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 List <IIdentifiedSpectrum> ReadFromFile(string fileName)
{
XElement root = XElement.Load(fileName);
var name = root.FindElement("AnalysisSoftwareList").
FindElement("AnalysisSoftware").
FindElement("SoftwareName").
FindElement("cvParam").Attribute("name").Value;
var defaultExp = Path.GetFileNameWithoutExtension(fileName);
foreach (var ext in extensions)
{
if (defaultExp.ToLower().EndsWith(ext))
{
defaultExp = defaultExp.Substring(0, defaultExp.Length - ext.Length);
}
}
//parsing identification protocol first
var protocols = root.FindElement("AnalysisProtocolCollection");
var sip = protocols.FindElement("SpectrumIdentificationProtocol");
var modMap = ParseSearchModificationMap(sip.FindElement("ModificationParams"));
var proteases = ParseEnzymes(sip.FindElement("Enzymes"));
var protease = proteases.FirstOrDefault();
//parsing sequence collection, including protein<->peptide map
var seqs = root.FindElement("SequenceCollection");
var proteinMap = (from ele in seqs.FindElements("DBSequence")
let id = ele.Attribute("id").Value
let accession = ParseAccession(ele.Attribute("accession").Value)
let db = ele.Attribute("searchDatabase_ref").Value
select new { Id = id, Accession = accession, DB = db }).ToDictionary(m => m.Id);
var peptideMap = (from ele in seqs.FindElements("Peptide")
let id = ele.Attribute("id").Value
let seq = ele.FindElement("PeptideSequence").Value
let mods = (from modEle in ele.FindElements("Modification")
let mod = ParseModification(modEle, modMap)
where mod != null
orderby mod.Location descending
select mod).ToArray()
let numMiss = protease == null ? 0 : protease.GetMissCleavageSiteCount(seq)
select new MzIdentPeptideItem()
{
Id = id,
PureSequence = seq,
Modifications = mods,
Sequence = GetModifiedSequence(seq, mods),
NumMissCleavage = numMiss
}).ToDictionary(m => m.Id);
var peptideEvidenceMap = (from g in
(from ele in seqs.FindElements("PeptideEvidence")
select new MzIdentPeptideEvidenceItem()
{
Id = ele.Attribute("id").Value,
PeptideRef = ele.Attribute("peptide_ref").Value,
DbRef = ele.Attribute("dBSequence_ref").Value,
Pre = ele.Attribute("pre").Value,
Post = ele.Attribute("post").Value
}).GroupBy(m => m.Id)
select g.First()).ToDictionary(m => m.Id);
//now parsing data
var data = root.FindElement("DataCollection");
var result = new List <IIdentifiedSpectrum>();
var analysisData = data.FindElement("AnalysisData");
var idList = analysisData.FindElement("SpectrumIdentificationList");
foreach (var sir in idList.FindElements("SpectrumIdentificationResult"))
{
var items = FilterItems(sir.FindElements("SpectrumIdentificationItem"), peptideMap, peptideEvidenceMap);
if (items.Count == 0)
{
continue;
}
var spectrum = new IdentifiedSpectrum();
result.Add(spectrum);
var spectrumId = sir.Attribute("spectrumID").Value;
var sirCvParams = GetCvParams(sir);
string value;
if (sirCvParams.TryGetValue("MS:1000796", out value))
{
spectrum.Query.FileScan = TitleParser.GetValue(value);
}
else
{
if (spectrumId.StartsWith("index=") || spectrumId.StartsWith("scan="))
{
spectrum.Query.FileScan.Experimental = defaultExp;
spectrum.Query.FileScan.FirstScan = int.Parse(spectrumId.StringAfter("="));
spectrum.Query.FileScan.LastScan = spectrum.Query.FileScan.FirstScan;
}
else
{
spectrum.Query.FileScan.Experimental = spectrumId;
}
}
if (sirCvParams.TryGetValue("MS:1001115", out value))
{
spectrum.Query.FileScan.FirstScan = int.Parse(value);
}
if (spectrum.Query.FileScan.FirstScan == 0)
{
throw new Exception(string.Format("Cannot find scan information in file {0}", fileName));
}
bool bFirst = true;
foreach (var sit in items)
{
if (bFirst) //only parse score once
{
spectrum.Id = sit.Attribute("id").Value;
spectrum.Charge = int.Parse(sit.Attribute("chargeState").Value);
spectrum.TheoreticalMH = PrecursorUtils.MzToMH(double.Parse(sit.Attribute("calculatedMassToCharge").Value), spectrum.Charge, true);
spectrum.ExperimentalMH = PrecursorUtils.MzToMH(double.Parse(sit.Attribute("experimentalMassToCharge").Value), spectrum.Charge, true);
var cvParams = GetCvParams(sit);
if (cvParams.TryGetValue("MS:1001121", out value))
{
spectrum.MatchedIonCount = int.Parse(value);
}
if (cvParams.TryGetValue("MS:1001362", out value))
{
