/// <summary>
/// The execution method for the activity.
/// </summary>
/// <param name="executionContext">The execution context.</param>
/// <returns>The execution status.</returns>
protected override ActivityExecutionStatus Execute(ActivityExecutionContext executionContext)
{
FastAFormatter formatter = new FastAFormatter();
formatter.Open(OutputFile);
if ((Sequence == null) && (SequenceList != null))
{
foreach (ISequence sequence in SequenceList)
{
formatter.Write(sequence);
}
}
else if ((Sequence != null) && (SequenceList == null))
{
formatter.Write(Sequence);
}
else if ((Sequence != null) && (SequenceList != null))
{
foreach (ISequence sequence in SequenceList)
{
formatter.Write(sequence);
}
formatter.Write(Sequence);
}
formatter.Close();
return(ActivityExecutionStatus.Closed);
}
/// <summary>
/// Write sequences to the file
/// </summary>
/// <param name="sequences"></param>
private void WriteSequences(IEnumerable <ISequence> sequences)
{
if (!string.IsNullOrEmpty(this.OutputFile))
{
int count = 0;
using (var formatter = new FastAFormatter(this.OutputFile))
{
formatter.AutoFlush = true;
foreach (ISequence sequence in sequences)
{
count++;
formatter.Write(sequence);
}
}
Output.WriteLine(OutputLevel.Information, "Wrote {0} sequences to {1}.", count, this.OutputFile);
}
else
{
Output.WriteLine(OutputLevel.Information, "Results:");
foreach (ISequence seq in sequences)
{
Output.WriteLine(OutputLevel.Results, seq.ID);
Output.WriteLine(OutputLevel.Results, new string(seq.Select(a => (char)a).ToArray()));
}
}
}
/// <summary>
/// Convert a list of ISequences to FASTA format and write to file. In order to reduce the amount of compute time required
/// by BLAST, we limit the number of sequences being fed to BLAST.
/// </summary>
/// <param name="sequences">IEnumerable list of Sequence objects</param>
/// <param name="output">Name of the output FASTA file</param>
/// <param name="maxSequences">Optional maximum number of sequences to convert</param>
/// <param name="overwrite">If true, any existing file with the same name will be overwritten. Otherwise, the file will not be overwritten and conversion will be skipped.</param>
/// <returns>True if a Fasta file was written, false if it already exists</returns>
public static bool ConvertToFASTA(IEnumerable <ISequence> sequences, string output, int maxSequences, bool overwrite = false)
{
// If conditions:
// 1. File doesn't exist; OR
// 2. File exists but is empty; OR
// 3. File exists but overwrite flag is set.
if (!File.Exists(output) || new FileInfo(output).Length == 0 || overwrite)
{
FastAFormatter fa = new FastAFormatter(output);
int count = 0;
foreach (var seqObj in sequences)
{
fa.Write(seqObj);
++count;
if (count >= maxSequences)
{
break;
}
}
fa.Close();
return(true);
}
return(false);
}
public HaploGrepSharp.NewSearchMethods.HaploTypeReport OutputAssembly(string fileNamePrefix)
{
if (SuccessfulAssembly)
{
FastAFormatter fa = new FastAFormatter(fileNamePrefix + "BestGreedyAssembly.fna");
StringBuilder sb = new StringBuilder(StaticResources.CRS_LENGTH);
var bestAssembly = GreedyPathAssembly;
bestAssembly.FinalizeAndOrientToReference();
Bio.Sequence s = new Bio.Sequence(bestAssembly.Sequence);
s.ID = "GreedyAssembly - length=" + AssemblyLength.ToString(); // + bestAssembly.FirstReferencePosition.Value.ToString() + " - " + GreedyPathAssembly.LastReferencePosition.Value.ToString();
fa.Write(s);
fa.Close();
//Now report all differences as well
StreamWriter sw = new StreamWriter(fileNamePrefix + "Report.txt");
var searcher = new HaploGrepSharp.NewSearchMethods.HaplotypeSearcher();
List <string> linesToWrite = new List <string> ();
var report = searcher.GetHaplotypeReport(s, linesToWrite, fileNamePrefix);
foreach (var l in linesToWrite)
{
sw.WriteLine(l);
}
sw.Close();
return(report);
}
return(null);
}
public void FastAFormatterValidateWrite()
{
using (FastAFormatter formatter = new FastAFormatter(Constants.FastaTempFileName))
{
// Gets the actual sequence and the alphabet from the Xml
string actualSequence = utilityObj.xmlUtil.GetTextValue(Constants.SimpleFastaNodeName,
Constants.ExpectedSequenceNode);
string alpName = utilityObj.xmlUtil.GetTextValue(Constants.SimpleFastaNodeName,
Constants.AlphabetNameNode);
// Logs information to the log file
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"FastA Formatter BVT: Validating with Sequence '{0}' and Alphabet '{1}'.",
actualSequence, alpName));
Sequence seqOriginal = new Sequence(Utility.GetAlphabet(alpName),
actualSequence);
seqOriginal.ID = "";
Assert.IsNotNull(seqOriginal);
// Use the formatter to write the original sequences to a temp file
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"FastA Formatter BVT: Creating the Temp file '{0}'.", Constants.FastaTempFileName));
formatter.Write(seqOriginal);
formatter.Close();
IEnumerable <ISequence> seqsNew = null;
// Read the new file, then compare the sequences
using (FastAParser parser = new FastAParser(Constants.FastaTempFileName))
{
parser.Alphabet = Alphabets.Protein;
seqsNew = parser.Parse();
char[] seqString = seqsNew.ElementAt(0).Select(a => (char)a).ToArray();
string newSequence = new string(seqString);
Assert.IsNotNull(seqsNew);
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"FastA Formatter BVT: New Sequence is '{0}'.",
newSequence));
// Now compare the sequences.
int countNew = seqsNew.Count();
Assert.AreEqual(1, countNew);
ApplicationLog.WriteLine("The Number of sequences are matching.");
Assert.AreEqual(seqOriginal.ID, seqsNew.ElementAt(0).ID);
string orgSeq = new string(seqsNew.ElementAt(0).Select(a => (char)a).ToArray());
Assert.AreEqual(orgSeq, newSequence);
Console.WriteLine(string.Format((IFormatProvider)null,
"FastA Formatter BVT: The FASTA sequences '{0}' are matching with Format() method and is as expected.",
newSequence));
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"FastA Formatter BVT: The FASTA sequences '{0}' are matching with Format() method.",
newSequence));
}
// Passed all the tests, delete the tmp file. If we failed an Assert,
// the tmp file will still be there in case we need it for debugging.
File.Delete(Constants.FastaTempFileName);
ApplicationLog.WriteLine("Deleted the temp file created.");
}
}
/// <summary>
/// Writes the contigs to the file.
/// </summary>
/// <param name="assembly">IDeNovoAssembly parameter is the result of running De Novo Assembly on a set of two or more sequences. </param>
protected void writeContigs(PadenaAssembly assembly)
{
if (assembly.AssembledSequences.Count == 0)
{
Output.WriteLine(OutputLevel.Results, "\tNo sequences assembled.");
return;
}
ensureContigNames(assembly.AssembledSequences);
if (!string.IsNullOrEmpty(this.DiagnosticFilePrefix))
{
using (FastAFormatter formatter = new FastAFormatter(ContigFileName)) {
formatter.AutoFlush = true;
foreach (ISequence seq in assembly.AssembledSequences)
{
formatter.Write(seq);
}
}
Output.WriteLine(OutputLevel.Information, "\tWrote {0} sequences to {1}", assembly.AssembledSequences.Count, ContigFileName);
}
else
{
Output.WriteLine(OutputLevel.Information, "\tAssembled Sequence Results: {0} sequences", assembly.AssembledSequences.Count);
using (FastAFormatter formatter = new FastAFormatter()) {
formatter.Open(new StreamWriter(Console.OpenStandardOutput()));
formatter.MaxSymbolsAllowedPerLine = decideOutputWidth();
formatter.AutoFlush = true;
foreach (ISequence seq in assembly.AssembledSequences)
{
formatter.Write(seq);
}
}
}
}
/// <summary>
/// Validates general FastA Parser test cases which are further Formatted
/// with the xml node name specified.
