private IEnumerable <AnnotationAndOffset> GetAnnotationsAndOffsets(FastaDatabase database, out long estimatedProteins, CancellationToken?cancellationToken = null)
{
var indexedDb = new IndexedDatabase(database);
indexedDb.Read();
estimatedProteins = indexedDb.EstimateTotalPeptides(SearchMode, MinSequenceLength, MaxSequenceLength, MaxNumNTermCleavages, MaxNumCTermCleavages);
IEnumerable <AnnotationAndOffset> annotationsAndOffsets;
if (SearchMode == InternalCleavageType.MultipleInternalCleavages)
{
//annotationsAndOffsets = indexedDb.AnnotationsAndOffsetsNoEnzyme(MinSequenceLength, MaxSequenceLength);
annotationsAndOffsets = indexedDb.AnnotationsAndOffsetsNoEnzymeParallel(MinSequenceLength, MaxSequenceLength, MaxNumThreads, cancellationToken);
}
else if (SearchMode == InternalCleavageType.NoInternalCleavage)
{
annotationsAndOffsets = indexedDb.IntactSequenceAnnotationsAndOffsets(MinSequenceLength, MaxSequenceLength, MaxNumCTermCleavages);
}
else
{
annotationsAndOffsets = indexedDb
.SequenceAnnotationsAndOffsetsWithNtermOrCtermCleavageNoLargerThan(
MinSequenceLength, MaxSequenceLength, MaxNumNTermCleavages, MaxNumCTermCleavages);
}
return(annotationsAndOffsets);
}
[TestCase(6, @"TEST_FOLDER\MSPathFinderT\ID_004530_B63BD900.fasta", 8898)] // 6MB
//[TestCase(15, @"TEST_FOLDER\MSPathFinderT\ID_004208_295531A4.fasta", 6334)] // 15MB
public void TestSequenceEnumerationIntact(double size, string dbFile, int expected)
{
var methodName = MethodBase.GetCurrentMethod().Name;
Utils.ShowStarting(methodName, dbFile);
var fastaFile = Utils.GetTestFile(methodName, dbFile.Replace("TEST_FOLDER", Utils.DEFAULT_TEST_FILE_FOLDER));
var sw = new System.Diagnostics.Stopwatch();
sw.Start();
const int numCTermCleavages = 0;
var db = new FastaDatabase(fastaFile.FullName);
var indexedDb = new IndexedDatabase(db);
var numSequences = 0L;
var timeDB = sw.Elapsed;
Console.WriteLine("Read DB in " + timeDB.TotalSeconds + " Seconds");
var estimatedAnnOff = indexedDb.EstimateTotalPeptides(2, 21, 300, 1, numCTermCleavages);
var timeEstimate = sw.Elapsed;
Console.WriteLine("Read Estimate in " + (timeEstimate - timeDB).TotalSeconds + " Seconds");
Console.WriteLine("Estimated results: " + estimatedAnnOff);
var annotationsAndOffsets = indexedDb.IntactSequenceAnnotationsAndOffsets(21, 300, numCTermCleavages);
var timeGetAnn = sw.Elapsed;
Console.WriteLine("Read Annotations in " + (timeGetAnn - timeEstimate).TotalSeconds + " Seconds");
/*/Parallel.ForEach(
* annotationsAndOffsets,
* // new ParallelOptions { MaxDegreeOfParallelism = 2},
* annotationAndOffset =>
* {
* Interlocked.Increment(ref numSequences);
* //++numSequences;
* }
* );/**/
//using (var ofstream = new FileStream(Path.Combine(@"F:\InformedProteomicsTestFiles", Path.GetFileNameWithoutExtension(fastaFile) + "_par.txt"), FileMode.Create))
//using (var fout = new StreamWriter(ofstream))
//{
// foreach (var annOff in annotationsAndOffsets)
// {
// numSequences++;
// fout.WriteLine(annOff.Annotation);
// }
//}
numSequences = annotationsAndOffsets.Count();
var timeParForEach = sw.Elapsed;
Console.WriteLine("Parallel ForEach in " + (timeParForEach - timeGetAnn).TotalSeconds + " Seconds");
