public void ReadInMLNFile(string filename, int _numdatasets)
{
// Read in MultiAlign file
// Note : sep 26, 2011 - This will need to be updated when the new MLN format comes out
CSVFileHandler CsvFileHandler2 = new CSVFileHandler(filename, CSVFileHandler.READ_ONLY);
CsvFileHandler2.openFile();
String[] Attributes2;
CsvFileHandler2.readLine();
while ((Attributes2 = CsvFileHandler2.readLine()) != null)
{
MultiAlignRecord mrecord = new MultiAlignRecord();
mrecord.ID = int.Parse(Attributes2[0]);
mrecord.Size = int.Parse(Attributes2[1]);
mrecord.Mass = double.Parse(Attributes2[2]);
mrecord.NET = double.Parse(Attributes2[3]);
mrecord.AllocateNumberDatasets(_numdatasets);
int n_dataset = 0;
for (int i = 4; i < Attributes2.Length; i += 4)
{
UMCRecord u = new UMCRecord();
if (Attributes2[i] != "")
{
u.ScanRep = int.Parse(Attributes2[i]);
u.Abundance = double.Parse(Attributes2[i + 1]);
u.ScanStart = int.Parse(Attributes2[i + 2]);
u.ScanEnd = int.Parse(Attributes2[i + 3]);
}
mrecord._AssociatedUMCRecords.Add(u);
n_dataset++;
}
AddRecord(mrecord);
}
}
/*public void WriteOutMapToCsv(ref Classes.MapRecord _glycoMap, string filename)
{
CSVFileHandler outfile = new CSVFileHandler(filename, CSVFileHandler.WRITE_ONLY);
outfile.openFile();
int numdatasets = _glycoMap._AssociatedDatasetNames.Count;
string[] header = { "ClusterID", "Mass", "NET" };
for (int i = 0; i < numdatasets; i++)
{
string[] ar2;
ar2 = new string[header.Length + 9];
header.CopyTo(ar2, 0);
ar2.SetValue("DatasetID" + "." + i.ToString(), header.Length);
ar2.SetValue("HCDScore" + "." + i.ToString(), header.Length + 1);
ar2.SetValue("CIDScore" + "." + i.ToString(), header.Length + 2);
ar2.SetValue("ETDScore" + "." + i.ToString(), header.Length + 3);
ar2.SetValue("Protein" + "." + i.ToString(), header.Length + 4);
ar2.SetValue("Peptide" + "." + i.ToString(), header.Length + 5);
ar2.SetValue("Site" + "." + i.ToString(), header.Length + 6);
ar2.SetValue("Glycan" + "." + i.ToString(), header.Length + 7);
ar2.SetValue("Abundance" + "." + i.ToString(), header.Length + 8);
header = ar2;
}
outfile.writeLine(header);
_glycoMap._AllMLNRecords.ForEach(delegate(Classes.MultiAlignRecord m)
{
string[] outline = { Convert.ToString(m.ID), Convert.ToString(m.Mass), Convert.ToString(m.NET) };
m._AssociatedUMCRecords.Sort(delegate(Classes.UMCRecord u1, Classes.UMCRecord u2) { return u1.DatasetID.CompareTo(u2.DatasetID); });
int count_index = 0;
for (int i = 0; i < numdatasets; i++)
{
string[] ar3 = new string[outline.Length + 9];
outline.CopyTo(ar3, 0);
Classes.UMCRecord u = m._AssociatedUMCRecords[count_index];
if (u.DatasetID == i)
{
ar3.SetValue(Convert.ToString(u.DatasetID), outline.Length);
ar3.SetValue(Convert.ToString(u.HCDScore), outline.Length + 1);
ar3.SetValue(Convert.ToString(u.CIDScore), outline.Length + 2);
ar3.SetValue(Convert.ToString(u.ETDScore), outline.Length + 3);
ar3.SetValue(u.ProteinName, outline.Length + 4);
ar3.SetValue(u.PeptideSeq, outline.Length + 5);
ar3.SetValue(u.NGlycoSite, outline.Length + 6);
ar3.SetValue(u.GlycanComposition, outline.Length + 7);
ar3.SetValue(Convert.ToString(u.Abundance), outline.Length + 8);
count_index++;
if (count_index >= m._AssociatedUMCRecords.Count)
count_index--; // To keep it within index.
