private static void ExportMixedSampleResult(Dictionary <Peptide, MaxFlowElutionCurve> ratios, Sample mixedSample, MixedPrecursor mixedPrecursor, double keyMz, DBOptions dbOptions)
{
// Export results in a file
vsCSVWriter writerRatio = new vsCSVWriter(dbOptions.OutputFolder + @"IndividualNoSpike\" + vsCSV.GetFileName_NoExtension(mixedSample.sSDF) + "_" + keyMz + "MZ_" + mixedPrecursor.Queries[0].spectrum.RetentionTimeInMin + "min.csv");
string titleIndividual = "Scan time,Total Area";
foreach (Peptide charPep in ratios.Keys)
{
titleIndividual += "," + charPep.Sequence;
}
writerRatio.AddLine(titleIndividual);
string line = "Total," + mixedPrecursor.eCurveIntensityCount.Area;
foreach (Peptide charPep in ratios.Keys)
{
line += "," + ratios[charPep].eCurvePerMs.Area;
}
writerRatio.AddLine(line);
for (int i = 0; i < mixedPrecursor.eCurveIntensityCount.intensityCount.Count; i++)
{
line = mixedPrecursor.eCurveIntensityCount.time[i] / (1000.0 * 60.0) + "," + mixedPrecursor.eCurveIntensityCount.intensityCount[i];
foreach (Peptide charPep in ratios.Keys)
{
line += "," + ratios[charPep].eCurvePerMs.InterpolateIntensity(mixedPrecursor.eCurveIntensityCount.time[i]);
}
writerRatio.AddLine(line);
}
writerRatio.WriteToFile();
}
private static void ExportSpikedSampleResult(Dictionary <double, Dictionary <Sample, CharacterizedPrecursor> > characterizedPeptides, DBOptions dbOptions)
{
foreach (double keyMz in characterizedPeptides.Keys)
{
foreach (Sample sample in characterizedPeptides[keyMz].Keys)
{
vsCSVWriter writerRatio = new vsCSVWriter(dbOptions.OutputFolder + @"IndividualNoSpike\" + vsCSV.GetFileName_NoExtension(sample.sSDF) + "_" + keyMz + "MZ.csv");
string titleIndividual = "Scan time,Precursor Intensity,Intensity Per Millisecond";
foreach (ProductMatch pm in characterizedPeptides[keyMz][sample].AllFragments)
{
titleIndividual += "," + pm.Fragment.Name + pm.fragmentPos + "^" + pm.charge;
}
writerRatio.AddLine(titleIndividual);
foreach (Query query in characterizedPeptides[keyMz][sample].Queries)
{
string line = query.spectrum.RetentionTimeInMin + "," + query.spectrum.PrecursorIntensity + "," + query.spectrum.PrecursorIntensityPerMilliSecond;
foreach (ProductMatch pm in characterizedPeptides[keyMz][sample].AllFragments)
{
double intensity = 0.0;
foreach (ProductMatch pmSpec in query.psms[0].AllProductMatches)
{
if (pmSpec.charge == pm.charge && pmSpec.Fragment == pm.Fragment && pmSpec.fragmentPos == pm.fragmentPos)
{
intensity = pmSpec.obsIntensity;
}
}
line += "," + intensity;
}
writerRatio.AddLine(line);
}
writerRatio.WriteToFile();
}
}
}
public static void Export(string filename, List <PeptideMatch> peptides)
{
vsCSVWriter writer = new vsCSVWriter(filename);
writer.AddLine("Sequence,Variable Modification,Score,Decoy,Precursor Mass Error");
foreach (PeptideMatch pm in peptides)
{
writer.AddLine(pm.peptide.BaseSequence + "," + pm.peptide.Sequence + "," + pm.ProbabilityScore() + "," + pm.peptide.Decoy + "," + pm.GetPrecursorMassError());
}
writer.WriteToFile();
}
public static void Export(string filename, List <ProteinGroupMatch> proteins)
{
vsCSVWriter writer = new vsCSVWriter(filename);
writer.AddLine(ProteinGroupMatch.Header);
foreach (ProteinGroupMatch group in proteins)
{
writer.AddLine(group.ToString());
}
writer.WriteToFile();
}
public static bool Run()
{
string outputPath = @"C:\_IRIC\DATA\Test\testMhc\Stats\";
vsCSVWriter writer = new vsCSVWriter(outputPath + "output.csv");
writer.AddLine("File,# MS1s,# MSMS,1 Charge,2 Charge,3 Charge,4 Charge,5 Charge,6 Charge,7 Charge,8 Charge,9 Charge,10 Charge,11 Charge,12 Charge,13 Charge,14 Charge");
DBOptions options = MhcSample.CreateOptions(outputPath);
string[] files = new string[] { @"N:\Thibault\-=Proteomics_Raw_Data=-\ELITE\JUL29_2013\Settepeptides_300713_10uL.raw",
@"N:\Thibault\-=Proteomics_Raw_Data=-\ELITE\JUL29_2013\Settepeptides_300713_10uL_MS60_MSMS15.raw",
@"N:\Thibault\-=Proteomics_Raw_Data=-\ELITE\JUL29_2013\Settepeptides_300713_10uL_MS60_MSMS30.raw",
@"N:\Thibault\-=Proteomics_Raw_Data=-\ELITE\JUL29_2013\Settepeptides_300713_10uL_MS60_MSMS60.raw",
@"N:\Thibault\-=Proteomics_Raw_Data=-\ELITE\JUL29_2013\Settepeptides_300713_10uL_MS120_MSMS15.raw",
@"N:\Thibault\-=Proteomics_Raw_Data=-\ELITE\JUL29_2013\Settepeptides_300713_10uL_MS120_MSMS30.raw",
@"N:\Thibault\-=Proteomics_Raw_Data=-\ELITE\JUL29_2013\Settepeptides_300713_10uL_MS120_MSMS60.raw" };
foreach (string file in files)
{
pwiz.CLI.msdata.MSDataFile msFile = new pwiz.CLI.msdata.MSDataFile(file);
Spectra spectra = Spectra.Load(msFile, options, file);
spectra.Sort(ProductSpectrum.AscendingPrecursorMassComparison);
Dictionary <Track, Precursor> DicOfComputedTracks = new Dictionary <Track, Precursor>();
int[] charges = new int[14];
foreach (Track track in spectra.tracks)
{
if (!DicOfComputedTracks.ContainsKey(track))
{
DicOfComputedTracks.Add(track, null);
int charge = 0;
foreach (Precursor precursor in Queries.GetIsotopes(track, options, spectra.tracks, null))
{
if (precursor.Charge > 0)
{
charge = precursor.Charge;
}
if (!DicOfComputedTracks.ContainsKey(precursor.Track))
{
DicOfComputedTracks.Add(precursor.Track, precursor);
}
}
charges[charge]++;
}
}
string line = file + "," + spectra.MS1s.Count + "," + spectra.Count;
for (int i = 0; i < charges.Length; i++)
{
line += "," + charges[i];
}
writer.AddLine(line);
}
writer.WriteToFile();
return(true);
}
public void Export(string filename)
{
vsCSVWriter writer = new vsCSVWriter(filename);
writer.AddLine(Track.TITLE);
foreach (Track track in this)
{
writer.AddLine(track.ToString());
}
writer.WriteToFile();
}
public void ExportMSMS(string filename)
{
vsCSVWriter writer = new vsCSVWriter(filename);
writer.AddLine(ProductSpectrum.TITLE);
foreach (ProductSpectrum spectrum in this)
{
writer.AddLine(spectrum.ToString());
}
writer.WriteToFile();
}
public static void ShuffleSequences(string fastaFile)
{
try
{
FileStream fs;
try
{
fs = new FileStream(fastaFile, FileMode.Open, FileAccess.Read, FileShare.Read);
}
catch (System.Exception)
{
fs = new FileStream(fastaFile, FileMode.Open, FileAccess.Read, FileShare.ReadWrite);
}
vsCSVWriter wrShuffled = new vsCSVWriter(vsCSV.GetFolder(fastaFile) + vsCSV.GetFileName_NoExtension(fastaFile) + "_Shuffled.fasta");
using (StreamReader sr = new StreamReader(fs))
{
ProteinIdType idType = ProteinIdType.Unknown;
string line;
string aaSeq = "";
while ((line = sr.ReadLine()) != null)
{
if (line.StartsWith(">"))
{
if (!string.IsNullOrEmpty(aaSeq))
{
wrShuffled.AddLine(Proteomics.Utilities.Tools.AminoAcidTools.Shuffle(aaSeq));
}
wrShuffled.AddLine(line);
aaSeq = "";
}
else
{
aaSeq += line;
}
}
