public ParseXML(String file, Boolean flag)
{
XmlReader xml = XmlReader.Create(file);
map = new List<GlycoRecord>();
GlycoRecord record = new GlycoRecord();
GlobalVar.assignMzKeys();
while (xml.Read())
{
if (xml.IsStartElement())
{
switch (xml.Name)
{
case "ID":
xml.Read();
record.id = int.Parse(xml.ReadString());
break;
case "Mass":
xml.Read();
record.mass = double.Parse(xml.ReadString());
if (flag)
{
if (GlobalVar.REFCMAXMAS < record.mass)
{
GlobalVar.REFCMAXMAS = record.mass;
}
if (GlobalVar.REFCMINMAS > record.mass)
{
GlobalVar.REFCMINMAS = record.mass;
}
}
else
{
if (GlobalVar.TARGMAXMAS < record.mass)
{
GlobalVar.TARGMAXMAS = record.mass;
}
if (GlobalVar.TARGMINMAS > record.mass)
{
GlobalVar.TARGMINMAS = record.mass;
}
}
break;
case "NET":
xml.Read();
record.net = double.Parse(xml.ReadString());
if (flag)
{
//record.net = double.Parse(xml.ReadString());//
if (GlobalVar.REFCMAXNET < record.net)
{
GlobalVar.REFCMAXNET = record.net;
}
if (GlobalVar.REFCMINNET > record.net)
{
GlobalVar.REFCMINNET = record.net;
}
}
else
{
//record.net = double.Parse(xml.ReadString()) + 0.024;//
if (GlobalVar.TARGMAXNET < record.net)
{
GlobalVar.TARGMAXNET = record.net;
}
if (GlobalVar.TARGMINNET > record.net)
{
GlobalVar.TARGMINNET = record.net;
}
}
break;
case "Protein":
xml.Read();
if (flag)
{
string prot = xml.ReadString();
if (!prot.Contains("decoy"))
{
record.protein = prot;
}
else
{
record = new GlycoRecord();
continue;
}
}
break;
case "Peptide":
xml.Read();
record.peptide = xml.ReadString();
break;
case "PeptideMass":
xml.Read();
record.pepmass = double.Parse(xml.ReadString());
break;
case "Site":
xml.Read();
record.site = xml.ReadString();
break;
case "Glycan":
xml.Read();
record.glycan = xml.ReadString();
break;
case "GlycanSequence":
xml.Read();
break;
case "GlycanMass":
xml.Read();
record.glymass = double.Parse(xml.ReadString());
break;
case "FalseHit":
xml.Read();
break;
case "IDType":
record.type = xml.ReadString();
break;
case "RepresentativeCIDLength":
xml.Read();
record.cidlen = int.Parse(xml.ReadString());
break;
case "RepresentativeCIDSpectra":
xml.Read();
record.cidstr = xml.ReadString();
Spectra cid = Utilities.parseBase64(record.cidlen, record.cidstr);
record.cidspec = Utilities.assignMzBucket(cid.mz);
break;
case "RepresentativeHCDLength":
xml.Read();
record.hcdlen = int.Parse(xml.ReadString());
break;
case "RepresentativeHCDSpectra":
xml.Read();
record.hcdstr = xml.ReadString();
//Spectra hcd = Utilities.parseBase64(record.hcdlen, record.hcdstr);
//record.hcdspec = Utilities.assignMzBucket(hcd.mz);
break;
case "RepresentativeETDLength":
xml.Read();
record.etdlen = int.Parse(xml.ReadString());
break;
case "RepresentativeETDSpectra":
xml.Read();
record.etdstr = xml.ReadString();
//Spectra etd = Utilities.parseBase64(record.etdlen, record.etdstr);
//record.etdspec = Utilities.assignMzBucket(etd.mz);
break;
case "RepCIDScore":
xml.Read();
record.cidscore = double.Parse(xml.ReadString());
break;
case "RepHCDScore":
xml.Read();
record.hcdscore = double.Parse(xml.ReadString());
break;
case "RepETDScore":
xml.Read();
record.etdscore = double.Parse(xml.ReadString());
break;
case "RepCIDSequencing":
xml.Read();
if (record.mass > 0)
{
map.Add(record);
}
break;
}
}
}
/*if (flag)
{
if ((GlobalVar.RMAXNET + GlobalVar.TOLNET) < 1.0)
{
GlobalVar.RMAXNET += GlobalVar.TOLNET;
