public void TestSequenceEnumerationParallel2()
{
var methodName = MethodBase.GetCurrentMethod().Name;
TestUtils.ShowStarting(methodName);
var sw = new System.Diagnostics.Stopwatch();
const string dbFile = @"\\proto-2\UnitTest_Files\InformedProteomics_TestFiles\MSPathFinderT\ID_002216_235ACCEA.fasta";
var db = new FastaDatabase(dbFile);
db.Read();
var indexedDb = new IndexedDatabase(db);
var arr = db.Characters().ToArray();
sw.Start();
//var annotationsAndOffsets = indexedDb.AnnotationsAndOffsetsNoEnzyme(7, 30);
// var num = annotationsAndOffsets.AsParallel().LongCount(annotationsAndOffset => annotationsAndOffset.Annotation.IndexOf('W') >= 0);
//var num = annotationsAndOffsets.LongCount(annotationsAndOffset => annotationsAndOffset.Annotation.IndexOf('W') >= 0);
//var num = arr.AsParallel().Where(c => c == 'W').LongCount();
var num = 0;
var sum = 0L;
//foreach (var c in arr)
for (var a = 0; a < arr.Length; a++)
{
var c = arr[a];
for (var i = 0; i < c * 10000; i++) sum += i;
// Interlocked.Increment(ref num);
if (++num == 1000) break;
}
Console.WriteLine("NumPeptides: {0}", sum);
sw.Stop();
Console.WriteLine(@"{0:f4} sec", sw.Elapsed.TotalSeconds);
}
private static void TestCountingPeptides()
{
var aaSet = new AminoAcidSet();
var sw = new Stopwatch();
sw.Start();
//const string dbFile = @"\\proto-2\UnitTest_Files\InformedProteomics_TestFiles\MSPathFinderT\ID_002166_F86E3B2F.fasta";
const string dbFile = @"\\proto-2\UnitTest_Files\InformedProteomics_TestFiles\MSPathFinderT\ID_003456_9B916A8B.fasta";
// const string dbFile = @"\\proto-2\UnitTest_Files\InformedProteomics_TestFiles\MSPathFinderT\ID_004208_295531A4.fasta";
var db = new FastaDatabase(dbFile);
var indexedDb = new IndexedDatabase(db);
indexedDb.Read();
//var numPeptides = indexedDb.AnnotationsAndOffsetsNoEnzyme(7, 150).LongCount();
var peptides =
indexedDb.AnnotationsAndOffsets(7, 40, 2, 2, Enzyme.Trypsin);
Parallel.ForEach(peptides, annotationAndOffset =>
//foreach(var annotationAndOffset in peptides)
{
var annotation = annotationAndOffset.Annotation;
var offset = annotationAndOffset.Offset;
var graph = SequenceGraph.CreateGraph(aaSet, annotation);
}
)
;
// Console.WriteLine("NumPeptides: {0}", numPeptides);
sw.Stop();
var sec = sw.ElapsedTicks / (double)Stopwatch.Frequency;
Console.WriteLine(@"{0:f4} sec", sec);
}
public void TestForManyMods()
{
var methodName = MethodBase.GetCurrentMethod().Name;
TestUtils.ShowStarting(methodName);
const string dbFilePath = @"\\protoapps\UserData\Jungkap\Lewy\db\ID_005140_7A170668.fasta";
var indexedDb = new IndexedDatabase(new FastaDatabase(dbFilePath));
indexedDb.Read();
var nProt = indexedDb.EstimateTotalPeptides(1, 21, 300, 1, 0);
Console.WriteLine(nProt);
nProt = indexedDb.EstimateTotalPeptides(1, 21, 400, 1, 0);
Console.WriteLine(nProt);
nProt = indexedDb.EstimateTotalPeptides(1, 21, 500, 1, 0);
Console.WriteLine(nProt);
Console.WriteLine(@"Test not implemented: " + methodName);
}
/// <summary>
/// Constructor
/// </summary>
/// <param name="fastaDatabase"></param>
public SearchableDatabase(FastaDatabase fastaDatabase)
{
FastaDatabase = fastaDatabase;
_sequence = fastaDatabase.GetSequence();
_suffixArray = new int[_sequence.Length];
SAIS.sufsort(_sequence, _suffixArray, _sequence.Length);
var neighboringLcps = new byte[_suffixArray.Length];
neighboringLcps[0] = 0;
for (var i = 1; i < _suffixArray.Length; i++)
{
var lcp = IndexedDatabase.GetLcp(_sequence, _suffixArray[i - 1], _suffixArray[i]);
neighboringLcps[i] = lcp;
}
_leftLcps = new byte[_suffixArray.Length];
_rightLcps = new byte[_suffixArray.Length];
InitializeLcps(neighboringLcps, _leftLcps, _rightLcps, 0, _suffixArray.Length - 1);
}
public void TestEnumeratingProteins()