if (!string.IsNullOrEmpty(aaSeq))
{
wrShuffled.AddLine(Proteomics.Utilities.Tools.AminoAcidTools.Shuffle(aaSeq));
}
}
fs.Close();
wrShuffled.WriteToFile();
}
catch (System.Exception ex)
{
Console.WriteLine(ex.Message);
Console.WriteLine(ex.StackTrace);
}
}
public static void Export(string filename, List <PeptideSpectrumMatch> psms)
{
vsCSVWriter writer = new vsCSVWriter(filename);
writer.AddLine("Mz,Rt,Charge,Sequence,Modifications,Precursor Score,Product Score,Intensity Score,Final Score,Precursor Mass Error,Decoy?,Protein Score");
foreach (PeptideSpectrumMatch psm in psms)
{
writer.AddLine(psm.Query.precursor.Track.MZ + "," + psm.Query.spectrum.RetentionTimeInMin + "," + psm.Query.precursor.Charge +
"," + psm.Peptide.BaseSequence + "," + psm.Peptide.Sequence + "," + psm.PrecursorScore + "," + psm.ProductScore + "," + psm.IntensityScore + "," + psm.ProbabilityScore() + "," +
psm.PrecursorMzError + "," + psm.Decoy + "," + psm.ProteinScore);
}
writer.WriteToFile();
}
public static void AppendProteinDescriptionToMascotReport(string csvMascotFile, string fastaFile, string csvFileOut)
{
vsCSV csvMascot = new vsCSV(csvMascotFile);
vsCSVWriter writer = new vsCSVWriter(csvFileOut);
try
{
FileStream fs;
try
{
fs = new FileStream(fastaFile, FileMode.Open, FileAccess.Read, FileShare.Read);
}
catch (System.Exception)
{
fs = new FileStream(fastaFile, FileMode.Open, FileAccess.Read, FileShare.ReadWrite);
}
Dictionary <string, string> DicOfProt = new Dictionary <string, string>();
foreach (string line in csvMascot.LINES_LIST)
{
string[] splits = line.Split(',');
if (splits.Length > 2 && !DicOfProt.ContainsKey(splits[2]))
{
DicOfProt.Add(splits[2], "");
}
}
using (StreamReader sr = new StreamReader(fs))
{
string line;
while ((line = sr.ReadLine()) != null)
{
if (line.StartsWith(">"))
{
string[] split = line.Substring(1).Split(' ');
if (DicOfProt.ContainsKey(split[0]))
{
DicOfProt[split[0]] = line.Substring(split[0].Length + 1);
}
}
}
}
foreach (string line in csvMascot.LINES_LIST)
{
string[] splits = line.Split(',');
string lineToWrite = line;
if (splits.Length > 2 && DicOfProt.ContainsKey(splits[2]))
{
lineToWrite += "," + DicOfProt[splits[2]];
}
writer.AddLine(lineToWrite);
}
writer.WriteToFile();
}
catch (System.Exception ex)
{
Console.WriteLine(ex.Message);
Console.WriteLine(ex.StackTrace);
}
}
public void ExportFragmentIntensitiesForAllPSM(List <PeptideSpectrumMatch> psms, Peptide peptide, int psmCharge, string fileName)
{
vsCSVWriter writer = new vsCSVWriter(fileName);
string title = "Retention Time";
for (int i = 1; i <= peptide.Length; i++)
{
for (int charge = 1; charge <= psmCharge; charge++)
{
foreach (FragmentClass fragment in dbOptions.fragments)
{
title += "," + i + fragment.Name + " ^" + charge;
}
}
}
writer.AddLine(title);
foreach (PeptideSpectrumMatch psm in psms)
{
string line = psm.Query.spectrum.RetentionTimeInMin.ToString();
for (int i = 1; i <= peptide.Length; i++)
{
for (int charge = 1; charge <= psmCharge; charge++)
{
foreach (FragmentClass fragment in dbOptions.fragments)
{
double cumul = 0.0;
foreach (ProductMatch match in psm.AllProductMatches)
{
if (fragment == match.Fragment && match.fragmentPos == i && match.charge == charge)
{
cumul += match.obsIntensity;
}
}
line += "," + cumul;
}
}
}
writer.AddLine(line);
}
writer.WriteToFile();
}
public static void Export(string filename, IEnumerable <Query> queries)
{
vsCSVWriter writer = new vsCSVWriter(filename);
writer.AddLine("Spectrum Precursor Mz,Rt,Charge,BaseSequence,Sequence,Precursor Score,Product Score,Intensity Score,Final Score,Precursor Mass Error,Decoy?,Protein Score");
foreach (Query query in queries)
{
string line = query.spectrum.PrecursorMZ + "," + query.precursor.Track.RT + "," + query.precursor.Charge + ",";
PeptideSpectrumMatch match = query.precursor.OptimizedBestPsm();
if (match != null)
{
line += match.Peptide.BaseSequence + "," + match.Peptide.Sequence + "," + match.PrecursorScore + "," + match.ProductScore + "," + match.IntensityScore + "," + query.ScoreFct(match.Peptide) + "," +
match.PrecursorMzError + "," + match.Decoy + "," + match.ProteinScore;
}
writer.AddLine(line);
}
writer.WriteToFile();
}
public static void SeparateForwardAndReverse(string fastaFile)
{
try
{
FileStream fs;
try
{
fs = new FileStream(fastaFile, FileMode.Open, FileAccess.Read, FileShare.Read);
}
catch (System.Exception)
{
fs = new FileStream(fastaFile, FileMode.Open, FileAccess.Read, FileShare.ReadWrite);
}
vsCSVWriter wrForward = new vsCSVWriter(vsCSV.GetFolder(fastaFile) + vsCSV.GetFileName_NoExtension(fastaFile) + "_ForwardOnly.fasta");
vsCSVWriter wrReverse = new vsCSVWriter(vsCSV.GetFolder(fastaFile) + vsCSV.GetFileName_NoExtension(fastaFile) + "_ReverseOnly.fasta");
using (StreamReader sr = new StreamReader(fs))
{
ProteinIdType idType = ProteinIdType.Unknown;
string line;
while ((line = sr.ReadLine()) != null)
{
if (line.StartsWith(">"))
{
if (line.StartsWith(">REVERSE_"))
{
idType = ProteinIdType.Reverse;
}
else
{
idType = ProteinIdType.Forward;
}
}
switch (idType)
{
case ProteinIdType.Forward: wrForward.AddLine(line); break;
case ProteinIdType.Reverse: wrReverse.AddLine(line); break;
case ProteinIdType.Unknown: break;
}
}
}
fs.Close();
wrForward.WriteToFile();
wrReverse.WriteToFile();
}
catch (System.Exception ex)
{
Console.WriteLine(ex.Message);
Console.WriteLine(ex.StackTrace);
}
}
public static void Export(string filename, List <Precursor> precursors)
{
vsCSVWriter writer = new vsCSVWriter(filename);
writer.AddLine("Index.Mz,Rt,Precursor Mz,Charge,Most Intense Charge,Precursor Mass,Peptide Mass,Sequence,Modified Sequence,Precursor Score,Product Score,Intensity Score,Final Score,Precursor Mass Error,Decoy?,Protein Score");
foreach (Precursor precursor in precursors)
{
string line = precursor.INDEX + "," + precursor.Track.RT + "," + precursor.Track.MZ + "," + precursor.Charge + "," + precursor.GetMostIntenseCharge() + "," + precursor.Mass + ",";
PeptideSpectrumMatch match = precursor.OptimizedBestPsm();
if (match != null)
{
line += match.Peptide.MonoisotopicMass + "," + match.Peptide.BaseSequence + "," + match.Peptide.Sequence + "," + match.PrecursorScore + "," + match.ProductScore + "," + match.IntensityScore + "," + precursor.ProbabilityScore(match.Peptide) + "," +
match.PrecursorMzError + "," + match.Decoy + "," + match.ProteinScore;
}
writer.AddLine(line);
}
writer.WriteToFile();
}
public static void ToCSV(string rawFileName, string csvOutFileName)
{
vsCSVWriter csvWriter = new vsCSVWriter(csvOutFileName);
csvWriter.AddLine("Scan Number,Retention Time (min),Ms Level");
