public SequestFilename GetValue(string obj)
{
for (int i = 0; i < parsers.Count; i++)
{
ITitleParser parser = parsers[i];
try
{
SequestFilename result = parser.GetValue(obj);
if (i != 0 && moveCount < 10)
{
parsers.Remove(parser);
parsers.Insert(0, parser);
moveCount++;
}
return(result);
}
catch (Exception)
{
}
}
return(MascotUtils.ParseTitle(obj, 2));
}
public void TestSetShortFilename3()
{
SequestFilename sf = new SequestFilename();
sf.ShortFileName = "\"JWH_SAX_25_050906,13426\"";
Assert.AreEqual("JWH_SAX_25_050906", sf.Experimental);
Assert.AreEqual(13426, sf.FirstScan);
Assert.AreEqual(13426, sf.LastScan);
}
/// <summary>
///
/// Get the query/peptide map from pNovo result.
///
/// </summary>
/// <param name="filename">pNovo proteins file</param>
/// <param name="minRank">Minimum rank of peptide identified in same spectrum</param>
/// <param name="minScore">Minimum score of peptide identified in same spectrum</param>
/// <returns>Query/peptide map</returns>
public List <IIdentifiedSpectrum> ParsePeptides(string filename, int maxRank, double minScore)
{
var result = new List <IIdentifiedSpectrum>();
SequestFilename sf = null;
int charge = 2;
double expmh = 0;
using (var sr = new StreamReader(filename))
{
string line;
while ((line = sr.ReadLine()) != null)
{
var parts = line.Split('\t');
if (parts.Length <= 5)
{ //spectrum information
var seqcount = Convert.ToInt32(parts.Last());
if (seqcount == 0)
{
continue;
}
sf = parser.GetValue(parts[0]);
expmh = MyConvert.ToDouble(parts[1]);
charge = Convert.ToInt32(parts[2]);
}
else
{
int curIndex = Convert.ToInt32(parts[0]);
if (curIndex <= maxRank)
{
var score = MyConvert.ToDouble(parts[2]);
if (score < minScore)
{
continue;
}
var curSpectrum = new IdentifiedSpectrum();
curSpectrum.Query.FileScan = sf;
curSpectrum.Query.Charge = charge;
curSpectrum.ExperimentalMH = expmh;
curSpectrum.Score = score;
result.Add(curSpectrum);
IdentifiedPeptide pep = new IdentifiedPeptide(curSpectrum);
pep.Sequence = ModifySequence(parts[9]);
pep.Spectrum.TheoreticalMH = MyConvert.ToDouble(parts[11]);
pep.Spectrum.Rank = curIndex;
}
}
}
}
return(result);
}
private static CensusPeptideItem Parse(string line)
{
var result = new CensusPeptideItem();
if (line.StartsWith("S\t"))
{
result.Singleton = false;
}
else if (line.StartsWith("&S\t"))
{
result.Singleton = true;
}
else
{
return(null);
}
string[] parts = line.Split(new[] { '\t' });
if (parts.Length < 13)
{
return(null);
}
result.Unique = parts[1];
result.Sequence = parts[2];
result.Ratio = MyConvert.ToDouble(parts[3]);
result.RegressionFactor = MyConvert.ToDouble(parts[4]);
result.DeterminantFactor = MyConvert.ToDouble(parts[5]);
result.Score = MyConvert.ToDouble(parts[6]);
result.DeltaScore = MyConvert.ToDouble(parts[7]);
result.SampleIntensity = MyConvert.ToDouble(parts[8]);
result.ReferenceIntensity = MyConvert.ToDouble(parts[9]);
result.AreaRatio = MyConvert.ToDouble(parts[10]);
result.SingletonScore = MyConvert.ToDouble(parts[11]);
if (parts[12].EndsWith("."))
{
result.Filename = SequestFilename.Parse(parts[12]);
}
else
{
result.Filename = SequestFilename.Parse(parts[12] + ".");
}
return(result);
}
public HashSet <string> ReadFromFile(string fileName)
{
HashSet <string> result = new HashSet <string>();
SequestFilename sf = new SequestFilename();
using (StreamReader sr = new StreamReader(fileName))
{
//ignore header lines
string line;
while ((line = sr.ReadLine()) != null)
{
string[] parts = line.Trim().Split(chars);
try
{
sf.ShortFileName = parts[0];
break;
}
catch (Exception)
{ }
}
if (line != null)
{
result.Add(sf.Experimental);
}
while ((line = sr.ReadLine()) != null)
{
line = line.Trim();
if (line.Length == 0)
{
break;
}
if (IdentifiedResultUtils.IsProteinLine(line))
{
continue;
}
string[] parts = line.Split(chars);
sf.ShortFileName = parts[0];
result.Add(sf.Experimental);
}
}
return(result);
}
public SequestFilename GetValue(string obj)
{
SequestFilename result = new SequestFilename();
if (rawFileRegex != null)
{
Match m = rawFileRegex.Match(obj);
if (!m.Success)
{
throw new ArgumentException("Cannot parse raw file from title " + obj);
}
result.Experimental = m.Groups[1].Value;
}
if (scanNumberRegex != null)
{
Match m = scanNumberRegex.Match(obj);
if (!m.Success)
{
throw new ArgumentException("Cannot parse scan number from title " + obj);
}
result.FirstScan = int.Parse(m.Groups[1].Value);
if (m.Groups.Count > 2)
{
result.LastScan = int.Parse(m.Groups[2].Value);
}
else
{
result.LastScan = result.FirstScan;
}
}
if (rtRegex != null)
{
Match m = rtRegex.Match(obj);
if (!m.Success)
{
throw new ArgumentException("Cannot parse retention time from title " + obj);
}
result.RetentionTime = double.Parse(m.Groups[1].Value);
}
result.Extension = "dta";
return(result);
}
public void TestCmpd2()
{
ParserItem item = new ParserItem();
ParserFormat format = new ParserFormat();
format.FormatName = "TurboRAW2MGF, Cmpd";
