public DatabaseSearcher(IList<string> dataFilepaths,
int minimumAssumedPrecursorChargeState, int maximumAssumedPrecursorChargeState,
double absoluteThreshold, double relativeThresholdPercent, int maximumNumberOfPeaks,
bool assignChargeStates, bool deisotope,
string proteinFastaDatabaseFilepath, bool onTheFlyDecoys,
Protease protease, int maximumMissedCleavages, InitiatorMethionineBehavior initiatorMethionineBehavior,
IEnumerable<Modification> fixedModifications, IEnumerable<Modification> variableModifications, int maximumVariableModificationIsoforms,
MassTolerance precursorMassTolerance, MassType precursorMassType,
bool precursorMonoisotopicPeakCorrection, int minimumPrecursorMonoisotopicPeakOffset, int maximumPrecursorMonoisotopicPeakOffset,
MassTolerance productMassTolerance, MassType productMassType,
double maximumFalseDiscoveryRate, bool considerModifiedFormsAsUniquePeptides,
int maximumThreads, bool minimizeMemoryUsage,
string outputFolder)
{
this.dataFilepaths = dataFilepaths;
this.assignChargeStates = assignChargeStates;
this.deisotope = deisotope;
this.proteinFastaDatabaseFilepath = proteinFastaDatabaseFilepath;
this.onTheFlyDecoys = onTheFlyDecoys;
this.protease = protease;
this.maximumMissedCleavages = maximumMissedCleavages;
this.initiatorMethionineBehavior = initiatorMethionineBehavior;
this.fixedModifications = fixedModifications;
this.variableModifications = variableModifications;
this.maximumVariableModificationIsoforms = maximumVariableModificationIsoforms;
this.minimumAssumedPrecursorChargeState = minimumAssumedPrecursorChargeState;
this.maximumAssumedPrecursorChargeState = maximumAssumedPrecursorChargeState;
this.absoluteThreshold = absoluteThreshold;
this.relativeThresholdPercent = relativeThresholdPercent;
this.maximumNumberOfPeaks = maximumNumberOfPeaks;
this.precursorMassTolerance = precursorMassTolerance;
this.precursorMassType = precursorMassType;
this.precursorMonoisotopicPeakCorrection = precursorMonoisotopicPeakCorrection;
this.minimumPrecursorMonoisotopicPeakOffset = minimumPrecursorMonoisotopicPeakOffset;
this.maximumPrecursorMonoisotopicPeakOffset = maximumPrecursorMonoisotopicPeakOffset;
this.productMassTolerance = productMassTolerance;
this.productMassType = productMassType;
this.maximumFalseDiscoveryRate = maximumFalseDiscoveryRate;
this.considerModifiedFormsAsUniquePeptides = considerModifiedFormsAsUniquePeptides;
this.maximumThreads = maximumThreads;
this.minimizeMemoryUsage = minimizeMemoryUsage;
this.outputFolder = outputFolder;
}
static void Main(string[] args)
{
if (args.Length > 0)
{
Arguments arguments = new Arguments(args);
List <string> data = new List <string>(arguments["d"].Split(','));
int min_assumed_precursor_charge_state = 2;
if (arguments["minprecz"] != null)
{
min_assumed_precursor_charge_state = int.Parse(arguments["minprecz"]);
}
int max_assumed_precursor_charge_state = 4;
if (arguments["maxprecz"] != null)
{
max_assumed_precursor_charge_state = int.Parse(arguments["maxprecz"]);
}
double abs_threshold = -1.0;
if (arguments["at"] != null)
{
abs_threshold = double.Parse(arguments["at"], CultureInfo.InvariantCulture);
}
double rel_threshold_percent = -1.0;
if (arguments["rt"] != null)
{
rel_threshold_percent = double.Parse(arguments["rt"], CultureInfo.InvariantCulture);
}
int max_peaks = 400;
if (arguments["mp"] != null)
{
max_peaks = int.Parse(arguments["mp"]);
}
bool assign_charge_states = true;
if (arguments["acs"] != null)
{
assign_charge_states = bool.Parse(arguments["acs"]);
}
bool deisotope = true;
if (arguments["di"] != null)
{
deisotope = bool.Parse(arguments["di"]);
}
string database = arguments["db"];
Dictionary <string, Modification> known_variable_modifications = null;
HashSet <Modification> variable_mods = new HashSet <Modification>();
