public void FastQFormatter()
{
string filepathOriginal = @"TestUtils\FASTQ\SRR002012_5.fastq";
Assert.IsTrue(File.Exists(filepathOriginal));
IList <QualitativeSequence> seqsOriginal = null;
string filepathTmp = Path.GetTempFileName();
using (FastQParser parser = new FastQParser())
{
parser.Open(filepathOriginal);
// Read the original file
seqsOriginal = parser.Parse().ToList();
Assert.IsNotNull(seqsOriginal);
// Use the formatter to write the original sequences to a temp file
using (FastQFormatter formatter = new FastQFormatter(filepathTmp))
{
foreach (QualitativeSequence s in seqsOriginal)
{
formatter.Write(s);
}
}
}
// Read the new file, then compare the sequences
IList <QualitativeSequence> seqsNew = null;
using (FastQParser parser = new FastQParser(filepathTmp))
{
seqsNew = parser.Parse().ToList();
Assert.IsNotNull(seqsNew);
// Now compare the sequences.
int countOriginal = seqsOriginal.Count();
int countNew = seqsNew.Count();
Assert.AreEqual(countOriginal, countNew);
int i;
for (i = 0; i < countOriginal; i++)
{
Assert.AreEqual(seqsOriginal[i].ID, seqsNew[i].ID);
string orgSeq = ASCIIEncoding.ASCII.GetString(seqsOriginal[i].ToArray());
string newSeq = ASCIIEncoding.ASCII.GetString(seqsNew[i].ToArray());
string orgscores = ASCIIEncoding.ASCII.GetString(seqsOriginal[i].GetEncodedQualityScores());
string newscores = ASCIIEncoding.ASCII.GetString(seqsNew[i].GetEncodedQualityScores());
Assert.AreEqual(orgSeq, newSeq);
Assert.AreEqual(orgscores, newscores);
}
// 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(filepathTmp);
}
}
/// <summary>
/// General method to validate FastQ Formatter on a Stream.
/// <param name="nodeName">xml node name.</param>
/// </summary>
void ValidateFastQFormatterOnAStream(string nodeName)
{
// Gets the expected sequence from the Xml
string filePath = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.FilePathNode);
string expectedQualitativeSequence = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.ExpectedSequenceNode);
string expectedSequenceId = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.SequenceIdNode);
string tempFileName1 = System.IO.Path.GetTempFileName();
string parsedValue = string.Empty;
string parsedID = string.Empty;
IEnumerable <QualitativeSequence> qualSequence = null;
// Parse a FastQ file using parseOne method.
using (FastQParser fastQParserObj = new FastQParser(filePath))
{
fastQParserObj.AutoDetectFastQFormat = false;
qualSequence = fastQParserObj.Parse();
// New Sequence after formatting file.
IEnumerable <QualitativeSequence> newQualSeq = null;
using (StreamWriter writer = new StreamWriter(tempFileName1))
{
using (FastQFormatter fastQFormatter = new FastQFormatter())
{
fastQFormatter.Open(writer);
fastQFormatter.Write(qualSequence.ElementAt(0));
}
}
using (FastQParser fastQParserObjTemp = new FastQParser(tempFileName1))
{
newQualSeq = fastQParserObjTemp.Parse();
parsedValue = new string(newQualSeq.ElementAt(0).Select(a => (char)a).ToArray());
parsedID = newQualSeq.ElementAt(0).ID.ToString((IFormatProvider)null);
}
// Validate qualitative parsing temporary file.
Assert.AreEqual(parsedValue, expectedQualitativeSequence);
Assert.AreEqual(parsedID, expectedSequenceId);
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"FastQ Formatter BVT: The FASTQ sequence '{0}' validation after Write() and Parse() is found to be as expected.",
parsedValue));
// Logs to the VSTest GUI (Console.Out) window
Console.WriteLine(string.Format((IFormatProvider)null,
"FastQ Formatter BVT: The FASTQ sequence '{0}' validation after Write() and Parse() is found to be as expected.",
parsedValue));
Console.WriteLine(string.Format((IFormatProvider)null,
"FastQ Formatter BVT: The FASTQ sequence '{0}' validation after Write() and Parse() is found to be as expected.",
parsedID));
qualSequence = null;
File.Delete(tempFileName1);
}
}
void InValidateFastQFormatter(FastQFormatParameters param)
{
// Gets the expected sequence from the Xml
string filepath = utilityObj.xmlUtil.GetTextValue(
Constants.MultiSeqSangerRnaProNode, Constants.FilePathNode);
// Parse a FastQ file.
