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  Scan
struct  Sample

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,
56 proteins,
57 protein_groups,
58 num_proteins,
59 num_protein_groups,
60 filename,
61 scannr,
62 rank,
63 label,
64 expmass,
65 calcmass,
66 charge,
67 peptide_len,
68 missed_cleavages,
69 semi_enzymatic,
70 isotope_error,
71 precursor_ppm,
72 fragment_ppm,
73 hyperscore,
74 delta_next,
75 delta_best,
76 rt,
77 aligned_rt,
78 predicted_rt,
79 delta_rt_model,
80 ion_mobility,
81 predicted_mobility,
82 delta_mobility,
83 matched_peaks,
84 longest_b,
85 longest_y,
86 longest_y_pct,
87 matched_intensity_pct,
88 scored_candidates,
89 poisson,
90 sage_discriminant_score,
91 posterior_error,
92 spectrum_q,
93 peptide_q,
94 protein_q,
95 protein_group_q,
96 ms2_intensity,
97 };
@ rt
Retention time.
Definition types.h:251

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 48 of file sagetsvhandler.cpp.

51 : m_sageReader(sage_reader), m_psmProteinMap(psm_protein_map)
52{
53 mp_monitor = p_monitor;
54 m_staticModificationList = sage_reader.getStaticModificationList();
55 m_variableModificationList = sage_reader.getVariableModificationList();
56 m_decoyTag = sage_reader.getDecoyTag();
57}
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_psmProteinMap, m_sageReader, m_staticModificationList, m_variableModificationList, and mp_monitor.

◆ ~SageTsvHandler()

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

Destructor

Definition at line 59 of file sagetsvhandler.cpp.

60{
61}

Member Function Documentation

◆ endDocument()

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

Definition at line 442 of file sagetsvhandler.cpp.

443{
444}

◆ endLine()

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

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

Definition at line 73 of file sagetsvhandler.cpp.

References 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 81 of file sagetsvhandler.cpp.

82{
83}

◆ parseMsRunFilename()

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

Definition at line 584 of file sagetsvhandler.cpp.

585{
586
587
588 // find the sample :
589 auto it_insert = m_sampleMap.insert({msrun_filename, {}});
590 mp_currentSample = &(it_insert.first->second);
591 if(it_insert.second)
592 {
593 // new sample
594 it_insert.first->second.name = msrun_filename;
595 QCborMap ms_file;
596 QCborMap identification_file;
597
598 it_insert.first->second.cbor_core_sample.insert(QString("name"),
599 QFileInfo(msrun_filename).baseName());
600
601 // identification_file_list
602 QCborArray identification_file_list;
603 identification_file.insert(QString("name"), m_sageReader.getmJsonAbsoluteFilePath());
604 identification_file_list.push_back(identification_file);
605 it_insert.first->second.cbor_core_sample.insert(QString("identification_file_list"),
606 identification_file_list);
607
608
609 ms_file.insert(QString("name"), m_sageReader.getMzmlPath(msrun_filename));
610 it_insert.first->second.cbor_core_sample.insert(QString("peaklist_file"), ms_file);
611 }
612
613 /*
614 msp_msrun = m_sageReader.getSageFileReader().getMsRunSpWithFileName(msrun_filename);
615 qDebug() << msp_msrun.get()->getFileName();
616
617 msp_identificationSageJsonFileSp =
618 m_sageReader.getSageFileReader().getIdentificationSageJsonFileSpWithFileName(msrun_filename);
619
620 mp_identificationGroup =
621 m_sageReader.getSageFileReader().getIdentificationGroupPtrWithFileName(msrun_filename);
622 qDebug() << msp_msrun.get()->getFileName();
623 */
624}
std::map< QString, Sample > m_sampleMap

References m_sageReader, m_sampleMap, and mp_currentSample.

Referenced by setCell().

◆ parsePeptide()

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

Definition at line 459 of file sagetsvhandler.cpp.

