/// <summary>
/// Refine layout in the delta alignments.
/// </summary>
public void RefineLayout()
{
TimeSpan timeSpan = new TimeSpan();
Stopwatch runAlgorithm = new Stopwatch();
runAlgorithm.Restart();
FileInfo inputFileinfo = new FileInfo(this.FilePath[1]);
long inputFileLength = inputFileinfo.Length;
FastASequencePositionParser queryParser;
using(var input = File.OpenRead(FilePath[1]))
{
queryParser = new FastASequencePositionParser(input, true);
queryParser.CacheSequencesForRandomAccess();
}
runAlgorithm.Stop();
if (this.Verbose)
{
Output.WriteLine(OutputLevel.Verbose);
Output.WriteLine(OutputLevel.Verbose, "Processed Query FastA file: {0}", Path.GetFullPath(this.FilePath[1]));
Output.WriteLine(OutputLevel.Verbose, " Read/Processing time : {0}", runAlgorithm.Elapsed);
Output.WriteLine(OutputLevel.Verbose, " File Size : {0}", inputFileLength);
}
inputFileinfo = new FileInfo(this.FilePath[0]);
inputFileLength = inputFileinfo.Length;
runAlgorithm.Restart();
using (var input = File.OpenRead(FilePath[0]))
using (DeltaAlignmentCollection deltaCollection = new DeltaAlignmentCollection(input, queryParser))
{
runAlgorithm.Stop();
if (this.Verbose)
{
Output.WriteLine(OutputLevel.Verbose);
Output.WriteLine(OutputLevel.Verbose, "Processed DeltaAlignment file: {0}", Path.GetFullPath(this.FilePath[0]));
Output.WriteLine(OutputLevel.Verbose, " Read/Processing time : {0}", runAlgorithm.Elapsed);
Output.WriteLine(OutputLevel.Verbose, " File Size : {0}", inputFileLength);
}
runAlgorithm.Restart();
IEnumerable<DeltaAlignment> result = LayoutRefiner.RefineLayout(deltaCollection);
DeltaAlignmentSorter sorter = new DeltaAlignmentSorter();
WriteDelta(result, sorter, UnsortedLayoutRefinmentOutputFilename);
runAlgorithm.Stop();
timeSpan = timeSpan.Add(runAlgorithm.Elapsed);
runAlgorithm.Restart();
WriteSortedDelta(sorter, UnsortedLayoutRefinmentOutputFilename, queryParser, this.OutputFile);
runAlgorithm.Stop();
}
if (this.Verbose)
{
Output.WriteLine(OutputLevel.Verbose);
Output.WriteLine(OutputLevel.Verbose, "Compute time: {0}", timeSpan);
Output.WriteLine(OutputLevel.Verbose, "Write time: {0}", runAlgorithm.Elapsed);
}
}
/// <summary>
/// Resolve ambiguity in the delta alignments.
/// </summary>
public void ResolveAmbiguity()
{
TimeSpan repeatResolutionSpan = new TimeSpan();
Stopwatch runRepeatResolution = new Stopwatch();
runRepeatResolution.Restart();
FileInfo inputFileinfo = new FileInfo(this.FilePath[1]);
long inputFileLength = inputFileinfo.Length;
runRepeatResolution.Stop();
if (this.Verbose)
{
Console.Error.WriteLine();
Console.Error.WriteLine(" Processed Query FastA file: {0}", Path.GetFullPath(this.FilePath[1]));
Console.Error.WriteLine(" Read/Processing time: {0}", runRepeatResolution.Elapsed);
Console.Error.WriteLine(" File Size : {0}", inputFileLength);
}
inputFileinfo = new FileInfo(this.FilePath[0]);
inputFileLength = inputFileinfo.Length;
runRepeatResolution.Restart();
DeltaAlignmentSorter sorter = null;
using (var alignmentStream = File.OpenRead(this.FilePath[0]))
using (var readStream = File.OpenRead(this.FilePath[1]))
using (DeltaAlignmentCollection deltaCollection = new DeltaAlignmentCollection(alignmentStream, readStream))
{
runRepeatResolution.Stop();
if (this.Verbose)
{
Console.Error.WriteLine();
Console.Error.WriteLine(" Processed DeltaAlignment file: {0}", Path.GetFullPath(this.FilePath[0]));
Console.Error.WriteLine(" Read/Processing time: {0}", runRepeatResolution.Elapsed);
Console.Error.WriteLine(" File Size : {0}", inputFileLength);
}
runRepeatResolution.Restart();
IEnumerable<DeltaAlignment> outputDeltas = RepeatResolver.ResolveAmbiguity(deltaCollection);
sorter = new DeltaAlignmentSorter();
WriteUnsortedDelta(outputDeltas, sorter);
}
runRepeatResolution.Stop();
repeatResolutionSpan = repeatResolutionSpan.Add(runRepeatResolution.Elapsed);
runRepeatResolution.Restart();
this.WriteDelta(sorter);
runRepeatResolution.Stop();
if (this.Verbose)
{
Console.Error.WriteLine(" Compute time: {0}", repeatResolutionSpan);
Console.Error.WriteLine(" Write() time: {0}", runRepeatResolution.Elapsed);
}
}
/// <summary>
/// Refine layout in the delta alignments.