using (FastQParser fastQParser = new FastQParser(filepath))
{
fastQParser.AutoDetectFastQFormat = true;
IEnumerable <QualitativeSequence> sequence = null;
FastQFormatter fastQFormatter = null;
switch (param)
{
case FastQFormatParameters.Sequence:
try
{
fastQFormatter = new FastQFormatter(filepath);
fastQFormatter.Write(null as ISequence);
Assert.Fail();
}
catch (ArgumentNullException)
{
fastQFormatter.Close();
ApplicationLog.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
Console.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
}
break;
default:
try
{
sequence = fastQParser.Parse();
fastQFormatter = new FastQFormatter(Constants.FastQTempFileName);
fastQFormatter.Write(sequence as QualitativeSequence);
Assert.Fail();
}
catch (ArgumentNullException)
{
fastQFormatter.Close();
ApplicationLog.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
Console.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
}
break;
}
}
}
static void Main(string[] args)
{
FastAParser fap = new FastAParser(@"D:\TestMixing\CRS.rn.fasta");
FastQFormatter faq = new FastQFormatter(@"D:\TestMixing\RefSeq.fastq");
var seq = fap.Parse().First() as Sequence;
seq = seq.GetSubSequence(1000, 300) as Sequence;
int coverage = 50;
int len = 75;
byte[] QualScores = Enumerable.Range(0, len).Select(x => (byte)(33 + 35)).ToArray();
for (int i = 0; i < (seq.Count - len); i++)
{
//string s=seq.GetSubSequence(i,len).ToString();
string s = (seq as Sequence).ConvertToString(i, len);
int hh = s.Length;
byte[] sb = Encoding.UTF8.GetBytes(s);
for (int j = 0; j < coverage; j++)
{
QualitativeSequence qs = new QualitativeSequence(Alphabets.DNA, FastQFormatType.Illumina_v1_8, sb, QualScores);
qs.ID = "REF-" + i.ToString();
faq.Write(qs);
}
}
faq.Close();
fap.Close();
byte[] newSeq = new byte[seq.Count];
seq.CopyTo(newSeq, 0, seq.Count);
byte oldBase = seq[seq.Count / 2];
newSeq[newSeq.Length / 2] = 65;
//now mutate one base and go again
Sequence nonRef = new Sequence(Alphabets.DNA, newSeq, true);
faq = new FastQFormatter(@"D:\TestMixing\NonRefSeq.fastq");
for (int i = 0; i < (seq.Count - len); i++)
{
//string s=seq.GetSubSequence(i,len).ToString();
string s = (nonRef as Sequence).ConvertToString(i, len);
int hh = s.Length;
byte[] sb = Encoding.UTF8.GetBytes(s);
for (int j = 0; j < coverage; j++)
{
QualitativeSequence qs = new QualitativeSequence(Alphabets.DNA, FastQFormatType.Illumina_v1_8, sb, QualScores);
qs.ID = "NONREF-" + i.ToString();
faq.Write(qs);
}
}
faq.Close();
}
private void ValidateFastQFormatter(string nodeName,
FastQFileParameters fileExtension)
{
// Gets the expected sequence from the Xml
string filePath = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.FilePathNode);
string expectedQualitativeSequence = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.ExpectedSequenceNode);
string expectedSequenceId = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.SequenceIdNode);
string tempFileName = Path.GetTempFileName();
// Parse a FastQ file using parseOne method.
using (var fastQParserObj = new FastQParser(filePath))
{
IEnumerable <QualitativeSequence> qualSequence = null;
qualSequence = fastQParserObj.Parse();
// New Sequence after formatting file.
IEnumerable <QualitativeSequence> newQualSeq = null;
string parsedValue = null;
string parsedID = null;
// Format Parsed Sequence to temp file with different extension.
switch (fileExtension)
{
case FastQFileParameters.FastQ:
using (var fastQFormatter = new FastQFormatter(tempFileName))
{
fastQFormatter.Write(qualSequence.ElementAt(0));
}
using (var fastQParserObjTemp = new FastQParser(tempFileName))
{
newQualSeq = fastQParserObjTemp.Parse();
parsedValue = new string(newQualSeq.ElementAt(0).Select(a => (char)a).ToArray());
parsedID = newQualSeq.ElementAt(0).ID.ToString(null);
}
break;
case FastQFileParameters.Fq:
using (var fastQFormatterFq = new FastQFormatter(tempFileName))
{
fastQFormatterFq.Write(qualSequence.ElementAt(0));
}
using (var fastQParserObjTemp1 = new FastQParser(tempFileName))
{
newQualSeq = fastQParserObjTemp1.Parse();
parsedValue = new string(newQualSeq.ElementAt(0).Select(a => (char)a).ToArray());
parsedID = newQualSeq.ElementAt(0).ID.ToString(null);
}
break;
default:
break;
}
// Validate qualitative parsing temporary file.