}
else
{
ar3.SetValue(Convert.ToString(i), outline.Length);
ar3.SetValue(Convert.ToString(1), outline.Length + 1);
ar3.SetValue(Convert.ToString(0), outline.Length + 2);
ar3.SetValue(Convert.ToString(0), outline.Length + 3);
ar3.SetValue("", outline.Length + 4);
ar3.SetValue("", outline.Length + 5);
ar3.SetValue("", outline.Length + 6);
ar3.SetValue("", outline.Length + 7);
ar3.SetValue(Convert.ToString(0), outline.Length + 8);
}
outline = ar3;
}
outfile.writeLine(outline);
});
outfile.closeFile();
}*/
public void WriteOutMapToCSV(ref Classes.MapRecord _glycoMap, string filename)
{
CSVFileHandler outfile = new CSVFileHandler(filename, CSVFileHandler.WRITE_ONLY);
outfile.openFile();
int numdatasets = _glycoMap._AssociatedDatasetNames.Count;
string[] header = { "ClusterID", "Mass", "NET", "Protein", "Peptide", "Site", "Glycan", "PeptideMass", "GlycanMass",
"TypeID", "TRUE_FALSE", "RepHCDScore", "RepCIDScore","RepETDScore", "RepCIDSeqScore" };
for (int i = 0; i < numdatasets; i++)
{
string[] ar2;
ar2 = new string[header.Length + 5];
header.CopyTo(ar2, 0);
ar2.SetValue("DatasetID" + "." + i.ToString(), header.Length);
ar2.SetValue("HCDScore" + "." + i.ToString(), header.Length + 1);
ar2.SetValue("CIDScore" + "." + i.ToString(), header.Length + 2);
ar2.SetValue("ETDScore" + "." + i.ToString(), header.Length + 3);
ar2.SetValue("Abundance" + "." + i.ToString(), header.Length + 4);
header = ar2;
}
outfile.writeLine(header);
_glycoMap._AllMLNRecords.ForEach(delegate(Classes.MultiAlignRecord m)
{
if (m.ID == 2290)
{
bool test = true;
}
if (m.BestMatchProteinName != "")
{
string true_false= "TRUE" ;
if(m.BestMatchFalseHit)
true_false = "FALSE";
string[] outline = { Convert.ToString(m.ID), Convert.ToString(m.Mass), Convert.ToString(m.NET), m.BestMatchProteinName,
m.BestMatchPeptideSeq, m.BestMatchNGlycoSite, m.BestMatchGlycanComposition,
m.BestMatchPeptideMass.ToString(), m.BestMatchGlycanMass.ToString(),
m.IDLabel.ToString(), true_false , m.RepHCDScore.ToString(), m.RepCIDScore.ToString(), m.RepETDScore.ToString(), m.RepCIDSequencingScore.ToString()};
m._AssociatedUMCRecords.Sort(delegate(Classes.UMCRecord u1, Classes.UMCRecord u2) { return u1.DatasetID.CompareTo(u2.DatasetID); });
int count_index = 0;
for (int i = 0; i < numdatasets; i++)
{
string[] ar3 = new string[outline.Length + 5];
outline.CopyTo(ar3, 0);
Classes.UMCRecord u = m._AssociatedUMCRecords[count_index];
if (u.DatasetID == i)
{
ar3.SetValue(Convert.ToString(u.DatasetID), outline.Length);
ar3.SetValue(Convert.ToString(u.UMCRepHCDScore), outline.Length + 1);
ar3.SetValue(Convert.ToString(u.UMCRepCIDScore), outline.Length + 2);
ar3.SetValue(Convert.ToString(u.UMCRepETDScore), outline.Length + 3);
ar3.SetValue(Convert.ToString(u.Abundance), outline.Length + 4);
count_index++;
if (count_index >= m._AssociatedUMCRecords.Count)
count_index--; // To keep it within index.
