From 53a96c0a25d3172fd3bbb8933484584617d76a50 Mon Sep 17 00:00:00 2001
From: Olivier Langella <olivier.langella@u-psud.fr>
Date: Tue, 19 Jun 2018 13:58:39 +0200
Subject: [PATCH] WIP: parsing pep xml files
---
src/CMakeLists.txt | 2 +
.../identificationpepxmlfile.cpp | 157 ++-
src/core/peptideevidence.cpp | 385 +++---
src/core/peptideevidence.h | 10 +
src/input/pepxmlsaxhandler.cpp | 521 ++++----
src/input/pepxmlsaxhandler.h | 70 +-
src/input/xtandemsaxhandler.cpp | 1117 ++++++++++-------
src/utils/identificationdatasourcestore.cpp | 8 +-
src/utils/types.h | 152 ++-
9 files changed, 1403 insertions(+), 1019 deletions(-)
diff --git a/src/CMakeLists.txt b/src/CMakeLists.txt
index a11e04512..840bbd57b 100644
--- a/src/CMakeLists.txt
+++ b/src/CMakeLists.txt
@@ -92,6 +92,7 @@ SET(CPP_FILES
core/identificationgroup.cpp
core/identification_sources/identificationdatasource.cpp
core/identification_sources/identificationmascotdatfile.cpp
+ core/identification_sources/identificationpepxmlfile.cpp
core/identification_sources/identificationpwizfile.cpp
core/identification_sources/identificationxtandemfile.cpp
core/labeling/label.cpp
@@ -122,6 +123,7 @@ SET(CPP_FILES
input/mascot/mimeparser.cpp
input/condorqxmlsaxhandler.cpp
input/identificationpwizreader.cpp
+ input/pepxmlsaxhandler.cpp
input/xpipsaxhandler.cpp
input/xtandemparamsaxhandler.cpp
input/xtandemsaxhandler.cpp
diff --git a/src/core/identification_sources/identificationpepxmlfile.cpp b/src/core/identification_sources/identificationpepxmlfile.cpp
index cbf39e195..464a691b8 100644
--- a/src/core/identification_sources/identificationpepxmlfile.cpp
+++ b/src/core/identification_sources/identificationpepxmlfile.cpp
@@ -6,92 +6,137 @@
*/
/*******************************************************************************
-* Copyright (c) 2018 Olivier Langella <olivier.langella@u-psud.fr>.
-*
-* This file is part of XTPcpp.
-*
-* XTPcpp is free software: you can redistribute it and/or modify
-* it under the terms of the GNU General Public License as published by
-* the Free Software Foundation, either version 3 of the License, or
-* (at your option) any later version.
-*
-* XTPcpp is distributed in the hope that it will be useful,
-* but WITHOUT ANY WARRANTY; without even the implied warranty of
-* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-* GNU General Public License for more details.
-*
-* You should have received a copy of the GNU General Public License
-* along with XTPcpp. If not, see <http://www.gnu.org/licenses/>.
-*
-******************************************************************************/
+ * Copyright (c) 2018 Olivier Langella <olivier.langella@u-psud.fr>.
+ *
+ * This file is part of XTPcpp.
+ *
+ * XTPcpp is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * XTPcpp is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with XTPcpp. If not, see <http://www.gnu.org/licenses/>.
+ *
+ ******************************************************************************/
#include "identificationpepxmlfile.h"
#include <pappsomspp/pappsoexception.h>
#include "../project.h"
-#include "../../input/mascot/mascotdatparser.h"
+#include "../../input/pepxmlsaxhandler.h"
-IdentificationPepXmlFile::IdentificationPepXmlFile(const QFileInfo & mascot_dat_file) : IdentificationDataSource(mascot_dat_file.absoluteFilePath()), _pep_xml_file(mascot_dat_file)
+IdentificationPepXmlFile::IdentificationPepXmlFile(
+ const QFileInfo &mascot_dat_file)
+ : IdentificationDataSource(mascot_dat_file.absoluteFilePath())
+ , _pep_xml_file(mascot_dat_file)
{
- _engine = IdentificationEngine::unknown;
+ _engine = IdentificationEngine::unknown;
}
-IdentificationPepXmlFile::IdentificationPepXmlFile(const IdentificationPepXmlFile& other) : IdentificationDataSource(other),_pep_xml_file (other._pep_xml_file)
+IdentificationPepXmlFile::IdentificationPepXmlFile(
+ const IdentificationPepXmlFile &other)
+ : IdentificationDataSource(other), _pep_xml_file(other._pep_xml_file)
{
- _engine = IdentificationEngine::unknown;
+ _engine = IdentificationEngine::unknown;
}
IdentificationPepXmlFile::~IdentificationPepXmlFile()
{
-
}
-bool IdentificationPepXmlFile::operator==(const IdentificationPepXmlFile& other) const
+bool
+IdentificationPepXmlFile::
+operator==(const IdentificationPepXmlFile &other) const
{
-
}
-pappso::SpectrumSp IdentificationPepXmlFile::getSpectrumSp(unsigned int scan_number) const {
- pappso::SpectrumSp spectrum_sp = IdentificationDataSource::getSpectrumSp(scan_number);
- return spectrum_sp;
+pappso::SpectrumSp
+IdentificationPepXmlFile::getSpectrumSp(unsigned int scan_number) const
+{
+ pappso::SpectrumSp spectrum_sp =
+ IdentificationDataSource::getSpectrumSp(scan_number);
+ return spectrum_sp;
}
-void IdentificationPepXmlFile::parseTo(Project* p_project) {
- qDebug() << __FILE__ << " " << __FUNCTION__ << " " << __LINE__;
-
-
- MsRunSp msrun_sp = p_project->getMsRunStore().getInstance(QFileInfo(_pep_xml_file).baseName());
- setMsRunSp(msrun_sp);
- std::vector<IdentificationGroup *> identification_list = p_project->getIdentificationGroupList();
- IdentificationGroup * identification_group_p = nullptr;
- if (p_project->getProjectMode() == ProjectMode::combined) {
- if (identification_list.size() == 0) {
- identification_group_p = p_project->newIdentificationGroup();
+void
+IdentificationPepXmlFile::parseTo(Project *p_project)
+{
+ qDebug() << __FILE__ << " " << __FUNCTION__ << " " << __LINE__;
+
+
+ MsRunSp msrun_sp =
+ p_project->getMsRunStore().getInstance(QFileInfo(_pep_xml_file).baseName());
+ setMsRunSp(msrun_sp);
+ std::vector<IdentificationGroup *> identification_list =
+ p_project->getIdentificationGroupList();
+ IdentificationGroup *identification_group_p = nullptr;
+ if(p_project->getProjectMode() == ProjectMode::combined)
+ {
+ if(identification_list.size() == 0)
+ {
+ identification_group_p = p_project->newIdentificationGroup();
}
- else {
- identification_group_p = identification_list[0];
+ else
+ {
+ identification_group_p = identification_list[0];
}
}
- else {
- for (IdentificationGroup * identification_p_flist : identification_list) {
- if (identification_p_flist->containSample(msrun_sp.get()->getSampleName())) {
- identification_group_p = identification_p_flist;
- break;
+ else
+ {
+ for(IdentificationGroup *identification_p_flist : identification_list)
+ {
+ if(identification_p_flist->containSample(
+ msrun_sp.get()->getSampleName()))
+ {
+ identification_group_p = identification_p_flist;
+ break;
}
}
- if (identification_group_p == nullptr) {
- identification_group_p = p_project->newIdentificationGroup();
+ if(identification_group_p == nullptr)
+ {
+ identification_group_p = p_project->newIdentificationGroup();
}
}
- identification_group_p->addIdentificationDataSourceP(this);
- MascotDatParser mascot_parser(p_project, identification_group_p, this);
+ identification_group_p->addIdentificationDataSourceP(this);
+
+ PepXmlSaxHandler *parser =
+ new PepXmlSaxHandler(p_project, identification_group_p, this);
+
+ QXmlSimpleReader simplereader;
+ simplereader.setContentHandler(parser);
+ simplereader.setErrorHandler(parser);
+
+ QFile qfile(_pep_xml_file.absoluteFilePath());
+ QXmlInputSource xmlInputSource(&qfile);
+
+ if(simplereader.parse(xmlInputSource))
+ {
+
+ qfile.close();
+ }
+ else
+ {
+ qDebug() << parser->errorString();
+ // throw PappsoException(
+ // QObject::tr("error reading tandem XML result file :\n").append(
+ // parser->errorString()));
+
+ qfile.close();
+
+ throw pappso::PappsoException(
+ QObject::tr("Error reading %1 pep xml file :\n %2")
+ .arg(_pep_xml_file.absoluteFilePath())
+ .arg(parser->errorString()));
+ }
- QFile qfile(_pep_xml_file.absoluteFilePath());
- mascot_parser.parse(&qfile);
-
- qfile.close();
- qDebug() << __FILE__ << " " << __FUNCTION__ << " " << __LINE__;
+ qDebug() << __FILE__ << " " << __FUNCTION__ << " " << __LINE__;
}
diff --git a/src/core/peptideevidence.cpp b/src/core/peptideevidence.cpp
index ee20bb878..5cfd69cf4 100644
--- a/src/core/peptideevidence.cpp
+++ b/src/core/peptideevidence.cpp
@@ -2,210 +2,315 @@
* \file utils/peptideevidence.cpp
* \date 18/11/2017
* \author Olivier Langella
- * \brief peptide evidence : a peptide sequence + spectrum + identification engine evaluation (psm)
+ * \brief peptide evidence : a peptide sequence + spectrum + identification
+ * engine evaluation (psm)
*/
/*******************************************************************************
-* Copyright (c) 2017 Olivier Langella <Olivier.Langella@u-psud.fr>.
-*
-* This file is part of XTPcpp.
-*
-* XTPcpp is free software: you can redistribute it and/or modify
-* it under the terms of the GNU General Public License as published by
-* the Free Software Foundation, either version 3 of the License, or
-* (at your option) any later version.
-*
-* XTPcpp is distributed in the hope that it will be useful,
-* but WITHOUT ANY WARRANTY; without even the implied warranty of
-* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-* GNU General Public License for more details.
-*
-* You should have received a copy of the GNU General Public License
-* along with XTPcpp. If not, see <http://www.gnu.org/licenses/>.
-*
-* Contributors:
-* Olivier Langella <Olivier.Langella@u-psud.fr> - initial API and implementation
-******************************************************************************/
+ * Copyright (c) 2017 Olivier Langella <Olivier.Langella@u-psud.fr>.
+ *
+ * This file is part of XTPcpp.
+ *
+ * XTPcpp is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * XTPcpp is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with XTPcpp. If not, see <http://www.gnu.org/licenses/>.
+ *
+ * Contributors:
+ * Olivier Langella <Olivier.Langella@u-psud.fr> - initial API and
+ *implementation
+ ******************************************************************************/
#include "peptideevidence.h"
#include <pappsomspp/pappsoexception.h>
std::hash<std::string> PeptideEvidence::_hash_fn;
-PeptideEvidence::PeptideEvidence(MsRun * msrunid_sp, unsigned int scan) {
- _msrunid_sp = msrunid_sp;
- _scan = scan;
+PeptideEvidence::PeptideEvidence(MsRun *msrunid_sp, unsigned int scan)
+{
+ _msrunid_sp = msrunid_sp;
+ _scan = scan;
- _hash_sample_scan = PeptideEvidence::_hash_fn (QString("%1 %2").arg(msrunid_sp->getXmlId()).arg(_scan).toStdString());
+ _hash_sample_scan = PeptideEvidence::_hash_fn(
+ QString("%1 %2").arg(msrunid_sp->getXmlId()).arg(_scan).toStdString());
+ _identification_engine = IdentificationEngine::unknown;
}
-PeptideEvidence::PeptideEvidence(const PeptideEvidence & other): PeptideEvidence(other._msrunid_sp, other._scan) {
- _hash_sample_scan = other._hash_sample_scan;
- _sp_grp_peptide = other._sp_grp_peptide;
- _peptide_sp = other._peptide_sp;
- _rt = other._rt;
- _evalue = other._evalue;
- _exp_mass = other._exp_mass;
- _charge= other._charge;
- _p_identification_source = other._p_identification_source;
- _params = other._params;
- _checked = other._checked;
- _proxy_valid = other._proxy_valid;
-
+PeptideEvidence::PeptideEvidence(const PeptideEvidence &other)
+ : PeptideEvidence(other._msrunid_sp, other._scan)
+{
+ _hash_sample_scan = other._hash_sample_scan;
+ _sp_grp_peptide = other._sp_grp_peptide;
+ _peptide_sp = other._peptide_sp;
+ _rt = other._rt;
+ _evalue = other._evalue;
+ _exp_mass = other._exp_mass;
+ _charge = other._charge;
+ _p_identification_source = other._p_identification_source;
+ _params = other._params;
+ _checked = other._checked;
+ _proxy_valid = other._proxy_valid;
+ _identification_engine = other._identification_engine;
}
-pappso::mz PeptideEvidence::getTheoreticalMz() const {
- return (getPeptideXtpSp().get()->getMz(getCharge()));
+pappso::mz
+PeptideEvidence::getTheoreticalMz() const
+{
+ return (getPeptideXtpSp().get()->getMz(getCharge()));
}
-PeptideEvidenceSp PeptideEvidence::makePeptideEvidenceSp() const {
- return std::make_shared<PeptideEvidence>(*this);
+PeptideEvidenceSp
+PeptideEvidence::makePeptideEvidenceSp() const
+{
+ return std::make_shared<PeptideEvidence>(*this);
}
-void PeptideEvidence::updateAutomaticFilters(const AutomaticFilterParameters & automatic_filter_parameters) {
- _proxy_valid = false;
+void
+PeptideEvidence::updateAutomaticFilters(
+ const AutomaticFilterParameters &automatic_filter_parameters)
+{
+ _proxy_valid = false;
- _proxy_valid = this->_p_identification_source->isValid(this, automatic_filter_parameters);
+ _proxy_valid =
+ this->_p_identification_source->isValid(this, automatic_filter_parameters);
+}
+void
+PeptideEvidence::setRetentionTime(pappso::pappso_double rt)
+{
+ _rt = rt;
}
-void PeptideEvidence::setRetentionTime(pappso::pappso_double rt) {
- _rt = rt;
+void
+PeptideEvidence::setEvalue(pappso::pappso_double evalue)
+{
+ _evalue = evalue;
}
-void PeptideEvidence::setEvalue(pappso::pappso_double evalue) {
- _evalue = evalue;
+
+
+void
+PeptideEvidence::setIdentificationEngine(
+ IdentificationEngine identification_engine)
+{
+ _identification_engine = identification_engine;
}
/** \brief set specific parameter value
*/
-void PeptideEvidence::setParam(PeptideEvidenceParam param, const QVariant& value) {
- _params.insert(std::pair<PeptideEvidenceParam, QVariant>(param, value));
-}
-const QVariant PeptideEvidence::getParam(PeptideEvidenceParam param) const {
- try {
- return _params.at(param);
+void
+PeptideEvidence::setParam(PeptideEvidenceParam param, const QVariant &value)
+{
+ _params.insert(std::pair<PeptideEvidenceParam, QVariant>(param, value));
+}
+const QVariant
+PeptideEvidence::getParam(PeptideEvidenceParam param) const
+{
+ try
+ {
+ return _params.at(param);
}
- catch (std::out_of_range) {
- return QVariant();
+ catch(std::out_of_range)
+ {
+ return QVariant();
}
}
-const std::map<PeptideEvidenceParam, QVariant> & PeptideEvidence::getParamList() const {
- return _params;
+const std::map<PeptideEvidenceParam, QVariant> &
+PeptideEvidence::getParamList() const
+{
+ return _params;
}
-std::size_t PeptideEvidence::getHashPeptideMassSample() const {
- return PeptideEvidence::_hash_fn (QString("%1 %2").arg(_peptide_sp.get()->toAbsoluteString()).arg(_msrunid_sp->getXmlId()).toStdString());
+std::size_t
+PeptideEvidence::getHashPeptideMassSample() const
+{
+ return PeptideEvidence::_hash_fn(QString("%1 %2")
+ .arg(_peptide_sp.get()->toAbsoluteString())
+ .arg(_msrunid_sp->getXmlId())
+ .toStdString());
}
-std::size_t PeptideEvidence::getHashSampleScan() const {
- return _hash_sample_scan;
-}
-pappso::pappso_double PeptideEvidence::getEvalue() const {
- return _evalue;
-}
-pappso::pappso_double PeptideEvidence::getExperimentalMass() const {
- return _exp_mass;
-}
-pappso::pappso_double PeptideEvidence::getExperimentalMhplus() const {
- return _exp_mass + pappso::MHPLUS;
+std::size_t
+PeptideEvidence::getHashSampleScan() const
+{
+ return _hash_sample_scan;
+}
+pappso::pappso_double
+PeptideEvidence::getEvalue() const
+{
+ return _evalue;
+}
+pappso::pappso_double
+PeptideEvidence::getExperimentalMass() const
+{
+ return _exp_mass;
+}
+pappso::pappso_double
+PeptideEvidence::getExperimentalMhplus() const
+{
+ return _exp_mass + pappso::MHPLUS;
}
-pappso::pappso_double PeptideEvidence::getExperimentalMz() const {
- pappso::mz mz = _exp_mass;
- for (unsigned int i=0; i < _charge; i++) {
- mz+=pappso::MHPLUS;
+pappso::pappso_double
+PeptideEvidence::getExperimentalMz() const
+{
+ pappso::mz mz = _exp_mass;
+ for(unsigned int i = 0; i < _charge; i++)
+ {
+ mz += pappso::MHPLUS;
}
- mz = mz/_charge;
- return mz;
-}
-void PeptideEvidence::setExperimentalMass(pappso::pappso_double exp_mass) {
- _exp_mass =exp_mass;
-}
-pappso::mz PeptideEvidence::getDeltaMass() const {
- return ((_exp_mass+pappso::MHPLUS) - _peptide_sp.get()->getMz(1));
-}
-pappso::mz PeptideEvidence::getPpmDeltaMass() const {
- //return (_peptide_sp.get()->getMz(1) - (_exp_mass+pappso::MHPLUS));
- pappso::pappso_double diff = getDeltaMass();
- while (diff > 0.5) {
- diff = diff - pappso::DIFFC12C13;
+ mz = mz / _charge;
+ return mz;
+}
+void
+PeptideEvidence::setExperimentalMass(pappso::pappso_double exp_mass)
+{
+ _exp_mass = exp_mass;
+}
+pappso::mz
+PeptideEvidence::getDeltaMass() const
+{
+ return ((_exp_mass + pappso::MHPLUS) - _peptide_sp.get()->getMz(1));
+}
+pappso::mz
+PeptideEvidence::getPpmDeltaMass() const
+{
+ // return (_peptide_sp.get()->getMz(1) - (_exp_mass+pappso::MHPLUS));
+ pappso::pappso_double diff = getDeltaMass();
+ while(diff > 0.5)
+ {
+ diff = diff - pappso::DIFFC12C13;
}
- diff = (diff / getPeptideXtpSp().get()->getMz(1)) * pappso::ONEMILLION;
- return diff;
+ diff = (diff / getPeptideXtpSp().get()->getMz(1)) * pappso::ONEMILLION;
+ return diff;
}
-void PeptideEvidence::setCharge(unsigned int charge) {
- _charge =charge;
+void
+PeptideEvidence::setCharge(unsigned int charge)
+{
+ _charge = charge;
}
-void PeptideEvidence::setPeptideXtpSp (PeptideXtpSp peptide) {
- _peptide_sp = peptide;
+void
+PeptideEvidence::setPeptideXtpSp(PeptideXtpSp peptide)
+{
+ _peptide_sp = peptide;
}
-void PeptideEvidence::setChecked(bool arg1) {
- _checked = arg1;
+void
+PeptideEvidence::setChecked(bool arg1)
+{
+ _checked = arg1;
}
-ValidationState PeptideEvidence::getValidationState() const {
- if (isGrouped()) {
- return ValidationState::grouped;
- } else if (isValidAndChecked()) {
- return ValidationState::validAndChecked;
- } else if (isValid()) {
- return ValidationState::valid;
+ValidationState
+PeptideEvidence::getValidationState() const
+{
+ if(isGrouped())
+ {
+ return ValidationState::grouped;
+ }
+ else if(isValidAndChecked())
+ {
+ return ValidationState::validAndChecked;
}
- return ValidationState::notValid;
+ else if(isValid())
+ {
+ return ValidationState::valid;
+ }
+ return ValidationState::notValid;
}
-bool PeptideEvidence::isValid() const {
- return _proxy_valid;
+bool
+PeptideEvidence::isValid() const
+{
+ return _proxy_valid;
}
-bool PeptideEvidence::isChecked() const {
- return _checked;
+bool
+PeptideEvidence::isChecked() const
+{
+ return _checked;
}
-bool PeptideEvidence::isValidAndChecked() const {
- return _proxy_valid && _checked;
+bool
+PeptideEvidence::isValidAndChecked() const
+{
+ return _proxy_valid && _checked;
}
-bool PeptideEvidence::isGrouped() const {
- if (_sp_grp_peptide.get() == nullptr) {
- return false;
+bool
+PeptideEvidence::isGrouped() const
+{
+ if(_sp_grp_peptide.get() == nullptr)
+ {
+ return false;
}
- if (_sp_grp_peptide.get()->getGroupNumber() ==0) {
- return false;
+ if(_sp_grp_peptide.get()->getGroupNumber() == 0)
+ {
+ return false;
}
- return true;
+ return true;
}
-void PeptideEvidence::setIdentificationDataSource(IdentificationDataSource* identification_source) {
- _p_identification_source = identification_source;
+void
+PeptideEvidence::setIdentificationDataSource(
+ IdentificationDataSource *identification_source)
+{
+ _p_identification_source = identification_source;
+
+ if(_identification_engine == IdentificationEngine::unknown)
+ {
+ _identification_engine = identification_source->getIdentificationEngine();
+ }
}
-IdentificationDataSource* PeptideEvidence::getIdentificationDataSource () const {
- return _p_identification_source;
+IdentificationDataSource *
+PeptideEvidence::getIdentificationDataSource() const
+{
+ return _p_identification_source;
}
-unsigned int PeptideEvidence::getScan() const {
- return _scan;
+unsigned int
+PeptideEvidence::getScan() const
+{
+ return _scan;
}
-pappso::pappso_double PeptideEvidence::getRetentionTime() const {
- return _rt;
+pappso::pappso_double
+PeptideEvidence::getRetentionTime() const
+{
+ return _rt;
}
-unsigned int PeptideEvidence::getCharge() const {
- return _charge;
+unsigned int
+PeptideEvidence::getCharge() const
+{
+ return _charge;
}
-const PeptideXtpSp & PeptideEvidence::getPeptideXtpSp() const {
- //if (_sp_grp_peptide.get() == nullptr) {
- // throw pappso::PappsoException(QObject::tr("Peptide is null in %1 %2").arg(_msrunid_sp->getXmlId()).arg(this->getScan()));
- //}
- return _peptide_sp;
+const PeptideXtpSp &
+PeptideEvidence::getPeptideXtpSp() const
+{
+ // if (_sp_grp_peptide.get() == nullptr) {
+ // throw pappso::PappsoException(QObject::tr("Peptide is null in %1
+ // %2").arg(_msrunid_sp->getXmlId()).arg(this->getScan()));
+ //}
+ return _peptide_sp;
}
-const MsRun * PeptideEvidence::getMsRunP() const {
- return _msrunid_sp;
+const MsRun *
+PeptideEvidence::getMsRunP() const
+{
+ return _msrunid_sp;
}
-void PeptideEvidence::setGrpPeptideSp(const pappso::GrpPeptideSp & sp_grp_peptide) {
- _sp_grp_peptide =sp_grp_peptide;
+void
+PeptideEvidence::setGrpPeptideSp(const pappso::GrpPeptideSp &sp_grp_peptide)
+{
+ _sp_grp_peptide = sp_grp_peptide;
}
-const pappso::GrpPeptideSp & PeptideEvidence::getGrpPeptideSp() const {
- return _sp_grp_peptide;
+const pappso::GrpPeptideSp &
+PeptideEvidence::getGrpPeptideSp() const
+{
+ return _sp_grp_peptide;
}
-
diff --git a/src/core/peptideevidence.h b/src/core/peptideevidence.h
index 199310e33..628aaf09e 100644
--- a/src/core/peptideevidence.h
+++ b/src/core/peptideevidence.h
@@ -93,6 +93,12 @@ public :
void setCharge(unsigned int charge);
void setPeptideXtpSp (PeptideXtpSp peptide);
void setIdentificationDataSource(IdentificationDataSource* identification_source);
+
+
+ /** @brief sets the identification engine
+ * by default, this is the identification engine of the datasource
+ */
+ void setIdentificationEngine(IdentificationEngine identification_engine);
void setChecked(bool arg1);
bool isChecked() const;
bool isValid() const;
@@ -157,5 +163,9 @@ private :
/** @brief automatic filter result (false by default)
*/
bool _proxy_valid = false;
+
+ /** @brief the search/identification engine that found this evidence
+ */
+ IdentificationEngine _identification_engine;
};
#endif // PEPTIDEEVIDENCE_H
diff --git a/src/input/pepxmlsaxhandler.cpp b/src/input/pepxmlsaxhandler.cpp
index 0879a049f..a031df10c 100644
--- a/src/input/pepxmlsaxhandler.cpp
+++ b/src/input/pepxmlsaxhandler.cpp
@@ -34,27 +34,31 @@
#include "../core/peptideevidence.h"
#include "../utils/peptidestore.h"
#include "../utils/proteinstore.h"
+#include "../utils/utils.h"
-PepXmlSaxHandler::PepXmlSaxHandler(WorkMonitorInterface *p_monitor,
- Project *p_project)
+
+PepXmlSaxHandler::PepXmlSaxHandler(
+ Project *p_project, IdentificationGroup *p_identification_group,
+ IdentificationDataSource *p_identification_data_source)
: _p_project(p_project)
{
qDebug() << __FILE__ << " " << __FUNCTION__ << " " << __LINE__;
- _p_monitor = p_monitor;
- qDebug() << __FILE__ << " " << __FUNCTION__ << " " << __LINE__;
+ _p_identification_group = p_identification_group;
+
+ _p_identification_data_source = p_identification_data_source;
+ _sp_msrun = p_identification_data_source->getMsRunSp();
}
PepXmlSaxHandler::~PepXmlSaxHandler()
{
}
-
bool
PepXmlSaxHandler::startElement(const QString &namespaceURI,
const QString &localName, const QString &qName,
const QXmlAttributes &attributes)
{
- qDebug() << __FILE__ << " " << __FUNCTION__ << " " << __LINE__;
