public void TestProteomeDb()
{
using (var testFilesDir = new TestFilesDir(TestContext, ZIP_FILE))
{
string fastaPath = testFilesDir.GetTestPath("high_ipi.Human.20060111.fasta");
string protDbPath = testFilesDir.GetTestPath("test.protdb");
using (ProteomeDb proteomeDb = ProteomeDb.CreateProteomeDb(protDbPath))
{
Enzyme trypsin = EnzymeList.GetDefault();
using (var reader = new StreamReader(fastaPath))
{
proteomeDb.AddFastaFile(reader, (msg, progress) => true);
}
// perform digestion
proteomeDb.Digest(new ProteaseImpl(trypsin), (msg, progress) => true);
Digestion digestion = proteomeDb.GetDigestion(trypsin.Name);
var digestedProteins0 = digestion.GetProteinsWithSequencePrefix("EDGWVK", 100);
Assert.IsTrue(digestedProteins0.Count >= 1);
}
}
}
public void TestProteomeDb()
{
using (var testFilesDir = new TestFilesDir(TestContext, ZIP_FILE))
{
string fastaPath = testFilesDir.GetTestPath("high_ipi.Human.20060111.fasta");
string protDbPath = testFilesDir.GetTestPath("test.protdb");
using (ProteomeDb proteomeDb = ProteomeDb.CreateProteomeDb(protDbPath))
{
Enzyme trypsin = EnzymeList.GetDefault();
IProgressStatus status = new ProgressStatus(string.Empty);
using (var reader = new StreamReader(fastaPath))
{
proteomeDb.AddFastaFile(reader, new SilentProgressMonitor(), ref status, true); // Delay indexing
}
// perform digestion
proteomeDb.Digest(new ProteaseImpl(trypsin), ProteomeDb.PROTDB_MAX_MISSED_CLEAVAGES, new SilentProgressMonitor(), ref status);
Digestion digestion = proteomeDb.GetDigestion(trypsin.Name);
var digestedProteins0 = digestion.GetProteinsWithSequencePrefix("EDGWVK", 100);
Assert.IsTrue(digestedProteins0.Count >= 1);
}
}
}
public void SettingsChangePeptides()
{
SrmDocument docFasta = CreateMixedDoc();
const int posList = 0; // Peptide list is first peptide group.
SrmSettings settings = docFasta.Settings;
// Change enzymes, and verify expected peptide changes
var enzymes = new EnzymeList();
enzymes.AddDefaults();
SrmDocument docCnbr = docFasta.ChangeSettings(settings.ChangePeptideSettings(
p => p.ChangeEnzyme(enzymes["CNBr [M | P]"])));
foreach (PeptideDocNode nodePeptide in docCnbr.Peptides)
{
if (nodePeptide.Peptide.FastaSequence == null)
continue;
Peptide peptide = nodePeptide.Peptide;
char prev = peptide.PrevAA;
if (prev != 'M')
Assert.Fail("Unexpected preceding cleavage at {0}", prev);
string seq = peptide.Sequence;
char last = seq[seq.Length - 1];
if (last != 'M' && peptide.NextAA != '-')
Assert.Fail("Unexpected cleavage at {0}", last);
}
Assert.IsTrue(docCnbr.PeptideCount < docFasta.PeptideCount);
// Peptide list should not have changed.
Assert.AreSame(docFasta.Children[posList], docCnbr.Children[posList]);
// Change back to original enzyme, and make sure peptides are restored
SrmDocument docFasta2 = docCnbr.ChangeSettings(settings);
Assert.AreEqual(docFasta.RevisionIndex + 2, docFasta2.RevisionIndex);
Assert.AreEqual(docFasta.PeptideCount, docFasta2.PeptideCount);
Assert.AreEqual(docFasta.PeptideTransitionCount, docFasta2.PeptideTransitionCount);
// Allow missed cleavages, and verify changes
docFasta2 = docFasta.ChangeSettings(settings.ChangePeptideSettings(
p => p.ChangeDigestSettings(new DigestSettings(1, false))));
Assert.IsTrue(docFasta.PeptideCount < docFasta2.PeptideCount);
// TODO: Make minimum transition count work immediately
// Assert.IsTrue((docFasta2.PeptideCount - docFasta.PeptideCount) * 3 <
// docFasta2.TransitionCount - docFasta.TransitionCount);
int missedCleavageCount = 0;
var dictOrig = docFasta.Peptides.ToDictionary(node => node.Peptide);
foreach (PeptideDocNode nodePeptide in docFasta2.Peptides)
{
// Make sure all zero-cleavage peptides are the same as the old document
int missed = nodePeptide.Peptide.MissedCleavages;
if (missed == 0)
Assert.AreEqual(nodePeptide, dictOrig[nodePeptide.Peptide]);
// Count the number of new missed cleavages
missedCleavageCount += nodePeptide.Peptide.MissedCleavages;
}
Assert.AreEqual(docFasta2.PeptideCount - docFasta.PeptideCount, missedCleavageCount);
// Peptide list should not have changed.