GlobalVar.RMAXNET = (Convert.ToInt32(GlobalVar.RMAXNET / GlobalVar.BINNET) + 1) * GlobalVar.BINNET;
}
else
{
GlobalVar.RMAXNET = 1.0;
}
if ((GlobalVar.RMINNET - GlobalVar.TOLNET) > 0.0)
{
GlobalVar.RMINNET -= GlobalVar.TOLNET;
GlobalVar.RMINNET = (Convert.ToInt32(GlobalVar.RMINNET / GlobalVar.BINNET) + 1) * GlobalVar.BINNET;
}
else
{
GlobalVar.RMINNET = GlobalVar.BINNET;
}
GlobalVar.RMAXMAS = ((GlobalVar.RMAXMAS * (1 - GlobalVar.TOLMAS)) / (1 + GlobalVar.TOLMAS));
GlobalVar.RMAXMAS = (Convert.ToInt32(GlobalVar.RMAXMAS / GlobalVar.BINNET) + 1) * GlobalVar.BINNET;
GlobalVar.RMINMAS = ((GlobalVar.RMINMAS * (1 + GlobalVar.TOLMAS)) / (1 - GlobalVar.TOLMAS));
GlobalVar.RMINMAS = (Convert.ToInt32(GlobalVar.RMINMAS / GlobalVar.BINNET) + 1) * GlobalVar.BINNET;
GlobalVar.assignNetKeys();
}*/
}
private void calculateStdDev()
{
List<double> masdiff = new List<double>();
List<double> netdiff = new List<double>();
maserr = new Dictionary<double, int>();
neterr = new Dictionary<double, int>();
for (double i = (-GlobalVar.TOLMAS * 1000000); i < (GlobalVar.TOLMAS * 1000000); i += GlobalVar.ERRBINMAS)
{
maserr[Math.Round(i, 3)] = 0;
}
for (double i = (-GlobalVar.TOLNET * 100); i < (GlobalVar.TOLNET * 100); i += GlobalVar.ERRBINNET)
{
neterr[Math.Round(i, 1)] = 0;
}
string str = "TargetID,TargetMass,TargetNET,ReferenceID,ReferenceMass,ReferenceNET,Protein,Site,Peptide,Glycan,Type\n";//
foreach (double okey in GlobalVar.NETKEYS)
{
foreach (double ikey in GlobalVar.NETKEYS)
{
int count = 0;
foreach (GlycoRecord outs in targ_buck[okey])
{
double dm = 0.0, dn = 0.0, euc = 100.0;
GlycoRecord temprec = new GlycoRecord();//
int chk = 0;
foreach (GlycoRecord ins in refc_buck[ikey])
{
if (Utilities.check(outs.mass, ins.mass, outs.net, ins.net))
{
double tempmd = Math.Abs((outs.mass - ins.mass) / (outs.mass + ins.mass));
double tempnd = Math.Abs(outs.net - ins.net);
double tempeuc = Math.Sqrt(Math.Pow(tempmd, 2) + Math.Pow(tempnd, 2));
if (euc > tempeuc)
{
dm = tempmd;
dn = tempnd;
euc = tempeuc;
temprec = ins;//
}
chk = 1;
}
}
if (chk == 1)
{
masdiff.Add(dm);
netdiff.Add(dn);
maserr[Utilities.assignMasbin((outs.mass - temprec.mass) / (outs.mass + temprec.mass))] += 1;
neterr[Utilities.assignNetbin(outs.net - temprec.net)] += 1;
str += outs.id + "," + outs.mass + "," + outs.net + "," +
temprec.id + "," + temprec.mass + "," + temprec.net + "," +
temprec.protein + "," + temprec.site + "," + temprec.peptide +
"," + temprec.glycan + "," + temprec.type + "\n";//
count++;
}
}
///*
int left;
if (targ_buck[okey].Count == 0)
{
left = (refc_buck[ikey].Count - count);
}
else if (refc_buck[ikey].Count == 0)
{
left = (targ_buck[okey].Count - count);
}
else if ((targ_buck[okey].Count - count) < (refc_buck[ikey].Count - count))
{
left = (targ_buck[okey].Count - count);
}
else
{
left = (refc_buck[ikey].Count - count);
}
//*/
//int left = (targ_buck[okey].Count - count) + (refc_buck[ikey].Count - count);
for (int i = 0; i < left; i++)
{
masdiff.Add(GlobalVar.TOLMAS);
netdiff.Add(GlobalVar.TOLNET);
}
}
}
System.IO.File.WriteAllText("hits.csv", str);
masstddev = Utilities.deviation(masdiff);
netstddev = Utilities.deviation(netdiff);
}
public ParseCSV(String name, Boolean flag)
{
StreamReader file = new StreamReader(name);
String line;
String[] values;
map = new List<GlycoRecord>();
GlycoRecord record = new GlycoRecord();
