public IdentifiedSpectrumBuilderResult Build(string parameterFile)
{
Options = new BuildSummaryOptions(parameterFile);
Options.DatasetList.RemoveDisabled();
IIdentifiedProteinBuilder proteinBuilder = new IdentifiedProteinBuilder();
IIdentifiedProteinGroupBuilder groupBuilder = new IdentifiedProteinGroupBuilder();
var fdrCalc = Options.FalseDiscoveryRate.GetFalseDiscoveryRateCalculator();
BuildResult = new DatasetList();
//从配置进行初始化
BuildResult.InitFromOptions(Options.DatasetList, this.Progress, parameterFile);
var totalCount = BuildResult.GetOptimalSpectrumCount();
string optimalResultFile = FileUtils.ChangeExtension(parameterFile, ".optimal");
using (var sw = new StreamWriter(optimalResultFile))
{
new OptimalFileTextWriter().WriteToStream(sw, BuildResult);
UniformProteinFdrOptimalResultCalculator proteinCalc = new UniformProteinFdrOptimalResultCalculator(fdrCalc, Options.GetDecoyGroupFilter())
{
Progress = this.Progress
};
Progress.SetMessage("Filtering PSMs by protein fdr {0}, using peptide fdr {1}...", Options.FalseDiscoveryRate.FdrValue, Options.FalseDiscoveryRate.MaxPeptideFdr);
var groupFilter = Options.FalseDiscoveryRate.FilterOneHitWonder ? new IdentifiedProteinGroupSingleWonderPeptideCountFilter(Options.FalseDiscoveryRate.MinOneHitWonderPeptideCount) : null;
var ret = proteinCalc.GetOptimalResultForGroupFilter(BuildResult, Options.FalseDiscoveryRate.MaxPeptideFdr, Options.FalseDiscoveryRate.FdrValue, groupFilter);
//只保留通过筛选的蛋白质包含的PSMs。
BuildResult.KeepOptimalResultInSetOnly(ret.AcceptedSpectra);
GC.Collect();
GC.WaitForPendingFinalizers();
sw.WriteLine("After SimpleProteinFDR filter {0} with condition {1}, required peptide fdr = {2} ", ret.ProteinFdr, ret.ProteinCondition, ret.PeptideFdr);
BuildResult.ForEach(ds =>
{
sw.WriteLine("Dataset {0}", ds.Options.Name);
OptimalResultConditionUtils.WriteSpectrumBin(sw, ds, f1, f2);
});
//sw.WriteLine();
//new OptimalFileTextWriter().WriteToStream(sw, BuildResult);
return(new IdentifiedSpectrumBuilderResult()
{
Spectra = ret.AcceptedSpectra.ToList(),
PeptideFDR = ret.PeptideFdr,
ProteinFDR = ret.ProteinFdr
});
}
}
public void LoadFromFile(string fileName)
{
if (!File.Exists(fileName))
{
throw new FileNotFoundException("Parameter file not found", fileName);
}
XElement docRoot = XElement.Load(fileName);
ApplicationTitle = docRoot.Element("Version").Value;
MergeResult = Convert.ToBoolean(docRoot.Element("MergeResult").Value);
ConflictType = ResolveSearchEngineConflictTypeFactory.Find(docRoot.GetChildValue("ConflictType", ResolveSearchEngineConflictTypeFactory.DiscardAll.Name));
if (docRoot.Element("MinimumEngineAgreeCount") != null)
{
MinimumEngineAgreeCount = int.Parse(docRoot.Element("MinimumEngineAgreeCount").Value);
}
if (docRoot.Element("MergeResultFromSameEngineButDifferentSearchParameters") != null)
{
KeepTopPeptideFromSameEngineButDifferentSearchParameters = bool.Parse(docRoot.Element("MergeResultFromSameEngineButDifferentSearchParameters").Value);
}
if (docRoot.Element("PeptideRetrieval") != null)
{
PeptideRetrieval = bool.Parse(docRoot.Element("PeptideRetrieval").Value);
}
Database.Load(docRoot);
FalseDiscoveryRate.Load(docRoot);
Classification.Load(docRoot);
PeptideFilter.Load(docRoot);
try
{
DatasetList.Load(docRoot);
DatasetList.ForEach(m => m.Parent = this);
}
catch (Exception ex)
{
MessageBox.Show("Load dataset error :" + ex.Message);
}
}
private void WriteScoreMap(StreamWriter sw, DatasetList BuildResult, ProteinFdrFilteredItem item)
{
if (item.ProteinCount == 0)
{
return;
}
BuildResult.BuildSpectrumBin();
BuildResult.KeepOptimalResultInSetOnly(item.AcceptedSpectra);
sw.WriteLine(MyConvert.Format("Filtering condition = {0}, PeptideFdr = {1}", item.ProteinCondition, item.PeptideFdr));
BuildResult.ForEach(ds =>
{
sw.WriteLine("Dataset {0}", ds.Options.Name);
OptimalResultConditionUtils.WriteSpectrumBin(sw, ds, f1, f2);
});
sw.WriteLine();
}
