- added support for Proteome Discoverer 3.1 in BiblioSpec: separate p…

…dResultDetails file, reading charge from PSM table instead of MSnSpectrumInfo, RAW file name in WorkflowInputFiles
ProteoWizard · Nov 6, 2023 · d2ae15b · d2ae15b
1 parent 9f74468
commit d2ae15b
Show file tree

Hide file tree

Showing 5 changed files with 96 additions and 5 deletions.
diff --git a/pwiz_tools/BiblioSpec/src/MSFReader.cpp b/pwiz_tools/BiblioSpec/src/MSFReader.cpp
@@ -143,7 +143,17 @@ namespace BiblioSpec
         sqlite3_stmt* statement = NULL; // id, rt, mass, charge, peaks
         bool hasCompensationVoltage = false;
 
-        if (filtered_ || !versionLess(2, 2)) { // < 2.2 and filtered, or 2.2+
+        if (!versionLess(3, 1) && bfs::exists(bfs::change_extension(bfs::path(msfName_), ".pdResultDetails")))
+        {
+            bfs::path pdResultDetails = bfs::change_extension(bfs::path(msfName_), ".pdResultDetails");
+            sqlite3_exec(msfFile_, ("ATTACH DATABASE '" + pdResultDetails.generic_string() + "' AS details").c_str(), nullptr, nullptr, nullptr);
+            specCount = getRowCount("MSnSpectrumInfo WHERE SpectrumID IN (SELECT DISTINCT MSnSpectrumInfoSpectrumID FROM TargetPsmsMSnSpectrumInfo)");
+            statement = getStmt(
+                std::string("SELECT SpectrumID, MSnSpectrumInfo.RetentionTime, Mass, Charge, Spectrum, MSnSpectrumInfo.WorkflowID") +
+                (hasCompensationVoltage ? ", CompVoltageV " : " ") +
+                "FROM MSnSpectrumInfo "
+                "JOIN details.MassSpectrumItems ON MSnSpectrumInfo.SpectrumID = details.MassSpectrumItems.ID AND MSnSpectrumInfo.WorkflowID = details.MassSpectrumItems.WorkflowID");
+        } else if (filtered_ || !versionLess(2, 2)) { // < 2.2 and filtered, or 2.2+
             specCount = getRowCount("MSnSpectrumInfo WHERE SpectrumID IN (SELECT DISTINCT MSnSpectrumInfoSpectrumID FROM TargetPsmsMSnSpectrumInfo)");
             hasCompensationVoltage = columnExists(msfFile_, "MSnSpectrumInfo", "CompVoltageV");
             statement = getStmt(
@@ -173,7 +183,10 @@ namespace BiblioSpec
             specData->id = sqlite3_column_int(statement, 0);
             specData->retentionTime = sqlite3_column_double(statement, 1);
             specData->charge = sqlite3_column_int(statement, 3);
-            specData->mz = (mass + (PROTON_MASS * specData->charge)) / specData->charge;
+            if (specData->charge > 0)
+                specData->mz = (mass + (PROTON_MASS * specData->charge)) / specData->charge;
+            else
+                specData->mz = mass;
             if (hasCompensationVoltage)
             {
                 specData->ionMobilityType = IONMOBILITY_COMPENSATION_V;
@@ -369,6 +382,7 @@ namespace BiblioSpec
             string specId = uniqueSpecId(sqlite3_column_int(statement, 1), sqlite3_column_int(statement, 4));
             string sequence = lexical_cast<string>(sqlite3_column_text(statement, 2));
             double qvalue = pepConfidence <= 0 ? sqlite3_column_double(statement, 3) : 0;
+            int charge = sqlite3_column_int(statement, 7);
 
             auto findItr = spectra_.find(specId);
             if (findItr == spectra_.end()) {
@@ -427,7 +441,14 @@ namespace BiblioSpec
                 processedSpectra[specId] = ProcessedMsfSpectrum(curPSM_, qvalue, altScore);
             }
 