format.Add(new ParserItem("rawFile", ""));
format.Add(new ParserItem("scanNumber", @"Cmpd\s*(\d+)\s*,"));
TitleParser parser = new TitleParser(format);
SequestFilename sf = parser.GetValue("Cmpd 2345, xxxxx");
Assert.AreEqual(2345, sf.FirstScan);
Assert.AreEqual(2345, sf.LastScan);
}
public void TestDta()
{
ParserItem item = new ParserItem();
ParserFormat format = new ParserFormat();
format.FormatName = "TurboRAW2MGF, DTA Format";
format.Add(new ParserItem("rawFile", @"(.+)\.\d+\.\d+\.\d\.(?:dta|DTA)"));
format.Add(new ParserItem("scanNumber", @".+\.(\d+)\.(\d+)\.\d\.(?:dta|DTA)"));
TitleParser parser = new TitleParser(format);
SequestFilename sf = parser.GetValue("TEST.2345.2346.1.dta");
Assert.AreEqual("TEST", sf.Experimental);
Assert.AreEqual(2345, sf.FirstScan);
Assert.AreEqual(2346, sf.LastScan);
}
public SequestFilename GetFilename(PeakList <Peak> pkl, String mgfName)
{
if (pkl.Annotations.ContainsKey(MascotGenericFormatConstants.TITLE_TAG))
{
var title = (String)pkl.Annotations[MascotGenericFormatConstants.TITLE_TAG];
SequestFilename sf = parser.GetValue(title);
sf.Extension = "dta";
sf.Charge = pkl.PrecursorCharge;
return(sf);
}
this.scanIndex++;
return(new SequestFilename(mgfName, this.scanIndex, this.scanIndex, pkl.PrecursorCharge, "dta"));
}
public override void SetProperty(CensusPeptideItem t, string value)
{
if (SequestFilename.IsLongFilename(value))
{
PureExperiment = false;
t.Filename = SequestFilename.Parse(value);
}
else
{
PureExperiment = true;
if (t.Filename == null)
{
t.Filename = new SequestFilename();
}
t.Filename.Experimental = value;
}
}
public void TestParseTitle()
{
SequestFilename sf = MascotUtils.ParseTitle(" Cmpd. 6612. 6612. 1. dta", 1);
Assert.AreEqual("Cmpd.6612.6612.1.dta", sf.LongFileName);
sf = MascotUtils.ParseTitle(" FIT_PPN_SAX_Online_1mg_060909_01, Cmpd 7736, +MSn(600.4082), 51.88 min", 1);
Assert.AreEqual("FIT_PPN_SAX_Online_1mg_060909_01.7736.7736.1.dta", sf.LongFileName);
sf =
MascotUtils.ParseTitle(
"spectrumId=6085 Polarity=Positive ScanMode=ProductIon TimeInMinutes=61.875 acqNumber=3712494", 1);
Assert.AreEqual(".6085.6085.1.dta", sf.LongFileName);
sf =
MascotUtils.ParseTitle(
"Elution from: 40.798 to 40.798 period: 0 experiment: 1 cycles: 1 precIntensity: 355220.0 FinneganScanNumber: 6070 MStype: enumIsNormalMS rawFile: KR_mix_lc_090115.raw",
1);
Assert.AreEqual("KR_mix_lc_090115.6070.6070.1.dta", sf.LongFileName);
}
/// <summary>
///
/// Get the query/peptide map from pNovo result.
///
/// </summary>
/// <param name="filename">pNovo proteins file</param>
/// <param name="minRank">Minimum rank of peptide identified in same spectrum</param>
/// <param name="minScore">Minimum score of peptide identified in same spectrum</param>
/// <returns>Query/peptide map</returns>
public List <IIdentifiedSpectrum> ParsePeptides(string filename, int maxRank = 10, double minScore = 0.0)
{
var result = new List <IIdentifiedSpectrum>();
SequestFilename sf = null;
int curIndex = 0;
using (var sr = new StreamReader(filename))
{
string line;
while ((line = sr.ReadLine()) != null)
{
if (string.IsNullOrWhiteSpace(line))
{
continue;
}
if (line.StartsWith("S"))
{
var title = line.StringAfter("\t");
sf = this.parser.GetValue(title);
curIndex = 0;
continue;
}
var parts = line.Split('\t');
var score = MyConvert.ToDouble(parts[2]);
if (score < minScore)
{
continue;
}
curIndex++;
IIdentifiedSpectrum curSpectrum;
if (curIndex == 1)
{
curSpectrum = new IdentifiedSpectrum();
curSpectrum.Query.FileScan = sf;
curSpectrum.Query.Charge = sf.Charge;
curSpectrum.Score = score;
curSpectrum.Rank = curIndex;
result.Add(curSpectrum);
}
else if (score == result.Last().Score)
{
curSpectrum = result.Last();
}
else if (curIndex > maxRank)
{
continue;
}
else
{
curSpectrum = new IdentifiedSpectrum();
curSpectrum.Query.FileScan = sf;
curSpectrum.Query.Charge = sf.Charge;
curSpectrum.Score = score;
curSpectrum.Rank = curIndex;
result.Add(curSpectrum);
}
IdentifiedPeptide pep = new IdentifiedPeptide(curSpectrum);
pep.Sequence = ModifySequence(parts[1]);
}
}
return(result);
}
/// <summary>
///
/// Get top one peptide list from xtandem xml file
///
/// </summary>
/// <param name="fileName">xtandem xml filename</param>
/// <returns>List of IIdentifiedSpectrum</returns>
public List <IIdentifiedSpectrum> ReadFromFile(string fileName)
{
string sourceFilename = GetSourceFile(fileName);
List <IIdentifiedSpectrum> result = new List <IIdentifiedSpectrum>();
XmlDocument doc = new XmlDocument();
doc.Load(fileName);
this.xmlHelper = new XmlHelper(doc);
XmlNode root = doc.DocumentElement;
Match mSource = Regex.Match(sourceFilename, @"(.+)\.(?:RAW)", RegexOptions.IgnoreCase);
if (mSource.Success)
{
sourceFilename = mSource.Groups[1].Value;
}
else
{
mSource = Regex.Match(sourceFilename, @"(.+?)\.");
if (mSource.Success)
{
sourceFilename = mSource.Groups[1].Value;
}
}