}
else
{
ar3.SetValue(Convert.ToString(i), outline.Length);
ar3.SetValue(Convert.ToString(1), outline.Length + 1);
ar3.SetValue(Convert.ToString(0), outline.Length + 2);
ar3.SetValue(Convert.ToString(0), outline.Length + 3);
ar3.SetValue(Convert.ToString(0), outline.Length + 4);
}
outline = ar3;
}
outfile.writeLine(outline);
}
});
outfile.closeFile();
}
public void WriteOutPrecursorInfoToFileV2(ref Classes.MapRecord _glycoMap, string filename)
{
CSVFileHandler outfile = new CSVFileHandler(filename, CSVFileHandler.WRITE_ONLY);
outfile.openFile();
int numdatasets = _glycoMap._AssociatedDatasetNames.Count;
string[] header = { "ClusterID", "Mass", "NET", "Protein", "Peptide", "Site", "Glycan", "PeptideMass", "GlycanMass",
"TypeID", "TRUE_FALSE", "RepHCDScore", "RepCIDScore","RepETDScore", "RepCIDSeqScore","ParentMZ", "ParentScanTime"};
for (int i = 0; i < numdatasets; i++)
{
}
outfile.writeLine(header);
_glycoMap._AllMLNRecords.ForEach(delegate(Classes.MultiAlignRecord m)
{
if (m.BestMatchProteinName != "")
{
string true_false = "TRUE";
if (m.BestMatchFalseHit)
true_false = "FALSE";
string[] outline = { Convert.ToString(m.ID), Convert.ToString(m.Mass), Convert.ToString(m.NET), m.BestMatchProteinName,
m.BestMatchPeptideSeq, m.BestMatchNGlycoSite, m.BestMatchGlycanComposition,
m.BestMatchPeptideMass.ToString(), m.BestMatchGlycanMass.ToString(),
m.IDLabel.ToString(), true_false , m.RepHCDScore.ToString(), m.RepCIDScore.ToString(), m.RepETDScore.ToString(), m.RepCIDSequencingScore.ToString(),
m.BestMatchParentMz.ToString(), m.BestMatchParentScanTime.ToString()};
outfile.writeLine(outline);
}
});
outfile.closeFile();
}
public void ReanInMLNV2File(string filename, int _numdatasets)
{
// Read in new version of MLN file
CSVFileHandler CsvFileHandler2 = new CSVFileHandler(filename, CSVFileHandler.READ_ONLY);
CsvFileHandler2.openFile();
String[] Attributes2;
CsvFileHandler2.readLine();
while ((Attributes2 = CsvFileHandler2.readLine()) != null)
{
MultiAlignRecord mrecord = new MultiAlignRecord();
mrecord.ID = int.Parse(Attributes2[0]);
mrecord.Mass = double.Parse(Attributes2[1]);
mrecord.NET = double.Parse(Attributes2[2]);
int numDatasetsToAllocate = 0;
if (mrecord.Mass < _MAP_MIN_MASS)
_MAP_MIN_MASS = mrecord.Mass;
if (mrecord.Mass > _MAP_MAX_MASS)
_MAP_MAX_MASS = mrecord.Mass;
if ((Attributes2.Length-5) / 8 != _numdatasets)
numDatasetsToAllocate = (Attributes2.Length -5) / 8;
else
numDatasetsToAllocate = _numdatasets;
mrecord.AllocateNumberDatasets(numDatasetsToAllocate);
for (int i = 5; i < Attributes2.Length; i += 8)
{
UMCRecord u = new UMCRecord();
if (Attributes2[i] != "")
{
u.ID = int.Parse(Attributes2[i]);
u.DatasetID = int.Parse(Attributes2[i + 1]);
u.MW = double.Parse(Attributes2[i + 2]);
u.Abundance = double.Parse(Attributes2[i + 4]);
u.ScanRep = int.Parse(Attributes2[i + 5]);
u.ScanStart = int.Parse(Attributes2[i + 6]);
u.ScanEnd = int.Parse(Attributes2[i + 7]);
mrecord._AssociatedUMCRecords.Add(u);
}
}
AddRecord(mrecord);
if (mrecord._AssociatedUMCRecords.Count > 10)
{
bool debig = true;
}
}
}
/// <summary>
/// Function to write out glycopeptides dictionary to file so that next time
/// </summary>
/// <param name="outfile"></param>
public void WriteOutGlycopeptidesToFile(string filename)
