public void TestFastaWhenParsingOneOfMany()
{
// parse
string filepath = System.IO.Path.Combine("TestUtils","Fasta","5_sequences.fasta");
FastAParser parser = new FastAParser { Alphabet = Alphabets.Protein };
using (parser.Open(filepath))
{
int[] sequenceCountArray = { 27, 29, 30, 35, 32 };
int i = 0;
foreach (ISequence seq in parser.Parse())
{
Assert.IsNotNull(seq);
Assert.AreEqual(seq.Count, sequenceCountArray[i]);
i++;
}
}
}
public void ValidateReadContigMap()
{
// Read all the input sequences from xml config file
string filePath = utilityObj.xmlUtil.GetTextValue(Constants.SmallChromosomeReadsNode,
Constants.FilePathNode);
IEnumerable<ISequence> sequenceReads = null;
FastAParser parser = new FastAParser ();
parser.Open( filePath.Replace("\\", System.IO.Path.DirectorySeparatorChar.ToString()));
sequenceReads = parser.Parse().ToList();
parser.Close ();
ReadContigMap map = new ReadContigMap(sequenceReads);
Assert.IsNotNull(map);
for (int i = 0; i < 10; i++)
{
Assert.IsTrue(map.ContainsKey(sequenceReads.ElementAt(0).ID));
}
}
public void FastAParserValidateParseWithAlphabetAsProperty()
{
string filePath = utilityObj.xmlUtil.GetTextValue(Constants.SimpleFastaDnaNodeName, Constants.FilePathNode);
Assert.IsTrue(File.Exists(filePath));
ApplicationLog.WriteLine(string.Format("FastA Parser : File Exists in the Path '{0}'.", filePath));
var parserObj = new FastAParser();
using (parserObj.Open(filePath))
{
parserObj.Alphabet = Utility.GetAlphabet(utilityObj.xmlUtil.GetTextValue(Constants.SimpleFastaDnaNodeName,
Constants.AlphabetNameNode));
ValidateParserGeneralTestCases(parserObj);
}
}
/// <summary>
/// Validate Parallel Denovo Assembly Assembled sequences.
/// </summary>
/// <param name="nodeName">XML node used to validate different test scenarios</param>
internal void ValidatePadenaAssembledSeqs(string nodeName)
{
// Get values from XML node.
string filePath = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.FilePathNode);
string kmerLength = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.KmerLengthNode);
string daglingThreshold = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.DanglingLinkThresholdNode);
string redundantThreshold = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.RedundantThreshold);
string libraray = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.LibraryName);
string stdDeviation = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.StdDeviation);
string mean = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.Mean);
string assembledSequences = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.SequencePathNode);
string assembledSeqCount = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.AssembledSeqCountNode);
string[] updatedAssembledSeqs = assembledSequences.Split(',');
// Get the input reads and build kmers
IEnumerable<ISequence> sequenceReads = null;
FastAParser parser = new FastAParser();
parser.Open(filePath);
sequenceReads = parser.Parse().ToList();
parser.Close ();
// Create a ParallelDeNovoAssembler instance.
ParallelDeNovoAssembler denovoObj = null;
try
{
denovoObj = new ParallelDeNovoAssembler();
denovoObj.KmerLength = Int32.Parse(kmerLength, (IFormatProvider)null);
denovoObj.DanglingLinksThreshold = Int32.Parse(daglingThreshold, (IFormatProvider)null);
denovoObj.RedundantPathLengthThreshold = Int32.Parse(redundantThreshold, (IFormatProvider)null);
CloneLibrary.Instance.AddLibrary(libraray, float.Parse(mean, (IFormatProvider)null),
float.Parse(stdDeviation, (IFormatProvider)null));
byte[] symbols = sequenceReads.ElementAt(0).Alphabet.GetSymbolValueMap();
IDeNovoAssembly assembly =
denovoObj.Assemble(sequenceReads.Select(a => new Sequence(Alphabets.DNA, a.Select(b => symbols[b]).ToArray()) { ID = a.ID }), true);
IList<ISequence> assembledSequenceList = assembly.AssembledSequences.ToList();
// Validate assembled sequences.
Assert.AreEqual(assembledSeqCount, assembledSequenceList.Count.ToString((IFormatProvider)null));
for (int i = 0; i < assembledSequenceList.Count; i++)
{
Assert.IsTrue(assembledSequences.Contains(
new string(assembledSequenceList[i].Select(a => (char)a).ToArray()))
|| updatedAssembledSeqs.Contains(
new string(assembledSequenceList[i].GetReverseComplementedSequence().Select(a => (char)a).ToArray())));
}
}
finally
{
if (denovoObj != null)
denovoObj.Dispose();
}
ApplicationLog.WriteLine("Padena P1 : Assemble() validation for Padena step6:step7 completed successfully");
}
/// <summary>
/// Validate scaffold paths for a given input reads.
/// </summary>
/// <param name="nodeName">xml node name used for different testcases</param>
internal void ValidateScaffoldPath(string nodeName)
{
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.FilePathNode);
string kmerLength = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.KmerLengthNode);
string daglingThreshold = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.DanglingLinkThresholdNode);
string redundantThreshold = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.RedundantThreshold);
string[] expectedScaffoldNodes = utilityObj.xmlUtil.GetTextValues(nodeName,Constants.ScaffoldNodes);
string libraray = utilityObj.xmlUtil.GetTextValue(nodeName,Constants.LibraryName);
string stdDeviation = utilityObj.xmlUtil.GetTextValue(nodeName,Constants.StdDeviation);
string mean = utilityObj.xmlUtil.GetTextValue(nodeName,Constants.Mean);
string expectedDepth = utilityObj.xmlUtil.GetTextValue(nodeName,Constants.DepthNode);
// Get the input reads and build kmers
FastAParser parser = new FastAParser();
parser.Open(filePath);
IEnumerable<ISequence> sequenceReads = parser.Parse().ToList();
parser.Close ();
// Build kmers from step1,graph in step2
// Remove the dangling links from graph in step3
// Remove bubbles form the graph in step4
// Pass the graph and build contigs
// Validate contig reads
this.KmerLength = Int32.Parse(kmerLength, null);
this.DanglingLinksThreshold = Int32.Parse(daglingThreshold, null);
this.DanglingLinksPurger = new DanglingLinksPurger(Int32.Parse(daglingThreshold, null));
this.RedundantPathsPurger = new RedundantPathsPurger(Int32.Parse(redundantThreshold, null));
this.RedundantPathLengthThreshold = Int32.Parse(redundantThreshold, null);
this.SequenceReads.Clear();
this.SetSequenceReads(sequenceReads.ToList());
this.CreateGraph();
ContigGraph graph = new ContigGraph();
this.UnDangleGraph();
// Build contig.
this.ContigBuilder = new SimplePathContigBuilder();
this.RemoveRedundancy();
IEnumerable<ISequence> contigs = this.BuildContigs();
IList<ISequence> sortedContigs = SortContigsData(contigs.ToList());
ReadContigMapper mapper = new ReadContigMapper();
ReadContigMap maps = mapper.Map(sortedContigs, sequenceReads, this.KmerLength);
// Find map paired reads.
CloneLibrary.Instance.AddLibrary(libraray, float.Parse(mean, null), float.Parse(stdDeviation, null));
MatePairMapper mapPairedReads = new MatePairMapper();
ContigMatePairs pairedReads = mapPairedReads.MapContigToMatePairs(sequenceReads, maps);
// Filter contigs based on the orientation.
OrientationBasedMatePairFilter filter = new OrientationBasedMatePairFilter();
ContigMatePairs contigpairedReads = filter.FilterPairedReads(pairedReads, 0);
DistanceCalculator dist = new DistanceCalculator(contigpairedReads);
dist.CalculateDistance();
graph.BuildContigGraph(contigs.ToList(), this.KmerLength);
// Validate ScaffoldPath using BFS.