/// </summary>
/// <param name="nodeName">xml node name.</param>
private void ValidateParseFormatGeneralTestCases(string nodeName)
{
// Gets the expected sequence from the Xml
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.FilePathNode);
string alphabet = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.AlphabetNameNode);
Assert.IsTrue(File.Exists(filePath));
string filepathTmp = Path.Combine(Path.GetTempPath(), "temp.fasta");
// Ensure output is deleted
if (File.Exists(filepathTmp))
{
File.Delete(filepathTmp);
}
List <ISequence> seqsOriginal;
using (var parserObj = new FastAParser(filePath))
{
// Read the original file
parserObj.Alphabet = Utility.GetAlphabet(alphabet);
seqsOriginal = parserObj.Parse().ToList();
Assert.IsFalse(seqsOriginal.Count == 0);
}
// Write to a new file
using (var formatter = new FastAFormatter(filepathTmp))
{
formatter.Write(seqsOriginal);
}
try
{
// Compare original with new file
using (var parserObjNew = new FastAParser(filepathTmp))
{
// Read the new file, then compare the sequences
parserObjNew.Alphabet = Utility.GetAlphabet(alphabet);
IEnumerable <ISequence> seqsNew = parserObjNew.Parse();
Assert.IsNotNull(seqsNew);
int count = 0;
foreach (ISequence newSequence in seqsNew)
{
string s1 = seqsOriginal[count].ConvertToString();
string s2 = newSequence.ConvertToString();
Assert.AreEqual(s1, s2);
count++;
}
Assert.AreEqual(count, seqsOriginal.Count, "Number of sequences is different.");
}
}
finally
{
// Delete new file
File.Delete(filepathTmp);
}
}
/// <summary>
/// Exports a given list of sequences to a file in FastA format
/// </summary>
/// <param name="sequences">List of Sequences to be exported.</param>
/// <param name="filename">Target filename.</param>
static void ExportFastA(ICollection <ISequence> sequences, string filename)
{
// A formatter to export the output
FastAFormatter formatter = new FastAFormatter(filename);
// Exports the sequences to a file
formatter.Write(sequences);
}
/// <summary>
/// Exports a given sequence to a file in FastA format
/// </summary>
/// <param name="sequence">Sequence to be exported.</param>
/// <param name="filename">Target filename.</param>
static void ExportFastA(ISequence sequence, string filename)
{
// A formatter to export the output
FastAFormatter formatter = new FastAFormatter(filename);
// Exports the sequence to a file
formatter.Write(sequence);
}
public void FastAFormatterValidateWriteWithStream()
{
string actualSequence = string.Empty;
using (var formatter = new FastAFormatter())
{
using (var writer = new StreamWriter(Constants.FastaTempFileName))
{
formatter.Open(writer);
// Gets the actual sequence and the alphabet from the Xml
actualSequence = utilityObj.xmlUtil.GetTextValue(Constants.SimpleFastaNodeName,
Constants.ExpectedSequenceNode);
string alpName = utilityObj.xmlUtil.GetTextValue(Constants.SimpleFastaNodeName,
Constants.AlphabetNameNode);
// Logs information to the log file
ApplicationLog.WriteLine(string.Format(null,
"FastA Formatter BVT: Validating with Sequence '{0}' and Alphabet '{1}'.",
actualSequence, alpName));
var seqOriginal = new Sequence(Utility.GetAlphabet(alpName),
actualSequence);
seqOriginal.ID = "";
Assert.IsNotNull(seqOriginal);
// Use the formatter to write the original sequences to a stream.
ApplicationLog.WriteLine(string.Format(null,
"FastA Formatter BVT: Creating the Temp file '{0}'.",
Constants.FastaTempFileName));
formatter.Write(seqOriginal);
formatter.Close();
}
IEnumerable <ISequence> seq = null;
using (var reader = new StreamReader(Constants.FastaTempFileName))
{
// Read the new file, then compare the sequences
using (var parser = new FastAParser())
{
parser.Alphabet = Alphabets.Protein;
seq = parser.Parse(reader);
//Create a list of sequences.
List <ISequence> seqsList = seq.ToList();
Assert.IsNotNull(seqsList);
var seqString = new string(seqsList[0].Select(a => (char)a).ToArray());
Assert.AreEqual(actualSequence, seqString);
}
}
// Passed all the tests, delete the tmp file. If we failed an Assert,
// the tmp file will still be there in case we need it for debugging.
File.Delete(Constants.FastaTempFileName);
ApplicationLog.WriteLine("Deleted the temp file created.");
}
}
private void WriteSequences(IEnumerable <ISequence> sequences)
{
using (FastAFormatter ff = new FastAFormatter(this.OutputFile))
{
foreach (ISequence sequence in sequences)
{
ff.Write(sequence);
}
}
}
private void ValidateFormatterGeneralTestCases(string nodeName)
{
// Gets the actual sequence and the alphabet from the Xml
string expectedSequence = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.ExpectedSequenceNode);
string formattedSequence = expectedSequence.Replace("\r", "").Replace("\n", "").Replace(" ", "");
string alphabet = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.AlphabetNameNode);
// Logs information to the log file
ApplicationLog.WriteLine(string.Format(null,
"FastA Formatter : Validating with Sequence '{0}' and Alphabet '{1}'.",
expectedSequence, alphabet));
// Replacing all the empty characters, Paragraphs and null entries added
// while formatting the xml.
ISequence seqOriginal = new Sequence(Utility.GetAlphabet(alphabet), formattedSequence)
{
ID = "test"
};
Assert.IsNotNull(seqOriginal);
// Write it to a file
using (var formatter = new FastAFormatter(Constants.FastaTempFileName))
{
// Use the formatter to write the original sequences to a temp file
ApplicationLog.WriteLine(string.Format(null, "FastA Formatter : Creating the Temp file '{0}'.",
Constants.FastaTempFileName));
formatter.Write(seqOriginal);
}
// Read the new file, then compare the sequences
using (var parserObj = new FastAParser(Constants.FastaTempFileName))
{
parserObj.Alphabet = Utility.GetAlphabet(alphabet);
IEnumerable <ISequence> seqsNew = parserObj.Parse();
// Get a single sequence
ISequence seqNew = seqsNew.FirstOrDefault();
Assert.IsNotNull(seqNew);
string newSequence = seqNew.ConvertToString();
ApplicationLog.WriteLine(string.Format(null, "FastA Formatter : New Sequence is '{0}'.", newSequence));
Assert.AreEqual(formattedSequence, newSequence);
Assert.AreEqual(seqOriginal.ID, seqNew.ID);
// Verify only one sequence exists.
