Merge pull request crux-toolkit#671 from crux-toolkit/tide-lite

Added tide-lite version

doc/user/release-notes.html

@@ -55,6 +55,9 @@ <h2>Release notes for Crux</h2>
 <h3>Version 4.2</h3> April 6, 2024
 
 <h4>Major changes</h4>
+  <li>18 Oct 2024: speeded up tide-search, restuctured its code.
+  <li>18 Oct 2024: Added support to produce output in mztab format.
+  <li>18 Oct 2024: tide-index supports unimod codes.  
   <li>6 April 2024: Updated to use Percolator commit d0d48b5.
   <li>11 March 2024: Updated to use ProteoWizard 3.0.24044.fd6604. This required shifting Crux and
   dependencies to the C++14 standard and disabling the C++11 ABI. This fixed
@@ -65,6 +68,10 @@ <h4>Major changes</h4>
   </li>
 <h4>Minor changes</h4>
 <ul>
+  <li>18 Oct 2024: terminal amino acids can be modified by terminal modifications and resiudal mods.
+  <li>18 Oct 2024: tide-search reports tailor scores, and statistics about b-y- ions.
+  <li>18 Oct 2024: tide-search runs only combined p-values.
+  <li>18 Oct 2024: non-used options removed from tide-search: --compute-sp, --file-column, --brief-output, --peptide-centric-search, --evidence-granularity, --use-tailor-calibration (it is automatically calculated), From tide-index:--keep-terminal-aminos.  
   <li>15 September 2024: Unify Sorting. Replace quick sort algorithms with std::sort</li>
   <li>11 September 2024: Removed usage plot from Crux website home page.
   <li>06 Auguest 2024: Minor changes to website support.</li>

src/app/AssignConfidenceApplication.cpp

@@ -179,7 +179,7 @@ int AssignConfidenceApplication::main(const vector<string>& input_files) {
 
     MatchCollection* match_collection = parser.create(target_path, Params::GetString("protein-database"));
     distinct_matches = match_collection->getHasDistinctMatches();
-    if (!match_collection->hasDecoyIndexes()) {
+    if (!match_collection->hasMulitpleDecoys()) {
       avgTdc = false;
     }
 
@@ -190,7 +190,7 @@ int AssignConfidenceApplication::main(const vector<string>& input_files) {
     // in the list below.
     if (score_type == INVALID_SCORER_TYPE) {
       vector<SCORER_TYPE_T> scoreTypes;
-      scoreTypes.push_back(TAILOR_SCORE); //Added for tailor score calibration method by AKF
+      scoreTypes.push_back(TAILOR_SCORE); 
       scoreTypes.push_back(XCORR);
       scoreTypes.push_back(EVALUE);
       scoreTypes.push_back(BOTH_PVALUE);
@@ -240,6 +240,8 @@ int AssignConfidenceApplication::main(const vector<string>& input_files) {
     target_matches->setScoredType(SP, match_collection->getScoredType(SP));
     target_matches->setScoredType(BY_IONS_MATCHED, match_collection->getScoredType(BY_IONS_MATCHED));
     target_matches->setScoredType(BY_IONS_TOTAL, match_collection->getScoredType(BY_IONS_TOTAL));
+    target_matches->setScoredType(BY_ION_FRACTION, match_collection->getScoredType(BY_ION_FRACTION));
+    target_matches->setScoredType(BY_ION_REPEAT_MATCH, match_collection->getScoredType(BY_ION_REPEAT_MATCH));
     target_matches->setScoredType(SIDAK_ADJUSTED, sidak);
     //Added for tailor score calibration method by AKF
     target_matches->setScoredType(TAILOR_SCORE, match_collection->getScoredType(TAILOR_SCORE));
@@ -257,7 +259,7 @@ int AssignConfidenceApplication::main(const vector<string>& input_files) {
       MatchCollection* temp_collection = parser.create(decoy_path, Params::GetString("protein-database"));
       carp(CARP_INFO, "Found %d PSMs in %s.", temp_collection->getMatchTotal(), decoy_path.c_str());
 
