public void FastQFormatter()
{
string filepathOriginal = @"TestUtils\FASTQ\SRR002012_5.fastq";
Assert.IsTrue(File.Exists(filepathOriginal));
FastQParser parser = new FastQParser();
FastQFormatter formatter = new FastQFormatter();
// Read the original file
IList <IQualitativeSequence> seqsOriginal = null;
parser = new FastQParser();
seqsOriginal = parser.Parse(filepathOriginal);
Assert.IsNotNull(seqsOriginal);
// Use the formatter to write the original sequences to a temp file
string filepathTmp = Path.GetTempFileName();
using (TextWriter writer = new StreamWriter(filepathTmp))
{
foreach (IQualitativeSequence s in seqsOriginal)
{
formatter.Format(s, writer);
}
}
// Read the new file, then compare the sequences
IList <IQualitativeSequence> seqsNew = null;
parser = new FastQParser();
seqsNew = parser.Parse(filepathTmp);
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 = seqsOriginal[i].ToString();
string newSeq = seqsNew[i].ToString();
string orgscores = ASCIIEncoding.ASCII.GetString(seqsOriginal[i].Scores);
string newscores = ASCIIEncoding.ASCII.GetString(seqsNew[i].Scores);
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);
((FastQParser)parser).Dispose();
}
private void InValidateFastQFormatter(FastQFormatParameters param)
{
// Gets the expected sequence from the Xml
string filepath = utilityObj.xmlUtil.GetTextValue(
Constants.MultiSeqSangerRnaProNode, Constants.FilePathNode);
// Parse a FastQ file.
var fastQParser = new FastQParser();
using (fastQParser.Open(filepath))
{
FastQFormatter fastQFormatter = null;
switch (param)
{
case FastQFormatParameters.Sequence:
try
{
fastQFormatter = new FastQFormatter();
fastQFormatter.Format(null as ISequence, filepath);
Assert.Fail();
}
catch (ArgumentNullException)
{
fastQFormatter.Close();
ApplicationLog.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
}
break;
default:
try
{
IEnumerable <IQualitativeSequence> sequence = fastQParser.Parse();
fastQFormatter = new FastQFormatter();
fastQFormatter.Format(sequence, null);
Assert.Fail();
}
catch (ArgumentNullException)
{
ApplicationLog.WriteLine("FastQ Parser P2 : Successfully validated the exception");
}
break;
}
}
}
/// <summary>
/// General method to validate FastQ Formatter.
/// <param name="nodeName">xml node name.</param>
/// <param name="fileExtension">Different temporary file extensions</param>
/// </summary>
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.
var fastQParserObj = new FastQParser();
using (fastQParserObj.Open(filePath))
{
IQualitativeSequence oneSequence = fastQParserObj.ParseOne();
// Format Parsed Sequence to temp file with different extension.
var fastQFormatter = new FastQFormatter();
using (fastQFormatter.Open(tempFileName))
{
fastQFormatter.Format(oneSequence);
}
string parsedValue;
string parsedId;
var fastQParserObjTemp = new FastQParser();
using (fastQParserObjTemp.Open(tempFileName))
{
oneSequence = fastQParserObjTemp.Parse().First();
parsedValue = oneSequence.ConvertToString();
parsedId = oneSequence.ID;
}
// Validate qualitative parsing temporary file.
Assert.AreEqual(expectedQualitativeSequence, parsedValue);
Assert.AreEqual(expectedSequenceId, parsedId);
ApplicationLog.WriteLine(string.Format("FastQ Formatter BVT: The FASTQ sequence '{0}' validation after Write() and Parse() is found to be as expected.",
parsedValue));
ApplicationLog.WriteLine(string.Format("FastQ Formatter BVT: The FASTQ sequence '{0}' validation after Write() and Parse() is found to be as expected.",
parsedId));
File.Delete(tempFileName);
}
}
private void InValidateFastQFormatter(FastQFormatParameters param)
{
// Gets the expected sequence from the Xml
string filepath = utilityObj.xmlUtil.GetTextValue(
Constants.MultiSeqSangerRnaProNode, Constants.FilePathNode);
// Parse a FastQ file.