pwiz.CLI.msdata.MSDataFile msFile = new pwiz.CLI.msdata.MSDataFile(rawFileName);
int num_spectra = msFile.run.spectrumList.size();
for (int i = 0; i < num_spectra; i++)
{
//Spectrum
pwiz.CLI.msdata.Spectrum mySpec = msFile.run.spectrumList.spectrum(i, false);
double retention_time = mySpec.scanList.scans[0].cvParam(pwiz.CLI.cv.CVID.MS_scan_start_time).timeInSeconds() / 60.0;
csvWriter.AddLine((i + 1) + "," + retention_time + "," + mySpec.cvParam(pwiz.CLI.cv.CVID.MS_ms_level).value);
}
csvWriter.WriteToFile();
}
public static void ExportAllVariables(string fileName, Dictionary <DateTime, List <Variable> > DicOfTime, Dictionary <string, List <Variable> > DicOfVar, Dictionary <string, double> DicOfCorr)
{
vsCSVWriter writer = new vsCSVWriter(fileName);
string title = "Date";
string corr = "";
foreach (string key in DicOfVar.Keys)
{
title += "," + key;
corr += "," + DicOfCorr[key];
}
writer.AddLine(title);
writer.AddLine(corr);
foreach (DateTime key in DicOfTime.Keys)
{
string newLine = key.ToString();
foreach (string nameToMatch in DicOfVar.Keys)
{
string varVal = ",";
foreach (Variable v in DicOfTime[key])
{
if (v.name.CompareTo(nameToMatch) == 0)
{
if (v.name.CompareTo("price") == 0)
{
varVal = "," + v.value;
}
else
{
varVal = "," + v.normValue;
}
}
}
newLine += varVal;
}
writer.AddLine(newLine);
}
writer.WriteToFile();
}
public static bool MascotCompare()
{
List <string> listMascotFiles = new List <string>();
listMascotFiles.Add(@"N:\Thibault\Frederic Lamoliatte\Olivier\no MSed.csv");
listMascotFiles.Add(@"N:\Thibault\Frederic Lamoliatte\Olivier\MSed1.csv");
listMascotFiles.Add(@"N:\Thibault\Frederic Lamoliatte\Olivier\MSed2.csv");
Dictionary <string, string[]> dicOfPep = new Dictionary <string, string[]>();
for (int i = 0; i < listMascotFiles.Count; i++)
{
vsCSV csv = new vsCSV(listMascotFiles[i]);
foreach (string line in csv.LINES_LIST)
{
string[] splits = line.Split(vsCSV._Generic_Separator);
if (splits.Length > 26)
{
string key = splits[1] + "," + splits[33];
if (!dicOfPep.ContainsKey(key))//raw+scan+seq+mod
{
dicOfPep.Add(key, new string[3]);
}
dicOfPep[key][i] = "," + splits[13] + "," + splits[14] + "," + splits[18] + "," + splits[26];
}
}
}
vsCSVWriter writer = new vsCSVWriter(@"C:\_IRIC\DATA\Sumo\outputCompare.csv");
foreach (string key in dicOfPep.Keys)
{
string str = key;
for (int i = 0; i < listMascotFiles.Count; i++)
{
if (dicOfPep[key][i] != null)
{
str += dicOfPep[key][i];
}
else
{
str += ",,,,";
}
}
writer.AddLine(str);
}
writer.WriteToFile();
return(true);
}
public static void AddIPIToUbiPredFile(string fastaFile, string csvUbiFile, string csvFileOut)
{
vsCSV csv = new vsCSV(csvUbiFile);
vsCSVWriter writer = new vsCSVWriter(csvFileOut);
try
{
FileStream fs;
try
{
fs = new FileStream(fastaFile, FileMode.Open, FileAccess.Read, FileShare.Read);
}
catch (System.Exception)
{
fs = new FileStream(fastaFile, FileMode.Open, FileAccess.Read, FileShare.ReadWrite);
}
Dictionary <int, string> IDs = new Dictionary <int, string>();
using (StreamReader sr = new StreamReader(fs))
{
int idNb = 0;
string line;
while ((line = sr.ReadLine()) != null)
{
if (line.StartsWith(">"))
{
idNb++;
foreach (string csvLine in csv.LINES_LIST)
{
string[] splits = csvLine.Split(vsCSV._Generic_Separator);
if (line.Contains(splits[1]))
{
writer.AddLine(csvLine + "," + line.Substring(splits[1].Length + 1, 13));
}
}
}
}
}
fs.Close();
writer.WriteToFile();
}
catch (System.Exception ex)
{
Console.WriteLine(ex.Message);
Console.WriteLine(ex.StackTrace);
}
}
public static void AppendUbiPredToMascotReport(string csvUbiFile, string csvMascotFile, string csvFileOut)
{
vsCSV csvUbi = new vsCSV(csvUbiFile);
vsCSV csvMascot = new vsCSV(csvMascotFile);
vsCSVWriter writer = new vsCSVWriter(csvFileOut);
try
{
foreach (string lineMascot in csvMascot.LINES_LIST)
{
string strToAppend = "";
try
{
string[] mSplits = lineMascot.Split(vsCSV._Generic_Separator);
if (mSplits.Length >= 17 && !lineMascot.StartsWith("Search"))
{
int indexStart = int.Parse(mSplits[16]);
int indexStop = int.Parse(mSplits[17]);
foreach (string lineUbi in csvUbi.LINES_LIST)
{
string[] splits = lineUbi.Split(vsCSV._Generic_Separator);
int indexUbi = int.Parse(splits[2]);
if (splits[4].Contains(mSplits[3]) && indexUbi >= indexStart && indexUbi <= indexStop)
{
strToAppend += "," + splits[2] + "," + splits[3];
}
}
}
}
catch (System.Exception ex)
{
Console.WriteLine(ex.Message);
Console.WriteLine(ex.StackTrace);
}
writer.AddLine(lineMascot + strToAppend);
}
writer.WriteToFile();
}
catch (System.Exception ex)
{
Console.WriteLine(ex.Message);
Console.WriteLine(ex.StackTrace);
}
}
public void ExportFragmentIntensities(List <PeptideSpectrumMatch> psms, Peptide peptide, int psmCharge, string fileName)
{
vsCSVWriter writer = new vsCSVWriter(fileName);
List <FragmentClass> fragments = new List <FragmentClass>();
foreach (FragmentClass fragment in dbOptions.fragments)
//foreach (string fragment in FragmentDictionary.Fragments.Keys)
{
bool found = false;
foreach (ProductMatch match in dbOptions.fragments.ComputeFragments(peptide, psmCharge, dbOptions))
{
if (fragment == match.Fragment)
{
found = true;
break;
}
}
if (found)
{
fragments.Add(fragment);
}
}
string title = "Cumulated Product Intensities";
for (int charge = 1; charge <= psmCharge; charge++)
{
foreach (FragmentClass fragment in dbOptions.fragments)
{
title += "," + fragment.Name + " ^" + charge;
}
}
for (int charge = 1; charge <= psmCharge; charge++)
{
foreach (FragmentClass fragment in fragments)
{
title += "," + fragment.Name + " ^" + charge;
}
}
writer.AddLine(title);
for (int i = 1; i <= peptide.Length; i++)
{
string line = i.ToString();
for (int charge = 1; charge <= psmCharge; charge++)
{
foreach (FragmentClass fragment in dbOptions.fragments)
{
double cumul = 0.0;
foreach (PeptideSpectrumMatch psm in psms)
{
foreach (ProductMatch match in psm.AllProductMatches)
{
if (fragment == match.Fragment && match.fragmentPos == i && match.charge == charge)
{
cumul += match.obsIntensity;
}
}
}
line += "," + cumul;
}
}
for (int charge = 1; charge <= psmCharge; charge++)
{
foreach (FragmentClass fragment in fragments)
{
double cumul = 0.0;
foreach (PeptideSpectrumMatch psm in psms)
{
foreach (ProductMatch match in psm.AllProductMatches)
{
if (fragment == match.Fragment && match.fragmentPos == i && match.charge == charge)
{
cumul += match.obsIntensity;
}
}
}
line += "," + cumul;
}
}
writer.AddLine(line);
}
writer.WriteToFile();
}
public static void YangLiuPeptidesWithAllProteins()
{
//vsCSV csvPeptides = new vsCSV(@"G:\Thibault\-=Proteomics_Raw_Data=-\ELITE\DEC18_2012\DMatton\Clustering_186716\Identifications.csv");
