public void TestFeatureId()
{
var methodName = MethodBase.GetCurrentMethod().Name;
TestUtils.ShowStarting(methodName);
const string dataSet = @"H:\Research\QCShew_TopDown\Production\QC_Shew_Intact_26Sep14_Bane_C2Column3";
if (!File.Exists(dataSet))
{
Assert.Ignore(@"Skipping test {0} since file not found: {1}", methodName, dataSet);
}
// Feature: 5236-5286 6-12 8480.3681 5
const int minScanNum = 5236;
const int maxScanNum = 5286;
const double featureMass = 8480.3681;
//const int minScanNum = 7251;
//const int maxScanNum = 7326;
//const double featureMass = 32347.18;
// const int minScanNum = 4451;
// const int maxScanNum = 4541;
// const double featureMass = 31267.95;
var tolerance = new Tolerance(10);
var relaxedTolerance = new Tolerance(20);
const int minTagLength = 5;
const int minMergedTagLength = 7;
const int minNumTagMatches = 1;
var rawFileName = MassSpecDataReaderFactory.ChangeExtension(dataSet, ".raw");
var run = PbfLcMsRun.GetLcMsRun(rawFileName);
var aminoAcidSet = AminoAcidSet.GetStandardAminoAcidSet();
var featureFileName = MassSpecDataReaderFactory.ChangeExtension(dataSet, ".ms1ft");
var filter = new Ms1FtFilter(run, tolerance, featureFileName);
var ms2ScanNums =
filter.GetMatchingMs2ScanNums(featureMass)
.Where(scanNum => scanNum > minScanNum && scanNum < maxScanNum)
.ToArray();
const string tagFileName = dataSet + ".seqtag"; //"_MinLength3.seqtag"; //Path.ChangeExtension(dataSet, ".seqtag");
const string fastaFilePath = @"H:\Research\QCShew_TopDown\Production\ID_002216_235ACCEA.fasta";
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 proteinsToTags = new Dictionary<string, IList<MatchedTag>>();
foreach (var ms2ScanNum in ms2ScanNums)
{
var tags = tagParser.GetSequenceTags(ms2ScanNum);
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.GetZeroBasedPositionInProtein(index);
var matchedTag = new MatchedTag(tag, startIndex, featureMass);
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);
var matchedTagSet = new MatchedTagSet(proteinSequence, aminoAcidSet,
tolerance, relaxedTolerance);
Console.WriteLine("********** Before merging");
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}\t{1}\t{2}\t{3}\t{4}\t{5}",
(matchedTag.NTermFlankingMass - nTermMass), seq, (matchedTag.CTermFlankingMass - cTermMass), matchedTag.StartIndex,
matchedTag.IsNTermFlankingMassReliable, matchedTag.IsCTermFlankingMassReliable);
matchedTagSet.Add(matchedTag);
}
Console.WriteLine("********** After merging");
foreach (var matchedTag in matchedTagSet.Tags)
{
if (matchedTag.Length < minMergedTagLength) continue;
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}\t{1}\t{2}\t{3}\t{4}\t{5}",
(matchedTag.NTermFlankingMass-nTermMass), seq, (matchedTag.CTermFlankingMass - cTermMass), matchedTag.StartIndex,
matchedTag.IsNTermFlankingMassReliable, matchedTag.IsCTermFlankingMassReliable);
}
break;
}
}
public void FindProteinDeltaMass()
{
var methodName = MethodBase.GetCurrentMethod().Name;
TestUtils.ShowStarting(methodName);
const string folderPath = @"D:\MassSpecFiles\Glyco\";
if (!Directory.Exists(folderPath))
{
Assert.Ignore(@"Skipping test {0} since folder not found: {1}", methodName, folderPath);
}
var fileSet = new string[]
{
"User_sample_test_02252015", "User_sample_test_MWCO_02262016", "User_sample_test_SEC_F3_03022105",
"User_sample_test_SEC_F1_02272015", "User_sample_test_SEC_F2_02282015"
};
const string fastaFilePath = folderPath + "ID_003836_DA9CC1E4.fasta";
for (var i = 0; i < fileSet.Length; i++)
{
var datasetName = fileSet[i];
var tagFilePath = folderPath + datasetName + ".seqtag";
//var outputFilePath = folderPath + datasetName + ".matchedtag";
var outputFilePath = folderPath + datasetName + ".dmass";
var fastaDb = new FastaDatabase(fastaFilePath);
var searchableDb = new SearchableDatabase(fastaDb);
using (var writer = new StreamWriter(outputFilePath))
{
var isHeader = true;
var nReadSeqTag = 0;
Console.WriteLine(@"Reading {0} file", tagFilePath);
var nColumn = 0;
foreach (var line in File.ReadAllLines(tagFilePath))
{
if (isHeader)
{
isHeader = false;
nColumn = line.Split('\t').Length;
writer.WriteLine(line + "\t" + "Protein" + "\t" + "DetectedFlankingMass" + "\t" + "ExpectedFlankingMass" + "\t" + "DeltaMass");
continue;
}
var token = line.Split('\t');
if (token.Length != nColumn) continue;
var tag = token[1];
//var scan = Convert.ToInt32(token[0]);
if (tag.Length < 6) continue;
var nTerminal = token[2].Equals("1");
var detectedFlankingMass = Double.Parse(token[3]);
if (!nTerminal) detectedFlankingMass -= Composition.H2O.Mass;
nReadSeqTag++;
var matchedProteins =
searchableDb.FindAllMatchedSequenceIndices(tag)
.Select(index => fastaDb.GetProteinName(index))
.Distinct().ToArray();
if (matchedProteins.Length < 1) continue;
foreach (var protName in matchedProteins)
{
var seqStr = fastaDb.GetProteinSequence(protName);
var oriSeq = new Sequence(seqStr, AminoAcidSet.GetStandardAminoAcidSet());
var startIdx = 0;
while (true)
{
var idx = seqStr.IndexOf(tag, startIdx);
if (idx < 0) break; //no matching
//var nClv = (nTerminal) ? idx : seqStr.Length - idx - tag.Length;
var nClv = (nTerminal) ? 2 : 1;
for (var j = 0; j < nClv; j++)
{
var flankComposition = (nTerminal)
? oriSeq.GetComposition(j, idx)
: oriSeq.GetComposition(idx + tag.Length, oriSeq.Count - j);
var massDiff = (detectedFlankingMass - flankComposition.Mass);
if (massDiff > -500 && massDiff < 2000)
{
//writer.WriteLine(massDiff);
writer.WriteLine("{0}\t{1}\t{2}\t{3}\t{4}", line, protName, detectedFlankingMass, flankComposition.Mass, massDiff);
}
if (massDiff > 2000) break;
}
startIdx = idx + tag.Length;
}
}
//var matchedProteinStr = string.Join(",", matchedProteins);
//var massDiffStr = string.Join(",", massDiffList);
//writer.WriteLine("{0}\t{1}\t{2}\t{3}", line, matchedProteins.Length, matchedProteinStr, massDiffStr);
}
Console.WriteLine(@"{0} seq tags are processed", nReadSeqTag);
}
Console.WriteLine(@"Done");
}
}
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);
}
}
}
