Kdn adding and diagnostic filtering

MetaMorpheus/EngineLayer/EngineLayer.csproj

@@ -59,9 +59,15 @@
     <None Update="Glycan_Mods\NGlycan\NGlycan.gdb">
       <CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
     </None>
+    <None Update="Glycan_Mods\OGlycan\Bullfrog 64 O-glycan wKdn corrected_convert.txt">
+      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
+    </None>
     <None Update="Glycan_Mods\OGlycan\OGlycan.gdb">
       <CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
     </None>
+    <None Update="Glycan_Mods\OGlycan\OGlycan_withIsobaric.gdb">
+      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
+    </None>
     <None Update="Glycan_Mods\OGlycan\Olgycan Database 28 glycans plus Sodium 56 total.txt">
       <CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
     </None>

MetaMorpheus/EngineLayer/Glycan_Mods/OGlycan/Bullfrog 64 O-glycan wKdn corrected_convert.txt

@@ -0,0 +1,64 @@
+HexNAc(1)	N1	203.07936
+HexNAc(1)Hex(1)	H1N1	365.1322
+HexNAc(2)	N2	406.15872
+Hex(1)NeuAc(1)	H1A1	453.14825
+HexNAc(1)Kdn(1)	N1K1	453.14832
+HexNAc(1)NeuAc(1)	N1A1	494.1748
+HexNAc(1)Hex(2)	H2N1	527.185
+HexNAc(2)Hex(1)	H1N2	568.21155
+HexNAc(3)	N3	609.2381
+HexNAc(1)Hex(1)NeuAc(1)	H1N1A1	656.2276
+HexNAc(2)Kdn(1)	N2K1	656.2277
+HexNAc(2)NeuAc(1)	N2A1	697.25415
+HexNAc(2)Hex(1)Fuc(1)	H1N2F1	714.2695
+HexNAc(2)NeuGc(1)	N2G1	713.249
+HexNAc(2)Hex(2)	H2N2	730.2644
+HexNAc(3)Fuc(1)	N3F1	755.296
+HexNAc(3)Hex(1)	H1N3	771.29095
+HexNAc(1)Hex(2)NeuAc(1)	H2N1A1	818.2804
+HexNAc(2)Hex(1)Kdn(1)	H1N2K1	818.2806
+HexNAc(2)Hex(1)NeuAc(1)	H1N2A1	859.30695
+HexNAc(2)Hex(2)Fuc(1)	H2N2F1	876.3223
+HexNAc(3)Hex(1)Fuc(1)	H1N3F1	917.3488
+HexNAc(3)Hex(2)	H2N3	933.34375
+HexNAc(4)Fuc(1)	N4F1	958.37537
+HexNAc(1)Hex(1)NeuAc(2)	H1N1A2	947.32306
+HexNAc(2)Hex(1)Fuc(1)Kdn(1)	H1N2F1K1	964.3384
+HexNAc(1)Hex(2)Fuc(1)NeuAc(1)	H2N1A1F1	964.3383
+HexNAc(1)Hex(3)NeuAc(1)	H3N1A1	980.33325
+HexNAc(2)Hex(2)Kdn(1)	H2N2K1	980.3334
+HexNAc(2)Hex(1)Fuc(1)NeuAc(1)	H1N2A1F1	1005.36487
+HexNAc(3)Fuc(1)Kdn(1)	N3F1K1	1005.365
+HexNAc(2)Hex(2)NeuAc(1)	H2N2A1	1021.35986
+HexNAc(3)Hex(1)Kdn(1)	H1N3K1	1021.3599
+HexNAc(3)Hex(1)NeuAc(1)	H1N3A1	1062.3864
+HexNAc(4)Kdn(1)	N4K1	1062.3865
+HexNAc(3)Hex(2)Fuc(1)	H2N3F1	1079.4017
+HexNAc(4)NeuAc(1)	N4A1	1103.4128
+HexNAc(1)Hex(2)NeuAc(2)	H2N1A2	1109.3759
+HexNAc(2)Hex(1)NeuAc(1)Kdn(1)	H1N2A1K1	1109.376
+HexNAc(4)Hex(2)	H2N4	1136.4231
+HexNAc(2)Hex(1)NeuAc(2)	H1N2A2	1150.4023
+HexNAc(2)Hex(2)Fuc(3)	H2N2F3	1168.4381
+HexNAc(2)Hex(2)Fuc(1)NeuAc(1)	H2N2A1F1	1167.4177
+HexNAc(3)Hex(1)Fuc(1)Kdn(1)	H1N3F1K1	1167.4178
+HexNAc(2)Hex(3)NeuAc(1)	H3N2A1	1183.4126
+HexNAc(3)Hex(2)Kdn(1)	H2N3K1	1183.4127
+HexNAc(3)Hex(1)Fuc(1)NeuAc(1)	H1N3A1F1	1208.4442
+HexNAc(3)Hex(2)Fuc(2)	H2N3F2	1225.4596
+HexNAc(3)Hex(2)NeuAc(1)	H2N3A1	1224.4392
+HexNAc(4)Hex(1)Kdn(1)	H1N4K1	1224.4393
+HexNAc(1)Hex(1)NeuAc(3)	H1N1A3	1238.4185
+HexNAc(2)Hex(1)Fuc(1)NeuAc(2)	H1N2A2F1	1296.4603
+HexNAc(3)Fuc(1)NeuAc(1)Kdn(1)	N3A1F1K1	1296.4604
+HexNAc(2)Hex(2)NeuAc(2)	H2N2A2	1312.4552
+HexNAc(3)Hex(1)NeuAc(1)Kdn(1)	H1N3A1K1	1312.4553
+HexNAc(3)Hex(1)NeuAc(2)	H1N3A2	1353.4818
+HexNAc(4)NeuAc(1)Kdn(1)	N4A1K1	1353.4819
+HexNAc(3)Hex(2)Fuc(1)NeuAc(1)	H2N3A1F1	1370.4971
+HexNAc(4)Hex(1)Fuc(1)Kdn(1)	H1N4F1K1	1370.4971
+HexNAc(4)NeuAc(2)	N4A2	1394.5083
+HexNAc(3)Hex(3)NeuAc(1)	H3N3A1	1386.492
+HexNAc(4)Hex(2)Kdn(1)	H2N4K1	1386.4922
+HexNAc(2)Hex(2)Fuc(1)NeuAc(2)	H2N2A2F1	1458.5131
+HexNAc(3)Hex(1)Fuc(1)NeuAc(1)Kdn(1)	H1N3A1F1K1	1458.5133

MetaMorpheus/EngineLayer/Glycan_Mods/OGlycan/OGlycan_withIsobaric.gdb

@@ -0,0 +1,13 @@
+(N)
+(N(H))
+(N(A))
+(N(H)(N))
+(N(H(A)))
+(N(N(K)))
+(N(H)(N(H)))
+(N(H(A))(N))
+(N(H(A))(A))
+(N(H(A))(N(H)))
+(N(H)(N(H(A))(F)))
+(N(H(A))(N(H(A))))
+(N(H(A))(N(H(A))(F)))

MetaMorpheus/EngineLayer/GlycoSearch/AdjNode.cs

@@ -4,6 +4,7 @@
 
 namespace EngineLayer.GlycoSearch
 {
+    //the class is for localization graph matrix. Each node in the matrix is represented by AdjNode.
     public class AdjNode
     {
         //AdjNode -> Adjactent node is used to build graph matrix for localizaiton. Each node in graph matrix contain Sources, max cost, current cost, etc.

MetaMorpheus/EngineLayer/GlycoSearch/GlycanBox.cs

@@ -9,20 +9,25 @@
 
 namespace EngineLayer
 {
-    //One peptide can have several o-glycans. The combined glycans are grouped as a glycan box. Used for localization. 
-    //GlycanBox -- A defined combination of glycans will be considered to modify on one peptide. 
-    //The GlycanBoxMass is the total mass of all glycans on the peptide
+
+    /// <summary>
+    /// A defined combination of glycans to modify on one peptide. Ex. if we have 3 glycans on one peptide (g1,g2,g3), the GlycanBoxMass is the sum of the three glycans.(glycanBox: [g1,g2,g3])
+    /// </summary>
     public class GlycanBox:ModBox
     {
-        public static Glycan[] GlobalOGlycans { get; set; }
+        public static Glycan[] GlobalOGlycans { get; set; } // The glycan list in the database file
+
+        public GlycanBox[] ChildGlycanBoxes { get; set; }   // all possible glycan combinations in the glycanBox
 
         public static Modification[] GlobalOGlycanModifications { get; set; }
 
-        public static GlycanBox[] OGlycanBoxes { get; set; }
+        public static GlycanBox[] OGlycanBoxes { get; set; } // all possible glycan boxes
+
+        public byte[] Kind { get; private set; } 
 
         //TO DO: Decoy O-glycan can be created, but the results need to be reasoned.
         //public static int[] SugarShift = new int[]{ -16205282, -20307937, -29109542, -14605791, -30709033, -15005282, -36513219, -40615874, 16205282, 20307937, 29109542, 14605791, 30709033, 15005282, 36513219, 40615874 };
-        private readonly static int[] SugarShift = new int[] 
+        private readonly static int[] SugarShift = new int[] //still unclear about the shift...
         {
             7103710, 10300920, 11502690, 12904260, 14706840, 5702150, 13705890, 12809500, 11308410, 13104050,
             11404290, 9705280, 12805860, 15610110, 8703200, 10104770, 9906840, 18607930, 16306330,
@@ -31,7 +36,11 @@ public class GlycanBox:ModBox
 
         };
 
-        //After O-glycans are read in from database, we build combinations of glycans into GlycanBox. The maxNum is maximum glycans allowed on one peptides.
+        /// <summary>
+        /// Use the glycan from database to create all possible combination glycan set into GlycanBox. 
+        /// </summary>
+        /// <param name="maxNum"> The maxNum is maximum glycans allowed on one peptides </param>
+        /// <returns> The glycanBox collection, glycanBox[]</returns>
         public static IEnumerable<GlycanBox> BuildOGlycanBoxes(int maxNum)
         {
             return BuildOGlycanBoxes(maxNum, false);
@@ -51,7 +60,7 @@ public static IEnumerable<GlycanBox> BuildOGlycanBoxes(int maxNum, bool buildDec
 
                     if (buildDecoy)
                     {
-                        GlycanBox glycanBox_decoy = new GlycanBox(idCombine.ToArray());
+                        GlycanBox glycanBox_decoy = new GlycanBox(idCombine.ToArray(),false); // decoy glycanBox
                         glycanBox_decoy.TargetDecoy = false;
                         glycanBox_decoy.ChildGlycanBoxes = BuildChildOGlycanBoxes(glycanBox_decoy.NumberOfMods, glycanBox_decoy.ModIds, glycanBox_decoy.TargetDecoy).ToArray();
                         yield return glycanBox_decoy;
@@ -60,8 +69,11 @@ public static IEnumerable<GlycanBox> BuildOGlycanBoxes(int maxNum, bool buildDec
             }
         }
 
-        //After O-glycans are read in from database, we transfer the glycans into 'Modification' class type for MetaMorpheus to manipulate sequences.
-        //In the future we may able to combine the two type together. 
+        /// <summary>
+        /// Convert the glycan into Modification type for MetaMorpheus to manipulate sequences. In the future we may able to combine the two type together.
+        /// </summary>
+        /// <param name="globalOGlycans"></param>
+        /// <returns></returns>
         public static Modification[] BuildGlobalOGlycanModifications(Glycan[] globalOGlycans)
         {
             Modification[] globalOGlycanModifications = new Modification[globalOGlycans.Length];
@@ -73,20 +85,26 @@ public static Modification[] BuildGlobalOGlycanModifications(Glycan[] globalOGly
             return globalOGlycanModifications;
         }
 