TracePath trace = new TracePath();
IList<ScaffoldPath> paths = trace.FindPaths(graph, contigpairedReads, Int32.Parse(kmerLength, null),
Int32.Parse(expectedDepth, null));
ScaffoldPath scaffold = paths.First();
foreach (KeyValuePair<Node, Edge> kvp in scaffold)
{
ISequence seq = graph.GetNodeSequence(kvp.Key);
string sequence = seq.ConvertToString();
string reversedSequence = seq.GetReverseComplementedSequence().ConvertToString();
Assert.IsTrue(expectedScaffoldNodes.Contains(sequence)
|| expectedScaffoldNodes.Contains(reversedSequence),
"Failed to find " + sequence + ", or " + reversedSequence);
}
ApplicationLog.WriteLine("PADENA P1 : FindPaths() validation for Padena step6:step6 completed successfully");
}
/// <summary>
/// Validate Filter contig nodes.
/// </summary>
/// <param name="nodeName">xml node name used for a differnt testcase.</param>
/// <param name="isFirstContig">Is First Contig?</param>
internal void ValidateFilterPaired(string nodeName, bool isFirstContig)
{
string filePath = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.FilePathNode);
string kmerLength = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.KmerLengthNode);
string daglingThreshold = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.DanglingLinkThresholdNode);
string redundantThreshold = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.RedundantThreshold);
string expectedContigPairedReadsCount = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.ContigPairedReadsCount);
string forwardReadStartPos = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.ForwardReadStartPos);
string reverseReadStartPos = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.ReverseReadStartPos);
string reverseComplementStartPos = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.RerverseReadReverseCompPos);
string[] expectedForwardReadStartPos = forwardReadStartPos.Split(',');
string[] expectedReverseReadStartPos = reverseReadStartPos.Split(',');
string[] expectedReverseComplementStartPos = reverseComplementStartPos.Split(',');
// Get the input reads and build kmers
IEnumerable<ISequence> sequenceReads = null;
FastAParser parser = new FastAParser();
parser.Open(filePath);
sequenceReads = parser.Parse().ToList();
parser.Close ();
// Build kmers from step1,graph in step2
// Remove the dangling links from graph in step3
// Remove bubbles form the graph in step4
// Pass the graph and build contigs
// Validate contig reads
this.KmerLength = Int32.Parse(kmerLength, (IFormatProvider)null);
this.DanglingLinksThreshold = Int32.Parse(daglingThreshold, (IFormatProvider)null);
this.DanglingLinksPurger = new DanglingLinksPurger(Int32.Parse(daglingThreshold, (IFormatProvider)null));
this.RedundantPathsPurger =
new RedundantPathsPurger(Int32.Parse(redundantThreshold, (IFormatProvider)null));
this.RedundantPathLengthThreshold = Int32.Parse(redundantThreshold, (IFormatProvider)null);
this.SequenceReads.Clear();
this.SetSequenceReads(sequenceReads.ToList());
this.CreateGraph();
this.UnDangleGraph();
// Build contig.
this.ContigBuilder = new SimplePathContigBuilder();
this.RemoveRedundancy();
IEnumerable<ISequence> contigs = this.BuildContigs();
IList<ISequence> sortedContigs = SortContigsData(contigs.ToList());
ReadContigMapper mapper = new ReadContigMapper();
ReadContigMap maps = mapper.Map(
sortedContigs, sequenceReads, this.KmerLength);
// Find map paired reads.
MatePairMapper mapPairedReads = new MatePairMapper();
ContigMatePairs pairedReads = mapPairedReads.MapContigToMatePairs(sequenceReads, maps);
// Filter contigs based on the orientation.
OrientationBasedMatePairFilter filter = new OrientationBasedMatePairFilter();
ContigMatePairs contigpairedReads = filter.FilterPairedReads(pairedReads, 0);
Assert.AreEqual(expectedContigPairedReadsCount,
contigpairedReads.Values.Count.ToString((IFormatProvider)null));
Dictionary<ISequence, IList<ValidMatePair>> map = null;
IList<ValidMatePair> valid = null;
ISequence firstSeq = sortedContigs[0];
ISequence secondSeq = sortedContigs[1];
// Validate Contig paired reads after filtering contig sequences.
if (isFirstContig)
{
map = contigpairedReads[firstSeq];
valid = SortPairedReads(map[secondSeq], sequenceReads);
}
else
{
map = contigpairedReads[secondSeq];
valid = SortPairedReads(map[firstSeq], sequenceReads);
}
for (int index = 0; index < valid.Count; index++)
{
Assert.IsTrue((expectedForwardReadStartPos[index] ==
valid[index].ForwardReadStartPosition[0].ToString((IFormatProvider)null)
|| (expectedForwardReadStartPos[index] ==
valid[index].ForwardReadStartPosition[1].ToString((IFormatProvider)null))));
if (valid[index].ReverseReadReverseComplementStartPosition.Count > 1)
{
Assert.IsTrue((expectedReverseReadStartPos[index] ==
valid[index].ReverseReadReverseComplementStartPosition[0].ToString((IFormatProvider)null)
|| (expectedReverseReadStartPos[index] ==
valid[index].ReverseReadReverseComplementStartPosition[1].ToString((IFormatProvider)null))));
}
if (valid[index].ReverseReadStartPosition.Count > 1)
{
Assert.IsTrue((expectedReverseComplementStartPos[index] ==
valid[index].ReverseReadStartPosition[0].ToString((IFormatProvider)null)
|| (expectedReverseComplementStartPos[index] ==
valid[index].ReverseReadStartPosition[1].ToString((IFormatProvider)null))));
}
}
ApplicationLog.WriteLine("PADENA P1 : FilterPairedReads() validation for Padena step6:step4 completed successfully");
}
/// <summary>
/// Validate Add library information in existing libraries.
/// </summary>
/// <param name="nodeName">xml node name used for different testcases</param>
/// <param name="IsLibraryInfo">Is library info?</param>
internal void AddLibraryInformation(string nodeName, bool IsLibraryInfo)
{
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.FilePathNode);
string expectedPairedReadsCount = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.PairedReadsCountNode);
string[] backwardReadsNode = utilityObj.xmlUtil.GetTextValues(nodeName,
Constants.BackwardReadsNode);
string[] forwardReadsNode = utilityObj.xmlUtil.GetTextValues(nodeName,
Constants.ForwardReadsNode);
string expectedLibraray = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.LibraryName);
string expectedStdDeviation = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.StdDeviation);
string mean = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.Mean);
IList<ISequence> sequenceReads = new List<ISequence>();
IList<MatePair> pairedreads = new List<MatePair>();
// Get the input reads
IEnumerable<ISequence> sequences = null;
FastAParser parser = new FastAParser();
parser.Open(filePath);
sequences = parser.Parse().ToList();
parser.Close ();
foreach (ISequence seq in sequences)
{
sequenceReads.Add(seq);
}
// Add a new library infomration.
if (IsLibraryInfo)
{
CloneLibraryInformation libraryInfo =
new CloneLibraryInformation();
libraryInfo.LibraryName = expectedLibraray;
libraryInfo.MeanLengthOfInsert = float.Parse(mean, (IFormatProvider)null);
libraryInfo.StandardDeviationOfInsert = float.Parse(expectedStdDeviation, (IFormatProvider)null);
CloneLibrary.Instance.AddLibrary(libraryInfo);
}
else
{
CloneLibrary.Instance.AddLibrary(expectedLibraray,
float.Parse(mean, (IFormatProvider)null), float.Parse(expectedStdDeviation, (IFormatProvider)null));
}
// Convert reads to map paired reads.
MatePairMapper pair = new MatePairMapper();
pairedreads = pair.Map(sequenceReads);
// Validate Map paired reads.
Assert.AreEqual(expectedPairedReadsCount, pairedreads.Count.ToString((IFormatProvider)null));
for (int index = 0; index < pairedreads.Count; index++)
{
Assert.IsTrue(forwardReadsNode.Contains(new string(pairedreads[index].GetForwardRead(sequenceReads).Select(a => (char)a).ToArray())));
Assert.IsTrue(backwardReadsNode.Contains(new string(pairedreads[index].GetReverseRead(sequenceReads).Select(a => (char)a).ToArray())));
Assert.AreEqual(expectedStdDeviation,
pairedreads[index].StandardDeviationOfLibrary.ToString((IFormatProvider)null));
Assert.AreEqual(expectedLibraray, pairedreads[index].Library.ToString((IFormatProvider)null));
Assert.AreEqual(mean, pairedreads[index].MeanLengthOfLibrary.ToString((IFormatProvider)null));
}
ApplicationLog.WriteLine(@"Padena P1 : Map paired reads has been verified successfully");
}
/// <summary>
/// Validate the SimpleContigBuilder Build() method using step 4 graph
/// </summary>
/// <param name="nodeName">xml node name used for different testcases</param>
/// <param name="isChromosomeRC">Is Chromosome RC?</param>
internal void ValidateSimpleContigBuilderBuild(string nodeName, bool isChromosomeRC)
{
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.FilePathNode);
string kmerLength = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.KmerLengthNode);
string expectedContigsString = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.ContigsNode);
string[] expectedContigs = expectedContigsString.Split(',');
string expectedContigsCount = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.ContigsCount);
// Get the input reads and build kmers
IEnumerable<ISequence> sequenceReads = null;
FastAParser parser = new FastAParser();
parser.Open(filePath);
sequenceReads = parser.Parse().ToList();
parser.Close ();
// Build kmers from step1,graph in step2
// Remove the dangling links from graph in step3
// Remove bubbles from graph in step4
this.KmerLength = int.Parse(kmerLength, (IFormatProvider)null);
this.SequenceReads.Clear();
this.SetSequenceReads(sequenceReads.ToList());
this.CreateGraph();
DeBruijnGraph graph = this.Graph;
this.UnDangleGraph();
this.RemoveRedundancy();
// Validate the SimpleContigBuilder.Build() by passing graph
SimplePathContigBuilder builder = new SimplePathContigBuilder();
IList<ISequence> contigs = builder.Build(graph).ToList();
if (isChromosomeRC)
{
Assert.AreEqual(expectedContigsCount,
contigs.Count.ToString((IFormatProvider)null));
}
else
{
// Validate the contigs
for (int index = 0; index < contigs.Count; index++)
{
Assert.IsTrue(expectedContigs.Contains(new string(contigs[index].Select(a => (char)a).ToArray())));
}
}
ApplicationLog.WriteLine(@"Padena P1 :SimpleContigBuilder.BuildContigs() validation for Padena step5 completed successfully");
}
/// <summary>
/// Validate the ParallelDeNovothis unDangleGraph() method which removes the dangling link
/// </summary>
/// <param name="nodeName">xml node name used for different testcases</param>
/// <param name="defaultThreshold">Default Threshold</param>
/// <param name="smallSizeChromosome">Small size chromosome</param>
internal void ValidatePadenaUnDangleGraph(string nodeName, bool defaultThreshold, bool smallSizeChromosome)
{
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.FilePathNode);
string kmerLength = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.KmerLengthNode);
string expectedNodesCount = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.NodesCountAfterDanglingGraphNode);
string danglingThreshold = null;
if (!defaultThreshold)
danglingThreshold = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.DanglingLinkThresholdNode);
// Get the input reads and build kmers
IEnumerable<ISequence> sequenceReads = null;
FastAParser parser = new FastAParser();
parser.Open(filePath);
sequenceReads = parser.Parse().ToList();
parser.Close ();
// Build kmers from step1,graph in step2
this.KmerLength = int.Parse(kmerLength, null);
if (!defaultThreshold)
{
this.DanglingLinksThreshold = int.Parse(danglingThreshold, null);
}
else
{
this.DanglingLinksThreshold = int.Parse(kmerLength, null) + 1;
}
this.SequenceReads.Clear();
this.SetSequenceReads(sequenceReads.ToList());
this.CreateGraph();
DeBruijnGraph graph = this.Graph;
ApplicationLog.WriteLine("Padena P1 : Step1,2 Completed Successfully");
this.DanglingLinksPurger = new DanglingLinksPurger(this.DanglingLinksThreshold);
this.UnDangleGraph();
ApplicationLog.WriteLine("Padena P1 : Step3 Completed Successfully");
if (smallSizeChromosome)
{
Assert.AreEqual(expectedNodesCount, graph.GetNodes().Count().ToString((IFormatProvider)null));
}
else
{
ValidateGraph(graph, nodeName);
}
ApplicationLog.WriteLine(@"Padena P1 :ParallelDeNovothis.UndangleGraph() validation for Padena step3 completed successfully");
}
/// <summary>
/// Validate ParallelDeNovothis.RemoveRedundancy() which removes bubbles formed in the graph
/// and validate the graph
/// </summary>
/// <param name="nodeName">xml node name used for different testcases</param>
/// <param name="defaultThreshold">Is Default Threshold?</param>
/// <param name="isMicroorganism">Is micro organsm?</param>
internal void ValidatePadenaRemoveRedundancy(string nodeName, bool defaultThreshold, bool isMicroorganism)
{
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.FilePathNode);
string kmerLength = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.KmerLengthNode);
string expectedNodesCount = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.ExpectedNodesCountRemoveRedundancy);
string danglingThreshold = null;
string pathlengthThreshold = null;
if (!defaultThreshold)
{
danglingThreshold = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.DanglingLinkThresholdNode);
pathlengthThreshold = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.PathLengthThresholdNode);
}
// Get the input reads and build kmers
IEnumerable<ISequence> sequenceReads = null;
FastAParser parser = new FastAParser();
parser.Open(filePath);
sequenceReads = parser.Parse().ToList();
parser.Close ();
// Build kmers from step1,graph in step2
// Remove the dangling links from graph in step3
// Remove bubbles from graph in step4
// Validate the graph
if (!defaultThreshold)
{
this.DanglingLinksThreshold = int.Parse(danglingThreshold, (IFormatProvider)null);
this.DanglingLinksPurger =
new DanglingLinksPurger(this.DanglingLinksThreshold);
this.RedundantPathLengthThreshold = int.Parse(pathlengthThreshold, (IFormatProvider)null);
this.RedundantPathsPurger =
new RedundantPathsPurger(this.RedundantPathLengthThreshold);
}
else
{
this.DanglingLinksPurger =
new DanglingLinksPurger(int.Parse(kmerLength, (IFormatProvider)null));
this.RedundantPathsPurger =
new RedundantPathsPurger(int.Parse(kmerLength, (IFormatProvider)null) + 1);
}
this.KmerLength = int.Parse(kmerLength, (IFormatProvider)null);
this.SequenceReads.Clear();
this.SetSequenceReads(sequenceReads.ToList());
this.CreateGraph();
DeBruijnGraph graph = this.Graph;
ApplicationLog.WriteLine("Padena P1 : Step1,2 Completed Successfully");
this.UnDangleGraph();
ApplicationLog.WriteLine("Padena P1 : Step3 Completed Successfully");
this.RemoveRedundancy();
ApplicationLog.WriteLine("Padena P1 : Step4 Completed Successfully");
if (isMicroorganism)
{
Assert.AreEqual(expectedNodesCount, graph.GetNodes().Count().ToString((IFormatProvider)null));
}
else
{
ValidateGraph(graph, nodeName);
}
ApplicationLog.WriteLine(@"Padena P1 :ParallelDeNovothis.RemoveRedundancy() validation for Padena step4 completed successfully");
}
/// <summary>
/// Validate graph generated using ParallelDeNovothis.CreateGraph() with kmers
/// </summary>
/// <param name="nodeName">xml node name used for different testcases</param>
/// <param name="isLargeSizeReads">Is large size reads?</param>
internal void ValidatePadenaBuildGraph(string nodeName, bool isLargeSizeReads)
{
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.FilePathNode);
string kmerLength = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.KmerLengthNode);
string expectedGraphsNodeCount = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.GraphNodesCountNode);
// Get the input reads and build kmers
FastAParser parser = new FastAParser();
parser.Open(filePath);
IEnumerable<ISequence> sequenceReads = parser.Parse().ToList();
parser.Close ();
this.KmerLength = int.Parse(kmerLength, null);
this.SequenceReads.Clear();
this.SetSequenceReads(sequenceReads.ToList());
this.CreateGraph();
DeBruijnGraph graph = this.Graph;
ApplicationLog.WriteLine("Padena P1 : Step1,2 Completed Successfully");
if (isLargeSizeReads)
Assert.AreEqual(Int32.Parse(expectedGraphsNodeCount, null), graph.GetNodes().Count());
else
ValidateGraph(graph, nodeName);
ApplicationLog.WriteLine(@"Padena P1 : ParallelDeNovothis CreateGraph() validation for Padena step2 completed successfully");