Console.WriteLine("NumPeptides: {0}", numSequences);
sw.Stop();
Console.WriteLine(@"{0:f4} sec", sw.Elapsed.TotalSeconds);
//Assert.AreEqual(188961836, numSequences);
Assert.AreEqual(expected, numSequences);
}
public void TestCountingProteoformsCloseToNTermOrCTerm()
{
var methodName = MethodBase.GetCurrentMethod().Name;
TestUtils.ShowStarting(methodName);
const int minSequenceLength = 21; // 21
const int maxSequenceLength = 300; // 300
const int maxNumNTermCleavages = 1;
const int maxNumCTermCleavages = 0;
var sw = new System.Diagnostics.Stopwatch();
sw.Start();
//const string dbFile = @"C:\cygwin\home\kims336\Data\TopDownQCShew\database\ID_002216_235ACCEA.fasta";
const string dbFile = @"\\proto-2\UnitTest_Files\InformedProteomics_TestFiles\MSPathFinderT\Short.fasta";
if (!File.Exists(dbFile))
{
Assert.Ignore(@"Skipping test {0} since file not found: {1}", methodName, dbFile);
}
var db = new FastaDatabase(dbFile);
var indexedDb = new IndexedDatabase(db);
var both = 0L;
var nTermOnly = 0L;
var cTermOnly = 0L;
foreach (
var annotationAndOffset in
indexedDb.IntactSequenceAnnotationsAndOffsets(minSequenceLength, int.MaxValue,
maxNumCTermCleavages))
{
// numCTermCleavages <= maxNumCTermCleavages
var annotation = annotationAndOffset.Annotation;
var length = (annotation.Length - 4);
var numNTermCleavage = 0;
int cleavedLength;
while ((cleavedLength = length - numNTermCleavage) >= minSequenceLength)
{
if (cleavedLength <= maxSequenceLength)
{
if (numNTermCleavage <= maxNumNTermCleavages)
{
++both;
}
else
{
++cTermOnly;
}
var anno = numNTermCleavage == 0
? annotation
: string.Format("{0}.{1}", annotation[1 + numNTermCleavage], annotation.Substring(2 + numNTermCleavage));
Console.WriteLine(anno);
}
++numNTermCleavage;
}
}
foreach (
var annotationAndOffset in
indexedDb.IntactSequenceAnnotationsAndOffsetsWithCTermCleavagesLargerThan(minSequenceLength, int.MaxValue,
maxNumCTermCleavages))
{
// numCTermCleavages > maxNumCTermCleavages
var annotation = annotationAndOffset.Annotation;
var length = (annotation.Length - 4);
for (var numNTermCleavage = 0; numNTermCleavage <= maxNumNTermCleavages; numNTermCleavage++)
{
var cleavedLength = length - numNTermCleavage;
if (cleavedLength >= minSequenceLength && cleavedLength <= maxSequenceLength)
{
++nTermOnly;
var anno = numNTermCleavage == 0
? annotation
: string.Format("{0}.{1}", annotation[1 + numNTermCleavage], annotation.Substring(2 + numNTermCleavage));
Console.WriteLine(anno);
}
}
}
Console.WriteLine("Both: {0}", both);
Console.WriteLine("N-term only: {0}", nTermOnly);
Console.WriteLine("C-term only: {0}", cTermOnly);
Console.WriteLine("All: {0}", both + nTermOnly + cTermOnly);
sw.Stop();
Console.WriteLine(@"{0:f4} sec", sw.Elapsed.TotalSeconds);
}
} // true: target and decoy, false: target only, null: decoy only
public void QuickId()
{
const string rawFilePath = @"H:\Research\QCShew_TopDown\Production\QC_Shew_Intact_26Sep14_Bane_C2Column3.raw";
const string fastaFilePath = @"H:\Research\QCShew_TopDown\Production\ID_002216_235ACCEA.fasta";
const string modFilePath = @"H:\Research\QCShew_TopDown\Production\Mods.txt";
const int numBits = 29; // max error: 4ppm