vsCSV csvPeptides = new vsCSV(@"G:\Thibault\-=Proteomics_Raw_Data=-\ELITE\DEC18_2012\DMatton\Clustering_186716\Cluster_Intensity_peptides_NormP.csv");
vsCSVWriter writer = new vsCSVWriter(@"G:\Thibault\-=Proteomics_Raw_Data=-\ELITE\DEC18_2012\DMatton\Clustering_186716\ProteinsPerPeptidesFromDatabases_AllReadingFrames.csv");
NucleicAcid.InitHash();
FileStream protein_fasta_database1 = new FileStream(@"G:\Thibault\Olivier\Databases\DMatton\Matton_Illumina_Anthesis_WithReverse.fasta", FileMode.Open, FileAccess.Read, FileShare.Read);
List <Protein> proteins1 = new List <Protein>(ProteinFastaReader.ReadProteins(protein_fasta_database1, false));
Dictionary <string, List <string> > protein1AAs = new Dictionary <string, List <string> >();
foreach (Protein prot in proteins1)
{
for (int shift = 0; shift < 3; shift++)
{
protein1AAs.Add(prot.Description + " | Reading Frame " + shift + " | Forward", NucleicAcid.ConvertNA3ToAAs(prot.BaseSequence, shift, false));
protein1AAs.Add(prot.Description + " | Reading Frame " + shift + " | Backward", NucleicAcid.ConvertNA3ToAAs(prot.BaseSequence, shift, true));
}
}
FileStream protein_fasta_database2 = new FileStream(@"G:\Thibault\Olivier\Databases\DMatton\mattond_20110418_WithReverse_EditedJuly2013.fasta", FileMode.Open, FileAccess.Read, FileShare.Read);
List <Protein> proteins2 = new List <Protein>(ProteinFastaReader.ReadProteins(protein_fasta_database2, false));
Dictionary <string, List <string> > protein2AAs = new Dictionary <string, List <string> >();
foreach (Protein prot in proteins2)
{
for (int shift = 0; shift < 3; shift++)
{
protein2AAs.Add(prot.Description + " | Reading Frame " + shift + " | Forward", NucleicAcid.ConvertNA3ToAAs(prot.BaseSequence, shift, false));
protein2AAs.Add(prot.Description + " | Reading Frame " + shift + " | Backward", NucleicAcid.ConvertNA3ToAAs(prot.BaseSequence, shift, true));
}
}
writer.AddLine(csvPeptides.LINES_LIST[0]);
Dictionary <string, List <string> > dicOfPepProt = new Dictionary <string, List <string> >();
for (int i = 1; i < csvPeptides.LINES_LIST.Count; i++)
{
string[] splits = csvPeptides.LINES_LIST[i].Split(vsCSV._Generic_Separator);
string seq = splits[4];
//string seq = splits[13];
/*
* string protDesc = splits[10];
* if (protein1AAs.ContainsKey(protDesc))
* if (!protein1AAs[protDesc].Contains(seq))
* Console.WriteLine("Should be there 1");
*
* if (protein2AAs.ContainsKey(protDesc))
* if (!protein2AAs[protDesc].Contains(seq))
* Console.WriteLine("Should be there 1");
* //*/
StringBuilder sb = new StringBuilder();
foreach (string key in protein1AAs.Keys)
{
foreach (string protSeq in protein1AAs[key])
{
if (protSeq.Contains(seq))
{
sb.Append(key + ";");
break;
}
}
}
foreach (string key in protein2AAs.Keys)
{
foreach (string protSeq in protein2AAs[key])
{
if (protSeq.Contains(seq))
{
sb.Append(key + ";");
break;
}
}
}
if (sb.Length == 0)
{
Console.WriteLine("Zut");
}
writer.AddLine(csvPeptides.LINES_LIST[i] + "," + sb.ToString().Trim());
}
writer.WriteToFile();
}
public void WriteFragmentation(bool target)
{
vsCSVWriter writer = new vsCSVWriter(dbOptions.OutputFolder + "FragmentStats_" + (target ? "Targets" : "Decoy") + ".csv");
writer.AddLine(" === Fragmentation of " + (target ? "Targets" : "Decoys") + " ===");
foreach (FragmentClass fragment in dbOptions.fragments)
{
double cumulIntensity = 0;
int nbFrag = 0;
Dictionary <int, int> positions = new Dictionary <int, int>();
foreach (Precursor precursor in matchedPrecursors)
{
PeptideSpectrumMatch psm = precursor.OptimizedBestPsm();
if (psm.Target == target)
{
foreach (ProductMatch match in psm.AllProductMatches)
{
if (fragment == match.Fragment)
{
nbFrag++;
if (!positions.ContainsKey(match.fragmentPos))
{
positions.Add(match.fragmentPos, 1);
}
else
{
positions[match.fragmentPos]++;
}
cumulIntensity += match.obsIntensity;
}
}
}
}
string strPos = "";
if (positions.Count > 0)
{
foreach (int key in positions.Keys)
{
strPos += "|" + key + ":" + positions[key];
}
}
else
{
strPos += ",";
}
writer.AddLine(" " + fragment.Name + ", Number of fragments = , " + nbFrag + ", Intensity = ," + cumulIntensity + ", fragment matched [" + strPos.Substring(1) + "]");
}
foreach (FragmentClass fragment in dbOptions.fragments)
//foreach (string fragment in FragmentDictionary.Fragments.Keys)
{
double cumulIntensity = 0;
int nbFrag = 0;
foreach (Precursor precursor in matchedPrecursors)
{
PeptideSpectrumMatch psm = precursor.OptimizedBestPsm();
if (psm.Target == target)
{
foreach (ProductMatch match in psm.AllProductMatches)
{
if (fragment == match.Fragment)
{
nbFrag++;
cumulIntensity += match.obsIntensity;
}
}
}
}
writer.AddLine(" " + fragment + ", Number of fragments = ," + nbFrag + ", Intensity = ," + cumulIntensity);
}
foreach (FragmentClass fragment in dbOptions.fragments)
//foreach (string fragment in FragmentDictionary.AAFragments.Keys)
{
double cumulIntensity = 0;
int nbFrag = 0;
foreach (Precursor precursor in matchedPrecursors)
{
PeptideSpectrumMatch psm = precursor.OptimizedBestPsm();
if (psm.Target == target)
{
foreach (ProductMatch match in psm.AllProductMatches)
{
if (fragment == match.Fragment)
{
nbFrag++;
cumulIntensity += match.obsIntensity;
}
}
}
}
writer.AddLine(" " + fragment + ", Number of fragments = ," + nbFrag + ", Intensity = ," + cumulIntensity);
}
writer.WriteToFile();
}
public void ExportFragments(PeptideSpectrumMatch psm)
{
vsCSVWriter writer = new vsCSVWriter(dbOptions.OutputFolder + psm.Peptide.Sequence + "_" + vsCSV.GetFileName_NoExtension(psm.Query.sample.sSDF) + "_" + psm.Query.precursor.Track.RT + ".csv");
List <FragmentClass> fragments = new List <FragmentClass>();
foreach (FragmentClass fragment in dbOptions.fragments)
//foreach (string fragment in FragmentDictionary.Fragments.Keys)
{
bool found = false;
foreach (ProductMatch match in dbOptions.fragments.ComputeFragments(psm.Peptide, psm.Query.precursor.Charge, dbOptions))
{
if (fragment == match.Fragment)
{
found = true;
break;
}
}
if (found)
{
fragments.Add(fragment);
}
}
string title = "Theoretical Fragments";
for (int charge = 1; charge <= psm.Query.precursor.Charge; charge++)
{
foreach (FragmentClass fragment in dbOptions.fragments)
{
title += "," + fragment.Name + " ^" + charge;
}
}
for (int charge = 1; charge <= psm.Query.precursor.Charge; charge++)
{
foreach (FragmentClass fragment in fragments)
{
title += "," + fragment.Name + " ^" + charge;
}
}
writer.AddLine(title);
for (int i = 1; i <= psm.Peptide.Length; i++)
{
string line = i.ToString();
for (int charge = 1; charge <= psm.Query.precursor.Charge; charge++)
{
foreach (FragmentClass fragment in dbOptions.fragments)
{
bool found = false;
