public IEnumerable <Peptide> Digest(FastaSequence fastaSeq, DigestSettings settings)
{
Regex regex = new Regex(Regex);
int begin = 0;
int len = fastaSeq.Sequence.Length;
while (begin < len)
{
int end = begin;
int endFirst = begin;
int missed = 0;
do
{
string sequence = fastaSeq.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;
}
// 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
{
yield return(new Peptide(fastaSeq, sequence.Substring(begin, end - begin),
begin, end, missed));
}
// Increment missed cleavages for next loop.
missed++;
}while (end < len && missed <= settings.MaxMissedCleavages);
begin = endFirst;
}
}
public bool Equals(DigestSettings obj)
{
if (ReferenceEquals(null, obj))
{
return(false);
}
if (ReferenceEquals(this, obj))
{
return(true);
}
return(obj.MaxMissedCleavages == MaxMissedCleavages &&
obj.ExcludeRaggedEnds.Equals(ExcludeRaggedEnds));
}
public IEnumerable <Peptide> Digest(FastaSequence fastaSeq, DigestSettings settings, int?maxPeptideSequenceLength = null, int?minPeptideSequenceLength = null)
{
int begin = 0;
var sequence = fastaSeq.Sequence;
int len = sequence.Length;
int maxPepLen = maxPeptideSequenceLength ?? int.MaxValue;
int minPepLen = minPeptideSequenceLength ?? 1;
var matcher = new Matcher(sequence, GetMatches(sequence));
while (begin < len)
{
matcher.Reset();
int end = begin;
int endFirst = begin;
int missed = 0;
do
{
int endLast = end;
var m = matcher.Match(end);
end = m + 1 ?? len;
// Save the end of the first cleavage
if (missed == 0)
{
endFirst = end;
}
// Deal with 'ragged ends', or cleavages one amino acid apart
// i.e. KR, RR, etc. for trypsin
if (settings.ExcludeRaggedEnds && end < len)
{
var mNext = matcher.Match(end);
if (mNext.HasValue && mNext == 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(matcher, mNext);
}
break;
}
}
// If the sequence is longer than we care to consider, quit
int count = end - begin;
bool tooLong = maxPeptideSequenceLength.HasValue && count > maxPeptideSequenceLength;
if (!minPeptideSequenceLength.HasValue || count >= minPeptideSequenceLength.Value)
{
// Single amino acid peptides have no fragment ions.
if (count > 1 && sequence.IndexOfAny(nonAAs, begin, count) == -1) // Not L10N
{
if (!tooLong)
{
yield return(new Peptide(fastaSeq, sequence.Substring(begin, end - begin),
begin, end, missed));
}
if (IsSemiCleaving)
{
// Add N-terminal semi-cleavage, which excludes peptides already included in prior peptide,
// when missed cleavage occurs
for (int i = Math.Min(count - 1, maxPepLen); i >= Math.Max(endLast - begin + 1, minPepLen); i--)
{
yield return(new Peptide(fastaSeq, sequence.Substring(begin, i), begin, begin + i, missed));
}
// Add C-terminal semi-cleavage, which excludes peptides to come in subsequent peptides,
// when missed cleavage occurs
for (int i = Math.Min(count - 1, maxPepLen); i >= Math.Max(end - endFirst + 1, minPepLen); i--)
{
yield return(new Peptide(fastaSeq, sequence.Substring(end - i, i), end - i, end, missed));
}
}
}
}
if (tooLong)
{
break;
}
// Increment missed cleavages for next loop.
missed++;
}while (end < len && missed <= settings.MaxMissedCleavages);
begin = endFirst;
}
}
public IEnumerable<Peptide> Digest(FastaSequence fastaSeq, DigestSettings settings)
{
Regex regex = new Regex(Regex);
int begin = 0;
int len = fastaSeq.Sequence.Length;
while (begin < len)
{
int end = begin;
int endFirst = begin;
int missed = 0;
do
{
string sequence = fastaSeq.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;
// 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
{
yield return new Peptide(fastaSeq, sequence.Substring(begin, end - begin),
begin, end, missed);
}
// Increment missed cleavages for next loop.