/// </summary>
public void GenerateConsensus()
{
TimeSpan timeSpan = new TimeSpan();
Stopwatch runAlgorithm = new Stopwatch();
runAlgorithm.Restart();
FileInfo inputFileinfo = new FileInfo(this.FilePath[1]);
long inputFileLength = inputFileinfo.Length;
runAlgorithm.Stop();
if (this.Verbose)
{
Output.WriteLine(OutputLevel.Verbose);
Output.WriteLine(OutputLevel.Verbose, "Processed Query FastA file: {0}", Path.GetFullPath(this.FilePath[1]));
Output.WriteLine(OutputLevel.Verbose, " Read/Processing time : {0}", runAlgorithm.Elapsed);
Output.WriteLine(OutputLevel.Verbose, " File Size : {0}", inputFileLength);
}
inputFileinfo = new FileInfo(this.FilePath[0]);
inputFileLength = inputFileinfo.Length;
runAlgorithm.Restart();
using (var alignmentStream = File.OpenRead(this.FilePath[0]))
using (var readStream = File.OpenRead(this.FilePath[1]))
using (DeltaAlignmentCollection deltaCollection = new DeltaAlignmentCollection(alignmentStream, readStream))
{
runAlgorithm.Stop();
if (this.Verbose)
{
Output.WriteLine(OutputLevel.Verbose);
Output.WriteLine(OutputLevel.Verbose, "Processed DeltaAlignment file: {0}", Path.GetFullPath(this.FilePath[0]));
Output.WriteLine(OutputLevel.Verbose, " Read/Processing time : {0}", runAlgorithm.Elapsed);
Output.WriteLine(OutputLevel.Verbose, " File Size : {0}", inputFileLength);
}
runAlgorithm.Restart();
IEnumerable<ISequence> consensus = ConsensusGeneration.GenerateConsensus(deltaCollection);
runAlgorithm.Stop();
timeSpan = timeSpan.Add(runAlgorithm.Elapsed);
runAlgorithm.Restart();
this.WriteSequences(consensus);
runAlgorithm.Stop();
}
if (this.Verbose)
{
Output.WriteLine(OutputLevel.Verbose, "Compute time: {0}", timeSpan);
Output.WriteLine(OutputLevel.Verbose, "Write() time: {0}", runAlgorithm.Elapsed);
}
}
/// <summary>
/// Generates a consensus sequence for the genomic region covered by reads.
/// </summary>
/// <param name="deltaAlignmentCollection">Alignment between reference genome and reads.</param>
/// <returns>List of contigs.</returns>
private IEnumerable<ISequence> ConsensusGenerator(DeltaAlignmentCollection deltaAlignmentCollection)
{
return ConsensusGeneration.GenerateConsensus(deltaAlignmentCollection);
}
/// <summary>
/// Reads ambiguously placed due to genomic reads.
/// This step requires mate pair information to resolve the ambiguity about placements of repeated sequences.