+ // qDebug() << __FILE__ << " " << __FUNCTION__ << " " << __LINE__;
_tag_stack.push_back(qName);
bool is_ok = true;
@@ -63,124 +67,58 @@ PepXmlSaxHandler::startElement(const QString &namespaceURI,
// startElement_group
if(_tag_stack.size() == 1)
{
- _is_xtpcpp_xpip = true;
- if(qName != "xpip")
+ if(qName != "msms_pipeline_analysis")
{
- _is_xtpcpp_xpip = false;
throw pappso::ExceptionNotFound(
QObject::tr("ERROR this file is not a pep xml file %1")
.arg(qName));
}
}
- else if(qName == "protein_match")
- {
- if(_count_total % 100 == 0)
- {
- _p_monitor->message(QString("reading protein matches %1 on %2")
- .arg(_count_protein_matches)
- .arg(_total_protein_matches),
- _count_total);
- }
- is_ok = startElement_protein_match(attributes);
- }
- else if(qName == "peptide_match")
+ else if(qName == "msms_pipeline_analysis")
{
- is_ok = startElement_peptide_match(attributes);
+ is_ok = startElement_msms_pipeline_analysis(attributes);
}
- else if(qName == "protein")
+ else if(qName == "msms_run_summary")
{
- if(_count_total % 100 == 0)
- {
- _p_monitor->message(QString("reading proteins %1 on %2")
- .arg(_count_proteins)
- .arg(_total_proteins),
- _count_total);
- }
- is_ok = startElement_protein(attributes);
+ is_ok = startElement_msms_run_summary(attributes);
}
- else if(qName == "identification_source")
+ else if(qName == "search_database")
{
- is_ok = startElement_identification_source(attributes);
+ is_ok = startElement_search_database(attributes);
}
- else if(qName == "param")
+ else if(qName == "search_summary")
{
- is_ok = startElement_param(attributes);
+ is_ok = startElement_search_summary(attributes);
}
- else if(qName == "stat")
+ else if(qName == "spectrum_query")
{
- is_ok = startElement_stat(attributes);
+ is_ok = startElement_spectrum_query(attributes);
}
- else if(qName == "identification_group")
+ else if(qName == "search_hit")
{
- is_ok = startElement_identification_group(attributes);
+ is_ok = startElement_search_hit(attributes);
}
- else if(qName == "peptide_evidence_list")
+ else if(qName == "alternative_protein")
{
- is_ok = startElement_peptide_evidence_list(attributes);
+ is_ok = startElement_alternative_protein(attributes);
}
- else if(qName == "counts")
+
+ else if(qName == "peptideprophet_result")
{
- is_ok = startElement_counts(attributes);
+ is_ok = startElement_peptideprophet_result(attributes);
}
- else if(qName == "label_method")
+ else if(qName == "interprophet_result")
{
- is_ok = startElement_label_method(attributes);
+ is_ok = startElement_interprophet_result(attributes);
}
//<sample value="P6_08_10"/>
- else if(qName == "msrun")
- {
- is_ok = startElement_msrun(attributes);
- }
- else if(qName == "peptide")
- {
- if(_count_total % 100 == 0)
- {
- _p_monitor->message(QObject::tr("reading peptide %1 on %2")
- .arg(_count_peptides)
- .arg(_total_peptides),
- _count_total);
- }
- is_ok = startElement_peptide(attributes);
- }
- else if(qName == "peptide_evidence")
- {
- if(_count_total % 100 == 0)
- {
- _p_monitor->message(
- QObject::tr("reading peptide evidence %1 on %2")
- .arg(_count_peptide_evidences)
- .arg(_total_peptide_evidences),
- _count_total);
- }
- is_ok = startElement_peptide_evidence(attributes);
- }
- else if(qName == "modification")
- {
- is_ok = startElement_modification(attributes);
- }
- else if(qName == "mod")
- {
- is_ok = startElement_mod(attributes);
- }
- else if(qName == "filter_params")
- {
- is_ok = startElement_filter_params(attributes);
- }
- else if(qName == "description")
- {
- is_ok = startElement_description(attributes);
- }
- else if(qName == "fasta_file")
- {
- is_ok = startElement_fasta_file(attributes);
- }
- else if(qName == "contaminants")
+ else if(qName == "search_score")
{
- is_ok = startElement_contaminants(attributes);
+ is_ok = startElement_search_score(attributes);
}
- else if(qName == "decoys")
+ else if(qName == "mod_aminoacid_mass")
{
- is_ok = startElement_decoys(attributes);
+ is_ok = startElement_mod_aminoacid_mass(attributes);
}
_current_text.clear();
@@ -210,46 +148,18 @@ PepXmlSaxHandler::endElement(const QString &namespaceURI,
const QString &localName, const QString &qName)
{
- qDebug() << __FILE__ << " " << __FUNCTION__ << " " << __LINE__;
+ // qDebug() << __FILE__ << " " << __FUNCTION__ << " " << __LINE__;
bool is_ok = true;
// endElement_peptide_list
try
{
- if(qName == "protein")
- {
- is_ok = endElement_protein();
- }
- else if(qName == "peptide")
- {
- is_ok = endElement_peptide();
- }
- else if(qName == "msrun")
- {
- is_ok = endElement_msrun();
- }
- else if(qName == "sequence")
- {
- is_ok = endElement_sequence();
- }
- else if(qName == "protein_match")
- {
- is_ok = endElement_protein_match();
- }
- else if(qName == "peptide_evidence")
- {
- is_ok = endElement_peptide_evidence();
- }
- else if(qName == "peptide_evidence_list")
- {
- is_ok = endElement_peptide_evidence_list();
- }
- else if(qName == "identification_group")
+ if(qName == "search_hit")
{
- is_ok = endElement_identification_group();
+ is_ok = endElement_search_hit();
}
- else if(qName == "identification_source")
+ else if(qName == "modification_info")
{
- is_ok = endElement_identification_source();
+ is_ok = endElement_modification_info();
}
// end of detection_moulon
@@ -289,7 +199,9 @@ PepXmlSaxHandler::endElement(const QString &namespaceURI,
bool
PepXmlSaxHandler::startElement_msms_pipeline_analysis(QXmlAttributes attributes)
{
+ bool is_ok = true;
QString original_filename = attributes.value("summary_xml");
+ return is_ok;
}
// <msms_run_summary
@@ -299,17 +211,31 @@ PepXmlSaxHandler::startElement_msms_pipeline_analysis(QXmlAttributes attributes)
bool
PepXmlSaxHandler::startElement_msms_run_summary(QXmlAttributes attributes)
{
+ bool is_ok = true;
QString mz_datafile = QString("%1%2")
.arg(attributes.value("base_name"))
.arg(attributes.value("raw_data"));
+ return is_ok;
}
// <search_database
// local_path="/gorgone/pappso/abrf_2015/fasta/iPRG2015.fasta" type="AA"/>
+//<search_database
+// local_path="/gorgone/pappso/abrf_2015/fasta/iPRG2015.TargDecoy.fasta"
+// database_name="SearchDB_1" size_in_db_entries="13256" type="NA"/>
+
bool
PepXmlSaxHandler::startElement_search_database(QXmlAttributes attributes)
{
- QString fastafile = attributes.value("local_path");
+ bool is_ok = true;
+ FastaFile fasta_file(attributes.value("local_path"));
+ if(!attributes.value("database_name").isEmpty())
+ {
+ fasta_file.setXmlId(attributes.value("database_name"));
+ }
+ _p_identification_data_source->addFastaFile(
+ _p_project->getFastaFileStore().getInstance(fasta_file));
+ return is_ok;
}
// <search_summary
@@ -319,7 +245,9 @@ PepXmlSaxHandler::startElement_search_database(QXmlAttributes attributes)
bool
PepXmlSaxHandler::startElement_search_summary(QXmlAttributes attributes)
{
+ bool is_ok = true;
_current_search_engine = attributes.value("search_engine");
+ return is_ok;
}
// <spectrum_query spectrum="JD_06232014_sample1-A.00005.00005.2"
@@ -331,36 +259,67 @@ PepXmlSaxHandler::startElement_search_summary(QXmlAttributes attributes)
bool
PepXmlSaxHandler::startElement_spectrum_query(QXmlAttributes attributes)
{
+ bool is_ok = true;
unsigned int start_scan = attributes.value("start_scan").toUInt();
unsigned int end_scan = attributes.value("end_scan").toUInt();
if(start_scan != end_scan)
{
- String message = "ERROR reading pepxml file :\n" +
- "unable to read search results from '" +
- this.currentSearchEngine + "' as start " +
- currentStartScan + " and end " + currentEndScan +
- " scans are different";
- logger.error(message);
- throw new MSMSException(message);
+ throw pappso::PappsoException(
+ QObject::tr("ERROR reading pepxml file :\nunable to read search "
+ "results from '%1' as start %2 and end %3 scans are "
+ "different")
+ .arg(_current_search_engine)
+ .arg(start_scan)
+ .arg(end_scan));
}
- currentZ = new Integer(attrs.getValue("assumed_charge"));
- if(attrs.getValue("retention_time_sec") == null)
+ _current_charge = attributes.value("assumed_charge").toUInt();
+ if(attributes.value("retention_time_sec").isEmpty())
{
- String message =
- "ERROR reading pepxml file :\n" +
- "unable to read search results from '" + this.currentSearchEngine +
- "' as retention time is not given in spectrum_query elements";
- logger.warn(message);
+ QString message =
+ QObject::tr("ERROR reading pepxml file :\n"
+ "unable to read search results from '%1' as retention time "
+ "is not given in spectrum_query elements")
+ .arg(_current_search_engine);
+ qDebug() << message;
// throw new MSMSException(message);
- currentRt = (double)0;
+ _current_retention_time = 0;
}
else
{
- currentRt = new Double(attrs.getValue("retention_time_sec"));
+ _current_retention_time =
+ attributes.value("retention_time_sec").toDouble();
}
- currentPrecursorNeutralMass =
- new Double(attrs.getValue("precursor_neutral_mass")) + Utils.mhplus;
+ _current_precursor_neutral_mass =
+ attributes.value("precursor_neutral_mass").toDouble();
+ return is_ok;
+}
+
+//<alternative_protein protein="sp|P46784|RS10B_YEAST" protein_descr="40S
+// ribosomal protein S10-B OS=Saccharomyces cerevisiae (strain ATCC 204508
+// \
+//S288c) GN=RPS10B PE=1 SV=1" num_tol_term="2" peptide_prev_aa="K"
+// peptide_next_aa="N"/>
+bool
+PepXmlSaxHandler::startElement_alternative_protein(QXmlAttributes attributes)
+{
+ bool is_ok = true;
+ ProteinXtpSp sp_xtp_protein = ProteinXtp().makeProteinXtpSp();
+ sp_xtp_protein.get()->setAccession(attributes.value("protein"));
+ sp_xtp_protein.get()->setDescription(attributes.value("protein_descr"));
+ sp_xtp_protein.get()->setFastaFileP(
+ _p_identification_data_source->getFastaFileList()[0].get());
+
+ sp_xtp_protein = _p_project->getProteinStore().getInstance(sp_xtp_protein);
+
+ _p_protein_match_list.push_back(
+ _p_identification_group->getProteinMatchInstance(
+ sp_xtp_protein.get()->getAccession()));
+
+ _p_protein_match_list.back()->setProteinXtpSp(sp_xtp_protein);
+
+ _p_protein_match_list.back()->setChecked(true);
+ return is_ok;
}
// <search_hit hit_rank="5" peptide="MKDFSTK" peptide_prev_aa="K"
@@ -371,81 +330,115 @@ PepXmlSaxHandler::startElement_spectrum_query(QXmlAttributes attributes)
bool
PepXmlSaxHandler::startElement_search_hit(QXmlAttributes attributes)
{
- QString proteinName = attributes.value("protein");
+ bool is_ok = true;
+ _p_protein_match_list.clear();
+ //_current_protein.setAccession(attributes.value("protein"));
+ ProteinXtpSp sp_xtp_protein = ProteinXtp().makeProteinXtpSp();
+ sp_xtp_protein.get()->setAccession(attributes.value("protein"));
+ sp_xtp_protein.get()->setDescription(attributes.value("protein_descr"));
+ sp_xtp_protein.get()->setFastaFileP(
+ _p_identification_data_source->getFastaFileList()[0].get());
+
+ sp_xtp_protein = _p_project->getProteinStore().getInstance(sp_xtp_protein);
+
+ _p_protein_match_list.push_back(
+ _p_identification_group->getProteinMatchInstance(
+ sp_xtp_protein.get()->getAccession()));
+
+ _p_protein_match_list[0]->setProteinXtpSp(sp_xtp_protein);
+
+ _p_protein_match_list[0]->setChecked(true);
+
+ _current_peptide_sp =
+ PeptideXtp(attributes.value("peptide").simplified()).makePeptideXtpSp();
+
+
+ _p_peptide_evidence = new PeptideEvidence(_sp_msrun.get(), _scan);
+
+ _p_peptide_evidence->setRetentionTime(_current_retention_time);
+ _p_peptide_evidence->setCharge(_current_charge);
+
+ pappso::pappso_double xtandem_mhtheoretical =
+ attributes.value("mh").simplified().toDouble();
+ pappso::pappso_double xtandem_delta =
+ attributes.value("delta").simplified().toDouble();
+
+ // delta – the spectrum mh minus the calculated mh
+
+ // exp mass computed from X!Tandem mh :
- Protein protein = new Protein();
- protein.set_description(proteinName);
- if(identification.contain_protein(protein))
+ pappso::pappso_double _mass_obser =
+ attributes.value("calc_neutral_pep_mass").toDouble() +
+ attributes.value("massdiff").toDouble();
+
+
+ _p_peptide_evidence->setExperimentalMass(_mass_obser);
+
+ _p_peptide_evidence->setIdentificationDataSource(
+ _p_identification_data_source);
+
+ IdentificationEngine search_engine = IdentificationEngine::unknown;
+ if(_current_search_engine == "X! Tandem (k-score)")
{
- // new protein, new match
- currentMatch = new Match();
- currentMatch.set_protein_match(protein);
- identification.add_protein(protein, currentMatch);
+ // search_engine="X! Tandem (k-score)"
+ search_engine = IdentificationEngine::XTandem;
}
-
- else
+ else if(_current_search_engine == "OMSSA")
+ {
+ search_engine = IdentificationEngine::OMSSA;
+ }
+ else if(_current_search_engine == "Comet")
{
- // get existing match for this protein
- currentMatch = (Match)identification.get_match(protein);
+ search_engine = IdentificationEngine::Comet;
+ }
+ else if(_current_search_engine == "MS-GF+")
+ {
+ search_engine = IdentificationEngine::MSGFplus;
}
- protein = currentMatch.get_protein_match();
- protein.setDatabase(
- identification.getDatabaseSet().getInstance(this.fastaFile.getName()));
- this.currentPeptide = new PeptideProphet();
- currentPeptide.set_sample_id(
- identification.getMsRunSet().getInstance(identificationDataSource),
- identificationDataSource);
+ if(search_engine == IdentificationEngine::unknown)
+ {
+ throw pappso::PappsoException(
+ QObject::tr(
+ "ERROR reading pepxml file :\nsearch engine %1 is not known.")