Assert.AreEqual(1, seqsNew.Count());
}
// Passed all the tests, delete the tmp file. If we failed an Assert,
// the tmp file will still be there in case we need it for debugging.
File.Delete(Constants.FastaTempFileName);
ApplicationLog.WriteLine("Deleted the temp file created.");
}
/// <summary>
/// Writes ambiguous reads that are filtered out to the specified file.
/// </summary>
/// <param name="ambiguousReads">Reads with ambiguous symbols.</param>
/// <param name="ambiguousFilename">File to write.</param>
private static void WriteAmbiguousReads(BlockingCollection <ISequence> ambiguousReads, string ambiguousFilename)
{
FastAFormatter formatter = new FastAFormatter(ambiguousFilename);
while (!ambiguousReads.IsCompleted)
{
ISequence seq;
if (ambiguousReads.TryTake(out seq, -1))
{
formatter.Write(seq);
formatter.Flush();
}
}
formatter.Close();
}
static void OldMain(string[] args)
{
StreamWriter SW = new StreamWriter(HOME + "CountsByDate.csv");
StreamReader SR = new StreamReader("FileLocations.csv");
string[] lines = SR.ReadToEnd().Split('\n');
lines = lines.Skip(1).ToArray();
// Parallel.ForEach(lines, line =>
Console.WriteLine("Starting");
foreach (string line in lines)
{
Console.WriteLine(line);
try
{
string[] split = line.Split(',');
string fname = split[0];
string patientid = split[1];
string date = split[2];
var mtReads = MitoDataGrabber.OutputMitoReadsFromBamFile(fname);
FastAFormatter fao = new FastAFormatter(HOME + patientid + ".fa");
long count = 0;
foreach (var seq in mtReads)
{
count++;
fao.Write(seq);
}
fao.Close();
FileInfo FI = new FileInfo(fname);
string size = FI.Length.ToString();
lock (SW)
{
SW.WriteLine(String.Join(",", patientid, count.ToString(), size, date));
Console.WriteLine(patientid + " has " + count.ToString() + " reads");
}
if (args.Length > 2)
{
break;
}
}
catch (Exception thrown)
{ Console.WriteLine(thrown.Message); }
}
//);
SW.Close();
}
private void WriteSequences(IEnumerable <ISequence> sequences)
{
if (!string.IsNullOrEmpty(this.OutputFile))
{
using (FastAFormatter ff = new FastAFormatter(this.OutputFile))
{
foreach (ISequence sequence in sequences)
{
ff.Write(sequence);
}
}
}
else
{
foreach (ISequence sequence in sequences)
{
Console.WriteLine(new string(sequence.Select(a => (char)a).ToArray()));
}
}
}
/// <summary>
/// It writes Contigs to the file.
/// </summary>
/// <param name="scaffolds">The list of scaffolds sequence.</param>
private void WriteContigs(IList <ISequence> scaffolds)
{
if (scaffolds.Count == 0)
{
Output.WriteLine(OutputLevel.Information, "No Scaffolds generated.");
return;
}
EnsureContigNames(scaffolds);
if (!string.IsNullOrEmpty(this.OutputFile))
{
using (FastAFormatter formatter = new FastAFormatter(this.OutputFile))
{
formatter.AutoFlush = true;
foreach (ISequence seq in scaffolds)
{
formatter.Write(seq);
}
}
Output.WriteLine(OutputLevel.Information, "Wrote {0} scaffolds to {1}", scaffolds.Count, this.OutputFile);
}
else
{
Output.WriteLine(OutputLevel.Information, "Scaffold Results: {0} sequences", scaffolds.Count);
using (FastAFormatter formatter = new FastAFormatter())
{
formatter.Open(new StreamWriter(Console.OpenStandardOutput()));
formatter.MaxSymbolsAllowedPerLine = Math.Min(80, Console.WindowWidth - 2);
formatter.AutoFlush = true;
foreach (ISequence seq in scaffolds)
{
formatter.Write(seq);
}
}
}
}
/// <summary>
/// It Writes the contigs to the file.
