From 58e8469d21f044d2313f9d44c8696290657dd524 Mon Sep 17 00:00:00 2001
From: Olivier Langella <Olivier.Langella@moulon.inra.fr>
Date: Wed, 19 Apr 2017 21:51:57 +0200
Subject: [PATCH] parsing tandem version OK
---
src/input/xtandemsaxhandler.cpp | 426 ++++++++++++++++----------------
1 file changed, 215 insertions(+), 211 deletions(-)
diff --git a/src/input/xtandemsaxhandler.cpp b/src/input/xtandemsaxhandler.cpp
index b32ac882d..1ef6a3d36 100644
--- a/src/input/xtandemsaxhandler.cpp
+++ b/src/input/xtandemsaxhandler.cpp
@@ -151,7 +151,7 @@ bool XtandemSaxHandler::startElement_note(QXmlAttributes attributes) {
_is_protein_description = true;
}
}
- return is_ok;
+ return is_ok;
}
bool XtandemSaxHandler::startElement_protein(QXmlAttributes attributes) {
@@ -193,7 +193,7 @@ bool XtandemSaxHandler::startElement_domain(QXmlAttributes attributes) {
bool is_ok = true;
_current_text = _current_text.simplified().replace(" ", "");
if (!_current_text.isEmpty()) {
- //._sequence.replace(QRegExp("\\*"), "")).removeTranslationStop()
+ //._sequence.replace(QRegExp("\\*"), "")).removeTranslationStop()
_p_protein_match->getProteinXtpSp().get()->setSequence(_current_text.replace(QRegExp("\\*"), ""));
}
@@ -204,76 +204,76 @@ bool XtandemSaxHandler::startElement_domain(QXmlAttributes attributes) {
// 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*/
+ – 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();
@@ -332,151 +332,155 @@ bool XtandemSaxHandler::endElement_note() {
_p_protein_match->getProteinXtpSp().get()->setDescription(_current_text.section(" ",1));
}
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>
- <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>
-
- */
+ /*
+ * <note type="input" label="list path, default parameters">/gorgone/pappso/tmp/temp_condor_job8533994640337729751189420695540169/QExactive_analysis_FDR_nosemi.xml</note>
+ <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>
-*/
+ /*
+ <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>
- <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>
- <note label="modelling, total proteins used">273656</note>
- <note label="modelling, total spectra assigned">7464</note>
- <note label="modelling, total spectra used">12199</note>
- <note label="modelling, total unique assigned">6260</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") {
- _p_identification_data_source->setIdentificationEngineVersion(_current_text);
- }
- /*
- <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="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>
+ <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>
+ <note label="modelling, total proteins used">273656</note>
+ <note label="modelling, total spectra assigned">7464</note>
+ <note label="modelling, total spectra used">12199</note>
+ <note label="modelling, total unique assigned">6260</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));
+ }
+ 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>
+ */
}
_current_text = "";
--
GitLab