[WIP] Transciptomics: Digestion, Fragmentaiton, Decoy Generation

mzLib/MzLibUtil/ClassExtensions.cs

@@ -19,6 +19,7 @@
 using System;
 using System.Collections.Generic;
 using System.Linq;
+using System.Text;
 
 namespace MzLibUtil
 {
@@ -100,6 +101,45 @@ public static bool AllSame<T>(this IEnumerable<T> list)
 
             return true;
         }
-
+
+        /// <summary>
+        /// Transcribes a DNA sequence into an RNA sequence
+        /// </summary>
+        /// <param name="dna">The input dna sequence</param>
+        /// <param name="isCodingStrand">True if the input sequence is the coding strand, False if the input sequence is the template strand</param>
+        /// <returns></returns>
+        public static string Transcribe(this string dna, bool isCodingStrand = true)
+        {
+            var sb = new StringBuilder();
+            foreach (var residue in dna)
+            {
+                if (isCodingStrand)
+                {
+                    sb.Append(residue == 'T' ? 'U' : residue);
+                }
+                else
+                {
+                    switch (residue)
+                    {
+                        case 'A':
+                            sb.Append('U');
+                            break;
+                        case 'T':
+                            sb.Append('A');
+                            break;
+                        case 'C':
+                            sb.Append('G');
+                            break;
+                        case 'G':
+                            sb.Append('C');
+                            break;
+                        default:
+                            sb.Append(residue);
+                            break;
+                    }
+                }
+            }
+            return sb.ToString();
+        }
     }
 }

mzLib/Omics/Digestion/DigestionAgent.cs

@@ -103,5 +103,7 @@ public List<int> GetDigestionSiteIndices(string sequence)
             indices.Add(sequence.Length); // The end of the protein is treated as a cleavage site to retain the c-terminal peptide
             return indices.Distinct().OrderBy(i => i).ToList();
         }
+
+
     }
 }

mzLib/Omics/Digestion/IDigestionParams.cs

@@ -2,7 +2,7 @@
 
 namespace Omics.Digestion
 {
-    public interface IDigestionParams
+    public interface IDigestionParams 
     {
         int MaxMissedCleavages { get; set; }
         int MinLength { get; set; }
@@ -11,5 +11,13 @@ public interface IDigestionParams
         int MaxMods { get; set; }
         DigestionAgent DigestionAgent { get; }
         FragmentationTerminus FragmentationTerminus { get; }
+        CleavageSpecificity SearchModeType { get; }
+
+        /// <summary>
+        /// new terminus parameter is for non and semi specific searches
+        /// </summary>
+        /// <param name="newTerminus"></param>
+        /// <returns></returns>
+        IDigestionParams Clone(FragmentationTerminus? newTerminus = null);
     }
-}
+}

mzLib/Omics/Digestion/LysisProduct.cs

@@ -0,0 +1,187 @@
+using Omics.Modifications;
+
+namespace Omics.Digestion
+{
+    public class LysisProduct
+    {
+        protected string _baseSequence;
+
+        public LysisProduct(IBioPolymer parent, int oneBasedStartResidue, int oneBasedEndResidue, int missedCleavages, 
+            CleavageSpecificity cleavageSpecificityForFdrCategory, string? description = null, string? baseSequence = null)
+        {
+            Parent = parent;
+            OneBasedStartResidue = oneBasedStartResidue;
+            OneBasedEndResidue = oneBasedEndResidue;
+            MissedCleavages = missedCleavages;
+            CleavageSpecificityForFdrCategory = cleavageSpecificityForFdrCategory;
+            Description = description;
+            _baseSequence = baseSequence;
+        }
+
+        [field: NonSerialized] public IBioPolymer Parent { get; protected set; } // BioPolymer that this lysis product is a digestion product of
+        public string Description { get; protected set; } //unstructured explanation of source
+        public int OneBasedStartResidue { get; }// the residue number at which the peptide begins (the first residue in a protein is 1)
+        public int OneBasedEndResidue { get; }// the residue number at which the peptide ends
+        public int MissedCleavages { get; } // the number of missed cleavages this peptide has with respect to the digesting protease
+        public virtual char PreviousResidue => OneBasedStartResidue > 1 ? Parent[OneBasedStartResidue - 2] : '-';
+
+        public virtual char NextResidue => OneBasedEndResidue < Parent.Length ? Parent[OneBasedEndResidue] : '-';
+        public string BaseSequence =>
+            _baseSequence ??= Parent.BaseSequence.Substring(OneBasedStartResidue - 1,
+                OneBasedEndResidue - OneBasedStartResidue + 1);
+        public CleavageSpecificity CleavageSpecificityForFdrCategory { get; set; } //structured explanation of source
+        public int Length => BaseSequence.Length; //how many residues long the peptide is
+        public char this[int zeroBasedIndex] => BaseSequence[zeroBasedIndex];
+
+        protected static IEnumerable<Dictionary<int, Modification>> GetVariableModificationPatterns(Dictionary<int, List<Modification>> possibleVariableModifications, int maxModsForPeptide, int peptideLength)
+        {
+            if (possibleVariableModifications.Count == 0)
+            {
+                yield return null;
+            }
+            else
+            {
+                var possible_variable_modifications = new Dictionary<int, List<Modification>>(possibleVariableModifications);
+
+                int[] base_variable_modification_pattern = new int[peptideLength + 4];
+                var totalAvailableMods = possible_variable_modifications.Sum(b => b.Value == null ? 0 : b.Value.Count);
+                for (int variable_modifications = 0; variable_modifications <= Math.Min(totalAvailableMods, maxModsForPeptide); variable_modifications++)
+                {
+                    foreach (int[] variable_modification_pattern in GetVariableModificationPatterns(new List<KeyValuePair<int, List<Modification>>>(possible_variable_modifications),
+                        possible_variable_modifications.Count - variable_modifications, base_variable_modification_pattern, 0))
+                    {
+                        yield return GetNewVariableModificationPattern(variable_modification_pattern, possible_variable_modifications);
+                    }
+                }
+            }
+        }
+
+        protected Dictionary<int, Modification> GetFixedModsOneIsNterminusOrFivePrime(int peptideLength,
+            IEnumerable<Modification> allKnownFixedModifications)
+        {
+            var fixedModsOneIsNterminus = new Dictionary<int, Modification>(peptideLength + 3);
+            foreach (Modification mod in allKnownFixedModifications)
+            {
+                switch (mod.LocationRestriction)
+                {
+                    case "5'-terminal.":
+                    case "Oligo 5'-terminal.":
+                    case "N-terminal.":
+                    case "Peptide N-terminal.":
+                        //the modification is protease associated and is applied to the n-terminal cleaved residue, not at the beginign of the protein
+                        if (mod.ModificationType == "Protease" && ModificationLocalization.ModFits(mod, Parent.BaseSequence, 1, peptideLength, OneBasedStartResidue))
+                        {
+                            if (OneBasedStartResidue != 1)
+                            {
+                                fixedModsOneIsNterminus[2] = mod;
+                            }
+                        }
+                        //Normal N-terminal peptide modification
+                        else if (ModificationLocalization.ModFits(mod, Parent.BaseSequence, 1, peptideLength, OneBasedStartResidue))
+                        {
+                            fixedModsOneIsNterminus[1] = mod;
+                        }
+                        break;
+
+                    case "Anywhere.":
+                        for (int i = 2; i <= peptideLength + 1; i++)
+                        {
+                            if (ModificationLocalization.ModFits(mod, Parent.BaseSequence, i - 1, peptideLength, OneBasedStartResidue + i - 2))
+                            {
+                                fixedModsOneIsNterminus[i] = mod;
+                            }
+                        }
+                        break;
+
+                    case "3'-terminal.":
+                    case "Oligo 3'-terminal.":
+                    case "C-terminal.":
+                    case "Peptide C-terminal.":
+                        //the modification is protease associated and is applied to the c-terminal cleaved residue, not if it is at the end of the protein
+                        if (mod.ModificationType == "Protease" && ModificationLocalization.ModFits(mod, Parent.BaseSequence, peptideLength, peptideLength, OneBasedStartResidue + peptideLength - 1))
+                        {
+                            if (OneBasedEndResidue != Parent.Length)
+                            {
+                                fixedModsOneIsNterminus[peptideLength + 1] = mod;
+                            }
+
+                        }
+                        //Normal C-terminal peptide modification 
+                        else if (ModificationLocalization.ModFits(mod, Parent.BaseSequence, peptideLength, peptideLength, OneBasedStartResidue + peptideLength - 1))
+                        {
+                            fixedModsOneIsNterminus[peptideLength + 2] = mod;
+                        }
+                        break;
+
+                    default:
+                        throw new NotSupportedException("This terminus localization is not supported.");
+                }
+            }
+            return fixedModsOneIsNterminus;
+        }
+
+
+        private static IEnumerable<int[]> GetVariableModificationPatterns(List<KeyValuePair<int, List<Modification>>> possibleVariableModifications,
+            int unmodifiedResiduesDesired, int[] variableModificationPattern, int index)
+        {
+            if (index < possibleVariableModifications.Count - 1)
+            {
+                if (unmodifiedResiduesDesired > 0)
+                {
+                    variableModificationPattern[possibleVariableModifications[index].Key] = 0;
+                    foreach (int[] new_variable_modification_pattern in GetVariableModificationPatterns(possibleVariableModifications,
+                        unmodifiedResiduesDesired - 1, variableModificationPattern, index + 1))
+                    {
+                        yield return new_variable_modification_pattern;
+                    }
+                }
+                if (unmodifiedResiduesDesired < possibleVariableModifications.Count - index)
+                {
+                    for (int i = 1; i <= possibleVariableModifications[index].Value.Count; i++)
+                    {
+                        variableModificationPattern[possibleVariableModifications[index].Key] = i;
+                        foreach (int[] new_variable_modification_pattern in GetVariableModificationPatterns(possibleVariableModifications,
+                            unmodifiedResiduesDesired, variableModificationPattern, index + 1))
+                        {
+                            yield return new_variable_modification_pattern;
+                        }
+                    }
+                }
+            }
+            else
+            {
+                if (unmodifiedResiduesDesired > 0)
+                {
+                    variableModificationPattern[possibleVariableModifications[index].Key] = 0;
+                    yield return variableModificationPattern;
+                }
+                else
+                {
+                    for (int i = 1; i <= possibleVariableModifications[index].Value.Count; i++)
+                    {
+                        variableModificationPattern[possibleVariableModifications[index].Key] = i;
+                        yield return variableModificationPattern;
+                    }
+                }
+            }
+        }
+
+        private static Dictionary<int, Modification> GetNewVariableModificationPattern(int[] variableModificationArray,
+            IEnumerable<KeyValuePair<int, List<Modification>>> possibleVariableModifications)
+        {
+            var modification_pattern = new Dictionary<int, Modification>();
+
+            foreach (KeyValuePair<int, List<Modification>> kvp in possibleVariableModifications)
+            {
+                if (variableModificationArray[kvp.Key] > 0)
+                {
+                    modification_pattern.Add(kvp.Key, kvp.Value[variableModificationArray[kvp.Key] - 1]);
+                }
+            }
+
+            return modification_pattern;
+        }
+
+
+    }
+}