}
/// <summary>
/// Validate ParallelDeNovothis step1 Build kmers
/// </summary>
/// <param name="nodeName">xml node for test data</param>
/// <param name="isSmallSize">Is file small size?</param>
internal void ValidatePadenaBuildKmers(string nodeName, bool isSmallSize)
{
// Read all the input sequences from xml config file
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.FilePathNode);
string kmerLength = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.KmerLengthNode);
string expectedKmersCount = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.ExpectedKmersCount);
// Set kmerLength
this.KmerLength = int.Parse(kmerLength, (IFormatProvider)null);
IEnumerable<ISequence> sequenceReads = null;
FastAParser parser = new FastAParser();
parser.Open(filePath);
sequenceReads = parser.Parse().ToList();
parser.Close ();
// Set all the input reads and execute build kmers
this.SequenceReads.Clear();
this.SetSequenceReads(sequenceReads.ToList());
IEnumerable<KmersOfSequence> lstKmers =
(new SequenceToKmerBuilder()).Build(this.SequenceReads, this.KmerLength);
if (isSmallSize)
{
Assert.AreEqual(expectedKmersCount, lstKmers.Count().ToString((IFormatProvider)null));
}
else
{
ValidateKmersList(new List<KmersOfSequence>(lstKmers), sequenceReads.ToList(), nodeName);
}
ApplicationLog.WriteLine(@"Padena P1 : Validation of Build with all input reads using ParallelDeNovothis sequence completed successfully");
}
/// <summary>
/// Validate SequenceRangeToKmerBuilder Build() which build kmers
/// using one base sequence
/// </summary>
/// <param name="nodeName">xml node name used for different testcases</param>
internal void ValidateKmerBuilderBuildWithSequence(string nodeName)
{
string filePath = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.FilePathNode);
string kmerLength = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.KmerLengthNode);
// Get the input reads
IEnumerable<ISequence> sequenceReads = null;
FastAParser parser = new FastAParser ();
parser.Open (filePath);
sequenceReads = parser.Parse().ToList();
parser.Close ();
// Pass each input read and kmerLength
// Add all the generated kmers to kmer list
SequenceToKmerBuilder builder = new SequenceToKmerBuilder();
IList<KmersOfSequence> lstKmers = new List<KmersOfSequence>();
foreach (ISequence sequence in sequenceReads)
{
lstKmers.Add(builder.Build(sequence, int.Parse(kmerLength, (IFormatProvider)null)));
}
// Validate all the kmers
ValidateKmersList(lstKmers, sequenceReads.ToList(), nodeName);
ApplicationLog.WriteLine(
@"Padena BVT : Validation of Build with each input read sequence
completed successfully");
}
/// <summary>
/// Validate SequenceRangeToKmerBuilder Build() method which build kmers
/// </summary>
/// <param name="nodeName">xml node name for test data</param>
internal void ValidateKmerBuilderBuild(string nodeName)
{
string filePath = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.FilePathNode);
string kmerLength = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.KmerLengthNode);
// Get the input reads
IEnumerable<ISequence> sequenceReads = null;
FastAParser parser = new FastAParser ();
parser.Open( filePath.Replace("\\", System.IO.Path.DirectorySeparatorChar.ToString()));
sequenceReads = parser.Parse().ToList();
parser.Close ();
// Pass all the input reads and kmerLength to generate kmers
SequenceToKmerBuilder builder = new SequenceToKmerBuilder();
IEnumerable<KmersOfSequence> lstKmers = builder.Build(sequenceReads,
int.Parse(kmerLength, (IFormatProvider)null));
// Validate kmers list
ValidateKmersList(new List<KmersOfSequence>(lstKmers),
new List<ISequence>(sequenceReads), nodeName);
ApplicationLog.WriteLine(
@"Padena BVT : Validation of Build with all input reads
sequence completed successfully");
}
/// <summary>
/// Validate ParallelDeNovoAssembler step1 Build kmers
/// </summary>
/// <param name="nodeName">xml node for test data</param>
internal void ValidateDe2AssemblerBuildKmers(string nodeName)
{
// Read all the input sequences from xml config file
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.FilePathNode);
string kmerLength = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.KmerLengthNode);
// set kmerLength
this.KmerLength = int.Parse(kmerLength, (IFormatProvider)null);
IEnumerable<ISequence> sequenceReads = null;
FastAParser parser = new FastAParser ();
parser.Open( filePath.Replace("\\", System.IO.Path.DirectorySeparatorChar.ToString()));
sequenceReads = parser.Parse().ToList();
parser.Close ();
this.SequenceReads.Clear(); // set all the input reads and execute build kmers
this.SetSequenceReads(sequenceReads.ToList());
IEnumerable<KmersOfSequence> lstKmers =
(new SequenceToKmerBuilder()).Build(this.SequenceReads,
this.KmerLength);
ValidateKmersList(new List<KmersOfSequence>(lstKmers),
new List<ISequence>(sequenceReads), nodeName);
ApplicationLog.WriteLine(
@"Padena BVT : Validation of Build with all input reads using
ParallelDeNovoAssembler sequence completed successfully");
}
/// <summary>
/// Creates RedundantPathPurger instance by passing pathlength and count. Detect
/// redundant error nodes and remove these nodes from the graph. Validate the graph.
/// </summary>
/// <param name="nodeName">xml node name used for different testcases</param>
/// <param name="isMicroOrganism">Is micro organism</param>
internal void ValidateRedundantPathPurgerCtor(string nodeName, bool isMicroOrganism)
{
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.FilePathNode);
string kmerLength = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.KmerLengthNode);
string expectedNodesCount = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.ExpectedNodesCountAfterDangling);
// Get the input reads and build kmers
IEnumerable<ISequence> sequenceReads = null;
FastAParser parser = new FastAParser();
parser.Open(filePath);
sequenceReads = parser.Parse().ToList();
parser.Close ();
// Build kmers from step1,graph in step2
// Remove the dangling links from graph in step3
// Validate the graph
this.KmerLength = int.Parse(kmerLength, (IFormatProvider)null);
this.SequenceReads.Clear();
this.SetSequenceReads(sequenceReads.ToList());
this.CreateGraph();
DeBruijnGraph graph = this.Graph;
this.DanglingLinksPurger = new DanglingLinksPurger(this.KmerLength);
this.UnDangleGraph();
// Create RedundantPathPurger instance, detect redundant nodes and remove error nodes
RedundantPathsPurger redundantPathPurger =
new RedundantPathsPurger(int.Parse(kmerLength, (IFormatProvider)null) + 1);
DeBruijnPathList redundantnodelist = redundantPathPurger.DetectErroneousNodes(graph);
redundantPathPurger.RemoveErroneousNodes(graph, redundantnodelist);
if (isMicroOrganism)
Assert.AreEqual(expectedNodesCount, graph.GetNodes().Count());
else
ValidateGraph(graph, nodeName);
ApplicationLog.WriteLine(@"Padena P1 :RedundantPathsPurger ctor and methods validation for Padena step4 completed successfully");
}
/// <summary>
/// Validate ParallelDeNovothis.BuildContigs() by passing graph object
/// </summary>
/// <param name="nodeName">xml node name used for different testcases</param>
/// <param name="isChromosomeRC">Is chromosome RC?</param>
internal void ValidateDe2thisBuildContigs(string nodeName, bool isChromosomeRC)
{
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.FilePathNode);
string kmerLength = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.KmerLengthNode);
string expectedContigsString = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.ContigsNode);
string[] expectedContigs;
if (!expectedContigsString.ToUpper(CultureInfo.InstalledUICulture).Contains("PADENATESTDATA"))
expectedContigs = expectedContigsString.Split(',');
else
expectedContigs =
ReadStringFromFile(expectedContigsString).Replace("\r\n", "").Split(',');
string expectedContigsCount = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.ContigsCount);
// Get the input reads and build kmers
IEnumerable<ISequence> sequenceReads = null;
FastAParser parser = new FastAParser();
parser.Open(filePath);
sequenceReads = parser.Parse().ToList();
parser.Close ();
// Build kmers from step1,graph in step2
// Remove the dangling links from graph in step3
// Remove bubbles form the graph in step4
// Pass the graph and build contigs
// Validate the contigs
this.KmerLength = int.Parse(kmerLength, (IFormatProvider)null);
this.SequenceReads.Clear();
this.SetSequenceReads(sequenceReads.ToList());
this.CreateGraph();
this.DanglingLinksPurger = new DanglingLinksPurger(this.KmerLength);
this.UnDangleGraph();
this.RedundantPathsPurger = new RedundantPathsPurger(this.KmerLength + 1);
this.RemoveRedundancy();
this.ContigBuilder = new SimplePathContigBuilder();
IList<ISequence> contigs = this.BuildContigs().ToList();
// Validate contigs count only for Chromosome files.