/// </summary>
/// <param name="deltaAlignmentCollection">Alignment between reference genome and reads.</param>
/// <returns>List of DeltaAlignments after resolving repeating reads.</returns>
private static IEnumerable<DeltaAlignment> RepeatResolution(DeltaAlignmentCollection deltaAlignmentCollection)
{
return RepeatResolver.ResolveAmbiguity(deltaAlignmentCollection);
}
/// <summary>
/// Refines layout of alignment between reads and reference genome by taking care of indels and rearrangements.
/// </summary>
/// <param name="deltaAlignmentCollection">Ordered Repeat Resolved Deltas.</param>
private static IEnumerable<DeltaAlignment> LayoutRefinment(DeltaAlignmentCollection deltaAlignmentCollection)
{
return LayoutRefiner.RefineLayout(deltaAlignmentCollection);
}
/// <summary>
/// Assemble the input sequences into the largest possible contigs.
/// </summary>
/// <param name="referenceSequence">The sequence used as backbone for assembly.</param>
/// <param name="queryParser">The parser to load the sequences to assemble.</param>
/// <returns>IComparativeAssembly instance which contains list of assembled sequences.</returns>
public IEnumerable<ISequence> Assemble(IEnumerable<ISequence> referenceSequence, FastASequencePositionParser queryParser)
{
if (referenceSequence == null)
{
throw new ArgumentNullException("referenceSequence");
}
if (queryParser == null)
{
throw new ArgumentNullException("queryParser");
}
Stream readAlignmentOutputStream = null;
Stream unsortedRepeatResolutionOutputStream = null;
Stream repeatResolutionOutputStream = null;
Stream unsortedLayoutRefinmentOutputStream = null;
Stream layoutRefinmentOutputStream = null;
try
{
// Converting to list to avoid multiple parse of the reference file if its a yield return
var refSequences = referenceSequence.ToList();
// CacheSequencesForRandomAccess will ignore the call if called more than once.
queryParser.CacheSequencesForRandomAccess();
IEnumerable<ISequence> reads = queryParser.Parse();
// Comparative Assembly Steps
// 1) Read Alignment (Calling NUCmer for aligning reads to reference sequence)
this.StatusEventStart(Properties.Resource.ReadAlignmentStarted);
IEnumerable<DeltaAlignment> alignmentBetweenReferenceAndReads = this.ReadAlignment(refSequences,
reads.Where(a => a.Count >= this.LengthOfMum));
readAlignmentOutputStream = PlatformManager.Services.CreateTempStream();
WriteDelta(alignmentBetweenReferenceAndReads, readAlignmentOutputStream);
this.StatusEventEnd(Properties.Resource.ReadAlignmentEnded);
// 2) Repeat Resolution
this.StatusEventStart(Properties.Resource.RepeatResolutionStarted);
DeltaAlignmentSorter sorter;
unsortedRepeatResolutionOutputStream = PlatformManager.Services.CreateTempStream();
using (var deltaAlignmentFromReadAlignment = new DeltaAlignmentCollection(readAlignmentOutputStream, queryParser))
{
IEnumerable<DeltaAlignment> repeatResolvedDeltas = RepeatResolution(deltaAlignmentFromReadAlignment);
sorter = new DeltaAlignmentSorter(refSequences[0].Count);
WriteUnsortedDelta(repeatResolvedDeltas, sorter, unsortedRepeatResolutionOutputStream);
}
this.StatusEventEnd(Properties.Resource.RepeatResolutionEnded);
this.StatusEventStart(Properties.Resource.SortingResolvedDeltasStarted);
repeatResolutionOutputStream = PlatformManager.Services.CreateTempStream();
WriteSortedDelta(sorter, unsortedRepeatResolutionOutputStream, queryParser, repeatResolutionOutputStream);
this.StatusEventEnd(Properties.Resource.SortingResolvedDeltasEnded);