460{
461 qDebug();
462 QString peptide_str_verif = peptide_str;
463 // fixed modifications :
464 for(SageReader::SageModification modif : m_staticModificationList)
465 {
466 qDebug() << modif.strModification;
467 qDebug() << modif.modification->getAccession();
468 peptide_str_verif = peptide_str_verif.replace(
469 modif.strModification, QString("[%1]").arg(modif.modification->getAccession()));
470 }
471 // variable modifications :
472 for(SageReader::SageModification modif : m_variableModificationList)
473 {
474 qDebug() << modif.strModification;
475 qDebug() << modif.modification->getAccession();
476 peptide_str_verif = peptide_str_verif.replace(
477 modif.strModification, QString("[%1]").arg(modif.modification->getAccession()));
478 }
479
480 qDebug() << peptide_str_verif;
481 // LPMFGC[+57.0216]NDATQVYK
483 qDebug();
484 // variable modifications :
485 /*
486 setVariableModifications(peptide_sp,
487 peptide_line.peptide_string_list.at(6));
488*/
489 qDebug() << msp_peptide.get()->toProForma();
490}
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 494 of file sagetsvhandler.cpp.

495{
496 m_proteinList.clear();
497 m_proteinList = proteins_str.split(";");
498 for(QString accession : m_proteinList)
499 {
500
501 PsmProtein psm_protein;
502 psm_protein.protein_sp = std::make_shared<pappso::Protein>(accession, "");
503 psm_protein.isTarget = true;
504 if(accession.startsWith(m_decoyTag))
505 {
506 psm_protein.isTarget = false;
507 }
508
509 m_psmProteinMap.insert(psm_protein);
510 }
511}

References 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 514 of file sagetsvhandler.cpp.

515{
516 m_spectrumNativeId = spectrum_string_id;
517 qDebug() << spectrum_string_id;
518 m_scanNumber = 0;
519 bool is_ok = false;
520 m_scanNumberIsOk = false;
521 // controllerType=0 controllerNumber=1 scan=176056
522 if(mp_currentSample->name.endsWith(".d"))
523 { // assume this is a Bruker's timTOF sample
524 // 200ngHeLaPASEF_2min_compressed.d 2005
525 std::size_t precursor_number = spectrum_string_id.toULongLong(&is_ok);
526 if(is_ok)
527 {
528 // precursor=2006 idxms2=4011
529 m_scanNumberIsOk = is_ok;
530 m_spectrumIndex = precursor_number * 2 + 1;
531 m_spectrumNativeId = QString("precursor=%1 idxms2=%2")
532 .arg(precursor_number + 1)
533 .arg(precursor_number * 2 + 1);
534 }
535 }
536
537 if(!is_ok)
538 {
539 QStringList scan_list = spectrum_string_id.split("scan=");
540 if(scan_list.size() == 2)
541 {
542 // we bet that there is a scan number, easy to parse
543 m_scanNumber = scan_list.at(1).toULongLong(&is_ok);
544 m_scanNumberIsOk = is_ok;
545 if(m_scanNumber > 0)
547 }
548 if(is_ok == false)
549 {
550 ;
551 QStringList scan_list = spectrum_string_id.split(QRegularExpression("[^\\d]"));
552 if(scan_list.size() == 2)
553 {
554 m_scanNumber = scan_list.at(0).toULongLong(&is_ok);
555 m_scanNumberIsOk = is_ok;
556 if(m_scanNumber > 0)
558 }
559 /*
560 if(msp_previousMsrun != msp_msrun)
561 {
562 mp_monitor->setStatus(
563 QObject::tr("Reading mz data file %1").arg(msp_msrun.get()->getFileName()));
564 msp_previousMsrun = msp_msrun;
565 }
566
567 pappso::MsRunReader *msrunreader_p = msp_msrun.get()->getMsRunReaderSPtr().get();
568 if(msrunreader_p->getMsRunId()->getMsDataFormat() == pappso::MsDataFormat::brukerTims)
569 {
570 m_spectrumIndex = spectrum_string_id.toInt() * 2 - 1;
571 }
572 else
573 {
574 m_spectrumIndex =
575 msrunreader_p->spectrumStringIdentifier2SpectrumIndex(spectrum_string_id);
576 }*/
577 }
578 }
579 qDebug() << spectrum_string_id;
580 return is_ok;
581}

References m_scanNumber, m_scanNumberIsOk, m_spectrumIndex, m_spectrumNativeId, and mp_currentSample.

Referenced by setCell().

◆ recordLine()

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

Definition at line 627 of file sagetsvhandler.cpp.

