Skip to content
Snippets Groups Projects
Commit 349d8838 authored by Langella Olivier's avatar Langella Olivier
Browse files

WIP: reading Xtandem files the xml stream way seems to work fine

parent fdd9cadb
No related branches found
No related tags found
No related merge requests found
Hide whitespace changes
Inline Side-by-side
src/input/tandem/tandemreader.cpp
+ 306
− 3
View file @ 349d8838
......@@ -209,11 +209,12 @@ TandemReader::readGroup()
while(m_qxmlStreamReader.readNext() ==
QXmlStreamReader::TokenType::Characters)
{
protein_sequence +=
m_qxmlStreamReader.Characters;
qDebug() << m_qxmlStreamReader.text();
protein_sequence += m_qxmlStreamReader.text();
}
protein_sequence =
protein_sequence.simplified().replace(" ", "");
qDebug() << protein_sequence;
if(!protein_sequence.isEmpty())
{
//._sequence.replace(QRegExp("\\*"),
......@@ -254,10 +255,17 @@ TandemReader::readGroup()
}
}
//m_qxmlStreamReader.skipCurrentElement();
// m_qxmlStreamReader.skipCurrentElement();
}
else if(tandem_group.type == "parameters")
{
readGroupTypeParameters(tandem_group);
}
else
{
m_qxmlStreamReader.raiseError(
QObject::tr("Not an X!Tandem input file (no bioml)"));
m_qxmlStreamReader.skipCurrentElement();
}
}
......@@ -520,3 +528,298 @@ TandemReader::readDomain(TandemReader::TandemGroup &tandem_group)
delete p_peptide_evidence;
}
}
void
TandemReader::readGroupTypeParameters(TandemGroup &tandem_group)
{
qDebug() << tandem_group.label;
while(m_qxmlStreamReader.readNextStartElement())
{
qDebug() << m_qxmlStreamReader.name();
if(m_qxmlStreamReader.name() == "note")
{
QString type =
m_qxmlStreamReader.attributes().value("type").toString();
QString label =
m_qxmlStreamReader.attributes().value("label").toString();
QString text = m_qxmlStreamReader.readElementText();
//<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(label == "list path, default parameters")
{
mp_identificationDataSource->setIdentificationEngineParam(
IdentificationEngineParam::tandem_param, 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(label == "spectrum, path")
{
//_sp_msrun.get()->setFileName(_current_text);
// already set by tandem info parser
}
/*
<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(label.startsWith("list path, sequence source #"))
{
mp_identificationDataSource->addFastaFile(
mp_project->getFastaFileStore().getInstance(FastaFile(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(label == "modelling, total peptides used")
{
mp_identificationDataSource->setIdentificationEngineStatistics(
IdentificationEngineStatistics::total_peptide_used,
text.toUInt());
}
//<note label="modelling, total proteins used">273656</note>
if(label == "modelling, total proteins used")
{
mp_identificationDataSource->setIdentificationEngineStatistics(
IdentificationEngineStatistics::total_proteins_used,
text.toUInt());
}
//<note label="modelling, total spectra assigned">7464</note>
if(label == "modelling, total spectra assigned")
{
mp_identificationDataSource->setIdentificationEngineStatistics(
IdentificationEngineStatistics::total_spectra_assigned,
text.toUInt());
}
//<note label="modelling, total spectra used">12199</note>
if(label == "modelling, total spectra used")
{
qDebug() << label;
mp_identificationDataSource->setIdentificationEngineStatistics(
IdentificationEngineStatistics::total_spectra_used,
text.toUInt());
}
//<note label="modelling, total unique assigned">6260</note>
if(label == "modelling, total unique assigned")
{
qDebug() << label;
mp_identificationDataSource->setIdentificationEngineStatistics(
IdentificationEngineStatistics::total_unique_assigned,
text.toUInt());
}
qDebug() << label;
if(label == "spectrum, timstof MS2 centroid parameters")
{
qDebug() << label;
mp_identificationDataSource->setTimstofMs2CentroidParameters(
text);
if((msp_msrun.get()->getFileName().endsWith(".tdf")) ||
(msp_msrun.get()->getFileName().endsWith(".d")))
{
// this is a TimsTOF tandem result file : scan numbers are in
// fact spectrum index: we have to notice this
mp_identificationDataSource->getPeptideEvidenceStore()
.ensureSpectrumIndexRef();
}
}
if(label == "output, spectrum index")
{
// TODO in pappsomspp : change tandem output to explicitly tell if
// we are dealing with spectrum index
qDebug() << label;
if(text == "true")
{ // this MUST be spectrum index instead of scan numbers
mp_identificationDataSource->getPeptideEvidenceStore()
.ensureSpectrumIndexRef();
}
}
if(label == "spectrum, timstof MS2 filters")
{
qDebug() << label;
// this is a TimsTOF tandem result file : scan numbers are in fact
// spectrum index:
// we have to notice this
if((msp_msrun.get()->getFileName().endsWith(".tdf")) ||
(msp_msrun.get()->getFileName().endsWith(".d")))
{
// this is a TimsTOF tandem result file : scan numbers are in
// fact spectrum index: we have to notice this
mp_identificationDataSource->getPeptideEvidenceStore()
.ensureSpectrumIndexRef();
}
}
//<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(label == "process, version")
{
QRegExp rx("\\((.*)\\)");
if(rx.indexIn(text, 0) != -1)
{
mp_identificationDataSource->setIdentificationEngineVersion(
rx.cap(1));
}
qDebug() << mp_identificationDataSource
->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>
*/
}
else
{
m_qxmlStreamReader.raiseError(
QObject::tr("Not an X!Tandem input "
"file (no bioml)"));
m_qxmlStreamReader.skipCurrentElement();
}
}
}
src/input/tandem/tandemreader.h
+ 1
− 0
View file @ 349d8838
......@@ -74,6 +74,7 @@ class TandemReader : public pappso::XmlStreamReaderInterface
PeptideMatch peptideMatch;
};
void readDomain(TandemGroup &tandem_group);
void readGroupTypeParameters(TandemGroup &tandem_group);
private:
pappso::UiMonitorInterface *mp_monitor;
......
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment