final comments

ProteoformSuiteGUI/DisplayObjects/DisplayTopDownHit.cs

@@ -106,9 +106,9 @@ public double Score
             get { return h.score; }
         }
 
-        public string PFR
+        public string PFR_accession
         {
-            get { return h.pfr; }
+            get { return h.pfr_accession; }
         }
 
         #endregion Public Properties
@@ -154,6 +154,7 @@ private static string header(string property_name)
             if (property_name == nameof(retention_time)) return "Retention Time";
             if (property_name == nameof(pscore)) return "P-Score";
             if (property_name == nameof(ptm_description)) return "PTM Description";
+            if (property_name == nameof(PFR_accession)) return "PFR Accession";
             return null;
         }
 

ProteoformSuiteGUI/DisplayObjects/DisplayTopDownProteoform.cs

@@ -109,9 +109,9 @@ public int Observations
             get { return t.topdown_hits.Count; }
         }
 
-        public string PFR
+        public string PFR_accession
         {
-            get { return t.pfr; }
+            get { return t.pfr_accession; }
         }
 
         public string family_id
@@ -170,6 +170,7 @@ public static string header(string name)
             if (name == nameof(manual_id)) return "Best Hit Info";
             if (name == nameof(family_id)) return "Family ID";
             if (name == nameof(mass_error)) return "Mass Error";
+            if (name == nameof(PFR_accession)) return "PFR Accession";
             return null;
         }
 

ProteoformSuiteGUI/ExperimentTheoreticalComparison.cs

@@ -477,10 +477,5 @@ private void ct_ET_peakList_MouseClick(object sender, MouseEventArgs e)
         }
 
         #endregion Tooltip Private Methods
-
-        private void label12_Click(object sender, EventArgs e)
-        {
-
-        }
     }
 }

ProteoformSuiteGUI/TopDown.cs

@@ -52,7 +52,7 @@ public void FillTablesAndCharts()
             mods = Sweet.lollipop.topdown_proteoforms.SelectMany(p => p.topdown_ptm_set.ptm_combination).Select(m => m.modification.id).Distinct().ToList();
             tb_tdProteoforms.Text = Sweet.lollipop.topdown_proteoforms.Count.ToString();
             tb_td_hits.Text = Sweet.lollipop.top_down_hits.Count.ToString();
-            tb_unique_PFRs.Text = Sweet.lollipop.topdown_proteoforms.Select(p => p.pfr).Distinct().Count().ToString();
+            tb_unique_PFRs.Text = Sweet.lollipop.topdown_proteoforms.Select(p => p.pfr_accession).Distinct().Count().ToString();
         }
 
         public void RunTheGamut(bool full_run)

ProteoformSuiteInternal/Calibration.cs

@@ -193,8 +193,11 @@ private DataPointAquisitionResults GetDataPoints()
                 {
                     //look around theoretical mass of topdown hit identified proteoforms - 10 ppm and 5 minutes same br, tr, fraction, condition (same file!)
                     //if neucode labled, look for the light component mass (loaded in...)
-                    List<Component> potential_matches = Sweet.lollipop.calibration_components.Where(c => c.input_file.lt_condition == raw_file.lt_condition && (Sweet.lollipop.neucode_labeled || c.input_file.biological_replicate == raw_file.biological_replicate) && c.input_file.fraction == raw_file.fraction
-                    && c.input_file.technical_replicate == raw_file.technical_replicate).ToList();
+                    List<Component> potential_matches = Sweet.lollipop.calibration_components.
+                        Where(c => c.input_file.lt_condition == raw_file.lt_condition
+                        && (Sweet.lollipop.neucode_labeled || c.input_file.biological_replicate == raw_file.biological_replicate)
+                        && c.input_file.fraction == raw_file.fraction
+                        && c.input_file.technical_replicate == raw_file.technical_replicate).ToList();
                     if (potential_matches.Count > 0)
                         matching_component = potential_matches.Where(c =>
                    Math.Abs(c.charge_states.OrderByDescending(s => s.intensity).First().mz_centroid.ToMass(c.charge_states.OrderByDescending(s => s.intensity).First().charge_count) - identification.theoretical_mass) * 1e6 / c.charge_states.OrderByDescending(s => s.intensity).First().mz_centroid.ToMass(c.charge_states.OrderByDescending(s => s.intensity).First().charge_count) < 10
@@ -211,14 +214,12 @@ private DataPointAquisitionResults GetDataPoints()
                         rt = myMsDataFile.GetOneBasedScan(scanNumber + 1).RetentionTime;
                     }
                     proteinCharge = matching_component.charge_states.OrderByDescending(c => c.intensity).First().charge_count;
-                }
-                else
-                {
-                    //if top-down file, needs to be hit from same techrep (exact same raw file...)
-                    if (identification.technical_replicate != raw_file.technical_replicate) continue;
-                }
+                }  
+                else if(identification.technical_replicate != raw_file.technical_replicate) continue;
+
 
