public static PsmDataCollection ExtractPsmData(XElement results, SearchAlgorithm searchAlgorithm)
{
PsmDataCollection psms = new PsmDataCollection();
PsmData psm;
if (searchAlgorithm == SearchAlgorithm.XTandem)
{
foreach (var x in results.Descendants("group").Where(x => x?.Element("protein") != null))
{
psm = new PsmData();
psm.Id = Convert.ToInt32(x.Attribute("id").Value);
psm.Decoy = x.Attribute("label").Value.StartsWith("DECOY_");
// it is possible for each "group" in the pepXML file to have more than one protein. This just means the peptide isn't
// unique to a single protein. However, the scoring and modifications are identical (since it is the same PSM), so we
// can just use the first protein. That is what we do below.
XElement domain = x.Element("protein").Element("peptide").Element("domain");
psm.Seq = domain.Attribute("seq").Value;
psm.Start = Convert.ToInt32(domain.Attribute("start").Value);
psm.End = Convert.ToInt32(domain.Attribute("end").Value);
psm.Hyperscore = Convert.ToDouble(domain.Attribute("hyperscore").Value);
psm.ExpectationValue = Convert.ToDouble(domain.Attribute("expect").Value);
psm.MassDrift = (Convert.ToDouble(x.Attribute("mh")?.Value) - Convert.ToDouble(domain?.Attribute("mh").Value)) /
Convert.ToDouble(domain?.Attribute("mh").Value) * 1e6;
psm.Charge = Convert.ToInt32(x.Attribute("z").Value);
psm.MissedCleavages = GetMissedCleavages(psm.Seq);
// add the modifications, if there are any
if (domain?.Elements("aa") != null)
{
foreach (XElement aa in domain.Elements("aa"))
{
Modification mod = new Modification();
// we convert the location to a zero-based index of the peptide
mod.Loc = Convert.ToInt32(aa.Attribute("at").Value) - psm.Start;
mod.AA = aa.Attribute("type").Value;
mod.Mass = Convert.ToDouble(aa.Attribute("modified").Value);
psm.Mods.Add(mod);
}
}
psms.Add(psm.Id, psm);
}
}
return(psms);
}
public static void ParseSearchResults(this QcDataContainer qcData, RawDataCollection rawData, IRawDataPlus rawFile, QcParameters qcParameters)
{
XElement results = LoadSearchResults(qcParameters, rawData);
PsmDataCollection Psms = ExtractPsmData(results, qcParameters.searchParameters.SearchAlgorithm);
qcData.ParsePSMs(Psms, qcParameters);
}
public static SearchMetricsContainer ParseSearchResults(SearchMetricsContainer searchMetrics, WorkflowParameters parameters, string rawFileName)
{
XElement results = LoadSearchResults(parameters, rawFileName);
PsmDataCollection Psms = ExtractPsmData(results, parameters.QcParams.SearchAlgorithm);
searchMetrics.ParsePSMs(Psms, parameters);
return(searchMetrics);
}
public static PsmDataCollection ExtractPsmData(XElement results, SearchAlgorithm searchAlgorithm)
{
PsmDataCollection psms = new PsmDataCollection();
PsmData psm;
if (searchAlgorithm == SearchAlgorithm.XTandem)
{
foreach (var x in results.Descendants("group").Where(x => x?.Element("protein") != null))
{
psm = new PsmData();
psm.Id = Convert.ToInt32(x.Attribute("id").Value);
psm.Decoy = x.Attribute("label").Value.StartsWith("DECOY_");
// it is possible for each "group" in the pepXML file to have more than one protein. This just means the peptide isn't
// unique to a single protein. However, the scoring and modifications are identical (since it is the same PSM), so we
// can just use the first protein. That is what we do below.
