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 static vsSDF LoadSDF(Sample project)
{
try
{
//if (project.m_vsSDF == null || string.Compare(project.m_vsSDF.m_name, project.sSDF) != 0)
//{
vsSDF result = null;
result = vsSDF.Load(project.sSDF, null);
result.MZ_GAPS = Proteomics.Cluster.Scoring.MzTol(result.MAX_MZ_VALUE);
project.sSDF = result.m_name;//Change the name in case there was misspelling fixed by the SDF.Load method
//project.m_vsSDF = result;
//}
return result;// project.m_vsSDF;
}
catch (Exception ex)
{
Sol.CONSOLE.OutputLine("Error jk302me :" + ex.Message + " " + ex.StackTrace);
return null;
}
}//*/
private void loadProjectFile(string project_file, int maxFractionSpreading)
{
// current line number in the project csv file
int lineNum = 0;
//vsList<stCondition> iterativeHelper = null;
try
{
this.Clear();
// project csv file is comma delimited
char[] splitter = { ',' };
vsCSV csvProject = new vsCSV(project_file);
for (int i = 0; i < csvProject.LINES_LIST.Count; i++)
{
try
{
string line = csvProject.LINES_LIST[i];
lineNum++;
string[] lineParts = line.Split(splitter);
// skip header line
if (lineNum == 1)
{
continue;
}
// project csv file format: REPLICATE,REPLICATE,FRACTION,peptide map location, sdf file location
// ex. 1,1,1,c:\work\adhoc\Promix_070706\Promix_10_070706_Out_peptides.csv,c:\work\adhoc\Promix_070706\Promix_10_070706_Out.sdf
int condition = int.Parse(lineParts[0]);
int replicate = int.Parse(lineParts[1]);
int fraction = int.Parse(lineParts[2]);
string peptideMap = lineParts[3];
string sdf = lineParts[4];
string nameCol = "";
if (lineParts.Length >= 6)
nameCol = lineParts[5];
// KE Aug 7 2008 - lower case
//OLI Why lower case? Files does not exist under linux!
this.Add(new Sample(condition, replicate, fraction, peptideMap, sdf, maxFractionSpreading, nameCol));
}
catch (System.Exception ex)
{
dbOptions.ConSole.WriteLine("Error sfj4aau34 : LineNum = " + lineNum + " " + ex.Message + " " + ex.StackTrace);
}
}
}
catch (Exception ex)
{
dbOptions.ConSole.WriteLine("Error sfj4u34 : " + ex.Message + " \n " + ex.StackTrace);
}
//ITERATIVE_HELPER = iterativeHelper;
// GenerateIterativeHelper();
// return iterativeHelper;
}
public static void FilterFromIDs(string fastaFileIn, string fastaFileOut, string csvFile)
{
vsCSV csv = new vsCSV(csvFile);
try
{
FileStream fs;
try
{
fs = new FileStream(fastaFileIn, FileMode.Open, FileAccess.Read, FileShare.Read);
}
catch (System.Exception)
{
fs = new FileStream(fastaFileIn, FileMode.Open, FileAccess.Read, FileShare.ReadWrite);
}
FileStream fsOut = new FileStream(fastaFileOut, FileMode.CreateNew);
using (StreamWriter sw = new StreamWriter(fsOut))
{
using (StreamReader sr = new StreamReader(fs))
{
string line;
bool ignore = true;
while ((line = sr.ReadLine()) != null)
{
if (line.StartsWith(">"))
{
ignore = true;
foreach (string id in csv.LINES_LIST)
{
if (line.Contains(id))
{
ignore = false;
break;
}
}
}
if (!ignore)
{
sw.WriteLine(line);
}
}
}
}
fsOut.Close();
fs.Close();
}
catch (System.Exception ex)
{
Console.WriteLine(ex.Message);
Console.WriteLine(ex.StackTrace);
}
}
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 Dictionary <string, List <int> > ReadZNF(string filename)
{
vsCSV csv = new vsCSV(filename);
Dictionary <string, List <int> > dicOfSites = new Dictionary <string, List <int> >();
for (int i = 0; i < csv.LINES_LIST.Count; i++)
{
string[] splits = csv.LINES_LIST[i].Split(vsCSV._Generic_Separator);
if (!dicOfSites.ContainsKey(splits[4] + "|" + splits[3]))
{
dicOfSites.Add(splits[4] + "|" + splits[3], new List <int>());
}
dicOfSites[splits[4] + "|" + splits[3]].Add(int.Parse(splits[3]));
}
return(dicOfSites);
}
public static Spectra Import(string filenameMSMS, string filenameTracks, DBOptions dbOptions)
{
Spectra spectra = new Spectra();
vsCSV csv = new vsCSV(filenameMSMS);
if (csv.LINES_LIST.Count == 0 || csv.LINES_LIST[0].CompareTo(ProductSpectrum.TITLE) != 0)
{
return(null);
}
for (int i = 1; i < csv.LINES_LIST.Count; i++)
{
string[] splits = csv.LINES_LIST[i].Split(vsCSV._Generic_Separator);
double mz = double.Parse(splits[3]);
int charge = int.Parse(splits[5]);
int nbPeaks = int.Parse(splits[9]);
GraphML_List <MsMsPeak> peaks = new GraphML_List <MsMsPeak>(nbPeaks);
i++;
for (int j = 0; j < nbPeaks; i++, j++)
{
try
{
string[] splitPeaks = csv.LINES_LIST[i].Split('\t');
if (splitPeaks.Length > 2)
{
peaks.Add(new MsMsPeak(double.Parse(splitPeaks[0]), double.Parse(splitPeaks[1]), int.Parse(splitPeaks[2])));
}
else
{
peaks.Add(new MsMsPeak(double.Parse(splitPeaks[0]), double.Parse(splitPeaks[1]), 0));
}
}
catch (Exception)
{
dbOptions.ConSole.WriteLine("Error parsing line : " + csv.LINES_LIST[i]);
}
}
spectra.AddMSMS(new ProductSpectrum(int.Parse(splits[0]), double.Parse(splits[1]), splits[2], mz, double.Parse(splits[4]), charge, Proteomics.Utilities.Numerics.MassFromMZ(mz, charge), peaks, double.Parse(splits[8]), double.Parse(splits[10]), double.Parse(splits[11])));
}
if (!string.IsNullOrEmpty(filenameTracks))
{
spectra.tracks = Tracks.Import(filenameTracks, dbOptions);
}
return(spectra);
}
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 static Tracks Import(string filename, DBOptions dbOptions)
{
vsCSV csv = new vsCSV(filename);
if (csv.LINES_LIST.Count == 0 || csv.LINES_LIST[0].CompareTo(Track.TITLE) != 0)
{
return(null);
}
Tracks tracks = new Tracks();
for (int i = 1; i < csv.LINES_LIST.Count; i++)
{
try
{
string[] splits = csv.LINES_LIST[i].Split(vsCSV._Generic_Separator);
tracks.AddTrack(double.Parse(splits[0]), double.Parse(splits[1]), double.Parse(splits[3]), double.Parse(splits[4]), double.Parse(splits[2]));
}
catch (Exception)
{
dbOptions.ConSole.WriteLine("Error parsing line : " + csv.LINES_LIST[i]);
}
}
return(tracks);
}
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 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);
}
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!");
}
// 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);
}
}
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();
}