-                var SequenceWithChemicalFormulas = identification.GetSequenceWithChemicalFormula();
+                var SequenceWithChemicalFormulas = identification.GetSequenceWithChemicalFormula
+                    ();
                 if (SequenceWithChemicalFormulas == null)
                 {
                     continue;

ProteoformSuiteInternal/ComponentReader.cs

@@ -37,7 +37,7 @@ public List<Component> read_components_from_xlsx(InputFile file, bool remove_mis
             int charge_row_index = 0;
             string scan_range = "";
             List<List<string>> cells = ExcelReader.get_cell_strings(file, false);
-            for (int i = 0; i < cells.Count(); i++)
+            for (int i = 0; i < cells.Count; i++)
             {
                 if (i == 0) continue; //skip component header                        
                 List<string> cellStrings = cells[i];

ProteoformSuiteInternal/Lollipop.cs

@@ -362,10 +362,10 @@ public List<TopDownProteoform> aggregate_td_hits(List<TopDownHit> top_down_hits,
             //get topdown hits that meet criteria
             List<TopDownHit> remaining_td_hits = top_down_hits.Where(h => h.score >= min_score_td && ((biomarker && h.tdResultType == TopDownResultType.Biomarker) || (tight_abs_mass && h.tdResultType == TopDownResultType.TightAbsoluteMass))).OrderByDescending(h => h.score).ThenBy(h => h.pscore).ThenBy(h => h.reported_mass).ToList();
 
-            List<string> PFRs = remaining_td_hits.Select(h => h.pfr).Distinct().ToList();
-            Parallel.ForEach(PFRs, pfr =>
+            List<string> unique_proteoform_ids = remaining_td_hits.Select(h => h.pfr_accession).Distinct().ToList();
+            Parallel.ForEach(unique_proteoform_ids, pfr =>
             {
-                List<TopDownHit> hits_by_pfr = remaining_td_hits.Where(h => h.pfr == pfr).ToList();
+                List<TopDownHit> hits_by_pfr = remaining_td_hits.Where(h => h.pfr_accession == pfr).ToList();
                 List<TopDownProteoform> first_aggregation = new List<TopDownProteoform>();
                 //aggregate to td hit w/ highest c-score as root - 1st average for retention time
                 while (hits_by_pfr.Count > 0)
@@ -400,7 +400,7 @@ public List<TopDownProteoform> aggregate_td_hits(List<TopDownHit> top_down_hits,
         //convert unlabeled mass to neucode light mass based on lysine count (used for topdown identifications)
         public double get_neucode_mass(double unlabeled_mass, int lysine_count)
         {
-            return (unlabeled_mass - lysine_count * 128.094963 + lysine_count * 136.109162);
+            return unlabeled_mass - lysine_count * 128.094963 + lysine_count * 136.109162;
         }
 