-            curPSM_->charge = findItr->second->charge;
+            if (findItr->second->charge > 0)
+                curPSM_->charge = findItr->second->charge;
+            else
+            {
+                // if charge was 0 for the spectrum, the mz should be mass, so convert it to m/z
+                curPSM_->charge = charge;
+                findItr->second->mz = (findItr->second->mz + (PROTON_MASS * charge)) / charge;
+            }
             curPSM_->unmodSeq = sequence;
             curPSM_->mods = versionLess(2, 2) && !filtered_
                 ? modSet.getMods(peptideId)
@@ -445,7 +466,7 @@ namespace BiblioSpec
                 psmFileName = fileIdToName(fileIdMapAccess->second);
                 fileIdMap.erase(fileIdMapAccess);
             } else {
-                psmFileName = lexical_cast<string>(sqlite3_column_text(statement, 5));
+                psmFileName = bfs::path(lexical_cast<string>(sqlite3_column_text(statement, 5))).filename().string();
             }
 
             // filename
@@ -531,6 +552,17 @@ namespace BiblioSpec
             }
         }
 
+        string filenameCol;
+        string filenameJoin;
+        if (columnExists(msfFile_, "TargetPsms", "SpectrumFileId"))
+        {
+            filenameCol = "wf.FileName";
+            filenameJoin = " JOIN WorkflowInputfiles wf ON psms.SpectrumFileId = wf.FileId";
+        } else
+        {
+            filenameCol = "psms.SpectrumFileName";
+        }
+
         string qValueCol;
         string qValueWhere;
         if (!hasQValues()) {
@@ -559,8 +591,9 @@ namespace BiblioSpec
         }
         stmtStr =
             "SELECT psms.PeptideID, psm_spec.MSnSpectrumInfoSpectrumID, psms.Sequence, " +
-                qValueCol + ", psms.WorkflowID, psms.SpectrumFileName" + (*outProtConfidence > 0 ? ", prots.ProteinFDRConfidence" : "") +
+                qValueCol + ", psms.WorkflowID, " + filenameCol + (*outProtConfidence > 0 ? ", prots.ProteinFDRConfidence" : ", 0") + ", psms.Charge" +
             " FROM TargetPsms psms"
+            + filenameJoin +
             " JOIN TargetPsmsMSnSpectrumInfo psm_spec ON psms.PeptideID = psm_spec.TargetPsmsPeptideID"
             "   AND psm_spec.TargetPsmsWorkflowID = psms.WorkflowID";
         countStr =

diff --git a/pwiz_tools/BiblioSpec/tests/Jamfile.jam b/pwiz_tools/BiblioSpec/tests/Jamfile.jam
@@ -263,6 +263,8 @@ blib-test-build tiny-v2-filtered-pdResult : -o : output/tiny-v2-filtered-pdResul
 blib-test-build md_special_filtered-pdResult : --unicode -o : output/md_special_filtered-pdResult.blib : md_special_filtered-pdResult.check zbuild.skip-lines : $(TEST_INPUTS_PATH)/md_special_filtered.pdResult ;
 blib-test-build example-pdResult-confidence3 : -o [email protected] : output/example-pdResult-confidence3.blib : example-pdResult-confidence3.check zbuild.skip-lines : $(TEST_INPUTS_PATH)/example.pdResult ;
 blib-test-build example-pdResult-numeric : -o [email protected] : output/example-pdResult-numeric.blib : example-pdResult-numeric.check zbuild.skip-lines : $(TEST_INPUTS_PATH)/example.pdResult ;
+blib-test-build-basic pd-3_1 : -o [email protected] : $(TEST_INPUTS_PATH)/230807_P1_Neo_ES904_TMTProPrecision_1ug_DIA1Th_HCD30_Survey.pdResult ;
+
 blib-test-build pilot : --unicode -o : output/pilot.blib : pilot.check : $(TEST_INPUTS_PATH)/MB1_98_03.group.xml ;
 blib-test-build pilot-mzid : --unicode -o : output/pilot-mzid.blib : pilot-mzid.check : $(TEST_INPUTS_PATH)/ProtPilotTest.mzid ;
 

diff --git a/...lioSpec/tests/inputs/230807_P1_Neo_ES904_TMTProPrecision_1ug_DIA1Th_HCD30_Survey.pdResult b/...lioSpec/tests/inputs/230807_P1_Neo_ES904_TMTProPrecision_1ug_DIA1Th_HCD30_Survey.pdResult
diff --git a/.../tests/inputs/230807_P1_Neo_ES904_TMTProPrecision_1ug_DIA1Th_HCD30_Survey.pdResultDetails b/.../tests/inputs/230807_P1_Neo_ES904_TMTProPrecision_1ug_DIA1Th_HCD30_Survey.pdResultDetails
diff --git a/pwiz_tools/BiblioSpec/tests/reference/pd-3_1.check b/pwiz_tools/BiblioSpec/tests/reference/pd-3_1.check
@@ -0,0 +1,56 @@
+libLSID	numSpecs	majorVersion	minorVersion
+urn:lsid:proteome.gs.washington.edu:spectral_library:bibliospec:redundant:pd-3_1.blib	10	1	10
+id	RefSpectraID	position	mass
+1	1	1	304.207146
+2	2	1	304.207146
+3	3	1	361.22861
+4	3	7	57.021464
+5	4	1	304.207146
+6	4	10	304.207146
+7	5	1	304.207146
+8	6	1	304.207146
+9	7	1	304.207146
+10	8	1	304.207146
+11	9	1	304.207146
+12	9	8	304.207146
+13	10	1	304.207146
+14	10	10	15.994915
+15	10	12	304.207146
+id	peptideSeq	precursorMZ	precursorCharge	peptideModSeq	prevAA	nextAA	copies	numPeaks	ionMobility	collisionalCrossSectionSqA	ionMobilityHighEnergyOffset	ionMobilityType	retentionTime	startTime	endTime	totalIonCurrent	moleculeName	chemicalFormula	precursorAdduct	inchiKey	otherKeys	fileID	SpecIDinFile	score	scoreType
+1	ASLTAAR	249.99881409	2	A[+304.2]SLTAAR	-	-	1	279	0.0	0.0	0.0	0	10.00001593	N/A	N/A	448944.42	N/A	N/A	N/A	N/A	N/A	1	174.67597	0.10103673	1
+2	SLSGTAR	250.49901245	2	S[+304.2]LSGTAR	-	-	1	287	0.0	0.0	0.0	0	10.00029557	N/A	N/A	524141.05	N/A	N/A	N/A	N/A	N/A	1	174.67598	0.12901614	1
+3	CHTIMNCTR	168.00210266	3	C[+361.2]HTIMNC[+57.0]TR	-	-	1	258	0.0	0.0	0.0	0	10.00099629	N/A	N/A	1117976.72	N/A	N/A	N/A	N/A	N/A	1	174.67600	0.12582744	1
+4	DNDNDDDDDK	200.68361104	3	D[+304.2]NDNDDDDDK[+304.2]	-	-	1	283	0.0	0.0	0.0	0	10.00065932	N/A	N/A	1243290.36	N/A	N/A	N/A	N/A	N/A	2	174.305486	0.45760199	1
+5	GQEQLNDQR	349.54405640	2	G[+304.2]QEQLNDQR	-	-	1	255	0.0	0.0	0.0	0	10.00002682	N/A	N/A	42187.50	N/A	N/A	N/A	N/A	N/A	3	174.547180	0.45065452	1
+6	EQEQQTEQA	350.54451416	2	E[+304.2]QEQQTEQA	-	-	1	282	0.0	0.0	0.0	0	10.00067368	N/A	N/A	112990.05	N/A	N/A	N/A	N/A	N/A	3	174.547182	0.00018705	1
+7	EQEQQTEQA	351.04472779	2	E[+304.2]QEQQTEQA	-	-	1	285	0.0	0.0	0.0	0	10.00099345	N/A	N/A	97466.69	N/A	N/A	N/A	N/A	N/A	3	174.547183	0.00926426	1
+8	QNSDRNDSR	351.54497193	2	Q[+304.2]NSDRNDSR	-	-	1	286	0.0	0.0	0.0	0	10.00131399	N/A	N/A	77916.64	N/A	N/A	N/A	N/A	N/A	3	174.547184	0.49736129	1