628{
629 qDebug();
630
631 for(const QString &accession : m_proteinList)
632 {
633 PsmProtein psm_protein;
634 psm_protein.protein_sp = std::make_shared<pappso::Protein>(accession, "");
635
636 QCborMap sage_eval;
637 sage_eval.insert(QString("protein_q"), m_line.protein_q);
638
639 auto it = m_psmProteinMap.insert(psm_protein);
640 it.first->second.cborEval.insert(QString("sage"), sage_eval);
641 }
642 /*
643 PeptideEvidence pe(msp_msrun.get(), m_spectrumIndex, true);
644 pe.setCharge(m_line.charge);
645 pe.setChecked(true);
646 pe.setExperimentalMass(m_line.expmass);
647 pe.setPeptideXtpSp(msp_peptide);
648 pe.setIdentificationDataSource(msp_identificationSageJsonFileSp.get());
649 pe.setIdentificationEngine(m_identificationEngine);
650 pe.setRetentionTime(m_line.rt);
651 pe.setParam(PeptideEvidenceParam::tandem_hyperscore, m_line.hyperscore);
652 pe.setParam(PeptideEvidenceParam::sage_sage_discriminant_score,
653 m_line.sage_discriminant_score);
654 pe.setParam(PeptideEvidenceParam::sage_peptide_q, m_line.peptide_q);
655 pe.setParam(PeptideEvidenceParam::sage_posterior_error, m_line.posterior_error);
656 pe.setParam(PeptideEvidenceParam::sage_spectrum_q, m_line.spectrum_q);
657 pe.setParam(PeptideEvidenceParam::sage_predicted_rt, m_line.predicted_rt);
658 pe.setParam(PeptideEvidenceParam::sage_isotope_error, m_line.isotope_error);
659
660
661 PeptideMatch peptide_match;
662 // peptide_match.setStart(mz_peptide_evidence.start);
663 peptide_match.setPeptideEvidenceSp(
664 msp_identificationSageJsonFileSp.get()->getPeptideEvidenceStore().getInstance(&pe));
665 */
666
667 // find the scan in sample
668 auto it_insert = mp_currentSample->scan_map.insert({m_spectrumNativeId, Scan()});
669 Scan *current_cbor_scan_p = &(it_insert.first->second);
670 if(it_insert.second)
671 {
672 // new scan
673 QCborMap &scan_id = it_insert.first->second.cbor_id;
675 {
676 scan_id.insert(QString("index"), (qint64)m_spectrumIndex);
677 if(m_scanNumber > 0)
678 scan_id.insert(QString("scan"), (qint64)m_scanNumber);
679 }
680 scan_id.insert(QString("native_id"), m_spectrumNativeId);
681
682 QCborMap &scan_ms2 = it_insert.first->second.cbor_ms2;
683 scan_ms2.insert(QString("rt"), m_line.rt);
684
685 QCborMap &scan_precursor = it_insert.first->second.cbor_precursor;
686 scan_precursor.insert(QString("z"), m_line.charge);
687 double mh = m_line.expmass + MHPLUS;
688 scan_precursor.insert(QString("mh"), mh);
689 double exp_mz = (m_line.expmass + (MHPLUS * m_line.charge)) / m_line.charge;
690 scan_precursor.insert(QString("mz"), exp_mz);
691 }
692
693 Psm one_psm;
694 one_psm.peptide_sequence_li = msp_peptide.get()->getSequenceLi();
695 one_psm.proforma = msp_peptide.get()->toProForma();
696 one_psm.protein_list = m_proteinList;
697
698
699 one_psm.cbor_eval.insert(QString("aligned_rt"), m_line.aligned_rt);