var fastQParser = new FastQParser();
using (fastQParser.Open(filepath))
{
FastQFormatter fastQFormatter = null;
switch (param)
{
case FastQFormatParameters.Sequence:
try
{
fastQFormatter = new FastQFormatter();
fastQFormatter.Format(null as ISequence, filepath);
Assert.Fail();
}
catch (ArgumentNullException)
{
fastQFormatter.Close();
ApplicationLog.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
}
break;
default:
try
{
IEnumerable<IQualitativeSequence> sequence = fastQParser.Parse();
fastQFormatter = new FastQFormatter();
fastQFormatter.Format(sequence, null);
Assert.Fail();
}
catch (ArgumentNullException)
{
ApplicationLog.WriteLine("FastQ Parser P2 : Successfully validated the exception");
}
break;
}
}
}
/// <summary>
/// General method to Invalidate FastQ Parser.
/// <param name="nodeName">xml node name.</param>
/// <param name="param">FastQ Formatter different parameters</param>
/// </summary>
void InValidateFastQFormatter(FastQFormatParameters param)
{
// Gets the expected sequence from the Xml
string filepath = _utilityObj._xmlUtil.GetTextValue(
Constants.MultiSeqSangerRnaProNode, Constants.FilePathNode);
FastQFormatType expectedFormatType = Utility.GetFastQFormatType(
_utilityObj._xmlUtil.GetTextValue(Constants.MultiSeqSangerRnaProNode,
Constants.FastQFormatType));
// Parse a FastQ file.
using (FastQParser fastQParser = new FastQParser())
{
fastQParser.AutoDetectFastQFormat = true;
fastQParser.FastqType = expectedFormatType;
IQualitativeSequence sequence = null;
sequence = fastQParser.ParseOne(filepath);
FastQFormatter fastQFormatter = new FastQFormatter();
TextWriter txtWriter = null;
switch (param)
{
case FastQFormatParameters.TextWriter:
try
{
fastQFormatter.Format(sequence, null as TextWriter);
Assert.Fail();
}
catch (Exception)
{
ApplicationLog.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
Console.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
}
break;
case FastQFormatParameters.Sequence:
try
{
fastQFormatter.Format(null as ISequence, txtWriter);
Assert.Fail();
}
catch (Exception)
{
ApplicationLog.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
Console.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
}
break;
case FastQFormatParameters.QualitativeSequence:
try
{
fastQFormatter.Format(null as IQualitativeSequence, txtWriter);
Assert.Fail();
}
catch (Exception)
{
ApplicationLog.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
Console.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
}
break;
default:
try
{
fastQFormatter.Format(sequence as QualitativeSequence, null as TextWriter);
Assert.Fail();
}
catch (Exception)
{
ApplicationLog.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
Console.WriteLine(
"FastQ Parser P2 : Successfully validated the exception");
}
break;
}
}
}
/// <summary>
/// General method to validate BasicSequence Parser.
/// <param name="nodeName">xml node name.</param>
/// </summary>
private void ValidateBasicSequenceParser(string nodeName)
{
// Gets the expected sequence from the Xml
string filepathOriginal = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.FilePathNode);
string expectedQualitativeSequence = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.ExpectedSequenceNode);
string expectedSequenceId = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.SequenceIdNode);
IAlphabet alphabet = Utility.GetAlphabet(utilityObj.xmlUtil.GetTextValue(nodeName, Constants.AlphabetNameNode));
Assert.IsTrue(File.Exists(filepathOriginal));
string tempPath = Path.GetTempFileName();
try
{
ISequenceParser fastQParserObj = SequenceParsers.FindParserByFileName("temp.fq");
// Read the original file
IEnumerable<ISequence> seqsOriginal = fastQParserObj.Parse(filepathOriginal);
Assert.IsNotNull(seqsOriginal);
// Use the formatter to write the original sequences to a temp file
var formatter = new FastQFormatter();
formatter.Format(seqsOriginal.ElementAt(0), tempPath);
// Read the new file, then compare the sequences
var fastQParserObjNew = new FastQParser();
IEnumerable<IQualitativeSequence> seqsNew = fastQParserObjNew.Parse(tempPath);
Assert.IsNotNull(seqsNew);
// Validate qualitative Sequence upon parsing FastQ file.