if (Path.GetExtension(database).Equals(".xml", StringComparison.InvariantCultureIgnoreCase))
{
bool no_uniprot_mods = false;
if (arguments["noup"] != null)
{
no_uniprot_mods = bool.Parse(arguments["noup"]);
}
if (!no_uniprot_mods)
{
known_variable_modifications = ProteomeDatabaseReader.ReadUniProtXmlModifications(database);
variable_mods.UnionWith(known_variable_modifications.Values);
}
}
bool append_decoys = false;
if (arguments["ad"] != null)
{
append_decoys = bool.Parse(arguments["ad"]);
}
else
{
append_decoys = Path.GetExtension(database).Equals(".xml", StringComparison.InvariantCultureIgnoreCase) || !ProteomeDatabaseReader.HasDecoyProteins(database);
}
ProteaseDictionary proteases = ProteaseDictionary.Instance;
Protease protease = proteases["trypsin (no proline rule)"];
if (arguments["p"] != null)
{
protease = proteases[arguments["p"]];
}
int max_missed_cleavages = 2;
if (arguments["mmc"] != null)
{
max_missed_cleavages = int.Parse(arguments["mmc"]);
}
InitiatorMethionineBehavior initiator_methionine_behavior = InitiatorMethionineBehavior.Variable;
if (arguments["imb"] != null)
{
initiator_methionine_behavior = (InitiatorMethionineBehavior)Enum.Parse(typeof(InitiatorMethionineBehavior), arguments["imb"], true);
}
ModificationDictionary mods = ModificationDictionary.Instance;
List <Modification> fixed_mods = new List <Modification>();
if (arguments["fm"] != null)
{
foreach (string fixed_mod in arguments["fm"].Split(';'))
{
fixed_mods.Add(mods[fixed_mod]);
}
}
if (arguments["vm"] != null)
{
foreach (string variable_mod in arguments["vm"].Split(';'))
{
Modification mod;
if (!mods.TryGetValue(variable_mod, out mod))
{
known_variable_modifications.TryGetValue(variable_mod, out mod);
}
variable_mods.Add(mod);
}
}
int max_variable_mod_isoforms_per_peptide = 1024;
if (arguments["mvmi"] != null)
{
max_variable_mod_isoforms_per_peptide = int.Parse(arguments["mvmi"]);
}
double precursor_mass_tolerance_value = 2.1;
if (arguments["precmtv"] != null)
{
precursor_mass_tolerance_value = double.Parse(arguments["precmtv"], CultureInfo.InvariantCulture);
}
MassToleranceUnits precursor_mass_tolerance_units = MassToleranceUnits.Da;
if (arguments["precmtu"] != null)
{
precursor_mass_tolerance_units = (MassToleranceUnits)Enum.Parse(typeof(MassToleranceUnits), arguments["precmtu"], true);
}
MassTolerance precursor_mass_tolerance = new MassTolerance(precursor_mass_tolerance_value, precursor_mass_tolerance_units);
MassType precursor_mass_type = MassType.Monoisotopic;
if (arguments["precmt"] != null)
{
precursor_mass_type = (MassType)Enum.Parse(typeof(MassType), arguments["precmt"], true);
}
List <double> accepted_precursor_mass_errors = new List <double>();
if (arguments["apme"] != null && arguments["apme"].Length > 0)
{
foreach (string accepted_precursor_mass_error in arguments["apme"].Split(';'))
{
accepted_precursor_mass_errors.Add(double.Parse(accepted_precursor_mass_error, CultureInfo.InvariantCulture));
}
}
else
{
accepted_precursor_mass_errors.Add(0.0);
}
double product_mass_tolerance_value = 0.015;
if (arguments["prodmtv"] != null)
{
product_mass_tolerance_value = double.Parse(arguments["prodmtv"], CultureInfo.InvariantCulture);
}
MassToleranceUnits product_mass_tolerance_units = MassToleranceUnits.Da;
if (arguments["prodmtu"] != null)
{
product_mass_tolerance_units = (MassToleranceUnits)Enum.Parse(typeof(MassToleranceUnits), arguments["prodmtu"], true);
}
MassTolerance product_mass_tolerance = new MassTolerance(product_mass_tolerance_value, product_mass_tolerance_units);
MassType product_mass_type = MassType.Monoisotopic;
if (arguments["prodmt"] != null)
{
product_mass_type = (MassType)Enum.Parse(typeof(MassType), arguments["prodmt"], true);
}
double max_fdr = 0.01;
if (arguments["fdr"] != null)