{
var methodName = MethodBase.GetCurrentMethod().Name;
TestUtils.ShowStarting(methodName);
var sw = new System.Diagnostics.Stopwatch();
sw.Start();
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);
foreach (var annotationAndOffset in indexedDb.IntactSequenceAnnotationsAndOffsetsWithCTermCleavagesLargerThan(100, 300, 3))
{
Console.WriteLine(annotationAndOffset.Annotation);
}
sw.Stop();
Console.WriteLine(@"{0:f4} sec", sw.Elapsed.TotalSeconds);
}
[TestCase(3, @"\\proto-2\UnitTest_Files\InformedProteomics_TestFiles\MSPathFinderT\ID_005133_8491EFA2.fasta", 323719193)] // 3MB
//[TestCase(6, @"\\proto-2\UnitTest_Files\InformedProteomics_TestFiles\MSPathFinderT\ID_004530_B63BD900.fasta", 595227563)] // 6MB
//[TestCase(15, @"\\proto-2\UnitTest_Files\InformedProteomics_TestFiles\MSPathFinderT\ID_004208_295531A4.fasta", 1882434687)] // 15MB
public void TestSequenceEnumeration(double size, string dbFile, int expected)
{
var methodName = MethodBase.GetCurrentMethod().Name;
TestUtils.ShowStarting(methodName, dbFile);
var sw = new System.Diagnostics.Stopwatch();
sw.Start();
var db = new FastaDatabase(dbFile);
var indexedDb = new IndexedDatabase(db);
var numSequences = 0L;
var timeDB = sw.Elapsed;
Console.WriteLine("Read DB in " + timeDB.TotalSeconds + " Seconds");
var estimatedAnnOff = indexedDb.EstimateTotalPeptides(0, 30, 250);
var timeEstimate = sw.Elapsed;
Console.WriteLine("Read Estimate in " + (timeEstimate - timeDB).TotalSeconds + " Seconds");
//int coreCount = 0;
//foreach (var item in new System.Management.ManagementObjectSearcher("Select NumberOfCores from Win32_Processor").Get())
//{
// coreCount += int.Parse(item["NumberOfCores"].ToString());
//}
//Console.WriteLine("Number Of Cores: {0}", coreCount);
//Console.WriteLine("Processors: " + System.Environment.ProcessorCount);
Console.WriteLine("Estimated results: " + estimatedAnnOff);
var annotationsAndOffsets = indexedDb.AnnotationsAndOffsetsNoEnzymeParallel(30, 250);
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;
}
);/**/
//annotationsAndOffsets.Select(annotationsAndOffset => annotationsAndOffset.)
// Below, original: 110, 109(total) seconds
// Parallelizing AnnotationsAndOffsetsNoEnzyme: 86 seconds
// Parallelizing AnnotationsAndOffsetsNoEnzyme, yield returns: 79.6, 94, 60, 60 seconds
//
// 3MB
// serial:
// Parallel2: 107,
//
// 6MB
// serial:
// Parallel2:
//
// 15MB
// serial:
// Parallel2:
//using (var ofstream = new FileStream(Path.Combine(@"F:\InformedProteomicsTestFiles", Path.GetFileNameWithoutExtension(dbFile) + "_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);
}
private IEnumerable<AnnotationAndOffset> GetAnnotationsAndOffsets(FastaDatabase database)
{
var indexedDbTarget = new IndexedDatabase(database);
IEnumerable<AnnotationAndOffset> annotationsAndOffsets;
if (NumTolerableTermini == 0)
{
annotationsAndOffsets = indexedDbTarget.AnnotationsAndOffsetsNoEnzyme(MinSequenceLength, MaxSequenceLength);
}
else
{
annotationsAndOffsets = indexedDbTarget.AnnotationsAndOffsets(MinSequenceLength, MaxSequenceLength,
NumTolerableTermini, 2, Enzyme);
}
return annotationsAndOffsets;
}
public void TestTopDownScoringForAllXics()
{
var methodName = MethodBase.GetCurrentMethod().Name;
TestUtils.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, null);
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);
}
public void TestNominalMassErrors()
{
const int minLength = 300;
const int maxLength = 400;
var sw = new System.Diagnostics.Stopwatch();
// const string dbFile = @"\\proto-2\UnitTest_Files\InformedProteomics_TestFiles\H_sapiens_Uniprot_SPROT_2013-05-01_withContam.fasta";
const string dbFile = @"C:\cygwin\home\kims336\Data\TopDownJia\database\ID_003962_71E1A1D4.fasta";
