public static HashSet <string> GetTags(string fileName, bool isProteinFile)
{
HashSet <string> result = new HashSet <string>();
using (StreamReader sr = new StreamReader(fileName))
{
if (isProteinFile)
{
sr.ReadLine();
}
var line = sr.ReadLine();
var parts = line.Split('\t');
var tagIndex = Array.IndexOf(parts, "Tag");
if (tagIndex >= 0)
{
while ((line = sr.ReadLine()) != null)
{
if (isProteinFile && IdentifiedResultUtils.IsProteinLine(line))
{
continue;
}
parts = line.Split('\t');
if (parts.Length <= tagIndex)
{
break;
}
result.Add(parts[tagIndex]);
}
}
}
return(result);
}
public override IIdentifiedResult ReadFromFile(string fileName)
{
if (!File.Exists(fileName))
{
throw new FileNotFoundException("Protein file not exist : " + fileName);
}
string peptideFilename = GetPeptideFileName(fileName);
if (!File.Exists(peptideFilename))
{
throw new FileNotFoundException("Peptide file not exist : " + peptideFilename);
}
string linkFileName = GetLinkFileName(fileName);
if (!File.Exists(linkFileName))
{
throw new FileNotFoundException("Peptide2group file not exist : " + linkFileName);
}
var pepFileReader = new PeptideTextReader(GetEngineName());
List <IIdentifiedSpectrum> spectra = pepFileReader.ReadFromFile(peptideFilename);
this.PeptideFormat = pepFileReader.PeptideFormat;
var proFileReader = new ProteinTextReader(GetEngineName());
List <IIdentifiedProtein> proteins = proFileReader.ReadFromFile(fileName);
this.ProteinFormat = proFileReader.ProteinFormat;
var peptideMap = spectra.ToDictionary(m => m.Id);
var proteinMap = proteins.GroupBy(m => m.GroupIndex);
IIdentifiedResult result = Allocate();
foreach (var pros in proteinMap)
{
var group = new IdentifiedProteinGroup();
pros.ToList().ForEach(m => group.Add(m));
result.Add(group);
}
new Peptide2GroupTextReader().LinkPeptideToGroup(linkFileName, peptideMap, result.ToDictionary(m => m.Index));
string fastaFile = fileName + ".fasta";
if (File.Exists(fastaFile))
{
IdentifiedResultUtils.FillSequenceFromFasta(fastaFile, result, null);
}
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);
}
protected override bool FillSequence(IIdentifiedResult groups)
{
if (File.Exists(fastaFilename))
{
try
{
IdentifiedResultUtils.FillSequenceFromFasta(acParser, fastaFilename, groups, Progress);
}
catch (Exception ex)
{
Progress.SetMessage("ERROR: fill sequence failed, file = {0}, error = {1}, trace = {2}", fastaFilename, ex.Message, ex.StackTrace);
return(false);
}
return(true);
}
return(false);
}
public override IIdentifiedResult ReadFromFile(string fileName)
{
if (!File.Exists(fileName))
{
throw new FileNotFoundException("File not exist : " + fileName);
}
IIdentifiedResult result = Allocate();
Dictionary <string, IIdentifiedSpectrum> peptideMap = new Dictionary <string, IIdentifiedSpectrum>();
using (StreamReader filein = new StreamReader(new FileStream(fileName, FileMode.Open, FileAccess.Read)))
{
Progress.SetRange(0, filein.BaseStream.Length);
IIdentifiedProteinGroup group;
string lastLine = filein.ReadLine();
if (lastLine == null)
{
return(result);
}
if (ProteinFormat != null)
{
ProteinFormat = new LineFormat <IIdentifiedProtein>(ProteinFormat.Factory, lastLine, GetEngineName());
}
else
{
ProteinFormat = new ProteinLineFormat(lastLine, GetEngineName());
}
lastLine = filein.ReadLine();
if (lastLine == null)
{
return(result);
}
if (PeptideFormat != null)
{
PeptideFormat = new LineFormat <IIdentifiedSpectrum>(PeptideFormat.Factory, lastLine, GetEngineName());
}
else
{
PeptideFormat = new PeptideLineFormat(lastLine, GetEngineName());
}
lastLine = null;
while ((group = ReadNextProteinGroup(filein, peptideMap, ref lastLine)) != null)
{
result.Add(group);
}
}
string fastaFile = fileName + ".fasta";
if (File.Exists(fastaFile))
{
IdentifiedResultUtils.FillSequenceFromFasta(fastaFile, result, null);
}
return(result);
}
private IIdentifiedProteinGroup ReadNextProteinGroup(StreamReader filein, Dictionary <string, IIdentifiedSpectrum> peptideMap, ref string lastLine)
{
Progress.SetPosition(filein.BaseStream.Position);
while (!IdentifiedResultUtils.IsProteinLine(lastLine) && (lastLine = filein.ReadLine()) != null)
{
}
if (lastLine == null)
{
return(null);
}
IIdentifiedProteinGroup result = new IdentifiedProteinGroup();
while (IdentifiedResultUtils.IsProteinLine(lastLine))
{
IIdentifiedProtein protein = ProteinFormat.ParseString(lastLine);
result.Add(protein);
protein.GroupIndex = IdentifiedResultUtils.GetGroupIndex(lastLine);
lastLine = filein.ReadLine();
}
List <IIdentifiedSpectrum> peptides = new List <IIdentifiedSpectrum>();
while (!IdentifiedResultUtils.IsProteinLine(lastLine))
{
if (Progress.IsCancellationPending())
{
throw new UserTerminatedException();
}
IIdentifiedSpectrum mphit = PeptideFormat.ParseString(lastLine);
string id = string.Format("{0}-{1}-{2}-{3}", mphit.Query.FileScan.LongFileName, mphit.Rank, mphit.Engine, mphit.Tag);
if (!peptideMap.ContainsKey(id))
{
peptideMap[id] = mphit;
}
else
{
mphit = peptideMap[id];
}
peptides.Add(mphit);
lastLine = filein.ReadLine();
if (lastLine == null || lastLine.Trim().Length == 0)
{
break;
}
}
foreach (IIdentifiedSpectrum hit in peptides)
{
result.AddIdentifiedSpectrum(hit);
}
return(result);
}
public void WriteFastaFile(string fastaFilename, IIdentifiedResult mr)
{
IdentifiedResultUtils.WriteFastaFile(fastaFilename, mr, ValidGroup);
}