/// </summary>
/// <param name="assembly">IDeNovoAssembly parameter is the result of running De Novo Assembly on a set of two or more sequences. </param>
protected void WriteContigs(IDeNovoAssembly assembly)
{
if (assembly.AssembledSequences.Count == 0)
{
Output.WriteLine(OutputLevel.Results, "No sequences assembled.");
return;
}
EnsureContigNames(assembly.AssembledSequences);
if (!string.IsNullOrEmpty(this.OutputFile))
{
using (FastAFormatter formatter = new FastAFormatter(this.OutputFile))
{
formatter.AutoFlush = true;
foreach (ISequence seq in assembly.AssembledSequences)
{
formatter.Write(seq);
}
}
Output.WriteLine(OutputLevel.Information, "Wrote {0} sequences to {1}", assembly.AssembledSequences.Count, this.OutputFile);
}
else
{
Output.WriteLine(OutputLevel.Information, "Assembled Sequence Results: {0} sequences", assembly.AssembledSequences.Count);
using (FastAFormatter formatter = new FastAFormatter())
{
formatter.Open(new StreamWriter(Console.OpenStandardOutput()));
formatter.MaxSymbolsAllowedPerLine = Math.Min(80, Console.WindowWidth - 2);
formatter.AutoFlush = true;
foreach (ISequence seq in assembly.AssembledSequences)
{
formatter.Write(seq);
}
}
}
}
public void OutputMTReads()
{
if (String.IsNullOrEmpty(Filename))
{
throw new ArgumentNullException("No input file specified");
}
if (!Filename.EndsWith(BAM_FILE_SUFFIX))
{
throw new ArgumentNullException("Input file must be a .BAM file");
}
if (string.IsNullOrEmpty(OutputFile))
{
OutputFile = Filename.Remove(Filename.Length - BAM_FILE_SUFFIX.Length) + DEFAULT_EXPORT_SUFFIX;
}
IEnumerable <ISequence> mtReads;
if (CRSAlignedOnly)
{
mtReads = MitoDataGrabber.OutputMitoReadsFromBamFileAlignedToCRSOnly(Filename, pfractionToOutput);
}
else
{
mtReads = MitoDataGrabber.OutputMitoReadsFromBamFile(Filename);
}
FastAFormatter fao = new FastAFormatter(OutputFile);
long count = 0;
foreach (var seq in mtReads)
{
count++;
fao.Write(seq);
}
fao.Close();
FileInfo FI = new FileInfo(OutputFile);
Console.WriteLine("Wrote " + count.ToString() + " reads to output file.");
Console.WriteLine("Of Size: " + GetMTDataFromBAM.Program.FormatMemorySize(FI.Length));
}
/// <summary>
/// It Writes the contigs to the file.
/// </summary>
/// <param name="assembly">IDeNovoAssembly parameter is the result of running De Novo Assembly on a set of two or more sequences. </param>
/// <param name="outputWriter">A TextWriter to which the output will be written to.</param>
protected void WriteContigs(IEnumerable <ISequence> assembly, TextWriter outputWriter)
{
if (!string.IsNullOrEmpty(this.OutputFile))
{
using (FastAFormatter formatter = new FastAFormatter(this.OutputFile))
{
formatter.AutoFlush = true;
foreach (ISequence seq in assembly)
{
formatter.Write(seq);
}
}
}
else
{
foreach (ISequence seq in assembly)
{
outputWriter.WriteLine(seq.ID);
outputWriter.WriteLine(new string(seq.Select(a => (char)a).ToArray()));
}
}
}
/// <summary>
/// It writes Contigs to the file.
/// </summary>
/// <param name="scaffolds">The list of scaffolds sequence.</param>
private void WriteContigs(IEnumerable <ISequence> scaffolds)
{
if (!string.IsNullOrEmpty(this.OutputFile))
{
using (FastAFormatter formatter = new FastAFormatter(this.OutputFile))
{
formatter.AutoFlush = true;
foreach (ISequence seq in scaffolds)
{
formatter.Write(seq);
}
}
}
else
{
foreach (ISequence seq in scaffolds)
{
Console.WriteLine(seq.ID);
Console.WriteLine(new string(seq.Select(a => (char)a).ToArray()));
}
}
}
/// <summary>
/// It Writes the contigs to the file.
/// </summary>
/// <param name="assembly">IDeNovoAssembly parameter is the result of running De Novo Assembly on a set of two or more sequences. </param>
protected void WriteContigs(IDeNovoAssembly assembly)
{
if (!string.IsNullOrEmpty(this.OutputFile))
{
using (FastAFormatter formatter = new FastAFormatter(this.OutputFile))
{
formatter.AutoFlush = true;
foreach (ISequence seq in assembly.AssembledSequences)
{
formatter.Write(seq);
}
}
}
else
{
foreach (ISequence seq in assembly.AssembledSequences)
{
Console.WriteLine(seq.ID);
Console.WriteLine(new string(seq.Select(a => (char)a).ToArray()));
}
}
}
/// <summary>
/// It Writes the contigs to the file.
/// </summary>
/// <param name="assembly">IDeNovoAssembly parameter is the result of running De Novo Assembly on a set of two or more sequences. </param>
protected void WriteContigs(IEnumerable <ISequence> assembly)
{
int counter = 1;
if (!string.IsNullOrEmpty(this.OutputFile))
{
using (FastAFormatter formatter = new FastAFormatter(this.OutputFile))
{
formatter.AutoFlush = true;
foreach (ISequence seq in assembly)
{
if (string.IsNullOrEmpty(seq.ID))
{
seq.ID = GenerateSequenceId(counter);
}
formatter.Write(seq);
counter++;
}
}
Output.WriteLine(OutputLevel.Information, Resources.OutPutWrittenToFileSpecified);
}
else
{
Output.WriteLine(OutputLevel.Information, "Assembled Sequence Results:");
foreach (ISequence seq in assembly)
{
if (string.IsNullOrEmpty(seq.ID))
{
seq.ID = GenerateSequenceId(counter);
}
Output.WriteLine(OutputLevel.Results, seq.ID);
Output.WriteLine(OutputLevel.Results, new string(seq.Select(a => (char)a).ToArray()));
counter++;
}
}
}
void ValidateParseFormatGeneralTestCases(string nodeName)
{
// Gets the expected sequence from the Xml
string filePath = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.FilePathNode);
string alphabet = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.AlphabetNameNode);
Assert.IsTrue(File.Exists(filePath));
// Logs information to the log file
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"FastA Formatter : File Exists in the Path '{0}'.",
filePath));
string filepathTmp = "tmp.ffn";
using (FastAParser parserObj = new FastAParser(filePath))
{
using (FastAFormatter formatter = new FastAFormatter(filepathTmp))
{
// Read the original file
IEnumerable <ISequence> seqsOriginal = null;
parserObj.Alphabet = Utility.GetAlphabet(alphabet);
seqsOriginal = parserObj.Parse();
Assert.IsNotNull(seqsOriginal);
// Use the formatter to write the original sequences to a temp file
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"FastA Formatter : Creating the Temp file '{0}'.",
filepathTmp));
foreach (Sequence s in seqsOriginal)
{
formatter.Write(s);
}
formatter.Close();
using (FastAParser parserObjNew = new FastAParser(filepathTmp))
{
// Read the new file, then compare the sequences
IEnumerable <ISequence> seqsNew = null;
parserObjNew.Alphabet = Utility.GetAlphabet(alphabet);
seqsNew = parserObjNew.Parse();
Assert.IsNotNull(seqsNew);
char[] seqString = seqsNew.ElementAt(0).Select(a => (char)a).ToArray();
string newSequence = new string(seqString);
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"FastA Formatter : New Sequence is '{0}'.",
newSequence));
// Now compare the sequences.
int countOriginal = seqsOriginal.Count();
int countNew = seqsNew.Count();
Assert.AreEqual(countOriginal, countNew);
ApplicationLog.WriteLine("FastA Formatter :The Number of sequences are matching.");
int i;
for (i = 0; i < countOriginal; i++)
{
Assert.AreEqual(seqsOriginal.ElementAt(i).ID, seqsNew.ElementAt(i).ID);
string orgSeq = new string(seqsOriginal.ElementAt(i).Select(a => (char)a).ToArray());
string newSeq = new string(seqsNew.ElementAt(i).Select(a => (char)a).ToArray());
Assert.AreEqual(orgSeq, newSeq);
Console.WriteLine(
string.Format((IFormatProvider)null,
"FastA Formatter : The FASTA sequences '{0}' are matching with Format() method and is as expected.",
seqsNew.ElementAt(i).ID));
ApplicationLog.WriteLine(
string.Format((IFormatProvider)null, "FastA Formatter : The FASTA sequences '{0}' are matching with Format() method.",
seqsNew.ElementAt(i).ID));
}
// Passed all the tests, delete the tmp file. If we failed an Assert,
// the tmp file will still be there in case we need it for debugging.
parserObjNew.Close();
}
File.Delete(filepathTmp);
ApplicationLog.WriteLine("Deleted the temp file created.");
}
}
}
/// <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(string.Format("Processing the file '{0}'.", inputFile));
// Read the inputfile with the help of FastA Parser
using (FastAParser parserObj = new FastAParser(inputFile))
{
using (FastAFormatter outputWriter = new FastAFormatter(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(string.Format("Character '{0}' repeated more than '{1}' times and read '{2}' is skipped",
(char)previousChar, repeatLength, seq.ID));
ignoreRead = true;
break;
}
else
{
continue;
}
}
else
{
repeatLenCount = 0;
previousChar = actualRead[j];
continue;
}
}
Console.WriteLine(string.Format("Read '{0}' Processed.", seq.ID));
// Check if the length exceeds the max length and write it to the output file
if (!ignoreRead)
{
outputWriter.Write(seq);
}
}
}
}
Console.WriteLine();
Console.WriteLine("Filtering Completed!!");
}
else
{
Console.WriteLine("Enter Valid File Path.");
}
}
/// <summary>
/// Does the logic behind the sequence simulation
/// </summary>
internal void DoSimulation(SimulatorWindow window, string outputFileName, SimulatorSettings settings)
{
FileInfo file = new FileInfo(outputFileName);
if (!file.Directory.Exists)
{
throw new ArgumentException("Could not write to the output directory for " + outputFileName);
}
if (settings.OutputSequenceCount <= 0)
{
throw new ArgumentException("'Max Output Sequences Per File' should be greater than zero.");
}
if (settings.SequenceLength <= 0)
{
throw new ArgumentException("'Mean Output Length' should be greater than zero.");
}
string filePrefix;
if (String.IsNullOrEmpty(file.Extension))
{
filePrefix = file.FullName;
}
else
{
filePrefix = file.FullName.Substring(0, file.FullName.IndexOf(file.Extension));
}
string filePostfix = "_{0}.fa";
long seqCount = (settings.DepthOfCoverage * SequenceToSplit.Count) / settings.SequenceLength;
long fileCount = seqCount / settings.OutputSequenceCount;
if (seqCount % settings.OutputSequenceCount != 0)
{
fileCount++;
}
window.UpdateSimulationStats(seqCount, fileCount);
if (generatedSequenceList == null)
{
generatedSequenceList = new List <ISequence>();
}
else
{
generatedSequenceList.Clear();
}
int fileIndex = 1;
FastAFormatter formatter = null;
for (long i = 0; i < seqCount; i++)
{
generatedSequenceList.Add(CreateSubsequence(settings, i));
if (generatedSequenceList.Count >= settings.OutputSequenceCount)
{
FileInfo outFile = new FileInfo(filePrefix + string.Format(filePostfix, fileIndex++));
formatter = new FastAFormatter(outFile.FullName);
foreach (ISequence seq in generatedSequenceList)
{
formatter.Write(seq);
}
formatter.Close();
generatedSequenceList.Clear();
}
}
if (generatedSequenceList.Count > 0)
{
FileInfo outFile = new FileInfo(filePrefix + string.Format(filePostfix, fileIndex++));
formatter = new FastAFormatter(outFile.FullName);
foreach (ISequence seq in generatedSequenceList)
{
formatter.Write(seq);
}
formatter.Close();
window.NotifySimulationComplete(formatter.Name);
}
else
{
window.NotifySimulationComplete(string.Empty);
}
}
/// <summary>
/// Does the logic behind the sequence simulation
/// </summary>
public void DoSimulation(string outputFileName, Action <long, long> updateSimulationStats, Action <string> simulationComplete)
{
const string filePostfix = "_{0}.fa";
FileInfo file = new FileInfo(outputFileName);
if (file.Directory == null || !file.Directory.Exists)
{
throw new ArgumentException("Could not write to the output directory for " + outputFileName);
}
if (Settings.OutputSequenceCount <= 0)
{
throw new ArgumentException("'Max Output Sequences Per File' should be greater than zero.");
}
if (Settings.SequenceLength <= 0)
{
throw new ArgumentException("'Mean Output Length' should be greater than zero.");
}
string filePrefix = String.IsNullOrEmpty(file.Extension) ? file.FullName : file.FullName.Substring(0, file.FullName.IndexOf(file.Extension));
long seqCount = (Settings.DepthOfCoverage * SequenceToSplit.Count) / Settings.SequenceLength;
long fileCount = seqCount / Settings.OutputSequenceCount;
if (seqCount % Settings.OutputSequenceCount != 0)
{
fileCount++;
}
// Update the UI
updateSimulationStats(seqCount, fileCount);
int fileIndex = 1;
FastAFormatter formatter = null;
List <ISequence> generatedSequenceList = new List <ISequence>();
for (long i = 0; i < seqCount; i++)
{
generatedSequenceList.Add(CreateSubsequence(i, SequenceToSplit, Settings));
if (generatedSequenceList.Count >= Settings.OutputSequenceCount)
{
FileInfo outFile = new FileInfo(filePrefix + string.Format(filePostfix, fileIndex++));
formatter = new FastAFormatter(outFile.FullName);
foreach (ISequence seq in generatedSequenceList)
{
formatter.Write(seq);
}
formatter.Close();
generatedSequenceList.Clear();
}
}
// Pick off any remaining sequences into the final file.
if (generatedSequenceList.Count > 0)
{
FileInfo outFile = new FileInfo(filePrefix + string.Format(filePostfix, fileIndex++));
formatter = new FastAFormatter(outFile.FullName);
foreach (ISequence seq in generatedSequenceList)
{
formatter.Write(seq);
}
formatter.Close();
simulationComplete(formatter.Name);
}
// Either we ended exactly on the boundary with no additional sequences
// generated, OR we never generated any files.
else
{
simulationComplete(formatter != null ? formatter.Name : string.Empty);
}
}
/// <summary>
/// Save to disk a list of sequences in FASTA format.
