public void TestForJiaData()
{
var methodName = MethodBase.GetCurrentMethod().Name;
Utils.ShowStarting(methodName);
// QC_Shew
//const string specFilePath = @"C:\cygwin\home\kims336\Data\TopDownQCShew\raw\QC_ShewIntact_2ug_3k_CID_4Apr14_Bane_PL011402.raw";
// var dbFilePath = Path.Combine(Utils.DEFAULT_TEST_FILE_FOLDER, @"MSPathFinderT\ID_002216_235ACCEA.fasta");
//const string dbFilePath = @"C:\cygwin\home\kims336\Data\TopDownQCShew\database\Test.fasta";
// Jia's data
const string specFilePath = @"C:\cygwin\home\kims336\Data\TopDownJia\raw\Synocho_D1_1.raw";
const string dbFilePath = @"C:\cygwin\home\kims336\Data\TopDownJia\database\ID_003962_71E1A1D4.fasta";
const string outputDir = @"C:\cygwin\home\kims336\Data\TopDownJia\raw\D1_1_Mode1";
if (!File.Exists(specFilePath))
{
Assert.Ignore(@"Skipping test {0} since file not found: {1}", methodName, specFilePath);
}
if (!File.Exists(dbFilePath))
{
Assert.Ignore(@"Skipping test {0} since file not found: {1}", methodName, dbFilePath);
}
// Configure amino acid set
var oxM = new SearchModification(Modification.Oxidation, 'M', SequenceLocation.Everywhere, false);
var dehydroC = new SearchModification(Modification.Dehydro, 'C', SequenceLocation.Everywhere, false);
var glutathioneC = new SearchModification(Modification.Glutathione, 'C', SequenceLocation.Everywhere, false);
var nitrosylC = new SearchModification(Modification.Nitrosyl, 'C', SequenceLocation.Everywhere, false);
var nethylmaleimideC = new SearchModification(Modification.Nethylmaleimide, 'C', SequenceLocation.Everywhere, false);
//var acetylN = new SearchModification(Modification.Acetylation, '*', SequenceLocation.ProteinNTerm, false);
//var pyroGluQ = new SearchModification(Modification.PyroGluQ, 'Q', SequenceLocation.Everywhere, false);
//var cysteinylC = new SearchModification(Modification.Cysteinyl, 'C', SequenceLocation.Everywhere, false);
//var deamdN = new SearchModification(Modification.Deamidation, 'N', SequenceLocation.Everywhere, false);
//var deamdQ = new SearchModification(Modification.Deamidation, 'Q', SequenceLocation.Everywhere, false);
const int numMaxModsPerProtein = 4;
var searchModifications = new List <SearchModification>
{
dehydroC,
glutathioneC,
nitrosylC,
nethylmaleimideC,
oxM,
};
var aaSet = new AminoAcidSet(searchModifications, numMaxModsPerProtein);
const InternalCleavageType searchMode = InternalCleavageType.SingleInternalCleavage; // 0: all subsequences, 1: close to N- or C-term, 2: close to N- and C-term
DatabaseSearchMode tda = DatabaseSearchMode.Both; // true: target & decoy, false: target, null: decoy
TestTopDownSearch(specFilePath, dbFilePath, outputDir, aaSet, tda, searchMode);
}
private void TestTopDownSearch(string specFilePath, string dbFilePath, string outputDir, AminoAcidSet aaSet,
int minSequenceLength, int maxSequenceLength,
int minPrecursorIonCharge, int maxPrecursorIonCharge,
int minProductIonCharge, int maxProductIonCharge,
double minSequenceMass, double maxSequenceMass,
DatabaseSearchMode tda, InternalCleavageType searchMode)
{
var methodName = MethodBase.GetCurrentMethod().Name;
Utils.ShowStarting(methodName);
// Search parameters
const int maxNumNTermCleavages = 1; // 30
const int maxNumCTermCleavages = 0;
const int precursorIonTolerancePpm = 10;
const int productIonTolerancePpm = 10;
var topDownOptions = new MsPfParameters(