XmlNode parameters = xmlHelper.GetFirstChildByNameAndAttribute(root, "group", "label", "input parameters");
ParseParameters(parameters);
int pos = sourceFilename.LastIndexOfAny(new char[] { '/', '\\' });
string rawFileName;
if (pos > 0)
{
rawFileName = sourceFilename.Substring(pos + 1);
}
else
{
rawFileName = sourceFilename;
}
rawFileName = FileUtils.ChangeExtension(rawFileName, "");
List <XmlNode> groupNodes = xmlHelper.GetChildrenByNameAndAttribute(root, "group", "type", "model");
foreach (XmlNode groupNode in groupNodes)
{
Dictionary <string, IIdentifiedPeptide> pepmap = new Dictionary <string, IIdentifiedPeptide>();
IIdentifiedSpectrum spectrum = new IdentifiedSpectrum();
List <XmlNode> proteins = xmlHelper.GetChildren(groupNode, "protein");
foreach (XmlNode proteinNode in proteins)
{
XmlNode domainNode = xmlHelper.GetValidChild(xmlHelper.GetValidChild(proteinNode, "peptide"), "domain");
int numMissedCleavages = int.Parse(domainNode.Attributes["missed_cleavages"].Value);
string preSeq = domainNode.Attributes["pre"].Value;
if (preSeq.Equals("["))
{
preSeq = "-";
}
string postSeq = domainNode.Attributes["post"].Value;
if (postSeq.Equals("]"))
{
postSeq = "-";
}
StringBuilder pepSeqSB = new StringBuilder(domainNode.Attributes["seq"].Value);
int start = int.Parse(domainNode.Attributes["start"].Value);
int end = int.Parse(domainNode.Attributes["end"].Value);
List <XmlNode> modifications = xmlHelper.GetChildren(domainNode, "aa");
if (modifications.Count > 0)
{
List <ModificationItem> items = new List <ModificationItem>();
foreach (XmlNode modification in modifications)
{
int at = int.Parse(modification.Attributes["at"].Value);
if (at < start || at > end)
{
continue;
}
ModificationItem item = new ModificationItem();
item.Type = modification.Attributes["type"].Value;
item.At = at;
item.Modified = MyConvert.ToDouble(modification.Attributes["modified"].Value);
if (!staticModifications.ContainsKey(item.Type[0]))
{
items.Add(item);
}
}
spectrum.Modifications = "";
if (items.Count > 0)
{
items.Sort((m1, m2) => m1.At - m2.At);
var mod = "";
foreach (ModificationItem item in items)
{
mod = mod + MyConvert.Format(",{0}({1:0.0000})", item.Type, item.Modified);
}
spectrum.Modifications = mod.Substring(1);
items.Sort((m1, m2) => m2.At - m1.At);
foreach (ModificationItem item in items)
{
var key = GetModifiedKey(item.Modified);
if (!dynamicModificationChars.ContainsKey(key))
{
AddDynamicModificationChar(key);
}
char modificationChar = dynamicModificationChars[key];
pepSeqSB.Insert(item.At - start + 1, modificationChar.ToString());
}
spectrum.Modifications = mod.Substring(1);
}
}
StringBuilder sb = new StringBuilder();
sb.Append(preSeq.Substring(preSeq.Length - 1));
sb.Append(".");
sb.Append(pepSeqSB.ToString());
sb.Append(".");
sb.Append(postSeq[0]);
string pepSeq = sb.ToString();
if (!pepmap.ContainsKey(pepSeq))
{
IdentifiedPeptide pep = new IdentifiedPeptide(spectrum);
pep.Sequence = pepSeq;
pepmap[pepSeq] = pep;
spectrum.TheoreticalMH = MyConvert.ToDouble(domainNode.Attributes["mh"].Value);
spectrum.Score = MyConvert.ToDouble(domainNode.Attributes["hyperscore"].Value);
double nextScore = MyConvert.ToDouble(domainNode.Attributes["nextscore"].Value);
spectrum.DeltaScore = (spectrum.Score - nextScore) / spectrum.Score;
spectrum.NumMissedCleavages = int.Parse(domainNode.Attributes["missed_cleavages"].Value);
}
var noteNode = xmlHelper.GetValidChild(proteinNode, "note");
string proteinName = noteNode.InnerText.StringBefore(" ").StringBefore("\t");
pepmap[pepSeq].AddProtein(proteinName);
}
if (spectrum.Peptides.Count > 0)
{
spectrum.DigestProtease = protease;
result.Add(spectrum);
spectrum.Query.QueryId = int.Parse(groupNode.Attributes["id"].Value);
spectrum.ExperimentalMH = MyConvert.ToDouble(groupNode.Attributes["mh"].Value);
spectrum.ExpectValue = MyConvert.ToDouble(groupNode.Attributes["expect"].Value);
XmlNode spectrumNode = xmlHelper.GetFirstChildByNameAndAttribute(groupNode, "group", "label", "fragment ion mass spectrum");
XmlNode labelNode = xmlHelper.GetFirstChildByNameAndAttribute(spectrumNode, "note", "label", "Description");
string title = labelNode.InnerText.Trim();
if (title.StartsWith("RTINSECONDS"))
{
var rtvalue = title.StringAfter("=").StringBefore(" ").StringBefore("-");
spectrum.Query.FileScan.RetentionTime = double.Parse(rtvalue);
title = title.StringAfter(" ").Trim();
}
SequestFilename sf = this.TitleParser.GetValue(title);
if (sf.Experimental == null || sf.Experimental.Length == 0)
{
sf.Experimental = sourceFilename;
}
spectrum.Query.FileScan.LongFileName = sf.LongFileName;
if (sf.RetentionTime > 0 && spectrum.Query.FileScan.RetentionTime == 0)
{
spectrum.Query.FileScan.RetentionTime = sf.RetentionTime;
}
spectrum.Query.Charge = int.Parse(groupNode.Attributes["z"].Value);
spectrum.Query.Title = title;
}
}
return(result);
}
/// <summary>
///
/// Get the query/peptide map from mascot dat file.
