From a38f40167de1525eb74f82f4e651164b5eb8acae Mon Sep 17 00:00:00 2001
From: Olivier Langella <olivier.langella@u-psud.fr>
Date: Thu, 3 May 2018 22:03:14 +0200
Subject: [PATCH] normalized spectral abundance factor done
---
src/core/proteinmatch.cpp | 6 +++
src/core/proteinmatch.h | 37 ++++++++---------
.../export_spreadsheet_dialog.ui | 40 ++++++++++++++++---
.../exportspreadsheetdialog.cpp | 9 +++++
.../exportspreadsheetdialog.h | 1 +
src/input/xtpxpipsaxhandler.cpp | 14 ++++++-
src/output/ods/comparbasesheet.cpp | 1 +
src/output/ods/comparbasesheet.h | 6 ++-
src/output/ods/comparspectrasheet.cpp | 21 ++++++++++
src/output/ods/comparspectrasheet.h | 12 ++++++
src/output/ods/odsexport.cpp | 4 ++
11 files changed, 124 insertions(+), 27 deletions(-)
diff --git a/src/core/proteinmatch.cpp b/src/core/proteinmatch.cpp
index cf3ba339f..464294f97 100644
--- a/src/core/proteinmatch.cpp
+++ b/src/core/proteinmatch.cpp
@@ -326,11 +326,17 @@ pappso::pappso_double ProteinMatch::getLogEvalue(const MsRun * sp_msrun_id) cons
}
pappso::pappso_double ProteinMatch::getNsaf(pappso::pappso_double proto_nsaf_sum, const MsRun * p_msrun_id) const {
+ if (proto_nsaf_sum == 0) {
+ throw pappso::PappsoException(QObject::tr("Error computing NSAF for protein %1 :\nproto_nsaf_sum is null").arg(this->getProteinXtpSp().get()->getAccession()));
+ }
return (getProtoNsaf(p_msrun_id)/proto_nsaf_sum);
}
pappso::pappso_double ProteinMatch::getProtoNsaf(const MsRun * sp_msrun_id) const {
try {
+ if (_protein_sp.get()->size() < 1) {
+ throw pappso::PappsoException(QObject::tr("protein has no amino acid sequence"));
+ }
pappso::pappso_double proto_nsaf = (pappso::pappso_double) countSampleScan(ValidationState::validAndChecked ,sp_msrun_id) / (pappso::pappso_double) _protein_sp.get()->size();
return proto_nsaf;
diff --git a/src/core/proteinmatch.h b/src/core/proteinmatch.h
index bb86106c8..d7e2db30d 100644
--- a/src/core/proteinmatch.h
+++ b/src/core/proteinmatch.h
@@ -45,7 +45,7 @@ public:
~ProteinMatch();
const ProteinXtpSp & getProteinXtpSp() const;
-
+
/** @brief compute protein log10(Evalue) within samples
* */
pappso::pappso_double getLogEvalue(const MsRun * sp_msrun_id = nullptr) const;
@@ -64,17 +64,18 @@ public:
**/
const QString getHtmlSequence(PeptideEvidence * peptide_evidence_to_locate = nullptr) const;
- /** @brief compute proto NSAF within msrun
- * Warning: this is not NSAF, just a part
- * @param p_msrun_id pointer on the msrun to get NSAF.
- * */
+ /** @brief compute proto NSAF within msrun : spectral abundance factor (SAF)
+ * Warning: this is not NSAF, just a part
+ * @param p_msrun_id pointer on the msrun to get NSAF.
+ * */
pappso::pappso_double getProtoNsaf(const MsRun * p_msrun_id) const;
- /** @brief compute NSAF within msrun
- * Warning: this is not NSAF, just a part
- * @param proto_nsaf_sum the sum of proto nsaf of all proteins within the msrun
- * @param p_msrun_id pointer on the msrun to get NSAF
- * */
+ /** @brief compute NSAF within msrun : normalized spectral abundance factor (NSAF)
+ * Florens L., Carozza M. J. C., Swanson S. K., et al. Analyzing chromatin remodeling complexes using shotgun proteomics and normalized spectral abundance factors. Methods. 2006;40(4):303–311. doi: 10.1016/j.ymeth.2006.07.028.