         #endregion TOPDOWN 
@@ -452,7 +452,7 @@ public List<ExperimentalProteoform> aggregate_proteoforms(bool two_pass_validati
             {
                 community.experimental_proteoforms = Sweet.lollipop.target_proteoform_community.experimental_proteoforms.Select(e => e.topdown_id ? new TopDownProteoform(e as TopDownProteoform) : new ExperimentalProteoform(e)).ToArray();
             }
-           if(get_files(input_files, Purpose.Quantification).Count() > 0)
+           if (get_files(input_files, Purpose.Quantification).Count() > 0)
             {
                 assignQuantificationComponents(vetted_proteoforms, raw_quantification_components);
             }
@@ -506,7 +506,7 @@ public void assign_best_components_for_manual_validation(IEnumerable<Experimenta
 
         public List<ExperimentalProteoform> add_topdown_proteoforms(List<ExperimentalProteoform> vetted_proteoforms, List<TopDownProteoform> topdown_proteoforms)
         {
-            foreach (TopDownProteoform topdown in topdown_proteoforms.Where(t => t.accepted).OrderByDescending(t => t.topdown_hits.Max(h => h.score)).ThenBy(t => t.topdown_hits.Min(h => h.pscore)).ThenBy(t => t.topdown_hits.Count()).ThenBy(t => t.agg_mass))
+            foreach (TopDownProteoform topdown in topdown_proteoforms.Where(t => t.accepted).OrderByDescending(t => t.topdown_hits.Max(h => h.score)).ThenBy(t => t.topdown_hits.Min(h => h.pscore)).ThenBy(t => t.topdown_hits.Count).ThenBy(t => t.agg_mass))
             {
                 double mass = topdown.modified_mass;
                 List<ProteoformRelation> all_td_relations = new List<ProteoformRelation>();
@@ -1171,7 +1171,12 @@ public string calibrate_files()
                                 //determine component and td hit shifts
                                 determine_shifts(raw_file);
                                 //calibrate component xlsx files
-                                foreach (InputFile f in input_files.Where(f => f.lt_condition == raw_file.lt_condition && f.purpose == Purpose.CalibrationIdentification && f.biological_replicate == raw_file.biological_replicate && f.fraction == raw_file.fraction && f.technical_replicate == raw_file.technical_replicate)) Calibration.calibrate_components_in_xlsx(f);
+                                foreach (InputFile f in input_files.Where(f => f.lt_condition == raw_file.lt_condition && f.purpose == Purpose.CalibrationIdentification 
+                                && f.biological_replicate == raw_file.biological_replicate && f.fraction == raw_file.fraction 
+                                && f.technical_replicate == raw_file.technical_replicate))
+                                {
+                                    Calibration.calibrate_components_in_xlsx(f);
+                                }
                             }
                             else filenames_did_not_calibrate.Add(raw_file.filename);
                         }
@@ -1180,7 +1185,8 @@ public string calibrate_files()
             }
             if (calibrate_td_files)
             {
-                foreach (InputFile file in input_files.Where(f => f.purpose == Purpose.CalibrationTopDown && td_hits_calibration.Any(h => h.file == f && td_hit_correction.ContainsKey(new Tuple<string, int, double>(h.filename, h.ms2ScanNumber, h.reported_mass)))))
+                foreach (InputFile file in input_files.Where(f => f.purpose == Purpose.CalibrationTopDown &&
+                td_hits_calibration.Any(h => h.file == f && td_hit_correction.ContainsKey(new Tuple<string, int, double>(h.filename, h.ms2ScanNumber, h.reported_mass)))))
                 {
                     Calibration.calibrate_td_hits_file(file);
                 }

ProteoformSuiteInternal/ProteinSequenceGroup.cs

@@ -6,7 +6,7 @@ namespace ProteoformSuiteInternal
 {
     public class ProteinSequenceGroup : ProteinWithGoTerms
     {
-        public List<ProteinWithGoTerms> proteinWithGoTermList;
+        public List<ProteinWithGoTerms> proteinWithGoTermList = new List<ProteinWithGoTerms>();
         public ProteinSequenceGroup(IEnumerable<ProteinWithGoTerms> proteins_with_contaminants_first)
             : base(proteins_with_contaminants_first.First().BaseSequence,
                 proteins_with_contaminants_first.First().Accession + "_" + proteins_with_contaminants_first.Count() + "G",