///
/// </summary>
/// <param name="filename">pFind proteins file</param>
/// <param name="minRank">Minimum rank of peptide identified in same spectrum</param>
/// <param name="minScore">Minimum score of peptide identified in same spectrum</param>
/// <returns>Query/peptide map</returns>
public Dictionary <int, List <IIdentifiedSpectrum> > ParsePeptides(string filename, int minRank, double minScore)
{
var result = new Dictionary <int, List <IIdentifiedSpectrum> >();
var sourceDir = GetSourceFile(filename);
using (var sr = new StreamReader(filename))
{
var parameters = ParseSection(sr, "Search");
var mm = ParseModification(parameters);
foreach (var mod in mm.DynamicModification)
{
if (!this.ModificationCharMap.ContainsKey(mod.Modification))
{
this.ModificationCharMap[mod.Modification] = ModificationConsts.MODIFICATION_CHAR[this.ModificationCharMap.Count + 1];
}
}
var headers = ParseSection(sr, "Total");
var queryCount = int.Parse(headers["Spectra"]);
Progress.SetRange(1, queryCount);
for (int queryId = 1; queryId <= queryCount; queryId++)
{
if (Progress.IsCancellationPending())
{
throw new UserTerminatedException();
}
Progress.SetPosition(queryId);
var speName = MyConvert.Format("Spectrum{0}", queryId);
var peptideSection = ParseSection(sr, speName);
int candidateCount = int.Parse(peptideSection["ValidCandidate"]);
if (candidateCount == 0)
{
continue;
}
var expMH = MyConvert.ToDouble(peptideSection["MH"]);
var expMz = MyConvert.ToDouble(peptideSection["MZ"]);
var charge = int.Parse(peptideSection["Charge"]);
var iPeps = new List <IIdentifiedSpectrum>();
result[queryId] = iPeps;
IIdentifiedSpectrum lastHit = null;
int rank = 0;
for (int k = 1; k <= candidateCount; k++)
{
string key = "NO" + k.ToString();
var scoreKey = key + "_Score";
if (!peptideSection.ContainsKey(scoreKey))
{
if (null != lastHit)
{
lastHit.DeltaScore = 1.0;
}
break;
}
double score = MyConvert.ToDouble(peptideSection[scoreKey]);
if (score < minScore || score == 0.0)
{
if (null != lastHit)
{
lastHit.DeltaScore = 1.0 - score / lastHit.Score;
}
break;
}
bool bSameRank = null != lastHit && score == lastHit.Score;
if (!bSameRank)
{
if (null != lastHit)
{
lastHit.DeltaScore = 1.0 - score / lastHit.Score;
}
rank++;
if (rank > minRank)
{
break;
}
}
IIdentifiedSpectrum mphit;
if (bSameRank)
{
mphit = lastHit;
}
else
{
mphit = new IdentifiedSpectrum();
mphit.Rank = rank;
mphit.Score = score;
mphit.ExpectValue = MyConvert.ToDouble(peptideSection[key + "_EValue"]);
var mhkey = key + "_MH";
if (peptideSection.ContainsKey(mhkey))
{
mphit.TheoreticalMH = MyConvert.ToDouble(peptideSection[mhkey]);
}
else
{
mphit.TheoreticalMH = MyConvert.ToDouble(peptideSection[key + "_Mass"]);
}
var micKey = key + "_Matched_Peaks";
if (peptideSection.ContainsKey(micKey))
{
mphit.MatchedIonCount = int.Parse(peptideSection[micKey]);
mphit.MatchedTIC = MyConvert.ToDouble(peptideSection[key + "_Matched_Intensity"]);
}
var misKey = key + "_MissCleave";
if (peptideSection.ContainsKey(misKey))
{
mphit.NumMissedCleavages = int.Parse(peptideSection[misKey]);
}
mphit.ExperimentalMH = expMH;
mphit.DeltaScore = 1.0;
mphit.Query.QueryId = queryId;
mphit.Query.ObservedMz = expMz;
mphit.Query.Charge = charge;
//mphit.Query.MatchCount = queryItem.MatchCount;
lastHit = mphit;
}
var mp = new IdentifiedPeptide(mphit);
mp.Sequence = peptideSection[key + "_SQ"];
string modificationPos = peptideSection[key + "_Modify_Pos"];
string modificationName = peptideSection[key + "_Modify_Name"];
Dictionary <int, string> modifications = GetModifications(modificationPos, modificationName);
ModifySequence(mp, modifications, mm);
AssignModification(mphit, modifications, mm);
string proteins = peptideSection[key + "_Proteins"];
var parts = proteins.Split(',');
for (int i = 1; i < parts.Count(); i++)
{
mp.AddProtein(parts[i]);
}
if (!bSameRank)
{
iPeps.Add(mphit);
}
}
var title = new FileInfo(peptideSection["Input"]).Name;
SequestFilename sf = this.TitleParser.GetValue(title);
sf.Charge = charge;
if (sf.Experimental == null || sf.Experimental.Length == 0)
{
sf.Experimental = sourceDir;
}
foreach (IIdentifiedSpectrum mp in iPeps)
{
mp.Query.Title = title;
mp.Query.FileScan.LongFileName = sf.LongFileName;
}
}
}
return(result);
}
public List <PeakList <Peak> > ReadFromFile(string fileName)
{
List <PeakList <Peak> > result = new List <PeakList <Peak> >();
using (StreamReader sr = new StreamReader(fileName))
{
Progress.SetRange(0, sr.BaseStream.Length);
string line;
Dictionary <string, string> headers = new Dictionary <string, string>();