// 3) Layout Refinement
this.StatusEventStart(Properties.Resource.LayoutRefinementStarted);
layoutRefinmentOutputStream = PlatformManager.Services.CreateTempStream();
using (var unsortedDeltaCollectionForLayoutRefinment = new DeltaAlignmentCollection(repeatResolutionOutputStream, queryParser))
{
unsortedLayoutRefinmentOutputStream = PlatformManager.Services.CreateTempStream();
IEnumerable<DeltaAlignment> layoutRefinedDeltas = LayoutRefinment(unsortedDeltaCollectionForLayoutRefinment);
sorter = new DeltaAlignmentSorter(refSequences[0].Count);
WriteUnsortedDelta(layoutRefinedDeltas, sorter, unsortedLayoutRefinmentOutputStream);
WriteSortedDelta(sorter, unsortedLayoutRefinmentOutputStream, queryParser, layoutRefinmentOutputStream);
}
this.StatusEventEnd(Properties.Resource.LayoutRefinementEnded);
// 4) Consensus Generation
this.StatusEventStart(Properties.Resource.ConsensusGenerationStarted);
IList<ISequence> contigs;
using (var delta = new DeltaAlignmentCollection(layoutRefinmentOutputStream, queryParser))
{
contigs = this.ConsensusGenerator(delta).ToList();
}
this.StatusEventEnd(Properties.Resource.ConsensusGenerationEnded);
if (this.ScaffoldingEnabled)
{
// 5) Scaffold Generation
this.StatusEventStart(Properties.Resource.ScaffoldGenerationStarted);
IEnumerable<ISequence> scaffolds = this.ScaffoldsGenerator(contigs, reads);
this.StatusEventEnd(Properties.Resource.ScaffoldGenerationEnded);
return scaffolds;
}
else
{
return contigs;
}
}
finally
{
// Cleanup temp files.
if (readAlignmentOutputStream != null)
readAlignmentOutputStream.Dispose();
if (unsortedRepeatResolutionOutputStream != null)
unsortedRepeatResolutionOutputStream.Dispose();
if (repeatResolutionOutputStream != null)
repeatResolutionOutputStream.Dispose();
if (unsortedLayoutRefinmentOutputStream != null)
unsortedLayoutRefinmentOutputStream.Dispose();
if (layoutRefinmentOutputStream != null)
layoutRefinmentOutputStream.Dispose();
}
}
/// <summary>
/// Refines alignment layout by taking in consideration indels (insertions and deletions) and rearrangements between two genomes.
/// Requires mate-pair information to resolve ambiguity.
/// </summary>
/// <param name="orderedDeltas">Order deltas.</param>
public static IEnumerable<DeltaAlignment> RefineLayout(DeltaAlignmentCollection orderedDeltas)
{
if (orderedDeltas == null)
{
throw new ArgumentNullException("orderedDeltas");
}
if (orderedDeltas.Count == 0)
{
yield break;
}
// As we dont know what is the maximum posible insert and deltes,
// assuming 1,000,000 deltas are sufficient for operation.
int windowSize = 1000;
VirtualDeltaAlignmentCollection deltaCatche = new VirtualDeltaAlignmentCollection(orderedDeltas, windowSize);
List<DeltaAlignment> deltasOverlappingAtCurrentIndex = null;
List<DeltaAlignment> leftSideDeltas = null;
List<DeltaAlignment> rightSideDeltas = null;
List<DeltaAlignment> unloadedDeltas = null;
try
{
deltasOverlappingAtCurrentIndex = new List<DeltaAlignment>();
leftSideDeltas = new List<DeltaAlignment>();
rightSideDeltas = new List<DeltaAlignment>();
long currentProcessedOffset = 0;
DeltaAlignment alignment = deltaCatche[0];
deltasOverlappingAtCurrentIndex.Add(alignment);
DeltaAlignment deltaWithLargestEndIndex = alignment;
for (int currentIndex = 0; currentIndex < deltaCatche.Count - 1; currentIndex++)
{
DeltaAlignment nextDelta = deltaCatche[currentIndex + 1];
unloadedDeltas = null;
if (deltaCatche.TryUnload(currentIndex + 1, out unloadedDeltas))
{