if (isChromosomeRC)
{
Assert.AreEqual(expectedContigsCount, contigs.Count.ToString((IFormatProvider)null));
}
// validate all contigs of a sequence.
else
{
for (int index = 0; index < contigs.Count(); index++)
{
Assert.IsTrue(expectedContigs.Contains(new string(contigs[index].Select(a => (char)a).ToArray())) ||
expectedContigs.Contains(new string(contigs[index].GetReverseComplementedSequence().Select(a => (char)a).ToArray())));
}
}
ApplicationLog.WriteLine(@"Padena P1 :ParallelDeNovothis.BuildContigs() validation for Padena step5 completed successfully");
}
/// <summary>
/// Validate KmersOfSequence ctor by passing base sequence reads, kmer length and
/// built kmers
/// </summary>
/// <param name="nodeName">xml node name.</param>
internal void ValidateKmersOfSequenceCtorWithBuildKmers(string nodeName)
{
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.FilePathNode);
string kmerLength = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.KmerLengthNode);
// Get the input reads
IEnumerable<ISequence> sequenceReads = null;
FastAParser parser = new FastAParser();
parser.Open(filePath);
sequenceReads = parser.Parse().ToList();
parser.Close ();
SequenceToKmerBuilder builder = new SequenceToKmerBuilder();
IList<KmersOfSequence> lstKmers = new List<KmersOfSequence>();
// Validate KmersOfSequence ctor using build kmers
foreach (ISequence sequence in sequenceReads)
{
KmersOfSequence kmer = builder.Build(sequence, int.Parse(kmerLength, (IFormatProvider)null));
KmersOfSequence kmerSequence = new KmersOfSequence(sequence,
int.Parse(kmerLength, (IFormatProvider)null), kmer.Kmers);
lstKmers.Add(kmerSequence);
}
ValidateKmersList(lstKmers, sequenceReads.ToList(), nodeName);
ApplicationLog.WriteLine(@"Padena P1 : KmersOfSequence ctor with build kmers method validation completed successfully");
}
/// <summary>
/// Validate library information
/// </summary>
/// <param name="nodeName">xml node name used for different testcases</param>
internal void GetLibraryInformation(string nodeName)
{
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.FilePathNode);
string expectedPairedReadsCount = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.PairedReadsCountNode);
string expectedLibraray = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.LibraryName);
string expectedStdDeviation = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.StdDeviation);
string mean = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.Mean);
IList<MatePair> pairedreads = new List<MatePair>();
// Get the input reads
IEnumerable<ISequence> sequences = null;
FastAParser parser = new FastAParser();
parser.Open(filePath);
sequences = parser.Parse().ToList();
parser.Close ();
// Convert reads to map paired reads.
MatePairMapper pair = new MatePairMapper();
pairedreads = pair.Map(new List<ISequence>(sequences));
// Validate Map paired reads.
Assert.AreEqual(expectedPairedReadsCount,
pairedreads.Count.ToString((IFormatProvider)null));
// Get library infomration and validate
CloneLibraryInformation libraryInfo =
CloneLibrary.Instance.GetLibraryInformation
(pairedreads[0].Library);
Assert.AreEqual(expectedStdDeviation, libraryInfo.StandardDeviationOfInsert.ToString((IFormatProvider)null));
Assert.AreEqual(expectedLibraray, libraryInfo.LibraryName.ToString((IFormatProvider)null));
Assert.AreEqual(mean, libraryInfo.MeanLengthOfInsert.ToString((IFormatProvider)null));
ApplicationLog.WriteLine(@"Padena P1 : Map paired reads has been verified successfully");
}
/// <summary>
/// Validate KmersOfSequence ctor by passing base sequence reads, kmer length and
/// built kmers and validate its properties.
/// </summary>
/// <param name="nodeName">xml node name.</param>
internal void ValidateKmersOfSequenceCtorProperties(string nodeName)
{
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.FilePathNode);
string kmerLength = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.KmerLengthNode);
string expectedSeq = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.BaseSequenceNode);
string expectedKmers = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.KmersCountNode);
// Get the input reads
IEnumerable<ISequence> sequenceReads = null;
FastAParser parser = new FastAParser();
parser.Open(filePath);
sequenceReads = parser.Parse().ToList();
parser.Close ();
SequenceToKmerBuilder builder = new SequenceToKmerBuilder();
KmersOfSequence kmer = builder.Build(sequenceReads.ToList()[0],
int.Parse(kmerLength, (IFormatProvider)null));
KmersOfSequence kmerSequence = new KmersOfSequence(sequenceReads.ToList()[0],
int.Parse(kmerLength, (IFormatProvider)null), kmer.Kmers);
// Validate KmerOfSequence properties.
Assert.AreEqual(expectedSeq, new string(kmerSequence.BaseSequence.Select(a => (char)a).ToArray()));
Assert.AreEqual(expectedKmers, kmerSequence.Kmers.Count.ToString((IFormatProvider)null));
ApplicationLog.WriteLine(@"Padena P1 : KmersOfSequence ctor with build kmers method validation completed successfully");
}
/// <summary>
/// Validate building map reads to contigs.