spectrum.TheoreticalIonCount = int.Parse(value) + spectrum.MatchedIonCount;
}
ParseScore(spectrum, cvParams);
var userParams = GetUserParams(sit);
ParseUserParams(spectrum, userParams);
bFirst = false;
}
var peptide = new IdentifiedPeptide(spectrum);
var pep_ref = sit.Attribute("peptide_ref").Value;
var pep = peptideMap[pep_ref];
spectrum.Modifications = (from m in pep.Modifications
select string.Format("{0}:{1}", m.Location, m.Item.Name)).Reverse().Merge(",");
spectrum.NumMissedCleavages = pep.NumMissCleavage;
foreach (var per in sit.FindElements("PeptideEvidenceRef"))
{
var pe_ref = per.Attribute("peptideEvidence_ref").Value;
var pe = peptideEvidenceMap[pe_ref];
peptide.Sequence = pe.Pre + "." + pep.Sequence + "." + pe.Post;
var protein = proteinMap[pe.DbRef];
peptide.AddProtein(protein.Accession);
}
}
}
return(result);
}
public List <IIdentifiedSpectrum> ReadFromFile(string fileName)
{
var result = new MascotPeptideTextFormat().ReadFromFile(fileName);
FilterSpectra(result);
UpdateModifications(result);
foreach (var peptide in result)
{
peptide.Peptide.AssignProteins((peptide.Annotations[PROTEIN_KEY] as string).Split(';'));
peptide.Annotations.Remove(PROTEIN_KEY);
peptide.TheoreticalMass = peptide.ExperimentalMass;
}
var i = 0;
while (i < result.Count - 1)
{
var ititle = result[i].Annotations[TITLE_KEY] as string;
while (i < result.Count - 1)
{
var jtitle = result[i + 1].Annotations[TITLE_KEY] as string;
if (!ititle.Equals(jtitle))
{
i++;
break;
}
for (int l = result[i + 1].Peptides.Count - 1; l >= 0; l--)
{
result[i].AddPeptide(result[i + 1].Peptides[l]);
}
result.RemoveAt(i + 1);
}
}
foreach (var peptide in result)
{
var title = peptide.Annotations[TITLE_KEY] as string;
peptide.Annotations.Remove(TITLE_KEY);
var oldCharge = peptide.Query.FileScan.Charge;
peptide.Query.FileScan = TitleParser.GetValue(title);
peptide.Query.FileScan.Charge = oldCharge;
if (string.IsNullOrEmpty(peptide.Query.FileScan.Experimental))
{
peptide.Query.FileScan.Experimental = Path.GetFileNameWithoutExtension(fileName);
}
var rtstr = peptide.Annotations[RT_KEY] as string;
if (!string.IsNullOrWhiteSpace(rtstr))
{
peptide.Query.FileScan.RetentionTime = double.Parse(rtstr.StringBefore("-"));
}
peptide.Annotations.Remove(RT_KEY);
}
return(result);
}
public virtual List <IIdentifiedSpectrum> ReadFromFile(string fileName)
{
if (this.TitleParser == null)
{
throw new Exception("Title format is not defined for parsing " + fileName);
}
List <IIdentifiedSpectrum> result = new List <IIdentifiedSpectrum>();
XElement root = XElement.Load(fileName);
var msms_run_summaries = root.FindDescendants("msms_run_summary");
foreach (var msms_run_summary in msms_run_summaries)
{
var search_summary = msms_run_summary.FindFirstDescendant("search_summary");
var engine = search_summary.Attribute("search_engine").Value;
var ismono = search_summary.Attribute("precursor_mass_type").Value.Equals("monoisotopic");
var enzyme = ParseProtease(msms_run_summary.FindFirstDescendant("sample_enzyme"));
var modifications = ParseModifications(msms_run_summary);
var spectrumQueries = msms_run_summary.FindDescendants("spectrum_query");
foreach (var sp in spectrumQueries)
{
IdentifiedSpectrum sph = new IdentifiedSpectrum();
sph.IsPrecursorMonoisotopic = ismono;
SequestFilename sf;
if (sp.Attribute("spectrumNativeID") != null)
{
sf = TitleParser.GetValue(sp.Attribute("spectrumNativeID").Value);
}
else
{
sf = TitleParser.GetValue(sp.Attribute("spectrum").Value);
}
sph.Query.FileScan.LongFileName = sf.LongFileName;
sph.ExperimentalMass = MyConvert.ToDouble(sp.Attribute("precursor_neutral_mass").Value);
sph.Query.Charge = int.Parse(sp.Attribute("assumed_charge").Value);
var searchResult = sp.FindFirstDescendant("search_result");
var searchHit = FindSearchHit(searchResult);
if (searchHit == null)
{
continue;
}
sph.TheoreticalMass = MyConvert.ToDouble(searchHit.Attribute("calc_neutral_pep_mass").Value);
sph.MatchedIonCount = int.Parse(searchHit.Attribute("num_matched_ions").Value);
sph.Rank = int.Parse(searchHit.Attribute("hit_rank").Value);
var ticAtt = searchHit.Attribute("tot_num_ions");
sph.TheoreticalIonCount = ticAtt == null ? 0 : int.Parse(ticAtt.Value);
ParseSearchHit(sph, searchHit, modifications);
sph.Engine = engine;
sph.DigestProtease = enzyme;
result.Add(sph);
}
}
return(result);
}