WIP: reading X\!Tandem results

src/CMakeLists.txt

@@ -29,8 +29,8 @@ SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${Qt5Xml_EXECUTABLE_COMPILE_FLAGS} ${Qt5
 
 #sudo apt-get install libpappsomspp-dev
 #FIND_PACKAGE( Pappsomspp REQUIRED )
- SET (PAPPSOMSPP_DIR  "/home/olivier/eclipse/git/pappsomspp")
-# SET (PAPPSOMSPP_DIR  "/home/langella/developpement/git/pappsomspp")
+# SET (PAPPSOMSPP_DIR  "/home/olivier/eclipse/git/pappsomspp")
+ SET (PAPPSOMSPP_DIR  "/home/langella/developpement/git/pappsomspp")
  SET (PAPPSOMSPP_INCLUDE_DIR "${PAPPSOMSPP_DIR}/src")
  SET (PAPPSOMSPP_QT4_LIBRARY "${PAPPSOMSPP_DIR}/cbuild/src/libpappsomspp-qt4.so")
 

src/core/identification_sources/identificationxtandemfile.cpp

@@ -78,7 +78,7 @@ void IdentificationXtandemFile::parseTo(Project* p_project) {
         }
     }
     
-    XtandemSaxHandler * parser = new XtandemSaxHandler(p_project, identification_group_p);
+    XtandemSaxHandler * parser = new XtandemSaxHandler(p_project, identification_group_p, this);
 
     QXmlSimpleReader simplereader;
     simplereader.setContentHandler(parser);

src/core/identificationgroup.cpp

@@ -67,7 +67,7 @@ void IdentificationGroup::addProteinMatch(ProteinMatch * protein_match) {
         throw pappso::PappsoException(QObject::tr("Error adding protein match : accession is empty"));
     }
     for (ProteinMatch * p_protein_match : _protein_match_list) {
-        if (p_protein_match->getProteinXtpSp().get()->getAccession() == accession) {
+        if ((p_protein_match != protein_match) && (p_protein_match->getProteinXtpSp().get()->getAccession() == accession)) {
             throw pappso::PappsoException(QObject::tr("Error adding protein match : accession %1 already registered").arg(accession));
         }
     }

src/gui/mainwindow.cpp

@@ -64,6 +64,7 @@ void XtpLoaderThread::doLoadingResults(bool is_individual, AutomaticFilterParame
             project_sp.get()->readResultFile(filename);
         }
 
+        project_sp.get()->updateAutomaticFilters(param);
         emit projectReady(project_sp);
 
     }
@@ -98,6 +99,7 @@ MainWindow::MainWindow(QWidget *parent):
     //addDockWidget(Qt::RightDockWidgetArea, dock);
 
     qRegisterMetaType<ProjectSp>("ProjectSp");
+    qRegisterMetaType<AutomaticFilterParameters>("AutomaticFilterParameters");
 #if QT_VERSION >= 0x050000
     // Qt5 code
     /*
@@ -110,6 +112,7 @@ MainWindow::MainWindow(QWidget *parent):
 
     connect(this, SIGNAL(operateXpipFile(QString)), worker,SLOT(doXpipFileLoad(QString)));
     connect(worker, SIGNAL(projectReady(ProjectSp)), this,SLOT(doProjectReady(ProjectSp)));
+    connect(this, SIGNAL(operateLoadingResults(bool,AutomaticFilterParameters,QStringList)), worker,SLOT(doLoadingResults(bool,AutomaticFilterParameters,QStringList)));
     connect(_p_load_results_dialog, SIGNAL(accepted()), this,SLOT(doAcceptedLoadResultDialog()));
     /*
         connect(&workerThread, SIGNAL(finished()), worker, SLOT(deleteLater()));

src/input/xpipsaxhandler.cpp

@@ -240,8 +240,6 @@ bool XpipSaxHandler::startElement_peptide(QXmlAttributes attributes) {
     _p_peptide_match->setStart(attributes.value("start").simplified().toUInt()-1);
     _p_peptide_match->setCharge(attributes.value("charge").simplified().toUInt());
 
-    _p_peptide_match->setCharge(attributes.value("charge").simplified().toUInt());
-
     IdentificationDataSource* p_identification_data_source = _p_project->getIdentificationDataSourceStore().getInstance(attributes.value("sample_file").simplified()).get();
     _p_peptide_match->setIdentificationDataSource( p_identification_data_source);
     if (p_identification_data_source->getMsRunSp().get() == nullptr) {

src/input/xtandemsaxhandler.cpp

@@ -35,9 +35,13 @@
 #include "../utils/peptidestore.h"
 #include "../utils/proteinstore.h"
 
