/// <summary>
/// Performs Stage 1, 2, and 3 as described in class description.
/// </summary>
/// <param name="inputSequences">Input sequences</param>
/// <returns>Alignment results</returns>
public IList <Alignment.ISequenceAlignment> Align(IEnumerable <ISequence> inputSequences)
{
// Reset all our data in case this same instance is used multiple times.
_alignedSequences = _alignedSequencesA = _alignedSequencesB = _alignedSequencesC = null;
_alignmentScore = _alignmentScoreA = _alignmentScoreB = _alignmentScoreC = float.MinValue;
// Get our list of sequences.
List <ISequence> sequences = inputSequences.ToList();
if (sequences.Count == 0)
{
throw new ArgumentException("Empty input sequences");
}
// Assign the gap open/extension cost if it hasn't been assigned.
if (GapOpenCost == 0)
{
GapOpenCost = -4;
}
if (GapExtensionCost == 0)
{
GapExtensionCost = -1;
}
Performance.Start();
// Assign the alphabet
SetAlphabet(sequences, SimilarityMatrix, true);
MsaUtils.SetProfileItemSets(_alphabet);
Performance.Snapshot("Start Aligning");
// Work...
DoAlignment(sequences);
// just for the purpose of integrating PW and MSA with the same output
var alignment = new Alignment.SequenceAlignment();
IAlignedSequence aSequence = new AlignedSequence();
foreach (var alignedSequence in AlignedSequences)
{
aSequence.Sequences.Add(alignedSequence);
}
foreach (var inputSequence in sequences)
{
alignment.Sequences.Add(inputSequence);
}
alignment.AlignedSequences.Add(aSequence);
return(new List <Alignment.ISequenceAlignment>()
{
alignment
});
}
/// <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>
/// Construct an aligner
/// </summary>
/// <param name="sequences">input sequences</param>
/// <param name="kmerLength">positive integer of kmer length</param>
/// <param name="distanceFunctionName">enum: distance function name</param>
/// <param name="hierarchicalClusteringMethodName">enum: cluster update method</param>
/// <param name="profileAlignerMethodName">enum: profile-profile aligner name</param>
/// <param name="profileFunctionName">enum: profile-profile distance function</param>
/// <param name="similarityMatrix">similarity matrix</param>
/// <param name="gapOpenPenalty">negative gapOpenPenalty</param>
/// <param name="gapExtendPenalty">negative gapExtendPenalty</param>
/// <param name="numberOfPartitions">the number of partitions in dynamic programming</param>
/// <param name="degreeOfParallelism">degree of parallelism option for parallel extension</param>
public PAMSAMMultipleSequenceAligner(
IList <ISequence> sequences,
int kmerLength,
DistanceFunctionTypes distanceFunctionName,
UpdateDistanceMethodsTypes hierarchicalClusteringMethodName,
ProfileAlignerNames profileAlignerMethodName,
ProfileScoreFunctionNames profileFunctionName,
SimilarityMatrix similarityMatrix,
int gapOpenPenalty,
int gapExtendPenalty,
int numberOfPartitions,
int degreeOfParallelism)
{
Performance.Start();
if (null == sequences)
{
throw new ArgumentNullException("sequences");
}
if (sequences.Count == 0)
{
throw new ArgumentException("Empty input sequences");
}
// Set parallel extension option
if (degreeOfParallelism <= 0)
{
throw new ArgumentException("Invalid parallel degree parameter");
}
PAMSAMMultipleSequenceAligner.parallelOption = new ParallelOptions {
MaxDegreeOfParallelism = degreeOfParallelism
};
if (numberOfPartitions <= 0)
{
throw new ArgumentException("Invalid number of partition parameter");
}
_numberOfPartitions = numberOfPartitions;
// Validate data type
_alphabet = sequences[0].Alphabet;
Parallel.For(1, sequences.Count, PAMSAMMultipleSequenceAligner.parallelOption, i =>
{
if (!Alphabets.CheckIsFromSameBase(sequences[i].Alphabet, _alphabet))
{
throw new ArgumentException("Inconsistent sequence alphabet");
}
});
List <String> similarityMatrixDNA = new List <String>();
similarityMatrixDNA.Add("AmbiguousDNA");
List <String> similarityMatrixRNA = new List <String>();