+9	EQVHPLHK	400.56721924	2	E[+304.2]QVHPLHK[+304.2]	-	-	1	131	0.0	0.0	0.0	0	10.00060151	N/A	N/A	14828.10	N/A	N/A	N/A	N/A	N/A	4	174.789774	0.49219457	1
+10	SGESSNSDAMGK	450.08977173	2	S[+304.2]GESSNSDAM[+16.0]GK[+304.2]	-	-	1	139	0.0	0.0	0.0	0	10.00024502	N/A	N/A	13120.38	N/A	N/A	N/A	N/A	N/A	5	174.1027885	0.24223713	1
+id	fileName	idFileName	cutoffScore
+1	230807_P1_Neo_ES904_TMTProPrecision_1ug_DIA1Th_HCD30_Survey1.raw	/BiblioSpec/tests/inputs/230807_P1_Neo_ES904_TMTProPrecision_1ug_DIA1Th_HCD30_Survey.pdResult	0.5
+2	230807_P1_Neo_ES904_TMTProPrecision_1ug_DIA1Th_HCD30_Survey2.raw	/BiblioSpec/tests/inputs/230807_P1_Neo_ES904_TMTProPrecision_1ug_DIA1Th_HCD30_Survey.pdResult	0.5
+3	230807_P1_Neo_ES904_TMTProPrecision_1ug_DIA1Th_HCD30_Survey3.raw	/BiblioSpec/tests/inputs/230807_P1_Neo_ES904_TMTProPrecision_1ug_DIA1Th_HCD30_Survey.pdResult	0.5
+4	230807_P1_Neo_ES904_TMTProPrecision_1ug_DIA1Th_HCD30_Survey4.raw	/BiblioSpec/tests/inputs/230807_P1_Neo_ES904_TMTProPrecision_1ug_DIA1Th_HCD30_Survey.pdResult	0.5
+5	230807_P1_Neo_ES904_TMTProPrecision_1ug_DIA1Th_HCD30_Survey5.raw	/BiblioSpec/tests/inputs/230807_P1_Neo_ES904_TMTProPrecision_1ug_DIA1Th_HCD30_Survey.pdResult	0.5
+id	scoreType	probabilityType
+0	UNKNOWN	NOT_A_PROBABILITY_VALUE
+1	PERCOLATOR QVALUE	PROBABILITY_THAT_IDENTIFICATION_IS_INCORRECT
+2	PEPTIDE PROPHET SOMETHING	PROBABILITY_THAT_IDENTIFICATION_IS_CORRECT
+3	SPECTRUM MILL	NOT_A_PROBABILITY_VALUE
+4	IDPICKER FDR	PROBABILITY_THAT_IDENTIFICATION_IS_INCORRECT
+5	MASCOT IONS SCORE	PROBABILITY_THAT_IDENTIFICATION_IS_INCORRECT
+6	TANDEM EXPECTATION VALUE	PROBABILITY_THAT_IDENTIFICATION_IS_INCORRECT
+7	PROTEIN PILOT CONFIDENCE	PROBABILITY_THAT_IDENTIFICATION_IS_CORRECT
+8	SCAFFOLD SOMETHING	PROBABILITY_THAT_IDENTIFICATION_IS_CORRECT
+9	WATERS MSE PEPTIDE SCORE	NOT_A_PROBABILITY_VALUE
+10	OMSSA EXPECTATION SCORE	PROBABILITY_THAT_IDENTIFICATION_IS_INCORRECT
+11	PROTEIN PROSPECTOR EXPECTATION SCORE	PROBABILITY_THAT_IDENTIFICATION_IS_INCORRECT
+12	SEQUEST XCORR	PROBABILITY_THAT_IDENTIFICATION_IS_INCORRECT
+13	MAXQUANT SCORE	PROBABILITY_THAT_IDENTIFICATION_IS_INCORRECT
+14	MORPHEUS SCORE	PROBABILITY_THAT_IDENTIFICATION_IS_INCORRECT
+15	MSGF+ SCORE	PROBABILITY_THAT_IDENTIFICATION_IS_INCORRECT
+16	PEAKS CONFIDENCE SCORE	PROBABILITY_THAT_IDENTIFICATION_IS_INCORRECT
+17	BYONIC SCORE	PROBABILITY_THAT_IDENTIFICATION_IS_INCORRECT
+18	PEPTIDE SHAKER CONFIDENCE	PROBABILITY_THAT_IDENTIFICATION_IS_CORRECT
+19	GENERIC Q-VALUE	PROBABILITY_THAT_IDENTIFICATION_IS_INCORRECT