700 one_psm.cbor_eval.insert(QString("calcmass"), m_line.calcmass);
701 one_psm.cbor_eval.insert(QString("delta_best"), m_line.delta_best);
702 one_psm.cbor_eval.insert(QString("delta_mobility"), m_line.delta_mobility);
703 one_psm.cbor_eval.insert(QString("delta_next"), m_line.delta_next);
704 one_psm.cbor_eval.insert(QString("delta_rt_model"), m_line.delta_rt_model);
705 one_psm.cbor_eval.insert(QString("fragment_ppm"), m_line.fragment_ppm);
706 one_psm.cbor_eval.insert(QString("hyperscore"), m_line.hyperscore);
707 one_psm.cbor_eval.insert(QString("ion_mobility"), m_line.ion_mobility);
708 one_psm.cbor_eval.insert(QString("isotope_error"), m_line.isotope_error);
709 one_psm.cbor_eval.insert(QString("label"), m_line.label);
710 one_psm.cbor_eval.insert(QString("longest_b"), (qint64)m_line.longest_b);
711 one_psm.cbor_eval.insert(QString("longest_y"), (qint64)m_line.longest_y);
712 one_psm.cbor_eval.insert(QString("longest_y_pct"), m_line.longest_y_pct);
713 one_psm.cbor_eval.insert(QString("matched_intensity_pct"), m_line.matched_intensity_pct);
714 one_psm.cbor_eval.insert(QString("matched_peaks"), (qint64)m_line.matched_peaks);
715 one_psm.cbor_eval.insert(QString("missed_cleavages"), m_line.missed_cleavages);
716 one_psm.cbor_eval.insert(QString("ms2_intensity"), m_line.ms2_intensity);
717 one_psm.cbor_eval.insert(QString("peptide_len"), (qint64)m_line.peptide_len);
718 one_psm.cbor_eval.insert(QString("peptide_q"), m_line.peptide_q);
719 one_psm.cbor_eval.insert(QString("poisson"), m_line.poisson);
720 one_psm.cbor_eval.insert(QString("posterior_error"), m_line.posterior_error);
721 one_psm.cbor_eval.insert(QString("precursor_ppm"), m_line.precursor_ppm);
722 one_psm.cbor_eval.insert(QString("predicted_mobility"), m_line.predicted_mobility);
723 one_psm.cbor_eval.insert(QString("predicted_rt"), m_line.predicted_rt);
724 one_psm.cbor_eval.insert(QString("protein_q"), m_line.protein_q);
725 one_psm.cbor_eval.insert(QString("rank"), m_line.rank);
726 one_psm.cbor_eval.insert(QString("sage_discriminant_score"), m_line.sage_discriminant_score);
727 one_psm.cbor_eval.insert(QString("scored_candidates"), (qint64)m_line.scored_candidates);
728 one_psm.cbor_eval.insert(QString("semi_enzymatic"), m_line.semi_enzymatic);
729 one_psm.cbor_eval.insert(QString("spectrum_q"), m_line.spectrum_q);
730
731 current_cbor_scan_p->psm_list.emplace_back(one_psm);
732
733
734 std::size_t progress = m_lineNumber / 10000;
735 if(progress > m_progressIndex)
736 {
737 if(mp_monitor->shouldIstop())
738 {
739 throw pappso::ExceptionInterrupted(
740 QObject::tr("Sage TSV data reading process interrupted"));
741 }
742 m_progressIndex = progress;
743 mp_monitor->setStatus(QString("%1K ").arg(m_progressIndex * 10));
744 }
745}
const pappso_double MHPLUS(1.007276466879)