/// </summary>
/// <param name="nodeName">xml node name used for a different testcases</param>
/// <param name="isFullOverlap">True if full overlap else false</param>
internal void ValidateMapReadsToContig(string nodeName, bool isFullOverlap)
{
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.FilePathNode);
string kmerLength = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.KmerLengthNode);
string daglingThreshold = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.DanglingLinkThresholdNode);
string redundantThreshold = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.RedundantThreshold);
string readMapLengthString = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.ReadMapLength);
string readStartPosString = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.ReadStartPos);
string contigStartPosString = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.ContigStartPos);
string[] expectedReadmapLength = readMapLengthString.Split(',');
string[] expectedReadStartPos = readStartPosString.Split(',');
string[] expectedContigStartPos = contigStartPosString.Split(',');
// Get the input reads and build kmers
FastAParser parser = new FastAParser();
parser.Open(filePath);
IEnumerable<ISequence> sequenceReads = parser.Parse().ToList();
parser.Close ();
// Build kmers from step1,graph in step2
// Remove the dangling links from graph in step3
// Remove bubbles form the graph in step4
// Pass the graph and build contigs
// Validate contig reads
this.KmerLength = Int32.Parse(kmerLength, null);
this.DanglingLinksThreshold = Int32.Parse(daglingThreshold, null);
this.DanglingLinksPurger = new DanglingLinksPurger(Int32.Parse(daglingThreshold, null));
this.RedundantPathsPurger = new RedundantPathsPurger(Int32.Parse(redundantThreshold, null));
this.RedundantPathLengthThreshold = Int32.Parse(redundantThreshold, null);
this.SetSequenceReads(sequenceReads.ToList());
this.CreateGraph();
this.UnDangleGraph();
this.ContigBuilder = new SimplePathContigBuilder();
this.RemoveRedundancy();
IEnumerable<ISequence> contigs = this.BuildContigs();
IList<ISequence> sortedContigs = SortContigsData(contigs.ToList());
ReadContigMapper mapper = new ReadContigMapper();
ReadContigMap maps = mapper.Map(sortedContigs, sequenceReads, this.KmerLength);
Assert.AreEqual(maps.Count, sequenceReads.Count());
Dictionary<ISequence, IList<ReadMap>> readMaps = maps[sequenceReads.ToList()[0].ID];
for (int i = 0; i < SortContigsData(readMaps.Keys.ToList()).Count; i++)
{
IList<ReadMap> readMap = readMaps[SortContigsData(readMaps.Keys.ToList())[i]];
if (isFullOverlap)
{
Assert.AreEqual(expectedReadmapLength[i], readMap[0].Length.ToString((IFormatProvider)null), "readMap failed for pos " + i);
Assert.AreEqual(expectedContigStartPos[i], readMap[0].StartPositionOfContig.ToString((IFormatProvider)null), "contigStart failed for pos " + i);
Assert.AreEqual(expectedReadStartPos[i], readMap[0].StartPositionOfRead.ToString((IFormatProvider)null), "readStart failed for pos " + i);
Assert.AreEqual(readMap[0].ReadOverlap, ContigReadOverlapType.FullOverlap);
}
else
{
Assert.AreEqual(readMap[0].ReadOverlap, ContigReadOverlapType.PartialOverlap);
break;
}
}
ApplicationLog.WriteLine("PADENA P1 :ReadContigMapper.Map() validation for Padena step6:step2 completed successfully");
}
/// <summary>
/// Validate KmersOfSequence ToSequences() method which returns kmers sequence
/// using its positions
/// </summary>
/// <param name="nodeName">xml node name used for different testcases</param>
internal void ValidateKmersOfSequenceToSequences(string nodeName)
{
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.FilePathNode);
string kmerLength = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.KmerLengthNode);
string kmerOutputFile = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.KmersOutputFileNode);
// Get the input reads and build kmers
IEnumerable<ISequence> sequenceReads = null;
FastAParser parser = new FastAParser();
parser.Open(filePath);
sequenceReads = parser.Parse().ToList();
parser.Close ();
this.KmerLength = int.Parse(kmerLength, (IFormatProvider)null);
this.SequenceReads.Clear();
this.SetSequenceReads(sequenceReads.ToList());
IList<KmersOfSequence> lstKmers = new List<KmersOfSequence>(
(new SequenceToKmerBuilder()).Build(this.SequenceReads, this.KmerLength));
// Get the array of kmer sequence using ToSequence()
int index = 0;
// Validate the generated kmer sequence with the expected output
using (StreamReader kmerFile = new StreamReader(kmerOutputFile))
{
string line = string.Empty;
List<string[]> fileContent = new List<string[]>();
while (null != (line = kmerFile.ReadLine()))
{
fileContent.Add(line.Split(','));
}
foreach (ISequence sequenceRead in sequenceReads)
{
int count = 0;
KmersOfSequence kmerSequence = new KmersOfSequence(sequenceRead,
int.Parse(kmerLength, (IFormatProvider)null), lstKmers[index].Kmers);
IEnumerable<ISequence> sequences = kmerSequence.KmersToSequences();
foreach (ISequence sequence in sequences)
{
string aab = new string(sequence.Select(a => (char)a).ToArray());
Assert.AreEqual(fileContent[index][count], aab);
count++;
}
index++;
}
}
ApplicationLog.WriteLine(@"Padena P1 : KmersOfSequence ToSequences() method validation completed successfully");
}
/// <summary>
/// Validate FilterPairedRead.FilterPairedRead() by passing graph object
/// </summary>
/// <param name="nodeName">xml node name used for a differnt testcase.</param>
internal void ValidateContigDistance(string nodeName)
{
string filePath = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.FilePathNode);
string kmerLength = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.KmerLengthNode);
string daglingThreshold = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.DanglingLinkThresholdNode);
string redundantThreshold = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.RedundantThreshold);
string expectedContigPairedReadsCount = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.ContigPairedReadsCount);
string distanceBetweenFirstContigs = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.DistanceBetweenFirstContig);
string distanceBetweenSecondContigs = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.DistanceBetweenSecondContig);
string firstStandardDeviation = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.FirstContigStandardDeviation);
string secondStandardDeviation = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.SecondContigStandardDeviation);
// Get the input reads and build kmers
IEnumerable<ISequence> sequenceReads = null;
FastAParser parser = new FastAParser();
parser.Open(filePath);
sequenceReads = parser.Parse().ToList();
parser.Close ();
// Build kmers from step1,graph in step2
// Remove the dangling links from graph in step3
// Remove bubbles form the graph in step4
// Pass the graph and build contigs
// Validate contig reads
this.KmerLength = Int32.Parse(kmerLength, (IFormatProvider)null);
this.DanglingLinksThreshold = Int32.Parse(daglingThreshold, (IFormatProvider)null);
this.DanglingLinksPurger =
new DanglingLinksPurger(Int32.Parse(daglingThreshold, (IFormatProvider)null));
this.RedundantPathsPurger =
new RedundantPathsPurger(Int32.Parse(redundantThreshold, (IFormatProvider)null));
this.RedundantPathLengthThreshold = Int32.Parse(redundantThreshold, (IFormatProvider)null);
this.SequenceReads.Clear();
this.SetSequenceReads(sequenceReads.ToList());
this.CreateGraph();
this.UnDangleGraph();
// Build contig.
this.ContigBuilder = new SimplePathContigBuilder();
this.RemoveRedundancy();
IEnumerable<ISequence> contigs = this.BuildContigs();
IList<ISequence> sortedContigs = SortContigsData(contigs.ToList());
ReadContigMapper mapper = new ReadContigMapper();
ReadContigMap maps = mapper.Map(sortedContigs, sequenceReads, this.KmerLength);
// Find map paired reads.
MatePairMapper mapPairedReads = new MatePairMapper();
ContigMatePairs pairedReads = mapPairedReads.MapContigToMatePairs(sequenceReads, maps);
// Filter contigs based on the orientation.
OrientationBasedMatePairFilter filter = new OrientationBasedMatePairFilter();
ContigMatePairs contigpairedReads = filter.FilterPairedReads(pairedReads, 0);
// Calculate the distance between contigs.
DistanceCalculator calc = new DistanceCalculator(contigpairedReads);
calc.CalculateDistance();
Assert.AreEqual(expectedContigPairedReadsCount,
contigpairedReads.Values.Count.ToString((IFormatProvider)null));
Dictionary<ISequence, IList<ValidMatePair>> map;
IList<ValidMatePair> valid;
ISequence firstSeq = sortedContigs[0];
ISequence secondSeq = sortedContigs[1];
if (contigpairedReads.ContainsKey(firstSeq))
{
map = contigpairedReads[firstSeq];
}
else
{
map = contigpairedReads[secondSeq];
}
if (map.ContainsKey(firstSeq))
{
valid = map[firstSeq];
}
else
{
valid = map[secondSeq];
}
// Validate distance and standard deviation between contigs.