//const string dbFile = @"C:\cygwin\home\kims336\Data\TopDownJia\database\TargetProteins.fasta";
var db = new FastaDatabase(dbFile);
db.Read();
var indexedDb = new IndexedDatabase(db);
var numSequences = 0L;
sw.Start();
var hist = new long[11];
var aaSet = new AminoAcidSet();
foreach (var peptideAnnotationAndOffset in indexedDb.AnnotationsAndOffsetsNoEnzyme(minLength, maxLength))
{
++numSequences;
var annotation = peptideAnnotationAndOffset.Annotation;
var sequenceStr = annotation.Substring(2, annotation.Length - 4);
var sequenceComp = aaSet.GetComposition(sequenceStr);
var mass = sequenceComp.Mass;
var nominalMass = sequenceComp.NominalMass;
var error = (int) Math.Round(mass*Constants.RescalingConstant) - nominalMass;
var errorBin = error + hist.Length/2;
if (errorBin < 0) errorBin = 0;
if (errorBin >= hist.Length) errorBin = hist.Length - 1;
hist[errorBin]++;
}
Console.WriteLine("NumSequences: {0}", numSequences);
for (var i = 0; i < hist.Length; i++)
{
Console.WriteLine("{0}\t{1}\t{2}", i - hist.Length/2, hist[i], hist[i]/(double)numSequences);
}
sw.Stop();
Console.WriteLine(@"Elapsed Time: {0:f4} sec", sw.Elapsed.TotalSeconds);
}
public void TestRunningTimeChromGen()
{
var methodName = MethodBase.GetCurrentMethod().Name;
TestUtils.ShowStarting(methodName);
const string rafFilePath = @"C:\cygwin\home\kims336\Data\QCShewQE\QC_Shew_13_04_A_17Feb14_Samwise_13-07-28.raf";
if (!File.Exists(rafFilePath))
{
Assert.Ignore(@"Skipping test {0} since file not found: {1}", methodName, rafFilePath);
}
var rafRun = new PbfLcMsRun(rafFilePath);
var tolerance = new Tolerance(10);
const string dbFile = @"D:\Research\Data\CommonContaminants\H_sapiens_Uniprot_SPROT_2013-05-01_withContam.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 aaSet = new AminoAcidSet(Modification.Carbamidomethylation);
var sw = new System.Diagnostics.Stopwatch();
sw.Start();
var numPeptides = 0;
foreach (var peptide in indexedDb.AnnotationsAndOffsets(6, 30, 2, 2, Enzyme.Trypsin))
{
++numPeptides;
var comp = new Sequence(peptide.Annotation.Substring(2, peptide.Annotation.Length-4), aaSet).Composition + Composition.H2O;
var mz = new Ion(comp, 2).GetMonoIsotopicMz();
//Console.WriteLine(peptide.Annotation + " " + mz);
rafRun.GetFullPrecursorIonExtractedIonChromatogram(mz, tolerance);
//run.GetFullPrecursorIonExtractedIonChromatogram(mz, tolerance);
//var xic1 = run.GetFullPrecursorIonExtractedIonChromatogram(mz, tolerance);
//var xic2 = rafRun.GetFullPrecursorIonExtractedIonChromatogram(mz, tolerance);
//Assert.True(xic1.Count == xic2.Count);
//for (var i = 0; i < xic1.Count; i++)
//{
// if (!xic1[i].Equals(xic2[i]))
// {
// Console.WriteLine("{0} {1} {2}", i, xic1[i], xic2[i]);
// }
// Assert.True(xic1[i].Equals(xic2[i]));
//}
if (numPeptides == 100000) break;
}
sw.Stop();
Console.WriteLine(@"{0:f4} sec", sw.Elapsed.TotalSeconds);
}
public void TestId()
{
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.icsfldecoy.fasta";
//const string fastaFilePath = @"H:\Research\QCShew_TopDown\Production\Decoy_SO4280.fasta";
const string fastaFilePath = @"H:\Research\QCShew_TopDown\Production\SO2312.fasta";
const string modFilePath = @"H:\Research\QCShew_TopDown\Production\Mods.txt";
const int numBits = 29; // max error: 4ppm
const int minCharge = 2;
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 ms2ScanNumArr = new[] {4130};
var ms2ScanNumArr = new[] { 5189 };
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;
productSpec.FilterNoise();
var deconvolutedPeaks = Deconvoluter.GetDeconvolutedPeaks(productSpec, 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:f4} 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}{1} proteins...", numProteins,
