static void NudgeWholeSequence(AlignedMacromolecule macromolecule, int nudgeAmount)
// Moves the entire sequences given by the sequenceIndices by the nudgeAmount.
{
//int[] seqAlignedPos = alignedMacromolecules[index].Item2;
int[] seqAlignedPos = macromolecule.AlignedPositions;
for (int i = 0; i < seqAlignedPos.Length; i++)
{
seqAlignedPos[i] += nudgeAmount;
}
}
//internal void RemoveAlignedMacromolecule(Tuple<Macromolecule, int[]> alignedMacromoleculeToRemove, bool doAdjustments = true)
internal void RemoveAlignedMacromolecule(AlignedMacromolecule alignedMacromoleculeToRemove, bool doAdjustments = true)
// Provides an interface to remove an aligned macromolecule from the list.
{
alignedMacromolecules.Remove(alignedMacromoleculeToRemove);
if (doAdjustments)
{
NormalizeAlignedPositions();
CalculateAlignmentLength();
NotifyPropertyChanged("AlignedMacromolecules");
RecalculateMaximumLength();
}
}
public AlignedMacromolecule Copy()
{
//Produces a copy of the alignment information only, and sets sequemceWeight to 0
AlignedMacromolecule copy = new AlignedMacromolecule(this, (int[])alignedPositions.Clone());
foreach (int newGap in newGaps)
{
copy.newGaps.Add(newGap);
}
sequenceWeight = 0;
return(copy);
}
//internal void AddAlignedMacromolecule(Tuple<Macromolecule, int[]> newAlignedMacromolecule, bool doAdjustments = true)
internal void AddAlignedMacromolecule(AlignedMacromolecule newAlignedMacromolecule, bool doAdjustments = true)
// Provides an interface to add an aligned macromolecule to the list.
// Adjust the name if it is not unique, adjust the alignmentLength, and add it to the list.
{
//Macromolecule newMacromolecule = newAlignedMacromolecule.Item1;
Macromolecule newMacromolecule = newAlignedMacromolecule;
// Rename the macromolecule if another with the same name is already loaded.
// Appends a "1" if already exists; then if this new name matches another, add "2", etc.
// Could lead to some weirdness if the loaded sequences were "seq1" "seq4" "seq4", which would
// become "seq1", "seq4", "seq4 1", but this is tolerable.
int nameInteger = 1;
for (int i = 0; i < alignedMacromolecules.Count; i++)
{
//Macromolecule testMacromolecule = alignedMacromolecules[i].Item1;
Macromolecule testMacromolecule = alignedMacromolecules[i];
if (newMacromolecule.Name == testMacromolecule.Name) // same name
{
newMacromolecule.Name += " " + nameInteger.ToString();
nameInteger++;
}
}
alignedMacromolecules.Add(newAlignedMacromolecule);
if (doAdjustments)
{ // Make into another sub so the Add routines can be synced?
NormalizeAlignedPositions();
CalculateAlignmentLength();
NotifyPropertyChanged("AlignedMacromolecules");
//isNucleicAcid = newAlignedMacromolecule.Item1.IsNucleicAcid;
isNucleicAcid = newAlignedMacromolecule.IsNucleicAcid;
NotifyPropertyChanged("IsNucleicAcid");
RecalculateMaximumLength();
}
}
internal static void Align(ref Alignment alignmentObject, ref BackgroundWorker myBackgroundWorker)
// Runs complete Clustal multiple sequence alignment on all loaded molecules
{
// Currently not set up to save files during alignment.
// Also not set to use the "stats" option
if (alignmentObject.IsNucleicAcid)
{
// Load alignment parameters for nucleic acids
}
else
{
// Load alignment parameters for protein
}
// Step 1: Do pairwise alignments and generate the distance matrix
myBackgroundWorker.ReportProgress(0, "Starting pairwise alignments...");
int numSequences = alignmentObject.NumberMacromolecules;
double[,] distanceMatrix = new double[numSequences, numSequences];
// This will select between fast and full pairwise alignment. Just implementing fast alignment to start.
PairwiseAlignment.IPairwiseAlignmentAlgorithm pairwiseAlignmentAlgorithm;
if (true)
{
// This sub basically calculates the score of the best alignment between each pair of sequences
pairwiseAlignmentAlgorithm = new PairwiseAlignment.FastPairwiseAlignment();
}
else
{
throw new NotImplementedException("Full Pairwise Alignment is not yet implemented");
// pairwiseAlignmentAlgorithm = new PairwiseAlignment.FullPairwiseAlignment();
}
pairwiseAlignmentAlgorithm.PairwiseAlign(ref alignmentObject, ref distanceMatrix);
// Step 2: Generate a phylogenetic tree of the sequences from the distance matrix
myBackgroundWorker.ReportProgress(0, "Generating phylogenetic tree...");
AlignedMacromolecule[] macromolecules = new AlignedMacromolecule[alignmentObject.NumberMacromolecules];
ReadOnlyCollection <AlignedMacromolecule> alignedMacromolecules = alignmentObject.AlignedMacromolecules;
for (int i = 0; i < alignmentObject.NumberMacromolecules; i++)
{
macromolecules[i] = alignedMacromolecules[i];
}
Tree.GuideTree <AlignedMacromolecule> tree = Tree.GuideTree <AlignedMacromolecule> .GetWeightsAndSteps(ref distanceMatrix, macromolecules);
// Transfer the weights from the tree to the macromolecules and fetch the similarities and steps
foreach (Tree.GuideTree <AlignedMacromolecule> .TreeLeaf leaf in tree.LeavesList)
{
AlignedMacromolecule macromolecule = (AlignedMacromolecule)leaf.Data;
macromolecule.SequenceWeight = leaf.weight;
}
ReadOnlyCollection <Tuple <ReadOnlyCollection <AlignedMacromolecule>, ReadOnlyCollection <AlignedMacromolecule>, double> > alignmentSteps = tree.Steps;
// Step 3: Multiple sequence alignment
myBackgroundWorker.ReportProgress(0, "Starting multiple sequence alignment...");
SubstitutionMatrix.SubstitutionMatrixSeries subMatrixType;
if (alignmentObject.IsNucleicAcid) // Replaced by more advanced logic later
{
subMatrixType = new SubstitutionMatrix.NucleotideIdentity();
}
else
{
subMatrixType = new SubstitutionMatrix.BLOSUM();
}
MultipleAlignment.MultipleAlignment.AlignSequences(ref alignmentObject, subMatrixType, ref tree.similarityMatrix, tree.LeavesList, alignmentSteps);
}