-      if (temp_collection->hasDecoyIndexes()) {
+      if (temp_collection->hasMulitpleDecoys()) {
         avgTdc = true;
         MatchIterator* decoy_iter = new MatchIterator(temp_collection);
         while (decoy_iter->hasNext()) {
@@ -524,6 +526,7 @@ int AssignConfidenceApplication::main(const vector<string>& input_files) {
     cols_to_print[FILE_COL] = Params::GetBool("file-column");
     cols_to_print[SCAN_COL] = true;
     cols_to_print[CHARGE_COL] = true;
+    cols_to_print[RETENTION_TIME_COL] = true;
     cols_to_print[SPECTRUM_PRECURSOR_MZ_COL] = true;
     cols_to_print[SPECTRUM_NEUTRAL_MASS_COL] = true;
     cols_to_print[PEPTIDE_MASS_COL] = true;
@@ -556,6 +559,8 @@ int AssignConfidenceApplication::main(const vector<string>& input_files) {
     }
     cols_to_print[BY_IONS_MATCHED_COL] = target_matches->getScoredType(BY_IONS_MATCHED);
     cols_to_print[BY_IONS_TOTAL_COL] = target_matches->getScoredType(BY_IONS_TOTAL);
+    cols_to_print[BY_IONS_FRACTION_COL] = target_matches->getScoredType(BY_ION_FRACTION);
+    cols_to_print[BY_IONS_REPEAT_MATCH_COL] = target_matches->getScoredType(BY_ION_REPEAT_MATCH);
 
     if (distinct_matches) {
       cols_to_print[DISTINCT_MATCHES_SPECTRUM_COL] = true;
@@ -651,9 +656,16 @@ int AssignConfidenceApplication::main(const vector<string>& input_files) {
     if (*i < 0.05) ++fdr5;
     if (*i < 0.10) ++fdr10;
   }
-  carp(CARP_INFO, "Number of PSMs at 1%% FDR = %d.", fdr1);
-  carp(CARP_INFO, "Number of PSMs at 5%% FDR = %d.", fdr5);
-  carp(CARP_INFO, "Number of PSMs at 10%% FDR = %d.", fdr10);
+  if (estimation_method == PEPTIDE_LEVEL_METHOD) {
+    carp(CARP_INFO, "Number of peptides at 1%% FDR = %d.", fdr1);
+    carp(CARP_INFO, "Number of peptides at 5%% FDR = %d.", fdr5);
+    carp(CARP_INFO, "Number of peptides at 10%% FDR = %d.", fdr10);
+  } else {
+    carp(CARP_INFO, "Number of PSMs at 1%% FDR = %d.", fdr1);
+    carp(CARP_INFO, "Number of PSMs at 5%% FDR = %d.", fdr5);
+    carp(CARP_INFO, "Number of PSMs at 10%% FDR = %d.", fdr10);
+
+  }
 
   // Store p-values to q-values as a hash, and then assign them.
   map<FLOAT_T, FLOAT_T> qvalue_hash = store_arrays_as_hash(target_scores, qvalues);

src/app/CruxApplication.cpp

@@ -192,6 +192,9 @@ void CruxApplication::initializeParams(
       for (map<string, string>::const_iterator options_index = options.begin(); options_index != options.end(); options_index++) {
         carp(CARP_DEBUG, "->: %s", options_index->first.c_str());
       }
+      for (vector<string>::const_iterator it = appOptions.begin(); it != appOptions.end(); ++it) {
+        carp(CARP_DEBUG, "%s options->: %s", appName.c_str(), (*it).c_str());
+      }
 
       /* This loop is intended to check the parameters of the current application against all the appplications in application list*/
       for (map<string, string>::const_iterator options_index = options.begin(); options_index != options.end(); options_index++) {