public HomeController(IParserManager parserManager,
IHierarchicalClustering hierarchicalClustering,
IClusterSerializer clusterSerializer)
{
ParserManager = parserManager;
HierarchicalClustering = hierarchicalClustering;
ClusterSerializer = clusterSerializer;
}
/// <summary>
/// Construct a tree by hierarchical clustering method.
///
/// The node list is already generated in the hierarchical clustering method
/// and the root will be the last node in the list
/// </summary>
/// <param name="hCluster">hierarcical clustering class object</param>
public BinaryGuideTree(IHierarchicalClustering hCluster)
{
if (hCluster == null)
{
throw new ArgumentException("null Hierarchical clustering class");
}
if (hCluster.Nodes.Count == 0)
{
throw new ArgumentException("empty node list in Hierarchical clustering class");
}
_nodes = hCluster.Nodes;
_edges = hCluster.Edges;
_root = hCluster.Nodes[hCluster.Nodes.Count - 1];
_numberOfNodes = hCluster.Nodes.Count;
_numberOfLeaves = (_numberOfNodes + 2) / 2;
}
/// <summary>
/// Performs Stage 1, 2, and 3 as described in class description.
/// </summary>
/// <param name="inputSequences"></param>
/// <returns></returns>
public IList <Bio.Algorithms.Alignment.ISequenceAlignment> Align(IEnumerable <ISequence> inputSequences)
{
List <ISequence> sequences = inputSequences.ToList();
// Initializations
if (sequences.Count > 0)
{
if (ConsensusResolver == null)
{
ConsensusResolver = new SimpleConsensusResolver(_alphabet);
}
else
{
ConsensusResolver.SequenceAlphabet = _alphabet;
}
}
// Get ProfileAligner ready
IProfileAligner profileAligner = null;
switch (_profileAlignerName)
{
case (ProfileAlignerNames.NeedlemanWunschProfileAligner):
if (_degreeOfParallelism == 1)
{
profileAligner = new NeedlemanWunschProfileAlignerSerial(
SimilarityMatrix, _profileProfileFunctionName, GapOpenCost, GapExtensionCost, _numberOfPartitions);
}
else
{
profileAligner = new NeedlemanWunschProfileAlignerParallel(
SimilarityMatrix, _profileProfileFunctionName, GapOpenCost, GapExtensionCost, _numberOfPartitions);
}
break;
case (ProfileAlignerNames.SmithWatermanProfileAligner):
if (_degreeOfParallelism == 1)
{
profileAligner = new SmithWatermanProfileAlignerSerial(
SimilarityMatrix, _profileProfileFunctionName, GapOpenCost, GapExtensionCost, _numberOfPartitions);
}
else
{
profileAligner = new SmithWatermanProfileAlignerParallel(
SimilarityMatrix, _profileProfileFunctionName, GapOpenCost, GapExtensionCost, _numberOfPartitions);
}
break;
default:
throw new ArgumentException("Invalid profile aligner name");
}
_alignedSequences = new List <ISequence>(sequences.Count);
float currentScore = 0;
// STAGE 1
Performance.Snapshot("Stage 1");
// Generate DistanceMatrix
KmerDistanceMatrixGenerator kmerDistanceMatrixGenerator =
new KmerDistanceMatrixGenerator(sequences, _kmerLength, _alphabet, _distanceFunctionName);
// Hierarchical clustering
IHierarchicalClustering hierarcicalClustering =
new HierarchicalClusteringParallel
(kmerDistanceMatrixGenerator.DistanceMatrix, _hierarchicalClusteringMethodName);
// Generate Guide Tree
BinaryGuideTree binaryGuideTree =
new BinaryGuideTree(hierarcicalClustering);
// Progressive Alignment
IProgressiveAligner progressiveAlignerA = new ProgressiveAligner(profileAligner);
progressiveAlignerA.Align(sequences, binaryGuideTree);
currentScore = MsaUtils.MultipleAlignmentScoreFunction(progressiveAlignerA.AlignedSequences, SimilarityMatrix, GapOpenCost, GapExtensionCost);
if (currentScore > _alignmentScoreA)
{
_alignmentScoreA = currentScore;