foreach (ProductMatch match in dbOptions.fragments.ComputeFragments(psm.Peptide, psm.Query.precursor.Charge, dbOptions))
{
if (fragment == match.Fragment && match.fragmentPos == i && match.charge == charge)
{
line += "," + match.theoMz;
found = true;
break;
}
}
if (!found)
{
line += ",";
}
}
}
for (int charge = 1; charge <= psm.Query.precursor.Charge; charge++)
{
foreach (FragmentClass fragment in fragments)
{
bool found = false;
foreach (ProductMatch match in dbOptions.fragments.ComputeFragments(psm.Peptide, psm.Query.precursor.Charge, dbOptions))
{
if (fragment == match.Fragment && match.fragmentPos == i && match.charge == charge)
{
line += "," + match.theoMz;
found = true;
break;
}
}
if (!found)
{
line += ",";
}
}
}
writer.AddLine(line);
}
title = "Observed Fragments Intensities";
for (int charge = 1; charge <= psm.Query.precursor.Charge; charge++)
{
foreach (FragmentClass fragment in dbOptions.fragments)
{
title += "," + fragment.Name + " ^" + charge;
}
}
for (int charge = 1; charge <= psm.Query.precursor.Charge; charge++)
{
foreach (FragmentClass fragment in fragments)
{
title += "," + fragment.Name + " ^" + charge;
}
}
writer.AddLine(title);
for (int i = 1; i <= psm.Peptide.Length; i++)
{
string line = i.ToString();
for (int charge = 1; charge <= psm.Query.precursor.Charge; charge++)
{
foreach (FragmentClass fragment in dbOptions.fragments)
{
bool found = false;
foreach (ProductMatch match in psm.AllProductMatches)
{
if (fragment == match.Fragment && match.fragmentPos == i && match.charge == charge)
{
line += "," + match.obsIntensity;
found = true;
break;
}
}
if (!found)
{
line += ",";
}
}
}
for (int charge = 1; charge <= psm.Query.precursor.Charge; charge++)
{
foreach (FragmentClass fragment in fragments)
{
bool found = false;
foreach (ProductMatch match in psm.AllProductMatches)
{
if (fragment == match.Fragment && match.fragmentPos == i && match.charge == charge)
{
line += "," + match.obsIntensity;
found = true;
break;
}
}
if (!found)
{
line += ",";
}
}
}
writer.AddLine(line);
}
title = "Observed Fragments Mz";
for (int charge = 1; charge <= psm.Query.precursor.Charge; charge++)
{
foreach (FragmentClass fragment in dbOptions.fragments)
{
title += "," + fragment.Name + " ^" + charge;
}
}
for (int charge = 1; charge <= psm.Query.precursor.Charge; charge++)
{
foreach (FragmentClass fragment in fragments)
{
title += "," + fragment.Name + " ^" + charge;
}
}
writer.AddLine(title);
for (int i = 1; i <= psm.Peptide.Length; i++)
{
string line = i.ToString();
for (int charge = 1; charge <= psm.Query.precursor.Charge; charge++)
{
foreach (FragmentClass fragment in dbOptions.fragments)
{
bool found = false;
foreach (ProductMatch match in psm.AllProductMatches)
{
if (fragment == match.Fragment && match.fragmentPos == i && match.charge == charge)
{
line += "," + match.obsMz;
found = true;
break;
}
}
if (!found)
{
line += ",";
}
}
}
for (int charge = 1; charge <= psm.Query.precursor.Charge; charge++)
{
foreach (FragmentClass fragment in fragments)
{
bool found = false;
foreach (ProductMatch match in psm.AllProductMatches)
{
if (fragment == match.Fragment && match.fragmentPos == i && match.charge == charge)
{
line += "," + match.obsMz;
found = true;
break;
}
}
if (!found)
{
line += ",";
}
}
}
writer.AddLine(line);
}
title = "Error on Fragments";
for (int charge = 1; charge <= psm.Query.precursor.Charge; charge++)
{
foreach (FragmentClass fragment in dbOptions.fragments)
{
title += "," + fragment.Name + " ^" + charge;
}
}
for (int charge = 1; charge <= psm.Query.precursor.Charge; charge++)
{
foreach (FragmentClass fragment in fragments)
{
title += "," + fragment.Name + " ^" + charge;
}
}
writer.AddLine(title);
for (int i = 1; i <= psm.Peptide.Length; i++)
{
string line = i.ToString();
for (int charge = 1; charge <= psm.Query.precursor.Charge; charge++)
{
foreach (FragmentClass fragment in dbOptions.fragments)
{
bool found = false;
foreach (ProductMatch match in psm.AllProductMatches)
{
if (fragment == match.Fragment && match.fragmentPos == i && match.charge == charge)
{
line += "," + match.mass_diff;
found = true;
break;
}
}
if (!found)
{
line += ",";
}
}
}
for (int charge = 1; charge <= psm.Query.precursor.Charge; charge++)
{
foreach (FragmentClass fragment in fragments)
{
bool found = false;
foreach (ProductMatch match in psm.AllProductMatches)
{
if (fragment == match.Fragment && match.fragmentPos == i && match.charge == charge)
{
line += "," + match.mass_diff;
found = true;
break;
}
}
if (!found)
{
line += ",";
}
}
}
writer.AddLine(line);
}
writer.WriteToFile();
}
public static void FromFolderWithRetentionTimeCSV(string mascotReportCSVFile, string folder, string outputCSV)
{
string[] files = Directory.GetFiles(folder, "*_RetentionTimes.csv");
List <vsCSV> RTs = new List <vsCSV>();
foreach (string file in files)
{
RTs.Add(new vsCSV(file));
}
vsCSVWriter writer = new vsCSVWriter(outputCSV);
vsCSV mascotReport = new vsCSV(mascotReportCSVFile);
int indexScanNumber = -1;
int indexFileName = -1;
int indexRetentionTime = -1;
bool isContent = false;
for (int i = 0; i < mascotReport.LINES_LIST.Count; i++)
{
string line = mascotReport.LINES_LIST[i];
string[] splits = line.Split(vsCSV._Generic_Separator);
if (line.Contains("Scan Number"))
{
indexScanNumber = vsCSV.GetColumnIndex(splits, "Scan Number");
}
if (line.Contains("FileName"))
{
indexFileName = vsCSV.GetColumnIndex(splits, "FileName");
}
if (line.Contains("Pep Elution Time"))
{
indexRetentionTime = vsCSV.GetColumnIndex(splits, "Pep Elution Time");
}
if (isContent)
{
string[] strScanSplits = splits[indexScanNumber].Split('-');
int tmpScan = 0;
for (int k = 0; k < strScanSplits.Length; k++)
{
tmpScan += int.Parse(strScanSplits[k]);
}
string file = vsCSV.GetFileName_NoExtension(splits[indexFileName]);
string rt = "";
for (int j = 0; j < files.Length; j++)
{
if (files[j].Contains(file))
{
rt = RTs[j].LINES_LIST[tmpScan].Split(vsCSV._Generic_Separator)[1];
break;
}
}
splits[indexRetentionTime] = rt;
line = vsCSV.Concatenate(splits, ",");
}
if (indexScanNumber >= 0 && indexScanNumber < splits.Length &&
indexFileName >= 0 && indexFileName < splits.Length &&
indexRetentionTime >= 0 && indexRetentionTime < splits.Length)
{
isContent = true;
}
writer.AddLine(line);
}
writer.WriteToFile();
}
/// <summary>
/// Provides deconvoluted elution curves of mixed spectra from the provided raw files using the provided synthetic raw file
/// Exports in CSV files and stores everything in class objects
/// </summary>
/// <param name="spikedRaws"></param>
/// <param name="mixedRaws"></param>
/// <param name="fastaFile"></param>
/// <param name="folderToOutputTo"></param>
