public void TestAddDigestFeatures()
{
Sequence seq = new Sequence("Test", "AAANESAARBBBNPSBBKFFFNITFFRGGGNDTGGR");
Digest digest = new Digest();
digest.DigestProtease = ProteaseManager.CreateProtease("Trypsin_TestAddDigestFeatures", true, "RK", "P");
digest.ProteinSequence = seq;
digest.MaxMissedCleavages = 0;
digest.AddDigestFeatures();
List<DigestPeptideInfo> peptides = (List<DigestPeptideInfo>)seq.Annotation[Digest.PEPTIDE_FEATURE_TYPE];
Assert.AreEqual(4, peptides.Count);
digest.MaxMissedCleavages = 1;
digest.AddDigestFeatures();
List<DigestPeptideInfo> missedPeptides = (List<DigestPeptideInfo>)seq.Annotation[Digest.PEPTIDE_FEATURE_TYPE];
Assert.AreEqual(7, missedPeptides.Count);
IRangeLocationFilter nglycanFilter = new NGlycanFilter();
digest.MaxMissedCleavages = 0;
digest.Filter = nglycanFilter;
digest.AddDigestFeatures();
List<DigestPeptideInfo> nglycanPeptides = (List<DigestPeptideInfo>)seq.Annotation[Digest.PEPTIDE_FEATURE_TYPE];
Assert.AreEqual(2, nglycanPeptides.Count);
Assert.AreEqual("AAANESAAR", nglycanPeptides[0].PeptideSeq);
Assert.AreEqual("FFFNITFFR", nglycanPeptides[1].PeptideSeq);
}
private void GetDigestPeptide(List <Sequence> seqs)
{
miss0 = new Dictionary <string, string>();
miss1 = new Dictionary <string, string>();
foreach (var seq in seqs)
{
Digest dig = new Digest();
dig.DigestProtease = options.Enzyme;
dig.ProteinSequence = seq;
dig.MaxMissedCleavages = 1;
dig.AddDigestFeatures();
var features = seq.GetDigestPeptideInfo();
foreach (var feature in features)
{
if (feature.PeptideSeq.Length < options.MinLength)
{
continue;
}
var pepseq = feature.PeptideSeq.Replace('I', 'L');
if (feature.MissCleavage == 0)
{
miss0[pepseq] = feature.PeptideSeq;
}
else
{
miss1[pepseq] = feature.PeptideSeq;
}
}
}
}
protected override IFileProcessor GetFileProcessor()
{
proteins = SequenceUtils.Read(new FastaFormat(), base.GetOriginFile());
Protease protease = ProteaseManager.GetProteaseByName(proteases.SelectedItem);
Digest digest = new Digest()
{
DigestProtease = protease,
MaxMissedCleavages = 2
};
List <SimplePeakChro> totalPeaks = new List <SimplePeakChro>();
foreach (var seq in proteins)
{
digest.ProteinSequence = seq;
digest.AddDigestFeatures();
List <DigestPeptideInfo> peptides = seq.GetDigestPeptideInfo();
peptides.RemoveAll(m => m.PeptideSeq.Length < 6);
foreach (var dpi in peptides)
{
double mass = aas.MonoPeptideMass(dpi.PeptideSeq);
List <SimplePeakChro> curPeaks = new List <SimplePeakChro>();
for (int charge = 2; charge <= 3; charge++)
{
double precursor = (mass + Atom.H.MonoMass * charge) / charge;
if (precursor < 300 || precursor > 2000)
{
continue;
}
curPeaks.Add(new SimplePeakChro()
{
Mz = precursor,
Sequence = dpi.PeptideSeq,
Charge = charge
});
}
if (curPeaks.Count > 0)
{
dpi.Annotations[CHRO_KEY] = curPeaks;
totalPeaks.AddRange(curPeaks);
}
}
peptides.RemoveAll(m => !m.Annotations.ContainsKey(CHRO_KEY));
}
return(new ProteinChromatographProcessor(totalPeaks, new string[] { rawFile.FullName }.ToList(), new RawFileImpl(), ppmTolerance.Value, 2.0, rebuildAll.Checked));
}
public override IEnumerable <string> Process(string filename)
{
FastaFormat ff = new FastaFormat();
Digest digest = new Digest();
digest.DigestProtease = ProteaseManager.FindOrCreateProtease("Trypsin", true, "RK", "P");
digest.MaxMissedCleavages = 1;
NGlycanFilter filter = new NGlycanFilter();
digest.Filter = filter;
string resultFile = filename + ".nglycan";
Dictionary <string, NGlycanValue> peptideProteinMap = new Dictionary <string, NGlycanValue>();
using (StreamReader sr = new StreamReader(filename))
{
Sequence seq;
while ((seq = ff.ReadSequence(sr)) != null)
{
digest.ProteinSequence = seq;
digest.AddDigestFeatures();
if (seq.Annotation.ContainsKey(Digest.PEPTIDE_FEATURE_TYPE))
{
bool[] isGlycans = filter.IsNglycan;
List <DigestPeptideInfo> nglycanPeptides = (List <DigestPeptideInfo>)seq.Annotation[Digest.PEPTIDE_FEATURE_TYPE];
foreach (DigestPeptideInfo dpi in nglycanPeptides)
{
if (!peptideProteinMap.ContainsKey(dpi.PeptideSeq))
{
StringBuilder sb = new StringBuilder();
for (int i = 0; i < dpi.PeptideSeq.Length; i++)
{
if (isGlycans[dpi.PeptideLoc.Min - 1 + i])
{
sb.Append(1);
}
else
{
sb.Append(0);
}
}
NGlycanValue value = new NGlycanValue();
value.NGlycanSites = sb.ToString();
peptideProteinMap[dpi.PeptideSeq] = value;
}
peptideProteinMap[dpi.PeptideSeq].Proteins.Add(parser.GetValue(dpi.ProteinName));
}
}
}
}
List <string> peptides = new List <string>(peptideProteinMap.Keys);
peptides.Sort();
using (StreamWriter sw = new StreamWriter(resultFile))
{
foreach (string pep in peptides)
{
NGlycanValue value = peptideProteinMap[pep];
sw.Write(pep + "\t" + value.NGlycanSites + "\t");
bool bFirst = true;
foreach (string protein in value.Proteins)
{
if (bFirst)
{
bFirst = false;
sw.Write(protein);
}
else
{
sw.Write(" ! " + protein);
}
}
sw.WriteLine();
}
}
return(new[] { resultFile });
}
/// <summary>
/// 读取fasta文件，进行数据处理。
/// </summary>
/// <param name="fileName"></param>
/// <returns></returns>
public override IEnumerable <string> Process(string fastaFile)
{
HashSet <string> result = new HashSet <string>();
var ff = new FastaFormat();
using (StreamReader sr = new StreamReader(fastaFile))
{
Progress.SetRange(0, sr.BaseStream.Length);
var aas = new Aminoacids();
Predicate <string> aaFilter = m =>
{
foreach (var aa in ignoreAminoacids)
{
if (m.Contains(aa))
{
return(false);
}
}
return(true);
};
Predicate <string> lengthFilter = m => m.Length >= minLength;
Predicate <string> massFilter = m =>
{
var mass = aas.MonoPeptideMass(m);
return(mass >= minMass && mass <= maxMass);
};
Predicate <string> filter = m => aaFilter(m) && lengthFilter(m) && massFilter(m);
List <Digest> digs = new List <Digest>();
foreach (var protease in proteases)
{
var dig = new Digest();
dig.DigestProtease = protease;
dig.MaxMissedCleavages = maxMissCleavage;
digs.Add(dig);
}
Sequence seq;
Progress.SetMessage("Digesting sequences ...");
while ((seq = ff.ReadSequence(sr)) != null)
{
Progress.SetPosition(sr.GetCharpos());
if (Progress.IsCancellationPending())
{
throw new UserTerminatedException();
}
HashSet <string> curseqs = new HashSet <string>();
curseqs.Add(seq.SeqString);
foreach (var dig in digs)
{
var last = curseqs;
curseqs = new HashSet <string>();
foreach (var curseq in last)
{
var pro = new Sequence(curseq, curseq);
dig.ProteinSequence = pro;
dig.AddDigestFeatures();
var infos = pro.GetDigestPeptideInfo();
infos.ForEach(m =>
{
if (filter(m.PeptideSeq))
{
curseqs.Add(m.PeptideSeq);
}
});
}
}
result.UnionWith(curseqs);
}
}
Progress.SetMessage("Sorting sequences ...");
var peps = new List <string>(result);
peps.Sort((m1, m2) =>
{
var res = m1.Length.CompareTo(m2.Length);
if (res == 0)
{
res = m1.CompareTo(m2);
}
return(res);
});
var resultFile = fastaFile + ".pep";
using (StreamWriter sw = new StreamWriter(resultFile))
{
peps.ForEach(m => sw.WriteLine(m));
}
return(new[] { resultFile });
}