Assert.AreEqual(expectedQualitativeSequence,
new string(seqsOriginal.ElementAt(0).Select(a => (char) a).ToArray()));
Assert.AreEqual(
seqsOriginal.ElementAt(0).ID.ToString(null),
expectedSequenceId);
Assert.AreEqual(
seqsOriginal.ElementAt(0).Alphabet.Name,
alphabet.Name);
ApplicationLog.WriteLine(string.Format("FastQ Parser P1: The FASTQ sequence '{0}' validation after Parse() is found to be as expected.",
seqsOriginal.ElementAt(0)));
}
finally
{
File.Delete(tempPath);
}
}
private void ValidateFastQFormatter(string nodeName, bool writeMultipleSequences)
{
// 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.
var fastQParserObj = new FastQParser();
using (fastQParserObj.Open(filePath))
{
IEnumerable<IQualitativeSequence> qualSequenceList = fastQParserObj.Parse();
var fastQFormatter = new FastQFormatter();
using (fastQFormatter.Open(tempFileName))
{
if (writeMultipleSequences)
{
foreach (IQualitativeSequence newQualSeq in qualSequenceList)
{
fastQFormatter.Format(newQualSeq);
}
}
else
{
fastQFormatter.Format(qualSequenceList.First());
}
} // temp file is closed.
// Read the new file and validate the first Sequence.
FastQParser fastQParserObjNew = new FastQParser();
IQualitativeSequence firstSequence = fastQParserObjNew.ParseOne(tempFileName);
// Validate qualitative Sequence upon parsing FastQ file.
Assert.AreEqual(expectedQualitativeSequence, firstSequence.ConvertToString());
Assert.AreEqual(expectedSequenceId, firstSequence.ID);
ApplicationLog.WriteLine(string.Format("FastQ Parser P1: The FASTQ sequence '{0}' validation after Parse() is found to be as expected.", firstSequence));
File.Delete(tempFileName);
}
}
/// <summary>
/// General method to validate FastQ formatting
/// Qualitative Sequence by passing TextWriter as a parameter
/// <param name="nodeName">xml node name.</param>
/// </summary>
private void ValidateFastQFormatByFormattingQualSeqeunce(string nodeName)
{
// Gets the actual sequence and the alphabet from the Xml
IAlphabet alphabet = Utility.GetAlphabet(utilityObj.xmlUtil.GetTextValue(nodeName, Constants.AlphabetNameNodeV2));
FastQFormatType expectedFormatType = Utility.GetFastQFormatType(utilityObj.xmlUtil.GetTextValue(nodeName, Constants.FastQFormatType));
string qualSequence = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.ExpectedSequenceNode);
string expectedQualitativeSequence = utilityObj.xmlUtil.GetTextValue(nodeName, Constants.ExpectedSequenceNode);
string qualityScores = "";
int i;
for (i = 0; i < qualSequence.Length; i++)
qualityScores = qualityScores + "}";
byte[] seq = Encoding.UTF8.GetBytes(qualSequence);
byte[] qScore = Encoding.UTF8.GetBytes(qualityScores);
string tempFileName = Path.GetTempFileName();
// Create a Qualitative Sequence.
var qualSeq = new QualitativeSequence(alphabet, expectedFormatType, seq, qScore);
var formatter = new FastQFormatter();
using (formatter.Open(tempFileName))
{
formatter.Format(qualSeq);
formatter.Close();
var fastQParserObj = new FastQParser();
using (fastQParserObj.Open(tempFileName))
{
// Read the new file and validate Sequences.
var seqsNew = fastQParserObj.Parse();
var firstSequence = seqsNew.First();
// Validate qualitative Sequence upon parsing FastQ file.