{
CSVFileHandler outfile = new CSVFileHandler(filename, CSVFileHandler.WRITE_ONLY);
outfile.openFile();
int numglycopeptides = _glycopeptides.Count;
string[] header = { "GlycoPeptideMonoMass", "GlycoPeptideAvgMass", "Protein", "Peptide", "DECOY_Peptide",
"Site", "PeptideMonoMass", "PeptideAvgMass", "Glycan", "DECOY_Glycan", "GlycanMonoMass", "GlycanAvgMass" };
outfile.writeLine(header) ;
for (int i = 0; i < numglycopeptides; i++)
{
string[] outline = {Convert.ToString(_glycopeptides[i].GP_Mono_Mass),
Convert.ToString(_glycopeptides[i].GP_Average_Mass),
Convert.ToString(_glycopeptides[i].Sequence.proteinName),
Convert.ToString(_glycopeptides[i].Sequence.sequence),
Convert.ToString(_glycopeptides[i].Sequence.is_decoy),
Convert.ToString(_glycopeptides[i].Sequence.nGlycoSite),
Convert.ToString(_glycopeptides[i].SequenceMonoMass) ,
Convert.ToString(_glycopeptides[i].SequenceAverageMass),
Convert.ToString(_glycopeptides[i].Glycan.composition) ,
Convert.ToString(_glycopeptides[i].Glycan.is_decoy),
Convert.ToString(_glycopeptides[i].GlycanMonoMass),
Convert.ToString(_glycopeptides[i].GlycanAverageMass)};
outfile.writeLine(outline);
}
outfile.closeFile();
}
/// <summary>
/// Function to read in glycopeptides dictionary from file
/// </summary>
/// <param name="infile"></param>
public void LoadGlycopeptidesFromFile(string infile, double min_mass, double max_mass, bool create_hash)
{
CSVFileHandler CsvFileHandler2 = new CSVFileHandler(infile, CSVFileHandler.READ_ONLY);
CsvFileHandler2.openFile();
String[] Attributes2;
CsvFileHandler2.readLine();
if (create_hash)
_dGlycopeptides = new Dictionary<int, List<GlycopeptideRecord>>();
else
_glycopeptides = new List<GlycopeptideRecord>();
while ((Attributes2 = CsvFileHandler2.readLine()) != null)
{
double gpmass = double.Parse(Attributes2[0]);
if (gpmass >= min_mass && gpmass <= max_mass)
{
GlycopeptideRecord gp = new GlycopeptideRecord();
gp.GP_Mono_Mass = gpmass ;
gp.GP_Average_Mass = double.Parse(Attributes2[1]) ;
gp.Sequence.proteinName = Attributes2[2] ;
gp.Sequence.sequence = Attributes2[3];
gp.Sequence.is_decoy = bool.Parse(Attributes2[4]);
gp.Sequence.nGlycoSite = Attributes2[5] ;
gp.SequenceMonoMass = double.Parse(Attributes2[6]) ;
gp.SequenceAverageMass = double.Parse(Attributes2[7]) ;
gp.Glycan.SetMonosaccharideCompostion(Attributes2[8]) ;
gp.Glycan.composition = Attributes2[8];
gp.Glycan.is_decoy = bool.Parse(Attributes2[9]) ;
gp.GlycanMonoMass = double.Parse(Attributes2[10]) ;
gp.GlycanAverageMass = double.Parse(Attributes2[11]) ;
gp.IsDecoy = gp.Sequence.is_decoy | gp.Glycan.is_decoy;
if (create_hash)
{
List<GlycopeptideRecord> value_gp_list = new List<GlycopeptideRecord>();
int key_mass = (int)Math.Floor(gp.GP_Mono_Mass);
int min_mass_int = (int)Math.Floor(min_mass);
int max_mass_int = (int)Math.Floor(max_mass);
if (!_dGlycopeptides.ContainsKey(key_mass))
{
if (value_gp_list.Count > 0)
value_gp_list.Clear();
value_gp_list.Add(gp);
_dGlycopeptides.Add(key_mass, value_gp_list);
}
else
{
value_gp_list.Clear();
value_gp_list = _dGlycopeptides[key_mass];
value_gp_list.Add(gp);
_dGlycopeptides[key_mass] = value_gp_list;
}
}
else
_glycopeptides.Add(gp);
}
}
CsvFileHandler2.closeFile();
}