{
max_fdr = double.Parse(arguments["fdr"], CultureInfo.InvariantCulture) / 100.0;
}
bool consider_mods_unique = false;
if (arguments["cmu"] != null)
{
consider_mods_unique = bool.Parse(arguments["cmu"]);
}
int max_threads = Environment.ProcessorCount;
if (arguments["mt"] != null)
{
max_threads = int.Parse(arguments["mt"]);
}
bool minimize_memory_usage = false;
if (arguments["mmu"] != null)
{
minimize_memory_usage = bool.Parse(arguments["mmu"]);
}
string output_folder = Environment.CurrentDirectory;
if (arguments["o"] != null)
{
output_folder = arguments["o"];
}
DatabaseSearcher database_searcher = new DatabaseSearcher(data,
min_assumed_precursor_charge_state, max_assumed_precursor_charge_state,
abs_threshold, rel_threshold_percent, max_peaks,
assign_charge_states, deisotope,
database, append_decoys,
protease, max_missed_cleavages, initiator_methionine_behavior,
fixed_mods, variable_mods, max_variable_mod_isoforms_per_peptide,
precursor_mass_tolerance, precursor_mass_type,
accepted_precursor_mass_errors,
product_mass_tolerance, product_mass_type,
max_fdr, consider_mods_unique,
max_threads, minimize_memory_usage,
output_folder);
database_searcher.Starting += HandleStarting;
database_searcher.StartingFile += HandleStartingFile;
database_searcher.UpdateStatus += HandleUpdateStatus;
database_searcher.UpdateProgress += HandleUpdateProgress;
database_searcher.ThrowException += HandleThrowException;
database_searcher.FinishedFile += HandleFinishedFile;
database_searcher.Finished += HandleFinished;
database_searcher.Search();
}
else
{
Console.WriteLine(Program.GetProductNameAndVersion() + " USAGE");
}
}
public static List <ProteinGroup> ApplyProteinParsimony(IEnumerable <PeptideSpectrumMatch> peptideSpectrumMatches, double morpheusScoreThreshold, FileStream proteinFastaDatabase, bool onTheFlyDecoys, IDictionary <string, Modification> knownVariableModifications, Protease protease, int maximumMissedCleavages, InitiatorMethionineBehavior initiatorMethionineBehavior, int maximumThreads)
{
// make a list of the all the distinct base leucine peptide sequences
Dictionary <string, List <Protein> > peptide_proteins = new Dictionary <string, List <Protein> >();
foreach (PeptideSpectrumMatch psm in peptideSpectrumMatches)
{
if (psm.MorpheusScore >= morpheusScoreThreshold)
{
if (!peptide_proteins.ContainsKey(psm.Peptide.BaseLeucineSequence))
{
peptide_proteins.Add(psm.Peptide.BaseLeucineSequence, new List <Protein>());
}
}
}
// record all proteins that could have been the source of each peptide
ParallelOptions parallel_options = new ParallelOptions();
parallel_options.MaxDegreeOfParallelism = maximumThreads;
Parallel.ForEach(ProteomeDatabaseReader.ReadProteins(proteinFastaDatabase, onTheFlyDecoys, REQUIRE_MATCHING_KNOWN_MODIFICATIONS_IN_PROTEIN_PARSIMONY ? knownVariableModifications : null), parallel_options, protein =>
{
foreach (Peptide peptide in protein.Digest(protease, maximumMissedCleavages, initiatorMethionineBehavior, null, null))
{
lock (peptide_proteins)
{
List <Protein> proteins;
if (peptide_proteins.TryGetValue(peptide.BaseLeucineSequence, out proteins))
{
List <Peptide> peptides;
if (!protein.IdentifiedPeptides.TryGetValue(peptide.BaseLeucineSequence, out peptides))
{
peptides = new List <Peptide>();
peptides.Add(peptide);
protein.IdentifiedPeptides.Add(peptide.BaseLeucineSequence, peptides);
}
else
{
peptides.Add(peptide);
}
proteins.Add(protein);
}
}
}
}
);
// create protein groups (initially with just one protein each) and assign PSMs to them
Dictionary <string, ProteinGroup> proteins_by_description = new Dictionary <string, ProteinGroup>();
foreach (PeptideSpectrumMatch psm in peptideSpectrumMatches)
{
if (psm.MorpheusScore >= morpheusScoreThreshold)
{