+ .arg(_current_search_engine));
+ }
- _current_peptide_sp =
- PeptideXtp(attributes.value("peptide").simplified()).makePeptideXtpSp();
+ _p_peptide_evidence->setIdentificationEngine(search_engine);
+ _p_peptide_evidence->setChecked(true);
- currentPeptide.set_pre(attrs.getValue("peptide_prev_aa"));
- currentPeptide.set_post(attrs.getValue("peptide_next_aa"));
-
- currentPeptide.set_scan(this.currentEndScan.intValue());
- Double calc_neutral_pep_mass =
- new Double(attrs.getValue("calc_neutral_pep_mass")) + Utils.mhplus;
- Double massdiff = new Double(attrs.getValue("massdiff"));
-
- currentPeptide.set_mhplus_theo(calc_neutral_pep_mass);
- currentPeptide.set_deltamass(massdiff);
- currentPeptide.set_mhplus_obser(currentPrecursorNeutralMass);
- currentPeptide.set_charge(this.currentZ);
- currentPeptide.setRt(this.currentRt.floatValue());
-
- /*
- * if (Math.abs(massdiff) > 1) { String message =
- * "massdiff is too high"; logger.error(message); throw new
- * MSMSException(message); }
- */
- // valeur specifique de la séquence matche
- // peptide.set_start(Integer.parseInt(attrs.getValue("start")));
- // peptide.set_stop(Integer.parseInt(attrs.getValue("end")));
- // peptide.set_evalue(Float.valueOf(attrs.getValue("expect")));
- // peptide.set_hypercorr(Float.valueOf(attrs.getValue("hyperscore")));
+ return is_ok;
}
bool
-XtpXpipSaxHandler::endElement_search_hit()
+PepXmlSaxHandler::endElement_search_hit()
{
- if(currentPeptideProphetProbability != null)
+
+ bool is_ok = true;
+ _current_peptide_sp =
+ _p_project->getPeptideStore().getInstance(_current_peptide_sp);
+
+ _p_peptide_evidence->setPeptideXtpSp(_current_peptide_sp);
+
+ _current_peptide_match.setPeptideEvidenceSp(
+ _p_peptide_evidence->getIdentificationDataSource()
+ ->getPeptideEvidenceStore()
+ .getInstance(_p_peptide_evidence));
+ if(_p_protein_match_list.size() == 0)
{
- currentPeptide.setProphetProbability(currentPeptideProphetProbability);
+ throw pappso::PappsoException(
+ QObject::tr("ERROR "
+ "PepXmlSaxHandler::endElement_search_hit:\n_p_protein_"
+ "match_list.size() == 0"));
}
- if(currentPeptideInterProphetProbability != null)
+
+ for(auto &protein_match : _p_protein_match_list)
{
- currentPeptide.setInterProphetProbability(
- currentPeptideInterProphetProbability);
+ protein_match->addPeptideMatch(_current_peptide_match);
}
- currentPeptide.setSearchEngine(this.currentSearchEngine);
- identification.add_peptide(this.currentPeptide);
- currentMatch.add_peptide_match(currentPeptide);
-
- currentPeptideProphetProbability = null;
- currentPeptideInterProphetProbability = null;
- currentExpectedValue = null;
+ delete _p_peptide_evidence;
+ return is_ok;
}
// <peptideprophet_result probability="0.0245"
@@ -453,8 +446,11 @@ XtpXpipSaxHandler::endElement_search_hit()
bool
PepXmlSaxHandler::startElement_peptideprophet_result(QXmlAttributes attributes)
{
- this.currentPeptideProphetProbability =
- Double.parseDouble(attrs.getValue("probability"));
+ bool is_ok = true;
+ _p_peptide_evidence->setParam(
+ PeptideEvidenceParam::peptide_prophet_probability,
+ attributes.value("probability").toDouble());
+ return is_ok;
}
// <interprophet_result probability="0.00886064"
@@ -462,8 +458,11 @@ PepXmlSaxHandler::startElement_peptideprophet_result(QXmlAttributes attributes)
bool
PepXmlSaxHandler::startElement_interprophet_result(QXmlAttributes attributes)
{
- this.currentPeptideInterProphetProbability =
- Double.parseDouble(attrs.getValue("probability"));
+ bool is_ok = true;
+ _p_peptide_evidence->setParam(
+ PeptideEvidenceParam::peptide_inter_prophet_probability,
+ attributes.value("probability").toDouble());
+ return is_ok;
}
/*
@@ -475,21 +474,28 @@ PepXmlSaxHandler::startElement_interprophet_result(QXmlAttributes attributes)
bool
PepXmlSaxHandler::startElement_search_score(QXmlAttributes attributes)
{
- String name = attrs.getValue("name");
- String valueStr = attrs.getValue("value");
+ bool is_ok = true;
+ QString name = attributes.value("name");
+ QString valueStr = attributes.value("value");
if(!valueStr.isEmpty())
{
- if(name.equals("expect"))
+ if(name == "expect")
{
- currentExpectedValue = new Double(valueStr);
- currentPeptide.set_evalue(currentExpectedValue.floatValue());
+ _p_peptide_evidence->setEvalue(valueStr.simplified().toDouble());
+ }
+ if(name == "EValue")
+ {
+ _p_peptide_evidence->setEvalue(valueStr.simplified().toDouble());
}
// <search_score name="hyperscore" value="232"/>
- if(name.equals("hyperscore"))
+ if(name == "hyperscore")
{
- currentPeptide.set_hypercorr(Float.parseFloat(valueStr));
+ _p_peptide_evidence->setParam(
+ PeptideEvidenceParam::tandem_hyperscore,
+ QVariant(attributes.value("hyperscore").toDouble()));
}
}
+ return is_ok;
}
// <modification_info modified_peptide="SQRDCR"> <mod_aminoacid_mass
@@ -497,59 +503,74 @@ PepXmlSaxHandler::startElement_search_score(QXmlAttributes attributes)
bool
PepXmlSaxHandler::startElement_mod_aminoacid_mass(QXmlAttributes attributes)
{
- double massFloat = attributes.value("mass").toDouble();
- int position = attributes.value("position").toUInt();
- String aa = _current_peptide_sp.get()->getSequence().substring(position - 1, position);
- Float massDiff = massFloat - Utils.getAaMass(aa.charAt(0));
-
- this.currentPeptide.set_Modifs(aa, position - 1, massDiff);
- // modifs liste for isotopic analysis
- identification.add_modifs_to_liste(new Modifs(massFloat));
-
- pappso::AaModificationP modif = Utils::guessAaModificationPbyMonoisotopicMassDelta(attributes.value("modified").simplified().toDouble());
-
-pappso::AaModificationP modif = pappso::AaModification::getInstance(attributes.value("mass").simplified());
- unsigned int position = attributes.value("position").simplified().toUInt();
- _current_peptide_sp.get()->addAaModification(modif, position-1);
+ bool is_ok = true;
+ double mass = attributes.value("mass").toDouble();
+ unsigned int position = attributes.value("position").toUInt() - 1;
+ const pappso::Aa &aa = _current_peptide_sp.get()->getConstAa(position);
+ double mass_modif = mass - aa.getMass();
+
+ pappso::AaModificationP modif =
+ Utils::guessAaModificationPbyMonoisotopicMassDelta(mass_modif);
+
+ _current_peptide_sp.get()->addAaModification(modif, position);
+ return is_ok;
}
bool
PepXmlSaxHandler::endElement_modification_info()
{
+ bool is_ok = true;
+ return is_ok;
}
-bool PepXmlSaxHandler::error(const QXmlParseException &exception) {
- _errorStr = QObject::tr("Parse error at line %1, column %2 :\n"
- "%3").arg(exception.lineNumber()).arg(exception.columnNumber()).arg(
- exception.message());
+bool
+PepXmlSaxHandler::error(const QXmlParseException &exception)
+{
+ _errorStr = QObject::tr("Parse error at line %1, column %2 :\n"
+ "%3")
+ .arg(exception.lineNumber())
+ .arg(exception.columnNumber())
+ .arg(exception.message());
- return false;
+ return false;
}
-bool PepXmlSaxHandler::fatalError(const QXmlParseException &exception) {
- _errorStr = QObject::tr("Parse error at line %1, column %2 :\n"
- "%3").arg(exception.lineNumber()).arg(exception.columnNumber()).arg(
- exception.message());
- return false;
+bool
+PepXmlSaxHandler::fatalError(const QXmlParseException &exception)
+{
+ _errorStr = QObject::tr("Parse error at line %1, column %2 :\n"
+ "%3")
+ .arg(exception.lineNumber())
+ .arg(exception.columnNumber())
+ .arg(exception.message());
+ return false;
}
-QString PepXmlSaxHandler::errorString() const {
- return _errorStr;
+QString
+PepXmlSaxHandler::errorString() const
+{
+ return _errorStr;
}
-bool PepXmlSaxHandler::endDocument() {
- return true;
+bool
+PepXmlSaxHandler::endDocument()
+{
+ return true;
}
-bool PepXmlSaxHandler::startDocument() {
- return true;
+bool
+PepXmlSaxHandler::startDocument()
+{
+ return true;
}
-bool PepXmlSaxHandler::characters(const QString &str) {
- _current_text += str;
- return true;
+bool
+PepXmlSaxHandler::characters(const QString &str)
+{
+ _current_text += str;
+ return true;
}
diff --git a/src/input/pepxmlsaxhandler.h b/src/input/pepxmlsaxhandler.h
index 2892c9859..ed38bc289 100644
--- a/src/input/pepxmlsaxhandler.h
+++ b/src/input/pepxmlsaxhandler.h
@@ -7,24 +7,24 @@
/*******************************************************************************
-* Copyright (c) 2018 Olivier Langella <Olivier.Langella@u-psud.fr>.
-*
-* This file is part of XTPcpp.
-*
-* XTPcpp is free software: you can redistribute it and/or modify
-* it under the terms of the GNU General Public License as published by
-* the Free Software Foundation, either version 3 of the License, or
-* (at your option) any later version.
-*
-* XTPcpp is distributed in the hope that it will be useful,
-* but WITHOUT ANY WARRANTY; without even the implied warranty of
-* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-* GNU General Public License for more details.
-*
-* You should have received a copy of the GNU General Public License
-* along with XTPcpp. If not, see <http://www.gnu.org/licenses/>.
-*
-******************************************************************************/
+ * Copyright (c) 2018 Olivier Langella <Olivier.Langella@u-psud.fr>.
+ *
+ * This file is part of XTPcpp.
+ *
+ * XTPcpp is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * XTPcpp is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with XTPcpp. If not, see <http://www.gnu.org/licenses/>.
+ *
+ ******************************************************************************/
#ifndef PEPXMLSAXHANDLER_H
@@ -42,8 +42,8 @@ class PepXmlSaxHandler : public QXmlDefaultHandler
{
public:
PepXmlSaxHandler(Project *p_project,
- IdentificationGroup *p_identification_group,
- IdentificationDataSource *p_identification_data_source);
+ IdentificationGroup *p_identification_group,
+ IdentificationDataSource *p_identification_data_source);
~PepXmlSaxHandler();
bool startElement(const QString &namespaceURI, const QString &localName,
@@ -66,13 +66,18 @@ class PepXmlSaxHandler : public QXmlDefaultHandler
private:
bool startElement_msms_pipeline_analysis(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_domain();
- bool endElement_note();
+ bool startElement_msms_run_summary(QXmlAttributes attributes);
+ bool startElement_search_database(QXmlAttributes attributes);
+ bool startElement_search_summary(QXmlAttributes attributes);
+ bool startElement_spectrum_query(QXmlAttributes attributes);
+ bool startElement_search_hit(QXmlAttributes attributes);
+ bool startElement_alternative_protein(QXmlAttributes attributes);
+ bool startElement_peptideprophet_result(QXmlAttributes attributes);
+ bool startElement_interprophet_result(QXmlAttributes attributes);
+ bool startElement_search_score(QXmlAttributes attributes);
+ bool startElement_mod_aminoacid_mass(QXmlAttributes attributes);
+ bool endElement_search_hit();
+ bool endElement_modification_info();
private:
std::vector<QString> _tag_stack;
@@ -84,22 +89,21 @@ class PepXmlSaxHandler : public QXmlDefaultHandler
IdentificationDataSource *_p_identification_data_source;
MsRunSp _sp_msrun;
- ProteinMatch *_p_protein_match;
+ std::vector<ProteinMatch *> _p_protein_match_list;
PeptideEvidence *_p_peptide_evidence;
PeptideMatch _current_peptide_match;
- ProteinXtp _current_protein;
PeptideXtpSp _current_peptide_sp;
QMap<QString, pappso::AaModificationP> _map_massstr_aamod;
- QString _current_group_label;
+ QString _current_search_engine;
QString _current_group_type;
QString _current_note_label;
QString _current_note_type;
unsigned int _scan;
- pappso::pappso_double _mhplus_obser;
- unsigned int _charge;
- pappso::pappso_double _retention_time;
+ unsigned int _current_charge;
+ pappso::pappso_double _current_retention_time;
+ pappso::pappso_double _current_precursor_neutral_mass;
bool _is_protein_description = false;
};
diff --git a/src/input/xtandemsaxhandler.cpp b/src/input/xtandemsaxhandler.cpp
index cd3bc25c0..a7fd35aea 100644
--- a/src/input/xtandemsaxhandler.cpp
+++ b/src/input/xtandemsaxhandler.cpp
@@ -7,26 +7,27 @@
/*******************************************************************************
-* Copyright (c) 2017 Olivier Langella <Olivier.Langella@u-psud.fr>.
-*
-* This file is part of XTPcpp.
-*
-* XTPcpp is free software: you can redistribute it and/or modify
-* it under the terms of the GNU General Public License as published by
-* the Free Software Foundation, either version 3 of the License, or
-* (at your option) any later version.
-*
-* XTPcpp is distributed in the hope that it will be useful,
-* but WITHOUT ANY WARRANTY; without even the implied warranty of
-* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-* GNU General Public License for more details.
-*
-* You should have received a copy of the GNU General Public License
-* along with XTPcpp. If not, see <http://www.gnu.org/licenses/>.
-*
-* Contributors:
-* Olivier Langella <Olivier.Langella@u-psud.fr> - initial API and implementation
-******************************************************************************/
+ * Copyright (c) 2017 Olivier Langella <Olivier.Langella@u-psud.fr>.
+ *
+ * This file is part of XTPcpp.
+ *
+ * XTPcpp is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * XTPcpp is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with XTPcpp. If not, see <http://www.gnu.org/licenses/>.
+ *
+ * Contributors:
+ * Olivier Langella <Olivier.Langella@u-psud.fr> - initial API and
+ *implementation
+ ******************************************************************************/
#include "xtandemsaxhandler.h"
@@ -38,555 +39,721 @@
#include "../utils/utils.h"
-XtandemSaxHandler::XtandemSaxHandler(Project * p_project, IdentificationGroup * p_identification_group,
- IdentificationDataSource * p_identification_data_source):_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_group = p_identification_group;
- _p_identification_data_source =p_identification_data_source;
- _sp_msrun = p_identification_data_source->getMsRunSp();
+ _p_identification_data_source = p_identification_data_source;
+ _sp_msrun = p_identification_data_source->getMsRunSp();
}
XtandemSaxHandler::~XtandemSaxHandler()
{
-
}
-bool XtandemSaxHandler::startElement(const QString & namespaceURI, const QString & localName,
- const QString & qName, const QXmlAttributes & attributes) {
- // qDebug() << namespaceURI << " " << localName << " " << qName ;
- _tag_stack.push_back(qName);
- bool is_ok = true;
-
- try {
- //startElement_group
- if (qName == "group") {
- is_ok = startElement_group(attributes);
- } else if (qName == "protein") {
- is_ok = startElement_protein(attributes);
- } else if (qName == "note") {
- is_ok = startElement_note(attributes);
+bool
+XtandemSaxHandler::startElement(const QString &namespaceURI,
+ const QString &localName, const QString &qName,
+ const QXmlAttributes &attributes)
+{
+ // qDebug() << namespaceURI << " " << localName << " " << qName ;
+ _tag_stack.push_back(qName);
+ bool is_ok = true;
+
+ try
+ {
+ // startElement_group
+ if(qName == "group")
+ {
+ is_ok = startElement_group(attributes);
}
- else if (qName == "file") {
- is_ok = startElement_file(attributes);
-
- } else if (qName == "aa") {
- is_ok = startElement_aa(attributes);
- } else if (qName == "domain") {
- is_ok = startElement_domain(attributes);
+ else if(qName == "protein")
+ {
+ is_ok = startElement_protein(attributes);
+ }
+ else if(qName == "note")
+ {
+ is_ok = startElement_note(attributes);
+ }
+ else if(qName == "file")
+ {
+ is_ok = startElement_file(attributes);
+ }
+ else if(qName == "aa")
+ {
+ is_ok = startElement_aa(attributes);
+ }
+ else if(qName == "domain")
+ {
+ is_ok = startElement_domain(attributes);
}
- _current_text.clear();
+ _current_text.clear();
}
- catch (pappso::PappsoException & exception_pappso) {
- _errorStr = QObject::tr("ERROR in XtandemSaxHandler::startElement tag %1, PAPPSO exception:\n%2").arg(qName).arg(exception_pappso.qwhat());
- return false;
+ catch(pappso::PappsoException &exception_pappso)
+ {
+ _errorStr = QObject::tr("ERROR in XtandemSaxHandler::startElement tag "
+ "%1, PAPPSO exception:\n%2")
+ .arg(qName)
+ .arg(exception_pappso.qwhat());
+ return false;
}
- catch (std::exception & exception_std) {
- _errorStr = QObject::tr("ERROR in XtandemSaxHandler::startElement tag %1, std exception:\n%2").arg(qName).arg(exception_std.what());
- return false;
+ catch(std::exception &exception_std)
+ {
+ _errorStr =
+ QObject::tr(
+ "ERROR in XtandemSaxHandler::startElement tag %1, std exception:\n%2")
+ .arg(qName)
+ .arg(exception_std.what());
+ return false;
}
- return is_ok;
+ return is_ok;
}
-bool XtandemSaxHandler::endElement(const QString & namespaceURI, const QString & localName,
- const QString & qName) {
+bool
+XtandemSaxHandler::endElement(const QString &namespaceURI,
+ const QString &localName, const QString &qName)
+{
- bool is_ok = true;
- // endElement_peptide_list
- try {
- if (qName == "note")
+ bool is_ok = true;
+ // endElement_peptide_list
+ try
+ {
+ if(qName == "note")
{
- is_ok = endElement_note();
- } else if (qName == "domain")
+ is_ok = endElement_note();
+ }
+ else if(qName == "domain")
{
- is_ok = endElement_domain();
+ is_ok = endElement_domain();
}
- // end of detection_moulon
- // else if ((_tag_stack.size() > 1) &&
- // (_tag_stack[_tag_stack.size() - 2] == "detection_moulon"))
+ // end of detection_moulon
+ // else if ((_tag_stack.size() > 1) &&
+ // (_tag_stack[_tag_stack.size() - 2] == "detection_moulon"))
}
- catch (pappso::PappsoException & exception_pappso) {
- _errorStr = QObject::tr("ERROR in XtandemSaxHandler::endElement tag %1, PAPPSO exception:\n%2").arg(qName).arg(exception_pappso.qwhat());
- return false;
+ catch(pappso::PappsoException &exception_pappso)
+ {
+ _errorStr = QObject::tr("ERROR in XtandemSaxHandler::endElement tag %1, "
+ "PAPPSO exception:\n%2")
+ .arg(qName)
+ .arg(exception_pappso.qwhat());
+ return false;
}
- catch (std::exception & exception_std) {
- _errorStr = QObject::tr("ERROR in XtandemSaxHandler::endElement tag %1, std exception:\n%2").arg(qName).arg(exception_std.what());
- return false;
+ catch(std::exception &exception_std)
+ {
+ _errorStr =
+ QObject::tr(
+ "ERROR in XtandemSaxHandler::endElement tag %1, std exception:\n%2")
+ .arg(qName)
+ .arg(exception_std.what());
+ return false;
}
- _current_text.clear();
- _tag_stack.pop_back();
+ _current_text.clear();
+ _tag_stack.pop_back();
- return is_ok;
+ return is_ok;
}
-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");
- _current_group_type = attrs.value("type");
- if (_current_group_type == "model") {
- _scan = attrs.value("id").toUInt();
- _mhplus_obser = attrs.value("mh").toDouble();
- _charge = attrs.value("z").toUInt();
- _retention_time = attrs.value("rt").replace("PT","").replace("S","").toDouble();
+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");
+ _current_group_type = attrs.value("type");
+ if(_current_group_type == "model")
+ {
+ _scan = attrs.value("id").toUInt();
+ _mhplus_obser = attrs.value("mh").toDouble();
+ _charge = attrs.value("z").toUInt();
+ _retention_time =
+ attrs.value("rt").replace("PT", "").replace("S", "").toDouble();
}
- //label="input parameters" type="parameters"
- return is_ok;
+ // label="input parameters" type="parameters"
+ 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;
- _current_note_label = attributes.value("label");
- _current_note_type = attributes.value("type");
- _is_protein_description = false;
- if (attributes.value("label") == "description") {
- if (_tag_stack[_tag_stack.size() - 2] == "protein") {
- _is_protein_description = true;
+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;
+ _current_note_label = attributes.value("label");
+ _current_note_type = attributes.value("type");
+ _is_protein_description = false;
+ if(attributes.value("label") == "description")
+ {
+ if(_tag_stack[_tag_stack.size() - 2] == "protein")
+ {
+ _is_protein_description = true;
}
}
- return is_ok;
+ 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")));
- if (_p_protein_match == nullptr) {
- throw pappso::PappsoException("ERROR in XtandemSaxHandler::startElement_file : _p_protein_match == nullptr");
+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")));
+ if(_p_protein_match == nullptr)
+ {
+ throw pappso::PappsoException("ERROR in "
+ "XtandemSaxHandler::startElement_file "
+ ": _p_protein_match == nullptr");
}
- _p_protein_match->getProteinXtpSp().get()->setFastaFileP(_p_project->getFastaFileStore().getInstance(FastaFile(attributes.value("URL"))).get());
+ _p_protein_match->getProteinXtpSp().get()->setFastaFileP(
+ _p_project->getFastaFileStore()
+ .getInstance(FastaFile(attributes.value("URL")))
+ .get());
}
- return is_ok;
+ return is_ok;
}
-bool XtandemSaxHandler::startElement_domain(QXmlAttributes attributes) {
- //mh="1120.529471"
-//<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()) {
- //._sequence.replace(QRegExp("\\*"), "")).removeTranslationStop()
- //_p_protein_match->getProteinXtpSp().get()->setSequence(_current_text.replace(QRegExp("\\*"), ""));
- if (_p_protein_match == nullptr) {
- throw pappso::PappsoException("ERROR in XtandemSaxHandler::startElement_domain : _p_protein_match == nullptr");
+bool
+XtandemSaxHandler::startElement_domain(QXmlAttributes attributes)
+{
+ // mh="1120.529471"
+ //<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())
+ {
+ //._sequence.replace(QRegExp("\\*"), "")).removeTranslationStop()
+ //_p_protein_match->getProteinXtpSp().get()->setSequence(_current_text.replace(QRegExp("\\*"),
+ //""));
+ if(_p_protein_match == nullptr)
+ {
+ throw pappso::PappsoException("ERROR in "
+ "XtandemSaxHandler::startElement_"
+ "domain : _p_protein_match == nullptr");
}
- _p_protein_match->getProteinXtpSp().get()->setSequence(_current_text);
+ _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">
- /*
- * id
- – the identifier for t
- his particular identified dom
- ain (s
- pectrum
- #).(i
- d
- #).(dom
- ain#)
- start
- – the first residue
- of t
- he dom
- ain
- end
- – the last residue
- of t
- he dom
- ain
- expect
- – the expe
- ctation va
- lue for t
- he peptide identification
- mh
- – the calculated pe
- ptide mass + a prot
- on
- delta
- – the spectrum
- mh m
- inus
- the calculated m
- h
- hyperscore
- – T
- ande
- m’s score for t
- he identification
- peak_count
- – the num
- ber of pe
- aks that matched be
- tween the theoretical
- and t
- he test mass spectrum
- pre
- – the four re
- sidue
- s pre
- ceding t
- he dom
- ain
- post
- – the four re
- sidue
- s fol
- lowing t
- he dom
- ain
- seq
- – the seque
- nce of t
- he dom
- ain
- missed_cleavages
- – the num
- ber of pot
- ential cleavage sites in this
- peptide seque
- nce*/
-
- // valeur généric du scan
- _current_peptide_sp = PeptideXtp(attributes.value("seq").simplified()).makePeptideXtpSp();
- _p_peptide_evidence = new PeptideEvidence(_sp_msrun.get(), attributes.value("id").simplified().section(".",0,0).toUInt());
-
- _p_peptide_evidence->setRetentionTime(_retention_time);
- _p_peptide_evidence->setEvalue(attributes.value("expect").simplified().toDouble());
- //qDebug() << "XtandemSaxHandler::startElement_domain evalue " << _p_peptide_match->getEvalue() << " scan " << _p_peptide_match->getScan();
-
- pappso::pappso_double xtandem_mhtheoretical = attributes.value("mh").simplified().toDouble();
- pappso::pappso_double xtandem_delta = attributes.value("delta").simplified().toDouble();
-
- //delta – the spectrum mh minus the calculated mh
-
- //exp mass computed from X!Tandem mh :
- pappso::pappso_double exp_mass = _mhplus_obser - pappso::MHPLUS;
-
-
- _p_peptide_evidence->setExperimentalMass(exp_mass);
- _current_peptide_match.setStart(attributes.value("start").simplified().toUInt()-1);
- _p_peptide_evidence->setCharge(_charge);
-
- _p_peptide_evidence->setParam(PeptideEvidenceParam::tandem_hyperscore, QVariant( attributes.value("hyperscore").toDouble()));
-
- _p_peptide_evidence->setIdentificationDataSource( _p_identification_data_source);
- _p_peptide_evidence->setChecked(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;
+ // <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">
+ /*
+ * id
+ – the identifier for t
+ his particular identified dom
+ ain (s
+ pectrum
+ #).(i
+ d
+ #).(dom
+ ain#)
+ start
+ – the first residue
+ of t
+ he dom
+ ain
+ end
+ – the last residue
+ of t
+ he dom
+ ain
+ expect
+ – the expe
+ ctation va
+ lue for t
+ he peptide identification
+ mh
+ – the calculated pe
+ ptide mass + a prot
+ on
+ delta
+ – the spectrum
+ mh m
+ inus
+ the calculated m
+ h
+ hyperscore
+ – T
+ ande
+ m’s score for t
+ he identification
+ peak_count
+ – the num
+ ber of pe
+ aks that matched be
+ tween the theoretical
+ and t
+ he test mass spectrum
+ pre
+ – the four re
+ sidue
+ s pre
+ ceding t
+ he dom
+ ain
+ post
+ – the four re
+ sidue
+ s fol
+ lowing t
+ he dom
+ ain
+ seq
+ – the seque
+ nce of t
+ he dom
+ ain
+ missed_cleavages
+ – the num
+ ber of pot
+ ential cleavage sites in this
+ peptide seque
+ nce*/
+
+ // valeur généric du scan
+ _current_peptide_sp =
+ PeptideXtp(attributes.value("seq").simplified()).makePeptideXtpSp();
+ _p_peptide_evidence = new PeptideEvidence(
+ _sp_msrun.get(),
+ attributes.value("id").simplified().section(".", 0, 0).toUInt());
+
+ _p_peptide_evidence->setRetentionTime(_retention_time);
+ _p_peptide_evidence->setEvalue(
+ attributes.value("expect").simplified().toDouble());
+ // qDebug() << "XtandemSaxHandler::startElement_domain evalue " <<
+ // _p_peptide_match->getEvalue() << " scan " << _p_peptide_match->getScan();
+
+ pappso::pappso_double xtandem_mhtheoretical =
+ attributes.value("mh").simplified().toDouble();
+ pappso::pappso_double xtandem_delta =
+ attributes.value("delta").simplified().toDouble();
+
+ // delta – the spectrum mh minus the calculated mh
+
+ // exp mass computed from X!Tandem mh :
+ pappso::pappso_double exp_mass = _mhplus_obser - pappso::MHPLUS;
+
+
+ _p_peptide_evidence->setExperimentalMass(exp_mass);
+ _current_peptide_match.setStart(
+ attributes.value("start").simplified().toUInt() - 1);
+ _p_peptide_evidence->setCharge(_charge);
+
+ _p_peptide_evidence->setParam(
+ PeptideEvidenceParam::tandem_hyperscore,
+ QVariant(attributes.value("hyperscore").toDouble()));
+
+ _p_peptide_evidence->setIdentificationDataSource(
+ _p_identification_data_source);
+ _p_peptide_evidence->setChecked(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 = Utils::guessAaModificationPbyMonoisotopicMassDelta(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-_current_peptide_match.getStart());
- //qDebug() << "startElement_aa 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 =
+ Utils::guessAaModificationPbyMonoisotopicMassDelta(
+ 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 - _current_peptide_match.getStart());
+ // qDebug() << "startElement_aa end" ;
+ return is_ok;
}
-bool XtandemSaxHandler::endElement_domain() {
- bool is_ok = true;
- _current_peptide_sp = _p_project->getPeptideStore().getInstance(_current_peptide_sp);
-
- _p_peptide_evidence->setPeptideXtpSp(_current_peptide_sp);
-
- _current_peptide_match.setPeptideEvidenceSp(_p_peptide_evidence->getIdentificationDataSource()->getPeptideEvidenceStore().getInstance(_p_peptide_evidence));
- if (_p_protein_match == nullptr) {
- throw pappso::PappsoException("ERROR in XtandemSaxHandler::endElement_domain : _p_protein_match == nullptr");
+bool
+XtandemSaxHandler::endElement_domain()
+{
+ bool is_ok = true;
+ _current_peptide_sp =
+ _p_project->getPeptideStore().getInstance(_current_peptide_sp);
+
+ _p_peptide_evidence->setPeptideXtpSp(_current_peptide_sp);
+
+ _current_peptide_match.setPeptideEvidenceSp(
+ _p_peptide_evidence->getIdentificationDataSource()
+ ->getPeptideEvidenceStore()
+ .getInstance(_p_peptide_evidence));
+ if(_p_protein_match == nullptr)
+ {
+ throw pappso::PappsoException("ERROR in "
+ "XtandemSaxHandler::endElement_domain : "
+ "_p_protein_match == nullptr");
}
- _p_protein_match->addPeptideMatch(_current_peptide_match);
-
- delete _p_peptide_evidence;
- return is_ok;
-}
+ _p_protein_match->addPeptideMatch(_current_peptide_match);
+ delete _p_peptide_evidence;
+ 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" >
- bool is_ok = true;
- //the protein label could be truncated => we must wait for the <note label="description">sp|P11413|G6PD_HUMAN Glucose-6-phosphate 1-dehydrogenase OS=Homo sapiens GN=G6PD PE=1 SV=4</note>
- //to get the real protein
- _p_protein_match = nullptr;
- //qDebug() << "startElement_protein end" ;
- 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" >
+ bool is_ok = true;
+
+ // the protein label could be truncated => we must wait for the <note
+ // label="description">sp|P11413|G6PD_HUMAN Glucose-6-phosphate 1-dehydrogenase
+ // OS=Homo sapiens GN=G6PD PE=1 SV=4</note> to get the real protein
+ _p_protein_match = nullptr;
+ // qDebug() << "startElement_protein end" ;
+ 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));
- _current_protein.setCompleteDescription(_current_text);
- if (!_current_protein.getAccession().endsWith(":reversed") && _current_protein.getDescription().endsWith(":reversed")) {
- //to fit most cases, just check that the :reversed chars added by X!Tandem are not in the description. if so, then add it too in the accession
- _current_protein.setAccession(QString("%1%2").arg(_current_protein.getAccession()).arg(":reversed"));
+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));
+ _current_protein.setCompleteDescription(_current_text);
+ if(!_current_protein.getAccession().endsWith(":reversed") &&
+ _current_protein.getDescription().endsWith(":reversed"))
+ {
+ // to fit most cases, just check that the :reversed chars added by
+ // X!Tandem are not in the description. if so, then add it too in the
+ // accession
+ _current_protein.setAccession(QString("%1%2")
+ .arg(_current_protein.getAccession())
+ .arg(":reversed"));
}
- //for older versions < 2013.09.01.1
- if (!_current_protein.getAccession().endsWith("|reversed") && _current_protein.getDescription().endsWith("|reversed")) {
- //to fit most cases, just check that the :reversed chars added by X!Tandem are not in the description. if so, then add it too in the accession
- _current_protein.setAccession(QString("%1%2").arg(_current_protein.getAccession()).arg("|reversed"));
+ // for older versions < 2013.09.01.1
+ if(!_current_protein.getAccession().endsWith("|reversed") &&
+ _current_protein.getDescription().endsWith("|reversed"))
+ {
+ // to fit most cases, just check that the :reversed chars added by
+ // X!Tandem are not in the description. if so, then add it too in the
+ // accession
+ _current_protein.setAccession(QString("%1%2")
+ .arg(_current_protein.getAccession())
+ .arg("|reversed"));
}
- //qDebug() << "startElement_protein accession" << accession;
- _p_protein_match = _p_identification_group->getProteinMatchInstance(_current_protein.getAccession());
-
- _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));
- _p_protein_match->setChecked(true);
-
+ // qDebug() << "startElement_protein accession" << accession;
+ _p_protein_match = _p_identification_group->getProteinMatchInstance(
+ _current_protein.getAccession());
+
+ _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));
+ _p_protein_match->setChecked(true);
}
- else {
+ else
+ {
-//<group label="input parameters" type="parameters">
- //<note type="input" label="list path, default parameters">/gorgone/pappso/tmp/temp_condor_job8533994640337729751189420695540169/QExactive_analysis_FDR_nosemi.xml</note>
- if (_current_note_label == "list path, default parameters") {
- _p_identification_data_source->setIdentificationEngineParam(IdentificationEngineParam::tandem_param,_current_text);
+ //<group label="input parameters" type="parameters">
+ //<note type="input" label="list path, default
+ //parameters">/gorgone/pappso/tmp/temp_condor_job8533994640337729751189420695540169/QExactive_analysis_FDR_nosemi.xml</note>
+ if(_current_note_label == "list path, default parameters")
+ {
+ _p_identification_data_source->setIdentificationEngineParam(
+ IdentificationEngineParam::tandem_param, _current_text);
}
- /*
- <note type="input" label="list path, taxonomy information">/gorgone/pappso/tmp/temp_condor_job8533994640337729751189420695540169/database.xml</note>
- <note type="input" label="output, histogram column width">30</note>
- <note type="input" label="output, histograms">yes</note>
- <note type="input" label="output, maximum valid expectation value">0.05</note>
- <note type="input" label="output, maximum valid protein expectation value">0.05</note>
- <note type="input" label="output, one sequence copy">yes</note>
- <note type="input" label="output, parameters">yes</note>
- <note type="input" label="output, path">/gorgone/pappso/formation/TD/xml_tandem/20120906_balliau_extract_1_A02_urzb-1.xml</note>
- <note type="input" label="output, path hashing">no</note>
- <note type="input" label="output, performance">yes</note>
- <note type="input" label="output, proteins">yes</note>
- <note type="input" label="output, results">valid</note>
- <note type="input" label="output, sequences">yes</note>
- <note type="input" label="output, sort results by">spectrum</note>
- <note type="input" label="output, spectra">yes</note>
- <note type="input" label="output, xsl path">tandem-style.xsl</note>
- <note type="input" label="protein, C-terminal residue modification mass">0.0</note>
- <note type="input" label="protein, N-terminal residue modification mass">0.0</note>
- <note type="input" label="protein, cleavage C-terminal mass change">+17.00305</note>
- <note type="input" label="protein, cleavage N-terminal mass change">+1.00794</note>
- <note type="input" label="protein, cleavage semi">no</note>
- <note type="input" label="protein, cleavage site">[RK]|{P}</note>
- <note type="input" label="protein, modified residue mass file"></note>
- <note type="input" label="protein, quick acetyl">yes</note>
- <note type="input" label="protein, quick pyrolidone">yes</note>
- <note type="input" label="protein, stP bias">yes</note>
- <note type="input" label="protein, taxon">usedefined</note>
- <note type="input" label="refine">yes</note>
- <note type="input" label="refine, cleavage semi">no</note>
- <note type="input" label="refine, maximum valid expectation value">0.01</note>
- <note type="input" label="refine, modification mass">57.02146@C</note>
- <note type="input" label="refine, modification mass 1"></note>
- <note type="input" label="refine, point mutations">no</note>
- <note type="input" label="refine, potential C-terminus modifications"></note>
- <note type="input" label="refine, potential N-terminus modifications">+42.01056@[</note>
- <note type="input" label="refine, potential modification mass">15.99491@M</note>
- <note type="input" label="refine, potential modification mass 1"></note>
- <note type="input" label="refine, potential modification motif"></note>
- <note type="input" label="refine, potential modification motif 1"></note>
- <note type="input" label="refine, spectrum synthesis">yes</note>
- <note type="input" label="refine, unanticipated cleavage">no</note>
- <note type="input" label="refine, use potential modifications for full refinement">yes</note>
- <note type="input" label="residue, modification mass">57.02146@C</note>
- <note type="input" label="residue, modification mass 1"></note>
- <note type="input" label="residue, potential modification mass">15.99491@M</note>
- <note type="input" label="residue, potential modification motif"></note>
- <note type="input" label="scoring, a ions">no</note>
- <note type="input" label="scoring, b ions">yes</note>
- <note type="input" label="scoring, c ions">no</note>
- <note type="input" label="scoring, cyclic permutation">yes</note>
- <note type="input" label="scoring, include reverse">yes</note>
- <note type="input" label="scoring, maximum missed cleavage sites">1</note>
- <note type="input" label="scoring, minimum ion count">4</note>
- <note type="input" label="scoring, x ions">no</note>
- <note type="input" label="scoring, y ions">yes</note>
- <note type="input" label="scoring, z ions">no</note>
- <note type="input" label="spectrum, dynamic range">100.0</note>
- <note type="input" label="spectrum, fragment mass type">monoisotopic</note>
- <note type="input" label="spectrum, fragment monoisotopic mass error">0.02</note>
- <note type="input" label="spectrum, fragment monoisotopic mass error units">Daltons</note>
- <note type="input" label="spectrum, maximum parent charge">4</note>
- <note type="input" label="spectrum, minimum fragment mz">150.0</note>
- <note type="input" label="spectrum, minimum parent m+h">500.0</note>
- <note type="input" label="spectrum, minimum peaks">15</note>
- <note type="input" label="spectrum, neutral loss mass">18.01057</note>
- <note type="input" label="spectrum, neutral loss window">0.02</note>
- <note type="input" label="spectrum, parent monoisotopic mass error minus">10</note>
- <note type="input" label="spectrum, parent monoisotopic mass error plus">10</note>
- <note type="input" label="spectrum, parent monoisotopic mass error units">ppm</note>
- <note type="input" label="spectrum, parent monoisotopic mass isotope error">yes</note>
- */
- //<note type="input" label="spectrum, path">/gorgone/pappso/formation/TD/mzXML/20120906_balliau_extract_1_A02_urzb-1.mzXML</note>
-
- if (_current_note_label == "spectrum, path") {
- _sp_msrun.get()->setFilename(_current_text);
+ /*
+ <note type="input" label="list path, taxonomy
+ information">/gorgone/pappso/tmp/temp_condor_job8533994640337729751189420695540169/database.xml</note>
+ <note type="input" label="output, histogram column width">30</note>
+ <note type="input" label="output, histograms">yes</note>
+ <note type="input" label="output, maximum valid expectation
+ value">0.05</note> <note type="input" label="output, maximum valid protein
+ expectation value">0.05</note> <note type="input" label="output, one
+ sequence copy">yes</note> <note type="input" label="output,
+ parameters">yes</note> <note type="input" label="output,
+ path">/gorgone/pappso/formation/TD/xml_tandem/20120906_balliau_extract_1_A02_urzb-1.xml</note>
+ <note type="input" label="output, path hashing">no</note>
+ <note type="input" label="output, performance">yes</note>
+ <note type="input" label="output, proteins">yes</note>
+ <note type="input" label="output, results">valid</note>
+ <note type="input" label="output, sequences">yes</note>
+ <note type="input" label="output, sort results by">spectrum</note>
+ <note type="input" label="output, spectra">yes</note>
+ <note type="input" label="output, xsl path">tandem-style.xsl</note>
+ <note type="input" label="protein, C-terminal residue modification
+ mass">0.0</note> <note type="input" label="protein, N-terminal residue
+ modification mass">0.0</note> <note type="input" label="protein, cleavage
+ C-terminal mass change">+17.00305</note> <note type="input"
+ label="protein, cleavage N-terminal mass change">+1.00794</note> <note
+ type="input" label="protein, cleavage semi">no</note> <note type="input"
+ label="protein, cleavage site">[RK]|{P}</note> <note type="input"
+ label="protein, modified residue mass file"></note> <note type="input"
+ label="protein, quick acetyl">yes</note> <note type="input"
+ label="protein, quick pyrolidone">yes</note> <note type="input"
+ label="protein, stP bias">yes</note> <note type="input" label="protein,
+ taxon">usedefined</note> <note type="input" label="refine">yes</note>
+ <note type="input" label="refine, cleavage semi">no</note>
+ <note type="input" label="refine, maximum valid expectation
+ value">0.01</note> <note type="input" label="refine, modification
+ mass">57.02146@C</note> <note type="input" label="refine, modification
+ mass 1"></note> <note type="input" label="refine, point
+ mutations">no</note> <note type="input" label="refine, potential
+ C-terminus modifications"></note> <note type="input" label="refine,
+ potential N-terminus modifications">+42.01056@[</note> <note type="input"
+ label="refine, potential modification mass">15.99491@M</note> <note
+ type="input" label="refine, potential modification mass 1"></note> <note
+ type="input" label="refine, potential modification motif"></note> <note
+ type="input" label="refine, potential modification motif 1"></note> <note
+ type="input" label="refine, spectrum synthesis">yes</note> <note
+ type="input" label="refine, unanticipated cleavage">no</note> <note
+ type="input" label="refine, use potential modifications for full
+ refinement">yes</note> <note type="input" label="residue, modification
+ mass">57.02146@C</note> <note type="input" label="residue, modification
+ mass 1"></note> <note type="input" label="residue, potential modification
+ mass">15.99491@M</note> <note type="input" label="residue, potential
+ modification motif"></note> <note type="input" label="scoring, a
+ ions">no</note> <note type="input" label="scoring, b ions">yes</note>
+ <note type="input" label="scoring, c ions">no</note>
+ <note type="input" label="scoring, cyclic permutation">yes</note>
+ <note type="input" label="scoring, include reverse">yes</note>
+ <note type="input" label="scoring, maximum missed cleavage sites">1</note>
+ <note type="input" label="scoring, minimum ion count">4</note>
+ <note type="input" label="scoring, x ions">no</note>
+ <note type="input" label="scoring, y ions">yes</note>
+ <note type="input" label="scoring, z ions">no</note>
+ <note type="input" label="spectrum, dynamic range">100.0</note>
+ <note type="input" label="spectrum, fragment mass
+ type">monoisotopic</note> <note type="input" label="spectrum, fragment
+ monoisotopic mass error">0.02</note> <note type="input" label="spectrum,
+ fragment monoisotopic mass error units">Daltons</note> <note type="input"
+ label="spectrum, maximum parent charge">4</note> <note type="input"
+ label="spectrum, minimum fragment mz">150.0</note> <note type="input"
+ label="spectrum, minimum parent m+h">500.0</note> <note type="input"
+ label="spectrum, minimum peaks">15</note> <note type="input"
+ label="spectrum, neutral loss mass">18.01057</note> <note type="input"
+ label="spectrum, neutral loss window">0.02</note> <note type="input"
+ label="spectrum, parent monoisotopic mass error minus">10</note> <note
+ type="input" label="spectrum, parent monoisotopic mass error
+ plus">10</note> <note type="input" label="spectrum, parent monoisotopic
+ mass error units">ppm</note> <note type="input" label="spectrum, parent
+ monoisotopic mass isotope error">yes</note>
+ */
+ //<note type="input" label="spectrum,
+ //path">/gorgone/pappso/formation/TD/mzXML/20120906_balliau_extract_1_A02_urzb-1.mzXML</note>
+
+ if(_current_note_label == "spectrum, path")
+ {
+ _sp_msrun.get()->setFilename(_current_text);
}
- /*
- <note type="input" label="spectrum, sequence batch size">1000</note>
- <note type="input" label="spectrum, threads">1</note>
- <note type="input" label="spectrum, total peaks">100</note>
- <note type="input" label="spectrum, use contrast angle">no</note>
- <note type="input" label="spectrum, use neutral loss window">yes</note>
- <note type="input" label="spectrum, use noise suppression">yes</note>
- </group>
-
- */
-
-//<group label="unused input parameters" type="parameters">
-
- /*
- <note type="input" label="protein, use minimal annotations">yes</note>
- <note type="input" label="refine, modification mass 2"></note>
- <note type="input" label="refine, potential modification mass 2"></note>
- <note type="input" label="refine, potential modification motif 2"></note>
- <note type="input" label="residue, modification mass 2"></note>
- <note type="input" label="residue, potential modification mass 1"></note>
- <note type="input" label="residue, potential modification mass 2"></note>
- <note type="input" label="residue, potential modification motif 1"></note>
- <note type="input" label="residue, potential modification motif 2"></note>
- <note type="input" label="scoring, pluggable scoring">no</note>
- </group>
- */
-
-//<group label="performance parameters" type="parameters">
-
- //<note label="list path, sequence source #1">/gorgone/pappso/formation/TD/Database/Genome_Z_mays_5a.fasta</note>
- //<note label="list path, sequence source #2">/gorgone/pappso/formation/TD/Database/contaminants_standarts.fasta</note>
- if (_current_note_label.startsWith("list path, sequence source #")) {
- _p_identification_data_source->addFastaFile(_p_project->getFastaFileStore().getInstance( FastaFile(_current_text)));
+ /*
+ <note type="input" label="spectrum, sequence batch size">1000</note>
+ <note type="input" label="spectrum, threads">1</note>
+ <note type="input" label="spectrum, total peaks">100</note>
+ <note type="input" label="spectrum, use contrast angle">no</note>
+ <note type="input" label="spectrum, use neutral loss window">yes</note>
+ <note type="input" label="spectrum, use noise suppression">yes</note>
+ </group>
+
+ */
+
+ //<group label="unused input parameters" type="parameters">
+
+ /*
+ <note type="input" label="protein, use minimal annotations">yes</note>
+ <note type="input" label="refine, modification mass 2"></note>
+ <note type="input" label="refine, potential modification mass 2"></note>
+ <note type="input" label="refine, potential modification motif
+ 2"></note> <note type="input" label="residue, modification mass 2"></note>
+ <note type="input" label="residue, potential modification mass
+ 1"></note> <note type="input" label="residue, potential modification mass
+ 2"></note> <note type="input" label="residue, potential modification motif
+ 1"></note> <note type="input" label="residue, potential modification motif
+ 2"></note> <note type="input" label="scoring, pluggable scoring">no</note>
+ </group>
+ */
+
+ //<group label="performance parameters" type="parameters">
+
+ //<note label="list path, sequence source
+ //#1">/gorgone/pappso/formation/TD/Database/Genome_Z_mays_5a.fasta</note>
+ //<note label="list path, sequence source
+ //#2">/gorgone/pappso/formation/TD/Database/contaminants_standarts.fasta</note>
+ if(_current_note_label.startsWith("list path, sequence source #"))
+ {
+ _p_identification_data_source->addFastaFile(
+ _p_project->getFastaFileStore().getInstance(
+ FastaFile(_current_text)));
}
- /*
- <note label="list path, sequence source description #1">no description</note>
- <note label="list path, sequence source description #2">no description</note>
- <note label="modelling, duplicate peptide ids">6019</note>
- <note label="modelling, duplicate proteins">19735</note>
- <note label="modelling, estimated false positives">18</note>
- <note label="modelling, reversed sequence false positives">20</note>
- <note label="modelling, spectrum noise suppression ratio">0.00</note>
- */
- //<note label="modelling, total peptides used">96618641</note>
- if (_current_note_label == "modelling, total peptides used") {
- _p_identification_data_source->setIdentificationEngineStatistics(IdentificationEngineStatistics::total_peptide_used, _current_text.toUInt());
+ /*
+ <note label="list path, sequence source description #1">no
+ description</note> <note label="list path, sequence source description
+ #2">no description</note> <note label="modelling, duplicate peptide
+ ids">6019</note> <note label="modelling, duplicate proteins">19735</note>
+ <note label="modelling, estimated false positives">18</note>
+ <note label="modelling, reversed sequence false positives">20</note>
+ <note label="modelling, spectrum noise suppression ratio">0.00</note>
+ */
+ //<note label="modelling, total peptides used">96618641</note>
+ if(_current_note_label == "modelling, total peptides used")
+ {
+ _p_identification_data_source->setIdentificationEngineStatistics(
+ IdentificationEngineStatistics::total_peptide_used,
+ _current_text.toUInt());
}
- //<note label="modelling, total proteins used">273656</note>
- if (_current_note_label == "modelling, total proteins used") {
- _p_identification_data_source->setIdentificationEngineStatistics(IdentificationEngineStatistics::total_proteins_used, _current_text.toUInt());
+ //<note label="modelling, total proteins used">273656</note>
+ if(_current_note_label == "modelling, total proteins used")
+ {
+ _p_identification_data_source->setIdentificationEngineStatistics(
+ IdentificationEngineStatistics::total_proteins_used,
+ _current_text.toUInt());
}
- //<note label="modelling, total spectra assigned">7464</note>
- if (_current_note_label == "modelling, total spectra assigned") {
- _p_identification_data_source->setIdentificationEngineStatistics(IdentificationEngineStatistics::total_spectra_assigned, _current_text.toUInt());
+ //<note label="modelling, total spectra assigned">7464</note>
+ if(_current_note_label == "modelling, total spectra assigned")
+ {
+ _p_identification_data_source->setIdentificationEngineStatistics(
+ IdentificationEngineStatistics::total_spectra_assigned,
+ _current_text.toUInt());
}
- //<note label="modelling, total spectra used">12199</note>
- if (_current_note_label == "modelling, total spectra used") {
- _p_identification_data_source->setIdentificationEngineStatistics(IdentificationEngineStatistics::total_spectra_used, _current_text.toUInt());
+ //<note label="modelling, total spectra used">12199</note>
+ if(_current_note_label == "modelling, total spectra used")
+ {
+ _p_identification_data_source->setIdentificationEngineStatistics(
+ IdentificationEngineStatistics::total_spectra_used,
+ _current_text.toUInt());
}
- //<note label="modelling, total unique assigned">6260</note>
- if (_current_note_label == "modelling, total unique assigned") {
- _p_identification_data_source->setIdentificationEngineStatistics(IdentificationEngineStatistics::total_unique_assigned, _current_text.toUInt());
+ //<note label="modelling, total unique assigned">6260</note>
+ if(_current_note_label == "modelling, total unique assigned")
+ {
+ _p_identification_data_source->setIdentificationEngineStatistics(
+ IdentificationEngineStatistics::total_unique_assigned,
+ _current_text.toUInt());
}
- //<note label="process, start time">2013:12:20:16:47:19</note>
+ //<note label="process, start time">2013:12:20:16:47:19</note>
- //<note label="process, version">X! Tandem Sledgehammer (2013.09.01.1)</note>
- if (_current_note_label == "process, version") {
- QRegExp rx("\\((.*)\\)");
- if (rx.indexIn(_current_text, 0) != -1) {
- _p_identification_data_source->setIdentificationEngineVersion(rx.cap(1));
+ //<note label="process, version">X! Tandem Sledgehammer
+ //(2013.09.01.1)</note>
+ if(_current_note_label == "process, version")
+ {
+ QRegExp rx("\\((.*)\\)");
+ if(rx.indexIn(_current_text, 0) != -1)
+ {
+ _p_identification_data_source->setIdentificationEngineVersion(
+ rx.cap(1));
}
- qDebug() << "XtandemSaxHandler::endElement_note() " << _p_identification_data_source->getIdentificationEngineVersion();
+ qDebug()
+ << "XtandemSaxHandler::endElement_note() "
+ << _p_identification_data_source->getIdentificationEngineVersion();
}
- /*
- <note label="quality values">243 476 437 382 384 417 399 416 346 387 390 382 321 355 311 283 253 272 251 228</note>
- <note label="refining, # input models">4893</note>
- <note label="refining, # input spectra">5520</note>
- <note label="refining, # partial cleavage">326</note>
- <note label="refining, # point mutations">0</note>
- <note label="refining, # potential C-terminii">0</note>
- <note label="refining, # potential N-terminii">392</note>
- <note label="refining, # unanticipated cleavage">0</note>
- <note label="timing, initial modelling total (sec)">170.96</note>
- <note label="timing, initial modelling/spectrum (sec)">0.0140</note>
- <note label="timing, load sequence models (sec)">0.33</note>
- <note label="timing, refinement/spectrum (sec)">0.0141</note>
- </group>
- */
-
+ /*
+ <note label="quality values">243 476 437 382 384 417 399 416 346 387 390
+ 382 321 355 311 283 253 272 251 228</note> <note label="refining, # input
+ models">4893</note> <note label="refining, # input spectra">5520</note>
+ <note label="refining, # partial cleavage">326</note>
+ <note label="refining, # point mutations">0</note>
+ <note label="refining, # potential C-terminii">0</note>
+ <note label="refining, # potential N-terminii">392</note>
+ <note label="refining, # unanticipated cleavage">0</note>
+ <note label="timing, initial modelling total (sec)">170.96</note>
+ <note label="timing, initial modelling/spectrum (sec)">0.0140</note>
+ <note label="timing, load sequence models (sec)">0.33</note>
+ <note label="timing, refinement/spectrum (sec)">0.0141</note>
+ </group>
+ */
}
- _current_text = "";
- return is_ok;
+ _current_text = "";
+ return is_ok;
}
+bool
+XtandemSaxHandler::error(const QXmlParseException &exception)
+{
+ _errorStr = QObject::tr("Parse error at line %1, column %2 :\n"
+ "%3")
+ .arg(exception.lineNumber())
+ .arg(exception.columnNumber())
+ .arg(exception.message());
-bool XtandemSaxHandler::error(const QXmlParseException &exception) {
- _errorStr = QObject::tr("Parse error at line %1, column %2 :\n"
- "%3").arg(exception.lineNumber()).arg(exception.columnNumber()).arg(
- exception.message());
-
- return false;
+ return false;
}
-bool XtandemSaxHandler::fatalError(const QXmlParseException &exception) {
- _errorStr = QObject::tr("Parse error at line %1, column %2 :\n"
- "%3").arg(exception.lineNumber()).arg(exception.columnNumber()).arg(
- exception.message());
- return false;
+bool
+XtandemSaxHandler::fatalError(const QXmlParseException &exception)
+{
+ _errorStr = QObject::tr("Parse error at line %1, column %2 :\n"
+ "%3")
+ .arg(exception.lineNumber())
+ .arg(exception.columnNumber())
+ .arg(exception.message());
+ return false;
}
-QString XtandemSaxHandler::errorString() const {
- return _errorStr;
+QString
+XtandemSaxHandler::errorString() const
+{
+ return _errorStr;
}
-bool XtandemSaxHandler::endDocument() {
- return true;
+bool
+XtandemSaxHandler::endDocument()
+{
+ return true;
}
-bool XtandemSaxHandler::startDocument() {
- return true;
+bool
+XtandemSaxHandler::startDocument()
+{
+ return true;
}
-bool XtandemSaxHandler::characters(const QString &str) {
- _current_text += str;
- return true;
+bool
+XtandemSaxHandler::characters(const QString &str)
+{
+ _current_text += str;
+ return true;
}
-
diff --git a/src/utils/identificationdatasourcestore.cpp b/src/utils/identificationdatasourcestore.cpp
index e4e16ba50..e15a027cc 100644
--- a/src/utils/identificationdatasourcestore.cpp
+++ b/src/utils/identificationdatasourcestore.cpp
@@ -32,6 +32,7 @@
#include "../core/identification_sources/identificationxtandemfile.h"
#include "../core/identification_sources/identificationmascotdatfile.h"
#include "../core/identification_sources/identificationpwizfile.h"
+#include "../core/identification_sources/identificationpepxmlfile.h"
#include <pappsomspp/pappsoexception.h>
#include <pappsomspp/utils.h>
@@ -90,7 +91,7 @@ IdentificationDataSourceSp IdentificationDataSourceStore::getInstance(const QStr
}
else {
QFileInfo location_file(location);
- QString ext = location_file.suffix();
+ QString ext = location_file.completeSuffix();
//QString sample_name = location_file.baseName();
IdentificationDataSourceSp p_identfile = nullptr;
if (ext.toLower() == "xml") {
@@ -98,7 +99,10 @@ IdentificationDataSourceSp IdentificationDataSourceStore::getInstance(const QStr
p_identfile = std::make_shared<IdentificationXtandemFile>(location_file);
} else if (ext.toLower() == "pep") {
//pep xml file
- p_identfile = std::make_shared<IdentificationPwizFile>(location_file);
+ p_identfile = std::make_shared<IdentificationPepXmlFile>(location_file);
+ } else if (ext.toLower() == "pep.xml") {
+ //pep xml file
+ p_identfile = std::make_shared<IdentificationPepXmlFile>(location_file);
} else if (ext.toLower() == "dat") {
//MASCOT dat file
p_identfile = std::make_shared<IdentificationMascotDatFile>(location_file);
diff --git a/src/utils/types.h b/src/utils/types.h
index 0809820b3..1a193327c 100644
--- a/src/utils/types.h
+++ b/src/utils/types.h
@@ -1,25 +1,26 @@
/*******************************************************************************
-* Copyright (c) 2017 Olivier Langella <olivier.langella@u-psud.fr>.
-*
-* This file is part of XTPcpp.
-*
-* XTPcpp is free software: you can redistribute it and/or modify
-* it under the terms of the GNU General Public License as published by
-* the Free Software Foundation, either version 3 of the License, or
-* (at your option) any later version.
-*
-* XTPcpp is distributed in the hope that it will be useful,
-* but WITHOUT ANY WARRANTY; without even the implied warranty of
-* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-* GNU General Public License for more details.
-*
-* You should have received a copy of the GNU General Public License
-* along with XTPcpp. If not, see <http://www.gnu.org/licenses/>.
-*
-* Contributors:
-* Olivier Langella <olivier.langella@u-psud.fr> - initial API and implementation
-******************************************************************************/
+ * Copyright (c) 2017 Olivier Langella <olivier.langella@u-psud.fr>.
+ *
+ * This file is part of XTPcpp.
+ *
+ * XTPcpp is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * XTPcpp is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with XTPcpp. If not, see <http://www.gnu.org/licenses/>.
+ *
+ * Contributors:
+ * Olivier Langella <olivier.langella@u-psud.fr> - initial API and
+ *implementation
+ ******************************************************************************/
#ifndef _TYPES_H_
@@ -31,82 +32,104 @@
/** \def ExternalDatabase external database references
*
*/
-enum class ExternalDatabase: std::int8_t {
- OboPsiMod =1, ///< OBO PSI MOD
- SwissProt =2, ///< Swiss-Prot
- TrEMBL=3, ///< TrEMBL
- AGI_LocusCode=4, ///< AGI_LocusCode
- NCBI_gi=5, ///< NCBI_gi
- ref=6 ///< ref
+enum class ExternalDatabase : std::int8_t
+{
+ OboPsiMod = 1, ///< OBO PSI MOD
+ SwissProt = 2, ///< Swiss-Prot
+ TrEMBL = 3, ///< TrEMBL
+ AGI_LocusCode = 4, ///< AGI_LocusCode
+ NCBI_gi = 5, ///< NCBI_gi
+ ref = 6 ///< ref
};
/** \def IdentificationEngine identification engine
*
*/
-enum class IdentificationEngine: std::int8_t {
- unknown=0, ///< X!Tandem
- XTandem=1, ///< X!Tandem
- mascot=2, ///< Mascot
- peptider=3 ///< peptider
+enum class IdentificationEngine : std::int8_t
+{
+ unknown = 0, ///< X!Tandem
+ XTandem = 1, ///< MS:1001476 X!Tandem was used to analyze the spectra.
+ mascot = 2, ///< MS:1001207 The name of the Mascot search engine.
+ peptider = 3, ///< peptider
+ OMSSA = 4, ///< MS:1001475 Open Mass Spectrometry Search Algorithm was used to
+ ///< analyze the spectra.
+ SEQUEST = 5, ///< MS:1001208 The name of the SEQUEST search engine.
+ Comet = 6, ///< MS:1002251 Comet open-source sequence search engine developed
+ ///< at the University of Washington. PMID:23148064
+ Morpheus = 7, ///< MS:1002661 "Morpheus search engine." [PMID:23323968]
+ MSGFplus =
+ 8, ///< MS:1002048 "MS-GF+ software used to analyze the spectra." [PSI:PI]
};
/** \def PeptideEvidenceParam peptide evidence specific parameters
* is_a: MS:1001143 ! PSM-level search engine specific statistic
*/
-enum class PeptideEvidenceParam: std::int8_t {
- tandem_hyperscore=0, ///< X!Tandem hyperscore MS:1001331
- tandem_expectation_value=1, ///< X!Tandem expectation value MS:1001330
- mascot_score=2, ///< PSI-MS MS:1001171 mascot:score 56.16
- mascot_expectation_value=3///< PSI-MS MS:1001172 mascot:expectation value 2.42102904673618e-006
+enum class PeptideEvidenceParam : std::int8_t
+{
+ tandem_hyperscore = 0, ///< X!Tandem hyperscore MS:1001331
+ tandem_expectation_value = 1, ///< X!Tandem expectation value MS:1001330
+ mascot_score = 2, ///< PSI-MS MS:1001171 mascot:score 56.16
+ mascot_expectation_value =
+ 3, ///< PSI-MS MS:1001172 mascot:expectation value 2.42102904673618e-006
+ peptide_prophet_probability = 4, ///< no PSI MS description
+ peptide_inter_prophet_probability = 5, ///< no PSI MS description
};
/** \def IdentificationEngineParam identification engine parameters
*
*/
-enum class IdentificationEngineParam: std::int8_t {
- tandem_param=0 ///< X!Tandem xml parameters file
+enum class IdentificationEngineParam : std::int8_t
+{
+ tandem_param = 0 ///< X!Tandem xml parameters file
};
/** \def IdentificationEngineStatistics identification engine statistics
*
*/
-enum class IdentificationEngineStatistics: std::int8_t {
- total_spectra_assigned=1, ///< total_spectra_assigned in one identification file (one sample)
- total_spectra_used=2,///< total_spectra_used in one identification file (one sample)
- total_peptide_used=3,///< total number of peptides generated and used in identification
- total_proteins_used=4,///< total number of proteins generated and used in identification
- total_unique_assigned=5,///< total number unique peptide sequence assigned
+enum class IdentificationEngineStatistics : std::int8_t
+{
+ total_spectra_assigned =
+ 1, ///< total_spectra_assigned in one identification file (one sample)
+ total_spectra_used =
+ 2, ///< total_spectra_used in one identification file (one sample)
+ total_peptide_used =
+ 3, ///< total number of peptides generated and used in identification
+ total_proteins_used =
+ 4, ///< total number of proteins generated and used in identification
+ total_unique_assigned = 5, ///< total number unique peptide sequence assigned
};
/** \def MsRunStatistics MS run statistics
*
*/
-enum class MsRunStatistics: std::int8_t {
- total_spectra=1, ///< total number of spectra
- total_spectra_ms1=2,///< total number of MS1 spectra
- total_spectra_ms2=3,///< total number of MS2 spectra
- total_spectra_ms3=4,///< total number of MS3 spectra
+enum class MsRunStatistics : std::int8_t
+{
+ total_spectra = 1, ///< total number of spectra
+ total_spectra_ms1 = 2, ///< total number of MS1 spectra
+ total_spectra_ms2 = 3, ///< total number of MS2 spectra
+ total_spectra_ms3 = 4, ///< total number of MS3 spectra
};
-
/** \def ProjectMode separate each samples or combine all
*
*/
-enum class ProjectMode {
- individual, ///< separate each biological samples (2D spots for example)
- combined ///< combine every MS runs to get only one protein list
+enum class ProjectMode
+{
+ individual, ///< separate each biological samples (2D spots for example)
+ combined ///< combine every MS runs to get only one protein list
};
/** \def GroupingType list of available grouping algoritms
*
*/
-enum class GroupingType {
- PeptideMass, ///< protein grouper algo
- Phospho, ///< phospho peptides grouping
- SampleScan ///< X!TandemPipeline algo
+enum class GroupingType
+{
+ PeptideMass, ///< protein grouper algo
+ Phospho, ///< phospho peptides grouping
+ SampleScan ///< X!TandemPipeline algo
};
@@ -114,11 +137,14 @@ enum class GroupingType {
*
*/
-enum class ValidationState: std::int8_t {
- notValid = 0,///< notValid : automatic filter validation failed
- valid =1, ///< valid : automatic filter validation passed
- validAndChecked=2, ///< validAndChecked : automatic filter validation passed + manual checking
- grouped=3 ///< grouped : automatic filter validation passed + manual checking + grouped
+enum class ValidationState : std::int8_t
+{
+ notValid = 0, ///< notValid : automatic filter validation failed
+ valid = 1, ///< valid : automatic filter validation passed
+ validAndChecked = 2, ///< validAndChecked : automatic filter validation passed
+ ///< + manual checking
+ grouped = 3 ///< grouped : automatic filter validation passed + manual
+ ///< checking + grouped
};
--
GitLab