specFilePath,
dbFilePath,
outputDir,
aaSet, "")
{
MinSequenceLength = minSequenceLength,
MaxSequenceLength = maxSequenceLength,
MaxNumNTermCleavages = maxNumNTermCleavages,
MaxNumCTermCleavages = maxNumCTermCleavages,
MinPrecursorIonCharge = minPrecursorIonCharge,
MaxPrecursorIonCharge = maxPrecursorIonCharge,
MinProductIonCharge = minProductIonCharge,
MaxProductIonCharge = maxProductIonCharge,
MinSequenceMass = minSequenceMass,
MaxSequenceMass = maxSequenceMass,
PrecursorIonTolerancePpm = precursorIonTolerancePpm,
ProductIonTolerancePpm = productIonTolerancePpm,
TargetDecoySearchMode = tda,
InternalCleavageMode = searchMode,
};
var topDownLauncher = new IcTopDownLauncher(topDownOptions);
//topDownLauncher.ForceParallel = true;
//topDownLauncher.MaxNumThreads = -1;
topDownLauncher.RunSearch(0.7);
//topDownLauncher.RunIntactProteinSearch();
}
public void TestForSbepData()
{
var methodName = MethodBase.GetCurrentMethod().Name;
Utils.ShowStarting(methodName);
//// Salmonella
var specFilePath = Path.Combine(Utils.DEFAULT_TEST_FILE_FOLDER, @"TopDown\SBEP_STM_001_02272012_Aragon.raw");
var dbFilePath = Path.Combine(Utils.DEFAULT_TEST_FILE_FOLDER, @"MSPathFinderT\ID_002166_F86E3B2F.fasta");
var outputDir = Path.Combine(Utils.DEFAULT_TEST_FILE_FOLDER, @"Results\Mod_M2");
if (!File.Exists(specFilePath))
{
Assert.Ignore(@"Skipping test {0} since file not found: {1}", methodName, specFilePath);
}
if (!File.Exists(dbFilePath))
{
Assert.Ignore(@"Skipping test {0} since file not found: {1}", methodName, dbFilePath);
}
if (!Directory.Exists(outputDir))
{
Assert.Ignore(@"Skipping test {0} since folder not found: {1}", methodName, outputDir);
}
// Configure amino acid set
var acetylN = new SearchModification(Modification.Acetylation, '*', SequenceLocation.ProteinNTerm, false);
var oxM = new SearchModification(Modification.Oxidation, 'M', SequenceLocation.Everywhere, false);
var dehydroC = new SearchModification(Modification.Dehydro, 'C', SequenceLocation.Everywhere, false);
var glutathioneC = new SearchModification(Modification.Glutathione, 'C', SequenceLocation.Everywhere, false);
const int numMaxModsPerProtein = 4;
var searchModifications = new List <SearchModification>
{
dehydroC,
glutathioneC,
oxM,
acetylN,
};
var aaSet = new AminoAcidSet(searchModifications, numMaxModsPerProtein);
const InternalCleavageType searchMode = InternalCleavageType.NoInternalCleavage; // 0: all subsequences, 1: close to N- or C-term, 2: close to N- and C-term
DatabaseSearchMode tda = DatabaseSearchMode.Both; // true: target & decoy, false: target, null: decoy
TestTopDownSearch(specFilePath, dbFilePath, outputDir, aaSet, tda, searchMode);
}
public void TestForAaronData()
{
var methodName = MethodBase.GetCurrentMethod().Name;
Utils.ShowStarting(methodName);
const string specFilePath = @"C:\cygwin\home\kims336\Data\TopDownAaron\raw\MTB_intact_1.raw";
const string dbFilePath = @"C:\cygwin\home\kims336\Data\TopDownAaron\database\ID_003121_998584F8.fasta";
const string outputDir = @"C:\cygwin\home\kims336\Data\TopDownAaron\Ic\Mode1_07";
if (!File.Exists(specFilePath))
{
Assert.Ignore(@"Skipping test {0} since file not found: {1}", methodName, specFilePath);
}
if (!File.Exists(dbFilePath))
{
Assert.Ignore(@"Skipping test {0} since file not found: {1}", methodName, dbFilePath);
}
// Configure amino acid set
var acetylN = new SearchModification(Modification.Acetylation, '*', SequenceLocation.ProteinNTerm, false);
var oxM = new SearchModification(Modification.Oxidation, 'M', SequenceLocation.Everywhere, false);
var dehydroC = new SearchModification(Modification.Dehydro, 'C', SequenceLocation.Everywhere, false);
var tevFp2C = new SearchModification(Modification.TevFp2, 'S', SequenceLocation.Everywhere, false);
const int numMaxModsPerProtein = 4;
var searchModifications = new List <SearchModification>
{
dehydroC,
//glutathioneC,
//nitrosylC,
//nethylmaleimideC,
oxM,
acetylN,
tevFp2C
};
var aaSet = new AminoAcidSet(searchModifications, numMaxModsPerProtein);
const InternalCleavageType searchMode = InternalCleavageType.SingleInternalCleavage; // 0: all subsequences, 1: close to N- or C-term, 2: close to N- and C-term
DatabaseSearchMode tda = DatabaseSearchMode.Both; // true: target & decoy, false: target, null: decoy
TestTopDownSearch(specFilePath, dbFilePath, outputDir, aaSet, tda, searchMode);
}
public void TestForQcShew()
{
var methodName = MethodBase.GetCurrentMethod().Name;
Utils.ShowStarting(methodName);
// QC_Shew
const string specFilePath = @"D:\MassSpecFiles\training\raw\QC_Shew_Intact_26Sep14_Bane_C2Column3.pbf";
const string dbFilePath = @"D:\MSPathFinder\Fasta\ID_002216_235ACCEA.fasta";
const string outputDir = @"D:\MassSpecFiles\training\test";
if (!File.Exists(specFilePath))
{
Assert.Ignore(@"Skipping test {0} since file not found: {1}", methodName, specFilePath);
}
if (!File.Exists(dbFilePath))
{
Assert.Ignore(@"Skipping test {0} since file not found: {1}", methodName, dbFilePath);
}
// Configure amino acid set
var oxM = new SearchModification(Modification.Oxidation, 'M', SequenceLocation.Everywhere, false);
var dehydroC = new SearchModification(Modification.Dehydro, 'C', SequenceLocation.Everywhere, false);
var acetylN = new SearchModification(Modification.Acetylation, '*', SequenceLocation.ProteinNTerm, false);
const int numMaxModsPerProtein = 4;
var searchModifications = new List <SearchModification>
{
dehydroC,
oxM,
acetylN
};
var aaSet = new AminoAcidSet(searchModifications, numMaxModsPerProtein);
const InternalCleavageType searchMode = InternalCleavageType.NoInternalCleavage; // 0: all subsequences, 1: close to N- or C-term, 2: close to N- and C-term
DatabaseSearchMode tda = DatabaseSearchMode.Both; // true: target & decoy, false: target, null: decoy
TestTopDownSearch(specFilePath, dbFilePath, outputDir, aaSet, tda, searchMode);
}
private void TestTopDownSearch(string specFilePath, string dbFilePath, string outputDir, AminoAcidSet aaSet,
DatabaseSearchMode tda, InternalCleavageType searchMode)
{
var methodName = MethodBase.GetCurrentMethod().Name;
Utils.ShowStarting(methodName);
const int minSequenceLength = 21; // 7
const int maxSequenceLength = 500; // 1000
const int minPrecursorIonCharge = 2; // 3
const int maxPrecursorIonCharge = 60; // 67
const int minProductIonCharge = 1; // 1
const int maxProductIonCharge = 20; // 15
const double minSequenceMass = 3000.0;
const double maxSequenceMass = 50000.0;
TestTopDownSearch(specFilePath, dbFilePath, outputDir, aaSet,
minSequenceLength, maxSequenceLength,
minPrecursorIonCharge, maxPrecursorIonCharge,
minProductIonCharge, maxProductIonCharge,
minSequenceMass, maxSequenceMass,
tda, searchMode
);
}
/// <summary>
/// Estimate the total number of peptides that will be used in processing - essential for reasonably accurate progress reporting
/// </summary>
/// <param name="mode"></param>
/// <param name="minLength"></param>
/// <param name="maxLength"></param>
/// <param name="numNTermCleavages"></param>
/// <param name="numCTermCleavages"></param>
/// <returns></returns>
public long EstimateTotalPeptides(InternalCleavageType mode, int minLength = 21, int maxLength = 300, int numNTermCleavages = 1, int numCTermCleavages = 0)
{
long count = 0;
if (mode == InternalCleavageType.MultipleInternalCleavages)
{
var curSequence = new LinkedList <byte>();
var lcpList = new LinkedList <byte>();
var lcpEnum = PLcps().GetEnumerator();
var fEnum = FastaDatabase.Characters().GetEnumerator();
// Use "IntWrapper" to allow modifying the value inside of the foreach
var seps = new Queue <IntWrapper>();
bool read = false;
while ((read = fEnum.MoveNext()) || curSequence.Count >= minLength)
{
if (read)
{
lcpEnum.MoveNext();
curSequence.AddLast(fEnum.Current);
lcpList.AddLast(lcpEnum.Current);
if (fEnum.Current == FastaDatabaseConstants.Delimiter)
{
seps.Enqueue(new IntWrapper(curSequence.Count - 1));
}
if (curSequence.Count < maxLength + 2)
{
continue;
}
}
if (seps.Count > 0 && seps.Peek().Value == 0)
{
seps.Dequeue();
}
var min = minLength > lcpList.First.Value ? minLength : lcpList.First.Value;
if (seps.Count == 0 || seps.Peek().Value >= maxLength + 2)
{
count += maxLength + 2 - min;
}
else if (seps.Peek().Value >= min)
{
count += seps.Peek().Value - min;
}
curSequence.RemoveFirst();
lcpList.RemoveFirst();
foreach (var sep in seps)
{
--sep.Value;
}
}
}
else
{
// mode 2
foreach (var sonc in SequencesWithOffsetNoCleavage())
{
var seqLength = sonc.Sequence.Length;
// mode 2
for (int i = 0; i <= numCTermCleavages; i++)
{
// mode 2
if (mode == InternalCleavageType.NoInternalCleavage && minLength <= seqLength - i && seqLength - i <= maxLength)
{
count++;
}
// mode 1 #1
if (mode == InternalCleavageType.SingleInternalCleavage)
{
for (int j = 0; minLength <= seqLength - i - j; j++)
{
if (seqLength - i - j <= maxLength)
{
count++;
}
}
}
}
if (mode == InternalCleavageType.SingleInternalCleavage)
{
// mode 1 #2
for (int i = numCTermCleavages + 1; i <= seqLength - minLength; i++)
{
for (int j = 0; j <= numNTermCleavages; j++)
{
if (minLength <= seqLength - i - j &&
seqLength - i - j <= maxLength)
{
count++;
}
}
}
}
}
}
return(count);
}
public void TestForVlad()
{
var methodName = MethodBase.GetCurrentMethod().Name;
Utils.ShowStarting(methodName);
const string specFilePath = @"D:\Research\Data\Vlad\raw\Alz_RA_C1_HCD_11012013_SW_03Nov2013.raw";
const string dbFilePath = @"D:\Research\Data\Vlad\database\ID_004221_1C042A1F.fasta";
//const string dbFilePath = @"D:\Research\Data\Vlad\database\HBA_MOUSE.fasta";
const string outputDir = @"D:\Research\Data\Vlad\Ic\POPSICLETest_M1";
if (!File.Exists(specFilePath))
{
Assert.Ignore(@"Skipping test {0} since file not found: {1}", methodName, specFilePath);
}
if (!File.Exists(dbFilePath))
{
Assert.Ignore(@"Skipping test {0} since file not found: {1}", methodName, dbFilePath);
}
// Configure amino acid set
var acetylN = new SearchModification(Modification.Acetylation, '*', SequenceLocation.ProteinNTerm, false);
var oxM = new SearchModification(Modification.Oxidation, 'M', SequenceLocation.Everywhere, false);
var dehydroC = new SearchModification(Modification.Dehydro, 'C', SequenceLocation.Everywhere, false);
var glutathioneC = new SearchModification(Modification.Glutathione, 'C', SequenceLocation.Everywhere, false);
var thrToAla = new SearchModification(Modification.ThrToAla, 'T', SequenceLocation.Everywhere, false);
var dethiomethylM = new SearchModification(Modification.Dethiomethyl, 'M', SequenceLocation.Everywhere, false);
var deamidatedN = new SearchModification(Modification.Deamidation, 'N', SequenceLocation.Everywhere, false);
var deamidatedQ = new SearchModification(Modification.Deamidation, 'Q', SequenceLocation.Everywhere, false);
var serToAsn = new SearchModification(Modification.SerToAsn, 'S', SequenceLocation.Everywhere, false);
var pyroCarbamidomethylC = new SearchModification(Modification.PyroCarbamidomethyl, 'C',
SequenceLocation.ProteinNTerm, false);
var phosphoS = new SearchModification(Modification.Phosphorylation, 'S', SequenceLocation.Everywhere, false);
var phosphoT = new SearchModification(Modification.Phosphorylation, 'T', SequenceLocation.Everywhere, false);
var phosphoY = new SearchModification(Modification.Phosphorylation, 'Y', SequenceLocation.Everywhere, false);
const int numMaxModsPerProtein = 4;
var searchModifications = new List <SearchModification>
{
dehydroC,
// glutathioneC,
oxM,
// dethiomethylM,
acetylN,
phosphoS,
phosphoT,
phosphoY
// thrToAla,
// serToAsn,
// deamidatedN,
// deamidatedQ,
// pyroCarbamidomethylC
};
var aaSet = new AminoAcidSet(searchModifications, numMaxModsPerProtein);
const InternalCleavageType searchMode = InternalCleavageType.SingleInternalCleavage; // 0: all subsequences, 1: close to N- or C-term, 2: close to N- and C-term
DatabaseSearchMode tda = DatabaseSearchMode.Target; // true: target & decoy, false: target, null: decoy
TestTopDownSearch(specFilePath, dbFilePath, outputDir, aaSet, tda, searchMode);
}
public void TestForYufeng()
{
var methodName = MethodBase.GetCurrentMethod().Name;
Utils.ShowStarting(methodName);
// QC_Shew
const string specFilePath = @"H:\Research\Yufeng\TopDownYufeng\raw\yufeng_column_test2.raw";
//const string dbFilePath = @"H:\Research\Yufeng\TopDownYufeng\database\ID_002216_235ACCEA.fasta";
const string dbFilePath = @"H:\Research\Yufeng\TopDownYufeng\database\SO_3942_Truncated.fasta";
const string outputDir = @"H:\Research\Yufeng\TopDownYufeng\Debug";
if (!File.Exists(specFilePath))
{
Assert.Ignore(@"Skipping test {0} since file not found: {1}", methodName, specFilePath);
}
if (!File.Exists(dbFilePath))
{
Assert.Ignore(@"Skipping test {0} since file not found: {1}", methodName, dbFilePath);
}
// Configure amino acid set
//var oxM = new SearchModification(Modification.Oxidation, 'M', SequenceLocation.Everywhere, false);
//var dehydroC = new SearchModification(Modification.Dehydro, 'C', SequenceLocation.Everywhere, false);
//// var glutathioneC = new SearchModification(Modification.Glutathione, 'C', SequenceLocation.Everywhere, false);
//var acetylN = new SearchModification(Modification.Acetylation, '*', SequenceLocation.ProteinNTerm, false);
//var pyroGluQ = new SearchModification(Modification.PTeyroGluQ, 'Q', SequenceLocation.Everywhere, false);
//var cysteinylC = new SearchModification(Modification.Cysteinyl, 'C', SequenceLocation.Everywhere, false);