References pappso::cbor::psm::SageTsvHandler::Psm::cbor_eval, m_line, m_lineNumber, m_progressIndex, m_proteinList, m_psmProteinMap, m_scanNumber, m_scanNumberIsOk, m_spectrumIndex, m_spectrumNativeId, pappso::MHPLUS(), mp_currentSample, mp_monitor, msp_peptide, pappso::cbor::psm::SageTsvHandler::Psm::peptide_sequence_li, pappso::cbor::psm::SageTsvHandler::Psm::proforma, pappso::cbor::psm::SageTsvHandler::Psm::protein_list, pappso::cbor::psm::PsmProtein::protein_sp, and pappso::cbor::psm::SageTsvHandler::Scan::psm_list.

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 86 of file sagetsvhandler.cpp.

87{
88 if(m_lineNumber == 0)
89 {
90 // header
91 QString tag = cell.getStringValue();
92 if(tag == "psm_id")
93 {
95 }
96 else if(tag == "peptide")
97 {
99 }
100 else if(tag == "proteins")
101 {
103 }
104 else if(tag == "protein_groups")
105 {
107 }
108 else if(tag == "num_protein_groups")
109 {
111 }
112 else if(tag == "num_proteins")
113 {
115 }
116 else if(tag == "filename")
117 {
119 }
120 else if(tag == "scannr")
121 {
123 }
124 else if(tag == "rank")
125 {
127 }
128 else if(tag == "label")
129 {
131 }
132 else if(tag == "expmass")
133 {
135 }
136
137 else if(tag == "calcmass")
138 {
140 }
141 else if(tag == "charge")
142 {
144 }
145 else if(tag == "peptide_len")
146 {
148 }
149 else if(tag == "missed_cleavages")
150 {
152 }
153 else if(tag == "semi_enzymatic")
154 {
156 }
157 else if(tag == "isotope_error")
158 {
160 }
161 else if(tag == "precursor_ppm")
162 {
164 }
165 else if(tag == "fragment_ppm")
166 {
168 }
169 else if(tag == "hyperscore")
170 {
172 }
173 else if(tag == "delta_next")
174 {
176 }
177 else if(tag == "delta_best")
178 {
180 }
181 else if(tag == "rt")
182 {
183 m_columnTypeList.push_back(Columns::rt);
184 }
185 else if(tag == "aligned_rt")
186 {
188 }
189 else if(tag == "predicted_rt")
190 {
192 }
193 else if(tag == "delta_rt_model")
194 {
196 }
197 else if(tag == "ion_mobility")
198 {
200 }
201 else if(tag == "predicted_mobility")
202 {
204 }
205 else if(tag == "delta_mobility")
206 {
208 }
209 else if(tag == "matched_peaks")
210 {
212 }
213 else if(tag == "longest_b")
214 {
216 }
217 else if(tag == "longest_y")
218 {
220 }
221 else if(tag == "longest_y_pct")
222 {
224 }
225 else if(tag == "matched_intensity_pct")
226 {
228 }
229 else if(tag == "scored_candidates")
230 {
232 }
233 else if(tag == "poisson")
234 {
236 }
237 else if(tag == "sage_discriminant_score")
238 {
240 }
241 else if(tag == "posterior_error")
242 {
244 }
245 else if(tag == "spectrum_q")
246 {
248 }
249 else if(tag == "peptide_q")
250 {
252 }
253 else if(tag == "protein_q")
254 {
256 }
257 else if(tag == "protein_group_q")
258 {
260 }
261 else if(tag == "ms2_intensity")
262 {
264 }
265 else
266 {
267 throw pappso::ExceptionNotPossible(QObject::tr("column \"%1\" not defined").arg(tag));
268 }
269 }
270 else
271 {
272 if(m_columnNumber >= m_columnTypeList.size())
273 {
274 throw pappso::ExceptionOutOfRange(
275 QObject::tr("the value %1 is out of range").arg(cell.getStringValue()));
276 }
278 switch(column_type)
279 {
280 case Columns::psm_id:
281 break;
283 break;
285 break;
287 break;
288 case Columns::peptide:
289 parsePeptide(cell.toString());
290 break;
292 parseProteins(cell.toString());
293 break;
295 if((std::size_t)cell.getDoubleValue() != (std::size_t)m_proteinList.size())
296 {
297 throw pappso::PappsoException(
298 QObject::tr("column \"num_proteins\"!=%1").arg(m_proteinList.size()));
299 }
300 break;
302 parseMsRunFilename(cell.toString());
303 break;
304 case Columns::scannr:
305 parseScanNrColumn(cell.toString());
306 break;
307 case Columns::rank:
308 m_line.rank = cell.getDoubleValue();