for (int i = 0; i < unloadedDeltas.Count; i++)
{
yield return unloadedDeltas[i];
}
unloadedDeltas.Clear();
}
if (currentProcessedOffset != 0)
{
nextDelta.FirstSequenceStart += currentProcessedOffset;
nextDelta.FirstSequenceEnd += currentProcessedOffset;
}
// Check if next delta is just adjacent
if (nextDelta.FirstSequenceStart - 1 == deltaWithLargestEndIndex.FirstSequenceEnd)
{
// If next delta is adjacent there is a possible insertion in target (deletion in reference)
// Try to extend the deltas from both sides and make them meet
leftSideDeltas.Clear();
for (int index = 0; index < deltasOverlappingAtCurrentIndex.Count; index++)
{
DeltaAlignment delta = deltasOverlappingAtCurrentIndex[index];
if (delta.FirstSequenceEnd >= deltaWithLargestEndIndex.FirstSequenceEnd)
{
leftSideDeltas.Add(delta);
}
}
// Find all deltas starting at the adjacent right side
rightSideDeltas.Clear();
for (long index = currentIndex + 1; index < deltaCatche.Count; index++)
{
DeltaAlignment delta = deltaCatche[index];
unloadedDeltas = null;
if (deltaCatche.TryUnload(currentIndex + 1, out unloadedDeltas))
{
for (int i = 0; i < unloadedDeltas.Count; i++)
{
yield return unloadedDeltas[i];
}
unloadedDeltas.Clear();
}
if (delta.FirstSequenceStart != nextDelta.FirstSequenceStart)
{
break;
}
rightSideDeltas.Add(delta);
}
long offset = ExtendDeltas(leftSideDeltas, rightSideDeltas);
if (offset != 0)
{
nextDelta.FirstSequenceStart += offset;
nextDelta.FirstSequenceEnd += offset;
}
currentProcessedOffset += offset;
}
else
if (nextDelta.FirstSequenceStart <= deltaWithLargestEndIndex.FirstSequenceEnd)
{
// Check if next delta overlaps with current overlap group
deltasOverlappingAtCurrentIndex.Add(nextDelta);
// Check if nextDelta is reaching farther than the current farthest delta
if (nextDelta.FirstSequenceEnd > deltaWithLargestEndIndex.FirstSequenceEnd)
{
deltaWithLargestEndIndex = nextDelta;
}
if (deltasOverlappingAtCurrentIndex.Count > windowSize)
{
for (int i = deltasOverlappingAtCurrentIndex.Count - 1; i >= 0; i--)
{
if (deltasOverlappingAtCurrentIndex[i].FirstSequenceEnd < deltaWithLargestEndIndex.FirstSequenceEnd)
{
deltasOverlappingAtCurrentIndex.RemoveAt(i);
}
}
}
}
else
{
// No overlap with nextDelta, so there is a gap at the end of deltaWithLargestEndIndex
// Try fix insertion in reference by pulling together two ends of deltas on both sides of the gap
leftSideDeltas.Clear();
for (int index = 0; index < deltasOverlappingAtCurrentIndex.Count; index++)
{
DeltaAlignment delta = deltasOverlappingAtCurrentIndex[index];
if (delta.FirstSequenceEnd >= deltaWithLargestEndIndex.FirstSequenceEnd)
{
leftSideDeltas.Add(delta);
}
}
// Find all deltas starting at the right end of the gap
rightSideDeltas.Clear();
for (long index = currentIndex + 1; index < deltaCatche.Count; index++)
{
DeltaAlignment delta = deltaCatche[index];
unloadedDeltas = null;
if (deltaCatche.TryUnload(currentIndex + 1, out unloadedDeltas))
{
for (int i = 0; i < unloadedDeltas.Count; i++)
{
yield return unloadedDeltas[i];
}
unloadedDeltas.Clear();
}
if (delta.FirstSequenceStart != nextDelta.FirstSequenceStart)
{
break;
}
rightSideDeltas.Add(delta);
}
int score = 0;
for (int i = 0; i < leftSideDeltas.Count; i++)
{
var l = leftSideDeltas[i];
int j = 0;
for (; j < rightSideDeltas.Count; j++)
{
var r = rightSideDeltas[j];
// if (object.ReferenceEquals(l.QuerySequence, r.QuerySequence))
// As reference check is not posible, verifying ids here. as id are unique for a given read.