file.ReadLine();
while ((line = file.ReadLine()) != null)
{
values = line.Split(',');
if (flag)
{
if (!values[3].Contains("decoy"))
{
if (values[10].Equals("true", StringComparison.OrdinalIgnoreCase))
{
record.id = int.Parse(values[0]);
record.mass = double.Parse(values[1]);
record.net = double.Parse(values[2]);
record.protein = values[3];
record.peptide = values[4];
record.site = values[5];
record.glycan = values[6];
record.pepmass = double.Parse(values[7]);
record.glymass = double.Parse(values[8]);
record.type = values[9];
record.hcdscore = double.Parse(values[11]);
record.cidscore = double.Parse(values[12]);
record.etdscore = double.Parse(values[13]);
if (GlobalVar.REFCMAXMAS < record.mass)
{
GlobalVar.REFCMAXMAS = record.mass;
}
if (GlobalVar.REFCMINMAS > record.mass)
{
GlobalVar.REFCMINMAS = record.mass;
}
if (GlobalVar.REFCMAXNET < record.net)
{
GlobalVar.REFCMAXNET = record.net;
}
if (GlobalVar.REFCMINNET > record.net)
{
GlobalVar.REFCMINNET = record.net;
}
}
}
}
else
{
record.id = int.Parse(values[0]);
record.mass = double.Parse(values[2]);
record.net = double.Parse(values[3]);
if (GlobalVar.TARGMAXMAS < record.mass)
{
GlobalVar.TARGMAXMAS = record.mass;
}
if (GlobalVar.TARGMINMAS > record.mass)
{
GlobalVar.TARGMINMAS = record.mass;
}
if (GlobalVar.TARGMAXNET < record.net)
{
GlobalVar.TARGMAXNET = record.net;
}
if (GlobalVar.TARGMINNET > record.net)
{
GlobalVar.TARGMINNET = record.net;
}
}
map.Add(record);
}
/*if (flag)
{
if ((GlobalVar.RMAXNET + GlobalVar.TOLNET) < 1.0)
{
GlobalVar.RMAXNET += GlobalVar.TOLNET;
GlobalVar.RMAXNET = (Convert.ToInt32(GlobalVar.RMAXNET / GlobalVar.BINNET) + 1) * GlobalVar.BINNET;
}
else
{
GlobalVar.RMAXNET = (1.0 + GlobalVar.BINNET);
}
if ((GlobalVar.RMINNET - GlobalVar.TOLNET) > 0.0)
{
GlobalVar.RMINNET -= GlobalVar.TOLNET;
GlobalVar.RMINNET = (Convert.ToInt32(GlobalVar.RMINNET / GlobalVar.BINNET) + 1) * GlobalVar.BINNET;
}
else
{
GlobalVar.RMINNET = GlobalVar.BINNET;
}
GlobalVar.RMAXMAS = ((GlobalVar.RMAXMAS * (1 - GlobalVar.TOLMAS)) / (1 + GlobalVar.TOLMAS));
GlobalVar.RMAXMAS = (Convert.ToInt32(GlobalVar.RMAXMAS / GlobalVar.BINNET) + 1) * GlobalVar.BINNET;
GlobalVar.RMINMAS = ((GlobalVar.RMINMAS * (1 + GlobalVar.TOLMAS)) / (1 - GlobalVar.TOLMAS));
GlobalVar.RMINMAS = (Convert.ToInt32(GlobalVar.RMINMAS / GlobalVar.BINNET) + 1) * GlobalVar.BINNET;
GlobalVar.assignNetKeys();
}*/
file.Close();
}
private void copyData(List<GlycoRecord> targ_ikey, List<GlycoRecord> refc_jkey)
{
foreach (GlycoRecord outs in targ_ikey)
{
double dm = 0.0, dn = 0.0, euc = 100.0;
GlycoRecord temprec = new GlycoRecord();//
int chk = 0;
foreach (GlycoRecord ins in refc_jkey)
{
if (Utilities.check(outs.mass, ins.mass, outs.net, ins.net))
{
double tempmd = Math.Abs((outs.mass - ins.mass) / (outs.mass + ins.mass));
double tempnd = Math.Abs(outs.net - ins.net);
double tempeuc = Math.Sqrt(Math.Pow(tempmd, 2) + Math.Pow(tempnd, 2));
if (euc > tempeuc)
{
dm = tempmd;
dn = tempnd;
euc = tempeuc;
temprec = ins;//
}
chk = 1;
//break;
}
}
if (chk == 1)
{
merg.Add(temprec);
str += outs.id + "," + outs.mass + "," + outs.net + "," +
temprec.id + "," + temprec.mass + "," + temprec.net + "," +
temprec.protein + "," + temprec.site + "," + temprec.peptide +
"," + temprec.glycan + "," + temprec.type + "\n";//
}
if (chk == 0)
{
//tempmap.Add(outs);
}
}
}