const int minCharge = 1;
const int maxCharge = 20;
var tolerance = new Tolerance(10);
const double corrThreshold = 0.7;
var comparer = new MzComparerWithBinning(numBits);
const double minFragmentMass = 200.0;
const double maxFragmentMass = 50000.0;
var minFragMassBin = comparer.GetBinNumber(minFragmentMass);
var maxFragMassBin = comparer.GetBinNumber(maxFragmentMass);
var aminoAcidSet = new AminoAcidSet(modFilePath);
var run = PbfLcMsRun.GetLcMsRun(rawFilePath);
var ms2ScanNumArr = run.GetScanNumbers(2).ToArray();
var sw = new Stopwatch();
sw.Start();
Console.Write("Building Spectrum Arrays...");
var massVectors = new BitArray[maxFragMassBin - minFragMassBin + 1];
for (var i = minFragMassBin; i <= maxFragMassBin; i++)
{
massVectors[i - minFragMassBin] = new BitArray(run.MaxLcScan + 1);
}
foreach (var ms2ScanNum in ms2ScanNumArr)
{
var productSpec = run.GetSpectrum(ms2ScanNum) as ProductSpectrum;
if (productSpec == null)
{
continue;
}
var deconvolutedPeaks = Deconvoluter.GetDeconvolutedPeaks(productSpec.Peaks, minCharge, maxCharge, 2, 1.1, tolerance, corrThreshold);
if (deconvolutedPeaks == null)
{
continue;
}
foreach (var p in deconvolutedPeaks)
{
var mass = p.Mass;
var deltaMass = tolerance.GetToleranceAsDa(mass, 1);
var minMass = mass - deltaMass;
var maxMass = mass + deltaMass;
var minBinNum = comparer.GetBinNumber(minMass);
var maxBinNum = comparer.GetBinNumber(maxMass);
for (var binNum = minBinNum; binNum <= maxBinNum; binNum++)
{
if (binNum >= minFragMassBin && binNum <= maxFragMassBin)
{
massVectors[binNum - minFragMassBin][ms2ScanNum] = true;
}
}
}
}
sw.Stop();
Console.WriteLine(@"{0:f1} sec.", sw.Elapsed.TotalSeconds);
sw.Reset();
sw.Start();
var fastaDb = new FastaDatabase(fastaFilePath);
fastaDb.Read();
var indexedDb = new IndexedDatabase(fastaDb);
var numProteins = 0;
var intactProteinAnnotationAndOffsets =
indexedDb.IntactSequenceAnnotationsAndOffsets(0, int.MaxValue);
var bestProtein = new string[run.MaxLcScan + 1];
var bestScore = new int[run.MaxLcScan + 1];
foreach (var annotationAndOffset in intactProteinAnnotationAndOffsets)
{
if (++numProteins % 10 == 0)
{
Console.WriteLine(@"Processing, {0} proteins done, {1:f1} sec elapsed",
numProteins,
sw.Elapsed.TotalSeconds);
}
var annotation = annotationAndOffset.Annotation;
var offset = annotationAndOffset.Offset;
var protSequence = annotation.Substring(2, annotation.Length - 4);
// suffix
var seqGraph = SequenceGraph.CreateGraph(aminoAcidSet, AminoAcid.ProteinNTerm, protSequence,
AminoAcid.ProteinCTerm);
if (seqGraph == null)
{
continue;
}
for (var numNTermCleavage = 0; numNTermCleavage <= 1; numNTermCleavage++)
{
if (numNTermCleavage > 0)
{
seqGraph.CleaveNTerm();
}
var allCompositions = seqGraph.GetAllFragmentNodeCompositions();
var scoreArr = new int[run.MaxLcScan + 1];
foreach (var fragComp in allCompositions)
{
var suffixMass = fragComp.Mass + BaseIonType.Y.OffsetComposition.Mass;
var binNum = comparer.GetBinNumber(suffixMass);
if (binNum < minFragMassBin || binNum > maxFragMassBin)
{
continue;
}
var vector = massVectors[binNum - minFragMassBin];
foreach (var ms2ScanNum in ms2ScanNumArr)
{
if (vector[ms2ScanNum])
{