/// <param name="conSol"></param>
public void Solve(string[] spikedRaws, string[] mixedRaws, string fastaFile, string folderToOutputTo, IConSol conSol)
{
dbOptions = CreateOptions(fastaFile, folderToOutputTo, precTolPpm, prodTolDa, conSol);
SpikedSamples = new Samples(dbOptions);
for (int i = 0; i < spikedRaws.Length; i++)
{
SpikedSamples.Add(new Sample(i + 1, 1, 1, spikedRaws[i], spikedRaws[i], 0, ""));
}
//Precompute Spiked peptide identifications
SpikedResult = Ace.Start(dbOptions, SpikedSamples, false, false);
SpikedResult.ExportPSMs(1, dbOptions.OutputFolder + "Identifications" + System.IO.Path.DirectorySeparatorChar + "SpikedSamplesPSMs.csv");
MixedSamples = new Samples(dbOptions);
for (int i = 0; i < mixedRaws.Length; i++)
{
MixedSamples.Add(new Sample(i + 1, 1, 1, mixedRaws[i], mixedRaws[i], 0, ""));
}
//Precompute Mixed peptide identifications
mixedResult = Ace.Start(dbOptions, MixedSamples, false, false);
if (mixedResult == null)
{
conSol.WriteLine("OOPS! No queries could be extracted from the list of mixed spectrum files...");
}
else
{
mixedResult.ExportPSMs(1, dbOptions.OutputFolder + "Identifications" + System.IO.Path.DirectorySeparatorChar + "MixedSamplesPSMs.csv");
conSol.WriteLine("Computing gradient descents...");
//Compute all usable spiked peptides
characterizedPeptides = CharacterizedPrecursor.GetSpikedPrecursors(SpikedSamples, SpikedResult, dbOptions, nbMinFragments, nbMaxFragments);
ExportSpikedSampleResult(characterizedPeptides, dbOptions);
vsCSVWriter writerCumul = new vsCSVWriter(OutputFolder + "Results.csv");
string titleCombined = "Mixed Sample,Precursor";
string curveStr = "Polynomial Curve,";
string spikedIntensityStr = "Area under the curve,";
foreach (double precursor in characterizedPeptides.Keys)
{
foreach (CharacterizedPrecursor charPrec in characterizedPeptides[precursor].Values)
{
titleCombined += "," + charPrec.Peptide.Sequence + " Charge " + charPrec.Charge;
if (charPrec.eCurveIntensityCount.Coefficients != null && charPrec.eCurveIntensityCount.Coefficients.Length == 3)
{
curveStr += "," + charPrec.eCurveIntensityCount.Coefficients[0] + "x^2 + " + charPrec.eCurveIntensityCount.Coefficients[1] + "x" + charPrec.eCurveIntensityCount.Coefficients[2];
}
else
{
curveStr += ",NA";
}
spikedIntensityStr += "," + charPrec.eCurveIntensityCount.Area;
}
}
writerCumul.AddLine(titleCombined);
writerCumul.AddLine(curveStr);
writerCumul.AddLine(spikedIntensityStr);
mixedPrecursors = new Dictionary <Sample, List <MixedPrecursor> >();
foreach (Sample mixedSample in MixedSamples)
{
mixedPrecursors.Add(mixedSample, MixedPrecursor.GetMixedPrecursors(mixedSample, mixedResult, dbOptions, characterizedPeptides));
}
//Get the list of precursors to characterize
foreach (Sample mixedSample in MixedSamples)
{
foreach (double keyMz in characterizedPeptides.Keys)
{
List <Dictionary <CharacterizedPrecursor, MaxFlowElutionCurve> > listOfRatios = new List <Dictionary <CharacterizedPrecursor, MaxFlowElutionCurve> >();
foreach (MixedPrecursor mPrec in mixedPrecursors[mixedSample])
{
if (mPrec.MZ == keyMz)
{
// Compute Max Flow for this precursor
Dictionary <CharacterizedPrecursor, MaxFlowElutionCurve> ratios = GetRatios(characterizedPeptides, mPrec, dbOptions, nbMinFragments, nbMaxFragments);
listOfRatios.Add(ratios);
ExportMixedSampleResult(ratios, mixedSample, mPrec, keyMz, dbOptions);
}
}
bool isEmpty = true;
string resultStr = vsCSV.GetFileName(mixedSample.sSDF) + "," + keyMz;
foreach (double precursor in characterizedPeptides.Keys)
{
foreach (CharacterizedPrecursor charPrec in characterizedPeptides[precursor].Values)
{
double cumulArea = 0.0;
foreach (Dictionary <CharacterizedPrecursor, MaxFlowElutionCurve> ratios in listOfRatios)
{
if (ratios.ContainsKey(charPrec))
{
cumulArea += ratios[charPrec].eCurvePerMs.Area;
}
}
resultStr += "," + cumulArea;
if (cumulArea > 0)
{
isEmpty = false;
}
}
}
if (!isEmpty)
{
writerCumul.AddLine(resultStr);
}
}
}
writerCumul.WriteToFile();
//List Modifications
Dictionary <Modification, double> dicOfIntensityPerMod = new Dictionary <Modification, double>();
foreach (Sample sample in mixedPrecursors.Keys)
{
foreach (MixedPrecursor mP in mixedPrecursors[sample])
{
foreach (CharacterizedPrecursor cP in mP.PeptideRatios.Keys)
{
if (cP.Peptide.VariableModifications != null)
{
foreach (Modification mod in cP.Peptide.VariableModifications.Values)
{
if (!dicOfIntensityPerMod.ContainsKey(mod))
{
dicOfIntensityPerMod.Add(mod, 0.0);
}
}
}
}
}
}
//Compute site occupancy for identical sequences (real positionnal isomers)
vsCSVWriter writerSitesOccupancy = new vsCSVWriter(OutputFolder + "Results_SiteOccupancy.csv");
List <Protein> AllProteins = Ace.ReadProteomeFromFasta(fastaFile, false, dbOptions);
foreach (Protein protein in AllProteins)
{
string newTitleProtein = protein.Description.Replace(',', ' ') + "," + protein.Sequence;
for (int i = 0; i < protein.Sequence.Length; i++)
{
newTitleProtein += "," + protein[i].ToString();
}
writerSitesOccupancy.AddLine(newTitleProtein);
foreach (Sample mixedSample in mixedPrecursors.Keys)
{
string coverage = "Coverage," + mixedSample.Name;
for (int i = 0; i < protein.Sequence.Length; i++)
{
double cumulSite = 0.0;
newTitleProtein += "," + protein[i].ToString();
foreach (MixedPrecursor mP in mixedPrecursors[mixedSample])
{
foreach (CharacterizedPrecursor cP in mP.PeptideRatios.Keys)
{
if (i + 1 >= cP.Peptide.StartResidueNumber && i + 1 <= cP.Peptide.EndResidueNumber)
{
cumulSite += mP.PeptideRatios[cP].eCurvePerMs.Area;
}
}
}
coverage += "," + cumulSite;
}
writerSitesOccupancy.AddLine(coverage);
}
foreach (Modification mod in dicOfIntensityPerMod.Keys)
{
Dictionary <Sample, string> dicOfLines = new Dictionary <Sample, string>();
for (int i = 0; i < protein.Sequence.Length; i++)
{
foreach (Sample mixedSample in mixedPrecursors.Keys)
{
double cumulModArea = 0.0;
foreach (MixedPrecursor mP in mixedPrecursors[mixedSample])
{
foreach (CharacterizedPrecursor cP in mP.PeptideRatios.Keys)
{
if (i + 1 >= cP.Peptide.StartResidueNumber && i + 1 <= cP.Peptide.EndResidueNumber &&
cP.Peptide.VariableModifications != null)
{
foreach (int pos in cP.Peptide.VariableModifications.Keys)
{
if (cP.Peptide.StartResidueNumber + pos - 2 == i + 1 && cP.Peptide.VariableModifications[pos] == mod)
{
cumulModArea += mP.PeptideRatios[cP].eCurvePerMs.Area;
}
}
}
}
}
if (!dicOfLines.ContainsKey(mixedSample))
{
dicOfLines.Add(mixedSample, mod.Description + "," + mixedSample.Name + "," + cumulModArea);
}
else
{
dicOfLines[mixedSample] += "," + cumulModArea;
}
}
}
foreach (string line in dicOfLines.Values)
{