missed++;
}
while (end < len && missed <= settings.MaxMissedCleavages);
begin = endFirst;
}
}
public bool Equals(DigestSettings obj)
{
if (ReferenceEquals(null, obj)) return false;
if (ReferenceEquals(this, obj)) return true;
return obj.MaxMissedCleavages == MaxMissedCleavages &&
obj.ExcludeRaggedEnds.Equals(ExcludeRaggedEnds);
}
public PeptideSettings ChangeDigestSettings(DigestSettings prop)
{
return ChangeProp(ImClone(this), im => im.DigestSettings = prop);
}
private PeptideSettings ValidateNewSettings(bool showMessages)
{
var helper = new MessageBoxHelper(this, showMessages);
// Validate and hold digestion settings
Enzyme enzyme = Settings.Default.GetEnzymeByName(comboEnzyme.SelectedItem.ToString());
Helpers.AssignIfEquals(ref enzyme, _peptideSettings.Enzyme);
int maxMissedCleavages =
int.Parse(comboMissedCleavages.SelectedItem.ToString());
bool excludeRaggedEnds = cbRaggedEnds.Checked;
DigestSettings digest = new DigestSettings(maxMissedCleavages, excludeRaggedEnds);
Helpers.AssignIfEquals(ref digest, Digest);
var backgroundProteomeSpec = _driverBackgroundProteome.SelectedItem;
BackgroundProteome backgroundProteome = BackgroundProteome.NONE;
if (!backgroundProteomeSpec.IsNone)
{
backgroundProteome = new BackgroundProteome(backgroundProteomeSpec, true);
if (backgroundProteome.DatabaseInvalid)
{
var message = TextUtil.LineSeparate(string.Format(Resources.PeptideSettingsUI_ValidateNewSettings_Failed_to_load_background_proteome__0__,
backgroundProteomeSpec.Name),
string.Format(Resources.PeptideSettingsUI_ValidateNewSettings_The_file__0__may_not_be_a_valid_proteome_file,
backgroundProteomeSpec.DatabasePath));
MessageDlg.Show(this, message);
tabControl1.SelectedIndex = 0;
_driverBackgroundProteome.Combo.Focus();
return null;
}
}
Helpers.AssignIfEquals(ref backgroundProteome, _peptideSettings.BackgroundProteome);
// Validate and hold prediction settings
string nameRT = comboRetentionTime.SelectedItem.ToString();
RetentionTimeRegression retentionTime =
Settings.Default.GetRetentionTimeByName(nameRT);
if (retentionTime != null && retentionTime.Calculator != null)
{
RetentionScoreCalculatorSpec retentionCalc =
Settings.Default.GetCalculatorByName(retentionTime.Calculator.Name);
// Just in case the calculator in use in the current documet got removed,
// never set the calculator to null. Just keep using the one we have.
if (retentionCalc != null && !ReferenceEquals(retentionCalc, retentionTime.Calculator))
retentionTime = retentionTime.ChangeCalculator(retentionCalc);
}
bool useMeasuredRT = cbUseMeasuredRT.Checked;
double? measuredRTWindow = null;
if (!string.IsNullOrEmpty(textMeasureRTWindow.Text))
{
double measuredRTWindowOut;
const double minWindow = PeptidePrediction.MIN_MEASURED_RT_WINDOW;
const double maxWindow = PeptidePrediction.MAX_MEASURED_RT_WINDOW;
if (!helper.ValidateDecimalTextBox(tabControl1, (int) TABS.Prediction,
textMeasureRTWindow, minWindow, maxWindow, out measuredRTWindowOut))
return null;
measuredRTWindow = measuredRTWindowOut;
}
string nameDt = comboDriftTimePredictor.SelectedItem.ToString();
DriftTimePredictor driftTimePredictor =
Settings.Default.GetDriftTimePredictorByName(nameDt);
if (driftTimePredictor != null && driftTimePredictor.IonMobilityLibrary != null)
{
IonMobilityLibrarySpec ionMobilityLibrary =
Settings.Default.GetIonMobilityLibraryByName(driftTimePredictor.IonMobilityLibrary.Name);
// Just in case the library in use in the current documet got removed,
// never set the library to null. Just keep using the one we have.
if (ionMobilityLibrary != null && !ReferenceEquals(ionMobilityLibrary, driftTimePredictor.IonMobilityLibrary))
driftTimePredictor = driftTimePredictor.ChangeLibrary(ionMobilityLibrary);
}
bool useLibraryDriftTime = cbUseSpectralLibraryDriftTimes.Checked;
double? libraryDTResolvingPower = null;
if (useLibraryDriftTime || !string.IsNullOrEmpty(textSpectralLibraryDriftTimesResolvingPower.Text))
{
double libraryDTWindowOut;
if (!helper.ValidateDecimalTextBox(tabControl1, (int)TABS.Prediction,
textSpectralLibraryDriftTimesResolvingPower, null, null, out libraryDTWindowOut))
return null;
string errmsg = EditDriftTimePredictorDlg.ValidateResolvingPower(libraryDTWindowOut);
if (errmsg != null)
{
helper.ShowTextBoxError(tabControl1, (int)TABS.Prediction, textSpectralLibraryDriftTimesResolvingPower, errmsg);
return null;
}
libraryDTResolvingPower = libraryDTWindowOut;
}
var prediction = new PeptidePrediction(retentionTime, driftTimePredictor, useMeasuredRT, measuredRTWindow, useLibraryDriftTime, libraryDTResolvingPower);
Helpers.AssignIfEquals(ref prediction, Prediction);
// Validate and hold filter settings
int excludeNTermAAs;
if (!helper.ValidateNumberTextBox(tabControl1, (int) TABS.Filter, textExcludeAAs,
PeptideFilter.MIN_EXCLUDE_NTERM_AA, PeptideFilter.MAX_EXCLUDE_NTERM_AA, out excludeNTermAAs))
return null;
int minPeptideLength;
if (!helper.ValidateNumberTextBox(tabControl1, (int) TABS.Filter, textMinLength,
PeptideFilter.MIN_MIN_LENGTH, PeptideFilter.MAX_MIN_LENGTH, out minPeptideLength))
return null;
int maxPeptideLength;
if (!helper.ValidateNumberTextBox(tabControl1, (int)TABS.Filter, textMaxLength,
Math.Max(PeptideFilter.MIN_MAX_LENGTH, minPeptideLength), PeptideFilter.MAX_MAX_LENGTH, out maxPeptideLength))
return null;
PeptideExcludeRegex[] exclusions = _driverExclusion.Chosen;
bool autoSelect = cbAutoSelect.Checked;
PeptideFilter filter;
try
{
filter = new PeptideFilter(excludeNTermAAs,
minPeptideLength,
maxPeptideLength,
exclusions,
autoSelect);
}
catch (InvalidDataException x)
{
if (showMessages)
MessageDlg.ShowException(this, x);
return null;
}
Helpers.AssignIfEquals(ref filter, Filter);
// Validate and hold libraries
PeptideLibraries libraries;
IList<LibrarySpec> librarySpecs = _driverLibrary.Chosen;
if (librarySpecs.Count == 0)
libraries = new PeptideLibraries(PeptidePick.library, null, null, false, librarySpecs, new Library[0]);
else
{
int? peptideCount = null;
if (cbLimitPeptides.Checked)
{
int peptideCountVal;
if (!helper.ValidateNumberTextBox(textPeptideCount, PeptideLibraries.MIN_PEPTIDE_COUNT,
PeptideLibraries.MAX_PEPTIDE_COUNT, out peptideCountVal))
return null;
peptideCount = peptideCountVal;
}
PeptidePick pick = (PeptidePick) comboMatching.SelectedIndex;
IList<Library> librariesLoaded = new Library[librarySpecs.Count];
bool documentLibrary = false;
if (Libraries != null)
{
// Use existing library spec's, if nothing was changed.
// Avoid changing the libraries, just because the the picking
// algorithm changed.
if (ArrayUtil.EqualsDeep(librarySpecs, Libraries.LibrarySpecs))
{
librarySpecs = Libraries.LibrarySpecs;
librariesLoaded = Libraries.Libraries;
}
documentLibrary = Libraries.HasDocumentLibrary;
// Otherwise, leave the list of loaded libraries empty,
// and let the LibraryManager refill it. This ensures a
// clean save of library specs only in the user config, rather
// than a mix of library specs and libraries.
}
PeptideRankId rankId = (PeptideRankId) comboRank.SelectedItem;
if (comboRank.SelectedIndex == 0)
rankId = null;
libraries = new PeptideLibraries(pick, rankId, peptideCount, documentLibrary, librarySpecs, librariesLoaded);
}
Helpers.AssignIfEquals(ref libraries, Libraries);
// Validate and hold modifications
int maxVariableMods;
if (!helper.ValidateNumberTextBox(tabControl1, (int)TABS.Modifications, textMaxVariableMods,
PeptideModifications.MIN_MAX_VARIABLE_MODS, PeptideModifications.MAX_MAX_VARIABLE_MODS, out maxVariableMods))
return null;
int maxNeutralLosses;
if (!helper.ValidateNumberTextBox(tabControl1, (int)TABS.Modifications, textMaxNeutralLosses,
PeptideModifications.MIN_MAX_NEUTRAL_LOSSES, PeptideModifications.MAX_MAX_NEUTRAL_LOSSES, out maxNeutralLosses))
return null;
var standardTypes = _driverLabelType.InternalStandardTypes;
PeptideModifications modifications = new PeptideModifications(
_driverStaticMod.Chosen, maxVariableMods, maxNeutralLosses,
_driverLabelType.GetHeavyModifications(), standardTypes);
// Should not be possible to change explicit modifications in the background,
// so this should be safe. CONSIDER: Document structure because of a library load?
