- fixed BiblioSpec to use the spectrumNativeID attribute in pepXML wh…

…en reading MSFragger pepXML (reported by Jennifer) - fixed replacement of invalid output filename characters (thanks to Nick)
ProteoWizard · Feb 6, 2024 · e0822ec · e0822ec
1 parent 1f52dda
commit e0822ec
Show file tree

Hide file tree

Showing 5 changed files with 365 additions and 12 deletions.
diff --git a/pwiz_tools/BiblioSpec/src/PepXMLreader.cpp b/pwiz_tools/BiblioSpec/src/PepXMLreader.cpp
@@ -305,16 +305,22 @@ void PepXMLreader::startElement(const XML_Char* name, const XML_Char** attr)
        }
        // if morpheus or msfragger type
        else if (analysisType_ == MORPHEUS_ANALYSIS || analysisType_ == MSFRAGGER_ANALYSIS || parentAnalysisType_ == MSFRAGGER_ANALYSIS) {
-           spectrumName = getRequiredAttrValue("spectrum", attr);
+           spectrumName = getAttrValue("spectrumNativeID", attr);
            scanNumber = getIntRequiredAttrValue("start_scan", attr);
            scanIndex = scanNumber - 1;
 
-           // HACK: remove zero padding of scan numbers in the spectrum attribute title because MSFragger MGF files don't have padding
-           if (lookUpBy_ == NAME_ID && (analysisType_ == MSFRAGGER_ANALYSIS || parentAnalysisType_ == MSFRAGGER_ANALYSIS))
-           {
-               namespace bxp = boost::xpressive;
-               auto scanNumberPaddingRegex = bxp::sregex::compile("(.*?\\.)0*(\\d+\\.)0*(\\d+\\.\\d+)");
-               spectrumName = bxp::regex_replace(spectrumName, scanNumberPaddingRegex, "$1$2$3");
+           if (!spectrumName.empty()) {
+               lookUpBy_ = NAME_ID;
+           }
+           else {
+               spectrumName = getRequiredAttrValue("spectrum", attr);
+               // HACK: remove zero padding of scan numbers in the spectrum attribute title because MSFragger MGF files don't have padding
+               if (lookUpBy_ == NAME_ID && (analysisType_ == MSFRAGGER_ANALYSIS || parentAnalysisType_ == MSFRAGGER_ANALYSIS))
+               {
+                   namespace bxp = boost::xpressive;
+                   auto scanNumberPaddingRegex = bxp::sregex::compile("(.*?\\.)0*(\\d+\\.)0*(\\d+\\.\\d+)");
+                   spectrumName = bxp::regex_replace(spectrumName, scanNumberPaddingRegex, "$1$2$3");
+               }
            }
        }
        // this should never happen, error should have been thrown earlier

diff --git a/pwiz_tools/BiblioSpec/tests/Jamfile.jam b/pwiz_tools/BiblioSpec/tests/Jamfile.jam
@@ -243,8 +243,9 @@ blib-test-build comet : -o : output/comet.blib : comet.check zbuild.skip-lines :
 blib-test-build comet-prg2012-wiff : -o -c@0 : output/comet-prg2012-wiff.blib : comet-prg2012-wiff.check zbuild.skip-lines : $(TEST_INPUTS_PATH)/201208-378803-cm.pep.xml : <vendor-api-support>off:<build>no ;
 blib-test-build msfragger-tims : -o : output/msfragger-tims.blib : msfragger-tims.check  : "$(TEST_INPUTS_PATH)/Hela$(.percent)20QC_PASEF_Slot1-5_01_57_cutout_2min.pepXML" ;
 blib-test-build msfragger-thermo : -o : output/msfragger-thermo.blib : msfragger-thermo.check  : $(TEST_INPUTS_PATH)/BSA_min_21.pepXML ;
-blib-test-build peptideprophet-msfragger-thermo-mzml : -o : output/peptideprophet-msfragger-thermo-mzml.blib : peptideprophet-msfragger-thermo-mzml.check  : $(TEST_INPUTS_PATH)/peptideprophet-msfragger-thermo-mzml.pep.xml ;
-blib-test-build peptideprophet-msfragger-bruker-mgf : -o : output/peptideprophet-msfragger-bruker-mgf.blib : peptideprophet-msfragger-bruker-mgf.check  : $(TEST_INPUTS_PATH)/peptideprophet-msfragger-bruker-mgf.pep.xml ;
+blib-test-build-basic peptideprophet-msfragger-thermo-mzml : -o : $(TEST_INPUTS_PATH)/peptideprophet-msfragger-thermo-mzml.pep.xml ;
+blib-test-build-basic peptideprophet-msfragger-thermo-mzml-nativeid : -o : $(TEST_INPUTS_PATH)/peptideprophet-msfragger-thermo-mzml-nativeid.pep.xml ;
+blib-test-build-basic peptideprophet-msfragger-bruker-mgf : -o : $(TEST_INPUTS_PATH)/peptideprophet-msfragger-bruker-mgf.pep.xml ;
 blib-test-build-basic msfragger-check-parent-path-first : -o : $(TEST_INPUTS_PATH)/msfragger-check-parent-path-first.pepXML ;
 blib-test-build-basic msfragger-check-parent-path-first-with-missing-file : -o -e@inputs$(.slash)msfragger-check-parent-path-first : $(TEST_INPUTS_PATH)/msfragger-check-parent-path-first-with-missing-file.pepXML ;