Merge branch 'master' into GetClosestOneBasedScanRefactor

mzLib/FlashLFQ/ChromatographicPeak.cs

@@ -169,6 +169,25 @@ public override string ToString()
             sb.Append(string.Join("|", Identifications.Select(p => p.BaseSequence).Distinct()) + '\t');
             sb.Append(string.Join("|", Identifications.Select(p => p.ModifiedSequence).Distinct()) + '\t');
 
+            //The semi-colon here splitting the protein groups requires some explanation
+            //During protein parsimony, you can get situations where all peptides are shared between two or more proteins. In other words, there is no unique peptide that could resolve the parsimony.
+            //In this case you would see something like P00001 | P00002.
+
+            //That’s the easy part and you already understand that.
+
+            //    Now imagine another scenario where you have some other peptides(that are not in either P00001 or P00002) that give you a second group, like the one above.Let’s call it P00003 | P00004.
+            // Everything is still fine her.
+
+            //    Now you have two protein groups each with two proteins. 
+
+            //    Here is where the semi - colon comes in.
+            //Imagine you now find a new peptide(totally different from any of the peptides used to create the two original protein groups) that is shared across all four proteins.The original peptides
+            //require that two different protein groups exist, but this new peptide could come from either or both.We don’t know. So, the quantification of that peptide must be allowed to be
+            //either/ both groups. For this peptide, the protein accession in the output will be P00001 | P00002; P00003 | P00004.
+
+            //    You could see an output that looks like P0000A; P0000B.Here there is only one protein in each protein group(as decided by parsimony).And you have a peptide that is shared.This would
+            // not ever be reported as P0000A | P0000B because each protein has a unique peptide that confirms its existence.
+
             var t = Identifications.SelectMany(p => p.ProteinGroups.Select(v => v.ProteinGroupName)).Distinct().OrderBy(p => p);
             if (t.Any())
             {

mzLib/MassSpectrometry/MsDataFile.cs

@@ -29,9 +29,9 @@ namespace MassSpectrometry
     /// <summary>
     /// A class for interacting with data collected from a Mass Spectrometer, and stored in a file
     /// </summary>
-    public abstract class MsDataFile
+    public abstract class MsDataFile : IEnumerable<MsDataScan>
     {
-        public MsDataScan[] Scans { get; set; }
+        public MsDataScan[] Scans { get; protected set; }
         public SourceFile SourceFile { get; set; }
         public int NumSpectra => Scans.Length;
         public string FilePath { get; }
@@ -73,33 +73,28 @@ public abstract MsDataScan GetOneBasedScanFromDynamicConnection(int oneBasedScan
         public virtual MsDataScan[] GetMsDataScans()
         {
             if (!CheckIfScansLoaded())
-            {
                 LoadAllStaticData();
-            }
+                
             return Scans;
         }
 
         public virtual List<MsDataScan> GetAllScansList()
         {
             if (!CheckIfScansLoaded())
-            {
                 LoadAllStaticData();
-            }
-
+
             return Scans.ToList();
         }
 
         public virtual IEnumerable<MsDataScan> GetMS1Scans()
         {
             if (!CheckIfScansLoaded())
-            {
-                LoadAllStaticData();
-            }
-
+              LoadAllStaticData();
+
             for (int i = 1; i <= NumSpectra; i++)
             {
                 var scan = GetOneBasedScan(i);
-                if (scan != null && scan.MsnOrder == 1)
+                if (scan.MsnOrder == 1)
                 {
                     yield return scan;
                 }
@@ -109,35 +104,26 @@ public virtual IEnumerable<MsDataScan> GetMS1Scans()
         public virtual MsDataScan GetOneBasedScan(int scanNumber)
         {
             if (!CheckIfScansLoaded())
-            {
-                LoadAllStaticData();
-            }
-
+              LoadAllStaticData();
+
             return Scans.SingleOrDefault(i => i.OneBasedScanNumber == scanNumber);
         }
 
         public virtual IEnumerable<MsDataScan> GetMsScansInIndexRange(int firstSpectrumNumber, int lastSpectrumNumber)
         {
             if (!CheckIfScansLoaded())
-            {
                 LoadAllStaticData();
-            }
-
+
             for (int oneBasedSpectrumNumber = firstSpectrumNumber;
-                 oneBasedSpectrumNumber <= lastSpectrumNumber;
-                 oneBasedSpectrumNumber++)
-            {
+                 oneBasedSpectrumNumber <= lastSpectrumNumber; oneBasedSpectrumNumber++)
                 yield return GetOneBasedScan(oneBasedSpectrumNumber);
-            }
         }
 
         public virtual IEnumerable<MsDataScan> GetMsScansInTimeRange(double firstRT, double lastRT)
         {
             if (!CheckIfScansLoaded())
-            {
                 LoadAllStaticData();
-            }
-
+
             int oneBasedSpectrumNumber = GetClosestOneBasedSpectrumNumber(firstRT) + 1;
 
             while (oneBasedSpectrumNumber < NumSpectra + 1)
@@ -173,20 +159,13 @@ public virtual IEnumerable<MsDataScan> GetMsScansInTimeRange(double firstRT, dou
         public virtual int GetClosestOneBasedSpectrumNumber(double retentionTime)
         {
             if (!CheckIfScansLoaded())
-            {
                 LoadAllStaticData();
-            }
 
             return ClassExtensions.GetClosestIndex(Scans
                 .Select(scan => scan.RetentionTime)
                 .ToArray(), retentionTime);
         }
 
-        public virtual IEnumerator<MsDataScan> GetEnumerator()
-        {
-            return GetMsScansInIndexRange(1, NumSpectra).GetEnumerator();
-        }
-
         public virtual int[] GetMsOrderByScanInDynamicConnection()
         {
             throw new NotImplementedException();
@@ -198,5 +177,17 @@ public virtual bool CheckIfScansLoaded()
         {
             return (Scans != null && Scans.Length > 0);
         }
+
+        public IEnumerator<MsDataScan> GetEnumerator()
+        {
+            return Scans.Where(scan => scan is not null).GetEnumerator();
+        }
+
+        IEnumerator IEnumerable.GetEnumerator()
+        {
+            return GetEnumerator();
+        }
     }
+
+
 }

mzLib/MassSpectrometry/MsDataScan.cs

@@ -18,6 +18,7 @@
 
 using MzLibUtil;
 using System;
+using System.Collections;
 using System.Collections.Generic;
 using System.Linq;
 

mzLib/Readers/Mgf/Mgf.cs

@@ -21,7 +21,12 @@ namespace Readers
 {
     public class Mgf : MsDataFile
     {
-        public Mgf(string filePath) : base(filePath) { }
+
+        protected MsDataScan[] IndexedScans { get; set; }
+        public Mgf(string filePath) : base(filePath)
+        {
+
+        }
 
         public override MsDataFile LoadAllStaticData(FilteringParams filterParams = null, int maxThreads = 1)
         {
@@ -56,8 +61,19 @@ public override MsDataFile LoadAllStaticData(FilteringParams filterParams = null
                     }
                 }
             }
-            SourceFile = GetSourceFile(); 
-            Scans = scans.OrderBy(x => x.OneBasedScanNumber).ToArray();
+
+            SourceFile = GetSourceFile();
+
+            // ensures that if a scan (OneBasedScanNumber) does not exist,
+            // the final scans array will contain a null value  
+            // this unique case is due to the nature of loading MGF files
+            var orderedScans = scans.OrderBy(x => x.OneBasedScanNumber).ToArray();
+            var indexedScans = new MsDataScan[orderedScans[^1].OneBasedScanNumber];
+            foreach (var scan in orderedScans)
+                indexedScans[scan.OneBasedScanNumber - 1] = scan;
+
+            IndexedScans = indexedScans;
+            Scans = orderedScans;
             return this;
         }
 
@@ -66,6 +82,11 @@ public override SourceFile GetSourceFile()
             return new SourceFile("no nativeID format", "mgf format", null, null, null);
         }
 
+        public override MsDataScan GetOneBasedScan(int scanNumber)
+        {
+            return IndexedScans[scanNumber - 1];
+        }
+
         public override MsDataScan GetOneBasedScanFromDynamicConnection(int scanNumber, IFilteringParams filterParams = null)
         {
             if (_streamReader == null)

mzLib/Test/FileReadingTests/FakeMsDataFile.cs

@@ -28,7 +28,6 @@ public class FakeMsDataFile : MsDataFile
     {
         public FakeMsDataFile(MsDataScan[] FakeScans) : base(FakeScans, new SourceFile(@"scan number only nativeID format", "mzML format", null, "SHA-1", @"C:\fake.mzML", null))
         {
-            this.Scans = FakeScans;
         }
 
         public int GetClosestOneBasedSpectrumNumber(double retentionTime)

mzLib/UsefulProteomicsDatabases/ProteinDbRetriever.cs

@@ -239,7 +239,7 @@ public enum IncludeIsoforms
 
         /// <summary>
         /// Columns to select for retrieving results in tab or xls format.
-        /// https://legacy.uniprot.org/help/uniprotkb_column_names
+        /// https://www.uniprot.org/help/return_fields
         /// </summary>
         public enum Columns
         {

mzLib/mzLib.nuspec

@@ -2,7 +2,7 @@
 <package>
   <metadata>
     <id>mzLib</id>
-    <version>5.0.539</version>
+    <version>5.0.540</version>
     <title>mzLib</title>
     <authors>Stef S.</authors>
     <owners>Stef S.</owners>