-XtandemSaxHandler::XtandemSaxHandler(Project * p_project, IdentificationGroup * p_identification_group):_p_project(p_project)
+XtandemSaxHandler::XtandemSaxHandler(Project * p_project, IdentificationGroup * p_identification_group,
+                                     IdentificationDataSource * p_identification_data_source):_p_project(p_project)
 {
     _p_identification_group = p_identification_group;
+
+    _p_identification_data_source =p_identification_data_source;
+    _sp_msrun = p_identification_data_source->getMsRunSp();
 }
 
 XtandemSaxHandler::~XtandemSaxHandler()
@@ -63,8 +67,7 @@ bool XtandemSaxHandler::startElement(const QString & namespaceURI, const QString
         }
         else if (qName == "file") {
             is_ok = startElement_file(attributes);
-        } else if (qName == "peptide") {
-            is_ok = startElement_peptide(attributes);
+
         } else if (qName == "aa") {
             is_ok = startElement_aa(attributes);
         } else if (qName == "domain") {
@@ -117,7 +120,7 @@ bool XtandemSaxHandler::endElement(const QString & namespaceURI, const QString &
 
 bool XtandemSaxHandler::startElement_group(QXmlAttributes attrs) {
     //<group id="1976" mh="1120.529471" z="2" rt="PT667.022S" expect="9.7e-04" label="GRMZM2G083841_P01 P04711 Phosphoenolpyruvate carboxylase 1 (PEPCase 1)(PEPC 1)(EC..." type="model" sumI="5.34" maxI="35986.9" fI="359.869" act="0" >
-
+    bool is_ok = true;
     // logger.debug("startElementgroup begin");
     // <group label="performance parameters" type="parameters">
     _current_group_label = attrs.value("label");
@@ -128,118 +131,127 @@ bool XtandemSaxHandler::startElement_group(QXmlAttributes attrs) {
         _charge = attrs.value("z").toUInt();
         //_retention_time = attrs.value("rt");
     }
+    return is_ok;
 }
 
 bool XtandemSaxHandler::startElement_note(QXmlAttributes attributes) {
 //<note label="description">GRMZM2G083841_P01 P04711 Phosphoenolpyruvate carboxylase 1 (PEPCase 1)(PEPC 1)(EC //4.1.1.31) seq=translation; coord=9:61296279..61301686:1; parent_transcript=GRMZM2G083841_T01;
     ////parent_gene=GRMZM2G083841</note>
+    bool is_ok = true;
     _is_protein_description = false;
     if (attributes.value("label") == "description") {
         if (_tag_stack[_tag_stack.size() - 2] == "protein") {
             _is_protein_description = true;
         }
     }
+    return is_ok;
 }
 
 bool XtandemSaxHandler::startElement_protein(QXmlAttributes attributes) {
 //<protein expect="-704.6" id="1976.1" uid="195701" label="GRMZM2G083841_P01 P04711 Phosphoenolpyruvate carboxylase 1 (PEPCase 1)(PEPC 1)(EC..." sumI="9.36" >
-
-    qDebug() << "startElement_protein ";
+    bool is_ok = true;
+    //qDebug() << "startElement_protein begin";
     QString accession = attributes.value("label").simplified().split(" ", QString::SkipEmptyParts).at(0);
-    ProteinMatch * p_protein_match = _p_identification_group->getProteinMatch(accession);
+    //qDebug() << "startElement_protein accession" << accession;
+    _p_protein_match = _p_identification_group->getProteinMatch(accession);
 
+    //qDebug() << "startElement_protein p_protein_match 1 " << _p_protein_match;
     _current_protein.setAccession(accession);
-    if (p_protein_match == nullptr) {
+    if (_p_protein_match == nullptr) {
         _p_protein_match = new ProteinMatch();
+	//qDebug() << "startElement_protein p_protein_match 2 " << _p_protein_match;
         _p_protein_match->setChecked(false);
 
     }
+    //qDebug() << "startElement_protein p_protein_match 3 " << _p_protein_match;
     ProteinXtpSp sp_xtp_protein = _current_protein.makeProteinXtpSp();
-    p_protein_match->setProteinXtpSp(_p_project->getProteinStore().getInstance(sp_xtp_protein));
-    qDebug() << "startElement_protein end" ;
-    return true;
+    _p_protein_match->setProteinXtpSp(_p_project->getProteinStore().getInstance(sp_xtp_protein));
+    
+    _p_identification_group->addProteinMatch(_p_protein_match);
+    //qDebug() << "startElement_protein end" ;
+    return is_ok;
 }
 