modifications = modifications.DeclareExplicitMods(_parent.DocumentUI,
Settings.Default.StaticModList, Settings.Default.HeavyModList);
Helpers.AssignIfEquals(ref modifications, _peptideSettings.Modifications);
PeptideIntegration integration = new PeptideIntegration(_driverPeakScoringModel.SelectedItem);
Helpers.AssignIfEquals(ref integration, Integration);
QuantificationSettings quantification = QuantificationSettings.DEFAULT
.ChangeNormalizationMethod(comboNormalizationMethod.SelectedItem as NormalizationMethod ?? NormalizationMethod.NONE)
.ChangeRegressionWeighting(comboWeighting.SelectedItem as RegressionWeighting)
.ChangeRegressionFit(comboRegressionFit.SelectedItem as RegressionFit)
.ChangeMsLevel(_quantMsLevels[comboQuantMsLevel.SelectedIndex])
.ChangeUnits(tbxQuantUnits.Text);
return new PeptideSettings(enzyme, digest, prediction, filter, libraries, modifications, integration, backgroundProteome)
.ChangeAbsoluteQuantification(quantification);
}
public PeptideSettings(Enzyme enzyme,
DigestSettings digestSettings,
PeptidePrediction prediction,
PeptideFilter filter,
PeptideLibraries libraries,
PeptideModifications modifications,
PeptideIntegration integration,
BackgroundProteome backgroundProteome
)
{
Enzyme = enzyme;
DigestSettings = digestSettings;
Prediction = prediction;
Filter = filter;
Libraries = libraries;
Modifications = modifications;
Integration = integration;
BackgroundProteome = backgroundProteome;
Quantification = QuantificationSettings.DEFAULT;
}
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;
}
}
public Digestion Digest(Enzyme enzyme, DigestSettings digestSettings, ILoadMonitor loader)
{
ProgressStatus progressStatus = new ProgressStatus(string.Format(Resources.BackgroundProteomeSpec_Digest_Digesting__0__, enzyme.Name));
using (var proteomeDb = OpenProteomeDb())
{
return proteomeDb.Digest(new ProteaseImpl(enzyme),
(s, i) =>
{
loader.UpdateProgress(progressStatus.ChangePercentComplete(i));
return !loader.IsCanceled;
});
}
}
public IEnumerable <Peptide> Digest(FastaSequence fastaSeq, DigestSettings settings, int?maxPeptideSequenceLength = null)
{
int begin = 0;
var sequence = fastaSeq.Sequence;
int len = sequence.Length;
var matcher = new Matcher(sequence, GetMatches(sequence));
while (begin < len)
{
matcher.Reset();
int end = begin;
int endFirst = begin;
int missed = 0;
do
{
var m = matcher.Match(end);
end = m + 1 ?? len;
// Save the end of the first cleavage
if (missed == 0)
{
endFirst = end;
}
// Deal with 'ragged ends', or cleavages one amino acid apart
// i.e. KR, RR, etc. for trypsin
if (settings.ExcludeRaggedEnds && end < len)
{
var mNext = matcher.Match(end);
if (mNext.HasValue && mNext == 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(matcher, mNext);
}
break;
}
}
// Single amino acid peptides have no fragment ions.
int count = end - begin;
// If the sequence is longer than we care to consider, quit
if (maxPeptideSequenceLength.HasValue && count > maxPeptideSequenceLength)
{
break;
}
if (count > 1 && sequence.IndexOfAny(nonAAs, begin, count) == -1) // Not L10N
{
yield return(new Peptide(fastaSeq, sequence.Substring(begin, end - begin),
begin, end, missed));
}
// Increment missed cleavages for next loop.
