Ptm stoichiometry

.github/workflows/dotnet.yml

@@ -65,18 +65,18 @@ jobs:
     - name: Change MetaMorpheus mzLib version and restore
       run: |
         cd ./MetaMorpheus/MetaMorpheus;
-        dotnet remove CMD package mzLib;
-        dotnet add CMD package mzLib -v 9.9.9;
-        dotnet remove GUI package mzLib;
-        dotnet add GUI package mzLib -v 9.9.9;
-        dotnet remove GuiFunctions package mzLib;
-        dotnet add GuiFunctions package mzLib -v 9.9.9;
-        dotnet remove EngineLayer package mzLib;
-        dotnet add EngineLayer package mzLib -v 9.9.9;
-        dotnet remove Test package mzLib;
-        dotnet add Test package mzLib -v 9.9.9;
-        dotnet remove TaskLayer package mzLib;
-        dotnet add TaskLayer package mzLib -v 9.9.9;
+        dotnet remove CMD/CMD.csproj package mzLib;
+        dotnet add CMD/CMD.csproj package mzLib -v 9.9.9;
+        dotnet remove GUI/GUI.csproj package mzLib;
+        dotnet add GUI/GUI.csproj package mzLib -v 9.9.9;
+        dotnet remove GuiFunctions/GuiFunctions.csproj package mzLib;
+        dotnet add GuiFunctions/GuiFunctions.csproj package mzLib -v 9.9.9;
+        dotnet remove EngineLayer/EngineLayer.csproj package mzLib;
+        dotnet add EngineLayer/EngineLayer.csproj package mzLib -v 9.9.9;
+        dotnet remove Test/Test.csproj package mzLib;
+        dotnet add Test/Test.csproj package mzLib -v 9.9.9;
+        dotnet remove TaskLayer/TaskLayer.csproj package mzLib;
+        dotnet add TaskLayer/TaskLayer.csproj package mzLib -v 9.9.9;
         dotnet restore;
     - name: Build MetaMorpheus
       run: cd ./MetaMorpheus/MetaMorpheus && dotnet build --no-restore

.gitignore

@@ -1,5 +1,12 @@
 ## Ignore Visual Studio temporary files, build results, and
 ## files generated by popular Visual Studio add-ons.
+# LLM/Agent specific files/.claude
+/.opencode
+/.opencode/config/coverage.json
+/AGENTS.md
+.claude/
+.serena/
+.pr_comments/ # Folder for agent-generate PR comments and suggested fixes
 
 # User-specific files
 *.suo
@@ -249,8 +256,3 @@ ModelManifest.xml
 
 # Macintosh files
 **/.DS_Store
-
-/.claude
-/.opencode
-/.opencode/config/coverage.json
-/AGENTS.md

mzLib/MassSpectrometry/ExperimentalDesign/ISampleInfo.cs

@@ -32,5 +32,12 @@ public interface ISampleInfo : IComparable<ISampleInfo>, IEquatable<ISampleInfo>
         /// Fraction identifier for fractionated workflows. Returns 0 if not applicable.
         /// </summary>
         int Fraction { get; }
+
+        /// <summary>
+        /// File name without extension, derived from <see cref="FullFilePathWithExtension"/>.
+        /// Used for display labels in quantification output columns.
+        /// </summary>
+        string FilenameWithoutExtension =>
+            System.IO.Path.GetFileNameWithoutExtension(FullFilePathWithExtension);
     }
 }

mzLib/MassSpectrometry/ScanMetadata.cs

@@ -0,0 +1,52 @@
+namespace MassSpectrometry;
+
+/// <summary>
+/// Lightweight, immutable snapshot of scan and precursor metadata extracted from an MS2 scan.
+/// Designed to be shared across spectral matches (PSMs) from the same scan/precursor,
+/// avoiding duplication of scalar metadata while allowing the heavyweight scan objects
+/// (MsDataScan, MzSpectrum, IsotopicEnvelope[]) to be released from memory after scoring.
+///
+/// Scan-level properties (OneBasedScanNumber through NativeId) are identical for all
+/// precursors deconvoluted from the same raw scan. Precursor-level properties
+/// (PrecursorCharge through OneOverK0) are specific to a single deconvoluted precursor
+/// and may differ across chimeric identifications from the same scan.
+/// </summary>
+/// <param name="OneBasedScanNumber">One-based scan number from the raw file.</param>
+/// <param name="OneBasedPrecursorScanNumber">One-based scan number of the precursor (MS1) scan, if available.</param>
+/// <param name="RetentionTime">Retention time in minutes.</param>
+/// <param name="NumPeaks">Number of peaks in the MS2 spectrum at the time of extraction.</param>
+/// <param name="TotalIonCurrent">Total ion current of the MS2 scan.</param>
+/// <param name="NativeId">Vendor-native scan identifier string.</param>
+/// <param name="FullFilePath">Absolute or relative path to the originating spectra file.</param>
+/// <param name="PrecursorCharge">Charge state assigned to the deconvoluted precursor.</param>
+/// <param name="PrecursorMonoisotopicPeakMz">Monoisotopic m/z of the deconvoluted precursor.</param>
+/// <param name="PrecursorMass">Neutral monoisotopic mass of the precursor, derived from m/z and charge.</param>
+/// <param name="PrecursorIntensity">MS1 intensity of the precursor ion.</param>
+/// <param name="PrecursorEnvelopePeakCount">Number of peaks in the precursor isotopic envelope.</param>
+/// <param name="PrecursorFractionalIntensity">Fraction of precursor intensity relative to envelope total. -1 if unavailable.</param>
+/// <param name="OneOverK0">Inverse reduced ion mobility (1/K0) for TIMS data; null for non-IMS instruments.</param>
+public record ScanMetadata(
+    // Scan-level properties
+    int OneBasedScanNumber,
+    int? OneBasedPrecursorScanNumber,
+    double RetentionTime,
+    int NumPeaks,
+    double TotalIonCurrent,
+    string NativeId,
+    string FullFilePath,
+
+    // Precursor-level properties
+    int PrecursorCharge,
+    double PrecursorMonoisotopicPeakMz,
+    double PrecursorMass,
+    double PrecursorIntensity,
+    int PrecursorEnvelopePeakCount,
+    double PrecursorFractionalIntensity,
+    double? OneOverK0 = null)
+{
+    /// <summary>
+    /// Convenience property deriving the file name without extension from <see cref="FullFilePath"/>.
+    /// </summary>
+    public string FilenameWithoutExtension =>
+        System.IO.Path.GetFileNameWithoutExtension(FullFilePath);
+}

mzLib/MzLibUtil/ClassExtensions.cs

@@ -25,6 +25,12 @@
 {
     public static class ClassExtensions
     {
+        public static readonly string ModificationPattern = @"-?\[(.+?)(?<!\[I+)\]";
+        public static readonly string ProteinSplitPattern = @";|\|";
+
+        private static readonly Regex CompiledModificationPattern = new(ModificationPattern, RegexOptions.Compiled);
+        private static readonly Regex CompiledProteinSplitPattern = new(ProteinSplitPattern, RegexOptions.Compiled);
+
         /// <summary>
         /// Applies a boxcar smoothing algorithm to the input data.
         /// </summary>
@@ -257,12 +263,9 @@
             // "(.+?)": captures the content of the mod, which can be anything except for a closing bracket
             // "(?<!\[I+)": negative lookbehind to ensure that the closing bracket match does not correspond to a cation charge state (also defined with brackets).
             // "\]": indicates the end of the mod
-            string pattern = @"-?\[(.+?)(?<!\[I+)\]";
-            Regex regex = new(pattern);
-
             Dictionary<int, string> modDict = new();
 
-            MatchCollection matches = regex.Matches(fullSeq);
+            MatchCollection matches = CompiledModificationPattern.Matches(fullSeq);
             int totalCaptureLength = 0;
             foreach (Match match in matches)
             {
@@ -283,6 +286,12 @@
             return modDict;
         }
 
+        public static string GetBaseSequenceFromFullSequence(this string fullSeq, string? modPattern=null, string? replacement=null)
+        {
+            Regex regex = modPattern != null ? new Regex(modPattern) : CompiledModificationPattern;
+            return regex.Replace(fullSeq, replacement ?? string.Empty);
+        }
+
         /// <summary>
         /// Fixes an issue where the | appears and throws off the numbering if there are multiple mods on a single amino acid.
         /// </summary>
@@ -296,5 +305,16 @@
             Regex regexSpecialChar = new(specialCharacter);
             fullSeq = regexSpecialChar.Replace(fullSeq, replacement);
         }
+
+        /// <summary>
+        /// Splits a protein group name into individual accessions by <c>;</c> or <c>|</c> delimiters.
+        /// Expects a clean accession string (e.g., "P12345|Q67890"), not a full sequence with
+        /// modification annotations — the <c>|</c> character inside modification brackets would
+        /// cause incorrect splits.
+        /// </summary>
+        public static string[] SplitProteinAccessions(this string proteinGroupName)
+        {
+            return CompiledProteinSplitPattern.Split(proteinGroupName);
+        }
     }
 }

mzLib/MzLibUtil/MzLibUtil.csproj

@@ -17,4 +17,8 @@
     <PackageReference Include="Microsoft.Win32.Registry" Version="5.0.0" />
   </ItemGroup>
 
