public IEnumerable<DigestedPeptide> Digest(Protein protein)
{
Regex regex = new Regex(Regex);
int begin = 0;
int len = protein.Sequence.Length;
while (begin < len)
{
int end = begin;
int endFirst = begin;
int missed = 0;
do
{
string sequence = protein.Sequence;
Match m = regex.Match(sequence, end);
end = (m.Success ? m.Index + 1 : len);
// Save the end of the first cleavage
if (missed == 0)
endFirst = end;
// TODO(nicksh)
//// Deal with 'ragged ends', or cleavages one amino acid apart
//// i.e. KR, RR, etc. for trypsin
//if (settings.ExcludeRaggedEnds && end < len)
//{
// Match mNext = regex.Match(sequence, end);
// if (mNext.Success && mNext.Index == end)
// {
// // If there are no missed cleavages, then move the
// // begin index to the next cleavage point that is
// // not part of a run.
// if (missed == 0)
// endFirst = GetDiscontiguousCleavageIndex(regex, mNext, sequence);
// break;
// }
//}
// Single amino acid peptides have no fragment ions.
int count = end - begin;
if (count > 1 && sequence.IndexOfAny(new[] { '*', '-' }, begin, count) == -1) // Not L10N
{
DigestedPeptide peptide = new DigestedPeptide
{
Index = begin,
Sequence = sequence.Substring(begin, end - begin)
};
yield return peptide;
}
// Increment missed cleavages for next loop.
missed++;
}
while (end < len);
begin = endFirst;
}
}
internal ProteolyticPeptide(Protein protein, int oneBasedStartResidueInProtein, int oneBasedEndResidueInProtein, int missedCleavages, CleavageSpecificity cleavageSpecificityForFdrCategory, string peptideDescription = null, string baseSequence = null)
{
_protein = protein;
OneBasedStartResidueInProtein = oneBasedStartResidueInProtein;
OneBasedEndResidueInProtein = oneBasedEndResidueInProtein;
MissedCleavages = missedCleavages;
CleavageSpecificityForFdrCategory = cleavageSpecificityForFdrCategory;
PeptideDescription = peptideDescription;
_baseSequence = baseSequence;
}
public string ToInsert()
{
var weight = Weight.ToString().Replace(',', '.');
var kcal = Kcal.ToString().Replace(',', '.');
var protein = Protein.ToString().Replace(',', '.');
var fat = Fat.ToString().Replace(',', '.');
var carbs = Carbs.ToString().Replace(',', '.');
return($"('{ID}', '{Name}', '{weight}', '{kcal}', '{protein}', '{fat}', '{carbs}', '{DietType}')");
}
public FastaSequence MakeFastaSequence(Protein protein)
{
List <ProteinMetadata> alternativeProteins = new List <ProteinMetadata>();
foreach (var alternativeName in protein.AlternativeNames)
{
alternativeProteins.Add(alternativeName);
}
return(new FastaSequence(protein.ProteinMetadata.Name, protein.ProteinMetadata.Description, alternativeProteins, protein.Sequence));
}
protected override IEnumerable <Peptide> SaveFileToEnumerable(System.IO.TextReader textReader, Dictionary <string, int> columnMapping)
{
var peptides = new List <Peptide>();
string line;
while ((line = textReader.ReadLine()) != null)
{
if (string.IsNullOrWhiteSpace(line))
{
continue;
}
var columns = line.Split('\t', '\n');
var peptide = new Peptide();
if (columnMapping.ContainsKey("Peptide.Scan"))
{
peptide.Scan = Convert.ToInt32(columns[columnMapping["Peptide.Scan"]]);
}
if (columnMapping.ContainsKey("Peptide.Charge"))
{
peptide.ChargeState = Convert.ToInt32(columns[columnMapping["Peptide.Charge"]]);
}
if (columnMapping.ContainsKey("Peptide.Protein"))
{
var protein = new Protein
{
ProteinDescription = columns[columnMapping["Peptide.Protein"]]
};
peptide.ProteinList.Add(protein);
}
if (columnMapping.ContainsKey("Peptide.Sequence"))
{
peptide.Sequence = columns[columnMapping["Peptide.Sequence"]];
}
if (columnMapping.ContainsKey("Peptide.Score"))
{
peptide.Score = Convert.ToDouble(columns[columnMapping["Peptide.Score"]]);
}
if (columnMapping.ContainsKey("Peptide.ScorePRISM"))
{
peptide.Score = Convert.ToDouble(columns[columnMapping["Peptide.ScorePRISM"]]);
}
if (columnMapping.ContainsKey("Peptide.evalue"))
{
peptide.Score = Convert.ToDouble(columns[columnMapping["peptide.evalue"]]);
}
if (columnMapping.ContainsKey("Peptide.PrecursorMz"))
{
peptide.Mz = Convert.ToDouble(columns[columnMapping["Peptide.PrecursorMz"]]);
}
peptides.Add(peptide);
}
return(peptides);
}
public static void XlTestXlPosCal()
{
var prot = new Protein("MNNNKQQQQ", null);
Protease protease = new Protease("New Custom Protease", new List <Tuple <string, TerminusType> > {
new Tuple <string, TerminusType>("K", TerminusType.C)
}, new List <Tuple <string, TerminusType> >(), CleavageSpecificity.Full, null, null, null);
ProteaseDictionary.Dictionary.Add(protease.Name, protease);
DigestionParams digestionParams = new DigestionParams(protease: protease.Name, minPeptideLength: 1, initiatorMethionineBehavior: InitiatorMethionineBehavior.Retain);
List <ModificationWithMass> variableModifications = new List <ModificationWithMass>();
var ye = prot.Digest(digestionParams, new List <ModificationWithMass>(), variableModifications).ToList();
var pep = ye[0];
Assert.AreEqual(pep.BaseSequence, "MNNNK");
CrosslinkerTypeClass crosslinker = new CrosslinkerTypeClass();
crosslinker.SelectCrosslinker(CrosslinkerType.DSS);
Assert.AreEqual(crosslinker.CrosslinkerModSites, "K");
Assert.AreEqual(Residue.GetResidue(crosslinker.CrosslinkerModSites).MonoisotopicMass, 128.09496301518999, 1e-9);
var n = pep.CompactPeptide(TerminusType.None).NTerminalMasses;
var c = pep.CompactPeptide(TerminusType.None).CTerminalMasses;
Assert.AreEqual(n.Count(), 4);
Assert.AreEqual(c.Count(), 4);
Assert.AreEqual(c[0], 128.09496301518999, 1e-6);
var x = PsmCross.XlPosCal(pep.CompactPeptide(TerminusType.None), crosslinker.CrosslinkerModSites).ToArray();
Assert.AreEqual(x[0], 4);
var pep2 = ye[2];
Assert.AreEqual("MNNNKQQQQ", pep2.BaseSequence);
var n2 = pep2.CompactPeptide(TerminusType.None).NTerminalMasses;
var c2 = pep2.CompactPeptide(TerminusType.None).CTerminalMasses;
Assert.AreEqual(n2.Count(), 8);
Assert.AreEqual(c2.Count(), 8);
Assert.AreEqual(n2[4] - n2[3], 128.09496301518999, 1e-6);
var x2 = PsmCross.XlPosCal(pep2.CompactPeptide(TerminusType.None), crosslinker.CrosslinkerModSites).ToArray();
Assert.AreEqual(x2[0], 4);
//Test crosslinker with multiple types of mod
var protSTC = new Protein("GASTACK", null);
var peps = protSTC.Digest(digestionParams, new List <ModificationWithMass>(), variableModifications).ToList();
var pepSTC = peps[0];
Assert.AreEqual(pepSTC.BaseSequence, "GASTACK");
CrosslinkerTypeClass crosslinker2 = new CrosslinkerTypeClass("ST", "C", "crosslinkerSTC", false, -18.01056, 0, 0, 0, 0, 0, 0);
string crosslinkerModSitesAll = new string((crosslinker2.CrosslinkerModSites + crosslinker2.CrosslinkerModSites2).ToCharArray().Distinct().ToArray());
Assert.AreEqual(crosslinkerModSitesAll, "STC");
}
/// <summary>
/// Gets peptides for semispecific digestion of a protein
///
/// semi-specific search enters here...