Assert.AreSame(docFasta.Children[posList], docFasta2.Children[posList]);
// Increase minimum peptide length
const int minNew = 12;
docFasta2 = docFasta.ChangeSettings(settings.ChangePeptideFilter(f => f.ChangeMinPeptideLength(minNew)));
CheckPeptides(docFasta, docFasta2, node => node.Peptide.Length >= minNew);
Assert.AreSame(docFasta.Children[posList], docFasta2.Children[posList]);
// Decrease maximum peptide length
const int maxNew = 18;
docFasta2 = docFasta.ChangeSettings(settings.ChangePeptideFilter(f => f.ChangeMaxPeptideLength(maxNew)));
CheckPeptides(docFasta, docFasta2, node => node.Peptide.Length <= maxNew);
Assert.AreSame(docFasta.Children[posList], docFasta2.Children[posList]);
// Increase n-term AA exclustion
const int ntermStart = 50;
docFasta2 = docFasta.ChangeSettings(settings.ChangePeptideFilter(
f => f.ChangeExcludeNTermAAs(ntermStart)));
CheckPeptides(docFasta, docFasta2, node =>
node.Peptide.Begin.HasValue && node.Peptide.Begin.Value >= ntermStart);
Assert.AreSame(docFasta.Children[posList], docFasta2.Children[posList]);
// Use ragged end exclusion
docFasta2 = docFasta.ChangeSettings(settings.ChangePeptideSettings(
p => p.ChangeDigestSettings(new DigestSettings(0, true))));
CheckPeptides(docFasta, docFasta2, IsNotRagged);
Assert.AreSame(docFasta.Children[posList], docFasta2.Children[posList]);
// Check custom exclusions
var exclusions = new PeptideExcludeList();
exclusions.AddDefaults();
// Exclude Cys
docFasta2 = docFasta.ChangeSettings(settings.ChangePeptideFilter(
f => f.ChangeExclusions(new[] { exclusions["Cys"] })));
CheckPeptides(docFasta, docFasta2, node => node.Peptide.Sequence.IndexOf('C') == -1);
Assert.AreSame(docFasta.Children[posList], docFasta2.Children[posList]);
// Exclude Met
docFasta2 = docFasta.ChangeSettings(settings.ChangePeptideFilter(
f => f.ChangeExclusions(new[] { exclusions["Met"] })));
CheckPeptides(docFasta, docFasta2, node => node.Peptide.Sequence.IndexOf('M') == -1);
// Exclude Hys
docFasta2 = docFasta.ChangeSettings(settings.ChangePeptideFilter(
f => f.ChangeExclusions(new[] { exclusions["His"] })));
CheckPeptides(docFasta, docFasta2, node => node.Peptide.Sequence.IndexOf('H') == -1);
// Exclude NXS/NXT
Regex regexNx = new Regex("N.[ST]");
docFasta2 = docFasta.ChangeSettings(settings.ChangePeptideFilter(
f => f.ChangeExclusions(new[] { exclusions["NXT/NXS"] })));
CheckPeptides(docFasta, docFasta2, node => !regexNx.Match(node.Peptide.Sequence).Success);
// Exclude RP/KP
docFasta2 = docFasta.ChangeSettings(settings.ChangePeptideFilter(
f => f.ChangeExclusions(new[] { exclusions["RP/KP"] })));
CheckPeptides(docFasta, docFasta2, node => node.Peptide.Sequence.IndexOf("RP", StringComparison.Ordinal) == -1 &&
node.Peptide.Sequence.IndexOf("KP", StringComparison.Ordinal) == -1);
// Custom exclude ^Q*K$
var excludeCustom = new PeptideExcludeRegex("Custom", "^Q.*K$");
docFasta2 = docFasta.ChangeSettings(settings.ChangePeptideFilter(
f => f.ChangeExclusions(new[] { excludeCustom })));
CheckPeptides(docFasta, docFasta2, node =>
(!node.Peptide.Sequence.StartsWith("Q") || !node.Peptide.Sequence.EndsWith("K")));
// Auto-picking off should keep any changes from occurring
docFasta2 = docFasta.ChangeSettings(settings.ChangePeptideFilter(
f => f.ChangeAutoSelect(false).ChangeExclusions(new[] { exclusions["Cys"], exclusions["Met"], excludeCustom })));
Assert.AreSame(docFasta.Children, docFasta2.Children);
// Removing restriction with auto-picking off should change anything
settings = docFasta2.Settings;
SrmDocument docFasta3 = docFasta2.ChangeSettings(settings.ChangePeptideFilter(
f => f.ChangeExclusions(new PeptideExcludeRegex[0])));
Assert.AreSame(docFasta2.Children, docFasta3.Children);
}
public void SettingsChangePeptides()
{
SrmDocument docFasta = CreateMixedDoc();
const int posList = 0; // Peptide list is first peptide group.
