libpappsomspp
Library for mass spectrometry
Loading...
Searching...
No Matches
pappso::cbor::psm::SageTsvHandler Class Reference

#include <sagetsvhandler.h>

Inheritance diagram for pappso::cbor::psm::SageTsvHandler:

Classes

struct  Line
 
struct  Psm
 
struct  Sample
 
struct  Scan
 

Public Types

enum class  Columns : std::int8_t {
  psm_id , peptide , proteins , protein_groups ,
  num_proteins , num_protein_groups , filename , scannr ,
  rank , label , expmass , calcmass ,
  charge , peptide_len , missed_cleavages , semi_enzymatic ,
  isotope_error , precursor_ppm , fragment_ppm , hyperscore ,
  delta_next , delta_best , rt , aligned_rt ,
  predicted_rt , delta_rt_model , ion_mobility , predicted_mobility ,
  delta_mobility , matched_peaks , longest_b , longest_y ,
  longest_y_pct , matched_intensity_pct , scored_candidates , poisson ,
  sage_discriminant_score , posterior_error , spectrum_q , peptide_q ,
  protein_q , protein_group_q , ms2_intensity
}
 

Public Member Functions

 SageTsvHandler (pappso::UiMonitorInterface *p_monitor, const SageReader &sage_reader, PsmProteinMap &psm_protein_map)
 
virtual ~SageTsvHandler ()
 
virtual void startSheet (const QString &sheet_name) override
 
virtual void endSheet () override
 
virtual void startLine () override
 
virtual void endLine () override
 
virtual void setCell (const OdsCell &cell) override
 
virtual void endDocument () override
 
void writeSampleList ()
 

Private Member Functions

void parsePeptide (const QString &peptide_str)
 
void parseProteins (const QString &proteins_str)
 
bool parseScanNrColumn (const QString &spectrum_string_id)
 
void parseMsRunFilename (const QString &msrun_filename)
 
void recordLine ()
 
void writeSample (const Sample &one_sample)
 
void writeScan (const Scan &one_scan)
 
void writePsm (const Psm &one_psm)
 

Private Attributes

const SageReaderm_sageReader
 
PsmProteinMapm_psmProteinMap
 
pappso::UiMonitorInterfacemp_monitor = nullptr
 
std::size_t m_progressIndex = 0
 
std::size_t m_lineNumber = 0
 
std::size_t m_columnNumber = 0
 
std::vector< Columnsm_columnTypeList
 
pappso::PeptideSp msp_peptide
 
std::vector< SageReader::SageModificationm_staticModificationList
 
std::vector< SageReader::SageModificationm_variableModificationList
 
std::size_t m_spectrumIndex
 
std::size_t m_scanNumber
 
bool m_scanNumberIsOk
 
Line m_line
 
QString m_decoyTag
 
QStringList m_proteinList
 
QString m_spectrumNativeId
 
std::map< QString, Samplem_sampleMap
 
Samplemp_currentSample
 

Detailed Description

Todo:
write docs

Definition at line 49 of file sagetsvhandler.h.

Member Enumeration Documentation

◆ Columns

enum class pappso::cbor::psm::SageTsvHandler::Columns : std::int8_t
strong
Enumerator
psm_id 
peptide 
proteins 
protein_groups 
num_proteins 
num_protein_groups 
filename 
scannr 
rank 
label 
expmass 
calcmass 
charge 
peptide_len 
missed_cleavages 
semi_enzymatic 
isotope_error 
precursor_ppm 
fragment_ppm 
hyperscore 
delta_next 
delta_best 
rt 
aligned_rt 
predicted_rt 
delta_rt_model 
ion_mobility 
predicted_mobility 
delta_mobility 
matched_peaks 
longest_b 
longest_y 
longest_y_pct 
matched_intensity_pct 
scored_candidates 
poisson 
sage_discriminant_score 
posterior_error 
spectrum_q 
peptide_q 
protein_q 
protein_group_q 
ms2_intensity 

Definition at line 52 of file sagetsvhandler.h.

53 {
54 psm_id,
55 peptide,
61 scannr,
62 rank,
63 label,
64 expmass,
66 charge,
76 rt,
89 poisson,
97 };

Constructor & Destructor Documentation

◆ SageTsvHandler()

pappso::cbor::psm::SageTsvHandler::SageTsvHandler ( pappso::UiMonitorInterface p_monitor,
const SageReader sage_reader,
PsmProteinMap psm_protein_map 
)

Default constructor

Definition at line 47 of file sagetsvhandler.cpp.

50 : m_sageReader(sage_reader), m_psmProteinMap(psm_protein_map)
51{
52 mp_monitor = p_monitor;
53 m_staticModificationList = sage_reader.getStaticModificationList();
54 m_variableModificationList = sage_reader.getVariableModificationList();
55 m_decoyTag = sage_reader.getDecoyTag();
56}
std::vector< SageReader::SageModification > m_staticModificationList
pappso::UiMonitorInterface * mp_monitor
std::vector< SageReader::SageModification > m_variableModificationList

References pappso::cbor::psm::SageReader::getDecoyTag(), pappso::cbor::psm::SageReader::getStaticModificationList(), pappso::cbor::psm::SageReader::getVariableModificationList(), m_decoyTag, m_staticModificationList, m_variableModificationList, and mp_monitor.

◆ ~SageTsvHandler()

pappso::cbor::psm::SageTsvHandler::~SageTsvHandler ( )
virtual

Destructor

Definition at line 58 of file sagetsvhandler.cpp.

59{
60}

Member Function Documentation

◆ endDocument()

void pappso::cbor::psm::SageTsvHandler::endDocument ( )
overridevirtual

Definition at line 441 of file sagetsvhandler.cpp.

442{
443}

◆ endLine()

void pappso::cbor::psm::SageTsvHandler::endLine ( )
overridevirtual

callback that indicates a line ending. Override it if needed.

Definition at line 72 of file sagetsvhandler.cpp.

References pappso::cbor::psm::SageTsvHandler::Line::charge, m_line, m_lineNumber, and recordLine().

◆ endSheet()

void pappso::cbor::psm::SageTsvHandler::endSheet ( )
overridevirtual

callback that indicates the end of the current data sheet. Override it if needed

Definition at line 80 of file sagetsvhandler.cpp.

81{
82}

◆ parseMsRunFilename()

void pappso::cbor::psm::SageTsvHandler::parseMsRunFilename ( const QString &  msrun_filename)
private

Definition at line 566 of file sagetsvhandler.cpp.

567{
568
569
570 // find the sample :
571 auto it_insert = m_sampleMap.insert({msrun_filename, {}});
572 mp_currentSample = &(it_insert.first->second);
573 if(it_insert.second)
574 {
575 // new sample
576 it_insert.first->second.name = msrun_filename;
577 QCborMap ms_file;
578 QCborMap identification_file;
579
580 it_insert.first->second.cbor_core_sample.insert(QString("name"),
581 QFileInfo(msrun_filename).baseName());
582
583 // identification_file_list
584 QCborArray identification_file_list;
585 identification_file.insert(QString("name"), m_sageReader.getmJsonAbsoluteFilePath());
586 identification_file_list.push_back(identification_file);
587 it_insert.first->second.cbor_core_sample.insert(QString("identification_file_list"),
588 identification_file_list);
589
590
591 ms_file.insert(QString("name"), m_sageReader.getMzmlPath(msrun_filename));
592 it_insert.first->second.cbor_core_sample.insert(QString("peaklist_file"), ms_file);
593 }
594
595 /*
596 msp_msrun = m_sageReader.getSageFileReader().getMsRunSpWithFileName(msrun_filename);
597 qDebug() << msp_msrun.get()->getFileName();
598
599 msp_identificationSageJsonFileSp =
600 m_sageReader.getSageFileReader().getIdentificationSageJsonFileSpWithFileName(msrun_filename);
601
602 mp_identificationGroup =
603 m_sageReader.getSageFileReader().getIdentificationGroupPtrWithFileName(msrun_filename);
604 qDebug() << msp_msrun.get()->getFileName();
605 */
606}
const QString & getMzmlPath(const QString &file_msrun) const
const QString & getmJsonAbsoluteFilePath() const
std::map< QString, Sample > m_sampleMap

References pappso::cbor::psm::SageReader::getmJsonAbsoluteFilePath(), pappso::cbor::psm::SageReader::getMzmlPath(), m_sageReader, m_sampleMap, mp_currentSample, and pappso::cbor::psm::SageTsvHandler::Sample::name.

Referenced by setCell().

◆ parsePeptide()

void pappso::cbor::psm::SageTsvHandler::parsePeptide ( const QString &  peptide_str)
private

Definition at line 458 of file sagetsvhandler.cpp.

459{
460 qDebug();
461 QString peptide_str_verif = peptide_str;
462 // fixed modifications :
463 for(SageReader::SageModification modif : m_staticModificationList)
464 {
465 qDebug() << modif.strModification;
466 qDebug() << modif.modification->getAccession();
467 peptide_str_verif = peptide_str_verif.replace(
468 modif.strModification, QString("[%1]").arg(modif.modification->getAccession()));
469 }
470 // variable modifications :
471 for(SageReader::SageModification modif : m_variableModificationList)
472 {
473 qDebug() << modif.strModification;
474 qDebug() << modif.modification->getAccession();
475 peptide_str_verif = peptide_str_verif.replace(
476 modif.strModification, QString("[%1]").arg(modif.modification->getAccession()));
477 }
478
479 qDebug() << peptide_str_verif;
480 // LPMFGC[+57.0216]NDATQVYK
482 qDebug();
483 // variable modifications :
484 /*
485 setVariableModifications(peptide_sp,
486 peptide_line.peptide_string_list.at(6));
487*/
488 qDebug() << msp_peptide.get()->toProForma();
489}
static PeptideSp parseString(const QString &pepstr)

References m_staticModificationList, m_variableModificationList, msp_peptide, and pappso::PeptideProFormaParser::parseString().

Referenced by setCell().

◆ parseProteins()

void pappso::cbor::psm::SageTsvHandler::parseProteins ( const QString &  proteins_str)
private

Definition at line 493 of file sagetsvhandler.cpp.

494{
495 m_proteinList.clear();
496 m_proteinList = proteins_str.split(";");
497 for(QString accession : m_proteinList)
498 {
499
500 PsmProtein psm_protein;
501 psm_protein.protein_sp = std::make_shared<pappso::Protein>(accession, "");
502 psm_protein.isTarget = true;
503 if(accession.startsWith(m_decoyTag))
504 {
505 psm_protein.isTarget = false;
506 }
507
508 m_psmProteinMap.insert(psm_protein);
509 }
510}
std::pair< std::map< QString, PsmProtein >::iterator, bool > insert(const PsmProtein &psm_protein)
standard map insert of a PsmProtein (accession is the key)

References pappso::cbor::psm::PsmProteinMap::insert(), pappso::cbor::psm::PsmProtein::isTarget, m_decoyTag, m_proteinList, m_psmProteinMap, and pappso::cbor::psm::PsmProtein::protein_sp.

Referenced by setCell().

◆ parseScanNrColumn()

bool pappso::cbor::psm::SageTsvHandler::parseScanNrColumn ( const QString &  spectrum_string_id)
private

Definition at line 513 of file sagetsvhandler.cpp.