writerSitesOccupancy.AddLine(line);
}
}
}
writerSitesOccupancy.WriteToFile();
}
}
public static void ComputeSequenceFROverlap(string fastaFile, bool addReverse, string csvFileOut)
{
try
{
FileStream fs;
try
{
fs = new FileStream(fastaFile, FileMode.Open, FileAccess.Read, FileShare.Read);
}
catch (System.Exception)
{
fs = new FileStream(fastaFile, FileMode.Open, FileAccess.Read, FileShare.ReadWrite);
}
Dictionary <char, Dictionary <string, long> > DicOfSeq = new Dictionary <char, Dictionary <string, long> >(30);
for (int i = 0; i < 26; i++)
{
DicOfSeq.Add((char)('A' + i), new Dictionary <string, long>());
}
using (StreamReader sr = new StreamReader(fs))
{
string line;
while ((line = sr.ReadLine()) != null)
{
if (!line.StartsWith(">"))
{
if (DicOfSeq[line[0]].ContainsKey(line))
{
DicOfSeq[line[0]][line] += 1;
}
else
{
DicOfSeq[line[0]].Add(line, 1);
}
if (addReverse)
{
string rev = Reverse(line);
if (DicOfSeq[line[0]].ContainsKey(rev))
{
DicOfSeq[line[0]][rev] += 1;
}
else
{
DicOfSeq[line[0]].Add(rev, 1);
}
}
}
}
}
fs.Close();
Dictionary <long, long> DicOfNb = new Dictionary <long, long>();
for (long i = 1; i <= 40; i++)
{
DicOfNb.Add(i, 0);
}
for (int i = 0; i < 26; i++)
{
foreach (long val in DicOfSeq[(char)('A' + i)].Values)
{
if (DicOfNb.ContainsKey(val))
{
DicOfNb[val] += 1;
}
else
{
DicOfNb.Add(val, 1);
}
}
}
vsCSVWriter writer = new vsCSVWriter(csvFileOut);
foreach (long key in DicOfNb.Keys)
{
writer.AddLine(key + "," + DicOfNb[key]);
}
writer.WriteToFile();
}
catch (System.Exception ex)
{
Console.WriteLine(ex.Message);
Console.WriteLine(ex.StackTrace);
}
}
public static bool LysineConservation()
{
List <string> zincIDs = GetZincProteinsENSP();
Dictionary <string, List <int> > dicOfSites = ReadZNF(@"C:\_IRIC\DATA\Sumo\ZNF.csv");
string csvMatrix = @"C:\_IRIC\DATA\Sumo\matrix_human.tsv";
string csvToAnnotate = @"C:\_IRIC\DATA\Sumo\liste des sites SUMO.csv";
string output = @"C:\_IRIC\DATA\Sumo\outputL.csv";
string outputConservation = @"C:\_IRIC\DATA\Sumo\outputConservation.csv";
string outputAll = @"C:\_IRIC\DATA\Sumo\outputConservationAll_b.csv";
vsCSV csvM = new vsCSV(csvMatrix);
vsCSV csvA = new vsCSV(csvToAnnotate);
Dictionary <string, int> dicOfAnnotates = new Dictionary <string, int>();
for (int i = 1; i < csvA.LINES_LIST.Count; i++)
{
string[] items = csvA.LINES_LIST[i].Split(vsCSV._Generic_Separator);
dicOfAnnotates.Add(items[0] + items[5], i);
}
vsCSVWriter writer = new vsCSVWriter(output);
writer.AddLine(csvA.getFirstLine());
Dictionary <string, List <double> > dicOfAllAA = new Dictionary <string, List <double> >();
vsCSVWriter writerConsAll = new vsCSVWriter(outputAll);
StringBuilder sb = new StringBuilder();
for (char aa = 'A'; aa <= 'Z'; aa++)
{
dicOfAllAA.Add(aa.ToString(), new List <double>());
sb.Append(aa + ",");
}
sb.Append("SpecialK,ZincEveryWhere,ZincSumo");
dicOfAllAA.Add("SpecialK", new List <double>());
dicOfAllAA.Add("ZincEveryWhere", new List <double>());
dicOfAllAA.Add("ZincSumo", new List <double>());
writerConsAll.AddLine(sb.ToString());
writer.AddLine("AminoAcid,Some Number");
Dictionary <string, double> dicOfAA = new Dictionary <string, double>();
Dictionary <string, int> dicOfAANumber = new Dictionary <string, int>();
int nbK = 0;
List <double> echantillonageNoZero = new List <double>();
double value = 0;
for (int j = 0; j < csvM.LINES_LIST.Count; j++)
{
string[] splitsJ = csvM.LINES_LIST[j].Split('\t');
string aa = splitsJ[3];
if (!dicOfAA.ContainsKey(aa))
{
dicOfAANumber.Add(aa, 0);
dicOfAA.Add(aa, 0);
}
value = -1;
if (double.TryParse(splitsJ[5], out value))
{
dicOfAA[aa] += value;
dicOfAANumber[aa]++;
dicOfAllAA[aa].Add(value);
}
//string ensbJ = splitsJ[1];
//int positionJ = int.Parse(splitsJ[2]);
if ("K".CompareTo(aa) == 0)
{
value = -1;
if (double.TryParse(splitsJ[5], out value))
{
bool found = false;
foreach (string id in zincIDs)
{
if (id.CompareTo(splitsJ[1]) == 0)
{
found = true;
}
}
if (found)
{
dicOfAllAA["ZincEveryWhere"].Add(value);
}
if (dicOfSites.ContainsKey(splitsJ[1] + "|" + splitsJ[2]))
{
dicOfAllAA["ZincSumo"].Add(value);
}
echantillonageNoZero.Add(value);
if (dicOfAnnotates.ContainsKey(splitsJ[1] + splitsJ[2]))
{
if (!dicOfAA.ContainsKey("SpecialK"))
{
dicOfAANumber.Add("SpecialK", 0);
dicOfAA.Add("SpecialK", 0);
}
dicOfAA["SpecialK"] += value;
dicOfAANumber["SpecialK"]++;
dicOfAllAA["SpecialK"].Add(value);
nbK++;
writer.AddLine(csvA.LINES_LIST[dicOfAnnotates[splitsJ[1] + splitsJ[2]]] + "," + csvM.LINES_LIST[j].Replace('\t', ','));
}
}
}
}
writer.WriteToFile();
vsCSVWriter writerCons = new vsCSVWriter(outputConservation);
foreach (string key in dicOfAA.Keys)
{
writerCons.AddLine(key + "," + dicOfAA[key] / (double)dicOfAANumber[key]);
}
double meanNoZero = 0;
Random r = new Random();
for (int i = 0; i < nbK; i++)
{
int index = (int)Math.Floor(r.NextDouble() * (echantillonageNoZero.Count - 1));
meanNoZero += echantillonageNoZero[index];
}
writerCons.AddLine("Echantillonnage K," + meanNoZero / (double)nbK);
writerCons.WriteToFile();
int lineIndex = 0;
bool keepGoing = true;
while (keepGoing)
{
StringBuilder sb2 = new StringBuilder();
keepGoing = false;
foreach (string key in dicOfAllAA.Keys)
{
if (lineIndex < dicOfAllAA[key].Count)
{
sb2.Append(dicOfAllAA[key][lineIndex] + ",");
keepGoing = true;
}
else
{
sb2.Append(",");
}
}
writerConsAll.AddLine(sb2.ToString());
lineIndex++;
}
writerConsAll.WriteToFile();
return(true);
}
// Proteomics.Utilities.Fasta.FastaRead.AppendProteinDescriptionToMascotReport(@"C:\Users\caronlio\Downloads\filtered peptides.csv",
// @"C:\_IRIC\DATA\Tariq\peptideDb-minOcc60_WithReverse.fasta",
// @"C:\Users\caronlio\Downloads\filtered peptides_WithProteinDescriptions.csv");
//
public static void AppendhCKSAAPToMascotReport(string txtHCKSAAPFile, string csvMascotFile, string csvFileOut)
{
vsCSV csvUbi = new vsCSV(txtHCKSAAPFile);
vsCSV csvMascot = new vsCSV(csvMascotFile);
vsCSVWriter writer = new vsCSVWriter(csvFileOut);
try
{
foreach (string lineMascot in csvMascot.LINES_LIST)
{
string strToAppend = "";
try
{
string[] mSplits = lineMascot.Split(vsCSV._Generic_Separator);
if (mSplits.Length >= 17 && !lineMascot.StartsWith("Search"))
{
int indexStart = int.Parse(mSplits[16]);
int indexStop = int.Parse(mSplits[17]);
bool inIPI = false;
foreach (string lineUbi in csvUbi.LINES_LIST)
{
if (lineUbi.StartsWith(">"))
{
if (inIPI)
{
break;
}
inIPI = false;
if (lineUbi.StartsWith(">IPI:") && lineUbi.Contains(mSplits[3]))
{
inIPI = true;
}
}
if (inIPI)
{
string[] splits = lineUbi.Split('\t');
int indexPos = -1;
if (splits.Length > 6 && int.TryParse(splits[0], out indexPos))
{
if (indexPos >= indexStart && indexPos <= indexStop)
