/** * This method outlines the first decision to test quality data and return whether it resides * in the higher ASCII regions greater than character J or in the lower regions below this * point * @param fastqFile */ private void DecisionTree(IFqFile fastqFile) { stopwatch.Start(); Boolean upper = false, lower = false; int i = 0, j = 0; for (i = 0; i < index; i++) { fastqSeq = fastqFile.getFastqSequenceByPosition(i); for (j = 0; j < fastqSeq.getFastqSeqSize(); j++) { char qualityValue = map[fastqSeq.getFastqSeqAtPosition(j)].getQualityRead(); if (qualityValue > 'J') { upper = true; goto search; } else if (qualityValue < ';') { lower = true; goto search; } } } search: if (upper == true) { upperTree(i, j); } else if (lower == true) { lowerTree(i, j); } }
///<summary> ///Default constructor for the SaveFile class, accepts string to save and parameters for the savefiledialogue window ///</summary> ///<param name="output">The string to be saved</param> ///<param name="message">Message to be displayed on the save file dialogue window</param> ///<param name="filter">String to filter access to file types in the savefiledialogue window</param> public SaveFile(IFqFile file, String message, FastqGUI o, String saveType, String filter = "Text File|*.txt|FastqFile|*.fq") { this.fqFile = file; this.message = message; this.filter = filter; this.observer = o; this.saveAction = saveType; }
/// <summary> /// Creates a fqFile_component_details class from the core information that is best still stored within the programs memory. /// These classes populate a dictionary within the fqfilemap class where the component filename is their key. /// </summary> /// <param name="component">The component who's details are to be stored</param> public void BuildFqFileMap(IFqFile component) { FqFile_Component_Details componentDetails = new FqFile_Component_Details(); componentDetails.ContructComponentDetails(component); fqFileMap.GetFqFileComponentDetailsMap()[component.getFileName()] = componentDetails; }
public SequencerDecisionTree(IFqFile aFastqFile) { ASSUMPTION_POINT = Preferences.getInstance().getAssumptionPref(); fastqFile = aFastqFile; index = fastqFile.getFastqArraySize(); map = fastqFile.getMap(); Console.WriteLine("Starting to search for sequencer"); DecisionTree(fastqFile); }
public IFqFile Parse() { if (IsStandardFormat == true) { FILE_FORMAT_TYPE = "Standard Fastq File Format"; fastqFile = ParseStandardFormat(); } else if (IsMultiLineFormat == true) { FILE_FORMAT_TYPE = "Multi-Line Fastq File Format"; fastqFile = ParseMultiLineFormat(); } return(fastqFile); }
/// <summary> /// Outputs the data for a FastqFile to the console, keeping code clean in other classes /// </summary> /// <param name="fqFile"></param> public void OutputFileDataToConsole(IFqFile fqFile) { Console.WriteLine("Joint Test Results Completed on " + fqFile.getTotalNucleotides() + " Nucleotides"); Console.WriteLine("Joint Test Results: " + fqFile.getGCount() + "G " + Math.Round(fqFile.gContents(), 2) + "% " + fqFile.getCCount() + "C " + Math.Round(fqFile.cContents(), 2) + " %"); Console.WriteLine("Misreads: " + fqFile.getNCount()); Console.WriteLine("Nucleotides Cleaned: {0}", fqFile.getNucleotidesCleaned()); Console.WriteLine("Distribution: " + fqFile.getDistribution().Count); Console.WriteLine("Stats Performed"); for (int i = 0; i < 20; i++) { FqSequence fqSeq = fqFile.getFastqSequenceByPosition(i); Console.WriteLine("-- -Stats for Sequence " + (i + 1) + ": LB: {0} 1Q: {1} Median: {2} Mean: {3} 3Q: {4} UB: {5}", fqSeq.getLowerThreshold(), fqSeq.getFirstQuartile(), fqSeq.getMedian(), Math.Round(fqSeq.getMean(), 2), fqSeq.getThirdQuartile(), fqSeq.getUpperThreshold()); } for (int i = 0; i < fqFile.getDistribution().Count; i++) Console.WriteLine("---> Quality Score: {0} Count: {1}", i, fqFile.getDistribution()[i]); for (int i = 0; i < fqFile.GetPerBaseStatisticsArray().Length; i ++) Console.WriteLine("===> BaseStatistic: {0} \tCount: {1} LB: {2} 1Q: {3} Median: {4} Mean: {5} 3Q: {6} UB: {7}", i, fqFile.GetPerBaseStatisticsArray()[i].BaseCount, fqFile.GetPerBaseStatisticsArray()[i].LowerThreshold, fqFile.GetPerBaseStatisticsArray()[i].FirstQuartile, fqFile.GetPerBaseStatisticsArray()[i].Median, fqFile.GetPerBaseStatisticsArray()[i].Mean, fqFile.GetPerBaseStatisticsArray()[i].ThirdQuartile, fqFile.GetPerBaseStatisticsArray()[i].UpperThreshold); }