XElement domain = x.Element("protein").Element("peptide").Element("domain");
psm.Seq = domain.Attribute("seq").Value;
psm.Start = Convert.ToInt32(domain.Attribute("start").Value);
psm.End = Convert.ToInt32(domain.Attribute("end").Value);
psm.Hyperscore = Convert.ToDouble(domain.Attribute("hyperscore").Value);
psm.ExpectationValue = Convert.ToDouble(domain.Attribute("expect").Value);
psm.MassDrift = (Convert.ToDouble(x.Attribute("mh")?.Value) - Convert.ToDouble(domain?.Attribute("mh").Value)) /
Convert.ToDouble(domain?.Attribute("mh").Value) * 1e6;
psm.Charge = Convert.ToInt32(x.Attribute("z").Value);
psm.MissedCleavages = GetMissedCleavages(psm.Seq);
// add the modifications, if there are any
if (domain?.Elements("aa") != null)
{
foreach (XElement aa in domain.Elements("aa"))
{
Modification mod = new Modification();
// we convert the location to a zero-based index of the peptide
mod.Loc = Convert.ToInt32(aa.Attribute("at").Value) - psm.Start;
mod.AA = aa.Attribute("type").Value;
mod.Mass = Convert.ToDouble(aa.Attribute("modified").Value);
psm.Mods.Add(mod);
}
}
psms.Add(psm.Id, psm);
}
}
if (searchAlgorithm == SearchAlgorithm.IdentiPy)
{
XNamespace nsp = "http://regis-web.systemsbiology.net/pepXML";
// first we need to make a dictionary of modification masses etc for the identipy results
// the keys are the amino acid mass after modification, which is what identipy reports
// the values are the mass difference values, which is what is given in the mass@aa arguments to the CLI
XElement summary = results.Descendants(nsp + "search_summary").First();
Dictionary <double, double> modInfo = new Dictionary <double, double>();
foreach (XElement mod in summary.Elements(nsp + "aminoacid_modification"))
{
modInfo.Add(Convert.ToDouble(mod.Attribute("mass").Value), Convert.ToDouble(mod.Attribute("massdiff").Value));
}
foreach (XElement mod in summary.Elements(nsp + "terminal_modification"))
{
modInfo.Add(Convert.ToDouble(mod.Attribute("mass").Value), Convert.ToDouble(mod.Attribute("massdiff").Value));
}
// now we can parse out the data
foreach (var x in results.Descendants(nsp + "spectrum_query"))
{
psm = new PsmData();
psm.Id = Convert.ToInt32(x.Attribute("index").Value);
XElement searchHit = x.Element(nsp + "search_result").Element(nsp + "search_hit");
psm.Decoy = searchHit.Attribute("protein").Value.StartsWith("DECOY_");
psm.Seq = searchHit.Attribute("peptide").Value;
psm.Start = -1;
psm.End = -1;
psm.Hyperscore = Convert.ToDouble(searchHit.Elements(nsp + "search_score")
.Where(y => y.Attribute("name").Value == "hyperscore").First().Attribute("value").Value);
psm.ExpectationValue = Convert.ToDouble(searchHit.Elements(nsp + "search_score")
.Where(y => y.Attribute("name").Value == "expect").First().Attribute("value").Value);
psm.MassDrift = Convert.ToDouble(searchHit.Attribute("massdiff").Value) / Convert.ToDouble(x.Attribute("precursor_neutral_mass").Value) * 1e6;
psm.Charge = Convert.ToInt32(x.Attribute("assumed_charge").Value);
psm.MissedCleavages = GetMissedCleavages(psm.Seq);
// add the modifications, if there are any
if (searchHit.Element(nsp + "modification_info")?.Attribute("mod_nterm_mass") != null)
{
Modification mod = new Modification();
mod.Loc = 0; // its the n-terminus
mod.AA = psm.Seq[0].ToString();
mod.Mass = modInfo[Convert.ToDouble(searchHit.Element(nsp + "modification_info").Attribute("mod_nterm_mass").Value)];
psm.Mods.Add(mod);
}
if (searchHit.Element(nsp + "modification_info")?.Elements(nsp + "mod_aminoacid_mass") != null)
{
foreach (XElement aa in searchHit.Element(nsp + "modification_info").Elements(nsp + "mod_aminoacid_mass"))
{