List <string> peaks = new List <string>();
while ((line = sr.ReadLine()) != null)
{
if (line.Trim().Equals("peaklist start"))
{
Progress.SetPosition(StreamUtils.GetCharpos(sr));
headers.Clear();
peaks.Clear();
bool inHeader = true;
while ((line = sr.ReadLine()) != null)
{
var tline = line.Trim();
if (tline.Equals("peaklist end"))
{
break;
}
if (tline.Length == 0)
{
continue;
}
if (!inHeader)
{
peaks.Add(tline);
}
else if (Char.IsLetter(tline[0]))
{
var pos = tline.IndexOf('=');
var key = tline.Substring(0, pos);
var value = tline.Substring(pos + 1);
headers[key] = value;
}
else
{
inHeader = false;
peaks.Add(tline);
}
}
if (headers.Count > 0 && peaks.Count > 0)
{
PeakList <Peak> pkl = new PeakList <Peak>();
pkl.PrecursorMZ = MyConvert.ToDouble(headers["mz"]);
pkl.PrecursorCharge = Convert.ToInt32(headers["charge"]);
pkl.MsLevel = 2;
pkl.ScanMode = headers["fragmentation"];
SequestFilename sf = parser.GetValue(headers["header"]);
pkl.ScanTimes.Add(new ScanTime(sf.FirstScan, 0.0));
pkl.Experimental = sf.Experimental;
result.Add(pkl);
foreach (var l in peaks)
{
var p = l.Split('\t');
if (p.Length > 1)
{
pkl.Add(new Peak(MyConvert.ToDouble(p[0]), MyConvert.ToDouble(p[1])));
}
}
}
}
}
}
return(result);
}
public static SequestFilename ParseTitle(string title, int charge)
{
string trimTitle = title.Trim();
if (trimTitle.StartsWith("Cmpd "))
{
Match match = cmpdRegex.Match(trimTitle);
if (match.Success)
{
int scan = int.Parse(match.Groups[1].Value);
var result = new SequestFilename();
result.Experimental = "Cmpd";
result.FirstScan = scan;
result.LastScan = scan;
result.Charge = charge;
result.Extension = "dta";
return(result);
}
else
{
throw new ArgumentException("Unknow title fomat :" + title + " ; contact author please.");
}
}
if (trimTitle.Contains("Cmpd "))
{
Match match = sqhCmpdRegex.Match(trimTitle);
if (match.Success)
{
int scan = int.Parse(match.Groups[2].Value);
var result = new SequestFilename();
result.Experimental = match.Groups[1].Value.Trim();
result.FirstScan = scan;
result.LastScan = scan;
result.Charge = charge;
result.Extension = "dta";
return(result);
}
else
{
throw new ArgumentException("Unknow title fomat :" + title + " ; contact author please.");
}
}
if (trimTitle.StartsWith("spectrumId="))
{
//spectrumId=6085 Polarity=Positive ScanMode=ProductIon TimeInMinutes=61.875 acqNumber=3712494
Match match = qtofRegex.Match(trimTitle);
if (match.Success)
{
int scan = int.Parse(match.Groups[1].Value);
var result = new SequestFilename();
result.Experimental = "";
result.FirstScan = scan;
result.LastScan = scan;
result.Charge = charge;
result.Extension = "dta";
return(result);
}
else
{
throw new ArgumentException("Unknow title fomat :" + title + " ; contact author please.");
}
}
//Elution from: 40.798 to 40.798 period: 0 experiment: 1 cycles: 1 precIntensity: 355220.0 FinneganScanNumber: 6070 MStype: enumIsNormalMS rawFile: KR_mix_lc_090115.raw
if (trimTitle.StartsWith("Elution from"))
{
Match match = dtasuperchargeRegex.Match(trimTitle);
if (match.Success)
{
int scan = int.Parse(match.Groups[1].Value);
var result = new SequestFilename();
result.Experimental = FileUtils.ChangeExtension(match.Groups[2].Value, "");
result.FirstScan = scan;
result.LastScan = scan;
result.Charge = charge;
result.Extension = "dta";
return(result);
}
else
{
throw new ArgumentException("Unknow title fomat :" + title + " ; contact author please.");
}
}
try
{
return(SequestFilename.Parse(trimTitle));
}
catch (Exception)
{
}
try
{
return(SequestFilename.Parse(trimTitle + ".dta"));
}
catch (Exception)
{
}
try
{
return(SequestFilename.Parse(trimTitle + "." + charge + ".dta"));
}
catch (Exception)
{
}
throw new ArgumentException("Unknow title format :" + title + " ; contact author please.");
}
public override IEnumerable <string> Process(string targetDir)
{
var result = new List <string>();
targetDir = new DirectoryInfo(targetDir).FullName;
foreach (var sourceFile in sourceFiles)
{
var sourceDir = new FileInfo(sourceFile).DirectoryName;
string targetFile;
bool isSame = sourceDir.ToUpper() == targetDir.ToUpper();
if (isSame)
{
targetFile = sourceFile + ".tmp";
}
else
{
targetFile = targetDir + "\\" + new FileInfo(sourceFile).Name;
}
var chargereg = new Regex(@"(\d+)");
using (StreamReader sr = new StreamReader(sourceFile))
{
using (StreamWriter sw = new StreamWriter(targetFile))
{
string line;
string filename = null;
while ((line = sr.ReadLine()) != null)
{
if (line.StartsWith("title="))
{
string title = Uri.UnescapeDataString(line.Substring(6));
SequestFilename sf = this.parser.GetValue(title);