Assert.AreEqual(parsedValue, expectedQualitativeSequence);
Assert.AreEqual(parsedID, expectedSequenceId);
ApplicationLog.WriteLine(string.Format(null,
"FastQ Formatter BVT: The FASTQ sequence '{0}' validation after Write() and Parse() is found to be as expected.",
parsedValue));
ApplicationLog.WriteLine(string.Format(null,
"FastQ Formatter BVT: The FASTQ sequence '{0}' validation after Write() and Parse() is found to be as expected.",
parsedID));
qualSequence = null;
File.Delete(tempFileName);
}
}
void ValidateFastQFormatter(string nodeName,
FastQFileParameters fileExtension)
{
// Gets the expected sequence from the Xml
string filePath = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.FilePathNode);
string expectedQualitativeSequence = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.ExpectedSequenceNode);
string expectedSequenceId = utilityObj.xmlUtil.GetTextValue(
nodeName, Constants.SequenceIdNode);
string tempFileName1 = System.IO.Path.GetTempFileName();
string tempFileName2 = System.IO.Path.GetTempFileName();
// Parse a FastQ file using parseOne method.
using (FastQParser fastQParserObj = new FastQParser(filePath))
{
fastQParserObj.AutoDetectFastQFormat = false;
IEnumerable <ISequence> qualSequence = null;
qualSequence = fastQParserObj.Parse();
// New Sequence after formatting file.
IEnumerable <ISequence> newQualSeq = null;
FastQFormatter fastQFormatter = new FastQFormatter(tempFileName1);
FastQFormatter fastQFormatterFq = new FastQFormatter(tempFileName2);
string parsedValue = null;
string parsedID = null;
// Format Parsed Sequence to temp file with different extension.
switch (fileExtension)
{
case FastQFileParameters.FastQ:
fastQFormatter.Write(qualSequence.ElementAt(0));
fastQFormatter.Close();
FastQParser fastQParserObjTemp = new FastQParser(tempFileName1);
newQualSeq = fastQParserObjTemp.Parse();
parsedValue = new string(newQualSeq.ElementAt(0).Select(a => (char)a).ToArray());
parsedID = newQualSeq.ElementAt(0).ID.ToString((IFormatProvider)null);
fastQParserObjTemp.Dispose();
break;
case FastQFileParameters.Fq:
fastQFormatterFq.Write(qualSequence.ElementAt(0));
fastQFormatterFq.Close();
FastQParser fastQParserObjTemp1 = new FastQParser(tempFileName2);
newQualSeq = fastQParserObjTemp1.Parse();
parsedValue = new string(newQualSeq.ElementAt(0).Select(a => (char)a).ToArray());
parsedID = newQualSeq.ElementAt(0).ID.ToString((IFormatProvider)null);
break;
default:
break;
}
// Validate qualitative parsing temporary file.
Assert.AreEqual(parsedValue, expectedQualitativeSequence);
Assert.AreEqual(parsedID, expectedSequenceId);
ApplicationLog.WriteLine(string.Format((IFormatProvider)null,
"FastQ Formatter BVT: The FASTQ sequence '{0}' validation after Write() and Parse() is found to be as expected.",
parsedValue));
// Logs to the NUnit GUI (Console.Out) window
Console.WriteLine(string.Format((IFormatProvider)null,
"FastQ Formatter BVT: The FASTQ sequence '{0}' validation after Write() and Parse() is found to be as expected.",
parsedValue));
Console.WriteLine(string.Format((IFormatProvider)null,
"FastQ Formatter BVT: The FASTQ sequence '{0}' validation after Write() and Parse() is found to be as expected.",
parsedID));
qualSequence = null;
fastQFormatter = null;
fastQFormatterFq = null;
GC.Collect();
GC.WaitForPendingFinalizers();
File.Delete(tempFileName1);
File.Delete(tempFileName2);
}
}