public void SequenceCIDPeaks(ref Classes.MapRecord _glycoMap, ref Classes.Params _params, string sequencingFolder)
{
Classes.MapRecord _tempMap = new MapRecord();
_tempMap._AssociatedDatasetNames = _glycoMap._AssociatedDatasetNames;
_tempMap._IsCID = _glycoMap._IsCID;
_tempMap._IsETD = _glycoMap._IsETD;
_tempMap._IsHCD = _glycoMap._IsHCD;
Classes.FragEvents e = new FragEvents();
if (sequencingFolder == "")
sequencingFolder = @"c:\sequencing\";
for (int i = 0; i < _glycoMap._AllMLNRecords.Count; i++)
{
MultiAlignRecord m = new MultiAlignRecord();
m = _glycoMap._AllMLNRecords[i];
int num_records = m._AssociatedUMCRecords.Count;
if (m.ID == 2290)
{
bool test = true;
}
//for (int j = 0; j < num_records; j++)
//{
// for (int k = 0; k < m._AssociatedUMCRecords[j]._AssociatedFragEvents.Count; k++)
for (int k = 0; k < m._ClusterRepFragEvents.Count; k++)
{
e = new FragEvents();
e = m._ClusterRepFragEvents[k]; // m._AssociatedUMCRecords[j]._AssociatedFragEvents[k];
if (e.ETDScore > 0)
{
float PeptideMass = 0;
float GlcNAcMass = 0;
COL.MassLib.MSScan _msScan = new COL.MassLib.MSScan(e.CIDMzs, e.CIDIntensities, Convert.ToSingle(e.TransformResult.mdbl_mz),
Convert.ToSingle(e.TransformResult.mdbl_mono_mw), Convert.ToSingle(e.TransformResult.mdbl_average_mw), Convert.ToInt32(e.TransformResult.mshort_cs));
if (e.TransformResult.mdbl_average_mw > 0)
{
PeptideMass = Convert.ToSingle(e.GP_Record.SequenceAverageMass); // this means proper deisotoping has occured so use average compostion
GlcNAcMass = COL.GlycoLib.GlycanMass.GetGlycanAVGMass(COL.GlycoLib.Glycan.Type.HexNAc);
}
else
{
PeptideMass = Convert.ToSingle(e.GP_Record.SequenceMonoMass); // CS has been assigned, in which case both y1 and precursor should be just mono
GlcNAcMass = COL.GlycoLib.GlycanMass.GetGlycanMass(COL.GlycoLib.Glycan.Type.HexNAc);
}
short y1cs = e.TransformResult.mshort_cs;
y1cs--;
while (y1cs > 0)
{
float y1Mz = ((PeptideMass + GlcNAcMass) + (float)_utils._CC_MASS * y1cs) / y1cs;
COL.GlycoSequence.GlycanSequencing _Gs = new COL.GlycoSequence.GlycanSequencing(_msScan, y1Mz, y1cs, e.GP_Record.Glycan.numHex,
e.GP_Record.Glycan.numHexNAc, e.GP_Record.Glycan.numDeHex, e.GP_Record.Glycan.numNeuAc, 0, sequencingFolder, true, 0.8f, 60);
_Gs.NumbersOfPeaksForSequencing = 140;
_Gs.CreatePrecursotMZ = true;
_Gs.RewardForCompleteStructure = 3;
if (e.TransformResult.mdbl_average_mw > 0)
_Gs.UseAVGMass = true;
else
_Gs.UseAVGMass = false;
int structure_count = _Gs.StartSequencing();
if (structure_count > 0)
{
List<COL.GlycoLib.GlycanStructure> topstructures = _Gs.GetTopRankScoreStructre(1);
e.CIDSequencingScore = topstructures[0].Score;
e.GP_Record.GlycanSequence = topstructures[0].IUPACString;
// Printing out the sequences
string opfile = sequencingFolder + m.ID.ToString() + "_" + e.CIDScan.ToString() + ".txt";
Utils.CSVFileHandler cidString = new CSVFileHandler(opfile, CSVFileHandler.WRITE_ONLY);
cidString.openFile();
for (int zz = 0; zz < topstructures.Count; zz++)
{
cidString.writeLine(topstructures[zz].IUPACString);
/*COL.GlycoLib.GlycansDrawer _gdraw = new COL.GlycoLib.GlycansDrawer(topstructures[zz].IUPACString, false);
System.Drawing.Image img1 = _gdraw.GetImage();*/
}
cidString.closeFile();
break;
}
y1cs--;
}
}
}
}
}