_alignedSequencesA = progressiveAlignerA.AlignedSequences;
}
if (_alignmentScoreA > _alignmentScore)
{
_alignmentScore = _alignmentScoreA;
_alignedSequences = _alignedSequencesA;
}
if (PAMSAMMultipleSequenceAligner.FasterVersion)
{
_alignedSequencesB = _alignedSequencesA;
_alignedSequencesC = _alignedSequencesA;
_alignmentScoreB = _alignmentScoreA;
_alignmentScoreC = _alignmentScoreA;
}
else
{
BinaryGuideTree binaryGuideTreeB = null;
IHierarchicalClustering hierarcicalClusteringB = null;
KimuraDistanceMatrixGenerator kimuraDistanceMatrixGenerator = new KimuraDistanceMatrixGenerator();
if (PAMSAMMultipleSequenceAligner.UseStageB)
{
// STAGE 2
Performance.Snapshot("Stage 2");
// Generate DistanceMatrix from Multiple Sequence Alignment
int iterateTime = 0;
while (true)
{
++iterateTime;
kimuraDistanceMatrixGenerator.GenerateDistanceMatrix(_alignedSequences);
// Hierarchical clustering
hierarcicalClusteringB = new HierarchicalClusteringParallel
(kimuraDistanceMatrixGenerator.DistanceMatrix, _hierarchicalClusteringMethodName);
// Generate Guide Tree
binaryGuideTreeB = new BinaryGuideTree(hierarcicalClusteringB);
BinaryGuideTree.CompareTwoTrees(binaryGuideTreeB, binaryGuideTree);
binaryGuideTree = binaryGuideTreeB;
// Progressive Alignment
IProgressiveAligner progressiveAlignerB = new ProgressiveAligner(profileAligner);
progressiveAlignerB.Align(sequences, binaryGuideTreeB);
currentScore = MsaUtils.MultipleAlignmentScoreFunction(progressiveAlignerB.AlignedSequences, SimilarityMatrix, GapOpenCost, GapExtensionCost);
if (currentScore > _alignmentScoreB)
{
_alignmentScoreB = currentScore;
_alignedSequencesB = progressiveAlignerB.AlignedSequences;
break;
}
else
{
break;
}
}
if (_alignmentScoreB > _alignmentScore)
{
_alignmentScore = _alignmentScoreB;
_alignedSequences = _alignedSequencesB;
}
}
else
{
binaryGuideTreeB = binaryGuideTree;
}
// STAGE 3
Performance.Snapshot("Stage 3");
// refinement
//int maxRefineMentTime = sequences.Count * 2 - 2;
int maxRefineMentTime = 1;
if (sequences.Count == 2)
{
maxRefineMentTime = 0;
}
int refinementTime = 0;
_alignedSequencesC = new List <ISequence>(sequences.Count);
for (int i = 0; i < sequences.Count; ++i)
{
_alignedSequencesC.Add(
new Sequence(Alphabets.GetAmbiguousAlphabet(_alphabet),
_alignedSequences[i].ToArray())
{
ID = _alignedSequences[i].ID,
Metadata = _alignedSequences[i].Metadata
});
}
List <int>[] leafNodeIndices = null;
List <int>[] allIndelPositions = null;
IProfileAlignment[] separatedProfileAlignments = null;
List <int>[] eStrings = null;
while (refinementTime < maxRefineMentTime)
{
++refinementTime;
Performance.Snapshot("Refinement iter " + refinementTime.ToString());
bool needRefinement = false;
for (int edgeIndex = 0; edgeIndex < binaryGuideTreeB.NumberOfEdges; ++edgeIndex)
{
leafNodeIndices = binaryGuideTreeB.SeparateSequencesByCuttingTree(edgeIndex);
allIndelPositions = new List <int> [2];
separatedProfileAlignments = ProfileAlignment.ProfileExtraction(_alignedSequencesC, leafNodeIndices[0], leafNodeIndices[1], out allIndelPositions);
eStrings = new List <int> [2];
if (separatedProfileAlignments[0].NumberOfSequences < separatedProfileAlignments[1].NumberOfSequences)
{
profileAligner.Align(separatedProfileAlignments[0], separatedProfileAlignments[1]);
eStrings[0] = profileAligner.GenerateEString(profileAligner.AlignedA);
eStrings[1] = profileAligner.GenerateEString(profileAligner.AlignedB);
}
else
{
profileAligner.Align(separatedProfileAlignments[1], separatedProfileAlignments[0]);