if (l.QuerySequence.ID == r.QuerySequence.ID)
{
score++;
break;
}
}
if (j == rightSideDeltas.Count)
{
score--;
}
}
// Score > 0 means most deltas share same query sequence at both ends, so close this gap
if (score > 0)
{
long gaplength = (nextDelta.FirstSequenceStart - deltaWithLargestEndIndex.FirstSequenceEnd) - 1;
currentProcessedOffset -= gaplength;
// Pull deltas on right side to close the gap
for (int i = 0; i < rightSideDeltas.Count; i++)
{
DeltaAlignment delta = rightSideDeltas[i];
delta.FirstSequenceStart -= gaplength;
delta.FirstSequenceEnd -= gaplength;
// deltaCatche.Update(delta.Id);
}
}
// Start a new group from the right side of the gap
deltaWithLargestEndIndex = nextDelta;
deltasOverlappingAtCurrentIndex.Clear();
deltasOverlappingAtCurrentIndex.Add(nextDelta);
}
}
unloadedDeltas = deltaCatche.GetCachedDeltas();
for (int i = 0; i < unloadedDeltas.Count; i++)
{
yield return unloadedDeltas[i];
}
unloadedDeltas.Clear();
}
finally
{
if (deltasOverlappingAtCurrentIndex != null)
{
deltasOverlappingAtCurrentIndex.Clear();
deltasOverlappingAtCurrentIndex = null;
}
if (leftSideDeltas != null)
{
leftSideDeltas.Clear();
leftSideDeltas = null;
}
if (rightSideDeltas != null)
{
rightSideDeltas.Clear();
rightSideDeltas = null;
}
if (deltaCatche != null)
{
deltaCatche = null;
}
}
}
/// <summary>
/// Initializes a new instance of the VirtualDeltaAlignmentCollection class.
/// </summary>
/// <param name="orderedDeltas"></param>
/// <param name="windowSize"></param>
public VirtualDeltaAlignmentCollection(DeltaAlignmentCollection orderedDeltas, int windowSize)
{
this.windowSize = windowSize;
this.Count = orderedDeltas.Count;
this.catchedDeltas = new List<DeltaAlignment>();
this.catchSize = windowSize * 1000;
this.sourceDeltas = orderedDeltas.DeltaAlignmentParser.Parse().GetEnumerator();
}
/// <summary>
/// Generates consensus sequences from alignment layout.
/// </summary>
/// <param name="alignmentBetweenReferenceAndReads">Input list of reads.</param>
/// <returns>List of contigs.</returns>
public static IEnumerable<ISequence> GenerateConsensus(DeltaAlignmentCollection alignmentBetweenReferenceAndReads)
{
if (alignmentBetweenReferenceAndReads == null)
{
throw new ArgumentNullException("alignmentBetweenReferenceAndReads");
}
SimpleConsensusResolver resolver = new SimpleConsensusResolver(AmbiguousDnaAlphabet.Instance, 49);
// this dictionary will not grow more than a few hundread in worst scenario,
// as this stores delta and its corresponding sequences
Dictionary<DeltaAlignment, ISequence> deltasInCurrentContig = new Dictionary<DeltaAlignment, ISequence>();
long currentAlignmentStartOffset = 0;
long currentIndex = 0;
List<byte> currentContig = new List<byte>();
List<DeltaAlignment> deltasToRemove = new List<DeltaAlignment>();
// no deltas
if (alignmentBetweenReferenceAndReads.Count == 0)
{
yield break;
}
long index = 0;
DeltaAlignment lastDelta = alignmentBetweenReferenceAndReads[index];
do
{
// Starting a new contig
if (deltasInCurrentContig.Count == 0)
{
currentAlignmentStartOffset = lastDelta.FirstSequenceStart;
currentIndex = 0;
currentContig.Clear();
}
// loop through all deltas at current index and find consensus
do
{
// Proceed creating consensus till we find another delta stats aligning
while (lastDelta != null && lastDelta.FirstSequenceStart == currentAlignmentStartOffset + currentIndex)
{
deltasInCurrentContig.Add(lastDelta, GetSequenceFromDelta(lastDelta));
// Get next delta
index++;