mzLib/Omics/Fragmentation/FragmentationTerminus.cs

@@ -1,19 +1,12 @@
-using System;
-using System.Collections.Generic;
-using System.Linq;
-using System.Text;
-using System.Threading.Tasks;
-
-namespace Omics.Fragmentation
+namespace Omics.Fragmentation
 {
     public enum FragmentationTerminus
-        {
-            Both, //N- and C-terminus
-            N, //N-terminus only
-            C, //C-terminus only
+    {
+        Both, //N- and C-terminus
+        N, //N-terminus only
+        C, //C-terminus only
         None, //used for internal fragments, could be used for top down intact mass?
         FivePrime, // 5' for NucleicAcids
         ThreePrime, // 3' for NucleicAcids
-        }
-
+    }
 }

mzLib/Omics/Fragmentation/Peptide/DissociationTypeCollection.cs

@@ -1,6 +1,5 @@
 using Chemistry;
 using MassSpectrometry;
-using Omics.Fragmentation;
 
 namespace Omics.Fragmentation.Peptide
 {

mzLib/Omics/Fragmentation/Peptide/TerminusSpecificProductTypes.cs

@@ -1,4 +1,4 @@
-namespace Omics.Fragmentation.Peptide
+namespace Omics.Fragmentation
 {
     public class TerminusSpecificProductTypes
     {

mzLib/Omics/IBioPolymer.cs

@@ -1,24 +1,23 @@
-using Chemistry;
-using MassSpectrometry;
-using System;
-using System.Collections.Generic;
-using System.Linq;
-using System.Text;
-using Omics.Digestion;
+using Omics.Digestion;
 using Omics.Modifications;
 
 namespace Omics
 {
     public interface IBioPolymer 
     {
         string Name { get; }
+        string FullName { get; }
         string BaseSequence { get; }
         int Length { get; }
         string DatabaseFilePath { get; }
         bool IsDecoy { get; }
         bool IsContaminant { get; }
         string Organism { get; }
         string Accession { get; }
+        /// <summary>
+        /// The list of gene names consists of tuples, where Item1 is the type of gene name, and Item2 is the name. There may be many genes and names of a certain type produced when reading an XML protein database.
+        /// </summary>
+        IEnumerable<Tuple<string, string>> GeneNames { get; }
         IDictionary<int, List<Modification>> OneBasedPossibleLocalizedModifications { get; }
         char this[int zeroBasedIndex] => BaseSequence[zeroBasedIndex];
 

mzLib/Omics/IBioPolymerWithSetMods.cs

@@ -18,6 +18,7 @@ public interface IBioPolymerWithSetMods : IHasChemicalFormula
     {
         string BaseSequence { get; }
         string FullSequence { get; }
+        string Description { get; }
         double MostAbundantMonoisotopicMass { get; }
         string SequenceWithChemicalFormulas { get; }
         int OneBasedStartResidue { get; }
@@ -41,6 +42,8 @@ public void Fragment(DissociationType dissociationType, FragmentationTerminus fr
         public void FragmentInternally(DissociationType dissociationType, int minLengthOfFragments,
             List<Product> products);
 
+        public IBioPolymerWithSetMods Localize(int j, double massToLocalize);
+
         public static string GetBaseSequenceFromFullSequence(string fullSequence)
         {
             StringBuilder sb = new StringBuilder();

mzLib/Omics/SpectrumMatch/SpectrumMatchFromTsv.cs

@@ -3,7 +3,6 @@
 using System.Globalization;
 using System.Text.RegularExpressions;
 using Chemistry;
-using Omics.Fragmentation.Peptide;
 
 namespace Omics.SpectrumMatch
 {