/// <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))
{
FastAFormatter formatter = new FastAFormatter { AutoFlush = true };
using (formatter.Open(this.OutputFile))
{
foreach (ISequence seq in assembly)
{
if (string.IsNullOrEmpty(seq.ID))
seq.ID = GenerateSequenceId(counter);
formatter.Format(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++;
}
}
}
/// <summary>
/// Writes the reads to StandardOutput.
/// </summary>
/// <param name="reads">Reads to write.</param>
private static void WriteOutput(IEnumerable<ISequence> reads)
{
FastAFormatter formatter = new FastAFormatter();
foreach (ISequence seq in reads)
{
Console.WriteLine(formatter.FormatString(seq));
}
}
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
var formatter = new FastAFormatter();
{
// Use the formatter to write the original sequences to a temp file
ApplicationLog.WriteLine(string.Format("FastA Formatter : Creating the Temp file '{0}'.",
Constants.FastaTempFileName));
formatter.Format(seqOriginal, Constants.FastaTempFileName);
}
// Read the new file, then compare the sequences
var parserObj = new FastAParser();
{
parserObj.Alphabet = Utility.GetAlphabet(alphabet);
IEnumerable<ISequence> seqsNew = parserObj.Parse(Constants.FastaTempFileName);
// 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>
/// 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;
var parserObj = new FastAParser();
{
// Read the original file
parserObj.Alphabet = Utility.GetAlphabet(alphabet);
seqsOriginal = parserObj.Parse(filePath).ToList();
Assert.IsFalse(seqsOriginal.Count == 0);
}
// Write to a new file
var formatter = new FastAFormatter();
formatter.Format(seqsOriginal, filepathTmp);
try
{
// Compare original with new file
var parserObjNew = new FastAParser();
{
// Read the new file, then compare the sequences
parserObjNew.Alphabet = Utility.GetAlphabet(alphabet);
IEnumerable<ISequence> seqsNew = parserObjNew.Parse(filepathTmp);
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>
public 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>
/// 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.");
}
public void FastAFormatterValidateWrite1()
{
var formatter = new FastAFormatter();
using (formatter.Open(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("FastA Formatter BVT: Validating with Sequence '{0}' and Alphabet '{1}'.",
actualSequence, alpName));
var seqOriginal = new Sequence(Utility.GetAlphabet(alpName),
actualSequence) { ID = "" };
Assert.IsNotNull(seqOriginal);
// Use the formatter to write the original sequences to a temp file
ApplicationLog.WriteLine(string.Format("FastA Formatter BVT: Creating the Temp file '{0}'.",
Constants.FastaTempFileName));
var seqList = new List<ISequence> { seqOriginal, seqOriginal, seqOriginal };
formatter.Format(seqList);
formatter.Close();
IEnumerable<ISequence> seqsNew = null;
// Read the new file, then compare the sequences
var parser = new FastAParser();
{
parser.Alphabet = Alphabets.Protein;
seqsNew = parser.Parse(Constants.FastaTempFileName);
char[] seqString = seqsNew.ElementAt(0).Select(a => (char) a).ToArray();
var newSequence = new string(seqString);
Assert.IsNotNull(seqsNew);
ApplicationLog.WriteLine(string.Format(null,
"FastA Formatter BVT: New Sequence is '{0}'.",
newSequence));
// Now compare the sequences.
int countNew = seqsNew.Count();
Assert.AreEqual(3, countNew);
ApplicationLog.WriteLine("The Number of sequences are matching.");
Assert.AreEqual(seqOriginal.ID, seqsNew.ElementAt(0).ID);
Assert.AreEqual(new string(seqsNew.ElementAt(0).Select(a => (char) a).ToArray()), newSequence);
ApplicationLog.WriteLine(string.Format(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.");
}
}
}
public void FastAFormatterInvalidateClose()
{
FastAFormatter formatter = new FastAFormatter();
formatter.Close();
}
public void FastAFormatterValidateGetSupportedFileTypes()
{
var formatter = new FastAFormatter();
string supportedFileType = formatter.SupportedFileTypes;
Assert.IsNotNull(supportedFileType);
Assert.IsTrue(supportedFileType.Contains(".fa"));
Assert.IsTrue(supportedFileType.Contains(".mpfa"));
Assert.IsTrue(supportedFileType.Contains(".fna"));
Assert.IsTrue(supportedFileType.Contains(".faa"));
Assert.IsTrue(supportedFileType.Contains(".fsa"));
Assert.IsTrue(supportedFileType.Contains(".fas"));
Assert.IsTrue(supportedFileType.Contains(".fasta"));
}
public void FastAFormatterValidateGetDescription()
{
var formatter = new FastAFormatter();
string desc = formatter.Description;
Assert.IsNotNull(desc);
}
public void FastAFormatterValidateGetName()
{
var formatter = new FastAFormatter();
string name = formatter.Name;
Assert.IsNotNull(name);
Assert.AreEqual(name, "FastA");
}
/// <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();
using (formatter.Open(outFile.FullName))
{
formatter.Format(generatedSequenceList);
}
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();
using (formatter.Open(outFile.FullName))
{
formatter.Format(generatedSequenceList);
}
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>
/// 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))
{
FastAFormatter formatter = new FastAFormatter { AutoFlush = true };
using (formatter.Open(this.OutputFile))
{
foreach (ISequence seq in assembly.AssembledSequences)
{
formatter.Format(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);
FastAFormatter formatter = new FastAFormatter {
AutoFlush = true,
MaxSymbolsAllowedPerLine = Math.Min(80, Console.WindowWidth - 2)
};
foreach (ISequence seq in assembly.AssembledSequences)
formatter.Format(Console.OpenStandardOutput(), seq);
}
}
/// <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() { AutoFlush = true };
using (formatter.Open(ambiguousFilename))
{
while (!ambiguousReads.IsCompleted)
{
ISequence seq;
if (ambiguousReads.TryTake(out seq, -1))
{
formatter.Format(seq);
}
}
}
}
public void FastAFormatterValidateWriteWithStream()
{
string actualSequence = string.Empty;
var formatter = new FastAFormatter();
{
using (formatter.Open(Constants.FastaTempFileName))
{
// 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("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("FastA Formatter BVT: Creating the Temp file '{0}'.",
Constants.FastaTempFileName));
formatter.Format(seqOriginal);
formatter.Close();
}
IEnumerable<ISequence> seq = null;
using (var reader = File.OpenRead(Constants.FastaTempFileName))
{
// Read the new file, then compare the sequences
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.");
}
}
/// <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;
var formatter = new FastAFormatter { AutoFlush = true };
using (formatter.Open(this.OutputFile))
{
foreach (ISequence sequence in sequences)
{
count++;
formatter.Format(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>
/// 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))
{
FastAFormatter formatter = new FastAFormatter { AutoFlush = true };
using (formatter.Open(this.OutputFile))
{
formatter.Format(scaffolds);
}
Output.WriteLine(OutputLevel.Information, "Wrote {0} scaffolds to {1}", scaffolds.Count, this.OutputFile);
}
else
{
Output.WriteLine(OutputLevel.Information, "Scaffold Results: {0} sequences", scaffolds.Count);
FastAFormatter formatter = new FastAFormatter {
MaxSymbolsAllowedPerLine = Math.Min(80, Console.WindowWidth - 2),
AutoFlush = true
};
formatter.Format(Console.OpenStandardOutput(), scaffolds);
}
}