if (alignmentBetweenReferenceAndReads.Count > index)
{
lastDelta = alignmentBetweenReferenceAndReads[index];
continue; // see if new delta starts from the same offset
}
else
{
lastDelta = null;
}
}
byte[] symbolsAtCurrentIndex = new byte[deltasInCurrentContig.Count];
int symbolCounter = 0;
foreach (var delta in deltasInCurrentContig)
{
long inDeltaIndex = currentIndex - (delta.Key.FirstSequenceStart - currentAlignmentStartOffset);
symbolsAtCurrentIndex[symbolCounter++] = delta.Value[inDeltaIndex];
if (inDeltaIndex == delta.Value.Count - 1)
{
deltasToRemove.Add(delta.Key);
}
}
if (deltasToRemove.Count > 0)
{
for (int i = 0; i < deltasToRemove.Count; i++)
{
deltasInCurrentContig.Remove(deltasToRemove[i]);
}
deltasToRemove.Clear();
}
byte consensusSymbol = resolver.GetConsensus(symbolsAtCurrentIndex);
currentContig.Add(consensusSymbol);
currentIndex++;
// See if another delta is adjacent
if (deltasInCurrentContig.Count == 0 && lastDelta != null && lastDelta.FirstSequenceStart == currentAlignmentStartOffset + currentIndex)
{
deltasInCurrentContig.Add(lastDelta, GetSequenceFromDelta(lastDelta));
// check next delta
index++;
if (alignmentBetweenReferenceAndReads.Count > index)
{
lastDelta = alignmentBetweenReferenceAndReads[index];
continue; // read next delta to see if it starts from current reference sequence offset
}
else
{
lastDelta = null;
}
}
}
while (deltasInCurrentContig.Count > 0);
yield return new Sequence(AmbiguousDnaAlphabet.Instance, currentContig.ToArray(), false);
}
while (lastDelta != null);
}
/// <summary>
/// Validate Step 3 of Comparative assembly i.e. RefineLayout() method.
/// <param name="nodeName">Parent node in Xml</param>
/// <param name="isFilePath">Represents sequence is in a file or not.</param>
/// </summary>
public void RefineLayout(string nodeName, bool isFilePath)
{
List<DeltaAlignment> repeatDeltaValues = null;
IList<IEnumerable<DeltaAlignment>> deltaValues = GetDeltaAlignment(nodeName, isFilePath);
List<DeltaAlignment> result = new List<DeltaAlignment>();
string deltaFile = Path.GetTempFileName();
while (deltaValues.Count > 0)
{
IEnumerable<DeltaAlignment> curReadDeltas = deltaValues.ElementAt(0);
deltaValues.RemoveAt(0); // remove currently processing item from the list
result.Add(curReadDeltas.ElementAt(0));
}
List<DeltaAlignment> orderedRepeatResolvedDeltas = result.OrderBy(a => a.FirstSequenceStart).ToList();
ComparativeGenomeAssembler.WriteDelta(orderedRepeatResolvedDeltas, deltaFile);
string readFilePath = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.FilePathNode2);
using (var deltaColl = new DeltaAlignmentCollection(deltaFile, readFilePath))
{
//Validate RefineLayout().
LayoutRefiner.RefineLayout(deltaColl);
repeatDeltaValues = orderedRepeatResolvedDeltas;
}
//Compare the delta's with the expected .
Assert.IsTrue(CompareDeltaValues(nodeName, repeatDeltaValues));
}
public void RepeatResolution(string nodeName, bool isFilePath)
{
IList<IEnumerable<DeltaAlignment>> deltaValues = GetDeltaAlignment(nodeName, isFilePath);
string deltaFile = Path.GetTempFileName();
string readsFile = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.FilePathNode2);
IEnumerable<DeltaAlignment> repeatDeltaValues = null;
ComparativeGenomeAssembler.WriteDelta(this.CovertListToIEnumerable(deltaValues), deltaFile);
DeltaAlignmentCollection daCollectionObj = new DeltaAlignmentCollection(deltaFile, readsFile);
repeatDeltaValues = RepeatResolver.ResolveAmbiguity(daCollectionObj);
//Compare the delta's with the expected .