514{
515 m_spectrumNativeId = spectrum_string_id;
516 qDebug() << spectrum_string_id;
517 // controllerType=0 controllerNumber=1 scan=176056
518
519 bool is_ok = false;
520 QStringList scan_list = spectrum_string_id.split("scan=");
521 m_scanNumberIsOk = false;
522 if(scan_list.size() == 2)
523 {
524 // we bet that there is a scan number, easy to parse
525 m_scanNumber = scan_list.at(1).toULongLong(&is_ok);
526 m_scanNumberIsOk = is_ok;
527 if(m_scanNumber > 0)
529 }
530 if(is_ok == false)
531 {
532 ;
533 QStringList scan_list = spectrum_string_id.split(QRegularExpression("[^\\d]"));
534 if(scan_list.size() == 2)
535 {
536 m_scanNumber = scan_list.at(0).toULongLong(&is_ok);
537 m_scanNumberIsOk = is_ok;
538 if(m_scanNumber > 0)
540 }
541 /*
542 if(msp_previousMsrun != msp_msrun)
543 {
544 mp_monitor->setStatus(
545 QObject::tr("Reading mz data file %1").arg(msp_msrun.get()->getFileName()));
546 msp_previousMsrun = msp_msrun;
547 }
548
549 pappso::MsRunReader *msrunreader_p = msp_msrun.get()->getMsRunReaderSPtr().get();
550 if(msrunreader_p->getMsRunId()->getMsDataFormat() == pappso::MsDataFormat::brukerTims)
551 {
552 m_spectrumIndex = spectrum_string_id.toInt() * 2 - 1;
553 }
554 else
555 {
556 m_spectrumIndex =
557 msrunreader_p->spectrumStringIdentifier2SpectrumIndex(spectrum_string_id);
558 }*/
559 }
560
561 qDebug() << spectrum_string_id;
562 return is_ok;
563}

References m_scanNumber, m_scanNumberIsOk, m_spectrumIndex, and m_spectrumNativeId.

Referenced by setCell().

◆ recordLine()

void pappso::cbor::psm::SageTsvHandler::recordLine ( )
private

Definition at line 609 of file sagetsvhandler.cpp.

610{
611 qDebug();
612
613 for(const QString &accession : m_proteinList)
614 {
615 PsmProtein psm_protein;
616 psm_protein.protein_sp = std::make_shared<pappso::Protein>(accession, "");
617
618 auto it = m_psmProteinMap.insert(psm_protein);
619 it.first->second.cborEval.insert(QString("protein_q"), m_line.protein_q);
620 }
621 /*
622 PeptideEvidence pe(msp_msrun.get(), m_spectrumIndex, true);
623 pe.setCharge(m_line.charge);
624 pe.setChecked(true);
625 pe.setExperimentalMass(m_line.expmass);
626 pe.setPeptideXtpSp(msp_peptide);
627 pe.setIdentificationDataSource(msp_identificationSageJsonFileSp.get());
628 pe.setIdentificationEngine(m_identificationEngine);
629 pe.setRetentionTime(m_line.rt);
630 pe.setParam(PeptideEvidenceParam::tandem_hyperscore, m_line.hyperscore);
631 pe.setParam(PeptideEvidenceParam::sage_sage_discriminant_score,
632 m_line.sage_discriminant_score);
633 pe.setParam(PeptideEvidenceParam::sage_peptide_q, m_line.peptide_q);
634 pe.setParam(PeptideEvidenceParam::sage_posterior_error, m_line.posterior_error);
635 pe.setParam(PeptideEvidenceParam::sage_spectrum_q, m_line.spectrum_q);
636 pe.setParam(PeptideEvidenceParam::sage_predicted_rt, m_line.predicted_rt);
637 pe.setParam(PeptideEvidenceParam::sage_isotope_error, m_line.isotope_error);
638
639
640 PeptideMatch peptide_match;
641 // peptide_match.setStart(mz_peptide_evidence.start);
642 peptide_match.setPeptideEvidenceSp(
643 msp_identificationSageJsonFileSp.get()->getPeptideEvidenceStore().getInstance(&pe));
644 */
645
646 // find the scan in sample
647 auto it_insert = mp_currentSample->scan_map.insert({m_spectrumNativeId, Scan()});
648 Scan *current_cbor_scan_p = &(it_insert.first->second);
649 if(it_insert.second)
650 {
651 // new scan
652 QCborMap &scan_id = it_insert.first->second.cbor_id;
654 {
655 scan_id.insert(QString("index"), (qint64)m_spectrumIndex);
656 scan_id.insert(QString("scan"), (qint64)m_scanNumber);
657 }
658 scan_id.insert(QString("native_id"), m_spectrumNativeId);
659
660 QCborMap &scan_ms2 = it_insert.first->second.cbor_ms2;
661 scan_ms2.insert(QString("rt"), m_line.rt);
662
663 QCborMap &scan_precursor = it_insert.first->second.cbor_precursor;
664 scan_precursor.insert(QString("z"), m_line.charge);
665 double mh = m_line.expmass + MHPLUS;
666 scan_precursor.insert(QString("mh"), mh);
667 double exp_mz = (m_line.expmass + (MHPLUS * m_line.charge)) / m_line.charge;
668 scan_precursor.insert(QString("mz"), exp_mz);
669 }
670
671 Psm one_psm;
672 one_psm.peptide_sequence_li = msp_peptide.get()->getSequenceLi();
673 one_psm.proforma = msp_peptide.get()->toProForma();
674 one_psm.protein_list = m_proteinList;
675
676
677 one_psm.cbor_eval.insert(QString("aligned_rt"), m_line.aligned_rt);
678 one_psm.cbor_eval.insert(QString("calcmass"), m_line.calcmass);
679 one_psm.cbor_eval.insert(QString("delta_best"), m_line.delta_best);
680 one_psm.cbor_eval.insert(QString("delta_mobility"), m_line.delta_mobility);
681 one_psm.cbor_eval.insert(QString("delta_next"), m_line.delta_next);
682 one_psm.cbor_eval.insert(QString("delta_rt_model"), m_line.delta_rt_model);
683 one_psm.cbor_eval.insert(QString("fragment_ppm"), m_line.fragment_ppm);
684 one_psm.cbor_eval.insert(QString("hyperscore"), m_line.hyperscore);
685 one_psm.cbor_eval.insert(QString("ion_mobility"), m_line.ion_mobility);
686 one_psm.cbor_eval.insert(QString("isotope_error"), m_line.isotope_error);
687 one_psm.cbor_eval.insert(QString("label"), m_line.label);
688 one_psm.cbor_eval.insert(QString("longest_b"), (qint64)m_line.longest_b);
689 one_psm.cbor_eval.insert(QString("longest_y"), (qint64)m_line.longest_y);
690 one_psm.cbor_eval.insert(QString("longest_y_pct"), m_line.longest_y_pct);
691 one_psm.cbor_eval.insert(QString("matched_intensity_pct"), m_line.matched_intensity_pct);
692 one_psm.cbor_eval.insert(QString("matched_peaks"), (qint64)m_line.matched_peaks);
693 one_psm.cbor_eval.insert(QString("missed_cleavages"), m_line.missed_cleavages);
694 one_psm.cbor_eval.insert(QString("ms2_intensity"), m_line.ms2_intensity);
695 one_psm.cbor_eval.insert(QString("peptide_len"), (qint64)m_line.peptide_len);
696 one_psm.cbor_eval.insert(QString("peptide_q"), m_line.peptide_q);
697 one_psm.cbor_eval.insert(QString("poisson"), m_line.poisson);
698 one_psm.cbor_eval.insert(QString("posterior_error"), m_line.posterior_error);
699 one_psm.cbor_eval.insert(QString("precursor_ppm"), m_line.precursor_ppm);
700 one_psm.cbor_eval.insert(QString("predicted_mobility"), m_line.predicted_mobility);
701 one_psm.cbor_eval.insert(QString("predicted_rt"), m_line.predicted_rt);
702 one_psm.cbor_eval.insert(QString("protein_q"), m_line.protein_q);
703 one_psm.cbor_eval.insert(QString("rank"), m_line.rank);
704 one_psm.cbor_eval.insert(QString("sage_discriminant_score"), m_line.sage_discriminant_score);
705 one_psm.cbor_eval.insert(QString("scored_candidates"), (qint64)m_line.scored_candidates);
706 one_psm.cbor_eval.insert(QString("semi_enzymatic"), m_line.semi_enzymatic);
707 one_psm.cbor_eval.insert(QString("spectrum_q"), m_line.spectrum_q);
708
709 current_cbor_scan_p->psm_list.emplace_back(one_psm);
710
711
712 std::size_t progress = m_lineNumber / 10000;
713 if(progress > m_progressIndex)
714 {
716 {
718 QObject::tr("Sage TSV data reading process interrupted"));
719 }
720 m_progressIndex = progress;
721 mp_monitor->setStatus(QString("%1K ").arg(m_progressIndex * 10));
722 }
723}
virtual void setStatus(const QString &status)=0
current status of the process
virtual bool shouldIstop()=0
should the procces be stopped ? If true, then cancel process Use this function at strategic point of ...
const pappso_double MHPLUS(1.007276466879)

References pappso::cbor::psm::SageTsvHandler::Line::aligned_rt, pappso::cbor::psm::SageTsvHandler::Line::calcmass, pappso::cbor::psm::SageTsvHandler::Psm::cbor_eval, pappso::cbor::psm::SageTsvHandler::Scan::cbor_id, pappso::cbor::psm::SageTsvHandler::Line::charge, pappso::cbor::psm::SageTsvHandler::Line::delta_best, pappso::cbor::psm::SageTsvHandler::Line::delta_mobility, pappso::cbor::psm::SageTsvHandler::Line::delta_next, pappso::cbor::psm::SageTsvHandler::Line::delta_rt_model, pappso::cbor::psm::SageTsvHandler::Line::expmass, pappso::cbor::psm::SageTsvHandler::Line::fragment_ppm, pappso::cbor::psm::SageTsvHandler::Line::hyperscore, pappso::cbor::psm::PsmProteinMap::insert(), pappso::cbor::psm::SageTsvHandler::Line::ion_mobility, pappso::cbor::psm::SageTsvHandler::Line::isotope_error, pappso::cbor::psm::SageTsvHandler::Line::label, pappso::cbor::psm::SageTsvHandler::Line::longest_b, pappso::cbor::psm::SageTsvHandler::Line::longest_y, pappso::cbor::psm::SageTsvHandler::Line::longest_y_pct, m_line, m_lineNumber, m_progressIndex, m_proteinList, m_psmProteinMap, m_scanNumber, m_scanNumberIsOk, m_spectrumIndex, m_spectrumNativeId, pappso::cbor::psm::SageTsvHandler::Line::matched_intensity_pct, pappso::cbor::psm::SageTsvHandler::Line::matched_peaks, pappso::MHPLUS(), pappso::cbor::psm::SageTsvHandler::Line::missed_cleavages, mp_currentSample, mp_monitor, pappso::cbor::psm::SageTsvHandler::Line::ms2_intensity, msp_peptide, pappso::cbor::psm::SageTsvHandler::Line::peptide_len, pappso::cbor::psm::SageTsvHandler::Line::peptide_q, pappso::cbor::psm::SageTsvHandler::Psm::peptide_sequence_li, pappso::cbor::psm::SageTsvHandler::Line::poisson, pappso::cbor::psm::SageTsvHandler::Line::posterior_error, pappso::cbor::psm::SageTsvHandler::Line::precursor_ppm, pappso::cbor::psm::SageTsvHandler::Line::predicted_mobility, pappso::cbor::psm::SageTsvHandler::Line::predicted_rt, pappso::cbor::psm::SageTsvHandler::Psm::proforma, pappso::cbor::psm::SageTsvHandler::Psm::protein_list, pappso::cbor::psm::SageTsvHandler::Line::protein_q, pappso::cbor::psm::PsmProtein::protein_sp, pappso::cbor::psm::SageTsvHandler::Scan::psm_list, pappso::cbor::psm::SageTsvHandler::Line::rank, pappso::cbor::psm::SageTsvHandler::Line::rt, pappso::cbor::psm::SageTsvHandler::Line::sage_discriminant_score, pappso::cbor::psm::SageTsvHandler::Sample::scan_map, pappso::cbor::psm::SageTsvHandler::Line::scored_candidates, pappso::cbor::psm::SageTsvHandler::Line::semi_enzymatic, pappso::UiMonitorInterface::setStatus(), pappso::UiMonitorInterface::shouldIstop(), and pappso::cbor::psm::SageTsvHandler::Line::spectrum_q.

Referenced by endLine().

◆ setCell()

void pappso::cbor::psm::SageTsvHandler::setCell ( const OdsCell &  cell)
overridevirtual

callback that report the content of the current cell in a dedicated Cell object. Override it if you need to retrieve cell content.

Definition at line 85 of file sagetsvhandler.cpp.

86{
87 if(m_lineNumber == 0)
88 {
89 // header
90 QString tag = cell.getStringValue();
91 if(tag == "psm_id")
92 {
94 }
95 else if(tag == "peptide")
96 {
98 }
99 else if(tag == "proteins")
100 {
102 }
103 else if(tag == "protein_groups")
104 {
106 }
107 else if(tag == "num_protein_groups")
108 {
110 }
111 else if(tag == "num_proteins")
112 {
114 }
115 else if(tag == "filename")
116 {
118 }
119 else if(tag == "scannr")
120 {
122 }
123 else if(tag == "rank")
124 {
126 }
127 else if(tag == "label")
128 {
130 }
131 else if(tag == "expmass")
132 {
134 }
135
136 else if(tag == "calcmass")
137 {
139 }
140 else if(tag == "charge")
141 {
143 }
144 else if(tag == "peptide_len")
145 {
147 }
148 else if(tag == "missed_cleavages")
149 {
151 }
152 else if(tag == "semi_enzymatic")
153 {
155 }
156 else if(tag == "isotope_error")
157 {
159 }
160 else if(tag == "precursor_ppm")
161 {
163 }
164 else if(tag == "fragment_ppm")
165 {
167 }
168 else if(tag == "hyperscore")
169 {
171 }
172 else if(tag == "delta_next")
173 {
175 }
176 else if(tag == "delta_best")
177 {
179 }
180 else if(tag == "rt")
181 {
182 m_columnTypeList.push_back(Columns::rt);
183 }
184 else if(tag == "aligned_rt")
185 {
187 }
188 else if(tag == "predicted_rt")
189 {
191 }
192 else if(tag == "delta_rt_model")
193 {
195 }
196 else if(tag == "ion_mobility")
197 {
199 }
200 else if(tag == "predicted_mobility")
201 {
203 }
204 else if(tag == "delta_mobility")
205 {
207 }
208 else if(tag == "matched_peaks")
209 {
211 }
212 else if(tag == "longest_b")
213 {
215 }
216 else if(tag == "longest_y")
217 {
219 }
220 else if(tag == "longest_y_pct")
221 {
223 }
224 else if(tag == "matched_intensity_pct")
225 {
227 }
228 else if(tag == "scored_candidates")
229 {
231 }
232 else if(tag == "poisson")
233 {
235 }
236 else if(tag == "sage_discriminant_score")
237 {
239 }
240 else if(tag == "posterior_error")
241 {
243 }
244 else if(tag == "spectrum_q")
245 {
247 }
248 else if(tag == "peptide_q")
249 {
251 }
252 else if(tag == "protein_q")
253 {
255 }
256 else if(tag == "protein_group_q")
257 {
259 }
260 else if(tag == "ms2_intensity")
261 {
263 }
264 else
265 {
266 throw pappso::ExceptionNotPossible(QObject::tr("column \"%1\" not defined").arg(tag));
267 }
268 }
269 else
270 {
271 if(m_columnNumber >= m_columnTypeList.size())
272 {
274 QObject::tr("the value %1 is out of range").arg(cell.getStringValue()));
275 }
277 switch(column_type)
278 {
279 case Columns::psm_id:
280 break;
282 break;
284 break;
286 break;
287 case Columns::peptide:
288 parsePeptide(cell.toString());
289 break;
291 parseProteins(cell.toString());
292 break;
294 if((std::size_t)cell.getDoubleValue() != (std::size_t)m_proteinList.size())
295 {
297 QObject::tr("column \"num_proteins\"!=%1").arg(m_proteinList.size()));
298 }
299 break;
301 parseMsRunFilename(cell.toString());
302 break;
303 case Columns::scannr:
304 parseScanNrColumn(cell.toString());
305 break;
306 case Columns::rank:
307 m_line.rank = cell.getDoubleValue();
308 break;
309 case Columns::label:
310 m_line.label = cell.getDoubleValue();
311 break;
312 case Columns::expmass:
313 m_line.expmass = cell.getDoubleValue();
314 break;
316 m_line.calcmass = cell.getDoubleValue();
317 break;
318 case Columns::charge:
319 m_line.charge = cell.getDoubleValue();
320 break;
322 m_line.peptide_len = cell.getDoubleValue();
323 break;
325 m_line.missed_cleavages = cell.getDoubleValue();
326 break;
328 m_line.semi_enzymatic = cell.getDoubleValue();
329 break;
331 m_line.isotope_error = cell.getDoubleValue();
332 break;
333
335 m_line.precursor_ppm = cell.getDoubleValue();
336 break;
338 m_line.fragment_ppm = cell.getDoubleValue();
339 break;
341 m_line.hyperscore = cell.getDoubleValue();
342 break;
344 m_line.delta_next = cell.getDoubleValue();
345 break;
347 m_line.delta_best = cell.getDoubleValue();
348 break;
349 case Columns::rt:
350 m_line.rt = cell.getDoubleValue() * 60; // to convert retention time in seconds
351 break;
353 m_line.aligned_rt = cell.getDoubleValue();
354 break;
356 m_line.predicted_rt = cell.getDoubleValue();
357 break;
359 m_line.delta_rt_model = cell.getDoubleValue();
360 break;
362 m_line.ion_mobility = cell.getDoubleValue();
363 break;
365 m_line.predicted_mobility = cell.getDoubleValue();
366 break;
368 m_line.delta_mobility = cell.getDoubleValue();
369 break;
371 m_line.matched_peaks = cell.getDoubleValue();
372 break;
374 m_line.longest_b = cell.getDoubleValue();
375 break;
377 m_line.longest_y = cell.getDoubleValue();
378 break;
380 m_line.longest_y_pct = cell.getDoubleValue();
381 break;
383 m_line.matched_intensity_pct = cell.getDoubleValue();
384 break;
386 m_line.scored_candidates = cell.getDoubleValue();
387 break;
388 case Columns::poisson:
389 m_line.poisson = cell.getDoubleValue();
390 break;
392 m_line.sage_discriminant_score = cell.getDoubleValue();
393 break;
395 m_line.posterior_error = cell.getDoubleValue();
396 break;
398 m_line.spectrum_q = cell.getDoubleValue();
399 break;
401 m_line.peptide_q = cell.getDoubleValue();
402 break;
404 m_line.protein_q = cell.getDoubleValue();
405 break;
407 m_line.ms2_intensity = cell.getDoubleValue();
408 break;
409 default:
410 qDebug() << "m_line.calcmass=" << m_line.calcmass;
412 QObject::tr("column type %1 not implemented").arg((std::uint8_t)column_type));
413 break;
414 }
415
416 /*
417
418 2333 TMISDSDYTEFENFTK
419 GRMZM2G018197_P01;GRMZM2G068952_P01;GRMZM5G822976_P01 3
420 20120906_balliau_extract_1_A01_urnb-1.mzML controllerType=0
421 controllerNumber=1 scan=12542 1 1 1926.8225 1926.8193 2 16 0 0
422 0.0 1.6471838 1.9796097 54.06803492297634 28.049970383419556 0.0 38.192993
423 0.76385987 0.7671368 0.0032769442 0.0 0.0 0.0 16 2 14 0.875 32.54396 380
424 -13.375352220427656 1.1570586 -34.13482 0.00016041065 0.00022231363
425 0.00040124074 1271951.1
426 */
427 }
429}
void parseProteins(const QString &proteins_str)
void parsePeptide(const QString &peptide_str)
void parseMsRunFilename(const QString &msrun_filename)
bool parseScanNrColumn(const QString &spectrum_string_id)
std::vector< Columns > m_columnTypeList

References aligned_rt, pappso::cbor::psm::SageTsvHandler::Line::aligned_rt, calcmass, pappso::cbor::psm::SageTsvHandler::Line::calcmass, charge, pappso::cbor::psm::SageTsvHandler::Line::charge, delta_best, pappso::cbor::psm::SageTsvHandler::Line::delta_best, delta_mobility, pappso::cbor::psm::SageTsvHandler::Line::delta_mobility, delta_next, pappso::cbor::psm::SageTsvHandler::Line::delta_next, delta_rt_model, pappso::cbor::psm::SageTsvHandler::Line::delta_rt_model, expmass, pappso::cbor::psm::SageTsvHandler::Line::expmass, filename, fragment_ppm, pappso::cbor::psm::SageTsvHandler::Line::fragment_ppm, hyperscore, pappso::cbor::psm::SageTsvHandler::Line::hyperscore, ion_mobility, pappso::cbor::psm::SageTsvHandler::Line::ion_mobility, isotope_error, pappso::cbor::psm::SageTsvHandler::Line::isotope_error, label, pappso::cbor::psm::SageTsvHandler::Line::label, longest_b, pappso::cbor::psm::SageTsvHandler::Line::longest_b, longest_y, pappso::cbor::psm::SageTsvHandler::Line::longest_y, longest_y_pct, pappso::cbor::psm::SageTsvHandler::Line::longest_y_pct, m_columnNumber, m_columnTypeList, m_line, m_lineNumber, m_proteinList, matched_intensity_pct, pappso::cbor::psm::SageTsvHandler::Line::matched_intensity_pct, matched_peaks, pappso::cbor::psm::SageTsvHandler::Line::matched_peaks, missed_cleavages, pappso::cbor::psm::SageTsvHandler::Line::missed_cleavages, ms2_intensity, pappso::cbor::psm::SageTsvHandler::Line::ms2_intensity, num_protein_groups, num_proteins, parseMsRunFilename(), parsePeptide(), parseProteins(), parseScanNrColumn(), peptide, peptide_len, pappso::cbor::psm::SageTsvHandler::Line::peptide_len, peptide_q, pappso::cbor::psm::SageTsvHandler::Line::peptide_q, poisson, pappso::cbor::psm::SageTsvHandler::Line::poisson, posterior_error, pappso::cbor::psm::SageTsvHandler::Line::posterior_error, precursor_ppm, pappso::cbor::psm::SageTsvHandler::Line::precursor_ppm, predicted_mobility, pappso::cbor::psm::SageTsvHandler::Line::predicted_mobility, predicted_rt, pappso::cbor::psm::SageTsvHandler::Line::predicted_rt, protein_group_q, protein_groups, protein_q, pappso::cbor::psm::SageTsvHandler::Line::protein_q, proteins, psm_id, rank, pappso::cbor::psm::SageTsvHandler::Line::rank, rt, pappso::cbor::psm::SageTsvHandler::Line::rt, sage_discriminant_score, pappso::cbor::psm::SageTsvHandler::Line::sage_discriminant_score, scannr, scored_candidates, pappso::cbor::psm::SageTsvHandler::Line::scored_candidates, semi_enzymatic, pappso::cbor::psm::SageTsvHandler::Line::semi_enzymatic, spectrum_q, and pappso::cbor::psm::SageTsvHandler::Line::spectrum_q.

◆ startLine()

void pappso::cbor::psm::SageTsvHandler::startLine ( )
overridevirtual

callback that indicates a new line start. Override it if needed.

Definition at line 432 of file sagetsvhandler.cpp.

433{
434 m_columnNumber = 0;
435 msp_peptide = nullptr;
436 m_proteinList.clear();
437 m_line = Line();
438}

References m_columnNumber, m_line, m_proteinList, and msp_peptide.

◆ startSheet()

void pappso::cbor::psm::SageTsvHandler::startSheet ( const QString &  sheet_name)
overridevirtual

callback that indicates the begining of a data sheet. Override it in order to retrieve information about the current data sheet.

Definition at line 445 of file sagetsvhandler.cpp.

446{
447 m_columnNumber = 0;
448 m_lineNumber = 0;
449 mp_monitor->setStatus(QObject::tr("reading Sage TSV file"));
450
452 {
453 throw pappso::ExceptionInterrupted(QObject::tr("Sage TSV data reading process interrupted"));
454 }
455}

References m_columnNumber, m_lineNumber, mp_monitor, pappso::UiMonitorInterface::setStatus(), and pappso::UiMonitorInterface::shouldIstop().

◆ writePsm()

void pappso::cbor::psm::SageTsvHandler::writePsm ( const Psm one_psm)
private

Definition at line 776 of file sagetsvhandler.cpp.

777{
779 m_sageReader.getCborStreamWriter().append("proforma");
780 m_sageReader.getCborStreamWriter().append(one_psm.proforma);
781 m_sageReader.getCborStreamWriter().append("protein_list");
782
783 QCborArray cbor_protein_list;
784 for(const QString &accession : one_psm.protein_list)
785 {
786 // qWarning() << "accession=" << accession;
787 QCborMap cbor_protein;
788 cbor_protein.insert(QString("accession"), accession);
789
790
791 // start/end positions
792 QString protein_sequence =
793 QString(m_psmProteinMap.getByAccession(accession).protein_sp.get()->getSequence())
794 .replace("L", "I");
795 int position = protein_sequence.indexOf(one_psm.peptide_sequence_li);
796
797 QCborArray positions;
798 while(position >= 0)
799 {
800 positions.push_back(position);
801 position = protein_sequence.indexOf(one_psm.peptide_sequence_li, position + 1);
802 }
803
804 cbor_protein.insert(QString("positions"), positions);
805
806 cbor_protein_list.append(cbor_protein);
807 }
808
809
810 QCborValue(cbor_protein_list).toCbor(m_sageReader.getCborStreamWriter());
811
812 m_sageReader.getCborStreamWriter().append("eval");
814 m_sageReader.getCborStreamWriter().append("sage");
815 QCborValue(one_psm.cbor_eval).toCbor(m_sageReader.getCborStreamWriter());
817
819}
const pappso::cbor::psm::PsmProtein & getByAccession(const QString &accession) const
retrieve a PsmProtein with its accession
pappso::cbor::CborStreamWriter & getCborStreamWriter() const
std::shared_ptr< Protein > protein_sp

References pappso::cbor::psm::SageTsvHandler::Psm::cbor_eval, pappso::cbor::psm::PsmProteinMap::getByAccession(), pappso::cbor::psm::SageReader::getCborStreamWriter(), m_psmProteinMap, m_sageReader, pappso::cbor::psm::SageTsvHandler::Psm::peptide_sequence_li, pappso::cbor::psm::SageTsvHandler::Psm::proforma, pappso::cbor::psm::SageTsvHandler::Psm::protein_list, and pappso::cbor::psm::PsmProtein::protein_sp.

Referenced by writeScan().

◆ writeSample()

void pappso::cbor::psm::SageTsvHandler::writeSample ( const Sample one_sample)
private

Definition at line 726 of file sagetsvhandler.cpp.

727{
729 m_sageReader.getCborStreamWriter().append("name");
730 one_sample.cbor_core_sample.value("name").toCbor(m_sageReader.getCborStreamWriter());
731
732 m_sageReader.getCborStreamWriter().append("identification_file_list");
733 one_sample.cbor_core_sample.value("identification_file_list")
735
736
737 m_sageReader.getCborStreamWriter().append("peaklist_file");
738 one_sample.cbor_core_sample.value("peaklist_file").toCbor(m_sageReader.getCborStreamWriter());
739 //"scan_list": [
740
741 m_sageReader.getCborStreamWriter().append("scan_list");
742 m_sageReader.getCborStreamWriter().startArray(one_sample.scan_map.size());
743 for(auto &it_scan : one_sample.scan_map)
744 {
745 writeScan(it_scan.second);
746 }
748
749
751}
void writeScan(const Scan &one_scan)

References pappso::cbor::psm::SageTsvHandler::Sample::cbor_core_sample, pappso::cbor::psm::SageReader::getCborStreamWriter(), m_sageReader, pappso::cbor::psm::SageTsvHandler::Sample::scan_map, and writeScan().

Referenced by writeSampleList().

◆ writeSampleList()

void pappso::cbor::psm::SageTsvHandler::writeSampleList ( )

Definition at line 63 of file sagetsvhandler.cpp.

64{
65 for(auto it_sample_map : m_sampleMap)
66 {
67 writeSample(it_sample_map.second);
68 }
69}
void writeSample(const Sample &one_sample)

References m_sampleMap, and writeSample().

Referenced by pappso::cbor::psm::SageReader::readTsvFile().

◆ writeScan()

void pappso::cbor::psm::SageTsvHandler::writeScan ( const Scan one_scan)
private

Definition at line 754 of file sagetsvhandler.cpp.

755{
757 m_sageReader.getCborStreamWriter().append("id");
758 QCborValue(one_scan.cbor_id).toCbor(m_sageReader.getCborStreamWriter());
759 m_sageReader.getCborStreamWriter().append("precursor");
760 QCborValue(one_scan.cbor_precursor).toCbor(m_sageReader.getCborStreamWriter());
761 m_sageReader.getCborStreamWriter().append("ms2");
762 QCborValue(one_scan.cbor_ms2).toCbor(m_sageReader.getCborStreamWriter());
763
764 m_sageReader.getCborStreamWriter().append("psm_list");
765 m_sageReader.getCborStreamWriter().startArray(one_scan.psm_list.size());
766 for(auto &it_psm : one_scan.psm_list)
767 {
768 writePsm(it_psm);
769 }
771
773}
void writePsm(const Psm &one_psm)

References pappso::cbor::psm::SageTsvHandler::Scan::cbor_id, pappso::cbor::psm::SageTsvHandler::Scan::cbor_ms2, pappso::cbor::psm::SageTsvHandler::Scan::cbor_precursor, pappso::cbor::psm::SageReader::getCborStreamWriter(), m_sageReader, pappso::cbor::psm::SageTsvHandler::Scan::psm_list, and writePsm().

Referenced by writeSample().

Member Data Documentation

◆ m_columnNumber

std::size_t pappso::cbor::psm::SageTsvHandler::m_columnNumber = 0
private

Definition at line 221 of file sagetsvhandler.h.

Referenced by setCell(), startLine(), and startSheet().

◆ m_columnTypeList

std::vector<Columns> pappso::cbor::psm::SageTsvHandler::m_columnTypeList
private

Definition at line 222 of file sagetsvhandler.h.

Referenced by setCell().

◆ m_decoyTag

QString pappso::cbor::psm::SageTsvHandler::m_decoyTag
private

Definition at line 232 of file sagetsvhandler.h.

Referenced by SageTsvHandler(), and parseProteins().

◆ m_line

Line pappso::cbor::psm::SageTsvHandler::m_line
private

Definition at line 231 of file sagetsvhandler.h.

Referenced by endLine(), recordLine(), setCell(), and startLine().

◆ m_lineNumber

std::size_t pappso::cbor::psm::SageTsvHandler::m_lineNumber = 0
private

Definition at line 220 of file sagetsvhandler.h.

Referenced by endLine(), recordLine(), setCell(), and startSheet().

◆ m_progressIndex

std::size_t pappso::cbor::psm::SageTsvHandler::m_progressIndex = 0
private

Definition at line 219 of file sagetsvhandler.h.

Referenced by recordLine().

◆ m_proteinList

QStringList pappso::cbor::psm::SageTsvHandler::m_proteinList
private

Definition at line 233 of file sagetsvhandler.h.

Referenced by parseProteins(), recordLine(), setCell(), and startLine().

◆ m_psmProteinMap

PsmProteinMap& pappso::cbor::psm::SageTsvHandler::m_psmProteinMap
private

Definition at line 217 of file sagetsvhandler.h.

Referenced by parseProteins(), recordLine(), and writePsm().

◆ m_sageReader

const SageReader& pappso::cbor::psm::SageTsvHandler::m_sageReader
private

Definition at line 216 of file sagetsvhandler.h.

Referenced by parseMsRunFilename(), writePsm(), writeSample(), and writeScan().

◆ m_sampleMap

std::map<QString, Sample> pappso::cbor::psm::SageTsvHandler::m_sampleMap
private

Definition at line 235 of file sagetsvhandler.h.

Referenced by parseMsRunFilename(), and writeSampleList().

◆ m_scanNumber

std::size_t pappso::cbor::psm::SageTsvHandler::m_scanNumber
private

Definition at line 228 of file sagetsvhandler.h.

Referenced by parseScanNrColumn(), and recordLine().

◆ m_scanNumberIsOk

bool pappso::cbor::psm::SageTsvHandler::m_scanNumberIsOk
private

Definition at line 229 of file sagetsvhandler.h.

Referenced by parseScanNrColumn(), and recordLine().

◆ m_spectrumIndex

std::size_t pappso::cbor::psm::SageTsvHandler::m_spectrumIndex
private

Definition at line 227 of file sagetsvhandler.h.

Referenced by parseScanNrColumn(), and recordLine().

◆ m_spectrumNativeId

QString pappso::cbor::psm::SageTsvHandler::m_spectrumNativeId
private

Definition at line 234 of file sagetsvhandler.h.

Referenced by parseScanNrColumn(), and recordLine().

◆ m_staticModificationList

std::vector<SageReader::SageModification> pappso::cbor::psm::SageTsvHandler::m_staticModificationList
private

Definition at line 225 of file sagetsvhandler.h.

Referenced by SageTsvHandler(), and parsePeptide().

◆ m_variableModificationList

std::vector<SageReader::SageModification> pappso::cbor::psm::SageTsvHandler::m_variableModificationList
private

Definition at line 226 of file sagetsvhandler.h.

Referenced by SageTsvHandler(), and parsePeptide().

◆ mp_currentSample

Sample* pappso::cbor::psm::SageTsvHandler::mp_currentSample
private

Definition at line 236 of file sagetsvhandler.h.

Referenced by parseMsRunFilename(), and recordLine().

◆ mp_monitor

pappso::UiMonitorInterface* pappso::cbor::psm::SageTsvHandler::mp_monitor = nullptr
private

Definition at line 218 of file sagetsvhandler.h.

Referenced by SageTsvHandler(), recordLine(), and startSheet().

◆ msp_peptide

pappso::PeptideSp pappso::cbor::psm::SageTsvHandler::msp_peptide
private

Definition at line 224 of file sagetsvhandler.h.

Referenced by parsePeptide(), recordLine(), and startLine().


The documentation for this class was generated from the following files: