Handling of applied variants with and without modifications

mzLib/Omics/BioPolymer/IHasSequenceVariants.cs

@@ -47,13 +47,19 @@ public interface IHasSequenceVariants
     /// </summary>
     List<TruncationProduct> TruncationProducts { get; }
 
-    
+
     /// <summary>
-    /// Used to construct a new variant of the same type as the original and is called in <see cref="VariantApplication"/>
+    /// Constructs a new variant biopolymer instance from the original, applying the specified sequence variants and modifications.
+    /// The method sets both the full set of database sequence variants and the subset of applied variants, ensuring that only unapplied variants remain in the SequenceVariations list,
+    /// while applied variants are tracked in AppliedSequenceVariations. This enables accurate representation of both the original and variant-specific annotations.
     /// </summary>
-    /// <remarks>The generic structure enables proteins to produce proteins and RNA to produce RNA</remarks>
-    /// <returns></returns>
-    TBioPolymerType CreateVariant<TBioPolymerType>(string variantBaseSequence, TBioPolymerType original, IEnumerable<SequenceVariation> appliedSequenceVariants,
-        IEnumerable<TruncationProduct> applicableProteolysisProducts, IDictionary<int, List<Modification>> oneBasedModifications, string sampleNameForVariants)
+    TBioPolymerType CreateVariant<TBioPolymerType>(
+        string variantBaseSequence,
+        TBioPolymerType original,
+        IEnumerable<SequenceVariation>? sequenceVariants,              // NEW: pass DB variants explicitly
+        IEnumerable<SequenceVariation>? appliedSequenceVariants,
+        IEnumerable<TruncationProduct> applicableProteolysisProducts,
+        IDictionary<int, List<Modification>> oneBasedModifications,
+        string sampleNameForVariants)
         where TBioPolymerType : IHasSequenceVariants;
 }

mzLib/Omics/BioPolymer/VariantApplication.cs

@@ -104,14 +104,24 @@ public static List<TBioPolymerType> ApplyVariants<TBioPolymerType>(TBioPolymerTy
                 .OrderByDescending(v => v.OneBasedBeginPosition) // apply variants at the end of the protein sequence first
                 .ToList();
 
-            TBioPolymerType proteinCopy = protein.CreateVariant(protein.BaseSequence, protein, null, protein.TruncationProducts, protein.OneBasedPossibleLocalizedModifications, null);
-
-            // If there aren't any variants to apply, just return the base protein
+            // If there aren't any variants to apply, just return the original as-is
             if (uniqueEffectsToApply.Count == 0)
             {
-                return new List<TBioPolymerType> { proteinCopy };
+                return new List<TBioPolymerType> { protein };
             }
 
+            // Start from a normalized copy whose “unapplied” list is the DB list.
+            TBioPolymerType proteinCopy = protein.CreateVariant(
+                protein.BaseSequence,
+                protein,
+                protein.SequenceVariations,            // pass DB variants
+                null,                                  // none applied yet
+                protein.TruncationProducts,
+                protein.OneBasedPossibleLocalizedModifications,
+                null);
+
+
+
             HashSet<string> individuals = new HashSet<string>(uniqueEffectsToApply.SelectMany(v => v.Description.Genotypes.Keys));
             List<TBioPolymerType> variantProteins = new();
             List<TBioPolymerType> newVariantProteins = new();
@@ -253,7 +263,15 @@ private static TBioPolymerType ApplySingleVariant<TBioPolymerType>(SequenceVaria
             Dictionary<int, List<Modification>> adjustedModifications = AdjustModificationIndices(variantGettingApplied, variantSequence, protein);
             List<SequenceVariation> adjustedAppliedVariations = AdjustSequenceVariationIndices(variantGettingApplied, variantSequence, appliedVariations);
 
-            return protein.CreateVariant(variantSequence, protein, adjustedAppliedVariations, adjustedProteolysisProducts, adjustedModifications, individual);
+            // Pass BOTH lists: current DB list (possibly already filtered on the interim proteoform) + newly applied
+            return protein.CreateVariant(
+                variantSequence,
+                protein,
+                protein.SequenceVariations,           // carry forward the current “unapplied” list
+                adjustedAppliedVariations,
+                adjustedProteolysisProducts,
+                adjustedModifications,
+                individual);
         }
 
         /// <summary>

mzLib/Proteomics/Protein/Protein.cs

@@ -133,8 +133,13 @@ public Protein(Protein originalProtein, string newBaseSequence)
         /// <param name="applicableProteolysisProducts"></param>
         /// <param name="oneBasedModifications"></param>
         /// <param name="sampleNameForVariants"></param>
-        public Protein(string variantBaseSequence, Protein protein, IEnumerable<SequenceVariation> appliedSequenceVariations,
-            IEnumerable<TruncationProduct> applicableProteolysisProducts, IDictionary<int, List<Modification>> oneBasedModifications, string sampleNameForVariants)
+        public Protein(string variantBaseSequence,
+            Protein protein,
+            IEnumerable<SequenceVariation>? sequenceVariations,
+            IEnumerable<SequenceVariation>? appliedSequenceVariations,
+            IEnumerable<TruncationProduct> applicableProteolysisProducts,
+            IDictionary<int, List<Modification>> oneBasedModifications,
+            string sampleNameForVariants)
             : this(
                   variantBaseSequence,
                   VariantApplication.GetAccession(protein, appliedSequenceVariations),
@@ -143,11 +148,11 @@ public Protein(string variantBaseSequence, Protein protein, IEnumerable<Sequence
                   oneBasedModifications: oneBasedModifications != null ? oneBasedModifications.ToDictionary(x => x.Key, x => x.Value) : new Dictionary<int, List<Modification>>(),
                   proteolysisProducts: new List<TruncationProduct>(applicableProteolysisProducts ?? new List<TruncationProduct>()),
                   name: VariantApplication.GetVariantName(protein.Name, appliedSequenceVariations),
-                  fullName: VariantApplication.GetVariantName(protein.FullName, appliedSequenceVariations), 
+                  fullName: VariantApplication.GetVariantName(protein.FullName, appliedSequenceVariations),
                   isDecoy: protein.IsDecoy,
                   isContaminant: protein.IsContaminant,
                   databaseReferences: new List<DatabaseReference>(protein.DatabaseReferences),
-                  sequenceVariations: new List<SequenceVariation>(protein.SequenceVariations),
+                  sequenceVariations: new List<SequenceVariation>(sequenceVariations ?? protein.SequenceVariations),
                   disulfideBonds: new List<DisulfideBond>(protein.DisulfideBonds),
                   spliceSites: new List<SpliceSite>(protein.SpliceSites),
                   databaseFilePath: protein.DatabaseFilePath,
@@ -596,15 +601,35 @@ private Protein GenerateFullyLabeledSilacProtein(SilacLabel label)
         /// </summary>
         public IDictionary<int, List<Modification>> OriginalNonVariantModifications { get; set; }
 
-        public TBioPolymerType CreateVariant<TBioPolymerType>(string variantBaseSequence, TBioPolymerType original, IEnumerable<SequenceVariation> appliedSequenceVariants,
-            IEnumerable<TruncationProduct> applicableProteolysisProducts, IDictionary<int, List<Modification>> oneBasedModifications, string sampleNameForVariants)
+        public TBioPolymerType CreateVariant<TBioPolymerType>(
+            string variantBaseSequence,
+            TBioPolymerType original,
+            IEnumerable<SequenceVariation>? sequenceVariants,
+            IEnumerable<SequenceVariation>? appliedSequenceVariants,
+            IEnumerable<TruncationProduct> applicableProteolysisProducts,
+            IDictionary<int, List<Modification>> oneBasedModifications,
+            string sampleNameForVariants)
             where TBioPolymerType : IHasSequenceVariants
         {
             if (original is not Protein originalProtein)
                 throw new ArgumentException("The original BioPolymer must be Protein to create a protein variant");
 
-            var variantProtein =  new Protein(variantBaseSequence, originalProtein, appliedSequenceVariants, 
-                applicableProteolysisProducts, oneBasedModifications, sampleNameForVariants);
+            var variantProtein = new Protein(
+                variantBaseSequence,
+                originalProtein,
+                sequenceVariants ?? originalProtein.SequenceVariations,
+                appliedSequenceVariants,
+                applicableProteolysisProducts,
+                oneBasedModifications,
+                sampleNameForVariants);
+
+            // Remove any applied variants from the list of (unapplied) database sequence variations
+            if (appliedSequenceVariants != null && appliedSequenceVariants.Any())
+            {
+                var appliedSimple = new HashSet<string>(appliedSequenceVariants.Select(v => v.SimpleString()));
+                variantProtein.SequenceVariations.RemoveAll(sv => appliedSimple.Contains(sv.SimpleString()));
+            }
+
             return (TBioPolymerType)(IHasSequenceVariants)variantProtein;
         }
         #endregion