SrmSettings settings = docFasta.Settings;
// Change enzymes, and verify expected peptide changes
var enzymes = new EnzymeList();
enzymes.AddDefaults();
SrmDocument docCnbr = docFasta.ChangeSettings(settings.ChangePeptideSettings(
p => p.ChangeEnzyme(enzymes["CNBr [M | P]"])));
foreach (PeptideDocNode nodePeptide in docCnbr.Peptides)
{
if (nodePeptide.Peptide.FastaSequence == null)
{
continue;
}
Peptide peptide = nodePeptide.Peptide;
char prev = peptide.PrevAA;
if (prev != 'M')
{
Assert.Fail("Unexpected preceding cleavage at {0}", prev);
}
string seq = peptide.Sequence;
char last = seq[seq.Length - 1];
if (last != 'M' && peptide.NextAA != '-')
{
Assert.Fail("Unexpected cleavage at {0}", last);
}
}
Assert.IsTrue(docCnbr.PeptideCount < docFasta.PeptideCount);
// Peptide list should not have changed.
Assert.AreSame(docFasta.Children[posList], docCnbr.Children[posList]);
// Change back to original enzyme, and make sure peptides are restored
SrmDocument docFasta2 = docCnbr.ChangeSettings(settings);
Assert.AreEqual(docFasta.RevisionIndex + 2, docFasta2.RevisionIndex);
Assert.AreEqual(docFasta.PeptideCount, docFasta2.PeptideCount);
Assert.AreEqual(docFasta.PeptideTransitionCount, docFasta2.PeptideTransitionCount);
// Allow missed cleavages, and verify changes
docFasta2 = docFasta.ChangeSettings(settings.ChangePeptideSettings(
p => p.ChangeDigestSettings(new DigestSettings(1, false))));
Assert.IsTrue(docFasta.PeptideCount < docFasta2.PeptideCount);
// TODO: Make minimum transition count work immediately
// Assert.IsTrue((docFasta2.PeptideCount - docFasta.PeptideCount) * 3 <
// docFasta2.TransitionCount - docFasta.TransitionCount);
int missedCleavageCount = 0;
var dictOrig = docFasta.Peptides.ToDictionary(node => node.Peptide);
foreach (PeptideDocNode nodePeptide in docFasta2.Peptides)
{
// Make sure all zero-cleavage peptides are the same as the old document
int missed = nodePeptide.Peptide.MissedCleavages;
if (missed == 0)
{
Assert.AreEqual(nodePeptide, dictOrig[nodePeptide.Peptide]);
}
// Count the number of new missed cleavages
missedCleavageCount += nodePeptide.Peptide.MissedCleavages;
}
Assert.AreEqual(docFasta2.PeptideCount - docFasta.PeptideCount, missedCleavageCount);
// Peptide list should not have changed.