if (string.IsNullOrEmpty(sf.Experimental))
{
if (string.IsNullOrEmpty(filename))
{
filename = Path.GetFileNameWithoutExtension(sourceFile);
}
sf.Experimental = filename;
}
List <string> lines = new List <string>();
while ((line = sr.ReadLine()) != null)
{
lines.Add(line);
if (line.StartsWith("--"))
{
break;
}
}
var chargeLine = lines.Where(m => m.StartsWith("charge=")).First();
sf.Charge = Convert.ToInt32(chargereg.Match(chargeLine).Groups[1].Value);
line = "title=" + Uri.EscapeDataString(sf.LongFileName);
sw.WriteLine(line);
lines.ForEach(m => sw.WriteLine(m));
}
else if (line.StartsWith("FILE="))
{
filename = Path.GetFileNameWithoutExtension(line.StringAfter("File Name:").Trim());
}
else
{
sw.WriteLine(line);
}
}
}
}
if (isSame)
{
File.Delete(sourceFile);
File.Move(targetFile, sourceFile);
result.Add(sourceFile);
}
else
{
result.Add(targetFile);
}
}
return(result);
}
public PeakList <T> ReadFromFile(string dtaFilename)
{
var fi = new FileInfo(dtaFilename);
if (!fi.Exists)
{
throw new FileNotFoundException("Cannot find the file " + dtaFilename);
}
var result = new PeakList <T>();
SequestFilename sf = SequestFilename.Parse(fi.Name);
result.Experimental = sf.Experimental;
result.ScanTimes.Add(new ScanTime(sf.FirstScan, 0.0));
if (sf.FirstScan != sf.LastScan)
{
result.ScanTimes.Add(new ScanTime(sf.LastScan, 0.0));
}
result.PrecursorCharge = sf.Charge;
using (var filein = new StreamReader(new FileStream(dtaFilename, FileMode.Open, FileAccess.Read)))
{
string lastline;
while ((lastline = filein.ReadLine()) != null)
{
if (lastline.Trim().Length > 0)
{
break;
}
}
if (lastline == null)
{
return(null);
}
string[] parts = Regex.Split(lastline, @"\s+");
double precursorMass = MyConvert.ToDouble(parts[0]);
result.PrecursorCharge = int.Parse(parts[1]);
result.PrecursorMZ = PrecursorUtils.MHToMz(precursorMass, result.PrecursorCharge, true);
while ((lastline = filein.ReadLine()) != null)
{
if (lastline.Length == 0)
{
continue;
}
if (lastline[0] == '>')
{
break;
}
string[] peakParts = Regex.Split(lastline, @"\s+");
var peak = new T();
peak.Mz = MyConvert.ToDouble(peakParts[0]);
peak.Intensity = MyConvert.ToDouble(peakParts[1]);
if (peakParts.Length > 2)
{
peak.Charge = int.Parse(peakParts[2]);
}
result.Add(peak);
}
return(result);
}
}
private static string GetScan(SequestFilename p)
{
return(MyConvert.Format("{0}.{1}", p.Experimental, p.FirstScan));
}
public IdentifiedSpectrum(SequestFilename sf)
: this()
{
query.FileScan = sf;
}
protected IdentifiedProtein ParseProtein(String proteinContent)
{
IdentifiedProtein result = GetProtein(proteinContent);
List <String> peptideInfoContentList = GetPeptideInfoContentList(proteinContent);
foreach (String peptideInfoContent in peptideInfoContentList)
{
List <String> peptideInfo = GetPeptideInfo(peptideInfoContent);
if (0 == peptideInfo.Count)
{
continue;
}
IIdentifiedSpectrum mphit = new IdentifiedSpectrum();
// Group 0 : peptide mass from observed m/z
double experimentalPeptideMass = MyConvert.ToDouble(peptideInfo[0]);
mphit.ExperimentalMass = experimentalPeptideMass;
// Group 1 : observed m/z
double observed = MyConvert.ToDouble(peptideInfo[1]);
mphit.Query.ObservedMz = observed;
// Group 2 : charge
int charge = int.Parse(peptideInfo[2]);
mphit.Query.Charge = charge;
// Group 3 : title
String title = Uri.UnescapeDataString(peptideInfo[3]).Trim();
mphit.Query.Title = title;
SequestFilename sf = MascotUtils.ParseTitle(title, charge);
if (sf != null)
{
mphit.Query.FileScan.LongFileName = sf.LongFileName;
}
// Group 4 : query
mphit.Query.QueryId = int.Parse(peptideInfo[4]);
// Group 5 equals Group 1
// Group 6 equals Group 0
// Group 7 : calculated peptide mass
mphit.TheoreticalMass = MyConvert.ToDouble(peptideInfo[7]);
// Group 8 : different between observed peptide mass and calculated
// peptide mass
// Group 9 : miss cleavage
mphit.NumMissedCleavages = int.Parse(peptideInfo[9]);
// Group 10: score
mphit.Score = int.Parse(peptideInfo[10]);
// Group 11: expect p value
mphit.ExpectValue = MyConvert.ToDouble(peptideInfo[11]);
// Group 12: rank
mphit.Rank = int.Parse(peptideInfo[12]);
// Group 13: peptide sequence
// K.YEINVLR<u>.</u>N + Label:18O(2) (C-term)
String seq = peptideInfo[13].Replace(" ", "");
var mpep = new IdentifiedPeptide(mphit);
string[] parts = Regex.Split(seq, "\\+");
if (parts.Length > 1)
{
seq = parts[0].Trim();
mphit.Modifications = parts[1].Trim();
string[] mods = parts[1].Trim().Split(new[] { ';' }, StringSplitOptions.RemoveEmptyEntries);
foreach (string mod in mods)
{
Match m = this.modificationReg.Match(mod.Trim());