Assert.AreEqual(float.Parse(distanceBetweenFirstContigs, (IFormatProvider)null),
valid.First().DistanceBetweenContigs[0]);
Assert.AreEqual(float.Parse(distanceBetweenSecondContigs, (IFormatProvider)null),
valid.First().DistanceBetweenContigs[1]);
Assert.AreEqual(float.Parse(firstStandardDeviation, (IFormatProvider)null),
valid.First().StandardDeviation[0]);
Assert.AreEqual(float.Parse(secondStandardDeviation, (IFormatProvider)null),
valid.First().StandardDeviation[1]);
ApplicationLog.WriteLine("PADENA P1 : DistanceCalculator() validation for Padena step6:step5 completed successfully");
}
/// <summary>
/// Validate Validate DeBruijinGraph properties
/// </summary>
/// <param name="nodeName">xml node name used for different testcases</param>
internal void ValidateDeBruijinGraphproperties(string nodeName)
{
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.FilePathNode);
string kmerLength = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.KmerLengthNode);
string ExpectedNodesCount = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.GraphNodesCountNode);
// Get the input reads and build kmers
IEnumerable<ISequence> sequenceReads = null;
FastAParser parser = new FastAParser();
parser.Open(filePath);
sequenceReads = parser.Parse().ToList();
parser.Close ();
this.KmerLength = int.Parse(kmerLength, (IFormatProvider)null);
this.SequenceReads.Clear();
this.SetSequenceReads(sequenceReads.ToList());
this.CreateGraph();
DeBruijnGraph graph = this.Graph;
ApplicationLog.WriteLine("Padena P1 : Step1,2 Completed Successfully");
// Validate DeBruijnGraph Properties.
Assert.AreEqual(ExpectedNodesCount, graph.GetNodes().Count().ToString((IFormatProvider)null));
ApplicationLog.WriteLine(@"Padena P1 : ParallelDeNovothis CreateGraph() validation for Padena step2 completed successfully");
}
/// <summary>
/// Validate scaffold sequence for a given input reads.
/// </summary>
/// <param name="nodeName">xml node name used for different testcases</param>
internal void ValidateScaffoldSequence(string nodeName)
{
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.FilePathNode);
string kmerLength = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.KmerLengthNode);
string daglingThreshold = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.DanglingLinkThresholdNode);
string redundantThreshold = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.RedundantThreshold);
string libraray = utilityObj.xmlUtil.GetTextValue(nodeName,Constants.LibraryName);
string stdDeviation = utilityObj.xmlUtil.GetTextValue(nodeName,Constants.StdDeviation);
string mean = utilityObj.xmlUtil.GetTextValue(nodeName,Constants.Mean);
string inputRedundancy = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.InputRedundancy);
string expectedSeq = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.ScaffoldSeq);
string[] scaffoldSeqNodes = expectedSeq.Split(',');
// Get the input reads and build kmers
FastAParser parser = new FastAParser();
parser.Open(filePath);
IEnumerable<ISequence> sequenceReads = parser.Parse().ToList();
parser.Close ();
// Build kmers from step1,graph in step2
// Remove the dangling links from graph in step3
// Remove bubbles form the graph in step4
// Pass the graph and build contigs
// Validate contig reads
this.KmerLength = Int32.Parse(kmerLength, null);
this.DanglingLinksThreshold = Int32.Parse(daglingThreshold, null);
this.DanglingLinksPurger = new DanglingLinksPurger(Int32.Parse(daglingThreshold, null));
this.RedundantPathsPurger = new RedundantPathsPurger(Int32.Parse(redundantThreshold, null));
this.RedundantPathLengthThreshold = Int32.Parse(redundantThreshold, null);
this.SequenceReads.Clear();
this.SetSequenceReads(sequenceReads.ToList());
this.CreateGraph();
this.UnDangleGraph();
// Build contig.
this.RemoveRedundancy();
IEnumerable<ISequence> contigs = this.BuildContigs();
// Find map paired reads.
CloneLibrary.Instance.AddLibrary(libraray, float.Parse(mean, null),
float.Parse(stdDeviation, null));
IEnumerable<ISequence> scaffoldSeq;
using (GraphScaffoldBuilder scaffold = new GraphScaffoldBuilder())
{
scaffoldSeq = scaffold.BuildScaffold(
sequenceReads, contigs.ToList(), this.KmerLength, redundancy: Int32.Parse(inputRedundancy, null));
}
AlignmentHelpers.CompareSequenceLists(new HashSet<string>(scaffoldSeqNodes), scaffoldSeq.ToList());
ApplicationLog.WriteLine("PADENA P1 : Scaffold sequence : validation for Padena step6:step8 completed successfully");
}
/// <summary>
/// Validate RemoveExtension() method of DeBruijnNode
/// </summary>
/// <param name="nodeName">xml node name used for different testcases</param>
internal void ValidateDeBruijnNodeRemoveExtension(string nodeName)
{
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.FilePathNode);
string kmerLength = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.KmerLengthNode);
// Get the input reads and build kmers
IEnumerable<ISequence> sequenceReads = null;
FastAParser parser = new FastAParser();
parser.Open(filePath);
sequenceReads = parser.Parse().ToList();
parser.Close ();
// Build kmers from step1
this.KmerLength = int.Parse(kmerLength, (IFormatProvider)null);
this.SequenceReads.Clear();
this.SetSequenceReads(sequenceReads.ToList());
IList<KmersOfSequence> lstKmers = new List<KmersOfSequence>(
(new SequenceToKmerBuilder()).Build(this.SequenceReads, this.KmerLength));
// Validate the node creation
// Create node and add left node.
ISequence seq = this.SequenceReads.First();
KmerData32 kmerData = new KmerData32();
kmerData.SetKmerData(seq, lstKmers[0].Kmers.First().Positions[0], this.KmerLength);
DeBruijnNode node = new DeBruijnNode(kmerData, 1);
kmerData = new KmerData32();
kmerData.SetKmerData(seq, lstKmers[1].Kmers.First().Positions[0], this.KmerLength);
DeBruijnNode leftnode = new DeBruijnNode(kmerData, 1);
DeBruijnNode rightnode = new DeBruijnNode(kmerData, 1);
node.SetExtensionNode(false, true, leftnode);
node.SetExtensionNode(true, true, rightnode);
// Validates count before removing right and left extension nodes.
Assert.AreEqual(lstKmers[1].Kmers.First().Count,
node.RightExtensionNodesCount);
Assert.AreEqual(1, node.RightExtensionNodesCount);
Assert.AreEqual(1, node.LeftExtensionNodesCount);
// Remove right and left extension nodes.
node.RemoveExtensionThreadSafe(rightnode);
node.RemoveExtensionThreadSafe(leftnode);
// Validate node after removing right and left extensions.
Assert.AreEqual(0, node.RightExtensionNodesCount);
Assert.AreEqual(0, node.LeftExtensionNodesCount);
ApplicationLog.WriteLine(@"Padena P1 :DeBruijnNode AddRightExtension() validation for Padena step2 completed successfully");
}
/// <summary>
/// Filters the test data for the input file
/// </summary>
/// <param name="inputFile">Input File</param>
/// <param name="outputFile">Output File</param>
/// <param name="repeatLength">Repeat Length</param>
static void FilterTestData(string inputFile, string outputFile, int repeatLength)
{
if (File.Exists(inputFile))
{
Console.WriteLine("Processing the file '{0}'.", inputFile);
// Read the inputfile with the help of FastA Parser
FastAParser parserObj = new FastAParser();
FastAFormatter outputWriter = new FastAFormatter();
using (parserObj.Open(inputFile))
using (outputWriter.Open(outputFile))
{
IEnumerable<ISequence> inputReads = parserObj.Parse();
// Going through read by read in a given file
foreach (ISequence seq in inputReads)
{
// Get the First read in the file
byte[] actualRead = seq.ToArray();
// Assign the temporary local variables required
byte previousChar = actualRead[0];
int repeatLenCount = 0;
bool ignoreRead = false;
// Go through each and every character/byte in the read
for (int j = 1; j < actualRead.Length; j++)
{
// Check if the previous character is same as current.
if (previousChar == actualRead[j])
{
repeatLenCount++;
// if repeat length exceeds, skip this read and continue with other read
if (repeatLenCount == repeatLength)
{
Console.WriteLine("Character '{0}' repeated more than '{1}' times and read '{2}' is skipped",
(char)previousChar, repeatLength, seq.ID);
ignoreRead = true;
break;
}
continue;
}
repeatLenCount = 0;
previousChar = actualRead[j];
}
Console.WriteLine("Read '{0}' Processed.", seq.ID);
// Check if the length exceeds the max length and write it to the output file
if (!ignoreRead)
{
outputWriter.Format(seq);
}
}
}
Console.WriteLine();
Console.WriteLine("Filtering Completed!!");
}
else
Console.WriteLine("Enter Valid File Path.");
}
/// <summary>
/// Validate the DeBruijnNode ctor by passing the kmer and validating
/// the node object.