//var deamdN = new SearchModification(Modification.Deamidation, 'N', SequenceLocation.Everywhere, false);
//var deamdQ = new SearchModification(Modification.Deamidation, 'Q', SequenceLocation.Everywhere, false);
//const int numMaxModsPerProtein = 0;
//var searchModifications = new List<SearchModification>
//{
// dehydroC,
// oxM,
// acetylN
//};
//var aaSet = new AminoAcidSet(searchModifications, numMaxModsPerProtein);
var aaSet = new AminoAcidSet();
const InternalCleavageType searchMode = InternalCleavageType.NoInternalCleavage; // 0: all subsequences, 1: close to N- or C-term, 2: close to N- and C-term
DatabaseSearchMode tda = DatabaseSearchMode.Target; // true: target & decoy, false: target, null: decoy
const int minSequenceLength = 21; // 7
const int maxSequenceLength = 500; // 1000
const int minPrecursorIonCharge = 2; // 3
const int maxPrecursorIonCharge = 50; // 67
const int minProductIonCharge = 1; // 1
const int maxProductIonCharge = 20; // 15
const double minSequenceMass = 3000.0;
const double maxSequenceMass = 50000.0;
TestTopDownSearch(specFilePath, dbFilePath, outputDir, aaSet,
minSequenceLength, maxSequenceLength,
minPrecursorIonCharge, maxPrecursorIonCharge,
minProductIonCharge, maxProductIonCharge,
minSequenceMass, maxSequenceMass,
tda, searchMode
);
}
public long EstimateTotalPeptides(InternalCleavageType mode, int minLength = 21, int maxLength = 300, int numNTermCleavages = 1, int numCTermCleavages = 0)
{
long count = 0;
if (mode == InternalCleavageType.MultipleInternalCleavages)
{
var curSequence = new LinkedList<byte>();
var lcpList = new LinkedList<byte>();
var lcpEnum = PLcps().GetEnumerator();
var fEnum = FastaDatabase.Characters().GetEnumerator();
var seps = new Queue<IntWrapper>();
bool read = false;
while ((read = fEnum.MoveNext()) || curSequence.Count >= minLength)
{
if (read)
{
lcpEnum.MoveNext();
curSequence.AddLast(fEnum.Current);
lcpList.AddLast(lcpEnum.Current);
if (fEnum.Current == FastaDatabase.Delimiter)
{
seps.Enqueue(new IntWrapper(curSequence.Count - 1));
}
if (curSequence.Count < maxLength + 2) continue;
}
if (seps.Count > 0 && seps.Peek().Value == 0)
{
seps.Dequeue();
}
var min = minLength > lcpList.First.Value ? minLength : lcpList.First.Value;
if (seps.Count == 0 || seps.Peek().Value >= maxLength + 2)
{
count += maxLength + 2 - min;
}
else if (seps.Peek().Value >= min)
{
count += seps.Peek().Value - min;
}
curSequence.RemoveFirst();
lcpList.RemoveFirst();
foreach (var sep in seps)
{
--sep.Value;
}
}
}
else
{
// mode 2
foreach (var sonc in SequencesWithOffsetNoCleavage())
{
var seqLength = sonc.Sequence.Length;
// mode 2
for (int i = 0; i <= numCTermCleavages; i++)
{
// mode 2
if (mode == InternalCleavageType.NoInternalCleavage && minLength <= seqLength - i && seqLength - i <= maxLength)
{
count++;
}
// mode 1 #1
if (mode == InternalCleavageType.SingleInternalCleavage)
{
for (int j = 0; minLength <= seqLength - i - j; j++)
{
if (seqLength - i - j <= maxLength)
{
count++;
}
}
}
}
if (mode == InternalCleavageType.SingleInternalCleavage)
{
// mode 1 #2
for (int i = numCTermCleavages + 1; i <= seqLength - minLength; i++)
{
for (int j = 0; j <= numNTermCleavages; j++)
{
if (minLength <= seqLength - i - j &&
seqLength - i - j <= maxLength)
{
count++;
}
}
}
}
}
}
return count;
}
