protected override IProcessor GetProcessor()
{
string dbFile;
if (fastaFile.Exists)
{
dbFile = fastaFile.FullName;
}
else
{
dbFile = databaseFile.FullName;
}
var options = new PNovoSAPValidatorOptions()
{
PnovoFiles = pNovoFiles.SelectedFileNames,
DatabaseFastaFile = dbFile,
TitleParser = titleParsers.SelectedItem,
AccessNumberParser = acParsers.SelectedItem,
Enzyme = ProteaseManager.GetProteaseByName(proteases.SelectedItem),
MinScore = minScore.Value,
ThreadCount = threadCount.Value,
IgnoreNtermMutation = ignoreNTerm.Checked,
IgnoreDeamidatedMutation = ignoreDeamidatedMutation.Checked,
IgnoreMultipleNucleotideMutation = ignoreMultipleNucleotideMutation.Checked,
MinLength = minLength.Value,
TargetDirectory = targetDirectory.FullName,
TargetFastaFile = databaseFile.FullName
};
return(new PNovoSAPValidator(options));
}
/// <summary>
///<Enzymes independent="false">
/// <Enzyme id="ENZ_1" cTermGain="OH" nTermGain="H" missedCleavages="1" minDistance="1" semiSpecific="false">
/// <SiteRegexp>(?<=[KR])</SiteRegexp>
/// <EnzymeName><cvParam cvRef="MS" accession="MS:1001313" name="Trypsin/P" value=""/></EnzymeName>
/// </Enzyme>
///</Enzymes>
/// </summary>
/// <param name="enzyme"></param>
/// <returns></returns>
public Protease ParseProtease(XElement enzyme)
{
var id = enzyme.Attribute("id").Value;
var name = enzyme.FindElement("EnzymeName").FindElement("cvParam").Attribute("name").Value;
if (ProteaseManager.Registered(name))
{
return(ProteaseManager.GetProteaseByName(name));
}
var siteEle = enzyme.FindElement("SiteRegexp");
if (siteEle != null)
{
string cut = string.Empty;
string notCut = string.Empty;
var sitereg = siteEle.Value;
var cutM = cutReg.Match(sitereg);
if (cutM.Success)
{
cut = cutM.Groups[1].Value;
}
var notCutM = notCutReg.Match(sitereg);
if (notCutM.Success)
{
notCut = notCutM.Groups[1].Value;
}
return(new Protease(name, true, cut, notCut)
{
Id = id
});
}
return(null);
}
public TheoreticalDigestionStatisticCalculatorUI()
{
InitializeComponent();
SetFileArgument("FastaFile", new OpenFileArgument("Protein Sequence", "fasta"));
lbProteases.Items.AddRange(ProteaseManager.GetNames().ToArray());
AddComponent(lbSelectedProteases);
this.minLength = new RcpaIntegerField(txtMinLength, "minlength", "Minimum peptide length", 6, true);
AddComponent(minLength);
this.maxMissCleavage = new RcpaIntegerField(txtMaxMissCleavage, "maxmisscleavage", "Maximum miss cleavage", 2, true);
AddComponent(maxMissCleavage);
this.minMass = new RcpaDoubleField(txtMinMass, "minmass", "Minimum peptide mass", 400, true);
AddComponent(minMass);
this.maxMass = new RcpaDoubleField(txtMaxMass, "maxmass", "Maximum peptide mass", 5000, true);
AddComponent(maxMass);
ignoreAminoacids = new RcpaTextField(txtIgnoreAminoacids, "ignoreaminoacids", "Ignore amino acids", "XB", true);
AddComponent(ignoreAminoacids);
this.Text = Constants.GetSQHTitle(title, version);
}
public ProteinChromatographViewer()
{
InitializeComponent();
ProteaseManager.Load();
proteases = new RcpaComboBox <string>(cbProtease, "ProteaseIndex", ProteaseManager.GetNames().ToArray(), 3);
AddComponent(proteases);
SetFileArgument("FastaFile", new OpenFileArgument("Fasta", "fasta"));
rawFile = new RcpaFileField(btnRawDirectory, txtRawDirectory, "RawFile", new OpenFileArgument("Thermo Raw", "raw"), true);
AddComponent(rawFile);
ppmTolerance = new RcpaDoubleField(txtPPMTolerance, "PPMTolerance", "Precursor PPM Tolerance", 10, true);
AddComponent(ppmTolerance);
rebuildAll = new RcpaCheckBox(cbRebuildAll, "RebuildAll", false);
AddComponent(rebuildAll);
noredundantFile = new RcpaFileField(btnNoredundant, txtNoredundant, "NoredundantFile", new OpenFileArgument("noredundant", "noredundant"), false);
AddComponent(noredundantFile);
//rawDirectory = new RcpaDirectoryField(btnRawDirectory, txtRawDirectory, "RawDirectory", "Thermo Fisher Raw", true);
//AddComponent(rawDirectory);
}
public PNovoSAPValidatorUI()
{
InitializeComponent();
this.Text = Constants.GetSQHTitle(title, version);
pNovoFiles.FileArgument = new OpenFileArgument("pNovo Result", "txt");
AddComponent(this.pNovoFiles);
this.minScore = new RcpaDoubleField(txtMinScore, "MinScore", "Minmum score", 0.65, true);
AddComponent(this.minScore);
this.threadCount = new RcpaIntegerField(txtThreadCount, "ThreadCount", "Thread count", Environment.ProcessorCount - 1, true);
AddComponent(this.threadCount);
toolTip1.SetToolTip(txtThreadCount, MyConvert.Format("Suggest max value = {0}", Environment.ProcessorCount + 1));
this.titleParsers = new RcpaComboBox <ITitleParser>(cbTitleFormat, "TitleFormat", TitleParserUtils.GetTitleParsers().ToArray(), -1);
AddComponent(this.titleParsers);
fastaFile.FileArgument = new OpenFileArgument("Fasta To Find Mutation", "fasta");
databaseFile.FileArgument = new OpenFileArgument("Fasta To Merge Mutated Peptide", "fasta");
this.acParsers = new RcpaComboBox <IAccessNumberParser>(cbAccessNumberPattern, "AccessNumberParser", AccessNumberParserFactory.GetParsers().ToArray(), -1);
AddComponent(this.acParsers);
this.proteases = new RcpaComboBox <string>(cbProtease, "Protease", ProteaseManager.GetNames().ToArray(), -1);
AddComponent(this.proteases);
this.minLength = new RcpaIntegerField(txtMinLength, "MinLength", "Minimum Peptide Length", 6, true);
AddComponent(this.minLength);
}
public ProteinChromatographProcessorUI()
{
InitializeComponent();
ProteaseManager.Load();
SetFileArgument("PeptideFile", new OpenFileArgument("peptides", "peptides"));
rawFile = new RcpaFileField(btnRawDirectory, txtRawDirectory, "RawFile", new OpenFileArgument("Thermo Raw", "raw"), true);
AddComponent(rawFile);
ppmTolerance = new RcpaDoubleField(txtPPMTolerance, "PPMTolerance", "Precursor PPM Tolerance", 10, true);
AddComponent(ppmTolerance);
window = new RcpaDoubleField(txtWindow, "Window", "Elution Window", 1, true);
AddComponent(window);
lvcPeptides = new ListViewColumnField(lvPeptides, "LvPeptides");
AddComponent(lvcPeptides);
rawonly = new RcpaCheckBox(cbShowInRawFileOnly, "ShowRawFileOnly", true);
AddComponent(rawonly);
bFirstLoad = true;
}
private void ParseProtease(XmlNode parameters)
{
XmlNode node = xmlHelper.GetFirstChildByNameAndAttribute(parameters, "note", "label", "protein, cleavage site");
Match m = Regex.Match(node.InnerText, @"\[(.+)\]\|\{(.+)\}");
protease = ProteaseManager.FindOrCreateProtease("XTANDEM_PROTEASE", true, m.Groups[1].Value, m.Groups[2].Value);
}
public PepXmlWriterParameters()
{
RawDataType = "raw";
Protease = ProteaseManager.GetProteaseByName("Trypsin");
SearchEngine = "unknown";
MassTypeParentAnnotation = "monoisotopic";
MassTypeFragmentAnnotation = "monoisotopic";
}
protected override IFileProcessor GetFileProcessor()
{
proteins = SequenceUtils.Read(new FastaFormat(), base.GetOriginFile());
Protease protease = ProteaseManager.GetProteaseByName(proteases.SelectedItem);
Digest digest = new Digest()
{
DigestProtease = protease,
MaxMissedCleavages = 2
};
List <SimplePeakChro> totalPeaks = new List <SimplePeakChro>();
foreach (var seq in proteins)
{
digest.ProteinSequence = seq;
digest.AddDigestFeatures();
List <DigestPeptideInfo> peptides = seq.GetDigestPeptideInfo();
peptides.RemoveAll(m => m.PeptideSeq.Length < 6);
foreach (var dpi in peptides)
{
double mass = aas.MonoPeptideMass(dpi.PeptideSeq);
List <SimplePeakChro> curPeaks = new List <SimplePeakChro>();
for (int charge = 2; charge <= 3; charge++)
{
double precursor = (mass + Atom.H.MonoMass * charge) / charge;