Assert.IsTrue(CompareDeltaValues(nodeName, repeatDeltaValues));
}
public void ValidateGenerateConsensus(string nodeName, bool isFilePath)
{
IList<IEnumerable<DeltaAlignment>> deltaValues = GetDeltaAlignment(nodeName, isFilePath);
List<DeltaAlignment> result = new List<DeltaAlignment>();
string deltaFile = Path.GetTempFileName();
string readsFile = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.FilePathNode2);
while (deltaValues.Count > 0)
{
IEnumerable<DeltaAlignment> curReadDeltas = deltaValues.ElementAt(0);
deltaValues.RemoveAt(0); // remove currently processing item from the list
result.Add(curReadDeltas.ElementAt(0));
}
ComparativeGenomeAssembler.WriteDelta(result.OrderBy(a => a.FirstSequenceStart), deltaFile);
var daCollectionObj = new DeltaAlignmentCollection(deltaFile, readsFile);
IEnumerable<ISequence> assembledOutput =
ConsensusGeneration.GenerateConsensus(daCollectionObj);
int index = 0;
//Validate consensus sequences.
foreach (ISequence seq in assembledOutput)
{
string[] expectedValue = utilityObj.xmlUtil.GetTextValues(nodeName,
Constants.ExpectedSequenceNode);
string actualOutput = new string(seq.Select(a => (char)a).ToArray());
Assert.AreEqual(expectedValue[index].ToUpperInvariant(), actualOutput.ToUpperInvariant());
index++;
}
}
/// <summary>
/// Reads ambiguously placed due to genomic reads.
/// This step requires mate pair information to resolve the ambiguity about placements of repeated sequences.
/// </summary>
/// <param name="alignmentBetweenReferenceAndReads">Alignment between reference genome and reads.</param>
/// <returns>List of DeltaAlignments after resolving repeating reads.</returns>
public static IEnumerable<DeltaAlignment> ResolveAmbiguity(DeltaAlignmentCollection alignmentBetweenReferenceAndReads)
{
if (alignmentBetweenReferenceAndReads == null)
{
throw new ArgumentNullException("alignmentBetweenReferenceAndReads");
}
// Process reads and add to result list.
// Loop till all reads are processed
foreach (var curReadDeltas in alignmentBetweenReferenceAndReads.GetDeltaAlignmentsByReads())
{
if (curReadDeltas == null)
continue;
int deltasInCurrentRead = curReadDeltas.Count;
// If curReadDeltas has only one delta, then there are no repeats so add it to result
// Or if any delta is a partial alignment, dont try to resolve, add all deltas to result
if (deltasInCurrentRead == 1 || curReadDeltas.Any(a => a.SecondSequenceEnd != a.QuerySequence.Count - 1))
{
//result.AddRange(curReadDeltas);
foreach (var delta in curReadDeltas)
{
yield return delta;
}
}
else if (deltasInCurrentRead == 0)
{
continue;
}
else
{
// Resolve repeats
string sequenceId = curReadDeltas[0].QuerySequence.ID;
string originalSequenceId;
bool forwardRead;
string pairedReadType;
string libraryName;
bool pairedRead =Helper.ValidatePairedSequenceId(sequenceId, out originalSequenceId, out forwardRead,out pairedReadType, out libraryName);
// If read is not having proper ID, ignore the read
if (!pairedRead)
{
//result.AddRange(curReadDeltas);
foreach (var delta in curReadDeltas)
{
yield return delta;
}
continue;
}
string pairedReadId = Helper.GetPairedReadId(originalSequenceId, Helper.GetMatePairedReadType(pairedReadType), libraryName);
// Find mate pair
List<DeltaAlignment> mateDeltas = alignmentBetweenReferenceAndReads.GetDeltaAlignmentFor(pairedReadId);
// If mate pair not found, ignore current read
if (mateDeltas.Count == 0)
{
//result.AddRange(curReadDeltas);
foreach (var delta in curReadDeltas)
{
yield return delta;
}
continue;
}
// Resolve using distance method
List<DeltaAlignment> resolvedDeltas = ResolveRepeatUsingMatePair(curReadDeltas, mateDeltas, libraryName);
if (resolvedDeltas != null)
{
//result.AddRange(resolvedDeltas);
foreach (var delta in resolvedDeltas)
{
yield return delta;
}
}
}
}
}