public override GenericFastqInputs perform(GenericFastqInputs inputs) { StreamWriter writer; String extension = Path.GetExtension(inputs.SaveFileName); String fileName = Path.GetFileNameWithoutExtension(inputs.SaveFileName); String[] part = Path.GetFileNameWithoutExtension(inputs.FastqFile.getFileName()).Split('_'); String directory = Path.GetDirectoryName(inputs.SaveFileName); String number = part[part.Length - 1]; String FullName = String.Format(@"{0}{1}{2}_{3}{4}", directory, Path.DirectorySeparatorChar, fileName, number, extension); string COMMA_DELIMITER = ","; string[] output; IFqFile fqFile = inputs.FastqFile; writer = new StreamWriter(FullName); output = new string[] { "Sequence Index", "Header", "Total Nucleotides", "G Count", "C Count", "Misread Count", "Lower Threshold", "First Quartile", "Median", "Mean", "Third Quartile", "Upper Threshold" }; writer.WriteLine(string.Join(COMMA_DELIMITER, output)); for (int i = 0; i < fqFile.getFastqArraySize(); i++) { FqSequence fqSeq = fqFile.getFastqSequenceByPosition(i); output = new string[] { fqSeq.getSeqIndex().ToString(), fqSeq.getSequenceHeader(), fqSeq.getFastqSeqSize().ToString(), fqSeq.getGCount().ToString(), fqSeq.getCCount().ToString(), fqSeq.getNCount().ToString(), fqSeq.getLowerThreshold().ToString(), fqSeq.getFirstQuartile().ToString(), fqSeq.getMedian().ToString(), fqSeq.getMean().ToString(), fqSeq.getThirdQuartile().ToString(), fqSeq.getUpperThreshold().ToString(), fqSeq.createSequenceString(fqFile.getMap()) }; writer.WriteLine(string.Join(COMMA_DELIMITER, output)); } Console.WriteLine("Saving CSV TO: {0}", FullName); writer.Flush(); writer.Close(); return(inputs); }
private void SaveFastqAction(IFqFile fq, String fileName) { StreamWriter writer; try { writer = new StreamWriter(@fileName); saveWorker.ReportProgress(40, "[CREATING FASTQ FORMAT]"); for (int i = 0; i < fqFile.getFastqArraySize(); i++) { writer.Write(fqFile.getFastqSequenceByPosition(i).createFastqBlock(fqFile.getMap())); } saveWorker.ReportProgress(100, "[FASTQ FORMAT CREATED]"); writer.Flush(); writer.Close(); } catch (IOException exception) { Console.WriteLine(exception.ToString()); UserResponse.ErrorResponse(exception.ToString()); } }
/// <summary> /// Outputs the data for a FastqFile to the console, keeping code clean in other classes /// </summary> /// <param name="fqFile"></param> public void OutputFileDataToConsole(IFqFile fqFile) { Console.WriteLine("Joint Test Results Completed on " + fqFile.getTotalNucleotides() + " Nucleotides"); Console.WriteLine("Joint Test Results: " + fqFile.getGCount() + "G " + Math.Round(fqFile.gContents(), 2) + "% " + fqFile.getCCount() + "C " + Math.Round(fqFile.cContents(), 2) + " %"); Console.WriteLine("Misreads: " + fqFile.getNCount()); Console.WriteLine("Nucleotides Cleaned: {0}", fqFile.getNucleotidesCleaned()); Console.WriteLine("Distribution: " + fqFile.getDistribution().Count); Console.WriteLine("Stats Performed"); for (int i = 0; i < 20; i++) { FqSequence fqSeq = fqFile.getFastqSequenceByPosition(i); Console.WriteLine("-- -Stats for Sequence " + (i + 1) + ": LB: {0} 1Q: {1} Median: {2} Mean: {3} 3Q: {4} UB: {5}", fqSeq.getLowerThreshold(), fqSeq.getFirstQuartile(), fqSeq.getMedian(), Math.Round(fqSeq.getMean(), 2), fqSeq.getThirdQuartile(), fqSeq.getUpperThreshold()); } for (int i = 0; i < fqFile.getDistribution().Count; i++) { Console.WriteLine("---> Quality Score: {0} Count: {1}", i, fqFile.getDistribution()[i]); } for (int i = 0; i < fqFile.GetPerBaseStatisticsArray().Length; i++) { Console.WriteLine("===> BaseStatistic: {0} \tCount: {1} LB: {2} 1Q: {3} Median: {4} Mean: {5} 3Q: {6} UB: {7}", i, fqFile.GetPerBaseStatisticsArray()[i].BaseCount, fqFile.GetPerBaseStatisticsArray()[i].LowerThreshold, fqFile.GetPerBaseStatisticsArray()[i].FirstQuartile, fqFile.GetPerBaseStatisticsArray()[i].Median, fqFile.GetPerBaseStatisticsArray()[i].Mean, fqFile.GetPerBaseStatisticsArray()[i].ThirdQuartile, fqFile.GetPerBaseStatisticsArray()[i].UpperThreshold); } }