++scoreArr[ms2ScanNum];
}
}
}
foreach (var ms2ScanNum in ms2ScanNumArr)
{
if (scoreArr[ms2ScanNum] > bestScore[ms2ScanNum])
{
bestScore[ms2ScanNum] = scoreArr[ms2ScanNum];
var proteinName = fastaDb.GetProteinName(offset);
bestProtein[ms2ScanNum] = proteinName + (numNTermCleavage == 1 ? "'" : "");
}
}
}
// prefix
}
Console.WriteLine("ScanNum\tBestProtein\tScore");
foreach (var ms2ScanNum in ms2ScanNumArr)
{
Console.WriteLine("{0}\t{1}\t{2}", ms2ScanNum, bestScore[ms2ScanNum], bestProtein[ms2ScanNum] ?? "");
}
}
public void TestCountingProteoformsCloseToNTermOrCTerm()
{
var methodName = MethodBase.GetCurrentMethod().Name;
Utils.ShowStarting(methodName);
const int minSequenceLength = 21; // 21
const int maxSequenceLength = 300; // 300
const int maxNumNTermCleavages = 1;
const int maxNumCTermCleavages = 0;
var sw = new System.Diagnostics.Stopwatch();
sw.Start();
var fastaFile = Utils.GetTestFile(methodName, Path.Combine(Utils.DEFAULT_TEST_FILE_FOLDER, @"MSPathFinderT\Short.fasta"));
var db = new FastaDatabase(fastaFile.FullName);
var indexedDb = new IndexedDatabase(db);
var both = 0L;
var nTermOnly = 0L;
var cTermOnly = 0L;
var displayedResults = 0;
foreach (
var annotationAndOffset in
indexedDb.IntactSequenceAnnotationsAndOffsets(minSequenceLength, int.MaxValue,
maxNumCTermCleavages))
{
// numCTermCleavages <= maxNumCTermCleavages
var annotation = annotationAndOffset.Annotation;
var length = (annotation.Length - 4);
var numNTermCleavage = 0;
int cleavedLength;
while ((cleavedLength = length - numNTermCleavage) >= minSequenceLength)
{
if (cleavedLength <= maxSequenceLength)
{
if (numNTermCleavage <= maxNumNTermCleavages)
{
++both;
}
else
{
++cTermOnly;
}
var anno = numNTermCleavage == 0
? annotation
: string.Format("{0}.{1}", annotation[1 + numNTermCleavage], annotation.Substring(2 + numNTermCleavage));
if (displayedResults < 20)
{
Console.WriteLine(anno);
}
displayedResults++;
}
++numNTermCleavage;
}
}
displayedResults = 0;
foreach (
var annotationAndOffset in
indexedDb.IntactSequenceAnnotationsAndOffsetsWithCTermCleavagesLargerThan(minSequenceLength, int.MaxValue,
maxNumCTermCleavages))
{
// numCTermCleavages > maxNumCTermCleavages
var annotation = annotationAndOffset.Annotation;
var length = (annotation.Length - 4);
for (var numNTermCleavage = 0; numNTermCleavage <= maxNumNTermCleavages; numNTermCleavage++)
{
var cleavedLength = length - numNTermCleavage;
if (cleavedLength >= minSequenceLength && cleavedLength <= maxSequenceLength)
{
++nTermOnly;
var anno = numNTermCleavage == 0
? annotation
: string.Format("{0}.{1}", annotation[1 + numNTermCleavage], annotation.Substring(2 + numNTermCleavage));
if (displayedResults < 20)
{
Console.WriteLine(anno);
}
displayedResults++;
}
}
}
Console.WriteLine("Both: {0}", both);
Console.WriteLine("N-term only: {0}", nTermOnly);
Console.WriteLine("C-term only: {0}", cTermOnly);
Console.WriteLine("All: {0}", both + nTermOnly + cTermOnly);
sw.Stop();
Console.WriteLine(@"{0:f4} sec", sw.Elapsed.TotalSeconds);
}
public void TestTopDownScoringForAllXics()
{
var methodName = MethodBase.GetCurrentMethod().Name;
Utils.ShowStarting(methodName);
// Search parameters
