public static void ExampleProteinGrouping(IProtease protease, double percentIdentified = 0.01, int maxMissed = 3, int minLength = 5, int maxLength = 50)
{
Stopwatch watch = new Stopwatch();
watch.Start();
List <Peptide> peps = new List <Peptide>(1000000);
List <Protein> proteins = new List <Protein>(7000);
using (FastaReader reader = new FastaReader("Resources/yeast_uniprot_120226.fasta"))
{
foreach (Protein protein in reader.ReadNextProtein())
{
peps.AddRange(protein.Digest(protease, maxMissed, minLength, maxLength));
proteins.Add(protein);
}
}
Console.WriteLine("Loaded {0:N0} peptides from {1:N0} proteins in {2} ms", peps.Count, proteins.Count, watch.ElapsedMilliseconds);
watch.Restart();
Random random = new Random(480912341);
// Take the first x % to act as our identified peptides
List <Peptide> identifiedPeptides = peps.OrderBy(x => random.Next()).Take((int)(peps.Count * percentIdentified)).ToList();
List <ProteinGroup> proteinGroups = ProteinGroup.GroupProteins(proteins, protease, identifiedPeptides, new AminoAcidLeucineSequenceComparer(), maxMissed).ToList();
watch.Stop();
Console.WriteLine("{0:N0} proteins produced {1:N0} protein groups from {2:N0} identified sequences", proteins.Count, proteinGroups.Count, identifiedPeptides.Count);
Console.WriteLine();
Console.WriteLine("Time elapsed: {0} ms", watch.ElapsedMilliseconds);
}
public static IEnumerable <ProteinGroup> GroupProteins(string fastaFile, IProtease protease, IEnumerable <IAminoAcidSequence> observeredSequences, IEqualityComparer <IAminoAcidSequence> peptideComparer, int MaxMissedCleavages = 3)
{
using (FastaReader fasta = new FastaReader(fastaFile))
{
return(GroupProteins(fasta.ReadNextProtein(), new[] { protease }, observeredSequences, peptideComparer, MaxMissedCleavages));
}
}
public static void StartRamp(IProtease protease, double percentIdentifiedSteps = 0.05, int maxMissed = 3, int minLength = 5, int maxLength = 35)
{
List <Peptide> peps = new List <Peptide>();
List <Protein> proteins = new List <Protein>();
using (FastaReader reader = new FastaReader("Resources/yeast_uniprot_120226.fasta"))
{
foreach (Protein protein in reader.ReadNextProtein())
{
foreach (Peptide peptide in protein.Digest(protease, maxMissed, minLength, maxLength))
{
peps.Add(peptide);
}
proteins.Add(protein);
}
}
// Fixed seed to make it reproducible
Random random = new Random(480912341);
peps = peps.OrderBy(x => random.Next()).ToList();
for (double percentIdentified = 0; percentIdentified <= 1; percentIdentified += percentIdentifiedSteps)
{
// Take the first x % to act as our identified peptides
List <Peptide> identifiedPeptides = peps.Take((int)(peps.Count * percentIdentified)).ToList();
List <ProteinGroup> proteinGroups = ProteinGroup.GroupProteins(proteins, protease, identifiedPeptides, new AminoAcidLeucineSequenceComparer(), maxMissed).ToList();
Console.WriteLine("{0} peptides {1} protein groups", identifiedPeptides.Count, proteinGroups.Count);
}
}
public static void Start(IProtease protease, int maxMissed = 3, int minLength = 5, int maxLength = 35)
{
Console.WriteLine("**Start Morpheus Search**");
Stopwatch watch = new Stopwatch();
watch.Start();
List <int> hashCodes = new List <int>();
// Generate peptide candidates
HashSet <Peptide> peptides = new HashSet <Peptide>();
using (FastaReader reader = new FastaReader("Resources/yeast_uniprot_120226.fasta"))
{
foreach (Protein protein in reader.ReadNextProtein())
{
foreach (Peptide peptide in protein.Digest(protease, maxMissed, minLength, maxLength))
{
peptides.Add(peptide);
}
}
}
MSSearchEngine engine = new MorpheusSearchEngine();
engine.PrecursorMassTolerance = Tolerance.FromPPM(100);
engine.ProductMassTolerance = Tolerance.FromPPM(10);
engine.LoadPeptides(peptides);
watch.Stop();
Console.WriteLine("Time elapsed: {0}", watch.Elapsed);
Console.WriteLine("Memory used: {0:N0} MB", Environment.WorkingSet / (1024 * 1024));
Console.WriteLine("**End Morpheus Search**");
}
public static void ExampleDigestion()
{
const string fastaFilePath = "Resources/yeast_uniprot_120226.fasta";
IProtease trypsin = Protease.GetProtease("Trypsin");
const int maxMissedCleavages = 3;
const int minPeptideLength = 5;
const int maxPeptideLength = 50;
List <double> masses = new List <double>();
Stopwatch watch = new Stopwatch();
watch.Start();
using (FastaReader reader = new FastaReader(fastaFilePath))
{
foreach (Protein protein in reader.ReadNextProtein())
{
foreach (Peptide peptide in protein.Digest(trypsin, maxMissedCleavages, minPeptideLength, maxPeptideLength))
{
masses.Add(peptide.MonoisotopicMass);
}
}
}
//Console.WriteLine("Average Peptide Mass = {0:F4}", masses.Average());
watch.Stop();
Console.WriteLine("Time elapsed: {0}", watch.Elapsed);
}
public static void Start(IProtease protease, int maxMissed = 1, int minLength = 0, int maxLength = int.MaxValue, bool storeSequenceString = true)
{
Console.WriteLine("**Start Digestion**");
Stopwatch watch = new Stopwatch();
watch.Start();
List <Peptide> peps = new List <Peptide>();
List <Protein> prots = new List <Protein>();
List <double> allMzs = new List <double>();
AminoAcidPolymer.StoreSequenceString = storeSequenceString;
using (FastaReader reader = new FastaReader("Resources/yeast_uniprot_120226.fasta"))
{
foreach (Protein protein in reader.ReadNextProtein())
{
foreach (Peptide peptide in protein.Digest(protease, maxMissed, minLength, maxLength))
{
peps.Add(peptide);
allMzs.Add(peptide.ToMz(2)); // forces the calculation of the mass and thus chemical formula
}
prots.Add(protein);
}
}
watch.Stop();
Console.WriteLine("{0:N0} proteins produced {1:N0} peptides using {2:N0} missed cleavages", prots.Count, peps.Count, maxMissed);
Console.WriteLine("Time elapsed: {0}", watch.Elapsed);
Console.WriteLine("Memory used: {0:N0} MB", Environment.WorkingSet / (1024 * 1024));
Console.WriteLine("**End Digestion**");
}
public static void BasicCsvWriting(string outputFilePath)
{
Console.WriteLine("Writing file to: " + outputFilePath);
// Create a stream writer to output data to a stream. In this case, the stream points to a file path on the
// computer and is saved as a file. The using statement is the same as doing the following:
// Stream writer = new StreamWriter(outputFilePath);
// writer.Open();
// writer.WriteLine("Hello World");
// writer.Close();
using (StreamWriter writer = new StreamWriter(outputFilePath))
{
// Now that the stream is open, we can a line of text to it to serve as the header row.
// CSV formats are just text files with fields seperated by commas.
writer.WriteLine("Protein Name,# of Amino Acids,Mass (da)");
// Open a connection to a fasta file (very similar syntax as the StreamWriter above)
using (FastaReader reader = new FastaReader("Resources/yeast_uniprot_120226.fasta"))
{
// Loop over each protein in the fasta file
foreach (Protein protein in reader.ReadNextProtein())
{
// StringBuilder objects are an effective tool for constructing strings to write to files.
StringBuilder sb = new StringBuilder();
// To add items to the string builder, just call the append method with whatever you want to add
sb.Append(protein.Description);
sb.Append(','); // we need to add the delimiter after each field we add as well.
// Add the next item
sb.Append(protein.Length);
sb.Append(',');
// The append method can take any object, it will simply call the .ToString() method on the object supplied.
sb.Append(protein.MonoisotopicMass);
// No delimiter is needed after the last field is added.
// Now to write this string to the file itself.
// We convert the StringBuilder object (named: sb) to a string, and then write it on its own line in the
// file writer (named: writer)
writer.WriteLine(sb.ToString());
}
}
} // The file is automatically written and closed after exiting the using {} block.
}
public static void Start(IProtease protease, double percentIdentified = 0.05, int maxMissed = 3, int minLength = 5, int maxLength = 35)
{
Console.WriteLine("**Start Protein Grouping**");
Stopwatch watch = new Stopwatch();
watch.Start();
List <Peptide> peps = new List <Peptide>();
List <Protein> proteins = new List <Protein>();
using (FastaReader reader = new FastaReader("Resources/yeast_uniprot_120226.fasta"))
{
foreach (Protein protein in reader.ReadNextProtein())
{
foreach (Peptide peptide in protein.Digest(protease, maxMissed, minLength, maxLength))
{
peps.Add(peptide);
}
proteins.Add(protein);
}
}
Console.WriteLine("Loaded {0:N0} peptides from {1:N0} proteins in {2} ms", peps.Count, proteins.Count, watch.ElapsedMilliseconds);
// Fixed seed to make it reproducible
Random random = new Random(480912341);
// Take the first x % to act as our identified peptides
List <Peptide> identifiedPeptides = peps.OrderBy(x => random.Next()).Take((int)(peps.Count * percentIdentified)).ToList();
List <ProteinGroup> proteinGroups = ProteinGroup.GroupProteins(proteins, protease, identifiedPeptides, new AminoAcidLeucineSequenceComparer(), maxMissed).ToList();
watch.Stop();
Console.WriteLine("{0:N0} proteins produced {1:N0} protein groups from {2:N0} identified sequences", proteins.Count, proteinGroups.Count, identifiedPeptides.Count);
Console.WriteLine("Time elapsed: {0}", watch.Elapsed);
Console.WriteLine("Memory used: {0:N0} MB", System.Environment.WorkingSet / (1024 * 1024));
Console.WriteLine("**END Protein Grouping**");
}