if (!this.modifications.ContainsKey(m.Groups[1].Value))
{
this.modifications[m.Groups[1].Value] = ' ';
}
}
}
mpep.Sequence = seq;
if (GetPeptideFilter().Accept(mphit))
{
mpep.AddProtein(result.Name);
result.Peptides.Add(mpep);
}
}
return(result);
}
public Dictionary <int, List <IIdentifiedSpectrum> > DoParsePeptides(string datFilename, int minRank, double minScore, bool isDecoy)
{
var result = new Dictionary <int, List <IIdentifiedSpectrum> >();
Dictionary <string, string> headers;
int queryCount;
Dictionary <int, MascotQueryItem> queryItems;
Dictionary <string, string> peptideSection;
var prefix = isDecoy ? "decoy_" : "";
using (var sr = new StreamReader(datFilename))
{
InitializeBoundary(sr);
CurrentParameters = ParseSection(sr, "parameters");
var hasDecoy = CurrentParameters.ContainsKey("DECOY") && CurrentParameters["DECOY"].Equals("1");
if (!hasDecoy && isDecoy)
{
return(result);
}
var masses = ParseSection(sr, "masses");
CurrentModifications = ParseModification(masses);
long curPos = sr.GetCharpos();
CurrentProtease = ParseEnzyme(sr);
sr.SetCharpos(curPos);
headers = ParseSection(sr, "header");
queryCount = int.Parse(headers["queries"]);
queryItems = ParseQueryItems(sr, queryCount, prefix);
peptideSection = ParseSection(sr, prefix + "peptides", !isDecoy);
}
string file = CurrentParameters["FILE"];
if (file.StartsWith("File Name: "))
{
file = file.Substring(10).Trim();
}
string defaultExperimental = FileUtils.ChangeExtension(new FileInfo(file).Name, "");
bool isPrecursorMonoisotopic = true;
if (CurrentParameters.ContainsKey("MASS"))
{
isPrecursorMonoisotopic = CurrentParameters["MASS"].Equals("Monoisotopic");
}
using (var sr = new StreamReader(datFilename))
{
//Progress.SetRange(1, queryCount);
for (int queryId = 1; queryId <= queryCount; queryId++)
{
if (Progress.IsCancellationPending())
{
throw new UserTerminatedException();
}
//Progress.SetPosition(queryId);
MascotQueryItem queryItem = queryItems[queryId];
var iPeps = new List <IIdentifiedSpectrum>();
result[queryId] = iPeps;
IIdentifiedSpectrum lastHit = null;
int rank = 0;
for (int k = 1; k <= 10; k++)
{
string key = "q" + queryId + "_p" + k;
if (!peptideSection.ContainsKey(key))
{
if (null != lastHit)
{
lastHit.DeltaScore = 1.0;
}
break;
}
string line = peptideSection[key];
if (line == null || line.Equals("-1"))
{
if (null != lastHit)
{
lastHit.DeltaScore = 1.0;
}
break;
}
Match mDetail = this.peptideRegex.Match(line);
if (!mDetail.Success)
{
throw new Exception("Wrong format of peptides : " + line);
}
double score = MyConvert.ToDouble(mDetail.Groups["Score"].Value);
if (score < minScore)
{
if (null != lastHit)
{
lastHit.DeltaScore = 1.0 - score / lastHit.Score;
}
break;
}
bool bSameRank = null != lastHit && score == lastHit.Score;
if (!bSameRank)
{
if (null != lastHit)
{
lastHit.DeltaScore = 1.0 - score / lastHit.Score;
}
rank++;
if (rank > minRank)
{
break;
}
}
IIdentifiedSpectrum mphit;
if (bSameRank)
{
mphit = lastHit;
}
else
{
mphit = new IdentifiedSpectrum();
mphit.IsPrecursorMonoisotopic = isPrecursorMonoisotopic;
mphit.Rank = rank;
mphit.NumMissedCleavages = int.Parse(mDetail.Groups["MissCleavage"].Value);
mphit.TheoreticalMass = MyConvert.ToDouble(mDetail.Groups["TheoreticalMass"].Value);
mphit.ExperimentalMass = queryItem.ExperimentalMass;
mphit.Score = score;
mphit.ExpectValue = ExpectValueCalculator.Calc(mphit.Score, queryItem.MatchCount, 0.05);
mphit.Query.QueryId = queryId;
mphit.Query.ObservedMz = queryItem.Observed;
mphit.Query.Charge = queryItem.Charge;
mphit.Query.MatchCount = queryItem.MatchCount;
if (queryItem.HomologyScore != 0)
{
mphit.Annotations[HomologyScoreKey] = queryItem.HomologyScore;
}
if (CurrentProtease.IsSemiSpecific)
{
mphit.NumProteaseTermini = 1;
}
lastHit = mphit;
}
var pureSeq = mDetail.Groups["Sequence"].Value;
string modification = mDetail.Groups["Modification"].Value;
var seq = ModifySequence(pureSeq, modification);
AssignModification(mphit, modification, CurrentModifications);
string proteins = mDetail.Groups["ProteinNames"].Value;
Match proteinNameMatch = this.proteinNameRegex.Match(proteins);
string key_terms = key + "_terms";
if (!peptideSection.ContainsKey(key_terms))
{
throw new Exception("Mascot version is too old. It's not supported.");
}
string value_terms = peptideSection[key_terms];
Match termsMatch = this.termsRegex.Match(value_terms);
int numProteaseTermini = 0;
while (proteinNameMatch.Success && termsMatch.Success)
{
var fullSeq = MyConvert.Format("{0}.{1}.{2}",
termsMatch.Groups[1].Value,
seq,
termsMatch.Groups[2].Value);
