public void TestSearching()
{
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 searchableDb = new SearchableDatabase(db);
//const string pattern = "NSGSHFCGGSLINSQWVVSAAH";
const string pattern = "FPTDDDDK";
var position = searchableDb.Search(pattern);
Assert.True(position >= 0);
Console.WriteLine("Position: {0}", position);
Console.WriteLine("Matched indices: {0}", string.Join(",", searchableDb.FindAllMatchedSequenceIndices(pattern)));
Console.WriteLine("Protein indices: {0}", string.Join(",", searchableDb.FindAllMatchedSequenceIndices(pattern).Select(i => db.GetOneBasedPositionInProtein(i))));
sw.Stop();
Console.WriteLine(@"{0:f4} sec", sw.Elapsed.TotalSeconds);
}
private void WriteResultsToFile(SortedSet<DatabaseSequenceSpectrumMatch>[] matches, string outputFilePath, FastaDatabase database)
{
using (var writer = new StreamWriter(outputFilePath))
{
writer.WriteLine("Scan\tPre\tSequence\tPost\tModifications\tComposition\tProteinName\tProteinDesc" +
"\tProteinLength\tStart\tEnd\tCharge\tMostAbundantIsotopeMz\tMass\t#MatchedFragments\tIcScore"
);
for (var scanNum = _run.MinLcScan; scanNum <= _run.MaxLcScan; scanNum++)
{
if (matches[scanNum] == null) continue;
foreach (var match in matches[scanNum].Reverse())
{
var sequence = match.Sequence;
var offset = match.Offset;
var start = database.GetOneBasedPositionInProtein(offset) + 1 + match.NumNTermCleavages;
var end = start + sequence.Length - 1;
var proteinName = database.GetProteinName(match.Offset);
var protLength = database.GetProteinLength(proteinName);
var ion = match.Ion;
var scores = _bottomUpScorer.GetScores(match, ion.Composition, ion.Charge, scanNum);
if (ion == null)
{
Console.WriteLine(@"Null ion!");
}
if (scores == null)
{
Console.WriteLine(@"Null scores");
}
// Note for DblToString(value, 9, true), by having "9" and "true",
// values between 100 and 999 Da will have 7 digits after the decimal place, and
// values between 1000 and 9999 will have 6 digits after the decimal place
writer.WriteLine("{0}\t{1}\t{2}\t{3}\t{4}\t{5}\t{6}\t{7}\t{8}\t{9}\t{10}\t{11}\t{12}\t{13}\t{14}\t{15}",
scanNum,
match.Pre,
sequence, // Sequence
match.Post,
scores.Modifications, // Modifications
ion.Composition, // Composition
proteinName, // ProteinName
database.GetProteinDescription(match.Offset), // ProteinDescription
protLength, // ProteinLength
start, // Start
end, // End
ion.Charge, // precursorCharge
StringUtilities.DblToString(ion.GetMostAbundantIsotopeMz(), 9, true), // MostAbundantIsotopeMz
StringUtilities.DblToString(ion.Composition.Mass, 9, true), // Mass
match.Score,
scores.Score // Score (re-scored)
);
}
}
}
}
private void WriteResultsToFile(DatabaseSequenceSpectrumMatch[] matches, string outputFilePath, FastaDatabase database)
{
using (var writer = new StreamWriter(outputFilePath))
{
writer.WriteLine("Scan\tPre\tSequence\tPost\tModifications\tComposition\tProteinName\tProteinDesc" +
"\tProteinLength\tStart\tEnd\tCharge\tMostAbundantIsotopeMz\tMass\t#MatchedFragments\tProbability\tSpecEValue\tEValue");
foreach(var scanNum in _ms2ScanNums)
{
var match = matches[scanNum];
if (match == null) continue;
var sequence = match.Sequence;
var offset = match.Offset;
var start = database.GetOneBasedPositionInProtein(offset) + 1 + match.NumNTermCleavages;
var end = start + sequence.Length - 1;
var proteinName = database.GetProteinName(match.Offset);
var protLength = database.GetProteinLength(proteinName);
var ion = match.Ion;
var proteinDescription = database.GetProteinDescription(match.Offset);
var probability = CompositeScorer.GetProbability(match.Score);
// Note for DblToString(value, 9, true), by having "9" and "true",
// values between 100 and 999 Da will have 7 digits after the decimal place, and
// values between 1000 and 9999 will have 6 digits after the decimal place
writer.WriteLine("{0}\t{1}\t{2}\t{3}\t{4}\t{5}\t{6}\t{7}\t{8}\t{9}\t{10}\t{11}\t{12}\t{13}\t{14}\t{15}\t{16}\t{17}",
scanNum,
match.Pre, // Pre
sequence, // Sequence
match.Post, // Post
match.ModificationText, // Modifications
ion.Composition, // Composition
proteinName, // ProteinName
proteinDescription, // ProteinDescription
protLength, // ProteinLength
start, // Start position in protein
end, // End position in protein
ion.Charge, // precursorCharge
StringUtilities.DblToString(ion.GetMostAbundantIsotopeMz(), 9, true), // MostAbundantIsotopeMz
StringUtilities.DblToString(ion.Composition.Mass, 9, true), // Mass
match.NumMatchedFragments, // (Number of matched fragments)
StringUtilities.DblToString(probability, 4), // Probability
StringUtilities.DblToString(ExcelMinValue(match.SpecEvalue), 6, true, 0.001), // EValue; will be displayed using scientific notation if the value is less than 0.001
StringUtilities.DblToString(ExcelMinValue(match.SpecEvalue * database.GetNumEntries()), 6, true, 0.001) // SpecEValue; will be displayed using scientific notation if the value is less than 0.001
);
}
}
}
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 TestGetProteinsWithTagMatchingSingleSpec()
{
var methodName = MethodBase.GetCurrentMethod().Name;
TestUtils.ShowStarting(methodName);
const string dataSet = @"H:\Research\Lewy\raw\Lewy_intact_07";
// const int scanNum = 5158;
const int minTagLength = 7;
const int minNumTagMatches = 1;
var aminoAcidSet = AminoAcidSet.GetStandardAminoAcidSet();
const int scanNum = 2;
// Parse sequence tags
//const string tagFileName = dataSet + ".seqtag"; //"_MinLength3.seqtag"; //Path.ChangeExtension(dataSet, ".seqtag");
const string rawFilePath = "";
const string fastaFilePath = @"H:\Research\Lewy\ID_004858_0EE8CF61.fasta";
if (!File.Exists(rawFilePath))
{
Assert.Ignore(@"Skipping test {0} since file not found: {1}", methodName, rawFilePath);
}
if (!File.Exists(fastaFilePath))
{
Assert.Ignore(@"Skipping test {0} since file not found: {1}", methodName, fastaFilePath);
}
var fastaDb = new FastaDatabase(fastaFilePath);
var searchableDb = new SearchableDatabase(fastaDb);
//var tagParser = new SequenceTagParser(tagFileName, minTagLength);
//var tags = tagParser.GetSequenceTags(scanNum);
var run = PbfLcMsRun.GetLcMsRun(rawFilePath);
var spec = run.GetSpectrum(scanNum) as ProductSpectrum;
var tagFinder = new SequenceTagFinder(spec, new Tolerance(5));
var tags = tagFinder.GetAllSequenceTagString();
var proteinsToTags = new Dictionary<string, IList<MatchedTag>>();
foreach (var tag in tags)
{
var matchedIndices = searchableDb.FindAllMatchedSequenceIndices(tag.Sequence).ToArray();
foreach (var index in matchedIndices)
{
var protein = fastaDb.GetProteinName(index);
var startIndex = fastaDb.GetOneBasedPositionInProtein(index);
var matchedTag = new MatchedTag(tag, startIndex, 0.0);
IList<MatchedTag> existingTags;
if (proteinsToTags.TryGetValue(protein, out existingTags))
{
existingTags.Add(matchedTag);
}
else
{
proteinsToTags.Add(protein, new List<MatchedTag> { matchedTag });
}
}
}
foreach (var entry in proteinsToTags.OrderByDescending(e => e.Value.Count))
{
if (entry.Value.Count < minNumTagMatches) break;
var proteinName = entry.Key;
var proteinSequence = fastaDb.GetProteinSequence(proteinName);
var protein = new Sequence(proteinSequence, aminoAcidSet);
Console.WriteLine(proteinName + "\t" + entry.Value.Count);
foreach (var matchedTag in entry.Value)
{
var seq = proteinSequence.Substring(matchedTag.StartIndex,
matchedTag.EndIndex - matchedTag.StartIndex);
var nTermMass = protein.GetMass(0, matchedTag.StartIndex);
var cTermMass = protein.GetMass(matchedTag.EndIndex, protein.Count);
Console.WriteLine("\t{0} ({1})\t{2}\t{3} ({4})\t{5}\t{6}\t{7}",
matchedTag.NTermFlankingMass, (matchedTag.NTermFlankingMass - nTermMass),
seq,
matchedTag.CTermFlankingMass, (matchedTag.CTermFlankingMass - cTermMass),
matchedTag.StartIndex,
matchedTag.IsNTermFlankingMassReliable, matchedTag.IsCTermFlankingMassReliable);
}
}
}