/// <summary>
/// Initiates a dynamic connection with a Thermo .raw file. Data can be "streamed" instead of loaded all at once. Use
/// GetOneBasedScanFromDynamicConnection to get data from a particular scan. Use CloseDynamicConnection to close the
/// dynamic connection after all desired data has been retrieved from the dynamic connection.
/// </summary>
private void InitiateDynamicConnection(string filePath)
{
Loaders.LoadElements();
if (dynamicConnection != null)
{
dynamicConnection.Dispose();
}
dynamicConnection = RawFileReaderAdapter.FileFactory(filePath);
if (!File.Exists(filePath))
{
throw new FileNotFoundException();
}
if (!dynamicConnection.IsOpen)
{
throw new MzLibException("Unable to access RAW file!");
}
if (dynamicConnection.IsError)
{
throw new MzLibException("Error opening RAW file!");
}
if (dynamicConnection.InAcquisition)
{
throw new MzLibException("RAW file still being acquired!");
}
dynamicConnection.SelectInstrument(Device.MS, 1);
GetMsOrdersByScanInDynamicConnection();
}
public List <Modification> get_mods(string current_directory)
{
var psiModDeserialized = Loaders.LoadPsiMod(Path.Combine(current_directory, "Mods", "PSI-MOD.obo.xml"));
Dictionary <string, int> formalChargesDictionary = Loaders.GetFormalChargesDictionary(psiModDeserialized);
Loaders.LoadElements();
List <Modification> all_known_modifications = new List <Modification>();
foreach (string filename in Directory.GetFiles(Path.Combine(current_directory, "Mods")))
{
List <Modification> new_mods = !filename.EndsWith("variable.txt") || Sweet.lollipop.methionine_oxidation ?
PtmListLoader.ReadModsFromFile(filename, formalChargesDictionary, out List <(Modification, string)> filteredModificationsWithWarnings).ToList() :
new List <Modification>(); // Empty variable modifications if not selected
if (filename.EndsWith("variable.txt"))
{
variableModifications = new_mods;
}
if (filename.EndsWith("UniprotGlycanDatabase.txt"))
{
glycan_mods = new_mods;
continue;
}
all_known_modifications.AddRange(new_mods);
}
all_known_modifications = new HashSet <Modification>(all_known_modifications).ToList();
uniprotModifications = make_modification_dictionary(all_known_modifications);
all_mods_with_mass = uniprotModifications.SelectMany(kv => kv.Value).Concat(variableModifications).ToList();
return(all_known_modifications);
}
public void Modification_read_write_into_proteinDb()
{
Loaders.LoadElements(Path.Combine(TestContext.CurrentContext.TestDirectory, "elements2.dat"));
var sampleModList = PtmListLoader.ReadModsFromFile(Path.Combine(TestContext.CurrentContext.TestDirectory, "z.txt")).ToList();
Assert.AreEqual(1, sampleModList.OfType <ModificationWithMass>().Count());
Protein protein = new Protein("MCSSSSSSSSSS", "accession", "organism", new List <Tuple <string, string> >(), new Dictionary <int, List <Modification> > {
{ 2, sampleModList.OfType <Modification>().ToList() }
}, null, "name", "full_name", false, false, new List <DatabaseReference>(), new List <SequenceVariation>(), new List <DisulfideBond>());
Assert.AreEqual(1, protein.OneBasedPossibleLocalizedModifications[2].OfType <ModificationWithMass>().Count());
ProteinDbWriter.WriteXmlDatabase(new Dictionary <string, HashSet <Tuple <int, Modification> > >(), new List <Protein> {
protein
}, Path.Combine(TestContext.CurrentContext.TestDirectory, "test_modifications_with_proteins.xml"));
List <Protein> new_proteins = ProteinDbLoader.LoadProteinXML(Path.Combine(TestContext.CurrentContext.TestDirectory, "test_modifications_with_proteins.xml"), true, DecoyType.None, new List <Modification>(), false, new List <string>(), out Dictionary <string, Modification> um);
Assert.AreEqual(1, new_proteins.Count);
Assert.AreEqual(1, new_proteins[0].OneBasedPossibleLocalizedModifications.Count);
Assert.AreEqual(1, new_proteins[0].OneBasedPossibleLocalizedModifications.SelectMany(kv => kv.Value).Count());
Assert.AreEqual("Type", new_proteins[0].OneBasedPossibleLocalizedModifications.SelectMany(kv => kv.Value).OfType <ModificationWithMass>().First().modificationType);
Assert.AreEqual("Palmitoylation of C", new_proteins[0].OneBasedPossibleLocalizedModifications[2][0].id);