numProteins == 1 ? "st" : numProteins == 2 ? "nd" : numProteins == 3 ? "rd" : "th");
if (numProteins != 0)
{
sw.Stop();
Console.WriteLine("Elapsed Time: {0:f4} sec", sw.Elapsed.TotalSeconds);
sw.Reset();
sw.Start();
}
}
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 <= 0; numNTermCleavage++)
{
if (numNTermCleavage > 0) seqGraph.CleaveNTerm();
var allCompositions = seqGraph.GetAllFragmentNodeCompositions().ToArray();
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];
Console.WriteLine(suffixMass);
}
}
}
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
//var seqGraphPrefix = SequenceGraph.CreateGraph(aminoAcidSet, AminoAcid.ProteinNTerm, protSequence,
// AminoAcid.ProteinCTerm);
//if (seqGraphPrefix == null) continue;
//{
// 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 ? "'" : "");
// }
// }
//}
}
Console.WriteLine("ScanNum\tBestProtein\tScore");
foreach (var ms2ScanNum in ms2ScanNumArr)
{
Console.WriteLine("{0}\t{1}\t{2}", ms2ScanNum, bestProtein[ms2ScanNum] ?? "", bestScore[ms2ScanNum]);
}
//sw.Stop();
//Console.WriteLine(@"Scoring: {0:f4} sec.", sw.Elapsed.TotalSeconds);
}
public void TestCountingPeptides()
{
var methodName = MethodBase.GetCurrentMethod().Name;
TestUtils.ShowStarting(methodName);
var sw = new System.Diagnostics.Stopwatch();
sw.Start();
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);
}
// const string dbFile = @"C:\cygwin\home\kims336\Data\QCShew\ID_003456_9B916A8B.fasta";
// const string dbFile = @"H:\Research\DDAPlus\database\Yeast_SGD_withContam.fasta";
// const string dbFile = @"H:\Research\CPTAC_Phospho\database\ID_004208_295531A4.fasta";
var db = new FastaDatabase(dbFile);
var indexedDb = new IndexedDatabase(db);
//var numPeptides = indexedDb.IntactSequenceAnnotationsAndOffsets(21, 300, 0).LongCount()*31;
var peptides = indexedDb
.SequenceAnnotationsAndOffsetsWithNtermOrCtermCleavageNoLargerThan(
100, 300, 1, 0);
var numPeptides = 0;
foreach (var peptide in peptides)
{
Console.WriteLine("{0}\t{1}",peptide.Annotation, peptide.Offset);
numPeptides++;
}
//var numPeptides = indexedDb.AnnotationsAndOffsetsNoEnzyme(7, 150).LongCount();
//var numPeptides =
// indexedDb.AnnotationsAndOffsets(7, 40, 2, 2, Enzyme.Trypsin).LongCount();
//var numPeptides = indexedDb.AnnotationsAndOffsets(6, 40, 2, 2, Enzyme.Trypsin).LongCount();
//var numPeptides = indexedDb.IntactSequenceAnnotationsAndOffsets(30, 250, 0).LongCount();
// .Select(annotationAndSequence => annotationAndSequence.Annotation.Length - 4)
// .Aggregate(0L, (current, length) => current + Math.Min(length - 29, 30));
Console.WriteLine("NumPeptides: {0}", numPeptides);
sw.Stop();
Console.WriteLine(@"{0:f4} sec", sw.Elapsed.TotalSeconds);
}
public void TestGettingProteinLengthAndPosition()
{
var methodName = MethodBase.GetCurrentMethod().Name;
TestUtils.ShowStarting(methodName);
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);
db.Read();
var indexedDb = new IndexedDatabase(db);
foreach (var peptideAnnotationAndOffset in indexedDb.AnnotationsAndOffsets(6, 20, 2, 0, Enzyme.Trypsin))
{
var annotation = peptideAnnotationAndOffset.Annotation;
var offset = peptideAnnotationAndOffset.Offset;
Console.WriteLine("{0}\t{1}\t{2}\t{3}\t{4}",
annotation,
offset,
db.GetProteinName(offset),
db.GetProteinLength(db.GetProteinName(offset)),
db.GetOneBasedPositionInProtein(offset)+1);
}
}
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);
}
[TestCase(6, @"\\proto-2\UnitTest_Files\InformedProteomics_TestFiles\MSPathFinderT\ID_004530_B63BD900.fasta", 8898)] // 6MB
//[TestCase(15, @"\\proto-2\UnitTest_Files\InformedProteomics_TestFiles\MSPathFinderT\ID_004208_295531A4.fasta", 6334)] // 15MB