Assert.AreSame(docFasta.Children[posList], docFasta2.Children[posList]);
// Increase minimum peptide length
const int minNew = 12;
docFasta2 = docFasta.ChangeSettings(settings.ChangePeptideFilter(f => f.ChangeMinPeptideLength(minNew)));
CheckPeptides(docFasta, docFasta2, node => node.Peptide.Length >= minNew);
Assert.AreSame(docFasta.Children[posList], docFasta2.Children[posList]);
// Decrease maximum peptide length
const int maxNew = 18;
docFasta2 = docFasta.ChangeSettings(settings.ChangePeptideFilter(f => f.ChangeMaxPeptideLength(maxNew)));
CheckPeptides(docFasta, docFasta2, node => node.Peptide.Length <= maxNew);
Assert.AreSame(docFasta.Children[posList], docFasta2.Children[posList]);
// Increase n-term AA exclustion
const int ntermStart = 50;
docFasta2 = docFasta.ChangeSettings(settings.ChangePeptideFilter(
f => f.ChangeExcludeNTermAAs(ntermStart)));
CheckPeptides(docFasta, docFasta2, node =>
node.Peptide.Begin.HasValue && node.Peptide.Begin.Value >= ntermStart);
Assert.AreSame(docFasta.Children[posList], docFasta2.Children[posList]);
// Use ragged end exclusion
docFasta2 = docFasta.ChangeSettings(settings.ChangePeptideSettings(
p => p.ChangeDigestSettings(new DigestSettings(0, true))));
CheckPeptides(docFasta, docFasta2, IsNotRagged);
Assert.AreSame(docFasta.Children[posList], docFasta2.Children[posList]);
// Check custom exclusions
var exclusions = new PeptideExcludeList();
exclusions.AddDefaults();
// Exclude Cys
docFasta2 = docFasta.ChangeSettings(settings.ChangePeptideFilter(
f => f.ChangeExclusions(new[] { exclusions["Cys"] })));
CheckPeptides(docFasta, docFasta2, node => node.Peptide.Sequence.IndexOf('C') == -1);
Assert.AreSame(docFasta.Children[posList], docFasta2.Children[posList]);
// Exclude Met
docFasta2 = docFasta.ChangeSettings(settings.ChangePeptideFilter(
f => f.ChangeExclusions(new[] { exclusions["Met"] })));
CheckPeptides(docFasta, docFasta2, node => node.Peptide.Sequence.IndexOf('M') == -1);
// Exclude Hys
docFasta2 = docFasta.ChangeSettings(settings.ChangePeptideFilter(
f => f.ChangeExclusions(new[] { exclusions["His"] })));
CheckPeptides(docFasta, docFasta2, node => node.Peptide.Sequence.IndexOf('H') == -1);
// Exclude NXS/NXT
Regex regexNx = new Regex("N.[ST]");
docFasta2 = docFasta.ChangeSettings(settings.ChangePeptideFilter(
f => f.ChangeExclusions(new[] { exclusions["NXT/NXS"] })));
CheckPeptides(docFasta, docFasta2, node => !regexNx.Match(node.Peptide.Sequence).Success);
// Exclude RP/KP
docFasta2 = docFasta.ChangeSettings(settings.ChangePeptideFilter(
f => f.ChangeExclusions(new[] { exclusions["RP/KP"] })));
CheckPeptides(docFasta, docFasta2, node => node.Peptide.Sequence.IndexOf("RP", StringComparison.Ordinal) == -1 &&
node.Peptide.Sequence.IndexOf("KP", StringComparison.Ordinal) == -1);
// Custom exclude ^Q*K$
var excludeCustom = new PeptideExcludeRegex("Custom", "^Q.*K$");
docFasta2 = docFasta.ChangeSettings(settings.ChangePeptideFilter(
f => f.ChangeExclusions(new[] { excludeCustom })));
CheckPeptides(docFasta, docFasta2, node =>
(!node.Peptide.Sequence.StartsWith("Q") || !node.Peptide.Sequence.EndsWith("K")));
// Auto-picking off should keep any changes from occurring
docFasta2 = docFasta.ChangeSettings(settings.ChangePeptideFilter(
f => f.ChangeAutoSelect(false).ChangeExclusions(new[] { exclusions["Cys"], exclusions["Met"], excludeCustom })));
Assert.AreSame(docFasta.Children, docFasta2.Children);
// Removing restriction with auto-picking off should change anything
settings = docFasta2.Settings;
SrmDocument docFasta3 = docFasta2.ChangeSettings(settings.ChangePeptideFilter(
f => f.ChangeExclusions(new PeptideExcludeRegex[0])));
Assert.AreSame(docFasta2.Children, docFasta3.Children);
}