if (precursor < 300 || precursor > 2000)
{
continue;
}
curPeaks.Add(new SimplePeakChro()
{
Mz = precursor,
Sequence = dpi.PeptideSeq,
Charge = charge
});
}
if (curPeaks.Count > 0)
{
dpi.Annotations[CHRO_KEY] = curPeaks;
totalPeaks.AddRange(curPeaks);
}
}
peptides.RemoveAll(m => !m.Annotations.ContainsKey(CHRO_KEY));
}
return(new ProteinChromatographProcessor(totalPeaks, new string[] { rawFile.FullName }.ToList(), new RawFileImpl(), ppmTolerance.Value, 2.0, rebuildAll.Checked));
}
/// <summary>
/// Parse enzyme used in database searching
/// </summary>
/// <param name="enzyme"></param>
/// <returns></returns>
public Protease ParseProtease(XElement enzyme)
{
var enzymeIndex = enzyme.FindElement("MSEnzymes").Value;
if (OmssaConsts.EnzymeMap.ContainsKey(enzymeIndex))
{
var name = OmssaConsts.EnzymeMap[enzymeIndex];
if (ProteaseManager.Registered(name))
{
return(ProteaseManager.GetProteaseByName(name));
}
}
return(null);
}
protected override IFileProcessor GetFileProcessor()
{
var proteases = new List <Protease>();
foreach (var obj in lbSelectedProteases.Items)
{
proteases.Add(ProteaseManager.GetProteaseByName((string)obj));
}
return(new TheoreticalDigestionStatisticCalculator(
proteases,
minLength.Value,
minMass.Value,
maxMass.Value,
maxMissCleavage.Value,
ignoreAminoacids.Text));
}
public Protease ParseProtease(XElement enzyme)
{
var name = enzyme.Attribute("name").Value;
if (ProteaseManager.Registered(name))
{
return(ProteaseManager.GetProteaseByName(name));
}
var specificity = enzyme.FindFirstDescendant("specificity");
if (specificity != null)
{
var cut = specificity.Attribute("cut").Value;
var notcut = specificity.Attribute("no_cut").Value;
var sense = specificity.Attribute("sense").Value;
return(new Protease(name, sense == "C", cut, notcut));
}
return(new Protease(name, true, string.Empty, string.Empty));
}
public override IEnumerable <string> Process(string filename)
{
FastaFormat ff = new FastaFormat();
Digest digest = new Digest();
digest.DigestProtease = ProteaseManager.FindOrCreateProtease("Trypsin", true, "RK", "P");
digest.MaxMissedCleavages = 1;
NGlycanFilter filter = new NGlycanFilter();
digest.Filter = filter;
string resultFile = filename + ".nglycan";
Dictionary <string, NGlycanValue> peptideProteinMap = new Dictionary <string, NGlycanValue>();
using (StreamReader sr = new StreamReader(filename))
{
Sequence seq;
while ((seq = ff.ReadSequence(sr)) != null)
{
digest.ProteinSequence = seq;
digest.AddDigestFeatures();
if (seq.Annotation.ContainsKey(Digest.PEPTIDE_FEATURE_TYPE))
{
bool[] isGlycans = filter.IsNglycan;
List <DigestPeptideInfo> nglycanPeptides = (List <DigestPeptideInfo>)seq.Annotation[Digest.PEPTIDE_FEATURE_TYPE];
foreach (DigestPeptideInfo dpi in nglycanPeptides)
{
if (!peptideProteinMap.ContainsKey(dpi.PeptideSeq))
{
StringBuilder sb = new StringBuilder();
for (int i = 0; i < dpi.PeptideSeq.Length; i++)
{
if (isGlycans[dpi.PeptideLoc.Min - 1 + i])
{
sb.Append(1);
}
else
{
sb.Append(0);
}
}
NGlycanValue value = new NGlycanValue();
value.NGlycanSites = sb.ToString();
peptideProteinMap[dpi.PeptideSeq] = value;
}
peptideProteinMap[dpi.PeptideSeq].Proteins.Add(parser.GetValue(dpi.ProteinName));
}
}
}
}
List <string> peptides = new List <string>(peptideProteinMap.Keys);
peptides.Sort();
using (StreamWriter sw = new StreamWriter(resultFile))
{
foreach (string pep in peptides)
{
NGlycanValue value = peptideProteinMap[pep];
sw.Write(pep + "\t" + value.NGlycanSites + "\t");
bool bFirst = true;
foreach (string protein in value.Proteins)
{
if (bFirst)
{
bFirst = false;
sw.Write(protein);
}
else
{
sw.Write(" ! " + protein);
}
}
sw.WriteLine();
}
}
return(new[] { resultFile });
}