eStrings[0] = profileAligner.GenerateEString(profileAligner.AlignedB);
eStrings[1] = profileAligner.GenerateEString(profileAligner.AlignedA);
}
for (int set = 0; set < 2; ++set)
{
Parallel.ForEach(leafNodeIndices[set], PAMSAMMultipleSequenceAligner.parallelOption, i =>
{
//Sequence seq = new Sequence(_alphabet, "");
List <byte> seqBytes = new List <byte>();
int indexAllIndel = 0;
for (int j = 0; j < _alignedSequencesC[i].Count; ++j)
{
if (indexAllIndel < allIndelPositions[set].Count && j == allIndelPositions[set][indexAllIndel])
{
++indexAllIndel;
}
else
{
seqBytes.Add(_alignedSequencesC[i][j]);
}
}
_alignedSequencesC[i] = profileAligner.GenerateSequenceFromEString(eStrings[set], new Sequence(Alphabets.GetAmbiguousAlphabet(_alphabet), seqBytes.ToArray()));
_alignedSequencesC[i].ID = _alignedSequencesC[i].ID;
(_alignedSequencesC[i] as Sequence).Metadata = _alignedSequencesC[i].Metadata;
});
}
currentScore = MsaUtils.MultipleAlignmentScoreFunction(_alignedSequencesC, SimilarityMatrix, GapOpenCost, GapExtensionCost);
if (currentScore > _alignmentScoreC)
{
_alignmentScoreC = currentScore;
needRefinement = true;
// recreate the tree
kimuraDistanceMatrixGenerator.GenerateDistanceMatrix(_alignedSequencesC);
hierarcicalClusteringB = new HierarchicalClusteringParallel
(kimuraDistanceMatrixGenerator.DistanceMatrix, _hierarchicalClusteringMethodName);
binaryGuideTreeB = new BinaryGuideTree(hierarcicalClusteringB);
break;
}
}
if (!needRefinement)
{
refinementTime = maxRefineMentTime;
break;
}
}
if (_alignmentScoreC > _alignmentScore)
{
_alignmentScore = _alignmentScoreC;
_alignedSequences = _alignedSequencesC;
}
Performance.Snapshot("Stop Stage 3");
}
//just for the purpose of integrating PW and MSA with the same output
IList <Bio.Algorithms.Alignment.ISequenceAlignment> results = new List <Bio.Algorithms.Alignment.ISequenceAlignment>();
return(results);
}
/// <summary>
/// Performs Stage 1, 2, and 3 as described in class description.
/// </summary>
/// <param name="sequences">Input sequences</param>
/// <returns>Alignment results</returns>
private void DoAlignment(IList <ISequence> sequences)
{
Debug.Assert(this.alphabet != null);
Debug.Assert(sequences.Count > 0);
// Initializations
if (ConsensusResolver == null)
{
ConsensusResolver = new SimpleConsensusResolver(this.alphabet);
}
else
{
ConsensusResolver.SequenceAlphabet = this.alphabet;
}
// Get ProfileAligner ready
IProfileAligner profileAligner = null;
switch (ProfileAlignerName)
{
case (ProfileAlignerNames.NeedlemanWunschProfileAligner):
if (this.degreeOfParallelism == 1)
{
profileAligner = new NeedlemanWunschProfileAlignerSerial(
SimilarityMatrix, ProfileProfileFunctionName, GapOpenCost, GapExtensionCost, this.numberOfPartitions);
}
else
{
profileAligner = new NeedlemanWunschProfileAlignerParallel(
SimilarityMatrix, ProfileProfileFunctionName, GapOpenCost, GapExtensionCost, this.numberOfPartitions);
}
break;
case (ProfileAlignerNames.SmithWatermanProfileAligner):
if (this.degreeOfParallelism == 1)
{
profileAligner = new SmithWatermanProfileAlignerSerial(
SimilarityMatrix, ProfileProfileFunctionName, GapOpenCost, GapExtensionCost, this.numberOfPartitions);
}
else
{
profileAligner = new SmithWatermanProfileAlignerParallel(
SimilarityMatrix, ProfileProfileFunctionName, GapOpenCost, GapExtensionCost, this.numberOfPartitions);
}
break;
default:
throw new ArgumentException("Invalid profile aligner name");
}
this.AlignedSequences = new List <ISequence>(sequences.Count);
float currentScore = 0;
// STAGE 1
ReportLog("Stage 1");