+  <ItemGroup>
+    <Folder Include="PositionFrequencyAnalysis\" />
+  </ItemGroup>
+
 </Project>

mzLib/MzLibUtil/PositionFrequencyAnalysis/PositionFrequencyAnalysis.cs

@@ -0,0 +1,72 @@
+using Easy.Common.Extensions;
+using System.Collections.Generic;
+using System;
+
+namespace MzLibUtil.PositionFrequencyAnalysis
+{
+    /// <summary>
+    /// Handles analysis and organization of protein group quantification from peptide records.
+    /// </summary>
+    public class PositionFrequencyAnalysis
+    {
+        /// <summary>
+        /// Dictionary mapping protein group names to their quantification data.
+        /// </summary>
+        public Dictionary<string, QuantifiedProteinGroup> ProteinGroups { get; private set; }
+
+        /// <summary>
+        /// Populates protein groups with their respective proteins and peptides from a list of quantifide peptide records. 
+        /// The resulting protein groups are stored in the ProteinGroups property with the protein group name strings as keys.
+        /// </summary>
+        /// <param name="peptides">A list of <see cref="QuantifiedPeptideRecord"/>, which store a peptide's full sequence, mapped protein groups, and intensity.</param>
+        /// <param name="proteinSequences">An optional dictionary of protein sequences to use for mapping peptides to proteins.
+        /// If not provided, the protein sequences will be left null in the <see cref="QuantifiedProtein"/> objects. However, this parameter should not be null if
+        /// protein stoichiometry is the goal, since it is needed to align the peptides to the parent protein.</param>
+        public void SetUpQuantificationFromQuantifiedPeptideRecords(List<QuantifiedPeptideRecord> peptides, Dictionary<string, string> proteinSequences = null)
+        {
+            ArgumentNullException.ThrowIfNull(peptides);
+            ProteinGroups = new Dictionary<string, QuantifiedProteinGroup>();
+            foreach (var peptide in peptides)
+            {
+                // Iterate through the peptide's protein groups in case it is a shared peptide protein groups.
+                // We want to map the peptide separately to each protein group it belongs to, primarily due to 
+                // each protein group is reported  separately in MetaMorpheus.
+                foreach (var pg in peptide.ProteinGroups)
+                {
+                    // If have not seen that protein group, store it
+                    if (!ProteinGroups.ContainsKey(pg))
+                    {
+                        ProteinGroups[pg] = new QuantifiedProteinGroup(pg);
+                    }
+                    var proteinGroup = ProteinGroups[pg];
+
+                    foreach (var proteinName in pg.SplitProteinAccessions())
+                    {
+                        // Add the protein to the protein group's dictionary if it has not been added
+                        if (!proteinGroup.Proteins.ContainsKey(proteinName))
+                        {
+                            proteinGroup.Proteins[proteinName] = new QuantifiedProtein(proteinName);
+                            if (proteinSequences != null && proteinSequences.TryGetValue(proteinName, out var sequence))
+                            {
+                                proteinGroup.Proteins[proteinName].Sequence = sequence;
+                            }
+                        }
+                        var protein = proteinGroup.Proteins[proteinName];
+
+                        // If the peptide's base sequence has not been seen, add it to the protein's dictionary; otherwise, update the existing entry
+                        if (!protein.Peptides.TryGetValue(peptide.BaseSequence, out var quantifiedPeptide))
+                        {
+                            quantifiedPeptide = new QuantifiedPeptide(peptide.FullSequence, intensity: peptide.Intensity);
+                            protein.Peptides[peptide.BaseSequence] = quantifiedPeptide;
+                        }
+                        else
+                        {
+                            // If the peptide's base sequence has been seen, add the new full sequence to the existing peptide
+                            quantifiedPeptide.AddFullSequence(peptide.FullSequence, intensity: peptide.Intensity);
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

mzLib/MzLibUtil/PositionFrequencyAnalysis/QuantifiedModification.cs

@@ -0,0 +1,28 @@
+namespace MzLibUtil.PositionFrequencyAnalysis
+{
+    /// <summary>
+    /// A class to store information about a quantified modification.
+    /// </summary>
+    public class QuantifiedModification
+    {
+        public string Name { get; set; }
+        public int PeptidePositionZeroIsNTerminus { get; set; }
+        public int ProteinPositionZeroIsNTerminus { get; set; }
+        public double Intensity { get; set; }
+
+        /// <summary>
+        /// Constructor for a QuantifiedModification object.
+        /// </summary>
+        /// <param name="name">Full name of the modification, in the format "MODTYPE: MODID on MOTIF" </param>
+        /// <param name="positionInPeptide">Zero-based position in the peptide.</param>
+        /// <param name="positionInProtein">Zero-based position in the peptide's parent protein.</param>
+        /// <param name="intensity"></param>
+        public QuantifiedModification(string name, int positionInPeptide, int? positionInProtein = null, double intensity = 0)
+        {
+            Name = name;
+            PeptidePositionZeroIsNTerminus = positionInPeptide;
+            ProteinPositionZeroIsNTerminus = positionInProtein ?? -1; // -1 means that the position in the protein is unknown
+            Intensity = intensity;
+        }
+    }
+}