Assert.AreEqual(expectedQualitativeSequence, firstSequence.ConvertToString());
Assert.IsTrue(string.IsNullOrEmpty(firstSequence.ID));
ApplicationLog.WriteLine(string.Format("FastQ Parser P1: The FASTQ sequence '{0}' validation after Parse() is found to be as expected.", firstSequence));
}
File.Delete(tempFileName);
}
}
public static void Main(string[] args)
{
try {
PlatformManager.Services.MaxSequenceSize = int.MaxValue;
PlatformManager.Services.DefaultBufferSize = 4096;
PlatformManager.Services.Is64BitProcessType = true;
if (args.Length > 3)
{
Console.WriteLine("Too many arguments");
DisplayHelp();
}
else if (args.Length < 2)
{
Console.WriteLine("Not enough arguments");
DisplayHelp();
}
else if (args [0] == "h" || args [0] == "help" || args [0] == "?" || args [0] == "-h")
{
DisplayHelp();
}
else
{
string bam_name = args [0];
string threshold = args [1];
string output = args [2];
if (!File.Exists(bam_name))
{
Console.WriteLine("Can't find file: " + bam_name);
return;
}
double min_rq;
bool converted = Double.TryParse(threshold, out min_rq);
if (!converted)
{
Console.WriteLine("Could not parse minimum threshold from : " + threshold + " expected decimal number in [0,1] interval.");
return;
}
if (min_rq < 0.0 || min_rq > 1.0)
{
Console.WriteLine("Minimum RQ value: " + min_rq + " was not in [0,1] interval.");
return;
}
if (File.Exists(output))
{
Console.WriteLine("The output file already exists, please specify a new name or delete the old one.");
return;
}
var fastq = new FastQFormatter();
fastq.FormatType = FastQFormatType.Sanger;
var os = new FileStream(output, FileMode.CreateNew);
// Filter and output
PacBioCCSBamReader bamreader = new PacBioCCSBamReader();
int numRead = 0;
int numFiltered = 0;
foreach (var read in bamreader.Parse(bam_name))
{
numRead++;
var ccs = read as PacBioCCSRead;
if (ccs.ReadQuality > min_rq)
{
//read.ID = read.ID + "/RQ=" + read.ReadQuality;
fastq.Format(os, read);
}
else
{
numFiltered++;
}
}
os.Close();
Console.WriteLine("Parsed " + numRead + " reads and filtered out " + numFiltered + " for RQ < " + min_rq);
}
}
catch (DllNotFoundException thrown) {
Console.WriteLine("Error thrown when attempting to generate the CCS results.");
Console.WriteLine("A shared library was not found. To solve this, please add the folder" +
" with the downloaded file libMonoPosixHelper" +
"to your environmental variables (LD_LIBRARY_PATH and DYLD_LIBRARY_PATH on Mac OS X).");
Console.WriteLine("Error: " + thrown.Message);
Console.WriteLine(thrown.StackTrace);
}
catch (Exception thrown) {
Console.WriteLine("Error thrown when attempting to generate the FASTQ File");
Console.WriteLine("Error: " + thrown.Message);
Console.WriteLine(thrown.StackTrace);
while (thrown.InnerException != null)
{
Console.WriteLine("Inner Exception: " + thrown.InnerException.Message);
thrown = thrown.InnerException;
}
}
}
/// <summary>
/// General method to validate FastQ Formatter on a Stream.