{
strToAppend += "," + splits[0] + "," + splits[5];
}
}
}
}
}
}
catch (System.Exception ex)
{
Console.WriteLine(ex.Message);
Console.WriteLine(ex.StackTrace);
}
writer.AddLine(lineMascot + strToAppend);
}
writer.WriteToFile();
}
catch (System.Exception ex)
{
Console.WriteLine(ex.Message);
Console.WriteLine(ex.StackTrace);
}
}
/// <summary>
/// Extract isomer ratios from a given spectrum (transformed into capacity vector)
/// </summary>
/// <param name="ratiosToFit"></param>
/// <param name="nbProductsToKeep"></param>
/// <param name="capacity"></param>
/// <param name="tolerance"></param>
/// <param name="PrecursorIntensityInCTrap"></param>
/// <param name="PrecursorIntensity"></param>
/// <param name="underFlow"></param>
/// <param name="percentError"></param>
/// <param name="ConSole"></param>
/// <returns></returns>
public static Dictionary <CharacterizedPrecursor, SolvedResult> SolveFromSpectrum(IEnumerable <CharacterizedPrecursor> ratiosToFit, int nbProductsToKeep,
IEnumerable <MsMsPeak> capacity, MassTolerance tolerance,
double PrecursorIntensityInCTrap, double PrecursorIntensity,
out double underFlow, out double percentError, IConSol ConSole, string fileOut = null)
{
bool keepGoing = true;
Dictionary <double, double> mixedSpectrum = new Dictionary <double, double>();
List <Dictionary <double, double> > unitSpectrum = new List <Dictionary <double, double> >();
foreach (CharacterizedPrecursor isomer in ratiosToFit)
{
foreach (double key in isomer.NormalizedFragments[nbProductsToKeep].Keys)
{
if (!mixedSpectrum.ContainsKey(key))
{
double cumulIntensity = 0.0;
foreach (MsMsPeak peak in capacity)
{
if (Math.Abs(Utilities.Numerics.CalculateMassError(peak.MZ, key, tolerance.Units)) <= tolerance.Value)
{
cumulIntensity += peak.Intensity;
}
}
mixedSpectrum.Add(key, cumulIntensity);// / PrecursorIntensityInCTrap);
}
}
if (isomer.NormalizedFragments.ContainsKey(nbProductsToKeep))
{
if (isomer.FragmentNormalizor.ContainsKey(nbProductsToKeep))
{
Dictionary <double, double> dic = new Dictionary <double, double>();
foreach (double key in isomer.NormalizedFragments[nbProductsToKeep].Keys)
{
dic.Add(key, isomer.NormalizedFragments[nbProductsToKeep][key] *
isomer.FragmentNormalizor[nbProductsToKeep].InterpolateIntensity(PrecursorIntensityInCTrap));
}
unitSpectrum.Add(dic);
}
else
{
unitSpectrum.Add(isomer.NormalizedFragments[nbProductsToKeep]);
}
}
else
{
keepGoing = false;
}
}
vsCSVWriter writerFrag = null;
if (!string.IsNullOrEmpty(fileOut))
{
writerFrag = new vsCSVWriter(fileOut);
string line = "Fragments:";
foreach (double key in mixedSpectrum.Keys)
{
line += "," + key;
}
writerFrag.AddLine(line);
line = "Mixed:";
foreach (double val in mixedSpectrum.Values)
{
line += "," + val;
}
writerFrag.AddLine(line);
}
//This nbProduct seems relevant, try to use isomer to get ratios for this spectrum
if (keepGoing)
{
List <double> solution = new List <double>();
double stepSize = PrecursorIntensityInCTrap / 1000.0;
if (stepSize < 1)
{
stepSize = 1;
}
double tmpUnderflow = 0;
Utilities.Methods.GradientDescent.SolveMaxFlowStyle(unitSpectrum, mixedSpectrum, out solution, out tmpUnderflow, ConSole, stepSize);
//Utilities.Methods.GradientDescent.SolveFromGradientDescent(unitSpectrum, mixedSpectrum, PrecursorIntensityInCTrap, out solution, out tmpUnderflow, ConSole);
double sumOfIntensities = 0;
foreach (double val in mixedSpectrum.Values)
{
sumOfIntensities += val;
}
underFlow = tmpUnderflow;
List <SolvedResult> result = GetResultList(solution, underFlow, sumOfIntensities);
Dictionary <CharacterizedPrecursor, SolvedResult> resultPerSample = new Dictionary <CharacterizedPrecursor, SolvedResult>();
int i = 0;
foreach (CharacterizedPrecursor key in ratiosToFit)
{
resultPerSample.Add(key, result[i]);
i++;
}
if (writerFrag != null)
{
foreach (CharacterizedPrecursor cPrec in ratiosToFit)
{
string line = cPrec.Peptide.Sequence;
foreach (double key in mixedSpectrum.Keys)
{
line += "," + cPrec.NormalizedFragments[nbProductsToKeep][key] * resultPerSample[cPrec].NbFitTimes;
}
writerFrag.AddLine(line);
}
writerFrag.WriteToFile();
}
percentError = (underFlow / sumOfIntensities);
return(resultPerSample);
}
else
{
percentError = 1.0;
underFlow = 0;
return(new Dictionary <CharacterizedPrecursor, SolvedResult>());
}
}
public static void Launch(IConSol console)
{
vsCSV csv = new vsCSV(@"C:\Users\caronlio\Downloads\Via.Science.Pre.Interview.Assignment.Data.2013.10.18.csv");
Dictionary <DateTime, List <Variable> > DicOfTime = new Dictionary <DateTime, List <Variable> >();
Dictionary <string, List <Variable> > DicOfVar = new Dictionary <string, List <Variable> >();
//Data sorted based on date
for (int i = 1; i < csv.LINES_LIST.Count; i++)
{
Variable tmpVar = new Variable(csv.LINES_LIST[i]);
if (!DicOfTime.ContainsKey(tmpVar.time))
{
DicOfTime.Add(tmpVar.time, new List <Variable>());
}
DicOfTime[tmpVar.time].Add(tmpVar);
if (!DicOfVar.ContainsKey(tmpVar.name))
{
DicOfVar.Add(tmpVar.name, new List <Variable>());
}
DicOfVar[tmpVar.name].Add(tmpVar);
}
foreach (string name in DicOfVar.Keys)
{
InterpolateMissingValues(name, DicOfTime, DicOfVar);
}
//Rebuild DicOfVar
DicOfVar.Clear();
foreach (List <Variable> list in DicOfTime.Values)
{
foreach (Variable variable in list)
{
if (!DicOfVar.ContainsKey(variable.name))
{
DicOfVar.Add(variable.name, new List <Variable>());
}
DicOfVar[variable.name].Add(variable);
}
}
//Compute Normalized values
NormalizeVariables(DicOfVar);
//Foreach variable, compare correlation with the "price" variable
List <double> prices = GetArrayofNormed("price", DicOfTime, DicOfVar);
Dictionary <string, double> DicOfCorrelation = new Dictionary <string, double>();
foreach (string name in DicOfVar.Keys)
{
List <double> normedVals = GetArrayofNormed(name, DicOfTime, DicOfVar);
double corr = MathNet.Numerics.Statistics.Correlation.Pearson(prices, normedVals);
if (name.CompareTo("price") == 0)
{
Console.WriteLine("test");
}
DicOfCorrelation.Add(name, corr);
}
//Prediction
vsCSVWriter output = new vsCSVWriter(@"C:\_IRIC\predictions.csv");
output.AddLine("Time,Price,Prediction");
foreach (DateTime time in DicOfTime.Keys)
{
double pred = 0;
foreach (string name in DicOfCorrelation.Keys)
{
if (name.CompareTo("price") != 0)
{
foreach (Variable v in DicOfTime[time])
{
if (v.name.CompareTo(name) == 0)
{
pred += DicOfCorrelation[name] * v.normValue;
}
}
}
}
pred *= 100000;
output.AddLine(pred.ToString());
}
output.WriteToFile();
//Export a csv of the varialbes, ordered by date
ExportAllVariables(@"C:\_IRIC\assignOut.csv", DicOfTime, DicOfVar, DicOfCorrelation);
Console.WriteLine("Done!");
}