public void ContructComponentDetails(IFqFile component) { this.ComponentName = component.getFileName(); this.FileName = component.getFileName(); this.sequencerType = component.getSequencerType(); this.ComponentNumber = component.getComponentNumber(); this.TotalNucs = component.getTotalNucleotides(); this.TotalSequences = component.getFastqArraySize(); this.NucleotidesCleaned = component.getNucleotidesCleaned(); this.Distribution = component.getDistribution(); this.SequenceLengthDistribution = component.getSequenceLengthDistribution(); this.NCount = component.getNCount(); this.CCount = component.getCCount(); this.GCount = component.getGCount(); this.MaxSeqSize = component.getMaxSeqSize(); this.MinSeqSize = component.getMinSeqSize(); this.NPercent = component.nContents(); this.CPercent = component.cContents(); this.GPercent = component.gContents(); this.SequencesRemoved = component.getSequencesRemoved(); this.RemovedAdapters = component.getRemovedAdapters(); this.perBaseStatistics = component.GetPerBaseStatisticsArray(); }
private void SaveCSVAction(IFqFile fq, String fileName) { StreamWriter writer; string COMMA_DELIMITER = ","; string[] output; try { writer = new StreamWriter(@fileName); saveWorker.ReportProgress(30, "[CREATING CSV FORMAT]"); output = new string[] { "Sequence Index", "Header", "Total Nucleotides", "G Count", "C Count", "Misread Count", "Lower Threshold", "First Quartile", "Median", "Mean", "Third Quartile", "Upper Threshold" }; writer.WriteLine(string.Join(COMMA_DELIMITER, output)); for (int i = 0; i < fqFile.getFastqArraySize(); i++) { FqSequence fqSeq = fqFile.getFastqSequenceByPosition(i); output = new string[] { fqSeq.getSeqIndex().ToString(), fqSeq.getSequenceHeader(), fqSeq.getFastqSeqSize().ToString(), fqSeq.getGCount().ToString(), fqSeq.getCCount().ToString(), fqSeq.getNCount().ToString(), fqSeq.getLowerThreshold().ToString(), fqSeq.getFirstQuartile().ToString(), fqSeq.getMedian().ToString(), fqSeq.getMean().ToString(), fqSeq.getThirdQuartile().ToString(), fqSeq.getUpperThreshold().ToString(), fqSeq.createSequenceString(fqFile.getMap()) }; writer.WriteLine(string.Join(COMMA_DELIMITER, output)); } saveWorker.ReportProgress(100, "[FASTQ FORMAT CREATED]"); writer.Flush(); writer.Close(); } catch (IOException exception) { Console.WriteLine(exception.ToString()); UserResponse.ErrorResponse(exception.ToString()); } }
private void SaveFastaAction(IFqFile fq, String fileName) { saveWorker.ReportProgress(40, "[CREATING FASTA FORMAT]"); String output = fqFile.createFastaFormat(""); saveWorker.ReportProgress(100, "[FASTA FORMAT CREATED]"); StreamWriter writer; try { writer = new StreamWriter(@fileName); writer.Write(output); writer.Flush(); writer.Close(); } catch (IOException exception) { Console.WriteLine(exception.ToString()); UserResponse.ErrorResponse(exception.ToString()); } }
public IFqFile Parse() { if (IsStandardFormat == true) { FILE_FORMAT_TYPE = "Standard Fastq File Format"; fastqFile = ParseStandardFormat(); } else if (IsMultiLineFormat == true) { FILE_FORMAT_TYPE = "Multi-Line Fastq File Format"; fastqFile = ParseMultiLineFormat(); } return fastqFile; }