similarityMatrixRNA.Add("AmbiguousRNA");
List <String> similarityMatrixProtein = new List <String>();
similarityMatrixProtein.Add("BLOSUM45");
similarityMatrixProtein.Add("BLOSUM50");
similarityMatrixProtein.Add("BLOSUM62");
similarityMatrixProtein.Add("BLOSUM80");
similarityMatrixProtein.Add("BLOSUM90");
similarityMatrixProtein.Add("PAM250");
similarityMatrixProtein.Add("PAM30");
similarityMatrixProtein.Add("PAM70");
if (_alphabet is DnaAlphabet)
{
if (!similarityMatrixDNA.Contains(similarityMatrix.Name))
{
throw new ArgumentException("Inconsistent similarity matrix");
}
}
else if (_alphabet is ProteinAlphabet)
{
if (!similarityMatrixProtein.Contains(similarityMatrix.Name))
{
throw new ArgumentException("Inconsistent similarity matrix");
}
}
else if (_alphabet is RnaAlphabet)
{
if (!similarityMatrixRNA.Contains(similarityMatrix.Name))
{
throw new ArgumentException("Inconsistent similarity matrix");
}
}
else
{
throw new ArgumentException("Invalid alphabet");
}
// Initialize parameters
_kmerLength = kmerLength;
_distanceFunctionName = distanceFunctionName;
_hierarchicalClusteringMethodName = hierarchicalClusteringMethodName;
_profileAlignerName = profileAlignerMethodName;
_profileProfileFunctionName = profileFunctionName;
SimilarityMatrix = similarityMatrix;
GapOpenCost = gapOpenPenalty;
GapExtensionCost = gapExtendPenalty;
MsaUtils.SetProfileItemSets(_alphabet);
Performance.Snapshot("Start Aligning");
// Work...
Align(sequences);
}
/// <summary>
/// Construct an aligner and run the alignment.
/// </summary>
/// <param name="sequences">input sequences</param>
/// <param name="kmerLength">positive integer of kmer length</param>
/// <param name="distanceFunctionName">enum: distance function name</param>
/// <param name="hierarchicalClusteringMethodName">enum: cluster update method</param>
/// <param name="profileAlignerMethodName">enum: profile-profile aligner name</param>
/// <param name="profileFunctionName">enum: profile-profile distance function</param>
/// <param name="similarityMatrix">similarity matrix</param>
/// <param name="gapOpenPenalty">negative gapOpenPenalty</param>
/// <param name="gapExtendPenalty">negative gapExtendPenalty</param>
/// <param name="numberOfPartitions">the number of partitions in dynamic programming</param>
/// <param name="degreeOfParallelism">degree of parallelism option for parallel extension</param>
public PAMSAMMultipleSequenceAligner(
IList <ISequence> sequences,
int kmerLength,
DistanceFunctionTypes distanceFunctionName,
UpdateDistanceMethodsTypes hierarchicalClusteringMethodName,
ProfileAlignerNames profileAlignerMethodName,
ProfileScoreFunctionNames profileFunctionName,
SimilarityMatrix similarityMatrix,
int gapOpenPenalty,
int gapExtendPenalty,
int numberOfPartitions,
int degreeOfParallelism)
{
Performance.Start();
if (null == sequences)
{
throw new ArgumentNullException("sequences");
}
if (sequences.Count == 0)
{
throw new ArgumentException("Empty input sequences");
}
// Set parallel extension option
if (degreeOfParallelism <= 0)
{
throw new ArgumentException("Invalid parallel degree parameter");
}
//_degreeOfParallelism = degreeOfParallelism;
parallelOption = new ParallelOptions {
MaxDegreeOfParallelism = degreeOfParallelism
};
if (numberOfPartitions <= 0)
{
throw new ArgumentException("Invalid number of partition parameter");
}
_numberOfPartitions = numberOfPartitions;
// Assign the alphabet
SetAlphabet(sequences, similarityMatrix, false);
// Initialize parameters
KmerLength = kmerLength;
DistanceFunctionName = distanceFunctionName;
HierarchicalClusteringMethodName = hierarchicalClusteringMethodName;
ProfileAlignerName = profileAlignerMethodName;
ProfileProfileFunctionName = profileFunctionName;
SimilarityMatrix = similarityMatrix;
GapOpenCost = gapOpenPenalty;
GapExtensionCost = gapExtendPenalty;
MsaUtils.SetProfileItemSets(_alphabet);
Performance.Snapshot("Start Aligning");
// Work...
DoAlignment(sequences);
}