/// </summary>
/// <param name="nodeName">xml node name used for different testcases</param>
internal void ValidateDeBruijnNodeCtor(string nodeName)
{
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.FilePathNode);
string kmerLength = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.KmerLengthNode);
string nodeExtensionsCount = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.NodeExtensionsCountNode);
string kmersCount = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.KmersCountNode);
string leftNodeExtensionCount = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.LeftNodeExtensionsCountNode);
string rightNodeExtensionCount = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.RightNodeExtensionsCountNode);
// Get the input reads and build kmers
IEnumerable<ISequence> sequenceReads = null;
FastAParser parser = new FastAParser();
parser.Open(filePath);
sequenceReads = parser.Parse().ToList();
parser.Close ();
// Build the kmers using this
this.KmerLength = int.Parse(kmerLength, (IFormatProvider)null);
this.SequenceReads.Clear();
this.SetSequenceReads(sequenceReads.ToList());
IList<KmersOfSequence> lstKmers = new List<KmersOfSequence>(
(new SequenceToKmerBuilder()).Build(this.SequenceReads, this.KmerLength));
// Validate the node creation
// Create node and add left node.
ISequence seq = this.SequenceReads.First();
KmerData32 kmerData = new KmerData32();
kmerData.SetKmerData(seq, lstKmers[0].Kmers.First().Positions[0], this.KmerLength);
DeBruijnNode node = new DeBruijnNode(kmerData, 1);
kmerData = new KmerData32();
kmerData.SetKmerData(seq, lstKmers[1].Kmers.First().Positions[0], this.KmerLength);
DeBruijnNode leftnode = new DeBruijnNode(kmerData, 1);
DeBruijnNode rightnode = new DeBruijnNode(kmerData, 1);
node.SetExtensionNode(false, true, leftnode);
node.SetExtensionNode(true, true, rightnode);
// Validate DeBruijnNode class properties.
Assert.AreEqual(nodeExtensionsCount, node.ExtensionsCount.ToString((IFormatProvider)null));
Assert.AreEqual(kmersCount, node.KmerCount.ToString((IFormatProvider)null));
Assert.AreEqual(leftNodeExtensionCount, node.LeftExtensionNodesCount.ToString((IFormatProvider)null));
Assert.AreEqual(rightNodeExtensionCount, node.RightExtensionNodesCount.ToString((IFormatProvider)null));
Assert.AreEqual(leftNodeExtensionCount, node.LeftExtensionNodesCount.ToString((IFormatProvider)null));
Assert.AreEqual(rightNodeExtensionCount, node.RightExtensionNodesCount.ToString((IFormatProvider)null));
ApplicationLog.WriteLine("Padena P1 : DeBruijnNode ctor() validation for Padena step2 completed successfully");
}
/// <summary>
/// Validate RemoveErrorNodes() method is removing dangling nodes from the graph
/// </summary>
/// <param name="nodeName">xml node name used for different testcases</param>
internal void ValidatePadenaRemoveErrorNodes(string nodeName)
{
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.FilePathNode);
string kmerLength = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.KmerLengthNode);
// Get the input reads and build kmers
IEnumerable<ISequence> sequenceReads = null;
FastAParser parser = new FastAParser();
parser.Open(filePath);
sequenceReads = parser.Parse().ToList();
parser.Close ();
// Build kmers from step1,graph in step2
// and remove the dangling links from graph in step3
// Validate the graph
this.KmerLength = int.Parse(kmerLength, (IFormatProvider)null);
this.SequenceReads.Clear();
this.SetSequenceReads(sequenceReads.ToList());
this.CreateGraph();
DeBruijnGraph graph = this.Graph;
// Find the dangling nodes and remove the dangling node
DanglingLinksPurger danglingLinksPurger =
new DanglingLinksPurger(int.Parse(kmerLength, (IFormatProvider)null) + 1);
DeBruijnPathList danglingnodes = danglingLinksPurger.DetectErroneousNodes(graph);
danglingLinksPurger.RemoveErroneousNodes(graph, danglingnodes);
Assert.IsFalse(graph.GetNodes().Contains(danglingnodes.Paths[0].PathNodes[0]));
ApplicationLog.WriteLine(@"Padena P1 :DeBruijnGraph.RemoveErrorNodes() validation for Padena step3 completed successfully");
}
/// <summary>
/// Validate ParallelDenovoAssembler class properties.
/// </summary>
/// <param name="nodeName">xml node name used for different testcases</param>
internal void ParallelDenovoAssemblyProperties(string nodeName)
{
// Get values from XML node.
string filePath = utilityObj.xmlUtil.GetTextValue (nodeName, Constants.FilePathNode);
string kmerLength = utilityObj.xmlUtil.GetTextValue (nodeName, Constants.KmerLengthNode);
string library = utilityObj.xmlUtil.GetTextValue (nodeName, Constants.LibraryName);
string StdDeviation = utilityObj.xmlUtil.GetTextValue (nodeName, Constants.StdDeviation);
string mean = utilityObj.xmlUtil.GetTextValue (nodeName, Constants.Mean);
// Get the input reads and build kmers
IEnumerable<ISequence> sequenceReads = null;
FastAParser parser = new FastAParser ();
parser.Open (filePath);
sequenceReads = parser.Parse ();
// Build kmers from step1,graph in step2
// Remove the dangling links from graph in step3
// Remove bubbles form the graph in step4
// Pass the graph and build contigs
// Validate the contigs
this.KmerLength = int.Parse (kmerLength, (IFormatProvider)null);
this.SequenceReads.Clear ();
this.SetSequenceReads (sequenceReads.ToList ());
this.CreateGraph ();
this.UnDangleGraph ();
this.RedundantPathsPurger =
new RedundantPathsPurger (int.Parse (kmerLength, (IFormatProvider)null) + 1);
this.RemoveRedundancy ();
this.ContigBuilder = new SimplePathContigBuilder ();
// Build contigs
IEnumerable<ISequence> contigs = this.BuildContigs ();
CloneLibraryInformation cloneLibInfoObj = new CloneLibraryInformation ();
cloneLibInfoObj.LibraryName = library;
cloneLibInfoObj.MeanLengthOfInsert = float.Parse (mean, (IFormatProvider)null);
cloneLibInfoObj.StandardDeviationOfInsert = float.Parse (StdDeviation, (IFormatProvider)null);
// Build scaffolds.
CloneLibrary.Instance.AddLibrary (library, float.Parse (mean, (IFormatProvider)null),
float.Parse (StdDeviation, (IFormatProvider)null));
IEnumerable<ISequence> scaffolds = BuildScaffolds (contigs.ToList ());
PadenaAssembly denovoAssembly = new PadenaAssembly ();
denovoAssembly.AddContigs (contigs);
denovoAssembly.AddScaffolds (scaffolds);
Assert.AreEqual (denovoAssembly.ContigSequences.Count (),
contigs.Count ());
Assert.AreEqual (denovoAssembly.Scaffolds.Count (), scaffolds.Count ());
Assert.IsNull (denovoAssembly.Documentation);
// Validates the Clone Library for the existing clone
CloneLibraryInformation actualObj = CloneLibrary.Instance.GetLibraryInformation (library);
Assert.IsTrue (actualObj.Equals (cloneLibInfoObj));
ApplicationLog.WriteLine ("CloneLibraryInformation Equals() is successfully validated");
// Validate ParallelDenovoAssembler properties.
ApplicationLog.WriteLine (
@"Padena BVT : Validated ParallelDenovo Assembly properties");
}