ProteoformSuiteInternal/ProteinWithGoTerms.cs

@@ -9,7 +9,7 @@ public class ProteinWithGoTerms : Protein
     {
         public List<string> AccessionList { get; set; }
         public List<GoTerm> GoTerms { get; set; }
-        public bool topdown_protein;
+        public bool topdown_protein { get; set; }
 
         public ProteinWithGoTerms(string sequence, string accession, List<Tuple<string, string>> gene_names, IDictionary<int, List<Modification>> oneBasedModifications, List<ProteolysisProduct> proteolysisProducts, string name, string full_name, bool isDecoy, bool isContaminant, IEnumerable<DatabaseReference> databaseReferences, IEnumerable<GoTerm> goTerms)
             : base(sequence, accession, gene_names: gene_names, oneBasedModifications: oneBasedModifications, proteolysisProducts: proteolysisProducts, name: name, full_name: full_name, isDecoy: isDecoy, isContaminant: isContaminant, databaseReferences: databaseReferences.ToList())

ProteoformSuiteInternal/Proteoform.cs

@@ -253,7 +253,10 @@ private void assign_pf_identity(ExperimentalProteoform e, PtmSet set, Proteoform
                     e.begin--;
                     remove.Add(mod);
                 }
-                foreach (var ptm in remove) e.ptm_set.ptm_combination.Remove(ptm);
+                foreach (var ptm in remove)
+                {
+                    e.ptm_set.ptm_combination.Remove(ptm);
+                }
                 e.ptm_set = new PtmSet(e.ptm_set.ptm_combination);
             }
             else
@@ -265,7 +268,7 @@ private void assign_pf_identity(ExperimentalProteoform e, PtmSet set, Proteoform
 
             if (e.gene_name == null)
                 e.gene_name = this.gene_name;
-            else if(!e.topdown_id)
+            else if (!e.topdown_id)
                 e.gene_name.gene_names.Concat(this.gene_name.gene_names);
 
         }

ProteoformSuiteInternal/ProteoformCommunity.cs

@@ -77,7 +77,7 @@ public List<ProteoformRelation> relate(ExperimentalProteoform[] pfs1, Proteoform
                     {
                         pf1.ptm_set = null;
                         pf1.linked_proteoform_references = null;
-                        if(pf1 as TopDownProteoform == null) pf1.gene_name = null;
+                        if (pf1 as TopDownProteoform == null) pf1.gene_name = null;
                     }
 
                     if (limit_et_relations && (relation_type == ProteoformComparison.ExperimentalTheoretical || relation_type == ProteoformComparison.ExperimentalDecoy))
@@ -354,7 +354,7 @@ public void clear_families()
                 p.family = null;
                 p.ptm_set = new PtmSet(new List<Ptm>());
                 p.linked_proteoform_references = null;
-                if(p as TopDownProteoform == null) p.gene_name = null;
+                if (p as TopDownProteoform == null) p.gene_name = null;
             }
             foreach (Proteoform p in theoretical_proteoforms) p.family = null;
         }

ProteoformSuiteInternal/ProteoformFamily.cs

@@ -84,7 +84,7 @@ select f
         public void identify_experimentals()
         {
             HashSet<ExperimentalProteoform> identified_experimentals = new HashSet<ExperimentalProteoform>();
-            foreach(TheoreticalProteoform t in theoretical_proteoforms)
+            foreach (TheoreticalProteoform t in theoretical_proteoforms)
             {
                 lock (identified_experimentals)
                     foreach (ExperimentalProteoform e in t.identify_connected_experimentals(Sweet.lollipop.theoretical_database.all_possible_ptmsets, Sweet.lollipop.theoretical_database.all_mods_with_mass))
@@ -100,7 +100,7 @@ public void identify_experimentals()
             {
                 last_identified_count = identified_experimentals.Count;
                 HashSet<ExperimentalProteoform> tmp_new_experimentals = new HashSet<ExperimentalProteoform>();
-                foreach(ExperimentalProteoform id_experimental in newly_identified_experimentals)
+                foreach (ExperimentalProteoform id_experimental in newly_identified_experimentals)
                 {
                     lock (identified_experimentals) lock (tmp_new_experimentals)
                             foreach (ExperimentalProteoform new_e in id_experimental.identify_connected_experimentals(Sweet.lollipop.theoretical_database.all_possible_ptmsets, Sweet.lollipop.theoretical_database.all_mods_with_mass))