Assert.AreEqual(1, new_proteins[0].OneBasedPossibleLocalizedModifications[2].OfType <ModificationWithMass>().Count());
// Check that Modifications were saved after last load
Assert.AreEqual(1, ProteinDbLoader.GetPtmListFromProteinXml(Path.Combine(TestContext.CurrentContext.TestDirectory, @"test_modifications_with_proteins.xml")).Count);
Assert.True(ProteinDbLoader.GetPtmListFromProteinXml(Path.Combine(TestContext.CurrentContext.TestDirectory, @"test_modifications_with_proteins.xml"))[0] == new_proteins[0].OneBasedPossibleLocalizedModifications.SelectMany(kv => kv.Value).First());
//But that we can still read modifications from other protein XMLs that exist
Assert.AreEqual(0, ProteinDbLoader.GetPtmListFromProteinXml(Path.Combine(TestContext.CurrentContext.TestDirectory, "xml.xml")).Count);
}
public static Dictionary <string, List <Modification> > read_mods()
{
Loaders.LoadElements(Path.Combine(TestContext.CurrentContext.TestDirectory, "elements.dat"));
List <ModificationWithLocation> all_modifications = SaveState.lollipop.get_files(SaveState.lollipop.input_files, Purpose.PtmList).SelectMany(file => PtmListLoader.ReadModsFromFile(file.complete_path)).ToList();
return(SaveState.lollipop.theoretical_database.make_modification_dictionary(all_modifications));
}
private void Window_Loaded(object sender, RoutedEventArgs e)
{
string dir = System.IO.Directory.GetCurrentDirectory();
Loaders.LoadElements(dir + @"\elements.dat");
listView.ItemsSource = DeconvolutedFeatures;
/*
* REngine R;
* REngine.SetEnvironmentVariables();
* R = REngine.GetInstance();
* R.Initialize();
* R.Evaluate("source(\"https://bioconductor.org/biocLite.R\")");
* try
* {
* R.Evaluate("biocLite(\"Prostar\")");
* }
* catch(Exception ex)
* {
*
* }
* R.Evaluate("");
* R.Dispose();
*/
}
public void DoNotWriteSameModTwiceButWriteInHeaderSinceDifferent()
{
Loaders.LoadElements(Path.Combine(TestContext.CurrentContext.TestDirectory, "elements2.dat"));
var sampleModList = PtmListLoader.ReadModsFromFile(Path.Combine(TestContext.CurrentContext.TestDirectory, "z.txt")).ToList();
Protein protein = new Protein("MCSSSSSSSSSS", "accession", "organism", new List <Tuple <string, string> >(), new Dictionary <int, List <Modification> > {
{ 2, sampleModList.OfType <Modification>().ToList() }
}, null, "name", "full_name", false, false, new List <DatabaseReference>(), new List <SequenceVariation>(), new List <DisulfideBond>());
Assert.AreEqual(1, protein.OneBasedPossibleLocalizedModifications[2].OfType <ModificationWithMass>().Count());
Dictionary <string, HashSet <Tuple <int, Modification> > > dictWithThisMod = new Dictionary <string, HashSet <Tuple <int, Modification> > >();
HashSet <Tuple <int, Modification> > value = new HashSet <Tuple <int, Modification> >();
ModificationMotif.TryGetMotif("C", out ModificationMotif motif);
ModificationWithMass newMod = new ModificationWithMass("Palmitoylation of C", "mt", motif, TerminusLocalization.Any, double.NaN, null, null);
Assert.AreNotEqual(newMod, sampleModList.First());
value.Add(new Tuple <int, Modification>(2, newMod));
dictWithThisMod.Add("accession", value);
var newModResEntries = ProteinDbWriter.WriteXmlDatabase(dictWithThisMod, new List <Protein> {
protein
}, Path.Combine(TestContext.CurrentContext.TestDirectory, "test_modifications_with_proteins2.xml"));
Assert.AreEqual(0, newModResEntries.Count);
List <Protein> new_proteins = ProteinDbLoader.LoadProteinXML(Path.Combine(TestContext.CurrentContext.TestDirectory, "test_modifications_with_proteins2.xml"), true, DecoyType.None, new List <Modification>(), false, new List <string>(), out Dictionary <string, Modification> um);
Assert.AreEqual(1, new_proteins.Count);
Assert.AreEqual(1, new_proteins[0].OneBasedPossibleLocalizedModifications.Count);
Assert.AreEqual(2, new_proteins[0].OneBasedPossibleLocalizedModifications.SelectMany(kv => kv.Value).Count());
}
/// <summary>
/// Gets UniProt ptmlist
/// </summary>
/// <param name="spritzDirectory"></param>
/// <returns></returns>
public static List <Modification> GetUniProtMods(string spritzDirectory)
{
Loaders.LoadElements();
var psiModDeserialized = Loaders.LoadPsiMod(Path.Combine(spritzDirectory, "PSI-MOD.obo.xml"));
return(Loaders.LoadUniprot(Path.Combine(spritzDirectory, "ptmlist.txt"), Loaders.GetFormalChargesDictionary(psiModDeserialized)).ToList());
}
public void FilesLoading()
{
Loaders.LoadElements(Path.Combine(TestContext.CurrentContext.TestDirectory, "elements.dat"));
Loaders.LoadUnimod(Path.Combine(TestContext.CurrentContext.TestDirectory, "unimod_tables.xml"));
Loaders.LoadPsiMod(Path.Combine(TestContext.CurrentContext.TestDirectory, "PSI-MOD.obo.xml"));
Loaders.LoadUniprot(Path.Combine(TestContext.CurrentContext.TestDirectory, "ptmlist.txt"));
}
public void Setup()
{
Loaders.LoadElements();
Assert.That(Thread.CurrentThread.CurrentCulture == CultureInfo.InvariantCulture);
Assert.That(Thread.CurrentThread.CurrentUICulture == CultureInfo.InvariantCulture);
}
public static void SetUpGlobalVariables()
{
Loaders.LoadElements();
AcceptedDatabaseFormats = new List <string> {
".fasta", ".fa", ".xml", ".msp"
};
AcceptedSpectraFormats = new List <string> {
".raw", ".mzml", ".mgf"
};
AnalyteType = "Peptide";
_InvalidAminoAcids = new char[] { 'X', 'B', 'J', 'Z', ':', '|', ';', '[', ']', '{', '}', '(', ')', '+', '-' };
ExperimentalDesignFileName = "ExperimentalDesign.tsv";
SeparationTypes = new List <string> {
{ "HPLC" }, { "CZE" }
};
SetMetaMorpheusVersion();
SetUpDataDirectory();
LoadCrosslinkers();
LoadModifications();
LoadGlycans();
LoadCustomAminoAcids();
SetUpGlobalSettings();
LoadDissociationTypes();
}
public static Dictionary <string, List <Modification> > read_mods()
{
Loaders.LoadElements();
List <Modification> all_modifications = Sweet.lollipop.get_files(Sweet.lollipop.input_files, Purpose.PtmList).SelectMany(file => PtmListLoader.ReadModsFromFile(file.complete_path, out List <(Modification, string)> filteredModificationsWithWarnings)).ToList();
return(Sweet.lollipop.theoretical_database.make_modification_dictionary(all_modifications));
}
public void load_save_unlocalized()
{
Loaders.LoadElements();
TheoreticalProteoformDatabase tpd = new TheoreticalProteoformDatabase();
List <Modification> mods = PtmListLoader.ReadModsFromFile(Path.Combine(TestContext.CurrentContext.TestDirectory, "Mods", "ptmlist.txt"), out List <(Modification, string)> filteredModificationsWithWarnings).ToList();
foreach (Modification m in mods)
{
if (!Sweet.lollipop.modification_ranks.TryGetValue(Math.Round((double)m.MonoisotopicMass, 5), out int x))
{
Sweet.lollipop.modification_ranks.Add(Math.Round((double)m.MonoisotopicMass, 5), -1);
}
}
tpd.unlocalized_lookup = tpd.make_unlocalized_lookup(mods);
tpd.load_unlocalized_names(Path.Combine(TestContext.CurrentContext.TestDirectory, "Mods", "stored_mods.modnames"));
tpd.save_unlocalized_names(Path.Combine(TestContext.CurrentContext.TestDirectory, "Mods", "fake_stored_mods.modnames"));
Modification firstAcetyl = mods.FirstOrDefault(x => x.OriginalId.StartsWith("N-acetyl"));
Assert.AreNotEqual(firstAcetyl.OriginalId, tpd.unlocalized_lookup[firstAcetyl].id);
//Test amending
mods.AddRange(PtmListLoader.ReadModsFromFile(Path.Combine(TestContext.CurrentContext.TestDirectory, "Mods", "intact_mods.txt"), out filteredModificationsWithWarnings).OfType <Modification>());
Sweet.lollipop.modification_ranks = mods.DistinctBy(m => m.MonoisotopicMass).ToDictionary(m => Math.Round((double)m.MonoisotopicMass, 5), m => - 1);
tpd.unlocalized_lookup = tpd.make_unlocalized_lookup(mods.OfType <Modification>());
tpd.amend_unlocalized_names(Path.Combine(TestContext.CurrentContext.TestDirectory, "Mods", "fake_stored_mods.modnames"));
}
/// <summary>
/// Requires at least one ProteinDatabase input file and one input file listing modifications.
/// </summary>
/// <returns></returns>
public bool ready_to_make_database(string current_directory)
{
Loaders.LoadElements();
List <InputFile> proteinDbs = Sweet.lollipop.get_files(Sweet.lollipop.input_files, Purpose.ProteinDatabase).ToList();
return(proteinDbs.Count > 0 &&
(proteinDbs.Any(file => file.extension == ".xml" && ProteinDbLoader.GetPtmListFromProteinXml(file.complete_path).Count > 0) ||
Sweet.lollipop.get_files(Sweet.lollipop.input_files, Purpose.PtmList).Count() > 0));
}
/// <summary>
/// Requires at least one ProteinDatabase input file and one input file listing modifications.
/// </summary>
/// <returns></returns>
public bool ready_to_make_database(string current_directory)
{
Loaders.LoadElements(Path.Combine(current_directory, "elements.dat"));
List <InputFile> proteinDbs = SaveState.lollipop.get_files(SaveState.lollipop.input_files, Purpose.ProteinDatabase).ToList();
return(proteinDbs.Count > 0 &&
(proteinDbs.Any(file => ProteinDbLoader.GetPtmListFromProteinXml(file.complete_path).Count > 0) ||
SaveState.lollipop.get_files(SaveState.lollipop.input_files, Purpose.PtmList).Count() > 0));
}
public static void TestPeakSplittingRight()
{
string fileToWrite = "myMzml.mzML";
string peptide = "PEPTIDE";
double intensity = 1e6;
Loaders.LoadElements(Path.Combine(TestContext.CurrentContext.TestDirectory, @"elements.dat"));
// generate mzml file
// 1 MS1 scan per peptide
MsDataScan[] scans = new MsDataScan[10];
double[] intensityMultipliers = { 1, 3, 5, 10, 5, 3, 1, 1, 3, 1 };
for (int s = 0; s < scans.Length; s++)
{
ChemicalFormula cf = new Proteomics.AminoAcidPolymer.Peptide(peptide).GetChemicalFormula();
IsotopicDistribution dist = IsotopicDistribution.GetDistribution(cf, 0.125, 1e-8);
double[] mz = dist.Masses.Select(v => v.ToMz(1)).ToArray();
double[] intensities = dist.Intensities.Select(v => v * intensity * intensityMultipliers[s]).ToArray();
// add the scan
scans[s] = new MsDataScan(massSpectrum: new MzSpectrum(mz, intensities, false), oneBasedScanNumber: s + 1, msnOrder: 1, isCentroid: true,
polarity: Polarity.Positive, retentionTime: 1.0 + s / 10.0, scanWindowRange: new MzRange(400, 1600), scanFilter: "f",
mzAnalyzer: MZAnalyzerType.Orbitrap, totalIonCurrent: intensities.Sum(), injectionTime: 1.0, noiseData: null, nativeId: "scan=" + (s + 1));
}
// write the .mzML
IO.MzML.MzmlMethods.CreateAndWriteMyMzmlWithCalibratedSpectra(new FakeMsDataFile(scans),
Path.Combine(TestContext.CurrentContext.TestDirectory, fileToWrite), false);
// set up spectra file info
SpectraFileInfo file1 = new SpectraFileInfo(Path.Combine(TestContext.CurrentContext.TestDirectory, fileToWrite), "", 0, 0, 0);
// create some PSMs
var pg = new ProteinGroup("MyProtein", "gene", "org");
Identification id1 = new Identification(file1, peptide, peptide,
new Proteomics.AminoAcidPolymer.Peptide(peptide).MonoisotopicMass, 1.3 + 0.001, 1, new List <ProteinGroup> {
pg
});
// create the FlashLFQ engine
FlashLFQEngine engine = new FlashLFQEngine(new List <Identification> {
id1
});
// run the engine
var results = engine.Run();
ChromatographicPeak peak = results.Peaks.First().Value.First();
Assert.That(peak.Apex.RetentionTime == 1.3);
Assert.That(peak.SplitRT == 1.6);
Assert.That(!peak.IsotopicEnvelopes.Any(p => p.RetentionTime > 1.6));
Assert.That(peak.IsotopicEnvelopes.Count == 6);
}
public static void Setup()
{
Environment.CurrentDirectory = TestContext.CurrentContext.TestDirectory;
Loaders.LoadElements(Path.Combine(TestContext.CurrentContext.TestDirectory, elementsLocation));
MetaMorpheusEngine.WarnHandler += WarnStatusHandler;
MetaMorpheusTask.WarnHandler += WarnStatusHandler;
EverythingRunnerEngine.FinishedAllTasksEngineHandler += SuccessfullyFinishedAllTasks;
}
public void TestUpdateElements()
{
var elementLocation = Path.Combine(TestContext.CurrentContext.TestDirectory, "lal.dat");
try
{
Loaders.LoadElements(elementLocation);
}
catch { }
Loaders.UpdateElements(elementLocation);
Assert.Throws <ArgumentException>(() => { Loaders.LoadElements(elementLocation); });
Assert.AreEqual(ValidationResult.PassedAbundanceValidation, PeriodicTable.ValidateAbundances(1e-15).ThisValidationResult);
Assert.AreEqual(ValidationResult.PassedAverageMassValidation, PeriodicTable.ValidateAverageMasses(1e-2).ThisValidationResult);
}
static void Main(string[] args)
{
Thread.CurrentThread.CurrentCulture = CultureInfo.InvariantCulture;
//Quick way to check parameters
//var apath = "G:\\Parameters\\Parameters_Topdown_ChargeExclusion_Mesh.toml";
//Parameters aparameters = AddParametersFromFile(apath);
//Initiate Element
Loaders.LoadElements();
//Loading avagine model for Deconvolution
var test = new MzSpectrumXY(new double[] { 1 }, new double[] { 1 }, true);
//Load parameters
string path = "";
if (args.Count() > 0)
{
path = args[0];
}
Parameters parameters = AddParametersFromFile(path);
//Generate Static BoxCarScan Properties.
BoxCarScan.BuildStaticBoxString(parameters);
//Start the task
if (parameters.GeneralSetting.TestMod)
{
Console.WriteLine("--------------In Test Mod--------------");
new CustomScansTandemByArrival(parameters).DoJob(5 * 60000);
}
else
{
Console.WriteLine("--------------In Gather Mod--------------");
var dataReceiver = new DataReceiver(parameters);
dataReceiver.InstrumentAccess = Connection.GetFirstInstrument();
dataReceiver.ScanContainer = dataReceiver.InstrumentAccess.GetMsScanContainer(0);
dataReceiver.DetectStartSignal();
dataReceiver.DoJob();
dataReceiver.ScanContainer = null;
dataReceiver.InstrumentAccess = null;
}
Console.WriteLine("Task Finished...");
}
public void FilesLoading()
{
Loaders.LoadElements(Path.Combine(TestContext.CurrentContext.TestDirectory, "elements2.dat"));
var unimodMods = Loaders.LoadUnimod(Path.Combine(TestContext.CurrentContext.TestDirectory, "unimod_tables2.xml")).ToList();
Assert.AreEqual(2, (unimodMods.First(b => b.id.Equals("HexNAc(2) on N at Any")) as ModificationWithMass).neutralLosses.Count);
var psiModDeserialized = Loaders.LoadPsiMod(Path.Combine(TestContext.CurrentContext.TestDirectory, "PSI-MOD.obo2.xml"));
// N6,N6,N6-trimethyllysine
var trimethylLysine = psiModDeserialized.Items.OfType <UsefulProteomicsDatabases.Generated.oboTerm>().First(b => b.id.Equals("MOD:00083"));
Assert.AreEqual("1+", trimethylLysine.xref_analog.First(b => b.dbname.Equals("FormalCharge")).name);
// Phosphoserine
Assert.IsFalse(psiModDeserialized.Items.OfType <UsefulProteomicsDatabases.Generated.oboTerm>().First(b => b.id.Equals("MOD:00046")).xref_analog.Any(b => b.dbname.Equals("FormalCharge")));
Dictionary <string, int> formalChargesDictionary = Loaders.GetFormalChargesDictionary(psiModDeserialized);
var uniprotPtms = Loaders.LoadUniprot(Path.Combine(TestContext.CurrentContext.TestDirectory, "ptmlist2.txt"), formalChargesDictionary).ToList();
using (StreamWriter w = new StreamWriter(Path.Combine(TestContext.CurrentContext.TestDirectory, "test.txt")))
{
foreach (var nice in uniprotPtms)
{
w.WriteLine(nice.ToString());
w.WriteLine("//");
}
foreach (var nice in unimodMods)
{
w.WriteLine(nice.ToString());
w.WriteLine("//");
}
}
var sampleModList = PtmListLoader.ReadModsFromFile(Path.Combine(TestContext.CurrentContext.TestDirectory, "test.txt")).ToList();
string stringRepresentation = "ID (3R)-3-hydroxyarginine\r\nMT UniProt\r\nPP Anywhere.\r\nDR RESID; AA0601\r\nDR PSI-MOD; MOD:01956\r\nDR UniProt; PTM-0476\r\nTG R\r\nMM 15.994915\r\nCF O";
Assert.AreEqual(stringRepresentation, sampleModList.First().ToString());
// N,N,N-trimethylalanine
var thisMod = sampleModList.First(b => b.id.Equals(@"N,N,N-trimethylalanine")) as ModificationWithMass;
Assert.IsTrue(thisMod.monoisotopicMass > 42);
Assert.IsTrue(thisMod.monoisotopicMass < 43);
}
protected override void InitiateDynamicConnection()
{
if (!File.Exists(FilePath))
{
throw new FileNotFoundException();
}
if (Path.GetExtension(FilePath).ToUpper() != ".MGF")
{
throw new InvalidDataException();
}
Loaders.LoadElements();
reader = new StreamReader(FilePath);
BuildIndex();
}
public ProteoformRelation(Proteoform pf1, Proteoform pf2, ProteoformComparison relation_type, double delta_mass, string current_directory)
{
connected_proteoforms[0] = pf1;
connected_proteoforms[1] = pf2;
RelationType = relation_type;
DeltaMass = delta_mass;
InstanceId = instanceCounter;
lock (SaveState.lollipop) instanceCounter += 1; //Not thread safe
if (CH2 == null || HPO3 == null)
{
Loaders.LoadElements(Path.Combine(current_directory, "elements.dat"));
CH2 = ChemicalFormula.ParseFormula("C1 H2");
HPO3 = ChemicalFormula.ParseFormula("H1 O3 P1");
}
if (SaveState.lollipop.neucode_labeled)
{
lysine_count = pf1.lysine_count;
}
if ((relation_type == ProteoformComparison.ExperimentalTheoretical || relation_type == ProteoformComparison.ExperimentalDecoy) &&
SaveState.lollipop.theoretical_database.possible_ptmset_dictionary.TryGetValue(Math.Round(delta_mass, 1), out List <PtmSet> candidate_sets) &&
pf2 as TheoreticalProteoform != null)
{
TheoreticalProteoform t = pf2 as TheoreticalProteoform;
double mass_tolerance = t.modified_mass / 1000000 * (double)SaveState.lollipop.mass_tolerance;
List <PtmSet> narrower_range_of_candidates = candidate_sets.Where(s => Math.Abs(s.mass - delta_mass) < 0.05).ToList();
candidate_ptmset = t.generate_possible_added_ptmsets(narrower_range_of_candidates, delta_mass, mass_tolerance, SaveState.lollipop.theoretical_database.all_mods_with_mass, t, t.sequence, SaveState.lollipop.mod_rank_first_quartile)
.OrderBy(x => x.ptm_rank_sum + Math.Abs(Math.Abs(x.mass) - Math.Abs(delta_mass)) * 10E-6) // major score: delta rank; tie breaker: deltaM, where it's always less than 1
.FirstOrDefault();
}
// Start the model (0 Da) at the mass defect of CH2 or HPO3 itself, allowing the peak width tolerance on either side
double half_peak_width = RelationType == ProteoformComparison.ExperimentalTheoretical || RelationType == ProteoformComparison.ExperimentalDecoy ?
SaveState.lollipop.peak_width_base_et / 2 :
SaveState.lollipop.peak_width_base_ee / 2;
double low_decimal_bound = half_peak_width + ((CH2.MonoisotopicMass - Math.Truncate(CH2.MonoisotopicMass)) / CH2.MonoisotopicMass) * (Math.Abs(delta_mass) <= CH2.MonoisotopicMass ? CH2.MonoisotopicMass : Math.Abs(delta_mass));
double high_decimal_bound = 1 - half_peak_width + ((HPO3.MonoisotopicMass - Math.Ceiling(HPO3.MonoisotopicMass)) / HPO3.MonoisotopicMass) * (Math.Abs(delta_mass) <= HPO3.MonoisotopicMass ? HPO3.MonoisotopicMass : Math.Abs(delta_mass));
double delta_mass_decimal = Math.Abs(delta_mass - Math.Truncate(delta_mass));
outside_no_mans_land = delta_mass_decimal <= low_decimal_bound || delta_mass_decimal >= high_decimal_bound ||
high_decimal_bound <= low_decimal_bound;
}
public void TestMgf()
{
// Get temp path for writing the test MGF
var tempFilePath = Path.GetTempPath();
var testRawFile = Path.Combine(AppDomain.CurrentDomain.BaseDirectory, @"small.RAW");
var parseInput = new ParseInput(testRawFile, tempFilePath, null, OutputFormat.MGF);
RawFileParser.Parse(parseInput);
// Do this for the mzLib library issue
var tempFileName = Path.GetTempPath() + "elements.dat";
Loaders.LoadElements(tempFileName);
var mgfData = Mgf.LoadAllStaticData(Path.Combine(tempFilePath, "small.mgf"));
Assert.AreEqual(34, mgfData.NumSpectra);
}
public static void ProteaseModTest()
{
Loaders.LoadElements();
string subFolder = Path.Combine(TestContext.CurrentContext.TestDirectory, @"DigestionTest");
Directory.CreateDirectory(subFolder);
string databasePath1 = Path.Combine(TestContext.CurrentContext.TestDirectory, "DatabaseTests", "ProteaseModTest.fasta");
var protDic = ProteaseDictionary.LoadProteaseDictionary(Path.Combine(GlobalVariables.DataDir, @"ProteolyticDigestion", @"proteases.tsv"), GlobalVariables.ProteaseMods);
DigestionParams param = new DigestionParams(protease: "CNBr", maxMissedCleavages: 0);
var proteinList = ProteinDbLoader.LoadProteinFasta(databasePath1, true, DecoyType.None, false, out List <string> errors);
var protein = proteinList[0];
var peptides = protein.Digest(param, new List <Modification>(), new List <Modification>()).ToList();
Assert.AreEqual(2, peptides.Count());
Assert.AreNotEqual(peptides[0].FullSequence, peptides[1].FullSequence);
Assert.AreEqual(882.39707781799996, peptides[0].MonoisotopicMass);
Assert.AreEqual(930.400449121, peptides[1].MonoisotopicMass);
}
public MainWindow()
{
InitializeComponent();
dataGridPeptideFiles.DataContext = DataFilesObservableCollection;
dataGridDatabaseFiles.DataContext = DatabasesObservableCollection;
DisplayedSamplesDataGrid.DataContext = FilesToDisplayObservableCollection;
HiddenSamplesDataGrid.DataContext = FilesToHideObservableCollection;
DisplayAnalyzedFilesDataGrid.DataContext = DataFilesObservableCollection;
HalfLifeHistogramPlot.Configure(enableScrollWheelZoom: false);
PrecisionPlot.Configure(enableScrollWheelZoom: false);
HalfLifeComparisonPlot.Configure(enableScrollWheelZoom: false);
RatioComparisonPlot.Configure(enableScrollWheelZoom: false);
peptideRadioButton.IsChecked = true;
proteinSpecificRadioButton.IsChecked = DisplayProteinInSpecificTable;
DisplayPeptidesView = CollectionViewSource.GetDefaultView(PeptidesToDisplay);
DisplayPeptidesDataGrid.DataContext = DisplayPeptidesView;
Loaders.LoadElements();
PopulateChoices();
}
static void Main(string[] args)
{
List <string> files = args.Where(f => File.Exists(f) & (Path.GetExtension(f) == ".xml" || Path.GetExtension(f) == ".xml.gz")).ToList();
if (files.Count < 2)
{
Console.WriteLine("Please enter at least two protein .xml or .xml.gz databases.");
return;
}
// check that file path is valid
string timestamp = DateTime.Now.Year.ToString("0000") + "-" + DateTime.Now.Month.ToString("00") + "-" + DateTime.Now.Day.ToString("00") + "-" + DateTime.Now.Hour.ToString("00") + "-" + DateTime.Now.Minute.ToString("00") + "-" + DateTime.Now.Second.ToString("00");
string outpath = Path.Combine(AppDomain.CurrentDomain.BaseDirectory, "merged_database_" + timestamp + ".xml");
// merge databases
Loaders.LoadElements(Path.Combine(AppDomain.CurrentDomain.BaseDirectory, "elements.dat"));
List <Protein> merged = ProteinDbLoader.merge_proteins(files.SelectMany(f => ProteinDbLoader.LoadProteinXML(f, false, new List <Modification>(), false, new List <string>(), out Dictionary <string, Modification> un))).ToList();
ProteinDbWriter.WriteXmlDatabase(new Dictionary <string, HashSet <Tuple <int, Modification> > >(), merged, outpath);
}
/// <summary>
/// Initiates the dynamic connection with the .mzML file.
/// </summary>
protected override void InitiateDynamicConnection()
{
if (!File.Exists(FilePath))
{
throw new FileNotFoundException();
}
if (Path.GetExtension(FilePath).ToUpper() != ".MZML")
{
throw new InvalidDataException();
}
Loaders.LoadElements();
reader = new StreamReader(FilePath);
ScanNumberToByteOffset = new Dictionary <int, long>();
NativeIdToScanNumber = new Dictionary <string, int>();
FindOrCreateIndex();
}
private static void BenchmarkDatabaseLoadWrite()
{
Console.WriteLine("Starting benchmark BenchmarkDatabaseLoadWrite");
Stopwatch stopWatch = new Stopwatch();
Loaders.LoadElements("elements2.dat");
IEnumerable <Modification> ya = PtmListLoader.ReadModsFromFile(@"ptmlist.txt").ToList();
stopWatch.Restart();
var a = ProteinDbLoader.LoadProteinXML(@"yeast_160126.xml.gz", true, ya, false, null, out Dictionary <string, Modification> um);
ProteinDbWriter.WriteXmlDatabase(new Dictionary <string, HashSet <System.Tuple <int, ModificationWithMass> > >(), a.Where(p => !p.IsDecoy).ToList(), "rewrite_yeast.xml");
var b = ProteinDbLoader.LoadProteinXML(@"rewrite_yeast.xml", true, ya, false, null, out um);
stopWatch.Stop();
Console.WriteLine("Time for getting formulas: " + stopWatch.Elapsed);
Console.WriteLine("Benchmark BenchmarkDatabaseLoadWrite finished");
}
/// <summary>
/// Initiates a dynamic connection with a Thermo .raw file. Data can be "streamed" instead of loaded all at once. Use
/// GetOneBasedScanFromDynamicConnection to get data from a particular scan. Use CloseDynamicConnection to close the
/// dynamic connection after all desired data has been retrieved from the dynamic connection.
/// </summary>
protected override void InitiateDynamicConnection()
{
if (!File.Exists(FilePath))
{
throw new FileNotFoundException();
}
if (Path.GetExtension(FilePath).ToUpper() != ".RAW")
{
throw new InvalidDataException();
}
Loaders.LoadElements();
if (dynamicConnection != null)
{
dynamicConnection.Dispose();
}
dynamicConnection = RawFileReaderAdapter.FileFactory(FilePath);
if (!dynamicConnection.IsOpen)
{
throw new MzLibException("Unable to access RAW file!");
}
if (dynamicConnection.IsError)
{
throw new MzLibException("Error opening RAW file!");
}
if (dynamicConnection.InAcquisition)
{
throw new MzLibException("RAW file still being acquired!");
}
dynamicConnection.SelectInstrument(Device.MS, 1);
GetMsOrdersByScanInDynamicConnection();
}
public void DoNotWriteSameModTwiceAndDoNotWriteInHeaderSinceDifferent()
{
Loaders.LoadElements();
var sampleModList = PtmListLoader.ReadModsFromFile(Path.Combine(TestContext.CurrentContext.TestDirectory, "DatabaseTests", "z.txt"), out var errors).ToList();
Protein protein = new Protein("MCSSSSSSSSSS", "accession", "organism", new List <Tuple <string, string> >(), new Dictionary <int, List <Modification> > {
{ 2, sampleModList.OfType <Modification>().ToList() }
}, null, "name", "full_name", false, false, new List <DatabaseReference>(), new List <SequenceVariation>(), disulfideBonds: new List <DisulfideBond>());
Assert.AreEqual(1, protein.OneBasedPossibleLocalizedModifications[2].OfType <Modification>().Count());
Dictionary <string, HashSet <Tuple <int, Modification> > > dictWithThisMod = new Dictionary <string, HashSet <Tuple <int, Modification> > >();
HashSet <Tuple <int, Modification> > value = new HashSet <Tuple <int, Modification> >();
var modReadFromFile = sampleModList.First() as Modification;
ModificationMotif.TryGetMotif("C", out ModificationMotif motif);
Modification newMod = new Modification(_originalId: "Palmitoylation of C", _modificationType: "Type", _target: motif, _locationRestriction: "Anywhere.", _chemicalFormula: modReadFromFile.ChemicalFormula, _monoisotopicMass: modReadFromFile.MonoisotopicMass, _featureType: "MOD_RES", _fileOrigin: "E:\\GitClones\\mzLib\\Test\\bin\\x64\\Debug\\DatabaseTests\\z.txt");
Assert.IsTrue(newMod.Equals(sampleModList.First()));
Assert.AreEqual(newMod, sampleModList.First());
Assert.AreEqual(sampleModList.First(), newMod);
value.Add(new Tuple <int, Modification>(2, newMod));
dictWithThisMod.Add("accession", value);
var newModResEntries = ProteinDbWriter.WriteXmlDatabase(dictWithThisMod, new List <Protein> {
protein
}, Path.Combine(TestContext.CurrentContext.TestDirectory, "test_modifications_with_proteins3.xml"));
Assert.AreEqual(0, newModResEntries.Count);
List <Protein> new_proteins = ProteinDbLoader.LoadProteinXML(Path.Combine(TestContext.CurrentContext.TestDirectory, "test_modifications_with_proteins3.xml"),
true, DecoyType.None, new List <Modification>(), false, new List <string>(), out Dictionary <string, Modification> um);
Assert.AreEqual(1, new_proteins.Count);
Assert.AreEqual(1, new_proteins[0].OneBasedPossibleLocalizedModifications.Count);
Assert.AreEqual(1, new_proteins[0].OneBasedPossibleLocalizedModifications.SelectMany(kv => kv.Value).Count());
}
public static Mgf LoadAllStaticData(string filePath, FilteringParams filterParams = null)
{
if (!File.Exists(filePath))
{
throw new FileNotFoundException();
}
Loaders.LoadElements();
List <MsDataScan> scans = new List <MsDataScan>();
HashSet <int> checkForDuplicateScans = new HashSet <int>();
using (FileStream fs = new FileStream(filePath, FileMode.Open, FileAccess.Read, FileShare.Read))
{
using (BufferedStream bs = new BufferedStream(fs))
{
using (StreamReader sr = new StreamReader(bs))
{
while (sr.Peek() > 0)
{
string line = sr.ReadLine();
if (line != "BEGIN IONS")
{
continue;
}
var scan = GetNextMsDataOneBasedScanFromConnection(sr, checkForDuplicateScans, filterParams);
scans.Add(scan);
}
}
}
}
SourceFile sourceFile = new SourceFile("no nativeID format", "mgf format", null, null, null);
return(new Mgf(scans.OrderBy(x => x.OneBasedScanNumber).ToArray(), sourceFile));
}