309 break;
310 case Columns::label:
311 m_line.label = cell.getDoubleValue();
312 break;
313 case Columns::expmass:
314 m_line.expmass = cell.getDoubleValue();
315 break;
317 m_line.calcmass = cell.getDoubleValue();
318 break;
319 case Columns::charge:
320 m_line.charge = cell.getDoubleValue();
321 break;
323 m_line.peptide_len = cell.getDoubleValue();
324 break;
326 m_line.missed_cleavages = cell.getDoubleValue();
327 break;
329 m_line.semi_enzymatic = cell.getDoubleValue();
330 break;
332 m_line.isotope_error = cell.getDoubleValue();
333 break;
334
336 m_line.precursor_ppm = cell.getDoubleValue();
337 break;
339 m_line.fragment_ppm = cell.getDoubleValue();
340 break;
342 m_line.hyperscore = cell.getDoubleValue();
343 break;
345 m_line.delta_next = cell.getDoubleValue();
346 break;
348 m_line.delta_best = cell.getDoubleValue();
349 break;
350 case Columns::rt:
351 m_line.rt = cell.getDoubleValue() * 60; // to convert retention time in seconds
352 break;
354 m_line.aligned_rt = cell.getDoubleValue();
355 break;
357 m_line.predicted_rt = cell.getDoubleValue();
358 break;
360 m_line.delta_rt_model = cell.getDoubleValue();
361 break;
363 m_line.ion_mobility = cell.getDoubleValue();
364 break;
366 m_line.predicted_mobility = cell.getDoubleValue();
367 break;
369 m_line.delta_mobility = cell.getDoubleValue();
370 break;
372 m_line.matched_peaks = cell.getDoubleValue();
373 break;
375 m_line.longest_b = cell.getDoubleValue();
376 break;
378 m_line.longest_y = cell.getDoubleValue();
379 break;
381 m_line.longest_y_pct = cell.getDoubleValue();
382 break;
384 m_line.matched_intensity_pct = cell.getDoubleValue();
385 break;
387 m_line.scored_candidates = cell.getDoubleValue();
388 break;
389 case Columns::poisson:
390 m_line.poisson = cell.getDoubleValue();
391 break;
393 m_line.sage_discriminant_score = cell.getDoubleValue();
394 break;
396 m_line.posterior_error = cell.getDoubleValue();
397 break;
399 m_line.spectrum_q = cell.getDoubleValue();
400 break;
402 m_line.peptide_q = cell.getDoubleValue();
403 break;
405 m_line.protein_q = cell.getDoubleValue();
406 break;
408 m_line.ms2_intensity = cell.getDoubleValue();
409 break;
410 default:
411 qDebug() << "m_line.calcmass=" << m_line.calcmass;
412 throw pappso::ExceptionNotImplemented(
413 QObject::tr("column type %1 not implemented").arg((std::uint8_t)column_type));
414 break;
415 }
416
417 /*
418
419 2333 TMISDSDYTEFENFTK
420 GRMZM2G018197_P01;GRMZM2G068952_P01;GRMZM5G822976_P01 3
421 20120906_balliau_extract_1_A01_urnb-1.mzML controllerType=0
422 controllerNumber=1 scan=12542 1 1 1926.8225 1926.8193 2 16 0 0
423 0.0 1.6471838 1.9796097 54.06803492297634 28.049970383419556 0.0 38.192993
424 0.76385987 0.7671368 0.0032769442 0.0 0.0 0.0 16 2 14 0.875 32.54396 380
425 -13.375352220427656 1.1570586 -34.13482 0.00016041065 0.00022231363
426 0.00040124074 1271951.1
427 */
428 }
430}
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, calcmass, charge, delta_best, delta_mobility, delta_next, delta_rt_model, expmass, filename, fragment_ppm, hyperscore, ion_mobility, isotope_error, label, longest_b, longest_y, longest_y_pct, m_columnNumber, m_columnTypeList, m_line, m_lineNumber, m_proteinList, matched_intensity_pct, matched_peaks, missed_cleavages, ms2_intensity, num_protein_groups, num_proteins, parseMsRunFilename(), parsePeptide(), parseProteins(), parseScanNrColumn(), peptide, peptide_len, peptide_q, poisson, posterior_error, precursor_ppm, predicted_mobility, predicted_rt, protein_group_q, protein_groups, protein_q, proteins, psm_id, rank, rt, sage_discriminant_score, scannr, scored_candidates, semi_enzymatic, and spectrum_q.