/// </summary>
/// <param name="protein"></param>
/// <returns></returns>
public IEnumerable <PeptideWithSetModifications> SemiSpecificDigestion(Protein protein)
{
List <ProteolyticPeptide> intervals = new List <ProteolyticPeptide>();
List <int> oneBasedIndicesToCleaveAfter = Protease.GetDigestionSiteIndices(protein.BaseSequence);
for (int i = 0; i < oneBasedIndicesToCleaveAfter.Count - MaximumMissedCleavages - 1; i++)
{
if (Protease.Retain(i, InitiatorMethionineBehavior, protein[0]) &&
Protease.OkayLength(oneBasedIndicesToCleaveAfter[i + MaximumMissedCleavages + 1] - oneBasedIndicesToCleaveAfter[i], MinPeptidesLength, MaxPeptidesLength))
{
intervals.Add(new ProteolyticPeptide(protein, oneBasedIndicesToCleaveAfter[i] + 1, oneBasedIndicesToCleaveAfter[i + MaximumMissedCleavages + 1],
oneBasedIndicesToCleaveAfter[i + MaximumMissedCleavages + 1] - oneBasedIndicesToCleaveAfter[i], "semi"));
}
if (Protease.Cleave(i, InitiatorMethionineBehavior, protein[0]) &&
Protease.OkayLength(oneBasedIndicesToCleaveAfter[i + MaximumMissedCleavages + 1] - 1, MinPeptidesLength, MaxPeptidesLength))
{
intervals.Add(new ProteolyticPeptide(protein, 2, oneBasedIndicesToCleaveAfter[i + MaximumMissedCleavages + 1],
oneBasedIndicesToCleaveAfter[i + MaximumMissedCleavages + 1] - 1, "semi:M cleaved"));
}
}
int lastIndex = oneBasedIndicesToCleaveAfter.Count - 1;
int maxIndex = MaximumMissedCleavages < lastIndex ? MaximumMissedCleavages : lastIndex;
for (int i = 1; i <= maxIndex; i++)
{
if (DigestionParams.TerminusTypeSemiProtease == FragmentationTerminus.N) //tricky, it's N because we want the extra peptide at the C terminus |_
{
if (Protease.OkayLength(oneBasedIndicesToCleaveAfter[lastIndex] - oneBasedIndicesToCleaveAfter[lastIndex - i], MinPeptidesLength, MaxPeptidesLength))
{
intervals.Add(new ProteolyticPeptide(protein, oneBasedIndicesToCleaveAfter[lastIndex - i] + 1, oneBasedIndicesToCleaveAfter[lastIndex],
oneBasedIndicesToCleaveAfter[lastIndex] - oneBasedIndicesToCleaveAfter[lastIndex - i], "semiN"));
}
}
else //TerminusType.C
{
if (Protease.OkayLength(oneBasedIndicesToCleaveAfter[i] - oneBasedIndicesToCleaveAfter[0], MinPeptidesLength, MaxPeptidesLength))
{
intervals.Add(new ProteolyticPeptide(protein, oneBasedIndicesToCleaveAfter[0] + 1, oneBasedIndicesToCleaveAfter[i],
oneBasedIndicesToCleaveAfter[i] - oneBasedIndicesToCleaveAfter[0], "semiC"));
}
}
}
// Also digest using the proteolysis product start/end indices
intervals.AddRange(
protein.ProteolysisProducts
.Where(proteolysisProduct => proteolysisProduct.OneBasedEndPosition.HasValue && proteolysisProduct.OneBasedBeginPosition.HasValue &&
(proteolysisProduct.OneBasedBeginPosition != 1 || proteolysisProduct.OneBasedEndPosition != protein.Length))
.Select(proteolysisProduct => new ProteolyticPeptide(protein, proteolysisProduct.OneBasedBeginPosition.Value, proteolysisProduct.OneBasedEndPosition.Value,
0, proteolysisProduct.Type + " start")));
return(intervals.SelectMany(peptide => peptide.GetModifiedPeptides(AllKnownFixedModifications, DigestionParams, VariableModifications)));
}
public static void TestUniProtGptmdConflict()
{
// this unit test checks to make sure GPTMD does not annotate mods at residues on
// proteins where the equivalent uniprot mod already exists
Modification uniProtPhospho = GlobalVariables.AllModsKnown.First(p => p.ModificationType == "UniProt" && p.IdWithMotif.Contains("Phosphoserine"));
Modification mmPhospho = GlobalVariables.AllModsKnown.First(p => p.ModificationType == "Common Biological" && p.IdWithMotif.Contains("Phosphorylation on S"));
Protein protein = new Protein("PEPTIDESK", "test",
oneBasedModifications: new Dictionary <int, List <Modification> >()
{
{ 8, new List <Modification> {
uniProtPhospho
} }
});
PeptideWithSetModifications pep = protein.Digest(new DigestionParams(), new List <Modification>(), new List <Modification>()).First(p => p.AllModsOneIsNterminus.Count == 0);
// mod should not fit anywhere on the protein
for (int i = 0; i < pep.Length; i++)
{
bool modFits = GptmdEngine.ModFits(mmPhospho, protein, i + 1, pep.Length, pep.OneBasedStartResidueInProtein + i);
Assert.That(!modFits);
}
// the following code is just a control to make sure the phosphorylation actually does fit
// at the given residue if the UniProt phosphorylation is not already present
var someOtherSMod = GlobalVariables.AllModsKnown.Where(p => p.ModificationType == "Common Biological" && p.IdWithMotif.Contains("HexNAc on S")).First();
protein = new Protein("PEPTIDESK", "test",
oneBasedModifications: new Dictionary <int, List <Modification> >()
{
{ 8, new List <Modification> {
someOtherSMod
} }
});
pep = protein.Digest(new DigestionParams(), new List <Modification>(), new List <Modification>()).First(p => p.AllModsOneIsNterminus.Count == 0);
// mod should fit at position 8
for (int i = 0; i < pep.Length; i++)
{
bool modFits = GptmdEngine.ModFits(mmPhospho, protein, i + 1, pep.Length, pep.OneBasedStartResidueInProtein + i);
if (i + 1 == 8)
{
Assert.That(modFits);
}
else
{
Assert.That(!modFits);
}
}
}
public static IProteinService CreateProteinService()
{
var service = new ProteinService();
var protein = new Protein();
protein.ProjectNumber = 6600;
protein.WorkUnitName = "WorkUnitName";
protein.Core = "GROGPU2";
protein.Credit = 450;
protein.KFactor = 0;
protein.Frames = 100;
protein.NumberOfAtoms = 5000;
protein.PreferredDays = 2;
protein.MaximumDays = 3;
service.Add(protein);
protein = new Protein();
protein.ProjectNumber = 5797;
protein.WorkUnitName = "WorkUnitName2";
protein.Core = "GROGPU2";
protein.Credit = 675;
protein.KFactor = 2.3;
protein.Frames = 100;
protein.NumberOfAtoms = 7000;
protein.PreferredDays = 2;
protein.MaximumDays = 3;
service.Add(protein);
protein = new Protein();
protein.ProjectNumber = 8011;
protein.WorkUnitName = "WorkUnitName3";
protein.Core = "GRO-A4";
protein.Credit = 106.6;
protein.KFactor = 0.75;
protein.Frames = 100;
protein.NumberOfAtoms = 9000;
protein.PreferredDays = 2.13;
protein.MaximumDays = 4.62;
service.Add(protein);
protein = new Protein();
protein.ProjectNumber = 6903;
protein.WorkUnitName = "WorkUnitName4";
protein.Core = "GRO-A5";
protein.Credit = 22706;
protein.KFactor = 38.05;
protein.Frames = 100;
protein.NumberOfAtoms = 11000;
protein.PreferredDays = 5;
protein.MaximumDays = 12;
service.Add(protein);
return(service);
}
public void Calculate()
{
Protein value = _proteinService.Get(SelectedProject);
if (value == null)
{
return;
}
Protein protein = CopyProtein(value);
if (PreferredDeadlineChecked)
{
protein.PreferredDays = PreferredDeadline;
}
if (FinalDeadlineChecked)
{
protein.MaximumDays = FinalDeadline;
}
if (KFactorChecked)
{
protein.KFactor = KFactor;
}
TimeSpan frameTime = TimeSpan.FromMinutes(TpfMinutes).Add(TimeSpan.FromSeconds(TpfSeconds));
TimeSpan totalTimeByFrame = TimeSpan.FromSeconds(frameTime.TotalSeconds * protein.Frames);
TimeSpan totalTimeByUser = totalTimeByFrame;
if (TotalWuTimeEnabled)
{
totalTimeByUser = TimeSpan.FromMinutes(TotalWuTimeMinutes).Add(TimeSpan.FromSeconds(TotalWuTimeSeconds));
// user time is less than total time by frame, not permitted
if (totalTimeByUser < totalTimeByFrame)
{
totalTimeByUser = totalTimeByFrame;
}
}
var decimalPlaces = _prefs.Get <int>(Preference.DecimalPlaces);
var noBonusValues = protein.GetProductionValues(frameTime, TimeSpan.Zero);
var bonusByUserSpecifiedTimeValues = protein.GetProductionValues(frameTime, totalTimeByUser);
var bonusByFrameTimeValues = protein.GetProductionValues(frameTime, totalTimeByFrame);
CoreName = protein.Core;
SlotType = protein.Core.ToSlotType().ToString();
NumberOfAtoms = protein.NumberOfAtoms;
CompletionTime = Math.Round((TotalWuTimeEnabled ? totalTimeByUser.TotalDays : totalTimeByFrame.TotalDays), decimalPlaces);
PreferredDeadline = protein.PreferredDays;
FinalDeadline = protein.MaximumDays;
KFactor = protein.KFactor;
BonusMultiplier = Math.Round((TotalWuTimeEnabled ? bonusByUserSpecifiedTimeValues.Multiplier : bonusByFrameTimeValues.Multiplier), decimalPlaces);
BaseCredit = noBonusValues.Credit;
TotalCredit = Math.Round((TotalWuTimeEnabled ? bonusByUserSpecifiedTimeValues.Credit : bonusByFrameTimeValues.Credit), decimalPlaces);
BasePpd = noBonusValues.PPD;
TotalPpd = Math.Round((TotalWuTimeEnabled ? bonusByUserSpecifiedTimeValues.PPD : bonusByFrameTimeValues.PPD), decimalPlaces);
}
/// <summary>
/// Adds the protein to the target, and maps the target onto the protein
/// </summary>
/// <param name="p"></param>
public void AddProtein(Protein p)
{
if (!m_proteinMap.ContainsKey(p.Reference))
{
m_proteinMap.Add(p.Reference, p);
}
else
{
m_proteinMap[p.Reference] = p;
}
}
public ProteinForTreeView(Protein protein, string displayName, List <InSilicoPep> uniquePep,
List <InSilicoPep> sharedPep, List <InSilicoPep> allPep)
{
Protein = protein;
Expanded = false;
DisplayName = displayName;
UniquePeptides = uniquePep;
SharedPeptides = sharedPep;
AllPeptides = allPep;
Summary = new ObservableCollection <SummaryForTreeView>();
}
public void GetRandomItemFromCollectionTest()
{
Protein protein1 = new Protein("protein1");
Protein protein2 = new Protein("protein2");
var listOfProteins = new List <Protein> {
protein1, protein2
};
Protein protein = listOfProteins.GetRandomItem();
CollectionAssert.Contains(listOfProteins, protein);
}
//TODO: Generate all the proteolytic products as distinct proteins during XML reading and delete the ProteolysisProducts code
public static List <Protein> LoadProteinXML(string proteinDbLocation, bool generateTargets, DecoyType decoyType, IEnumerable <Modification> allKnownModifications,
bool isContaminant, IEnumerable <string> modTypesToExclude, out Dictionary <string, Modification> unknownModifications, int maxThreads = -1,
int maxHeterozygousVariants = 4, int minAlleleDepth = 1)
{
List <Modification> prespecified = GetPtmListFromProteinXml(proteinDbLocation);
allKnownModifications = allKnownModifications ?? new List <Modification>();
modTypesToExclude = modTypesToExclude ?? new List <string>();
//Dictionary<string, IList<Modification>> modsDictionary = new Dictionary<string, IList<Modification>>();
if (prespecified.Count > 0 || allKnownModifications.Count() > 0)
{
//modsDictionary = GetModificationDict(new HashSet<Modification>(prespecified.Concat(allKnownModifications)));
IdToPossibleMods = GetModificationDict(new HashSet <Modification>(prespecified.Concat(allKnownModifications)));
IdWithMotifToMod = GetModificationDictWithMotifs(new HashSet <Modification>(prespecified.Concat(allKnownModifications)));
}
List <Protein> targets = new List <Protein>();
unknownModifications = new Dictionary <string, Modification>();
using (var stream = new FileStream(proteinDbLocation, FileMode.Open, FileAccess.Read, FileShare.Read))
{
Regex substituteWhitespace = new Regex(@"\s+");
Stream uniprotXmlFileStream = proteinDbLocation.EndsWith("gz") ? // allow for .bgz and .tgz, which are (rarely) used
(Stream)(new GZipStream(stream, CompressionMode.Decompress)) :
stream;
ProteinXmlEntry block = new ProteinXmlEntry();
using (XmlReader xml = XmlReader.Create(uniprotXmlFileStream))
{
while (xml.Read())
{
if (xml.NodeType == XmlNodeType.Element)
{
block.ParseElement(xml.Name, xml);
}
if (xml.NodeType == XmlNodeType.EndElement || xml.IsEmptyElement)
{
Protein newProtein = block.ParseEndElement(xml, modTypesToExclude, unknownModifications, isContaminant, proteinDbLocation);
if (newProtein != null)
{
targets.Add(newProtein);
}
}
}
}
}
List <Protein> decoys = DecoyProteinGenerator.GenerateDecoys(targets, decoyType, maxThreads);
IEnumerable <Protein> proteinsToExpand = generateTargets ? targets.Concat(decoys) : decoys;
return(proteinsToExpand.SelectMany(p => p.GetVariantProteins(maxHeterozygousVariants, minAlleleDepth)).ToList());
}
private void GetProteinAfterDeserialization(Dictionary <string, Protein> idToProtein)
{
Protein protein = null;
if (ProteinAccession != null && !idToProtein.TryGetValue(ProteinAccession, out protein))
{
throw new MzLibUtil.MzLibException("Could not find protein accession after deserialization! " + ProteinAccession);
}
Protein = protein;
}
public override int GetHashCode()
{
unchecked
{
var hashCode = (Peptide != null ? Peptide.GetHashCode() : 0);
hashCode = (hashCode * 397) ^ (Protein != null ? Protein.GetHashCode() : 0);
hashCode = (hashCode * 397) ^ (LabelType != null ? LabelType.GetHashCode() : 0);
hashCode = (hashCode * 397) ^ MsLevel.GetHashCode();
return(hashCode);
}
}
public FoldChangeRow(Protein protein, Model.Databinding.Entities.Peptide peptide, IsotopeLabelType labelType,
int?msLevel, GroupIdentifier group, int replicateCount, FoldChangeResult foldChangeResult)
{
Protein = protein;
Peptide = peptide;
IsotopeLabelType = labelType;
MsLevel = msLevel;
ReplicateCount = replicateCount;
FoldChangeResult = foldChangeResult;
Group = group;
}
public static void XlTestXlPosCal()
{
var prot = new Protein("MNNNKQQQQ", null);
List <DigestionMotif> motifs = new List <DigestionMotif> {
new DigestionMotif("K", null, 1, null)
};
Protease protease = new Protease("New Custom Protease", CleavageSpecificity.Full, null, null, motifs);
ProteaseDictionary.Dictionary.Add(protease.Name, protease);
DigestionParams digestionParams = new DigestionParams(protease: protease.Name, minPeptideLength: 1, initiatorMethionineBehavior: InitiatorMethionineBehavior.Retain);
List <Modification> variableModifications = new List <Modification>();
var ye = prot.Digest(digestionParams, new List <Modification>(), variableModifications).ToList();
var pep = ye[0];
Assert.AreEqual(pep.BaseSequence, "MNNNK");
Crosslinker crosslinker = GlobalVariables.Crosslinkers.Where(p => p.CrosslinkerName == "DSS").First();
Assert.AreEqual(crosslinker.CrosslinkerModSites, "K");
Assert.AreEqual(Residue.GetResidue(crosslinker.CrosslinkerModSites).MonoisotopicMass, 128.09496301518999, 1e-9);
var n = pep.Fragment(DissociationType.HCD, FragmentationTerminus.N);
var c = pep.Fragment(DissociationType.HCD, FragmentationTerminus.C);
Assert.AreEqual(n.Count(), 4);
Assert.AreEqual(c.Count(), 4);
Assert.AreEqual(c.First().NeutralMass, 146.10552769899999, 1e-6);
var x = CrosslinkSpectralMatch.GetPossibleCrosslinkerModSites(crosslinker.CrosslinkerModSites.ToCharArray(), pep).ToArray();
Assert.AreEqual(x[0], 5);
var pep2 = ye[2];
Assert.AreEqual("MNNNKQQQQ", pep2.BaseSequence);
var n2 = pep2.Fragment(DissociationType.HCD, FragmentationTerminus.N);
var c2 = pep2.Fragment(DissociationType.HCD, FragmentationTerminus.C);
Assert.AreEqual(n2.Count(), 8);
Assert.AreEqual(c2.Count(), 8);
var x2 = CrosslinkSpectralMatch.GetPossibleCrosslinkerModSites(crosslinker.CrosslinkerModSites.ToCharArray(), pep2).ToArray();
Assert.AreEqual(x2[0], 5);
//Test crosslinker with multiple types of mod
var protSTC = new Protein("GASTACK", null);
var peps = protSTC.Digest(digestionParams, new List <Modification>(), variableModifications).ToList();
var pepSTC = peps[0];
Assert.AreEqual(pepSTC.BaseSequence, "GASTACK");
Crosslinker crosslinker2 = new Crosslinker("ST", "C", "crosslinkerSTC", false, -18.01056, 0, 0, 0, 0, 0, 0);
string crosslinkerModSitesAll = new string((crosslinker2.CrosslinkerModSites + crosslinker2.CrosslinkerModSites2).ToCharArray().Distinct().ToArray());
Assert.AreEqual(crosslinkerModSitesAll, "STC");
}
public static void TestNoCleavage()
{
List <Modification> fixedModifications = new List <Modification>();
var prot = new Protein("MNNNKQQQQ", null, null, null, new Dictionary <int, List <Modification> >(), new List <ProteolysisProduct> {
new ProteolysisProduct(5, 6, "lala")
});
DigestionParams digestionParams = new DigestionParams(minPeptideLength: 5);
var ye = prot.Digest(digestionParams, fixedModifications, new List <Modification>()).ToList();
Assert.AreEqual(3, ye.Count);
}
public ActionResult Create([Bind(Include = "ProteinId,Name,Price,NumberOfProductsInStock,Description,ImageURL")] Protein protein)
{
if (ModelState.IsValid)
{
db.Proteins.Add(protein);
db.SaveChanges();
return(RedirectToAction("Index"));
}
return(View(protein));
}
public void WorkUnitModel_PreferredDeadlineTest1()
{
var protein = new Protein {
ProjectNumber = 1, PreferredDays = 3
};
var workUnit = new WorkUnit {
Assigned = DateTime.UtcNow
};
var workUnitModel = CreateWorkUnitModel(protein, workUnit);
Assert.AreEqual(workUnit.Assigned.AddDays(3).ToLocalTime(), workUnitModel.PreferredDeadline);
}
private static WorkUnitModel CreateWorkUnitModel(Protein protein, WorkUnit workUnit, IProteinBenchmarkService benchmarkService = null)
{
var slotModel = new SlotModel(new NullClient(null, null, benchmarkService)
{
Settings = new ClientSettings()
});
return(new WorkUnitModel(slotModel, workUnit)
{
CurrentProtein = protein ?? new Protein()
});
}
public void WorkUnitModel_FinalDeadlineTest1()
{
var protein = new Protein {
ProjectNumber = 1, MaximumDays = 6
};
var workUnit = new WorkUnit {
Assigned = DateTime.UtcNow
};
var workUnitModel = CreateWorkUnitModel(protein, workUnit);
Assert.AreEqual(workUnit.Assigned.AddDays(6).ToLocalTime(), workUnitModel.FinalDeadline);
}
private void LoadWeekProtein()
{
var protein = MainWindow.UserNutritionRepository.GetSumsOfProtein(MainWindow.UserId, 7);
foreach (var i in protein)
{
Protein.Add(new GraphicPoint()
{
Date = i.Key.ToShortDateString(), Number = i.Value
});
}
}
public static void TestGptmdEngine(string proteinSequence, string accession, string sequenceVariantDescription, int numModifiedResidues)
{
List <PeptideSpectralMatch> allResultingIdentifications = null;
ModificationMotif.TryGetMotif("N", out ModificationMotif motifN);
var gptmdModifications = new List <Modification> {
new Modification(_originalId: "21", _modificationType: "mt", _target: motifN, _locationRestriction: "Anywhere.", _monoisotopicMass: 21.981943)
};
IEnumerable <Tuple <double, double> > combos = new List <Tuple <double, double> >();
Tolerance precursorMassTolerance = new PpmTolerance(10);
allResultingIdentifications = new List <PeptideSpectralMatch>();
var fsp = new List <(string fileName, CommonParameters fileSpecificParameters)>();
fsp.Add(("", new CommonParameters()));
var engine = new GptmdEngine(allResultingIdentifications, gptmdModifications, combos, new Dictionary <string, Tolerance> {
{ "filepath", precursorMassTolerance }
}, new CommonParameters(), fsp, new List <string>());
var res = (GptmdResults)engine.Run();
Assert.AreEqual(0, res.Mods.Count);
var parentProtein = new Protein(proteinSequence, accession, sequenceVariations: new List <SequenceVariation> {
new SequenceVariation(1, "N", "A", sequenceVariantDescription)
});
var variantProteins = parentProtein.GetVariantProteins();
CommonParameters commonParameters = new CommonParameters(digestionParams: new DigestionParams(minPeptideLength: 5));
List <Modification> variableModifications = new List <Modification>();
var modPep = variantProteins.SelectMany(p => p.Digest(commonParameters.DigestionParams, new List <Modification>(), variableModifications)).First();
//PsmParent newPsm = new TestParentSpectrumMatch(588.22520189093 + 21.981943);
Ms2ScanWithSpecificMass scan = new Ms2ScanWithSpecificMass(new MsDataScan(new MzSpectrum(new double[] { 1 }, new double[] { 1 }, false), 0, 1, true, Polarity.Positive, double.NaN, null, null, MZAnalyzerType.Orbitrap, double.NaN, null, null, "scan=1", double.NaN, null, null, double.NaN, null, DissociationType.AnyActivationType, 0, null), (new Proteomics.AminoAcidPolymer.Peptide(modPep.BaseSequence).MonoisotopicMass + 21.981943).ToMz(1), 1, "filepath", new CommonParameters());
var peptidesWithSetModifications = new List <PeptideWithSetModifications> {
modPep
};
PeptideSpectralMatch newPsm = new PeptideSpectralMatch(peptidesWithSetModifications.First(), 0, 0, 0, scan, commonParameters, new List <MatchedFragmentIon>());
Tolerance fragmentTolerance = new AbsoluteTolerance(0.01);
newPsm.SetFdrValues(1, 0, 0, 1, 0, 0, 0, 0);
allResultingIdentifications.Add(newPsm);
engine = new GptmdEngine(allResultingIdentifications, gptmdModifications, combos, new Dictionary <string, Tolerance> {
{ "filepath", precursorMassTolerance }
}, new CommonParameters(), null, new List <string>());
res = (GptmdResults)engine.Run();
Assert.AreEqual(1, res.Mods.Count);
Assert.AreEqual(numModifiedResidues, res.Mods["accession"].Count);
}
public static void TestLocalization()
{
Protein parentProteinForMatch = new Protein("MEK", null);
DigestionParams digestionParams = new DigestionParams(minPeptideLength: 1);
ModificationMotif.TryGetMotif("E", out ModificationMotif motif);
List <ModificationWithMass> variableModifications = new List <ModificationWithMass> {
new ModificationWithMass("21", null, motif, TerminusLocalization.Any, 21.981943)
};
List <PeptideWithSetModifications> allPeptidesWithSetModifications = parentProteinForMatch.Digest(digestionParams, new List <ModificationWithMass>(), variableModifications).ToList();
Assert.AreEqual(4, allPeptidesWithSetModifications.Count());
PeptideWithSetModifications ps = allPeptidesWithSetModifications.First();
List <ProductType> lp = new List <ProductType> {
ProductType.BnoB1ions, ProductType.Y
};
PeptideWithSetModifications pepWithSetModsForSpectrum = allPeptidesWithSetModifications[1];
MsDataFile myMsDataFile = new TestDataFile(new List <PeptideWithSetModifications> {
pepWithSetModsForSpectrum
});
Tolerance fragmentTolerance = new AbsoluteTolerance(0.01);
Ms2ScanWithSpecificMass scan = new Ms2ScanWithSpecificMass(myMsDataFile.GetAllScansList().Last(), pepWithSetModsForSpectrum.MonoisotopicMass.ToMz(1), 1, null);
PeptideSpectralMatch newPsm = new PeptideSpectralMatch(ps.CompactPeptide(TerminusType.None), 0, 0, 2, scan, digestionParams);
Dictionary <ModificationWithMass, ushort> modsDictionary = new Dictionary <ModificationWithMass, ushort>();
Dictionary <CompactPeptideBase, HashSet <PeptideWithSetModifications> > matching = new Dictionary <CompactPeptideBase, HashSet <PeptideWithSetModifications> >
{
{ ps.CompactPeptide(TerminusType.None), new HashSet <PeptideWithSetModifications> {
ps
} }
};
newPsm.MatchToProteinLinkedPeptides(matching);
CommonParameters commonParameters = new CommonParameters(productMassTolerance: fragmentTolerance);
LocalizationEngine f = new LocalizationEngine(new List <PeptideSpectralMatch> {
newPsm
}, lp, myMsDataFile, commonParameters, new List <string>());
f.Run();
// Was single peak!!!
Assert.AreEqual(0, newPsm.MatchedIonMassToChargeRatioDict[ProductType.BnoB1ions].Count(b => b > 0));
Assert.AreEqual(1, newPsm.MatchedIonMassToChargeRatioDict[ProductType.Y].Count(b => b > 0));
Assert.AreEqual(0, newPsm.MatchedIonIntensitiesDict[ProductType.BnoB1ions].Count(b => b > 0));
Assert.AreEqual(1, newPsm.MatchedIonIntensitiesDict[ProductType.Y].Count(b => b > 0));
// If localizing, three match!!!
Assert.IsTrue(newPsm.LocalizedScores[1] > 3 && newPsm.LocalizedScores[1] < 4);
}
public static void TestAmbiguousModFits(string proteinSequence, string motifString, bool result)
{
Protein protein = new Protein(proteinSequence, null);
int peptideOneBasedIndex = 1;
int peptideLength = 1;
int proteinOneBasedIndex = 1;
ModificationMotif.TryGetMotif(motifString, out ModificationMotif motif);
Modification attemptToLocalize = new Modification(_target: motif, _locationRestriction: "Anywhere.", _monoisotopicMass: double.NaN);
Assert.AreEqual(result, ModificationLocalization.ModFits(attemptToLocalize, protein.BaseSequence, peptideOneBasedIndex, peptideLength, proteinOneBasedIndex));
}
public static void TestVeryCloseExperimentalsModern()
{
IDictionary <int, List <Modification> > mods = new Dictionary <int, List <Modification> >();
ModificationMotif.TryGetMotif("M", out ModificationMotif motif);
var prot = new Protein("MMMM", null, null, null, mods);
DigestionParams digestionParams = new DigestionParams
{
MinPeptideLength = 1,
};
var thePep = prot.Digest(digestionParams, new List <ModificationWithMass>(), new List <ModificationWithMass>()).First();
var massArray = thePep.CompactPeptide(TerminusType.None).ProductMassesMightHaveDuplicatesAndNaNs(new List <ProductType> {
ProductType.B, ProductType.Y
});
Array.Sort(massArray);
double[] intensities = new double[] { 1, 1, 1, 1 };
double[] mz = new double[] { 1, 2, massArray[4].ToMz(1), massArray[4].ToMz(1) + 1e-9 };
MzmlMzSpectrum massSpectrum = new MzmlMzSpectrum(mz, intensities, false);
IMsDataScanWithPrecursor <IMzSpectrum <IMzPeak> > scan = new MzmlScanWithPrecursor(1, massSpectrum, 1, true, Polarity.Positive, 1, new MzRange(300, 2000), "", MZAnalyzerType.Unknown, massSpectrum.SumOfAllY, 0, null, null, 0, null, DissociationType.Unknown, 1, null, null, "scan=1");
PeptideSpectralMatch[] globalPsms = new PeptideSpectralMatch[1];
Ms2ScanWithSpecificMass[] arrayOfSortedMS2Scans = { new Ms2ScanWithSpecificMass(scan, 600, 1, null) };
CommonParameters CommonParameters = new CommonParameters
{
ProductMassTolerance = new PpmTolerance(5),
DigestionParams = new DigestionParams
{
MaxMissedCleavages = 0,
MinPeptideLength = null,
MaxModificationIsoforms = int.MaxValue,
InitiatorMethionineBehavior = InitiatorMethionineBehavior.Retain,
},
ConserveMemory = false,
ScoreCutoff = 1
};
var indexEngine = new IndexingEngine(new List <Protein> {
prot
}, new List <ModificationWithMass>(), new List <ModificationWithMass>(), new List <ProductType> {
ProductType.B, ProductType.Y
}, 1, DecoyType.Reverse, new List <IDigestionParams> {
CommonParameters.DigestionParams
}, CommonParameters, 30000, new List <string>());
var indexResults = (IndexingResults)indexEngine.Run();
var cse = new ModernSearchEngine(globalPsms, arrayOfSortedMS2Scans, indexResults.PeptideIndex, indexResults.FragmentIndex, new List <ProductType> {
ProductType.B, ProductType.Y
}, 0, CommonParameters, false, new OpenSearchMode(), 0, new List <string>());
cse.Run();
Assert.Less(globalPsms[0].Score, 2);
Assert.Greater(globalPsms[0].Score, 1);
}
private void SeedProductsIDs()
{
for (int i = 0; i < LoopIterations; i++)
{
var product = new Protein();
product.Id = i == 0 ? ProductId : ProductId + i;
this.context.Products.Add(product);
}
this.context.SaveChanges();
}
private readonly string ProteinAccession; // used to get protein object after deserialization
/// <summary>
/// Creates a PeptideWithSetModifications object from a protein. Used when a Protein is digested.
/// </summary>
public PeptideWithSetModifications(Protein protein, DigestionParams digestionParams, int oneBasedStartResidueInProtein,
int oneBasedEndResidueInProtein, string peptideDescription, int missedCleavages,
Dictionary <int, Modification> allModsOneIsNterminus, int numFixedMods)
: base(protein, oneBasedStartResidueInProtein, oneBasedEndResidueInProtein, missedCleavages, peptideDescription)
{
_allModsOneIsNterminus = allModsOneIsNterminus;
NumFixedMods = numFixedMods;
_digestionParams = digestionParams;
DetermineFullSequence();
ProteinAccession = protein.Accession;
DigestionParamString = digestionParams.ToString();
}
private readonly string ProteinAccession; // used to get protein object after deserialization
/// <summary>
/// Creates a PeptideWithSetModifications object from a protein. Used when a Protein is digested.
/// </summary>
public PeptideWithSetModifications(Protein protein, DigestionParams digestionParams, int oneBasedStartResidueInProtein,
int oneBasedEndResidueInProtein, CleavageSpecificity cleavageSpecificity, string peptideDescription, int missedCleavages,
Dictionary <int, Modification> allModsOneIsNterminus, int numFixedMods, string baseSequence = null)
: base(protein, oneBasedStartResidueInProtein, oneBasedEndResidueInProtein, missedCleavages, cleavageSpecificity, peptideDescription, baseSequence)
{
_allModsOneIsNterminus = allModsOneIsNterminus;
NumFixedMods = numFixedMods;
_digestionParams = digestionParams;
DetermineFullSequence();
ProteinAccession = protein.Accession;
UpdateCleavageSpecificity();
}
public static InteractionSet BuildInteractionSet(IEnumerable<Part> parts)
{
InteractionSet set = new InteractionSet();
foreach (PartList.Part part in parts)
{
Protein protein = new Protein();
protein.stringExternalID = part.stringID;
protein.sequence = part;
protein.name = part.data.ShortDesc;
protein.attributes["length"] = part.data.Sequence.Length.ToString();
protein.attributes["biobrick"] = part.data.Name;
protein.attributes["url"] = BiobrickCache.PartRegistryLink(part.data.Name);
set.startProteins.Add(protein);
set.proteins[part.stringID] = protein;
}
return set;
}
public Peptide(Protein parent, int startResidueNumber, int endResidueNumber, int missedCleavages)
: base(parent.BaseSequence.Substring(startResidueNumber - 1, endResidueNumber - startResidueNumber + 1))
{
Parent = parent;
StartResidueNumber = startResidueNumber;
EndResidueNumber = endResidueNumber;
MissedCleavages = missedCleavages;
if(startResidueNumber - 1 - 1 >= 0)
{
PreviousAminoAcid = parent[startResidueNumber - 1 - 1];
}
else
{
PreviousAminoAcid = '-';
}
if(endResidueNumber - 1 + 1 < parent.Length)
{
NextAminoAcid = parent[endResidueNumber - 1 + 1];
}
else
{
NextAminoAcid = '-';
}
if(parent.KnownModifications != null && parent.KnownModifications.Count > 0)
{
for(int i = 0; i < endResidueNumber - startResidueNumber + 1; i++)
{
List<Modification> modifications;
if(parent.KnownModifications.TryGetValue(startResidueNumber - 1 + i + 2, out modifications))
{
if(KnownModifications == null)
{
KnownModifications = new Dictionary<int, List<Modification>>();
}
KnownModifications.Add(i + 2, modifications);
}
}
}
}
// public Peptide(Protein parent, int startResidueNumber, int endResidueNumber, int missedCleavages)
// : base(parent.BaseSequence.Substring(startResidueNumber - 1, endResidueNumber - startResidueNumber + 1), true)
// {
// Parent = parent;
// StartResidueNumber = startResidueNumber;
// EndResidueNumber = endResidueNumber;
// MissedCleavages = missedCleavages;
// if(startResidueNumber - 1 - 1 >= 0)
// {
// PreviousAminoAcid = parent[startResidueNumber - 1 - 1];
// }
// else
// {
// PreviousAminoAcid = '-';
// }
// if(endResidueNumber - 1 + 1 < parent.Length)
// {
// NextAminoAcid = parent[endResidueNumber - 1 + 1];
// }
// else
// {
// NextAminoAcid = '-';
// }
// }
// private Peptide(Peptide peptide) : this(peptide.Parent, peptide.StartResidueNumber, peptide.EndResidueNumber, peptide.MissedCleavages) { }
public void Init(Protein parent, int startResidueNumber, int endResidueNumber, int missedCleavages)
{
BaseInit(new FastSubstring(parent.BaseSequence, startResidueNumber - 1, endResidueNumber - startResidueNumber + 1));
Parent = parent;
StartResidueNumber = startResidueNumber;
EndResidueNumber = endResidueNumber;
MissedCleavages = missedCleavages;
if(startResidueNumber - 1 - 1 >= 0)
{
PreviousAminoAcid = parent[startResidueNumber - 1 - 1];
}
else
{
PreviousAminoAcid = '-';
}
if(endResidueNumber - 1 + 1 < parent.Length)
{
NextAminoAcid = parent[endResidueNumber - 1 + 1];
}
else
{
NextAminoAcid = '-';
}
}
public void AddNewProtein(Protein _in)
{
allSelectableTargets.Add(_in.gameObject);
// selectedTargets.Add(_in.gameObject);
CheckSelectedUnits();
}
private static IEnumerable<Protein> ReadUniProtXmlProteins(FileStream uniProtXmlProteomeDatabase, bool onTheFlyDecoys, IDictionary<string, Modification> knownVariableModifications)
{
XmlReader xml = XmlReader.Create(uniProtXmlProteomeDatabase);
string[] nodes = new string[6];
string dataset = null;
string accession = null;
string name = null;
string full_name = null;
bool fragment = false;
string organism = null;
string gene_name = null;
string protein_existence = null;
string sequence_version = null;
string sequence = null;
string feature_type = null;
string feature_description = null;
int feature_position = -1;
Dictionary<int, List<Modification>> modifications = new Dictionary<int, List<Modification>>();
while(xml.Read())
{
switch(xml.NodeType)
{
case XmlNodeType.Element:
nodes[xml.Depth] = xml.Name;
switch(xml.Name)
{
case "entry":
dataset = xml.GetAttribute("dataset");
break;
case "accession":
if(accession == null)
{
accession = xml.ReadElementString();
}
break;
case "name":
if(xml.Depth == 2)
{
name = xml.ReadElementString();
}
else if(nodes[2] == "gene")
{
if(gene_name == null)
{
gene_name = xml.ReadElementString();
}
}
else if(nodes[2] == "organism")
{
if(organism == null)
{
organism = xml.ReadElementString();
}
}
break;
case "fullName":
if(full_name == null)
{
full_name = xml.ReadElementString();
}
break;
case "proteinExistence":
protein_existence = xml.GetAttribute("type");
break;
case "feature":
feature_type = xml.GetAttribute("type");
feature_description = xml.GetAttribute("description");
break;
case "position":
feature_position = int.Parse(xml.GetAttribute("position")) - 1;
break;
case "sequence":
fragment = xml.GetAttribute("fragment") != null;
sequence_version = xml.GetAttribute("version");
sequence = xml.ReadElementString().Replace("\n", null);
break;
}
break;
case XmlNodeType.EndElement:
switch(xml.Name)
{
case "feature":
if(feature_type == "modified residue" && knownVariableModifications != null && !feature_description.Contains("variant"))
{
List<Modification> residue_modifications;
if(!modifications.TryGetValue(feature_position + 2, out residue_modifications))
{
residue_modifications = new List<Modification>();
modifications.Add(feature_position + 2, residue_modifications);
}
int semicolon_index = feature_description.IndexOf(';');
if(semicolon_index >= 0)
{
feature_description = feature_description.Substring(0, semicolon_index);
}
Modification modification;
if(knownVariableModifications.TryGetValue("UniProt: " + feature_description, out modification))
{
residue_modifications.Add(modification);
}
}
break;
case "entry":
string dataset_abbreviation = dataset.Equals("Swiss-Prot", StringComparison.InvariantCultureIgnoreCase) ? "sp" : "tr";
string protein_existence_code = proteinExistenceCodes[protein_existence];
string description = dataset_abbreviation + '|' + accession + '|' + name + ' ' + full_name + (fragment ? " (Fragment)" : null) + " OS=" + organism + (gene_name != null ? " GN=" + gene_name : null) + " PE=" + protein_existence_code + " SV=" + sequence_version;
Protein protein;
if(modifications.Count > 0)
{
protein = new Protein(sequence, description, modifications);
}
else
{
protein = new Protein(sequence, description);
}
yield return protein;
if(onTheFlyDecoys)
{
if(protein.Decoy)
{
throw new ArgumentException(uniProtXmlProteomeDatabase.Name + " contains decoy proteins; database should not contain decoy proteins when \"create target–decoy database on the fly\" option is enabled");
}
char[] sequence_array = sequence.ToCharArray();
Dictionary<int, List<Modification>> decoy_modifications = null;
if(sequence.StartsWith("M"))
{
Array.Reverse(sequence_array, 1, sequence.Length - 1);
if(modifications != null)
{
decoy_modifications = new Dictionary<int, List<Modification>>(modifications.Count);
foreach(KeyValuePair<int, List<Modification>> kvp in modifications)
{
if(kvp.Key == 2)
{
decoy_modifications.Add(2, kvp.Value);
}
else if(kvp.Key > 2)
{
decoy_modifications.Add(sequence.Length - (kvp.Key - 2) - 1 + 1 + 2, kvp.Value);
}
}
}
}
else
{
Array.Reverse(sequence_array);
if(modifications != null)
{
decoy_modifications = new Dictionary<int, List<Modification>>(modifications.Count);
foreach(KeyValuePair<int, List<Modification>> kvp in modifications)
{
decoy_modifications.Add(sequence.Length - (kvp.Key - 2) - 1 + 2, kvp.Value);
}
}
}
string reversed_sequence = new string(sequence_array);
Protein decoy_protein = new Protein(reversed_sequence, description[2] == '|' ? description.Insert(3, Protein.DECOY_IDENTIFIER) : Protein.DECOY_IDENTIFIER + description, decoy_modifications);
yield return decoy_protein;
}
dataset = null;
accession = null;
name = null;
full_name = null;
fragment = false;
organism = null;
gene_name = null;
protein_existence = null;
sequence_version = null;
sequence = null;
feature_type = null;
feature_description = null;
feature_position = -1;
modifications = new Dictionary<int, List<Modification>>();
break;
}
break;
}
}
uniProtXmlProteomeDatabase.Seek(0, SeekOrigin.Begin);
}
private static IEnumerable<Protein> ReadFastaProteins(FileStream fastaProteomeDatabase, bool onTheFlyDecoys)
{
StreamReader fasta = new StreamReader(fastaProteomeDatabase);
string description = null;
string sequence = null;
while(true)
{
string line = fasta.ReadLine();
if(line.StartsWith(">"))
{
description = line.Substring(1);
}
else
{
sequence += line.Trim();
}
if(fasta.Peek() == '>' || fasta.Peek() == -1)
{
Protein protein = new Protein(sequence, description);
yield return protein;
if(onTheFlyDecoys)
{
if(protein.Decoy)
{
throw new ArgumentException(fastaProteomeDatabase.Name + " contains decoy proteins; database should not contain decoy proteins when \"create target–decoy database on the fly\" option is enabled");
}
char[] sequence_array = sequence.ToCharArray();
if(sequence.StartsWith("M"))
{
Array.Reverse(sequence_array, 1, sequence.Length - 1);
}
else
{
Array.Reverse(sequence_array);
}
string reversed_sequence = new string(sequence_array);
Protein decoy_protein = new Protein(reversed_sequence, description[2] == '|' ? description.Insert(3, Protein.DECOY_IDENTIFIER) : Protein.DECOY_IDENTIFIER + description);
yield return decoy_protein;
}
description = null;
sequence = null;
if(fasta.Peek() == -1)
{
break;
}
}
}
fastaProteomeDatabase.Seek(0, SeekOrigin.Begin);
}
public MassTagDatabase LoadDatabase()
{
var database = new MassTagDatabase();
//Implement the loading / reading of the MTDB Framework objects.
var reader = new SqLiteTargetDatabaseReader();
var mtdbDatabase = reader.ReadDb(m_path);
var massTags = new List<MassTagLight>();
// Mapping objects to create unique proteins and for the mass tag database to load only those proteins for
// the given consensus targets/mass tags.
var proteinMap = new Dictionary<int, Protein>();
var massTagProteinMap = new Dictionary<int, List<Protein>>();
if (mtdbDatabase == null)
return database;
foreach (var target in mtdbDatabase.ConsensusTargets)
{
// Copy the consensus data into a mass tag light.
var tag = new MassTagLight
{
Id = target.Id,
MassMonoisotopic = target.TheoreticalMonoIsotopicMass,
NetAverage = target.AverageNet,
NetPredicted = target.PredictedNet,
PeptideSequence = target.Sequence,
NetStandardDeviation = target.StdevNet
};
// Here we create unique proteins for the mass tag copying information from the consensus target proteins.
var proteinsForMassTag = new List<Protein>();
foreach (var targetProtein in target.Proteins)
{
if (!proteinMap.ContainsKey(targetProtein.Id))
{
var newProtein = new Protein
{
Id = targetProtein.Id,
Name = targetProtein.ProteinName,
ResidueStartPosition = targetProtein.ResidueStart,
ResidueEndPosition = targetProtein.ResidueEnd
};
//TODO: Do something about the cleavage state and terminus state of a protein loaded from MTDBCreator database.
//protein.CleavageState = ??
//protein.TerminusState = ??
proteinMap.Add(newProtein.Id, newProtein);
}
var protein = proteinMap[targetProtein.Id];
proteinsForMassTag.Add(protein);
}
massTagProteinMap.Add(tag.Id, proteinsForMassTag);
massTags.Add(tag);
}
database.AddMassTagsAndProteins(massTags, massTagProteinMap);
return database;
}
public IEnumerable<DigestedPeptide> Digest(Protein protein)
{
if (string.IsNullOrEmpty(protein.Sequence))
{
yield break;
}
FastaSequence fastaSequence;
try
{
fastaSequence = new FastaSequence("name", "description", new List<ProteinMetadata>(), protein.Sequence); // Not L10N
}
catch (InvalidDataException)
{
// It's possible that the peptide sequence in the fasta file was bogus, in which case we just don't digest it.
yield break;
}
DigestSettings digestSettings = new DigestSettings(6, false);
foreach (var digest in _enzyme.Digest(fastaSequence, digestSettings))
{
var digestedPeptide = new DigestedPeptide
{
Index = digest.Begin ?? 0,
Sequence = digest.Sequence
};
yield return digestedPeptide;
}
}
static void Main( )
{
// Read proteins in FASTA format from the file.
using( StreamReader sr = new StreamReader( fastaFile ) )
{
string id = null;
string name = null;
string line = sr.ReadLine();
//while line not null
while( line != null)
{
//set header to null
string header = null;
//while header null and line not null
while ((line != null) && (header == null))
{
// if empty line, skip it (i.e., read next line)
if (string.IsNullOrWhiteSpace(line)== true)
{
line = sr.ReadLine();
}
// else if header line, set header, read next line
else if (line.StartsWith(">"))
{
header = line;
//split the header into the id and the chemical name
id = header.Substring(1,10);
name = header.Substring(12);
line = sr.ReadLine();
}
// else throw an exception (expected a header line)
else
{
throw new Exception("expected a header line");
}
}
//set sequence to null, not complete
bool IsComplete = false;
string sequence = null;
// it's in a infinite loop right nowwwww
//while sequence not complete and line not null
while( (!IsComplete) && (line != null) )
{
//| if empty line, skip it (i.e., read next line)
if (string.IsNullOrWhiteSpace(line))
{
line = sr.ReadLine();
}
//else if not header line, concatenate to sequence, read next line
else if(!line.StartsWith(">"))
{
sequence = sequence + line.Trim();
line = sr.ReadLine();
}
//else (is header line) if sequence not null, sequence is complete
else if (sequence != null)
{
// if(sequence != null)
// {
IsComplete = true;
// }
}
//| else throw an exception (expected a sequence line)
else
{
throw new Exception
(" Expected sequence line");
}
}
//if header not null
if (header != null)
{
//| if sequence not null
if(sequence != null)
{
//| | add protein to collection
// This is how to create a new object
Protein p = new Protein( id, name, sequence);
proteins.Add(p);
}
//| else throw an exception (header with missing sequence)
else
{
throw new Exception ("Header with missing sequence");
}
}
}
// Report count of proteins loaded.
Console.WriteLine( );
Console.WriteLine( "Loaded {0} proteins from the {1} file.",
proteins.Count, fastaFile );
// Report proteins containing a specified sequence.
Console.WriteLine( );
Console.WriteLine( "Proteins containing sequence RILED:" );
foreach( Protein p in proteins )
{
if( p.ContainsSubsequence( "RILED" ) )
{
Console.WriteLine( p.Name );
}
}
// Report proteins containing a repeated sequence.
Console.WriteLine( );
Console.WriteLine(
"Proteins containing sequence SNL more than 5 times:" );
foreach( Protein p in proteins )
{
if( p.CountSubsequence( "SNL" ) > 5 )
{
Console.WriteLine( p.Name );
}
}
// Locate the specified sequence in proteins containing it.
Console.WriteLine( );
Console.WriteLine( "Proteins containing sequence DEVGG:" );
foreach( Protein p in proteins )
{
if( p.ContainsSubsequence( "DEVGG" ) )
{
Console.WriteLine( p.Name );
Console.WriteLine( p.LocateSubsequence( "DEVGG" ) );
}
}
// Show FASTA output for proteins containing a specified sequence.
Console.WriteLine( );
Console.WriteLine( "Proteins containing sequence DEVGG:" );
foreach( Protein p in proteins )
{
if( p.ContainsSubsequence( "DEVGG" ) )
{
p.WriteFasta( Console.Out );
}
}
}// done using file
}
public ProteinInfo(Protein protein)
{
ProteinMetadata = protein.ProteinMetadata;
Sequence = protein.Sequence;
Alternatives = ImmutableList.ValueOf(protein.AlternativeNames);
}
public void Add (Protein pro)
{
insertRow(Table.Protein, new object[] {pro.Id, pro.Accession, pro.Length});
insertRow(Table.ProteinMetadata, new object[] {pro.Id, pro.Description});
insertRow(Table.ProteinData, new object[] {pro.Id, pro.Sequence});
long length = pro.Sequence != null ? pro.Sequence.Length : 0;
for (long i = currentMaxSequenceLength + 1; i <= length; ++i)
insertRow(Table.IntegerSet, new object[] {i});
currentMaxSequenceLength = Math.Max(length, currentMaxSequenceLength);
}
private void button2_Click(object sender, EventArgs e)
{
readAll3Ngrams();
StreamReader srNgram = new StreamReader("3grams1.csv");
Stream myStream = null;
//OpenFileDialog theDialog = new OpenFileDialog();
//theDialog.Title = "Open Text File";
//theDialog.Filter = "Text Files (.txt)|*.txt|All Files (*.*)|*.*";
//theDialog.FilterIndex = 1;
//// theDialog.Filter = "TXT files|*.txt";
//theDialog.InitialDirectory = @"C:\";
string folderSource = textBox1.Text;
string[] fileNames = Directory.GetFiles(folderSource, "*.*", SearchOption.AllDirectories);
SortedDictionary<Protein, string> protHash = new SortedDictionary<Protein, string>();
StreamWriter sw = new StreamWriter("Protein_SVM_3Gm_Oct_5th.csv");
/*string ngramLine = "";
while ((ngramLine = srNgram.ReadLine()) != null)
{
sw.Write(ngramLine + ",");
}
srNgram.Close();
sw.WriteLine(); */
int size = -1;
// DialogResult result = theDialog.ShowDialog(); // Show the dialog.
// if (result == DialogResult.OK) // Test result.
//StreamWriter swn = new StreamWriter("bbb.csv");
foreach (string file in fileNames)
{
// string file = theDialog.FileName;
string text = null;
int nGramSize = 3;
//try
//{
// text = File.ReadAllText(file);
//}
//catch (IOException)
//{
//}
string protein = "";
string line1;
// sw.WriteLine("Protein_SVM" + "," + "Current subject file is " + file);
FileStream fs = new FileStream(file, FileMode.Open, FileAccess.Read);
BufferedStream bs = new BufferedStream(fs);
StreamReader sr = new StreamReader(fs);
bool startProtFlag = false;
string proteinString = "";
int occurence = 0;
int counter = 0;
string protNameFinal = "";
string proteinFinal = "";
string ngramLine1 = "";
string lastName = "";
string className = "";
string lastclassName = "";
while (!sr.EndOfStream)// (line1 = sr.ReadLine()) != null)
{
line1 = sr.ReadLine();
counter++;
lastclassName = className;
if (line1.Contains(">") && line1.Length < 15)
{
className = "";
if(line1.EndsWith(" C")){
className = "C";
}
else if(line1.EndsWith(" P")){
className = "P";
}
else if(line1.EndsWith(" N")){
className = "N";
}
else if(line1.EndsWith(" M")){
className = "M";
}
else {
className = "X";
}
// swn.WriteLine(line1);
lastName = file+","+protNameFinal;
startProtFlag = true;
// protein = line1.Substring(1, line1.IndexOf('|') - 1);
line1 = line1.Remove(0, 1);
protein = line1;
protNameFinal = protein;
proteinFinal = proteinString;
proteinString = "";
occurence = 0;
if (counter > 2)
{
goto Analyse;
}
else
{
continue;
}
}
else
{
proteinString += line1;
continue;
}
Analyse:
Protein p1 = new Protein(lastclassName, lastName);
// protNameFinal=file+protNameFinal;
if (protHash.ContainsKey(p1) == false)
{
protHash.Add(p1, proteinFinal);
lastName = lastclassName+ file + protNameFinal;
}
/* occurence = 0;
*
StreamReader srNgram1 = new StreamReader("Ngrams.csv");
sw.Write(protNameFinal);
while ((ngramLine1 = srNgram1.ReadLine()) != null)
{
// string SearchText = "7,true,NA,false:67,false,NA,false:5,false,NA,false:5,false,NA,false";
// string Regex = @"\btrue\b";
int NumberOfTrues = Regex.Matches(proteinFinal, ngramLine1).Count;
sw.Write(NumberOfTrues + ",");
//if (proteinFinal.Contains(ngramLine1))
//{
// occurence++;
//}
// continue;
}
srNgram1.Close();
sw.WriteLine(); */
continue;
// sw.WriteLine(protNameFinal + "," + occurence);
}
Protein p2 = new Protein(lastclassName, lastName);
if (protHash.ContainsKey(p2) == false)
{
protHash.Add(p2, proteinFinal);
}
}
//swn.Close();
sw.Write("3gram_Protein" + ",");
//StreamWriter sw9 = new StreamWriter("izz.csv");
//foreach (KeyValuePair<string,string> de in protHash)
//{
// sw9.WriteLine(de.Key.ToString() + ",");
//}
//sw9.Close();
foreach (KeyValuePair<string, int> kvp in nGramHash)
{
//if (!test11.Contains(kvp.Key.ToString()))
//{
sw.Write(kvp.Key +",");
// }
// test11 += kvp.Key;
}
sw.Write("Class");
sw.WriteLine();
string ngramLine = "";
foreach (KeyValuePair<Protein,string> de in protHash)
{
srNgram = new StreamReader("3grams1.csv");
Protein p = (Protein)de.Key;
sw.Write(p.PClass + ","+p.PName+",");
while ((ngramLine = srNgram.ReadLine()) != null)
{
int NumberOfTrues = Regex.Matches(de.Value.ToString(), ngramLine).Count;
sw.Write(NumberOfTrues + ",");
}
// srNgram.Close();
// sw.Write(de.Key.ToString() + ",");
sw.Write(de.Key.ToString());
sw.WriteLine();
}
sw.Close();
MessageBox.Show("Done");
}
public ProteinViewModel(Protein p)
{
m_protein = p;
}
private List<Protein> CompileResults(List<LocalizedHit> hits, string csvFile, string outputDirectory, bool breakProteinsApart = false)
{
Dictionary<string, LocalizedHit> hitsdict = new Dictionary<string, LocalizedHit>();
// Group all the localized Hits into proteins
Dictionary<string, Protein> proteins = new Dictionary<string, Protein>();
foreach (LocalizedHit hit in hits)
{
hitsdict.Add(hit.PSM.Filename, hit);
string defline = hit.PSM.Defline;
if (breakProteinsApart)
{
string[] groups = hit.PSM.ProteinGroup.Split('|');
foreach (string group in groups)
{
Protein prot;
if (!proteins.TryGetValue(group, out prot))
{
prot = new Protein(group, defline);
proteins.Add(group, prot);
}
prot.AddHit(hit);
}
}
else
{
Protein prot;
if (!proteins.TryGetValue(hit.PSM.ProteinGroup, out prot))
{
prot = new Protein(hit.PSM.ProteinGroup, defline);
proteins.Add(hit.PSM.ProteinGroup, prot);
}
prot.AddHit(hit);
}
}
using (StreamWriter writer = new StreamWriter(Path.Combine(outputDirectory, Path.GetFileNameWithoutExtension(csvFile) + "_all.csv")),
localizedWriter = new StreamWriter(Path.Combine(outputDirectory, Path.GetFileNameWithoutExtension(csvFile) + "_localized.csv")))
{
using (CsvReader reader = new CsvReader(new StreamReader(csvFile), true))
{
LocalizedHit hit = null;
headerInfo = reader.GetFieldHeaders();
bool tqFound = false;
for (int i = 0; i < reader.FieldCount; i++)
{
if (headerInfo[i].EndsWith("NL)"))
{
if (!tqFound)
{
FirstQuantColumn = i;
tqFound = true;
}
}
if(headerInfo[i] == "Channels Detected")
LastQuantColumn = i-1;
}
string header = string.Join(",", headerInfo) + ",# Isoforms,# of Considered Fragments,Localized?,Delta Score,Best Isoform,Spectral Matches,% TIC,Second Best Isoform,Second Spectral Matches,Second % TIC";
writer.WriteLine(header);
localizedWriter.WriteLine(header);
while (reader.ReadNextRecord())
{
string mods = reader["Mods"];
if (string.IsNullOrEmpty(mods))
continue;
List<Modification> variableMods = OmssaModification.ParseModificationLine(mods).Select(item => item.Item1).OfType<Modification>().ToList();
// Only keep things with quantified Modifications
if (!variableMods.Any(mod => QuantifiedModifications.Contains(mod)))
continue;
string filename = reader["Filename/id"];
if(!hitsdict.TryGetValue(filename, out hit))
continue;
string[] data = new string[reader.FieldCount];
reader.CopyCurrentRecordTo(data);
hit.omssapsm = data;
StringBuilder sb = new StringBuilder();
foreach (string datum in data)
{
if (datum.Contains(','))
{
sb.Append("\"");
sb.Append(datum);
sb.Append("\"");
}
else
sb.Append(datum);
sb.Append(',');
}
sb.Append(hit.PSM.Isoforms);
sb.Append(',');
sb.Append(hit.LocalizedIsoform.Fragments.Count);
sb.Append(',');
sb.Append(hit.IsLocalized);
sb.Append(',');
sb.Append(hit.MatchDifference);
sb.Append(',');
sb.Append(hit.LocalizedIsoform.SequenceWithModifications);
sb.Append(',');
sb.Append(hit.LocalizedIsoform.SpectralMatch.Matches);
sb.Append(',');
sb.Append(hit.LocalizedIsoform.SpectralMatch.PercentTIC);
if (hit.PSM.Isoforms > 1)
{
//sb.Append(',');
//sb.Append(hit.BestPeptideSDFCount);
sb.Append(',');
sb.Append(hit.SecondBestPeptideIsoform.SequenceWithModifications);
sb.Append(',');
sb.Append(hit.SecondBestPeptideIsoform.SpectralMatch.Matches);
sb.Append(',');
sb.Append(hit.SecondBestPeptideIsoform.SpectralMatch.PercentTIC);
//sb.Append(',');
//sb.Append(hit.SecondBestPeptideSDFCount);
}
if(hit.IsLocalized)
localizedWriter.WriteLine(sb.ToString());
writer.WriteLine(sb.ToString());
}
}
}
return proteins.Values.ToList();
}
public ProteinMatch(ProteinMatchSettings proteinMatchSettings, Protein protein)
{
Settings = proteinMatchSettings;
Protein = protein;
String ltext = proteinMatchSettings.SearchText.ToLower();
for (int bit = 1; bit < (int)ProteinMatchType.all; bit <<= 1) // name, accession, gene, etc - case insenstive
{
ProteinMatchType matchType = (ProteinMatchType) bit;
if ((0 != (proteinMatchSettings.MatchTypes & matchType)) &&
(0==(matchType &(ProteinMatchType.sequence|ProteinMatchType.description)))) // handle sequence and description below
{
if (Matches(protein.ProteinMetadata, matchType, ltext))
{
MatchType |= matchType;
}
else
{
foreach (ProteinMetadata alternative in Protein.AlternativeNames)
{
if (Matches(alternative, matchType, ltext))
{
MatchType |= matchType;
AlternativeName = alternative;
break;
}
}
}
}
}
if ((MatchType == 0) && // Don't bother declaring a description match if we already have a more specific one (name, accession etc)
(0 != (proteinMatchSettings.MatchTypes & ProteinMatchType.description)))
{
if (ContainsLowerCase(protein.Description, ltext) ||
ContainsLowerCase(protein.Name, ltext))
{
MatchType |= ProteinMatchType.description;
}
else
{
foreach (ProteinMetadata alternative in Protein.AlternativeNames)
{
if (ContainsLowerCase(alternative.Name, ltext) ||
ContainsLowerCase(alternative.Description, ltext))
{
MatchType |= ProteinMatchType.description;
AlternativeDescription = alternative;
}
}
}
}
List<DigestedPeptide> digestedPeptides = new List<DigestedPeptide>();
if (0 != (proteinMatchSettings.MatchTypes & ProteinMatchType.sequence))
{
if (proteinMatchSettings.Protease != null)
{
String lastPeptide = null;
foreach (var peptide in proteinMatchSettings.Protease.Digest(protein))
{
if (!peptide.Sequence.StartsWith(proteinMatchSettings.SearchText))
{
continue;
}
// If this peptide is just an extension of the previous peptide (i.e. with one
// more missed cleavage), then only include it if the user has typed the entire
// sequence of the previous peptide.