missed++;
}while (end < len && missed <= settings.MaxMissedCleavages);
begin = endFirst;
}
}
public bool ImportFasta()
{
var settings = SkylineWindow.Document.Settings;
var peptideSettings = settings.PeptideSettings;
int missedCleavages = MaxMissedCleavages;
var enzyme = Enzyme;
if (!Equals(missedCleavages, peptideSettings.DigestSettings.MaxMissedCleavages) || !Equals(enzyme, peptideSettings.Enzyme))
{
var digest = new DigestSettings(missedCleavages, peptideSettings.DigestSettings.ExcludeRaggedEnds);
peptideSettings = peptideSettings.ChangeDigestSettings(digest).ChangeEnzyme(enzyme);
SkylineWindow.ModifyDocument(string.Format(Resources.ImportFastaControl_ImportFasta_Change_digestion_settings), doc =>
doc.ChangeSettings(settings.ChangePeptideSettings(peptideSettings)));
}
if (!ContainsFastaContent) // The user didn't specify any FASTA content
{
var docCurrent = SkylineWindow.DocumentUI;
// If the document has precursor transitions already, then just trust the user
// knows what they are doing, and this document is already set up for MS1 filtering
if (HasPrecursorTransitions(docCurrent))
return true;
if (docCurrent.PeptideCount == 0)
{
MessageDlg.Show(WizardForm, TextUtil.LineSeparate(Resources.ImportFastaControl_ImportFasta_The_document_does_not_contain_any_peptides_,
Resources.ImportFastaControl_ImportFasta_Please_import_FASTA_to_add_peptides_to_the_document_));
return false;
}
if (MessageBox.Show(WizardForm, TextUtil.LineSeparate(Resources.ImportFastaControl_ImportFasta_The_document_does_not_contain_any_precursor_transitions_,
Resources.ImportFastaControl_ImportFasta_Would_you_like_to_change_the_document_settings_to_automatically_pick_the_precursor_transitions_specified_in_the_full_scan_settings_),
Program.Name, MessageBoxButtons.OKCancel) != DialogResult.OK)
return false;
SkylineWindow.ModifyDocument(Resources.ImportFastaControl_ImportFasta_Change_settings_to_add_precursors, doc => ImportPeptideSearch.ChangeAutoManageChildren(doc, PickLevel.transitions, true));
}
else // The user specified some FASTA content
{
// If the user is about to add any new transitions by importing
// FASTA, set FragmentType='p' and AutoSelect=true
var docCurrent = SkylineWindow.Document;
var docNew = ImportPeptideSearch.PrepareImportFasta(docCurrent);
var nodeInsert = SkylineWindow.SequenceTree.SelectedNode as SrmTreeNode;
IdentityPath selectedPath = nodeInsert != null ? nodeInsert.Path : null;
int emptyPeptideGroups = 0;
if (!_fastaFile)
{
// Import FASTA as content
docNew = ImportFastaHelper.AddFasta(docNew, ref selectedPath, out emptyPeptideGroups);
// Document will be null if there was an error
if (docNew == null)
return false;
}
else
{
// Import FASTA as file
var fastaPath = tbxFasta.Text;
try
{
using (var longWaitDlg = new LongWaitDlg(SkylineWindow) { Text = Resources.ImportFastaControl_ImportFasta_Insert_FASTA })
{
IdentityPath to = selectedPath;
var docImportFasta = docNew;
longWaitDlg.PerformWork(WizardForm, 1000, longWaitBroker =>
{
IdentityPath nextAdd;
docImportFasta = ImportPeptideSearch.ImportFasta(docImportFasta, fastaPath,
longWaitBroker, to, out selectedPath, out nextAdd, out emptyPeptideGroups);
});
docNew = docImportFasta;
}
}
catch (Exception x)
{
MessageDlg.ShowWithException(this, string.Format(Resources.SkylineWindow_ImportFastaFile_Failed_reading_the_file__0__1__,
fastaPath, x.Message), x);
return false;
}
}
// Check for empty proteins
docNew = ImportFastaHelper.HandleEmptyPeptideGroups(WizardForm, emptyPeptideGroups, docNew);
// Document will be null if user was given option to keep or remove empty proteins and pressed cancel
if (docNew == null)
return false;
SkylineWindow.ModifyDocument(Resources.ImportFastaControl_ImportFasta_Insert_FASTA, doc =>
{
if (!ReferenceEquals(doc, docCurrent))
throw new InvalidDataException(Resources.SkylineWindow_ImportFasta_Unexpected_document_change_during_operation);
return docNew;
});
if (!VerifyAtLeastOnePrecursorTransition(SkylineWindow.Document))
return false;
}
return true;
}