private void sequencer(IFqFile fastqFile) { String sequencer = null; Boolean completed = false; Boolean sangerLowerBoundary = false, sangerUpperBoundary = false, solexaLowerBoundary = false, sharedUpperBoundary = false, illuminaThreeLowerBoundary = false, illuminaFiveLowerBoundary = false, illuminaEightLowerBoundary = false, illuminaNineLowerBoundary = false, illuminaEightNineUpperBoundary = false; // char variables for the upper and lower boundaries of the sequencer types char sangerLower = '!'; char sangerUpper = 'I'; char solexaLower = ';'; char solilmixedUpper = 'h'; char illuminathreeLower = '@'; char illuminafiveLower = 'B'; char illuminaeightLower = '!'; char illuminanineLower = '#'; char illuminamixedUpper = 'J'; Stopwatch stopwatch = new Stopwatch(); stopwatch.Start(); while (completed != true) { for (int i = 0; i < fastqFile.getFastqArraySize(); i++) { FqSequence fqSeq = fastqFile.getFastqSequenceByPosition(i); for (int j = 0; j < fqSeq.getFastqSeqSize(); j++) { char qualityValue = map[fqSeq.getFastqSeqAtPosition(j)].getQualityRead(); if (qualityValue == sangerLower) { sangerLowerBoundary = true; } else if (qualityValue == sangerUpper) { sangerUpperBoundary = true; } else if (qualityValue == solexaLower) { solexaLowerBoundary = true; } else if (qualityValue == solilmixedUpper) { sharedUpperBoundary = true; } else if (qualityValue == illuminathreeLower) { illuminaThreeLowerBoundary = true; } else if (qualityValue == illuminafiveLower) { illuminaFiveLowerBoundary = true; } else if (qualityValue == illuminaeightLower) { illuminaEightLowerBoundary = true; } else if (qualityValue == illuminanineLower) { illuminaNineLowerBoundary = true; } else if (qualityValue == illuminamixedUpper) { illuminaEightNineUpperBoundary = true; } } } if (sangerLowerBoundary != false && sangerUpperBoundary != false && illuminaEightNineUpperBoundary != true) { sequencer = "Sanger"; completed = true; } else if (solexaLowerBoundary != false && sharedUpperBoundary != false) { sequencer = "Solexa"; completed = true; } else if (illuminaThreeLowerBoundary != false && sharedUpperBoundary != false && solexaLowerBoundary != true) { sequencer = "Illumina 1.3"; completed = true; } else if (illuminaFiveLowerBoundary != false && sharedUpperBoundary != false && illuminaThreeLowerBoundary != true) { sequencer = "Illumina 1.5"; completed = true; } else if (illuminaEightLowerBoundary != false && illuminaEightNineUpperBoundary != false) { sequencer = "Illumina 1.8"; completed = true; } else if (illuminaNineLowerBoundary != false && illuminaEightNineUpperBoundary != false && illuminaEightLowerBoundary != true) { sequencer = "Illumina 1.9"; completed = true; } else if (completed != true) { sequencer = "Default"; completed = true; } else if ((sequencer == null)) { sequencer = "Default"; completed = true; } } this.sequencerType = sequencer; fastqFile.setSequencerType(sequencerType); if (fastqFile is FqFile_Component) { fastqFile.setFqHashMap(FastqController.getInstance().GetFqFileMap().ConstructSequencerSpecificReadMap(sequencerType)); Console.WriteLine("Calculating and setting sequencer specific file map to component"); } stopwatch.Stop(); Console.WriteLine("Time To Determine ISequencer: " + stopwatch.Elapsed); Console.WriteLine("ISequencer Name: " + sequencer); Console.WriteLine("File contains {0} sequences", fastqFile.getFastqArraySize()); }
public SequencerDetermination(IFqFile fastqFile) { map = fastqFile.getMap(); sequencer(fastqFile); }
private void sequencer(IFqFile fastqFile) { String sequencer = null; Boolean completed = false; Boolean sangerLowerBoundary = false, sangerUpperBoundary = false, solexaLowerBoundary = false, sharedUpperBoundary = false, illuminaThreeLowerBoundary = false, illuminaFiveLowerBoundary = false, illuminaEightLowerBoundary = false, illuminaNineLowerBoundary = false, illuminaEightNineUpperBoundary = false; // char variables for the upper and lower boundaries of the sequencer types char sangerLower = '!'; char sangerUpper = 'I'; char solexaLower = ';'; char solilmixedUpper = 'h'; char illuminathreeLower = '@'; char illuminafiveLower = 'B'; char illuminaeightLower = '!'; char illuminanineLower = '#'; char illuminamixedUpper = 'J'; Stopwatch