/// <param name="nodeName">xml node name.</param>
/// </summary>
private 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 = Path.GetTempFileName();
// Parse a FastQ file using parseOne method.
var fastQParserObj = new FastQParser();
using (fastQParserObj.Open(filePath))
{
var oneSequence = fastQParserObj.ParseOne();
// New Sequence after formatting file.
var fastQFormatter = new FastQFormatter();
using (fastQFormatter.Open(tempFileName1))
fastQFormatter.Format(oneSequence);
var fastQParserObjTemp = new FastQParser();
string parsedValue, parsedId;
using (fastQParserObjTemp.Open(tempFileName1))
{
oneSequence = fastQParserObjTemp.Parse().First();
parsedValue = oneSequence.ConvertToString();
parsedId = oneSequence.ID;
}
// Validate qualitative parsing temporary file.
Assert.AreEqual(expectedQualitativeSequence, parsedValue);
Assert.AreEqual(expectedSequenceId, parsedId);
ApplicationLog.WriteLine(string.Format("FastQ Formatter BVT: The FASTQ sequence '{0}' validation after Write() and Parse() is found to be as expected.", parsedValue));
ApplicationLog.WriteLine(string.Format("FastQ Formatter BVT: The FASTQ sequence '{0}' validation after Write() and Parse() is found to be as expected.", parsedId));
File.Delete(tempFileName1);
}
}
public static void Main(string[] args)
{
try {
PlatformManager.Services.MaxSequenceSize = int.MaxValue;
PlatformManager.Services.DefaultBufferSize = 4096;
PlatformManager.Services.Is64BitProcessType = true;
if (args.Length > 3) {
Console.WriteLine ("Too many arguments");
DisplayHelp ();
} else if (args.Length < 2) {
Console.WriteLine("Not enough arguments");
DisplayHelp();
} else if (args [0] == "h" || args [0] == "help" || args [0] == "?" || args [0] == "-h") {
DisplayHelp ();
} else {
string bam_name = args [0];
string threshold = args [1];
string output = args [2];
if (!File.Exists(bam_name)) {
Console.WriteLine ("Can't find file: " + bam_name);
return;
}
double min_rq;
bool converted = Double.TryParse(threshold, out min_rq);
if (!converted) {
Console.WriteLine ("Could not parse minimum threshold from : " + threshold + " expected decimal number in [0,1] interval.");
return;
}
if (min_rq < 0.0 || min_rq > 1.0) {
Console.WriteLine ("Minimum RQ value: " + min_rq + " was not in [0,1] interval.");
return;
}
if (File.Exists (output)) {
Console.WriteLine ("The output file already exists, please specify a new name or delete the old one.");
return;
}
var fastq = new FastQFormatter();
fastq.FormatType = FastQFormatType.Sanger;
var os = new FileStream(output, FileMode.CreateNew);
// Filter and output
PacBioCCSBamReader bamreader = new PacBioCCSBamReader ();
int numRead = 0;
int numFiltered = 0;
foreach(var read in bamreader.Parse(bam_name)) {
numRead++;
var ccs = read as PacBioCCSRead;
if (ccs.ReadQuality > min_rq) {
//read.ID = read.ID + "/RQ=" + read.ReadQuality;
fastq.Format(os,read);
}
else {
numFiltered ++;
}
}
os.Close();
Console.WriteLine("Parsed " + numRead + " reads and filtered out " + numFiltered + " for RQ < " + min_rq);
}
}
catch(DllNotFoundException thrown) {
Console.WriteLine ("Error thrown when attempting to generate the CCS results.");
Console.WriteLine("A shared library was not found. To solve this, please add the folder" +
" with the downloaded file libMonoPosixHelper" +
"to your environmental variables (LD_LIBRARY_PATH and DYLD_LIBRARY_PATH on Mac OS X).");
Console.WriteLine ("Error: " + thrown.Message);
Console.WriteLine (thrown.StackTrace);
}
catch(Exception thrown) {
Console.WriteLine ("Error thrown when attempting to generate the FASTQ File");
Console.WriteLine ("Error: " + thrown.Message);
Console.WriteLine (thrown.StackTrace);
while (thrown.InnerException != null) {
Console.WriteLine ("Inner Exception: " + thrown.InnerException.Message);
thrown = thrown.InnerException;
}
}
}