/// </summary>
/// <param name="sequences"></param>
/// <param name="saveFilename"></param>
public static string SaveSequencesAsFasta(List <ISequence> sequences, string saveFilename, bool appendSequenceCountToFilename = true, FileExistsHandler.FileExistsOptions fileExistsOptions = FileExistsHandler.FileExistsOptions.AppendNumberToFilename, ProgressActionSet progressActionSet = null)
{
if (sequences == null) // || sequences.Count == 0)
{
throw new ArgumentOutOfRangeException(nameof(sequences));
}
if (string.IsNullOrWhiteSpace(saveFilename))
{
throw new ArgumentOutOfRangeException(nameof(saveFilename));
}
string result = null; // new List<string>();
if (appendSequenceCountToFilename)
{
saveFilename = AddSequenceAndProteinCountToFilename(sequences, saveFilename);
}
// make sure directory exists
var fileInfo = new FileInfo(saveFilename);
if (fileInfo.Exists)
{
if (fileExistsOptions == FileExistsHandler.FileExistsOptions.AppendNumberToFilename)
{
fileInfo = new FileInfo(FileExistsHandler.FindNextFreeOutputFilename(fileInfo.FullName));
if (progressActionSet != null)
{
ProgressActionSet.Report("Save sequence: already exists, appended number: " + fileInfo.FullName, progressActionSet);
}
}
else if (fileExistsOptions == FileExistsHandler.FileExistsOptions.OverwriteFile)
{
if (progressActionSet != null)
{
ProgressActionSet.Report("Save sequence: overwriting file: " + fileInfo.FullName, progressActionSet);
}
}
else if (fileExistsOptions == FileExistsHandler.FileExistsOptions.SkipFile)
{
if (progressActionSet != null)
{
ProgressActionSet.Report("Save sequence: skipped file, already exists: " + fileInfo.FullName, progressActionSet);
}
return(result);
}
}
else
{
if (progressActionSet != null)
{
ProgressActionSet.Report("Save sequence: new file: " + fileInfo.FullName, progressActionSet);
}
}
if (fileInfo.Directory != null)
{
fileInfo.Directory.Create();
}
var formatter = new FastAFormatter(fileInfo.FullName);
formatter.Write(sequences);
formatter.Close();
result = fileInfo.FullName;
return(result);
}
void ValidateFormatterGeneralTestCases(string nodeName)
{
using (FastAFormatter formatter = new FastAFormatter(Constants.FastaTempFileName))
{
// Gets the actual sequence and the alphabet from the Xml
string actualSequence = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.ExpectedSequenceNode);
string formattedActualSequence = actualSequence.Replace("\r", "").Replace("\n", "").Replace(" ", "");
string alphabet = utilityObj.xmlUtil.GetTextValue(nodeName,
Constants.AlphabetNameNode);
// Logs information to the log file
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"FastA Formatter : Validating with Sequence '{0}' and Alphabet '{1}'.",
actualSequence, alphabet));
// Replacing all the empty characters, Paragraphs and null entries added
// while formatting the xml.
Sequence seqOriginal = new Sequence(Utility.GetAlphabet(alphabet),
encodingObj.GetBytes(actualSequence.Replace("\r", "").Replace("\n", "").Replace(" ", "")));
seqOriginal.ID = "";
Assert.IsNotNull(seqOriginal);
// Use the formatter to write the original sequences to a temp file
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"FastA Formatter : Creating the Temp file '{0}'.",
Constants.FastaTempFileName));
formatter.Write(seqOriginal);
formatter.Close();
// Read the new file, then compare the sequences
IEnumerable <ISequence> seqsNew = null;
using (FastAParser parserObj = new FastAParser(Constants.FastaTempFileName))
{
parserObj.Alphabet = Utility.GetAlphabet(alphabet);
seqsNew = parserObj.Parse();
char[] seqString = seqsNew.ElementAt(0).Select(a => (char)a).ToArray();
string newSequence = new string(seqString);
Assert.IsNotNull(seqsNew);
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"FastA Formatter : New Sequence is '{0}'.",
newSequence));
// Now compare the sequences.
int countNew = seqsNew.Count();
Assert.AreEqual(1, countNew);
ApplicationLog.WriteLine("The Number of sequences are matching.");
Assert.AreEqual(seqOriginal.ID, seqsNew.ElementAt(0).ID);
Assert.AreEqual(formattedActualSequence, newSequence);
Console.WriteLine(string.Format((IFormatProvider)null,
"FastA Formatter : The FASTA sequences '{0}' are matching with Format() method and is as expected.",
newSequence));
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"FastA Formatter : The FASTA sequences '{0}' are matching with Format() method.",
newSequence));
}
// Passed all the tests, delete the tmp file. If we failed an Assert,
// the tmp file will still be there in case we need it for debugging.
File.Delete(Constants.FastaTempFileName);
ApplicationLog.WriteLine("Deleted the temp file created.");
}
}