const int numNTermCleavages = 1; // 30
const int minLength = 7;
const int maxLength = 1000;
//const int minCharge = 5; // 3
//const int maxCharge = 15; // 67
const int numMaxModsPerProtein = 0; // 6
var precursorTolerance = new Tolerance(10);
const string dbFilePath = @"..\..\..\TestFiles\sprot.Ecoli.2012_07.fasta";
//const string dbFilePath = @"..\..\..\TestFiles\sprot.Ecoli.2012_07.icdecoy.KR.fasta";
//const string dbFilePath = @"..\..\..\TestFiles\H_sapiens_Uniprot_SPROT_2013-05-01_withContam.fasta";
// const string dbFilePath =
// @"C:\cygwin\home\kims336\Data\TopDown\ID_003558_56D73071.fasta";
var sw = new System.Diagnostics.Stopwatch();
sw.Start();
Console.Write("Reading raw file...");
const string specFilePath = @"C:\workspace\TopDown\E_coli_iscU_60_mock.raw";
var run = InMemoryLcMsRun.GetLcMsRun(specFilePath);
sw.Stop();
Console.WriteLine(@"Elapsed Time: {0:f4} sec", sw.Elapsed.TotalSeconds);
// Configure amino acid set
// var pyroGluQ = new SearchModification(Modification.PyroGluQ, 'Q', SequenceLocation.ProteinNTerm, false);
var dehydro = new SearchModification(Modification.PyroGluQ, 'C', SequenceLocation.Everywhere, false);
var cysteinylC = new SearchModification(Modification.Cysteinyl, 'C', SequenceLocation.Everywhere, false);
var glutathioneC = new SearchModification(Modification.Glutathione, 'C', SequenceLocation.Everywhere, false);
// var oxM = new SearchModification(Modification.Oxidation, 'M', SequenceLocation.Everywhere, false);
var searchModifications = new List <SearchModification>
{
//pyroGluQ,
dehydro,
cysteinylC,
glutathioneC,
//oxM
};
var aaSet = new AminoAcidSet(searchModifications, numMaxModsPerProtein);
var targetDb = new FastaDatabase(dbFilePath);
// targetDb.CreateDecoyDatabase(Enzyme.Trypsin);
// System.Environment.Exit(1);
var indexedDb = new IndexedDatabase(targetDb);
var numProteins = 0;
long totalProtCompositions = 0;
//long numXics = 0;
TopDownScorer.MaxCharge = 25;
TopDownScorer.MinCharge = 8;
sw.Reset();
sw.Start();
Console.WriteLine("Generating XICs...");
foreach (var protAnnotationAndOffset in indexedDb.IntactSequenceAnnotationsAndOffsets(minLength, maxLength))
{
++numProteins;
//if (numProteins > 2000) break;
if (numProteins % 1000 == 0)
{
Console.WriteLine("Processed {0} proteins", numProteins);
}
//Console.WriteLine(protAnnotation);
var seqGraph = SequenceGraph.CreateGraph(aaSet, protAnnotationAndOffset.Annotation);
//Console.WriteLine(seqGraph.GetSequenceCompositions()[0]);
if (seqGraph == null)
{
continue;
}
for (var nTermCleavages = 0; nTermCleavages <= numNTermCleavages; nTermCleavages++)
{
if (nTermCleavages > 0)
{
seqGraph.CleaveNTerm();
}
var protCompositions = seqGraph.GetSequenceCompositions();
foreach (var protComposition in protCompositions)
{
totalProtCompositions++;
// Console.WriteLine(protComposition);
var scorer = new TopDownScorer(protComposition, run, precursorTolerance);
var score = scorer.GetScore();
Console.WriteLine(score);
}
}
}
sw.Stop();
Console.WriteLine("NumProteins: {0}", numProteins);
Console.WriteLine("NumProteinCompositions: {0}", totalProtCompositions);
Console.WriteLine(@"Elapsed Time: {0:f4} sec", sw.Elapsed.TotalSeconds);
}