-        //The function here is to build GlycanBoxes used for LocalizationGraph. 
-        //In LocalizationGraph matrix, for each AdjNode, it represent a ChildOGlycanBox here at certain glycosite.
+
+        /// <summary>
+        /// Generate all possible child/fragment box of the specific glycanBox. The childBoxes is uesd for LocalizationGraph.
+        /// </summary>
+        /// <param name="maxNum"></param>
+        /// <param name="glycanIds"> The glycanBox, ex. [0,0,1] means glycan0 + glycan0 + glycan1 </param>
+        /// <param name="targetDecoy"></param>
+        /// <returns> The ChildBox collection, ChildBox[] </returns>
         public static IEnumerable<GlycanBox> BuildChildOGlycanBoxes(int maxNum, int[] glycanIds, bool targetDecoy = true)
         {
             yield return new GlycanBox(new int[0], targetDecoy);
             HashSet<string> seen = new HashSet<string>();
             for (int i = 1; i <= maxNum; i++)
             {
-                foreach (var idCombine in Glycan.GetKCombs(Enumerable.Range(0, maxNum), i))
-                {
-                    List<int> ids = new List<int>();
-                    foreach (var id in idCombine)
+                foreach (var idCombine in Glycan.GetKCombs(Enumerable.Range(0, maxNum), i)) //get all combinations of glycans on the peptide, ex. we have three glycosite and three glycan maybe on that (A,B,C) 
+                {                                                                           //the combination of glycans on the peptide can be (A),(A+B),(A+C),(B+C),(A+B+C) totally six 
+                    List<int> ids = new List<int>(); 
+                    foreach (var id in idCombine)    
                     {
-                        ids.Add(glycanIds[id]);
+                        ids.Add(glycanIds[id]);      
                     }
 
                     if (!seen.Contains(string.Join(",", ids.Select(p => p.ToString()))))
@@ -102,14 +120,19 @@ public static IEnumerable<GlycanBox> BuildChildOGlycanBoxes(int maxNum, int[] gl
             }
         }
 
+        /// <summary>
+        /// Constructor of GlycanBox.
+        /// </summary>
+        /// <param name="ids"> The glycanBox composition, each number represent one glycan index in the database</param>
+        /// <param name="targetDecoy"></param>
         public GlycanBox(int[] ids, bool targetDecoy = true):base(ids)
         {
-            byte[] kind = new byte[] { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 };
-            foreach (var id in ModIds)
+            byte[] kind = new byte[] { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 };
+            foreach (var id in ModIds) //ModIds is the same as ids.
             {
-                for (int i = 0; i < kind.Length; i++)
+                for (int i = 0; i < kind.Length; i++)   
                 {
-                    kind[i] += GlobalOGlycans[id].Kind[i];
+                    kind[i] += GlobalOGlycans[id].Kind[i]; //kind is the sum of all glycan Kind in the Box.
                 }
             }
             Kind = kind;
@@ -125,18 +148,13 @@ public GlycanBox(int[] ids, bool targetDecoy = true):base(ids)
                 Mass = (double)(Glycan.GetMass(Kind) + SugarShift[shiftInd]) / 1E5;
             }
         }
-
-        public GlycanBox[] ChildGlycanBoxes { get; set; }
-
-        public string GlycanIdString
+
+        public string GlycanIdString // the composition of glycanBox. Example: [1,2,3] means glycan1 + glycan2 + glycan3 are on the peptide.
         {
             get
             {
                 return string.Join(",", ModIds.Select(p => p.ToString()));
             }
         }
-
-        public byte[] Kind{ get; private set; }
-
     }
 }