stopwatch = new Stopwatch(); stopwatch.Start(); while (completed != true) { for (int i = 0; i < fastqFile.getFastqArraySize();i++) { FqSequence fqSeq = fastqFile.getFastqSequenceByPosition(i); for (int j = 0; j < fqSeq.getFastqSeqSize(); j++) { char qualityValue = map[fqSeq.getFastqSeqAtPosition(j)].getQualityRead(); if (qualityValue == sangerLower) sangerLowerBoundary = true; else if (qualityValue == sangerUpper) sangerUpperBoundary = true; else if (qualityValue == solexaLower) solexaLowerBoundary = true; else if (qualityValue == solilmixedUpper) sharedUpperBoundary = true; else if (qualityValue == illuminathreeLower)illuminaThreeLowerBoundary = true; else if (qualityValue == illuminafiveLower) illuminaFiveLowerBoundary = true; else if (qualityValue == illuminaeightLower)illuminaEightLowerBoundary = true; else if (qualityValue == illuminanineLower) illuminaNineLowerBoundary = true; else if (qualityValue == illuminamixedUpper)illuminaEightNineUpperBoundary = true; } } if (sangerLowerBoundary != false && sangerUpperBoundary != false && illuminaEightNineUpperBoundary != true) { sequencer = "Sanger"; completed = true; } else if (solexaLowerBoundary != false && sharedUpperBoundary != false) { sequencer = "Solexa"; completed = true; } else if (illuminaThreeLowerBoundary != false && sharedUpperBoundary != false && solexaLowerBoundary != true) { sequencer = "Illumina 1.3"; completed = true; } else if (illuminaFiveLowerBoundary != false && sharedUpperBoundary != false && illuminaThreeLowerBoundary != true) { sequencer = "Illumina 1.5"; completed = true; } else if (illuminaEightLowerBoundary != false && illuminaEightNineUpperBoundary != false) { sequencer = "Illumina 1.8"; completed = true; } else if (illuminaNineLowerBoundary != false && illuminaEightNineUpperBoundary != false && illuminaEightLowerBoundary != true) { sequencer = "Illumina 1.9"; completed = true; } else if (completed != true) { sequencer = "Default"; completed = true; } else if ((sequencer == null)) { sequencer = "Default"; completed = true; } } this.sequencerType = sequencer; fastqFile.setSequencerType(sequencerType); if (fastqFile is FqFile_Component) { fastqFile.setFqHashMap(FastqController.getInstance().GetFqFileMap().ConstructSequencerSpecificReadMap(sequencerType)); Console.WriteLine("Calculating and setting sequencer specific file map to component"); } stopwatch.Stop(); Console.WriteLine("Time To Determine ISequencer: " + stopwatch.Elapsed); Console.WriteLine("ISequencer Name: " + sequencer); Console.WriteLine("File contains {0} sequences", fastqFile.getFastqArraySize()); }
private void SaveCSVAction(IFqFile fq, String fileName) { StreamWriter writer; string COMMA_DELIMITER = ","; string[] output; try { writer = new StreamWriter(@fileName); saveWorker.ReportProgress(30, "[CREATING CSV FORMAT]"); output = new string[] {"Sequence Index", "Header", "Total Nucleotides", "G Count", "C Count", "Misread Count", "Lower Threshold", "First Quartile", "Median", "Mean", "Third Quartile", "Upper Threshold" }; writer.WriteLine(string.Join(COMMA_DELIMITER, output)); for (int i = 0; i < fqFile.getFastqArraySize(); i++) { FqSequence fqSeq = fqFile.getFastqSequenceByPosition(i); output = new string[] { fqSeq.getSeqIndex().ToString(), fqSeq.getSequenceHeader(), fqSeq.getFastqSeqSize().ToString(), fqSeq.getGCount().ToString(), fqSeq.getCCount().ToString(), fqSeq.getNCount().ToString(), fqSeq.getLowerThreshold().ToString(), fqSeq.getFirstQuartile().ToString(), fqSeq.getMedian().ToString(), fqSeq.getMean().ToString(), fqSeq.getThirdQuartile().ToString(), fqSeq.getUpperThreshold().ToString(), fqSeq.createSequenceString(fqFile.getMap()) }; writer.WriteLine(string.Join(COMMA_DELIMITER, output)); } saveWorker.ReportProgress(100, "[FASTQ FORMAT CREATED]"); writer.Flush(); writer.Close(); } catch (IOException exception) { Console.WriteLine(exception.ToString()); UserResponse.ErrorResponse(exception.ToString()); } }