var name = proteinNameMatch.Groups[1].Value.Replace("/", "_");
if (isDecoy)
{
name = DECOY_PREFIX + name;
}
bool findPeptide = false;
for (int i = 0; i < mphit.Peptides.Count; i++)
{
if (mphit.Peptides[i].Sequence == fullSeq)
{
mphit.Peptides[i].AddProtein(name);
findPeptide = true;
break;
}
}
if (!findPeptide)
{
var mp = new IdentifiedPeptide(mphit);
mp.Sequence = fullSeq;
mp.AddProtein(name);
if (CurrentProtease.IsSemiSpecific)
{
int position = Convert.ToInt32(proteinNameMatch.Groups[2].Value);
int count = CurrentProtease.GetNumProteaseTermini(termsMatch.Groups[1].Value[0], pureSeq, termsMatch.Groups[2].Value[0], '-', position);
numProteaseTermini = Math.Max(numProteaseTermini, count);
}
}
proteinNameMatch = proteinNameMatch.NextMatch();
termsMatch = termsMatch.NextMatch();
}
if (CurrentProtease.IsSemiSpecific)
{
mphit.NumProteaseTermini = Math.Max(mphit.NumProteaseTermini, numProteaseTermini);
}
if (!bSameRank)
{
iPeps.Add(mphit);
}
}
string query = "query" + queryId;
Dictionary <string, string> querySection = ParseSection(sr, query);
string title = Uri.UnescapeDataString(querySection["title"]);
SequestFilename sf = this.TitleParser.GetValue(title);
sf.Charge = queryItem.Charge;
if (sf.Experimental == null || sf.Experimental.Length == 0)
{
sf.Experimental = defaultExperimental;
}
foreach (IIdentifiedSpectrum mp in iPeps)
{
mp.Query.Title = title;
mp.Query.FileScan = sf;
}
}
}
return(result);
}
public override IEnumerable <string> Process()
{
var spectra = new MaxQuantPeptideTextReader().ReadFromFile(options.SiteFile);
spectra.RemoveAll(m => m.DeltaScore < options.MinDeltaScore || m.Probability < options.MinProbability);
spectra = (from g in spectra.GroupBy(m => m.Query.FileScan.ShortFileName)
select g.OrderBy(l => l.Score).Last()).ToList();
if (options.IsSILAC)
{
var spmap = spectra.ToDictionary(m => m.Query.FileScan.ShortFileName);
var existModificationChar = (from sp in spectra
from c in sp.Sequence
where !char.IsLetter(c)
select c).Distinct().Count();
Dictionary <char, char> labelChars = new Dictionary <char, char>();
foreach (var c in options.SILACAminoacids)
{
labelChars[c] = ModificationConsts.MODIFICATION_CHAR[++existModificationChar];
}
using (var sr = new StreamReader(options.MSMSFile))
{
var headers = sr.ReadLine().Split('\t');
var rawIndex = Array.IndexOf(headers, "Raw file");
var scanIndex = Array.IndexOf(headers, "Scan number");
string line;
while ((line = sr.ReadLine()) != null)
{
if (string.IsNullOrWhiteSpace(line))
{
break;
}
var parts = line.Split('\t');
var raw = parts[rawIndex];
var scan = int.Parse(parts[scanIndex]);
var sf = new SequestFilename(raw, scan, scan, 0, "");
var name = sf.ShortFileName;
IIdentifiedSpectrum sp;
if (spmap.TryGetValue(name, out sp))
{
foreach (var pep in sp.Peptides)
{
var seq = pep.Sequence;
StringBuilder sb = new StringBuilder();
for (int i = seq.Length - 1; i >= 0; i--)
{
char heavyChar;
if (labelChars.TryGetValue(seq[i], out heavyChar))
{
sb.Append(heavyChar);
}
sb.Append(seq[i]);
}
pep.Sequence = SequenceUtils.GetReversedSequence(sb.ToString());
}
}
}
}
}
string resultFilename = options.SiteFile + ".peptides";
new MascotPeptideTextFormat("\t\"File, Scan(s)\"\tSequence\tCharge\tScore\tDeltaScore\tExpectValue\tPValue\tModification").WriteToFile(resultFilename, spectra);
return(new[] { resultFilename });
}
public override IEnumerable <string> Process(string targetDir)
{
var result = new List <string>();
targetDir = new DirectoryInfo(targetDir).FullName;
foreach (var sourceFile in sourceFiles)
{
var sourceDir = new FileInfo(sourceFile).DirectoryName;
string targetFile;
bool isSame = sourceDir.ToUpper() == targetDir.ToUpper();
if (isSame)
{
targetFile = sourceFile + ".tmp";
}
else
{
targetFile = targetDir + "\\" + new FileInfo(sourceFile).Name;
}
var chargereg = new Regex(@"(\d+)");
using (StreamReader sr = new StreamReader(sourceFile))
{
using (StreamWriter sw = new StreamWriter(targetFile))
{
string line;
int charge = 0;
while ((line = sr.ReadLine()) != null)
{
if (line.StartsWith("BEGIN IONS"))
{
charge = 0;
}
else if (line.StartsWith("CHARGE="))
{
charge = Convert.ToInt32(chargereg.Match(line).Groups[1].Value);
}
else if (line.StartsWith("TITLE="))
{
string title = line.Substring(6);
SequestFilename sf = this.parser.GetValue(title);
sf.Extension = "dta";
sf.Charge = charge;
line = "TITLE=" + sf.LongFileName;
}
sw.WriteLine(line);
}
}
}
if (isSame)
{
File.Delete(sourceFile);
File.Move(targetFile, sourceFile);
result.Add(sourceFile);
}
else
{
result.Add(targetFile);
}
}
return(result);
}