if (lastPeptide != null && peptide.Sequence.StartsWith(lastPeptide)
&& lastPeptide.Length > proteinMatchSettings.SearchText.Length)
{
continue;
}
lastPeptide = peptide.Sequence;
MatchType |= ProteinMatchType.sequence;
digestedPeptides.Add(peptide);
}
}
}
DigestedPeptides = digestedPeptides;
}
public FoldChangeRow(Protein protein, Model.Databinding.Entities.Peptide peptide, IsotopeLabelType labelType,
int? msLevel, GroupIdentifier group, int replicateCount, FoldChangeResult foldChangeResult)
{
Protein = protein;
Peptide = peptide;
IsotopeLabelType = labelType;
MsLevel = msLevel;
ReplicateCount = replicateCount;
FoldChangeResult = foldChangeResult;
Group = group;
}
public ProteinResult(Protein protein, ResultFile resultFile)
: base(protein, resultFile)
{
}
public Digestion Digest(IProtease protease, ProgressMonitor progressMonitor)
{
using (ISession session = OpenWriteSession())
{
DbDigestion dbDigestion = GetDbDigestion(protease.Name);
HashSet<string> existingSequences = new HashSet<string>();
using (var transaction = session.BeginTransaction())
{
if (dbDigestion != null)
{
if (dbDigestion.MaxSequenceLength >= MAX_SEQUENCE_LENGTH)
{
return new Digestion(this, dbDigestion);
}
if (!progressMonitor.Invoke(Resources.ProteomeDb_Digest_Listing_existing_peptides, 0))
{
return null;
}
IQuery query = session.CreateQuery("SELECT P.Sequence FROM " // Not L10N
+ typeof(DbDigestedPeptide) + " P WHERE P.Digestion = :Digestion") // Not L10N
.SetParameter("Digestion", dbDigestion); // Not L10N
List<String> listSequences = new List<string>();
query.List(listSequences);
existingSequences.UnionWith(listSequences);
dbDigestion.MaxSequenceLength = MAX_SEQUENCE_LENGTH;
session.Update(dbDigestion);
}
else
{
dbDigestion = new DbDigestion
{
Name = protease.Name,
MinSequenceLength = MIN_SEQUENCE_LENGTH,
MaxSequenceLength = MAX_SEQUENCE_LENGTH,
};
session.Save(dbDigestion);
}
if (!progressMonitor.Invoke(Resources.ProteomeDb_Digest_Listing_proteins, 0))
{
return null;
}
List<DbProtein> proteins = new List<DbProtein>();
session.CreateCriteria(typeof(DbProtein)).List(proteins);
Dictionary<String, long> digestedPeptideIds
= new Dictionary<string, long>();
const String sqlPeptide =
"INSERT INTO ProteomeDbDigestedPeptide (Digestion, Sequence) VALUES(?,?);select last_insert_rowid();"; // Not L10N
using (var commandPeptide = session.Connection.CreateCommand())
using (var commandProtein = session.Connection.CreateCommand())
{
commandPeptide.CommandText = sqlPeptide;
commandPeptide.Parameters.Add(new SQLiteParameter());
commandPeptide.Parameters.Add(new SQLiteParameter());
const String sqlPeptideProtein =
"INSERT INTO ProteomeDbDigestedPeptideProtein (Peptide, Protein) VALUES(?,?);"; // Not L10N
commandProtein.CommandText = sqlPeptideProtein;
commandProtein.Parameters.Add(new SQLiteParameter());
commandProtein.Parameters.Add(new SQLiteParameter());
commandProtein.Parameters.Add(new SQLiteParameter());
for (int i = 0; i < proteins.Count; i++)
{
var proteinSequences = new HashSet<string>();
if (!progressMonitor.Invoke(string.Format(Resources.ProteomeDb_Digest_Digesting__0__proteins,proteins.Count), 100 * i / proteins.Count))
{
return null;
}
Protein protein = new Protein(ProteomeDbPath, proteins[i]);
foreach (DigestedPeptide digestedPeptide in protease.Digest(protein))
{
if (digestedPeptide.Sequence.Length < dbDigestion.MinSequenceLength)
{
continue;
}
String truncatedSequence = digestedPeptide.Sequence.Substring(
0, Math.Min(digestedPeptide.Sequence.Length, dbDigestion.MaxSequenceLength));
if (existingSequences.Contains(truncatedSequence))
{
continue;
}
if (proteinSequences.Contains(truncatedSequence))
{
continue;
}
proteinSequences.Add(truncatedSequence);
long digestedPeptideId;
if (!digestedPeptideIds.TryGetValue(truncatedSequence, out digestedPeptideId))
{
((SQLiteParameter)commandPeptide.Parameters[0]).Value = dbDigestion.Id;
((SQLiteParameter)commandPeptide.Parameters[1]).Value = truncatedSequence;
digestedPeptideId = Convert.ToInt64(commandPeptide.ExecuteScalar());
digestedPeptideIds.Add(truncatedSequence, digestedPeptideId);
}
((SQLiteParameter)commandProtein.Parameters[0]).Value = digestedPeptideId;
((SQLiteParameter)commandProtein.Parameters[1]).Value = protein.Id;
commandProtein.ExecuteNonQuery();
}
}
}
if (!progressMonitor.Invoke(Resources.ProteomeDb_AddFastaFile_Saving_changes, 99))
{
return null;
}
transaction.Commit();
AnalyzeDb(session);
progressMonitor.Invoke(
string.Format(Resources.ProteomeDb_Digest_Digested__0__proteins_into__1__unique_peptides,
proteins.Count, digestedPeptideIds.Count),
100);
}
return new Digestion(this, dbDigestion);
}
}
public ProteinColumn(int index, Protein protein)
{
Index = index;
Protein = protein;
}
private TreeNode CreateProteinNode(Protein prot)
{
treeNodes[prot] = new TreeNode(prot.name);
treeNodes[prot].Expand();
return treeNodes[prot];
}
void TreeUpdateLogCallback(Protein org, Protein prot, string msg)
{
treeView.Invoke(new Action(delegate {
if (treeNodes.ContainsKey(prot))
return;
if (!treeNodes.ContainsKey(org))
treeView.Nodes.Add(CreateProteinNode(prot));
string annotation = null;
prot.attributes.TryGetValue("annotation", out annotation);
treeNodes[prot] = treeNodes[org].Nodes.Add(prot.name + (annotation != null ? ": " + annotation : ""));
}));
}
/// <summary>
/// Loads the protein information.
/// </summary>
protected virtual Dictionary<int, List<Protein>> LoadProteins()
{
var massTagToProtein = new Dictionary<int, List<Protein>>();
using (var connection = CreateConnection(CreateConnectionString()))
{
connection.Open();
using (var command = connection.CreateCommand())
{
SetupProteinMassTagCommand(command);
using (var reader = command.ExecuteReader())
{
while (reader.Read())
{
if (reader["Mass_Tag_ID"] != DBNull.Value)
{
var id = Convert.ToInt32(reader["Mass_Tag_ID"]);
var refName = "";
var proteinId = -1;
var refID = -1;
if (reader["Ref_ID"] != DBNull.Value) refID = Convert.ToInt32(reader["Ref_ID"]);
if (reader["Reference"] != DBNull.Value) refName = reader["Reference"].ToString();
if (reader["Protein_ID"] != DBNull.Value)
proteinId = Convert.ToInt32(reader["Protein_ID"]);
var protein = new Protein();
protein.Sequence = refName;
protein.RefId = refID;
protein.ProteinId = proteinId;
// Link to the Mass tags.
var hasMassTagID = massTagToProtein.ContainsKey(id);
if (!hasMassTagID)
{
massTagToProtein.Add(id, new List<Protein>());
}
massTagToProtein[id].Add(protein);
;
}
}
reader.Close();
}
}
connection.Close();
}
return massTagToProtein;
}
private void UpdateResults()
{
var results = GroupComparisonModel.Results;
var rows = new List<FoldChangeRow>();
if (null != results)
{
var groupComparisonDef = results.GroupComparer.ComparisonDef;
var adjustedPValues = PValues.AdjustPValues(results.ResultRows.Select(
row => row.LinearFitResult.PValue)).ToArray();
for (int iRow = 0; iRow < results.ResultRows.Count; iRow++)
{
var resultRow = results.ResultRows[iRow];
var protein = new Protein(_skylineDataSchema, new IdentityPath(resultRow.Selector.Protein.Id));
Model.Databinding.Entities.Peptide peptide = null;
if (null != resultRow.Selector.Peptide)
{
peptide = new Model.Databinding.Entities.Peptide(_skylineDataSchema,
new IdentityPath(protein.IdentityPath, resultRow.Selector.Peptide.Id));
}
rows.Add(new FoldChangeRow(protein, peptide, resultRow.Selector.LabelType,
resultRow.Selector.MsLevel, resultRow.Selector.GroupIdentifier, resultRow.ReplicateCount,
new FoldChangeResult(groupComparisonDef.ConfidenceLevel,
adjustedPValues[iRow], resultRow.LinearFitResult)));
}
}
var defaultViewSpec = GetDefaultViewSpec(rows);
if (!Equals(defaultViewSpec, ViewContext.BuiltInViews.First()))
{
var viewInfo = new ViewInfo(_skylineDataSchema, typeof (FoldChangeRow), defaultViewSpec).ChangeViewGroup(ViewGroup.BUILT_IN);
ViewContext.SetRowSources(new[]
{
new RowSourceInfo(
rows, viewInfo)
});
if (null != _bindingListSource.ViewSpec && _bindingListSource.ViewSpec.Name == defaultViewSpec.Name &&
!_bindingListSource.ViewSpec.Equals(defaultViewSpec))
{
_bindingListSource.SetView(viewInfo, rows);
}
}
_bindingListSource.RowSource = rows;
}