.SeparationFactor = (float)DiagFactor;
foreach (ISequence qrySequence in querySequence)
{
queryCount++;
yield return(nucmer.GetDeltaAlignments(qrySequence, false));
}
}
}
else
{
foreach (ISequence refSeq in referenceSequence)
{
NUCmer nucmer = new NUCmer((Sequence)refSeq);
nucmer.FixedSeparation = FixedSeparation;
nucmer.BreakLength = BreakLength;
nucmer.LengthOfMUM = MinMatch;
nucmer.MaximumSeparation = MaxGap;
nucmer.MinimumScore = MinCluster;
nucmer.SeparationFactor = (float)DiagFactor;
foreach (ISequence qrySequence in querySequence)
{
queryCount++;
yield return(nucmer.GetDeltaAlignments(qrySequence));
}
}
}
}
/// <summary>
/// Aligns reads to reference genome using NUCmer.
/// </summary>
/// <param name="referenceSequence">Sequence of reference genome.</param>
/// <param name="reads">List of sequence reads.</param>
/// <returns>Delta alignments after read alignment.</returns>
private IEnumerable <DeltaAlignment> ReadAlignment(IEnumerable <ISequence> referenceSequence, IEnumerable <ISequence> reads)
{
foreach (ISequence sequence in referenceSequence)
{
NUCmer nucmer = new NUCmer((Sequence)sequence);
nucmer.FixedSeparation = this.FixedSeparation;
nucmer.MinimumScore = this.MinimumScore;
nucmer.SeparationFactor = this.SeparationFactor;
nucmer.MaximumSeparation = this.MaximumSeparation;
nucmer.BreakLength = this.BreakLength;
nucmer.LengthOfMUM = this.LengthOfMum;
foreach (ISequence qrySequence in reads)
{
foreach (DeltaAlignment delta in nucmer.GetDeltaAlignments(qrySequence, false))
{
yield return(delta);
}
}
}
}