Modification mod = new Modification();
// we convert the location to a zero-based index of the peptide
mod.Loc = Convert.ToInt32(aa.Attribute("position").Value) - 1;
mod.AA = psm.Seq[mod.Loc].ToString();
mod.Mass = modInfo[Convert.ToDouble(aa.Attribute("mass").Value)];
psm.Mods.Add(mod);
}
}
psms.Add(psm.Id, psm);
}
}
return(psms);
}
public static void ParsePSMs(this SearchMetricsContainer searchMetrics, PsmDataCollection psmCollection, WorkflowParameters parameters)
{
int numGoodPSMs, pepsWithNoMissedCleavages;
IEnumerable <int> charges;
double IdRate, chargeRatio3to2, chargeRatio4to2;
double digestionEfficiency, topDecoyScore;
double missedCleavageRate;
Dictionary <int, int> numCharges = new Dictionary <int, int>();
List <PsmData> psms;
IEnumerable <PsmData> goodPsms, nonDecoys;
int numSearched = parameters.QcParams.NumberSpectra;
// convert the dictionary to a list for easy parsing
psms = psmCollection.Values.ToList();
// get the top decoy score
topDecoyScore = (from x in psms
where x.Decoy
select x.Hyperscore)
.ToArray().Percentile(95);
// get the non-decoys
nonDecoys = from x in psms
where !x.Decoy
select x;
// and select the non-decoy hits which are above the top decoy score
goodPsms = from x in psms
where !x.Decoy & x.Hyperscore > topDecoyScore
select x;
Console.WriteLine("Total hits: {0}", psms.Count());
Console.WriteLine("Top decoy score: {0}", topDecoyScore);
Console.WriteLine("Non-decoy hits: {0}", nonDecoys.Count());
Console.WriteLine("Non-decoy hits above top decoy score: {0}", goodPsms.Count());
// parse out the charges
charges = from x in goodPsms
select x.Charge;
// get the number of each charge, add to a dictionary
foreach (int charge in new List <int>()
{
2, 3, 4
})
{
numCharges.Add(charge, (from x in charges where x == charge select 1).Count());
}
// calculate charge ratios
chargeRatio3to2 = Convert.ToDouble(numCharges[3]) / Convert.ToDouble(numCharges[2]);
chargeRatio4to2 = Convert.ToDouble(numCharges[4]) / Convert.ToDouble(numCharges[2]);
// parse out the missed cleavage data
pepsWithNoMissedCleavages = (from x in goodPsms
where x.MissedCleavages == 0
select 1).Sum();
// number of PSMs is the length of this collection
numGoodPSMs = goodPsms.Count();
// missed cleavages per PSM
digestionEfficiency = (double)pepsWithNoMissedCleavages / numGoodPSMs;
Console.WriteLine("Digestion efficiency: {0}", digestionEfficiency);
// get missed cleavage rate, i.e. number of missed cleavages per psm
missedCleavageRate = (double)(from x in goodPsms select x.MissedCleavages).Sum() / numGoodPSMs;
Console.WriteLine("Missed cleavage rate (/PSM): {0}", missedCleavageRate);
// calculate ID rate
IdRate = (double)numGoodPSMs / numSearched;
Console.WriteLine("IDrate: {0}", IdRate);
// get labeling efficiency metrics
if ((parameters.QcParams.NMod != null) | (parameters.QcParams.KMod != null) | (parameters.QcParams.XMod != null))
{
searchMetrics.GetModificationFrequency(goodPsms, parameters);
}
// get median mass drift
searchMetrics.MedianMassDrift = (from x in goodPsms
select x.MassDrift)
.ToArray().Percentile(50);
searchMetrics.SearchData.PSMsWithNoMissedCleavages = pepsWithNoMissedCleavages;
searchMetrics.SearchData.TotalNumGoodPSMs = numGoodPSMs;
searchMetrics.SearchData.NumCharge2 = numCharges[2];
searchMetrics.SearchData.NumCharge3 = numCharges[3];
searchMetrics.SearchData.NumCharge4 = numCharges[4];
searchMetrics.IdentificationRate = IdRate;
searchMetrics.MissedCleavageRate = missedCleavageRate;
searchMetrics.DigestionEfficiency = digestionEfficiency;
searchMetrics.ChargeRatio3to2 = chargeRatio3to2;
searchMetrics.ChargeRatio4to2 = chargeRatio4to2;
}