foreach (Protein protein in peptide_proteins[psm.Peptide.BaseLeucineSequence])
{
if (REQUIRE_MATCHING_KNOWN_MODIFICATIONS_IN_PROTEIN_PARSIMONY)
{
// check to make sure this protein's known modifications match the PSM's
bool known_modification_match = true;
if (psm.Peptide.VariableModifications != null && psm.Peptide.VariableModifications.Count > 0)
{
foreach (KeyValuePair <int, Modification> kvp in psm.Peptide.VariableModifications)
{
if (kvp.Value.Known)
{
List <Modification> protein_modifications = null;
if (protein.KnownModifications == null ||
!protein.KnownModifications.TryGetValue(psm.Peptide.StartResidueNumber - 1 + kvp.Key, out protein_modifications) ||
!protein_modifications.Contains(kvp.Value))
{
known_modification_match = false;
break;
}
}
}
if (!known_modification_match)
{
continue;
}
}
}
ProteinGroup protein_group;
if (!proteins_by_description.TryGetValue(protein.Description, out protein_group))
{
protein_group = new ProteinGroup();
protein_group.Add(protein);
protein_group.PeptideSpectrumMatches.Add(psm);
proteins_by_description.Add(protein.Description, protein_group);
}
else
{
protein_group.PeptideSpectrumMatches.Add(psm);
}
}
}
}
List <ProteinGroup> protein_groups = new List <ProteinGroup>(proteins_by_description.Values);
protein_groups.Sort(ProteinGroup.DescendingSummedMorpheusScoreProteinGroupComparison);
// todo: remove shared peptides from lower-scoring protein group?
// merge indistinguishable proteins (technically protein groups but they only contain a single protein thus far)
for (int i = 0; i < protein_groups.Count - 1; i++)
{
ProteinGroup protein_group = protein_groups[i];
int j = i + 1;
while (j < protein_groups.Count)
{
ProteinGroup lower_protein_group = protein_groups[j];
if (lower_protein_group.SummedMorpheusScore < protein_group.SummedMorpheusScore)
{
break;
}
if (lower_protein_group.BaseLeucinePeptideSequences.SetEquals(protein_group.BaseLeucinePeptideSequences))
{
protein_group.UnionWith(lower_protein_group); // should only ever be one protein in the group to add
protein_groups.RemoveAt(j);
}
else
{
j++;
}
}
}
// remove subset and subsumable protein groups
int k = protein_groups.Count - 1;
while (k >= 1)
{
ProteinGroup protein_group = protein_groups[k];
HashSet <string> protein_group_peptides = new HashSet <string>(protein_group.BaseLeucinePeptideSequences);
for (int l = 0; l < k; l++)
{
ProteinGroup higher_protein_group = protein_groups[l];
protein_group_peptides.ExceptWith(higher_protein_group.BaseLeucinePeptideSequences);
if (protein_group_peptides.Count == 0)
{
break;
}
}
if (protein_group_peptides.Count == 0)
{
protein_groups.RemoveAt(k);
}
k--;
}
return(protein_groups);
}
private void btnSearch_Click(object sender, EventArgs e)
{
if (lstData.Items.Count == 0)
{
MessageBox.Show("No data files selected");
btnAdd.Focus();
return;
}
List <string> data_filepaths = new List <string>(lstData.Items.Count);
foreach (string data_filepath in lstData.Items)
{
data_filepaths.Add(data_filepath);
}
bool assign_charge_states = chkAssignChargeStates.Checked;
bool deisotope = chkDeisotope.Checked;
string fasta_filepath = txtFastaFile.Text;
if (!File.Exists(fasta_filepath))
{
if (fasta_filepath.Length > 0)
{
MessageBox.Show("Invalid protein database file: " + fasta_filepath);
}
else
{
MessageBox.Show("Invalid protein database file");
}
txtFastaFile.Focus();
return;
}
bool on_the_fly_decoys = chkOnTheFlyDecoys.Checked;
Protease protease = (Protease)cboProtease.SelectedItem;
int max_missed_cleavages = (int)numMaxMissedCleavages.Value;
InitiatorMethionineBehavior initiator_methionine_behavior = (InitiatorMethionineBehavior)Enum.Parse(typeof(InitiatorMethionineBehavior), cboInitiatorMethionineBehavior.Text, true);
List <Modification> fixed_modifications = new List <Modification>(clbFixedModifications.CheckedItems.Count);
foreach (object fixed_modification in clbFixedModifications.CheckedItems)
{
fixed_modifications.Add((Modification)fixed_modification);
}
List <Modification> variable_modifications = new List <Modification>(clbVariableModifications.CheckedItems.Count);
foreach (object variable_modification in clbVariableModifications.CheckedItems)
{
variable_modifications.Add((Modification)variable_modification);
}
int max_variable_mod_isoforms = (int)numMaxVariableModIsoforms.Value;
int min_assumed_precursor_charge_state = (int)numMinimumAssumedPrecursorChargeState.Value;
int max_assumed_precursor_charge_state = (int)numMaximumAssumedPrecursorChargeState.Value;
double absolute_threshold = -1.0;
if (chkAbsoluteThreshold.Checked)
{
if (!double.TryParse(txtAbsoluteThreshold.Text, NumberStyles.Float | NumberStyles.AllowThousands, CultureInfo.InvariantCulture, out absolute_threshold))
{
MessageBox.Show("Cannot parse absolute MS/MS peak threshold: " + txtAbsoluteThreshold.Text);
txtAbsoluteThreshold.Focus();
return;
}
}
double relative_threshold_percent = -1.0;
if (chkRelativeThreshold.Checked)
{
if (!double.TryParse(txtRelativeThresholdPercent.Text, NumberStyles.Float | NumberStyles.AllowThousands, CultureInfo.InvariantCulture, out relative_threshold_percent))
{
MessageBox.Show("Cannot parse relative MS/MS peak threshold: " + txtRelativeThresholdPercent.Text);
txtRelativeThresholdPercent.Focus();
return;
}
}
int max_peaks = -1;
if (chkMaxNumPeaks.Checked)
{
max_peaks = (int)numMaxPeaks.Value;
}
MassTolerance precursor_mass_tolerance = new MassTolerance((double)numPrecursorMassTolerance.Value, (MassToleranceUnits)cboPrecursorMassToleranceUnits.SelectedIndex);
MassType precursor_mass_type = (MassType)cboPrecursorMassType.SelectedIndex;
List <double> accepted_precursor_mass_errors = new List <double>();
if (txtAcceptedPrecursorMassErrors.Text.Length > 0)
{
foreach (string accepted_precursor_mass_error_text in txtAcceptedPrecursorMassErrors.Text.Split(';'))
{
double accepted_precursor_mass_error;
if (!double.TryParse(accepted_precursor_mass_error_text, NumberStyles.Float | NumberStyles.AllowThousands, CultureInfo.InvariantCulture, out accepted_precursor_mass_error))
{
MessageBox.Show("Cannot parse accepted precursor mass errors: " + txtRelativeThresholdPercent.Text);
txtAcceptedPrecursorMassErrors.Focus();
return;
}
accepted_precursor_mass_errors.Add(accepted_precursor_mass_error);
}
}
else
{
accepted_precursor_mass_errors.Add(0.0);
}
MassTolerance product_mass_tolerance = new MassTolerance((double)numProductMassTolerance.Value, (MassToleranceUnits)cboProductMassToleranceUnits.SelectedIndex);
MassType product_mass_type = (MassType)cboProductMassType.SelectedIndex;
double max_false_discovery_rate = (double)numMaximumFalseDiscoveryRatePercent.Value / 100.0;
bool consider_modified_unique = chkConsiderModifiedUnique.Checked;
int max_threads = (int)numMaxThreads.Value;
bool minimize_memory_usage = chkMinimizeMemoryUsage.Checked;
string output_folder = txtOutputFolder.Text;
if (!Directory.Exists(output_folder))
{
try
{
Directory.CreateDirectory(output_folder);
}
catch
{
if (output_folder.Length > 0)
{
MessageBox.Show("Invalid output folder: " + output_folder);
}
else
{
MessageBox.Show("Invalid output folder");
}
txtOutputFolder.Focus();
return;
}
}
DatabaseSearcher database_searcher = new DatabaseSearcher(data_filepaths,
min_assumed_precursor_charge_state, max_assumed_precursor_charge_state,
absolute_threshold, relative_threshold_percent, max_peaks,
assign_charge_states, deisotope,
fasta_filepath, on_the_fly_decoys,
protease, max_missed_cleavages, initiator_methionine_behavior,
fixed_modifications, variable_modifications, max_variable_mod_isoforms,
precursor_mass_tolerance, precursor_mass_type,
accepted_precursor_mass_errors,
product_mass_tolerance, product_mass_type,
max_false_discovery_rate, consider_modified_unique,
max_threads, minimize_memory_usage,
output_folder);
database_searcher.Starting += HandleStarting;
database_searcher.StartingFile += HandleStartingFile;
database_searcher.UpdateStatus += HandleUpdateStatus;
database_searcher.ReportTaskWithoutProgress += HandleReportTaskWithoutProgress;
database_searcher.ReportTaskWithProgress += HandleReportTaskWithProgress;
database_searcher.UpdateProgress += HandleUpdateProgress;
database_searcher.ThrowException += HandleThrowException;
database_searcher.FinishedFile += HandleFinishedFile;
database_searcher.Finished += HandleFinished;
lstData.SelectedItem = null;
tspbProgress.Value = tspbProgress.Minimum;
Thread thread = new Thread(new ThreadStart(database_searcher.Search));
thread.IsBackground = true;
thread.Start();
}
public IEnumerable <Peptide> Digest(Protease protease, int maximumMissedCleavages, InitiatorMethionineBehavior initiatorMethionineBehavior,
int?minimumPeptideLength, int?maximumPeptideLength)
{
if (Length > 0)
{
if (protease.CleavageSpecificity != CleavageSpecificity.None)
{
// these are the 0-based residue indices the protease cleaves AFTER
List <int> indices = protease.GetDigestionSiteIndices(this);
indices.Insert(0, -1);
indices.Add(Length - 1);
if (protease.CleavageSpecificity == CleavageSpecificity.Full)
{
for (int missed_cleavages = 0; missed_cleavages <= maximumMissedCleavages; missed_cleavages++)
{
for (int i = 0; i < indices.Count - missed_cleavages - 1; i++)
{
if (initiatorMethionineBehavior != InitiatorMethionineBehavior.Cleave || indices[i] + 1 != 0 || this[0] != 'M')
{
int length = indices[i + missed_cleavages + 1] - indices[i];
if ((!minimumPeptideLength.HasValue || length >= minimumPeptideLength.Value) && (!maximumPeptideLength.HasValue || length <= maximumPeptideLength.Value))
{
// start residue number: +1 for starting at the next residue after the cleavage, +1 for 0->1 indexing
// end residue number: +1 for 0->1 indexing
Peptide peptide = new Peptide(this, indices[i] + 1 + 1, indices[i + missed_cleavages + 1] + 1, missed_cleavages);
yield return(peptide);
}
}
if (initiatorMethionineBehavior != InitiatorMethionineBehavior.Retain && indices[i] + 1 == 0 && this[0] == 'M')
{
int length = indices[i + missed_cleavages + 1] - indices[i] - 1;
if (length > 0 && (!minimumPeptideLength.HasValue || length >= minimumPeptideLength.Value) && (!maximumPeptideLength.HasValue || length <= maximumPeptideLength.Value))
{
// start residue number: +1 for skipping initiator methionine, +1 for starting at the next residue after the cleavage, +1 for 0->1 indexing
// end residue number: +1 for 0->1 indexing
Peptide peptide_without_initiator_methionine = new Peptide(this, indices[i] + 1 + 1 + 1, indices[i + missed_cleavages + 1] + 1, missed_cleavages);
yield return(peptide_without_initiator_methionine);
}
}
}
}
}
else // protease.CleavageSpecificity == CleavageSpecificity.Semi || protease.CleavageSpecificity == CleavageSpecificity.SemiN || protease.CleavageSpecificity == CleavageSpecificity.SemiC
{
if (protease.CleavageSpecificity == CleavageSpecificity.Semi || protease.CleavageSpecificity == CleavageSpecificity.SemiN)
{
for (int missed_cleavages = 0; missed_cleavages <= maximumMissedCleavages; missed_cleavages++)
{
for (int i = 0; i < indices.Count - missed_cleavages - 1; i++)
{
if (initiatorMethionineBehavior != InitiatorMethionineBehavior.Cleave || indices[i] + 1 != 0 || this[0] != 'M')
{
// conditional ensures that we are generating peptides at their lowest missed cleavage state
for (int length = indices[i + missed_cleavages + 1] - indices[i]; length > (indices[i + missed_cleavages + 1] - indices[i]) - (indices[i + missed_cleavages + 1] - indices[(i + missed_cleavages + 1) - 1]); length--)
{
if ((indices[i] + 1 + 1) + length - 1 <= Length)
{
if ((!minimumPeptideLength.HasValue || length >= minimumPeptideLength.Value) && (!maximumPeptideLength.HasValue || length <= maximumPeptideLength.Value))
{
// start residue number: +1 for starting at the next residue after the cleavage, +1 for 0->1 indexing
// end residue number: start residue number + length - 1
Peptide peptide = new Peptide(this, indices[i] + 1 + 1, (indices[i] + 1 + 1) + length - 1, missed_cleavages);
yield return(peptide);
}
}
}
}
if (initiatorMethionineBehavior != InitiatorMethionineBehavior.Retain && indices[i] + 1 == 0 && this[0] == 'M')
{
// conditional ensures that we are generating peptides at their lowest missed cleavage state
for (int length = indices[i + missed_cleavages + 1] - indices[i]; length > (indices[i + missed_cleavages + 1] - indices[i]) - (indices[i + missed_cleavages + 1] - indices[(i + missed_cleavages + 1) - 1]); length--)
{
if ((indices[i] + 1 + 1 + 1) + length - 1 <= Length)
{
if ((!minimumPeptideLength.HasValue || length >= minimumPeptideLength.Value) && (!maximumPeptideLength.HasValue || length <= maximumPeptideLength.Value))
{
// start residue number: +1 for skipping initiator methionine, +1 for starting at the next residue after the cleavage, +1 for 0->1 indexing
// end residue number: start residue number + length - 1
Peptide peptide_without_initiator_methionine = new Peptide(this, indices[i] + 1 + 1 + 1, (indices[i] + 1 + 1 + 1) + length - 1, missed_cleavages);
yield return(peptide_without_initiator_methionine);
}
}
}
}
}
}
}
if (protease.CleavageSpecificity == CleavageSpecificity.Semi || protease.CleavageSpecificity == CleavageSpecificity.SemiC)
{
for (int missed_cleavages = 0; missed_cleavages <= maximumMissedCleavages; missed_cleavages++)
{
for (int i = 0; i < indices.Count - missed_cleavages - 1; i++)
{
// handling for initiator methionine not required
// - (protease.CleavageSpecificity == CleavageSpecificity.Semi ? 1 : 0) ensures that we don't repeat the same peptides we generated above in the SemiN digestion
// conditional ensures that we are generating peptides at their lowest missed cleavage state
for (int length = indices[i + missed_cleavages + 1] - indices[i] - (protease.CleavageSpecificity == CleavageSpecificity.Semi ? 1 : 0); length > (indices[i + missed_cleavages + 1] - indices[i]) - (indices[i + 1] - indices[i]); length--)
{
if ((indices[i + missed_cleavages + 1] + 1) - length + 1 >= 1)
{
if ((!minimumPeptideLength.HasValue || length >= minimumPeptideLength.Value) && (!maximumPeptideLength.HasValue || length <= maximumPeptideLength.Value))
{
// start residue number: end residue number - length + 1
// end residue number: +1 for 0->1 indexing
Peptide peptide = new Peptide(this, (indices[i + missed_cleavages + 1] + 1) - length + 1, indices[i + missed_cleavages + 1] + 1, missed_cleavages);
yield return(peptide);
}
}
}
}
}
}
}
}
else // protease.CleavageSpecificity == CleavageSpecificity.None
{
if (initiatorMethionineBehavior != InitiatorMethionineBehavior.Cleave || this[0] != 'M')
{
if ((!minimumPeptideLength.HasValue || Length >= minimumPeptideLength.Value) && (!maximumPeptideLength.HasValue || Length <= maximumPeptideLength.Value))
{
Peptide peptide = new Peptide(this, 1, Length, -1);
yield return(peptide);
}
}
if (initiatorMethionineBehavior != InitiatorMethionineBehavior.Retain && this[0] == 'M')
{
if (Length > 1 && (!minimumPeptideLength.HasValue || Length - 1 >= minimumPeptideLength.Value) && (!maximumPeptideLength.HasValue || Length - 1 <= maximumPeptideLength.Value))
{
Peptide peptide_without_initiator_methionine = new Peptide(this, 2, Length, -1);
yield return(peptide_without_initiator_methionine);
}
}
}
}
}