+ * https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1815300/
+ * @param proto_nsaf_sum the sum of SAF of all proteins within the msrun
+ * @param p_msrun_id pointer on the msrun to get NSAF
+ * */
pappso::pappso_double getNsaf(pappso::pappso_double proto_nsaf_sum, const MsRun * p_msrun_id) const;
/** @brief compute Protein Abundance Index (PAI) within sample
@@ -91,7 +92,7 @@ public:
void addPeptideMatch(const PeptideMatch & peptide_match);
std::vector<PeptideMatch> & getPeptideMatchList();
const std::vector<PeptideMatch> & getPeptideMatchList() const;
-
+
/** @brief get peptide match sublist with required validation state
* @param state the validation state to select
* @param sp_msrun_id the msrun to look for, if nullptr, then get peptide match overall MSruns
@@ -106,15 +107,15 @@ public:
bool isGrouped() const;
ValidationState getValidationState() const;
-
+
/** @brief count peptide match (psm) listed in this protein match
*/
unsigned int countPeptideMatch(ValidationState state) const;
-
+
/** @brief count distinct sample + scans implied in this protein identification
*/
unsigned int countSampleScan(ValidationState state, const MsRun * p_msrun_id=nullptr) const;
-
+
/** @brief count peptide (peptide+mass)
*/
void countPeptideMass(std::vector<pappso::GrpPeptide *> & count_peptide_mass, ValidationState state) const;
@@ -130,17 +131,17 @@ public:
* */
void updateAutomaticFilters(const AutomaticFilterParameters & automatic_filter_parameters);
-
+
/** @brief collect distinct peptide evidences
*/
void collectPeptideEvidences(std::set<const PeptideEvidence *> & peptide_evidence_set, ValidationState state) const;
-
+
/** @brief count distinct sequence taking into account equivalence between Leucine and Isoleucine
* @param state validation state of peptides to count
* @param p_msrun_id count within the specified sample
*/
size_t countSequenceLi(ValidationState state,const MsRun * p_msrun_id=nullptr) const;
-
+
/** @brief count distinct peptide+mass+charge
* peptide is the peptide sequence LI (Leucine => Isoleucine)
* mass is the peptide mass, not considering labelled residues (if any)
@@ -148,7 +149,7 @@ public:
* @param p_msrun_id count within the specified sample
*/
unsigned int countPeptideMassCharge(ValidationState state, const MsRun * sp_msrun_id=nullptr) const;
-
+
/** @brief count distinct MS samples in which the protein is observed
* @param state validation state of peptides to count
*/
diff --git a/src/gui/export_spreadsheet_dialog/export_spreadsheet_dialog.ui b/src/gui/export_spreadsheet_dialog/export_spreadsheet_dialog.ui
index c2d5c0c1d..8aa973a7e 100644
--- a/src/gui/export_spreadsheet_dialog/export_spreadsheet_dialog.ui
+++ b/src/gui/export_spreadsheet_dialog/export_spreadsheet_dialog.ui
@@ -64,6 +64,9 @@
</item>
<item>
<widget class="QGroupBox" name="compar_groupbox">
+ <property name="toolTip">
+ <string/>
+ </property>
<property name="title">
<string>Compar</string>
</property>
@@ -110,6 +113,16 @@
</property>
</widget>
</item>
+ <item row="0" column="3">
+ <widget class="QCheckBox" name="comparnsaf_checkbox">
+ <property name="toolTip">
+ <string>normalized spectral abundance factor (NSAF)</string>
+ </property>
+ <property name="text">
+ <string>NSAF</string>
+ </property>
+ </widget>
+ </item>
</layout>
</widget>
</item>
@@ -328,7 +341,7 @@
<slot>doComparUniqueSequence(bool)</slot>
<hints>
<hint type="sourcelabel">
- <x>437</x>
+ <x>359</x>
<y>296</y>
</hint>
<hint type="destinationlabel">
@@ -344,7 +357,7 @@
<slot>doComparSpecificSpectra(bool)</slot>
<hints>
<hint type="sourcelabel">
- <x>231</x>
+ <x>167</x>
<y>328</y>
</hint>
<hint type="destinationlabel">
@@ -360,7 +373,7 @@
<slot>doComparSpecificUniqueSequence(bool)</slot>
<hints>
<hint type="sourcelabel">
- <x>437</x>
+ <x>359</x>
<y>328</y>
</hint>
<hint type="destinationlabel">
@@ -376,7 +389,7 @@
<slot>doComparPai(bool)</slot>
<hints>
<hint type="sourcelabel">
- <x>642</x>
+ <x>501</x>
<y>296</y>
</hint>
<hint type="destinationlabel">
@@ -392,7 +405,7 @@
<slot>doComparEmpai(bool)</slot>
<hints>
<hint type="sourcelabel">
- <x>642</x>
+ <x>501</x>
<y>328</y>
</hint>
<hint type="destinationlabel">
@@ -433,6 +446,22 @@
</hint>
</hints>
</connection>
+ <connection>
+ <sender>comparnsaf_checkbox</sender>
+ <signal>toggled(bool)</signal>
+ <receiver>ExportSpreadsheetDialog</receiver>
+ <slot>doComparNsaf(bool)</slot>
+ <hints>
+ <hint type="sourcelabel">
+ <x>550</x>
+ <y>286</y>
+ </hint>
+ <hint type="destinationlabel">
+ <x>806</x>
+ <y>294</y>
+ </hint>
+ </hints>
+ </connection>
</connections>
<slots>
<slot>reject()</slot>
@@ -452,5 +481,6 @@
<slot>doComparEmpai(bool)</slot>
<slot>doPtmIslands(bool)</slot>
<slot>doPtmSpectra(bool)</slot>
+ <slot>doComparNsaf(bool)</slot>
</slots>
</ui>
diff --git a/src/gui/export_spreadsheet_dialog/exportspreadsheetdialog.cpp b/src/gui/export_spreadsheet_dialog/exportspreadsheetdialog.cpp
index 45a1a878f..60ec8e679 100644
--- a/src/gui/export_spreadsheet_dialog/exportspreadsheetdialog.cpp
+++ b/src/gui/export_spreadsheet_dialog/exportspreadsheetdialog.cpp
@@ -88,6 +88,10 @@ ExportSpreadsheetDialog::ExportSpreadsheetDialog(QWidget * parent):
if (settings.value("export_ods/comparempai", "true").toBool()) {
ui->comparempai_checkbox->setCheckState(Qt::Checked);
}
+ ui->comparnsaf_checkbox->setCheckState(Qt::Unchecked);
+ if (settings.value("export_ods/comparnsaf", "true").toBool()) {
+ ui->comparnsaf_checkbox->setCheckState(Qt::Checked);
+ }
ui->samples_checkbox->setCheckState(Qt::Unchecked);
if (settings.value("export_ods/samples", "true").toBool()) {
ui->samples_checkbox->setCheckState(Qt::Checked);
@@ -170,6 +174,11 @@ void ExportSpreadsheetDialog::doComparPai(bool simple) {
QSettings settings;
settings.setValue("export_ods/comparpai", QString("%1").arg(simple));
}
+void ExportSpreadsheetDialog::doComparNsaf(bool simple) {
+
+ QSettings settings;
+ settings.setValue("export_ods/comparnsaf", QString("%1").arg(simple));
+}
void ExportSpreadsheetDialog::doPeptidePos(bool simple) {
QSettings settings;
diff --git a/src/gui/export_spreadsheet_dialog/exportspreadsheetdialog.h b/src/gui/export_spreadsheet_dialog/exportspreadsheetdialog.h
index 33892c523..0214e871e 100644
--- a/src/gui/export_spreadsheet_dialog/exportspreadsheetdialog.h
+++ b/src/gui/export_spreadsheet_dialog/exportspreadsheetdialog.h
@@ -50,6 +50,7 @@ public slots:
void doGroups(bool simple);
void doPeptidePos(bool simple);
void doComparEmpai(bool simple);
+ void doComparNsaf(bool simple);
void doComparPai(bool simple);
void doComparSpecificUniqueSequence(bool simple);
void doComparUniqueSequence(bool simple);
diff --git a/src/input/xtpxpipsaxhandler.cpp b/src/input/xtpxpipsaxhandler.cpp
index ab4743b4b..3d9fa5c31 100644
--- a/src/input/xtpxpipsaxhandler.cpp
+++ b/src/input/xtpxpipsaxhandler.cpp
@@ -493,18 +493,28 @@ bool XtpXpipSaxHandler::startElement_protein(QXmlAttributes attributes) {
</protein>
*/
_sp_current_protein = ProteinXtp().makeProteinXtpSp();
-
- _sp_current_protein.get()->setFastaFileP(_map_fasta_files.at(attributes.value("fasta_id")).get());
+
+ auto fasta_it = _map_fasta_files.find(attributes.value("fasta_id"));
+ if (fasta_it == _map_fasta_files.end()) {
+ throw pappso::ExceptionNotFound(QObject::tr("ERROR fasta_id %1 not found").arg(attributes.value("fasta_id")));
+ }
+ //qDebug() << "startElement_protein fastaid=" << attributes.value("fasta_id");
+ _sp_current_protein.get()->setFastaFileP(fasta_it->second.get());
_sp_current_protein.get()->setAccession(attributes.value("acc"));
+
+ //qDebug() << "startElement_protein acc=" << attributes.value("acc");
+ //qDebug() << "startElement_protein description=" << attributes.value("description");
_sp_current_protein.get()->setDescription(attributes.value("description"));
_sp_current_protein.get()->setIsContaminant(false);
if (attributes.value("is_contaminant").simplified().toLower() == "true") {
_sp_current_protein.get()->setIsContaminant(true);
}
+ //qDebug() << "startElement_protein iscontaminant";
_sp_current_protein.get()->setIsDecoy(false);
if (attributes.value("is_decoy").simplified().toLower() == "true") {
_sp_current_protein.get()->setIsDecoy(true);
}
+ //qDebug() << "startElement_protein isdecoy";
qDebug() << "startElement_protein end" ;
return true;
diff --git a/src/output/ods/comparbasesheet.cpp b/src/output/ods/comparbasesheet.cpp
index 775d06a61..f228d5186 100644
--- a/src/output/ods/comparbasesheet.cpp
+++ b/src/output/ods/comparbasesheet.cpp
@@ -129,6 +129,7 @@ void ComparBaseSheet::writeProteinMatch(const ProteinMatch * p_protein_match) {
void ComparBaseSheet::writeIdentificationGroup(IdentificationGroup * p_ident) {
qDebug() << "ComparBaseSheet::writeIdentificationGroup begin";
+ _p_current_identification_group = p_ident;
writeHeaders(p_ident);
diff --git a/src/output/ods/comparbasesheet.h b/src/output/ods/comparbasesheet.h
index da230ef14..c0fc4f460 100644
--- a/src/output/ods/comparbasesheet.h
+++ b/src/output/ods/comparbasesheet.h
@@ -42,12 +42,12 @@ public :
private :
void writeIdentificationGroup(IdentificationGroup * p_ident);
void writeHeaders(IdentificationGroup * p_ident);
- void writeProteinMatch(const ProteinMatch * p_protein_match);
-
public :
void writeSheet();
protected :
virtual void writeComparValue(const ProteinMatch * p_protein_match, ValidationState state, const MsRun * p_msrun)=0;
+ void writeProteinMatch(const ProteinMatch * p_protein_match);
+
protected :
OdsExport * _p_ods_export;
@@ -58,6 +58,8 @@ protected :
QString _first_cell_coordinate;
+ IdentificationGroup * _p_current_identification_group;
+
};
#endif // COMPARBASESHEET_H
diff --git a/src/output/ods/comparspectrasheet.cpp b/src/output/ods/comparspectrasheet.cpp
index cfc10cbc9..fb5c82395 100644
--- a/src/output/ods/comparspectrasheet.cpp
+++ b/src/output/ods/comparspectrasheet.cpp
@@ -74,3 +74,24 @@ void ComparEmpaiSheet::writeComparValue(const ProteinMatch * p_protein_match, Va
_p_writer->writeCell(p_protein_match->getEmPAI(p_msrun));
qDebug() << "ComparEmpaiSheet::writeComparValue end";
}
+
+ComparNsafSheet::ComparNsafSheet(OdsExport* p_ods_export, CalcWriterInterface* p_writer, const Project* p_project): ComparBaseSheet(p_ods_export, p_writer, p_project) {
+ _title_sheet = "compar NSAF";
+}
+
+void ComparNsafSheet::writeComparValue(const ProteinMatch * p_protein_match, ValidationState state, const MsRun * p_msrun) {
+ qDebug() << "ComparNsafSheet::writeComparValue begin";
+ pappso::pappso_double proto_nsaf_sum=0;
+ std::pair<std::map<const MsRun *,pappso::pappso_double>::iterator,bool> ret = _map_proto_nsaf_sum_by_msrun.insert(std::pair<const MsRun *,pappso::pappso_double>(p_msrun,0));
+ if (ret.second==false) {
+ //"element 'z' already existed";
+ proto_nsaf_sum = ret.first->second;
+ }
+ else {
+ proto_nsaf_sum = _p_current_identification_group->computeProtoNsafSum(p_msrun);
+ ret.first->second = proto_nsaf_sum;
+ }
+
+ _p_writer->writeCell(p_protein_match->getNsaf(proto_nsaf_sum,p_msrun));
+ qDebug() << "ComparNsafSheet::writeComparValue end";
+}
diff --git a/src/output/ods/comparspectrasheet.h b/src/output/ods/comparspectrasheet.h
index c3926823f..29653e279 100644
--- a/src/output/ods/comparspectrasheet.h
+++ b/src/output/ods/comparspectrasheet.h
@@ -69,4 +69,16 @@ protected :
virtual void writeComparValue(const ProteinMatch * p_protein_match, ValidationState state, const MsRun * p_msrun) override;
};
+class ComparNsafSheet:public ComparBaseSheet
+{
+public :
+ ComparNsafSheet (OdsExport * p_ods_export, CalcWriterInterface * p_writer, const Project * p_project);
+
+protected :
+ virtual void writeComparValue(const ProteinMatch * p_protein_match, ValidationState state, const MsRun * p_msrun) override;
+private:
+
+ std::map<const MsRun *, pappso::pappso_double> _map_proto_nsaf_sum_by_msrun;
+};
+
#endif // COMPARSPECTRASHEET_H
diff --git a/src/output/ods/odsexport.cpp b/src/output/ods/odsexport.cpp
index ad1b661c6..6adb5c960 100644
--- a/src/output/ods/odsexport.cpp
+++ b/src/output/ods/odsexport.cpp
@@ -114,6 +114,10 @@ void OdsExport::write(CalcWriterInterface * p_writer, WorkMonitorInterface * p_m
p_monitor->message(QObject::tr("writing emPAI comparisons"));
ComparEmpaiSheet(this, p_writer, _p_project).writeSheet();
}
+ if (settings.value("export_ods/comparnsaf", "true").toBool()) {
+ p_monitor->message(QObject::tr("writing NSAF comparisons"));
+ ComparNsafSheet(this, p_writer, _p_project).writeSheet();
+ }
}
if (settings.value("export_ods/samples", "true").toBool()) {
p_monitor->message(QObject::tr("writing samples"));
--
GitLab