public void TestSequenceEnumerationIntact(double size, string dbFile, int expected)
{
var methodName = MethodBase.GetCurrentMethod().Name;
TestUtils.ShowStarting(methodName, dbFile);
var sw = new System.Diagnostics.Stopwatch();
sw.Start();
const int numCTermCleavages = 0;
var db = new FastaDatabase(dbFile);
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(dbFile) + "_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);
}
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(3, @"\\proto-2\UnitTest_Files\InformedProteomics_TestFiles\MSPathFinderT\ID_005133_8491EFA2.fasta", 323719193)] // 3MB
//[TestCase(6, @"\\proto-2\UnitTest_Files\InformedProteomics_TestFiles\MSPathFinderT\ID_004530_B63BD900.fasta", 595227563)] // 6MB
//[TestCase(15, @"\\proto-2\UnitTest_Files\InformedProteomics_TestFiles\MSPathFinderT\ID_004208_295531A4.fasta", 1882434687)] // 15MB
public void TestSequenceEnumerationSerial(double size, string dbFile, int expected)
{
var methodName = MethodBase.GetCurrentMethod().Name;
TestUtils.ShowStarting(methodName, dbFile);
var sw = new System.Diagnostics.Stopwatch();
sw.Start();
//const string dbFile = @"\\proto-2\UnitTest_Files\InformedProteomics_TestFiles\MSPathFinderT\ID_002216_235ACCEA.fasta"; // 1.5MB
//const string dbFile = @"\\proto-2\UnitTest_Files\InformedProteomics_TestFiles\MSPathFinderT\ID_005133_8491EFA2.fasta"; // 3MB
//const string dbFile = @"\\proto-2\UnitTest_Files\InformedProteomics_TestFiles\MSPathFinderT\ID_004530_B63BD900.fasta"; // 6MB
//const string dbFile = @"\\proto-2\UnitTest_Files\InformedProteomics_TestFiles\MSPathFinderT\ID_004208_295531A4.fasta"; // 15MB
var db = new FastaDatabase(dbFile);
var indexedDb = new IndexedDatabase(db);
indexedDb.Read();
var numSequences = 0L;
var timeDB = sw.Elapsed;
Console.WriteLine("Read DB in " + timeDB.TotalSeconds + " Seconds");
var estimatedAnnOff = indexedDb.EstimateTotalPeptides(0, 30, 250);
var timeEstimate = sw.Elapsed;
Console.WriteLine("Read Estimate in " + (timeEstimate - timeDB).TotalSeconds + " Seconds");
Console.WriteLine("Estimated results: " + estimatedAnnOff);
var annotationsAndOffsets = indexedDb.AnnotationsAndOffsetsNoEnzyme(30, 250);
var timeGetAnn = sw.Elapsed;
Console.WriteLine("Read Annotations in " + (timeGetAnn - timeEstimate).TotalSeconds + " Seconds");
//foreach (var annotationsAndOffset in annotationsAndOffsets)
//{
// //Interlocked.Increment(ref numSequences);
// ++numSequences;
//}
//using (
// var ofstream =
// new FileStream(
// Path.Combine(@"F:\InformedProteomicsTestFiles",
// Path.GetFileNameWithoutExtension(dbFile) + "_old.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 CreateTargetList()
{
var methodName = MethodBase.GetCurrentMethod().Name;
TestUtils.ShowStarting(methodName);
const string databaseFilePath = @"D:\Research\Data\IPRG2014\database\SpikedInPeptides.fasta";
if (!File.Exists(databaseFilePath))
{
Assert.Ignore(@"Skipping test {0} since file not found: {1}", methodName, databaseFilePath);
}
var database = new FastaDatabase(databaseFilePath);
database.Read();
var indexedDatabase = new IndexedDatabase(database);
var numTargets = 0;
var aaSet = new AminoAcidSet(Modification.Carbamidomethylation);
Console.WriteLine("Peptide\tFormula\tProtein");
foreach (var annotationAndOffset in indexedDatabase.AnnotationsAndOffsets(6, 30, 1, 1, Enzyme.Trypsin))
{
var annotation = annotationAndOffset.Annotation;
var peptide = annotation.Substring(2, annotation.Length - 4);
var offset = annotationAndOffset.Offset;
Console.WriteLine("{0}\t{1}\t{2}", peptide, (aaSet.GetComposition(peptide) + Composition.H2O).ToPlainString(), database.GetProteinName(offset));
numTargets++;
}
Console.WriteLine("NumTargets: {0}", numTargets);
}