ProteoformSuiteInternal/ResultsSummaryGenerator.cs

@@ -241,7 +241,7 @@ public static string proteoform_families_report()
             List<string> experimental_ids = Sweet.lollipop.target_proteoform_community.experimental_proteoforms.Where(e => !e.topdown_id && e.linked_proteoform_references != null && (Sweet.lollipop.count_adducts_as_identifications || !e.adduct))
                 .Select(p => String.Join(",", (p.linked_proteoform_references.First() as TheoreticalProteoform).ExpandedProteinList.SelectMany(e => e.AccessionList.Select(a => a.Split('_')[0])).Distinct()) + "_" + p.begin + "_" + p.end + "_" + String.Join(", ", p.ptm_set.ptm_combination.Select(ptm => Sweet.lollipop.theoretical_database.unlocalized_lookup.TryGetValue(ptm.modification, out UnlocalizedModification x) ? x.id : ptm.modification.id).OrderBy(m => m))).ToList();
             report += experimental_ids.Distinct().Count() + "\tUnique Intact-Mass Experimental Proteoforms Identifications" + Environment.NewLine;
-            int unique_td = Sweet.lollipop.topdown_proteoforms.Select(p => p.pfr).Distinct().Count();
+            int unique_td = Sweet.lollipop.topdown_proteoforms.Select(p => p.pfr_accession).Distinct().Count();
             report += unique_td + "\tUnique Top-Down Proteoforms Identifications (TDPortal)"  + Environment.NewLine;
             List<string> topdown_ids = Sweet.lollipop.topdown_proteoforms
                .Select(p => p.accession.Split('_')[0].Split('-')[0] + "_" + p.topdown_begin + "_" + p.topdown_end + "_" + String.Join(", ", p.topdown_ptm_set.ptm_combination.Select(ptm => Sweet.lollipop.theoretical_database.unlocalized_lookup.TryGetValue(ptm.modification, out UnlocalizedModification x) ? x.id : ptm.modification.id).OrderBy(m => m))).ToList();
@@ -468,10 +468,10 @@ public static DataTable experimental_results_dataframe(TusherAnalysis analysis)
         public static DataTable topdown_results_dataframe()
         {
             DataTable results = new DataTable();
-            results.Columns.Add("PFR", typeof(string));
-            results.Columns.Add("Theoretiecal Accession", typeof(string));
+            results.Columns.Add("PFR Accession", typeof(string));
+            results.Columns.Add("Theoretical Accession", typeof(string));
             results.Columns.Add("Top-Down Full Accession", typeof(string));
-            results.Columns.Add("Top-Down  Accession", typeof(string));
+            results.Columns.Add("Top-Down Accession", typeof(string));
             results.Columns.Add("Theoretical Description", typeof(string));
             results.Columns.Add("Theoretical Begin and End", typeof(string));
             results.Columns.Add("Top-Down Begin and End", typeof(string));
@@ -493,7 +493,7 @@ public static DataTable topdown_results_dataframe()
             foreach (TopDownProteoform td in Sweet.lollipop.topdown_proteoforms)
             {
                 results.Rows.Add(
-                    td.pfr,
+                    td.pfr_accession,
                     td.linked_proteoform_references == null ? "N/A" : (td.linked_proteoform_references.First() as TheoreticalProteoform).accession,
                     td.accession,
                     td.accession.Split('_')[0],