 
 bool XtandemSaxHandler::startElement_file(QXmlAttributes attributes) {
+    bool is_ok = true;
     //<file type="peptide" URL="/gorgone/pappso/formation/TD/Database/Genome_Z_mays_5a.fasta"/>
     if (attributes.value("type") == "peptide") {
         //prot_.setDatabase(identification_.getDatabaseSet().getInstance(
-         //                     attrs.getValue("URL")));
+        //                     attrs.getValue("URL")));
     }
+    return is_ok;
 }
 
 bool XtandemSaxHandler::startElement_domain(QXmlAttributes attributes) {
 //<domain id="1976.1.1" start="620" end="629" expect="9.7e-04" mh="1120.5307" delta="-0.0012" hyperscore="29.9"
     //nextscore="10.2" y_score="10.4" y_ions="7" b_score="11.2" b_ions="3" pre="QLYR" post="RYGV"
     //seq="AQEEMAQVAK" missed_cleavages="0">
-
     qDebug() << "startElement_domain ";
+    bool is_ok = true;
+    _current_text = _current_text.simplified().replace(" ", "");
+    if (!_current_text.isEmpty()) {
+        _p_protein_match->getProteinXtpSp().get()->setSequence(_current_text);
+    }
+
+    // <domain id="4017.1.1" start="21" end="31" expect="2.0e-06"
+    // mh="1263.575"
+    // delta="0.998" hyperscore="32.9" nextscore="12.2" y_score="10.7"
+    // y_ions="9" b_score="0.0" b_ions="0"
+    // pre="VLGR" post="VEFM" seq="TGSQGQCTQVR" missed_cleavages="10">
+
+    // valeur généric du scan
+    _current_peptide_sp = PeptideXtp(attributes.value("seq").simplified()).makePeptideXtpSp();
+    _p_peptide_match = new PeptideMatch(_sp_msrun.get(), attributes.value("id").simplified().section(".",0,0).toUInt());
+
+    _p_peptide_match->setRetentionTime(_retention_time);
+    _p_peptide_match->setEvalue(attributes.value("expect").simplified().toDouble());
+
+    pappso::pappso_double xtandem_mhtheo = attributes.value("mh").simplified().toDouble();
+    pappso::pappso_double xtandem_delta = attributes.value("delta").simplified().toDouble();
+
+    pappso::pappso_double exp_mass = xtandem_mhtheo - xtandem_delta;
 
-    MsRunSp ms_run =  _p_project->getMsRunStore().getInstance(attributes.value("value").simplified());
-    ms_run.get()->setXmlId(attributes.value("value").simplified());
-    ms_run.get()->setFilename(attributes.value("value").simplified());
-    _p_identification_group->addMsRunSp(ms_run);
-    qDebug() << "startElement_domain end" ;
-    return true;
-}
-bool XtandemSaxHandler::startElement_peptide(QXmlAttributes attributes) {
-
-//<peptide sample="20120208_Blein_rep4_1_B03_DW21-4-26-328"
-    //sample_file="/gorgone/pappso/moulon/users/Melisande/test-param-masschroq/20120208_Blein_rep4_1_B03_DW21-4-26-328.xml"
-    //scan="2589" scan_in_xtandem="2589" RT="603" mhplus_obser="873.5401" mhplus_theo="873.5408" deltamass="-7.0E-4"
-    //sequence="IATAIEKK" pre="NPAR" post="AADA" start="331" stop="338" charge="2" evalue="9.2E-4" hypercorr="35.2" validate="true">
-//<modifs></modifs></peptide>
-
-    //<modifs><modif aa="M" modvalue="15.99491" posi="17" posi_in_prot="49"/>
-//</modifs>
-    qDebug() << "startElement_peptide ";
-    _current_peptide_sp = PeptideXtp(attributes.value("sequence").simplified()).makePeptideXtpSp();
-    MsRunSp ms_run_id =  _p_project->getMsRunStore().getInstance(attributes.value("sample").simplified());
-    _p_peptide_match = new PeptideMatch(ms_run_id.get(), attributes.value("scan").simplified().toUInt());
-    _p_peptide_match->setRetentionTime(attributes.value("RT").simplified().toDouble());
-    _p_peptide_match->setEvalue(attributes.value("evalue").simplified().toDouble());
-    pappso::pappso_double exp_mass = attributes.value("mhplus_obser").simplified().toDouble() - pappso::MHPLUS;
     _p_peptide_match->setExperimentalMass(exp_mass);
     _p_peptide_match->setStart(attributes.value("start").simplified().toUInt()-1);
-    _p_peptide_match->setCharge(attributes.value("charge").simplified().toUInt());
-
-    _p_peptide_match->setCharge(attributes.value("charge").simplified().toUInt());
+    _p_peptide_match->setCharge(_charge);
 
-    IdentificationDataSource* p_identification_data_source = _p_project->getIdentificationDataSourceStore().getInstance(attributes.value("sample_file").simplified()).get();
-    _p_peptide_match->setIdentificationDataSource( p_identification_data_source);
-    if (p_identification_data_source->getMsRunSp().get() == nullptr) {
-        p_identification_data_source->setMsRunSp(ms_run_id);
-    }
-    if (p_identification_data_source->getMsRunSp().get() != ms_run_id.get()) {
-        throw pappso::PappsoException(QObject::tr("p_identification_data_source->getMsRunSp().get() != ms_run_id.get()"));
-    }
+    _p_peptide_match->setIdentificationDataSource( _p_identification_data_source);
     _p_peptide_match->setChecked(false);
     if (attributes.value("validate").simplified().toLower() == "true") {
         _p_peptide_match->setChecked(true);
     }
     _p_protein_match->addPeptideMatch(_p_peptide_match);
-    qDebug() << "startElement_peptide end" ;
-    return true;
+
+
+
+    // missing informations
+    //peptide.set_hypercorr(Float.valueOf(attrs.getValue("hyperscore")));
+    //peptide.set_pre(attrs.getValue("pre"));
+    //peptide.set_post(attrs.getValue("post"));
+    //qDebug() << "startElement_domain end" ;
+    return is_ok;
 }
 
 bool XtandemSaxHandler::startElement_aa(QXmlAttributes attributes) {
 //<aa type="M" at="624" modified="15.99491" />
+    bool is_ok = true;
     qDebug() << "startElement_aa ";
-    pappso::AaModificationP modif = _map_massstr_aamod[attributes.value("modvalue").simplified()];
-    unsigned int position = attributes.value("posi").simplified().toUInt();
-    _current_peptide_sp.get()->addAaModification(modif, position-1);
+    pappso::AaModificationP modif = getAaModificationP(attributes.value("modified").simplified().toDouble());
+    unsigned int position_in_prot = attributes.value("at").simplified().toUInt()-1;
+    _current_peptide_sp.get()->addAaModification(modif, position_in_prot-_p_peptide_match->getStart());
     qDebug() << "startElement_aa end" ;
-    return true;
+    return is_ok;
 }
 
 bool XtandemSaxHandler::endElement_note() {
 //<note label="description">GRMZM2G083841_P01 P04711 Phosphoenolpyruvate carboxylase 1 (PEPCase 1)(PEPC 1)(EC //4.1.1.31) seq=translation; coord=9:61296279..61301686:1; parent_transcript=GRMZM2G083841_T01;
     ////parent_gene=GRMZM2G083841</note>
+    bool is_ok = true;
     if (_is_protein_description) {
         _p_protein_match->getProteinXtpSp().get()->setDescription(_current_text.section(" ",1));
     }
-    return true;
+    return is_ok;
 }
 
 

src/input/xtandemsaxhandler.h

@@ -43,7 +43,8 @@
 class XtandemSaxHandler: public QXmlDefaultHandler
 {
 public:
-    XtandemSaxHandler(Project * p_project, IdentificationGroup * p_identification_group);
+    XtandemSaxHandler(Project * p_project, IdentificationGroup * p_identification_group, 
+    IdentificationDataSource * p_identification_data_source);
     ~XtandemSaxHandler();
 
     bool startElement(const QString & namespaceURI, const QString & localName,
@@ -65,15 +66,14 @@ public:
 
 
 private:
-  bool startElement_group(QXmlAttributes attrs);
-    bool startElement_peptide(QXmlAttributes attributes);
+    bool startElement_group(QXmlAttributes attrs);
     bool startElement_protein(QXmlAttributes attributes);
     bool startElement_note(QXmlAttributes attributes);
     bool startElement_file(QXmlAttributes attributes);
     bool startElement_aa(QXmlAttributes attributes);
     bool startElement_domain(QXmlAttributes attributes);
     bool endElement_note();
-    
+
     pappso::AaModificationP getAaModificationP(pappso::mz mass) const;
 
 private:
@@ -83,14 +83,16 @@ private:
 
     Project * _p_project;
     IdentificationGroup * _p_identification_group;
-    
+    IdentificationDataSource * _p_identification_data_source;
+    MsRunSp _sp_msrun;
+
     ProteinMatch * _p_protein_match;
     PeptideMatch * _p_peptide_match;
     ProteinXtp _current_protein;
     PeptideXtpSp _current_peptide_sp;
-    
+
     QMap<QString, pappso::AaModificationP> _map_massstr_aamod;
-    
+
     QString _current_group_label;
     QString _current_group_type;
     unsigned int _scan;