public SingleNucleotidePolymorphism GetNotGsnapMismatch(string querySequence)
{
if (this.NumberOfMismatch == 0)
{
return(null);
}
var isPositiveStrand = this.Strand == '+';
var m = mismatch.Match(this.MismatchPositions);
if (!m.Success)
{
return(null);
}
var seq = isPositiveStrand ? querySequence : SequenceUtils.GetReversedSequence(querySequence);
var pos = int.Parse(m.Groups[1].Value);
var detectedChr = seq[pos];
var chr = m.Groups[2].Value.First();
chr = isPositiveStrand ? chr : SequenceUtils.GetComplementAllele(chr);
return(new SingleNucleotidePolymorphism(pos, chr, detectedChr));
}
public Sequence GetReversedSequence(int index, Sequence seq)
{
if (options.DecoyType == DecoyType.Index)
{
return(SequenceUtils.GetReversedSequence(seq.SeqString, index));
}
else
{
var description = options.DecoyKey + " " + seq.Description;
var sequence = SequenceUtils.GetReversedSequence(seq.SeqString);
string prefix = string.Empty, oldname;
if (options.DecoyType == DecoyType.Middle)
{
oldname = seq.Name.StringAfter("|");
if (oldname.Equals(seq.Name))
{
oldname = seq.Name.StringAfter(":");
if (!oldname.Equals(seq.Name))
{
prefix = seq.Name.StringBefore(":") + ":";
}
}
else
{
prefix = seq.Name.StringBefore("|") + "|";
}
}
else
{
oldname = seq.Name;
}
var newname = prefix + options.DecoyKey + "_" + oldname;
return(new Sequence(newname + " " + description, sequence));
}
}
public override IEnumerable <string> Process()
{
var format = new MascotPeptideTextFormat();
Progress.SetMessage("reading peptide-spectra-matches from " + options.PeptideFile + " ...");
var spectra = format.ReadFromFile(options.PeptideFile);
var seqMap = new Dictionary <string, IIdentifiedPeptide>();
foreach (var spec in spectra)
{
seqMap[spec.Peptide.PureSequence] = spec.Peptide;
}
var aas = (from c in new Aminoacids().GetVisibleAminoacids()
where c != 'I'
select c.ToString()).Merge("");
var ff = new FastaFormat();
Progress.SetMessage("inserting amino acid ...");
using (var sw = new StreamWriter(options.OutputFile))
{
sw.WriteLine(File.ReadAllText(options.DatabaseFile));
var seqs = seqMap.Keys.OrderBy(m => m).ToArray();
var reversed_index = 1000000;
foreach (var seq in seqs)
{
for (int i = 0; i < seq.Length; i++)
{
for (int j = 0; j < aas.Length; j++)
{
var newsequence = seq.Insert(i, aas[j].ToString());
var newref = string.Format("INS_{0}_{1}{2} Insertion of {3}", seq, i, aas[j], seqMap[seq].Proteins.Merge("/"));
var newseq = new Sequence(newref, newsequence);
ff.WriteSequence(sw, newseq);
if (options.GenerateReversedPeptide)
{
var revsequence = SequenceUtils.GetReversedSequence(newsequence);
var revref = string.Format("REVERSED_{0}", reversed_index++);
var revseq = new Sequence(revref, revsequence);
ff.WriteSequence(sw, revseq);
}
}
}
}
}
return(new[] { options.OutputFile });
}
private void ProcessFile(ref int index, StreamWriter sw, string fastaFile, bool isContaminant)
{
FastaFormat ff = new FastaFormat();
using (StreamReader sr = new StreamReader(fastaFile))
{
Progress.SetRange(0, sr.BaseStream.Length);
Sequence seq;
while ((seq = ff.ReadSequence(sr)) != null)
{
Progress.SetPosition(sr.BaseStream.Position);
if (isContaminant)
{
if (!seq.Reference.StartsWith("CON_"))
{
seq.Reference = "CON_" + seq.Reference;
}
}
if (options.ReversedOnly)
{
ff.WriteSequence(sw, seq);
}
if (options.IsPseudoAminoacid)
{
options.PseudoAminoacidBuilder.Build(seq);
}
index++;
Sequence reversedSeq = SequenceUtils.GetReversedSequence(seq.SeqString, index);
ff.WriteSequence(sw, reversedSeq);
}
}
}
public Dictionary <int, IIdentifiedProtein> ParseProteinMap(string fileName, bool isDecoy)
{
var suffix = isDecoy ? "_decoy" : "";
SQLiteDBHelper sqlite = new SQLiteDBHelper(fileName);
var result = new Dictionary <int, IIdentifiedProtein>();
string sqlProtein = string.Format("select ps.ProteinID, pa.Description, pro.Sequence, ps.ProteinScore, ps.Coverage from ProteinAnnotations as pa, Proteins as pro, ProteinScores{0} as ps where pro.ProteinID=pa.ProteinID and pro.ProteinID=ps.ProteinID", suffix);
var proteinReader = sqlite.ExecuteReader(sqlProtein, null);
Progress.SetMessage("Parsing proteins ...");
while (proteinReader.Read())
{
var protein = new IdentifiedProtein();
var proid = proteinReader.GetInt32(0);
var des = proteinReader.GetString(1);
if (des.Length > 0 && des[0] == '>')
{
des = des.Substring(1);
}
protein.Reference = des;
protein.Sequence = proteinReader.GetString(2);
protein.Score = proteinReader.GetDouble(3);
protein.Coverage = proteinReader.GetDouble(4);
result[proid] = protein;
}
if (isDecoy)
{
foreach (var v in result.Values)
{
v.Sequence = SequenceUtils.GetReversedSequence(v.Sequence);
v.Reference = GetReversedReference(v.Reference);
}
}
return(result);
}
public override IEnumerable <string> Process()
{
var spectra = new MaxQuantPeptideTextReader().ReadFromFile(options.SiteFile);
spectra.RemoveAll(m => m.DeltaScore < options.MinDeltaScore || m.Probability < options.MinProbability);
spectra = (from g in spectra.GroupBy(m => m.Query.FileScan.ShortFileName)
select g.OrderBy(l => l.Score).Last()).ToList();
if (options.IsSILAC)
{
var spmap = spectra.ToDictionary(m => m.Query.FileScan.ShortFileName);
var existModificationChar = (from sp in spectra
from c in sp.Sequence
where !char.IsLetter(c)
select c).Distinct().Count();
Dictionary <char, char> labelChars = new Dictionary <char, char>();
foreach (var c in options.SILACAminoacids)
{
labelChars[c] = ModificationConsts.MODIFICATION_CHAR[++existModificationChar];
}
using (var sr = new StreamReader(options.MSMSFile))
{
var headers = sr.ReadLine().Split('\t');
var rawIndex = Array.IndexOf(headers, "Raw file");
var scanIndex = Array.IndexOf(headers, "Scan number");
string line;
while ((line = sr.ReadLine()) != null)
{
if (string.IsNullOrWhiteSpace(line))
{
break;
}
var parts = line.Split('\t');
var raw = parts[rawIndex];
var scan = int.Parse(parts[scanIndex]);
var sf = new SequestFilename(raw, scan, scan, 0, "");
var name = sf.ShortFileName;
IIdentifiedSpectrum sp;
if (spmap.TryGetValue(name, out sp))
{
foreach (var pep in sp.Peptides)
{
var seq = pep.Sequence;
StringBuilder sb = new StringBuilder();
for (int i = seq.Length - 1; i >= 0; i--)
{
char heavyChar;
if (labelChars.TryGetValue(seq[i], out heavyChar))
{
sb.Append(heavyChar);
}
sb.Append(seq[i]);
}
pep.Sequence = SequenceUtils.GetReversedSequence(sb.ToString());
}
}
}
}
}
string resultFilename = options.SiteFile + ".peptides";
new MascotPeptideTextFormat("\t\"File, Scan(s)\"\tSequence\tCharge\tScore\tDeltaScore\tExpectValue\tPValue\tModification").WriteToFile(resultFilename, spectra);
return(new[] { resultFilename });
}
public override IEnumerable <string> Process(string fileName)
{
var parser = new MsfDatabaseParser(SearchEngineType.SEQUEST);
var seqs = parser.ParseProteinSequences(fileName);
SQLiteDBHelper sqlite = new SQLiteDBHelper(fileName);
var result = new List <Sequence>();
var aaReader = sqlite.ExecuteReader("select count(*) from peptides_decoy", null);
if (aaReader.Read())
{
if (aaReader.GetInt32(0) > 0) // there are decoy database
{
foreach (var seq in seqs)
{
result.Add(seq);
var revseq = new Sequence(MsfDatabaseParser.GetReversedReference(seq.Reference), SequenceUtils.GetReversedSequence(seq.SeqString));
result.Add(revseq);
}
}
}
if (result.Count == 0)
{
result = seqs;
}
var fastafile = fileName + ".fasta";
using (var sw = new StreamWriter(fastafile))
{
var ff = new FastaFormat();
foreach (var seq in result)
{
ff.WriteSequence(sw, seq);
}
}
return(new[] { fastafile });
}