// Generate DistanceMatrix
var kmerDistanceMatrixGenerator = new KmerDistanceMatrixGenerator(sequences, KmerLength, this.alphabet, DistanceFunctionName);
// Hierarchical clustering
IHierarchicalClustering hierarcicalClustering =
new HierarchicalClusteringParallel
(kmerDistanceMatrixGenerator.DistanceMatrix, HierarchicalClusteringMethodName);
// Generate Guide Tree
var binaryGuideTree = new BinaryGuideTree(hierarcicalClustering);
// Progressive Alignment
IProgressiveAligner progressiveAlignerA = new ProgressiveAligner(profileAligner);
progressiveAlignerA.Align(sequences, binaryGuideTree);
currentScore = MsaUtils.MultipleAlignmentScoreFunction(progressiveAlignerA.AlignedSequences, SimilarityMatrix, GapOpenCost, GapExtensionCost);
if (currentScore > this.AlignmentScoreA)
{
this.AlignmentScoreA = currentScore;
this.AlignedSequencesA = progressiveAlignerA.AlignedSequences;
}
if (this.AlignmentScoreA > this.AlignmentScore)
{
this.AlignmentScore = this.AlignmentScoreA;
this.AlignedSequences = this.AlignedSequencesA;
}
if (PAMSAMMultipleSequenceAligner.FasterVersion)
{
this.AlignedSequencesB = this.AlignedSequencesA;
this.AlignedSequencesC = this.AlignedSequencesA;
this.AlignmentScoreB = this.AlignmentScoreA;
this.AlignmentScoreC = this.AlignmentScoreA;
}
else
{
BinaryGuideTree binaryGuideTreeB = null;
IHierarchicalClustering hierarcicalClusteringB = null;
KimuraDistanceMatrixGenerator kimuraDistanceMatrixGenerator = new KimuraDistanceMatrixGenerator();
if (UseStageB)
{
// STAGE 2
ReportLog("Stage 2");
// Generate DistanceMatrix from Multiple Sequence Alignment
while (true)
{
kimuraDistanceMatrixGenerator.GenerateDistanceMatrix(this.AlignedSequences);
// Hierarchical clustering
hierarcicalClusteringB = new HierarchicalClusteringParallel
(kimuraDistanceMatrixGenerator.DistanceMatrix, HierarchicalClusteringMethodName);
// Generate Guide Tree
binaryGuideTreeB = new BinaryGuideTree(hierarcicalClusteringB);
BinaryGuideTree.CompareTwoTrees(binaryGuideTreeB, binaryGuideTree);
binaryGuideTree = binaryGuideTreeB;
// Progressive Alignment
IProgressiveAligner progressiveAlignerB = new ProgressiveAligner(profileAligner);
progressiveAlignerB.Align(sequences, binaryGuideTreeB);
currentScore = MsaUtils.MultipleAlignmentScoreFunction(progressiveAlignerB.AlignedSequences, SimilarityMatrix, GapOpenCost, GapExtensionCost);
if (currentScore > this.AlignmentScoreB)
{
this.AlignmentScoreB = currentScore;
this.AlignedSequencesB = progressiveAlignerB.AlignedSequences;
}
break;
}
if (this.AlignmentScoreB > this.AlignmentScore)
{
this.AlignmentScore = this.AlignmentScoreB;
this.AlignedSequences = this.AlignedSequencesB;
}
}
else
{
binaryGuideTreeB = binaryGuideTree;
}
// STAGE 3
ReportLog("Stage 3");
// refinement
int maxRefineMentTime = 1;
if (sequences.Count == 2)
{
maxRefineMentTime = 0;
}
int refinementTime = 0;
this.AlignedSequencesC = new List <ISequence>(this.AlignedSequences.Count);
foreach (ISequence t in this.AlignedSequences)
{
this.AlignedSequencesC.Add(new Sequence(Alphabets.GetAmbiguousAlphabet(this.alphabet), t.ToArray())
{
ID = t.ID,
// Do not shallow copy dictionary
//Metadata = t.Metadata
});
}
while (refinementTime < maxRefineMentTime)
{
++refinementTime;
ReportLog("Refinement iter " + refinementTime);
bool needRefinement = false;
for (int edgeIndex = 0; edgeIndex < binaryGuideTreeB.NumberOfEdges; ++edgeIndex)
{
List <int>[] leafNodeIndices = binaryGuideTreeB.SeparateSequencesByCuttingTree(edgeIndex);
List <int>[] allIndelPositions = new List <int> [2];
IProfileAlignment[] separatedProfileAlignments = ProfileAlignment.ProfileExtraction(this.AlignedSequencesC, leafNodeIndices[0], leafNodeIndices[1], out allIndelPositions);
List <int>[] eStrings = new List <int> [2];
if (separatedProfileAlignments[0].NumberOfSequences < separatedProfileAlignments[1].NumberOfSequences)
{
profileAligner.Align(separatedProfileAlignments[0], separatedProfileAlignments[1]);
eStrings[0] = profileAligner.GenerateEString(profileAligner.AlignedA);
eStrings[1] = profileAligner.GenerateEString(profileAligner.AlignedB);
}
else
{
profileAligner.Align(separatedProfileAlignments[1], separatedProfileAlignments[0]);
eStrings[0] = profileAligner.GenerateEString(profileAligner.AlignedB);
eStrings[1] = profileAligner.GenerateEString(profileAligner.AlignedA);
}
for (int set = 0; set < 2; ++set)
{
Parallel.ForEach(leafNodeIndices[set], ParallelOption, i =>
{
//Sequence seq = new Sequence(_alphabet, "");
List <byte> seqBytes = new List <byte>();
int indexAllIndel = 0;
for (int j = 0; j < this.AlignedSequencesC[i].Count; ++j)
{
if (indexAllIndel < allIndelPositions[set].Count && j == allIndelPositions[set][indexAllIndel])
{
++indexAllIndel;
}
else
{
seqBytes.Add(this.AlignedSequencesC[i][j]);
}
}
this.AlignedSequencesC[i] = profileAligner.GenerateSequenceFromEString(eStrings[set], new Sequence(Alphabets.GetAmbiguousAlphabet(this.alphabet), seqBytes.ToArray()));
this.AlignedSequencesC[i].ID = this.AlignedSequencesC[i].ID;
// Do not shallow copy dictionary
//(_alignedSequencesC[i] as Sequence).Metadata = _alignedSequencesC[i].Metadata;
});
}
currentScore = MsaUtils.MultipleAlignmentScoreFunction(this.AlignedSequencesC, SimilarityMatrix, GapOpenCost, GapExtensionCost);
if (currentScore > this.AlignmentScoreC)
{
this.AlignmentScoreC = currentScore;
needRefinement = true;
// recreate the tree
kimuraDistanceMatrixGenerator.GenerateDistanceMatrix(this.AlignedSequencesC);
hierarcicalClusteringB = new HierarchicalClusteringParallel
(kimuraDistanceMatrixGenerator.DistanceMatrix, HierarchicalClusteringMethodName);
binaryGuideTreeB = new BinaryGuideTree(hierarcicalClusteringB);
break;
}
}
if (!needRefinement)
{
refinementTime = maxRefineMentTime;
break;
}
}
if (this.AlignmentScoreC > this.AlignmentScore)
{
this.AlignmentScore = this.AlignmentScoreC;
this.AlignedSequences = this.AlignedSequencesC;
}
ReportLog("Stop Stage 3");
}
}
/// <summary>
/// Get the binary tree object using hierarchical clustering object
/// </summary>
/// <param name="hierarchicalClustering">hierarchical Clustering</param>
/// <returns>Binary guide tree</returns>
private static BinaryGuideTree GetBinaryTree(IHierarchicalClustering hierarchicalClustering)
{
// Generate Guide Tree
var binaryGuideTree =
new BinaryGuideTree(hierarchicalClustering);
return binaryGuideTree;
}
/// <summary>
/// Construct a tree by hierarchical clustering method.
///
/// The node list is already generated in the hierarchical clustering method
/// and the root will be the last node in the list
/// </summary>
/// <param name="hCluster">hierarcical clustering class object</param>
public BinaryGuideTree(IHierarchicalClustering hCluster)
{
if (hCluster == null)
{
throw new ArgumentException("null Hierarchical clustering class");
}
if (hCluster.Nodes.Count == 0)
{
throw new ArgumentException("empty node list in Hierarchical clustering class");
}
_nodes = hCluster.Nodes;
_edges = hCluster.Edges;
_root = hCluster.Nodes[hCluster.Nodes.Count - 1];
_numberOfNodes = hCluster.Nodes.Count;
_numberOfLeaves = (_numberOfNodes + 2) / 2;
}