◆ startLine()

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

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

Definition at line 433 of file sagetsvhandler.cpp.

434{
435 m_columnNumber = 0;
436 msp_peptide = nullptr;
437 m_proteinList.clear();
438 m_line = Line();
439}

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 446 of file sagetsvhandler.cpp.

447{
448 m_columnNumber = 0;
449 m_lineNumber = 0;
450 mp_monitor->setStatus(QObject::tr("reading Sage TSV file"));
451
452 if(mp_monitor->shouldIstop())
453 {
454 throw pappso::ExceptionInterrupted(QObject::tr("Sage TSV data reading process interrupted"));
455 }
456}

References m_columnNumber, m_lineNumber, and mp_monitor.

◆ writePsm()

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

Definition at line 798 of file sagetsvhandler.cpp.

799{
800 m_sageReader.getCborStreamWriter().startMap();
801 m_sageReader.getCborStreamWriter().append("proforma");
802 m_sageReader.getCborStreamWriter().append(one_psm.proforma);
803 m_sageReader.getCborStreamWriter().append("protein_list");
804
805 QCborArray cbor_protein_list;
806 for(const QString &accession : one_psm.protein_list)
807 {
808 // qWarning() << "accession=" << accession;
809 QCborMap cbor_protein;
810 cbor_protein.insert(QString("accession"), accession);
811
812
813 // start/end positions
814 QString protein_sequence =
815 QString(m_psmProteinMap.getByAccession(accession).protein_sp.get()->getSequence())
816 .replace("L", "I");
817 int position = protein_sequence.indexOf(one_psm.peptide_sequence_li);
818
819 QCborArray positions;
820 while(position >= 0)
821 {
822 positions.push_back(position);
823 position = protein_sequence.indexOf(one_psm.peptide_sequence_li, position + 1);
824 }
825
826 cbor_protein.insert(QString("positions"), positions);
827
828 cbor_protein_list.append(cbor_protein);
829 }
830
831
832 QCborValue(cbor_protein_list).toCbor(m_sageReader.getCborStreamWriter());
833
834 m_sageReader.getCborStreamWriter().append("eval");
835 m_sageReader.getCborStreamWriter().startMap();
836 m_sageReader.getCborStreamWriter().append("sage");
837 QCborValue(one_psm.cbor_eval).toCbor(m_sageReader.getCborStreamWriter());
838 m_sageReader.getCborStreamWriter().endMap();
839
840 m_sageReader.getCborStreamWriter().endMap();
841}

References pappso::cbor::psm::SageTsvHandler::Psm::cbor_eval, m_psmProteinMap, m_sageReader, pappso::cbor::psm::SageTsvHandler::Psm::peptide_sequence_li, pappso::cbor::psm::SageTsvHandler::Psm::proforma, and pappso::cbor::psm::SageTsvHandler::Psm::protein_list.

Referenced by writeScan().

◆ writeSample()

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

Definition at line 748 of file sagetsvhandler.cpp.

749{
750 m_sageReader.getCborStreamWriter().startMap();
751 m_sageReader.getCborStreamWriter().append("name");
752 one_sample.cbor_core_sample.value("name").toCbor(m_sageReader.getCborStreamWriter());
753
754 m_sageReader.getCborStreamWriter().append("identification_file_list");
755 one_sample.cbor_core_sample.value("identification_file_list")
756 .toCbor(m_sageReader.getCborStreamWriter());
757
758
759 m_sageReader.getCborStreamWriter().append("peaklist_file");
760 one_sample.cbor_core_sample.value("peaklist_file").toCbor(m_sageReader.getCborStreamWriter());
761 //"scan_list": [
762
763 m_sageReader.getCborStreamWriter().append("scan_list");
764 m_sageReader.getCborStreamWriter().startArray(one_sample.scan_map.size());
765 for(auto &it_scan : one_sample.scan_map)
766 {
767 writeScan(it_scan.second);
768 }
769 m_sageReader.getCborStreamWriter().endArray();
770
771
772 m_sageReader.getCborStreamWriter().endMap();
773}
void writeScan(const Scan &one_scan)

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

Referenced by writeSampleList().

◆ writeSampleList()

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

Definition at line 64 of file sagetsvhandler.cpp.

65{
66 for(auto it_sample_map : m_sampleMap)
67 {
68 writeSample(it_sample_map.second);
69 }
70}
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 776 of file sagetsvhandler.cpp.

777{
778 m_sageReader.getCborStreamWriter().startMap();
779 m_sageReader.getCborStreamWriter().append("id");
780 QCborValue(one_scan.cbor_id).toCbor(m_sageReader.getCborStreamWriter());
781 m_sageReader.getCborStreamWriter().append("precursor");
782 QCborValue(one_scan.cbor_precursor).toCbor(m_sageReader.getCborStreamWriter());
783 m_sageReader.getCborStreamWriter().append("ms2");
784 QCborValue(one_scan.cbor_ms2).toCbor(m_sageReader.getCborStreamWriter());
785
786 m_sageReader.getCborStreamWriter().append("psm_list");
787 m_sageReader.getCborStreamWriter().startArray(one_scan.psm_list.size());
788 for(auto &it_psm : one_scan.psm_list)
789 {
790 writePsm(it_psm);
791 }
792 m_sageReader.getCborStreamWriter().endArray();
793
794 m_sageReader.getCborStreamWriter().endMap();
795}
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, 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 SageTsvHandler(), parseProteins(), recordLine(), and writePsm().

◆ m_sageReader

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

◆ 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(), parseScanNrColumn(), 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: