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 SageReader & m_sageReader
PsmProteinMap & m_psmProteinMap
pappso::UiMonitorInterface * mp_monitor = nullptr
std::size_t m_progressIndex = 0
std::size_t m_lineNumber = 0
std::size_t m_columnNumber = 0
std::vector< Columns > m_columnTypeList
pappso::PeptideSp msp_peptide
std::vector< SageReader::SageModification > m_staticModificationList
std::vector< SageReader::SageModification > m_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, Sample > m_sampleMap
Sample * mp_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:240

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 50 of file sagetsvhandler.cpp.

53 : m_sageReader(sage_reader), m_psmProteinMap(psm_protein_map)
54{
55 mp_monitor = p_monitor;
56 m_staticModificationList = sage_reader.getStaticModificationList();
57 m_variableModificationList = sage_reader.getVariableModificationList();
58 m_decoyTag = sage_reader.getDecoyTag();
59}
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 61 of file sagetsvhandler.cpp.

62{
63}

Member Function Documentation

◆ endDocument()

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

Definition at line 444 of file sagetsvhandler.cpp.

445{
446}

◆ endLine()

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

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

Definition at line 75 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 83 of file sagetsvhandler.cpp.

84{
85}

◆ parseMsRunFilename()

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

Definition at line 587 of file sagetsvhandler.cpp.

588{
589
590
591 // find the sample :
592 auto it_insert = m_sampleMap.insert({msrun_filename, {}});
593 mp_currentSample = &(it_insert.first->second);
594 if(it_insert.second)
595 {
596 // new sample
597 it_insert.first->second.name = msrun_filename;
598 QCborMap ms_file;
599 QCborMap identification_file;
600
601 it_insert.first->second.cbor_core_sample.insert(QString("name"),
602 QFileInfo(msrun_filename).baseName());
603
604 // identification_file_list
605 QCborArray identification_file_list;
606 identification_file.insert(QString("name"), m_sageReader.getmJsonAbsoluteFilePath());
607 identification_file_list.push_back(identification_file);
608 it_insert.first->second.cbor_core_sample.insert(QString("identification_file_list"),
609 identification_file_list);
610
611
612 ms_file.insert(QString("name"), m_sageReader.getMzmlPath(msrun_filename));
613 it_insert.first->second.cbor_core_sample.insert(QString("peaklist_file"), ms_file);
614 }
615
616 /*
617 msp_msrun = m_sageReader.getSageFileReader().getMsRunSpWithFileName(msrun_filename);
618 qDebug() << msp_msrun.get()->getFileName();
619
620 msp_identificationSageJsonFileSp =
621 m_sageReader.getSageFileReader().getIdentificationSageJsonFileSpWithFileName(msrun_filename);
622
623 mp_identificationGroup =
624 m_sageReader.getSageFileReader().getIdentificationGroupPtrWithFileName(msrun_filename);
625 qDebug() << msp_msrun.get()->getFileName();
626 */
627}
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 461 of file sagetsvhandler.cpp.

462{
463 qDebug();
464 QString peptide_str_verif = peptide_str;
465 // fixed modifications :
466 for(SageReader::SageModification modif : m_staticModificationList)
467 {
468 qDebug() << modif.strModification;
469 qDebug() << modif.modification->getAccession();
470 peptide_str_verif = peptide_str_verif.replace(
471 modif.strModification, QString("[%1]").arg(modif.modification->getAccession()));
472 }
473 // variable modifications :
474 for(SageReader::SageModification modif : m_variableModificationList)
475 {
476 qDebug() << modif.strModification;
477 qDebug() << modif.modification->getAccession();
478 peptide_str_verif = peptide_str_verif.replace(
479 modif.strModification, QString("[%1]").arg(modif.modification->getAccession()));
480 }
481
482 qDebug() << peptide_str_verif;
483 // LPMFGC[+57.0216]NDATQVYK
485 qDebug();
486 // variable modifications :
487 /*
488 setVariableModifications(peptide_sp,
489 peptide_line.peptide_string_list.at(6));
490*/
491 qDebug() << msp_peptide.get()->toProForma();
492}
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 496 of file sagetsvhandler.cpp.

497{
498
499 m_proteinList.clear();
500 m_proteinList = proteins_str.split(";", Qt::SkipEmptyParts);
501 for(QString accession : m_proteinList)
502 {
503
504 PsmProtein psm_protein;
505 psm_protein.protein_sp = std::make_shared<pappso::Protein>(accession, "");
506 psm_protein.isTarget = true;
507 if(accession.startsWith(m_decoyTag))
508 {
509 psm_protein.isTarget = false;
510 }
511
512 m_psmProteinMap.insert(psm_protein);
513 }
514}

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 517 of file sagetsvhandler.cpp.

518{
519 m_spectrumNativeId = spectrum_string_id;
520 qDebug() << spectrum_string_id;
521 m_scanNumber = 0;
522 bool is_ok = false;
523 m_scanNumberIsOk = false;
524 // controllerType=0 controllerNumber=1 scan=176056
525 if(mp_currentSample->name.endsWith(".d"))
526 { // assume this is a Bruker's timTOF sample
527 // 200ngHeLaPASEF_2min_compressed.d 2005
528 std::size_t precursor_number = spectrum_string_id.toULongLong(&is_ok);
529 if(is_ok)
530 {
531 // precursor=2006 idxms2=4011
532 m_scanNumberIsOk = is_ok;
533 m_spectrumIndex = precursor_number * 2 + 1;
534 m_spectrumNativeId = QString("precursor=%1 idxms2=%2")
535 .arg(precursor_number + 1)
536 .arg(precursor_number * 2 + 1);
537 }
538 }
539
540 if(!is_ok)
541 {
542 QStringList scan_list = spectrum_string_id.split("scan=");
543 if(scan_list.size() == 2)
544 {
545 // we bet that there is a scan number, easy to parse
546 m_scanNumber = scan_list.at(1).toULongLong(&is_ok);
547 m_scanNumberIsOk = is_ok;
548 if(m_scanNumber > 0)
550 }
551 if(is_ok == false)
552 {
553 ;
554 QStringList scan_list = spectrum_string_id.split(QRegularExpression("[^\\d]"));
555 if(scan_list.size() == 2)
556 {
557 m_scanNumber = scan_list.at(0).toULongLong(&is_ok);
558 m_scanNumberIsOk = is_ok;
559 if(m_scanNumber > 0)
561 }
562 /*
563 if(msp_previousMsrun != msp_msrun)
564 {
565 mp_monitor->setStatus(
566 QObject::tr("Reading mz data file %1").arg(msp_msrun.get()->getFileName()));
567 msp_previousMsrun = msp_msrun;
568 }
569
570 pappso::MsRunReader *msrunreader_p = msp_msrun.get()->getMsRunReaderSPtr().get();
571 if(msrunreader_p->getMsRunId()->getMsDataFormat() == pappso::MsDataFormat::brukerTims)
572 {
573 m_spectrumIndex = spectrum_string_id.toInt() * 2 - 1;
574 }
575 else
576 {
577 m_spectrumIndex =
578 msrunreader_p->spectrumStringIdentifier2SpectrumIndex(spectrum_string_id);
579 }*/
580 }
581 }
582 qDebug() << spectrum_string_id;
583 return is_ok;
584}

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 630 of file sagetsvhandler.cpp.

631{
632 qDebug();
633
634 for(const QString &accession : m_proteinList)
635 {
636 PsmProtein psm_protein;
637 psm_protein.protein_sp = std::make_shared<pappso::Protein>(accession, "");
638
639 QCborMap sage_eval;
640 sage_eval.insert(QString("protein_q"), m_line.protein_q);
641
642 auto it = m_psmProteinMap.insert(psm_protein);
643 it.first->second.cborEval.insert(QString("sage"), sage_eval);
644 }
645 /*
646 PeptideEvidence pe(msp_msrun.get(), m_spectrumIndex, true);
647 pe.setCharge(m_line.charge);
648 pe.setChecked(true);
649 pe.setExperimentalMass(m_line.expmass);
650 pe.setPeptideXtpSp(msp_peptide);
651 pe.setIdentificationDataSource(msp_identificationSageJsonFileSp.get());
652 pe.setIdentificationEngine(m_identificationEngine);
653 pe.setRetentionTime(m_line.rt);
654 pe.setParam(PeptideEvidenceParam::tandem_hyperscore, m_line.hyperscore);
655 pe.setParam(PeptideEvidenceParam::sage_sage_discriminant_score,
656 m_line.sage_discriminant_score);
657 pe.setParam(PeptideEvidenceParam::sage_peptide_q, m_line.peptide_q);
658 pe.setParam(PeptideEvidenceParam::sage_posterior_error, m_line.posterior_error);
659 pe.setParam(PeptideEvidenceParam::sage_spectrum_q, m_line.spectrum_q);
660 pe.setParam(PeptideEvidenceParam::sage_predicted_rt, m_line.predicted_rt);
661 pe.setParam(PeptideEvidenceParam::sage_isotope_error, m_line.isotope_error);
662
663
664 PeptideMatch peptide_match;
665 // peptide_match.setStart(mz_peptide_evidence.start);
666 peptide_match.setPeptideEvidenceSp(
667 msp_identificationSageJsonFileSp.get()->getPeptideEvidenceStore().getInstance(&pe));
668 */
669
670 // find the scan in sample
671 auto it_insert = mp_currentSample->scan_map.insert({m_spectrumNativeId, Scan()});
672 Scan *current_cbor_scan_p = &(it_insert.first->second);
673 if(it_insert.second)
674 {
675 // new scan
676 QCborMap &scan_id = it_insert.first->second.cbor_id;
678 {
679 scan_id.insert(QString("index"), (qint64)m_spectrumIndex);
680 if(m_scanNumber > 0)
681 scan_id.insert(QString("scan"), (qint64)m_scanNumber);
682 }
683 scan_id.insert(QString("native_id"), m_spectrumNativeId);
684
685 QCborMap &scan_ms2 = it_insert.first->second.cbor_ms2;
686 scan_ms2.insert(QString("rt"), m_line.rt);
687
688 QCborMap &scan_precursor = it_insert.first->second.cbor_precursor;
689 scan_precursor.insert(QString("z"), m_line.charge);
690 double mh = m_line.expmass + MHPLUS;
691 scan_precursor.insert(QString("mh"), mh);
692 double exp_mz = (m_line.expmass + (MHPLUS * m_line.charge)) / m_line.charge;
693 scan_precursor.insert(QString("mz"), exp_mz);
694 }
695
696 Psm one_psm;
697 one_psm.peptide_sequence_li = msp_peptide.get()->getSequenceLi();
698 one_psm.proforma = msp_peptide.get()->toProForma();
699 one_psm.protein_list = m_proteinList;
700
701
702 one_psm.cbor_eval.insert(QString("aligned_rt"), m_line.aligned_rt);
703 one_psm.cbor_eval.insert(QString("calcmass"), m_line.calcmass);
704 one_psm.cbor_eval.insert(QString("delta_best"), m_line.delta_best);
705 one_psm.cbor_eval.insert(QString("delta_mobility"), m_line.delta_mobility);
706 one_psm.cbor_eval.insert(QString("delta_next"), m_line.delta_next);
707 one_psm.cbor_eval.insert(QString("delta_rt_model"), m_line.delta_rt_model);
708 one_psm.cbor_eval.insert(QString("fragment_ppm"), m_line.fragment_ppm);
709 one_psm.cbor_eval.insert(QString("hyperscore"), m_line.hyperscore);
710 one_psm.cbor_eval.insert(QString("ion_mobility"), m_line.ion_mobility);
711 one_psm.cbor_eval.insert(QString("isotope_error"), m_line.isotope_error);
712 one_psm.cbor_eval.insert(QString("label"), m_line.label);
713 one_psm.cbor_eval.insert(QString("longest_b"), (qint64)m_line.longest_b);
714 one_psm.cbor_eval.insert(QString("longest_y"), (qint64)m_line.longest_y);
715 one_psm.cbor_eval.insert(QString("longest_y_pct"), m_line.longest_y_pct);
716 one_psm.cbor_eval.insert(QString("matched_intensity_pct"), m_line.matched_intensity_pct);
717 one_psm.cbor_eval.insert(QString("matched_peaks"), (qint64)m_line.matched_peaks);
718 one_psm.cbor_eval.insert(QString("missed_cleavages"), m_line.missed_cleavages);
719 one_psm.cbor_eval.insert(QString("ms2_intensity"), m_line.ms2_intensity);
720 one_psm.cbor_eval.insert(QString("peptide_len"), (qint64)m_line.peptide_len);
721 one_psm.cbor_eval.insert(QString("peptide_q"), m_line.peptide_q);
722 one_psm.cbor_eval.insert(QString("poisson"), m_line.poisson);
723 one_psm.cbor_eval.insert(QString("posterior_error"), m_line.posterior_error);
724 one_psm.cbor_eval.insert(QString("precursor_ppm"), m_line.precursor_ppm);
725 one_psm.cbor_eval.insert(QString("predicted_mobility"), m_line.predicted_mobility);
726 one_psm.cbor_eval.insert(QString("predicted_rt"), m_line.predicted_rt);
727 one_psm.cbor_eval.insert(QString("protein_q"), m_line.protein_q);
728 one_psm.cbor_eval.insert(QString("rank"), m_line.rank);
729 one_psm.cbor_eval.insert(QString("sage_discriminant_score"), m_line.sage_discriminant_score);
730 one_psm.cbor_eval.insert(QString("scored_candidates"), (qint64)m_line.scored_candidates);
731 one_psm.cbor_eval.insert(QString("semi_enzymatic"), m_line.semi_enzymatic);
732 one_psm.cbor_eval.insert(QString("spectrum_q"), m_line.spectrum_q);
733
734 current_cbor_scan_p->psm_list.emplace_back(one_psm);
735
736
737 std::size_t progress = m_lineNumber / 10000;
738 if(progress > m_progressIndex)
739 {
740 if(mp_monitor->shouldIstop())
741 {
742 throw pappso::ExceptionInterrupted(
743 QObject::tr("Sage TSV data reading process interrupted"));
744 }
745 m_progressIndex = progress;
746 mp_monitor->setStatus(QString("%1K ").arg(m_progressIndex * 10));
747 }
748}
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 88 of file sagetsvhandler.cpp.

89{
90 if(m_lineNumber == 0)
91 {
92 // header
93 QString tag = cell.getStringValue();
94 if(tag == "psm_id")
95 {
97 }
98 else if(tag == "peptide")
99 {
101 }
102 else if(tag == "proteins")
103 {
105 }
106 else if(tag == "protein_groups")
107 {
109 }
110 else if(tag == "num_protein_groups")
111 {
113 }
114 else if(tag == "num_proteins")
115 {
117 }
118 else if(tag == "filename")
119 {
121 }
122 else if(tag == "scannr")
123 {
125 }
126 else if(tag == "rank")
127 {
129 }
130 else if(tag == "label")
131 {
133 }
134 else if(tag == "expmass")
135 {
137 }
138
139 else if(tag == "calcmass")
140 {
142 }
143 else if(tag == "charge")
144 {
146 }
147 else if(tag == "peptide_len")
148 {
150 }
151 else if(tag == "missed_cleavages")
152 {
154 }
155 else if(tag == "semi_enzymatic")
156 {
158 }
159 else if(tag == "isotope_error")
160 {
162 }
163 else if(tag == "precursor_ppm")
164 {
166 }
167 else if(tag == "fragment_ppm")
168 {
170 }
171 else if(tag == "hyperscore")
172 {
174 }
175 else if(tag == "delta_next")
176 {
178 }
179 else if(tag == "delta_best")
180 {
182 }
183 else if(tag == "rt")
184 {
185 m_columnTypeList.push_back(Columns::rt);
186 }
187 else if(tag == "aligned_rt")
188 {
190 }
191 else if(tag == "predicted_rt")
192 {
194 }
195 else if(tag == "delta_rt_model")
196 {
198 }
199 else if(tag == "ion_mobility")
200 {
202 }
203 else if(tag == "predicted_mobility")
204 {
206 }
207 else if(tag == "delta_mobility")
208 {
210 }
211 else if(tag == "matched_peaks")
212 {
214 }
215 else if(tag == "longest_b")
216 {
218 }
219 else if(tag == "longest_y")
220 {
222 }
223 else if(tag == "longest_y_pct")
224 {
226 }
227 else if(tag == "matched_intensity_pct")
228 {
230 }
231 else if(tag == "scored_candidates")
232 {
234 }
235 else if(tag == "poisson")
236 {
238 }
239 else if(tag == "sage_discriminant_score")
240 {
242 }
243 else if(tag == "posterior_error")
244 {
246 }
247 else if(tag == "spectrum_q")
248 {
250 }
251 else if(tag == "peptide_q")
252 {
254 }
255 else if(tag == "protein_q")
256 {
258 }
259 else if(tag == "protein_group_q")
260 {
262 }
263 else if(tag == "ms2_intensity")
264 {
266 }
267 else
268 {
269 throw pappso::ExceptionNotPossible(QObject::tr("column \"%1\" not defined").arg(tag));
270 }
271 }
272 else
273 {
274 if(m_columnNumber >= m_columnTypeList.size())
275 {
276 throw pappso::ExceptionOutOfRange(
277 QObject::tr("the value %1 is out of range").arg(cell.getStringValue()));
278 }
280 switch(column_type)
281 {
282 case Columns::psm_id:
283 break;
285 break;
287 break;
289 break;
290 case Columns::peptide:
291 parsePeptide(cell.toString());
292 break;
294 parseProteins(cell.toString());
295 break;
297 if((std::size_t)cell.getDoubleValue() != (std::size_t)m_proteinList.size())
298 {
299 throw pappso::PappsoException(
300 QObject::tr("column \"num_proteins\"!=%1").arg(m_proteinList.size()));
301 }
302 break;
304 parseMsRunFilename(cell.toString());
305 break;
306 case Columns::scannr:
307 parseScanNrColumn(cell.toString());
308 break;
309 case Columns::rank:
310 m_line.rank = cell.getDoubleValue();
311 break;
312 case Columns::label:
313 m_line.label = cell.getDoubleValue();
314 break;
315 case Columns::expmass:
316 m_line.expmass = cell.getDoubleValue();
317 break;
319 m_line.calcmass = cell.getDoubleValue();
320 break;
321 case Columns::charge:
322 m_line.charge = cell.getDoubleValue();
323 break;
325 m_line.peptide_len = cell.getDoubleValue();
326 break;
328 m_line.missed_cleavages = cell.getDoubleValue();
329 break;
331 m_line.semi_enzymatic = cell.getDoubleValue();
332 break;
334 m_line.isotope_error = cell.getDoubleValue();
335 break;
336
338 m_line.precursor_ppm = cell.getDoubleValue();
339 break;
341 m_line.fragment_ppm = cell.getDoubleValue();
342 break;
344 m_line.hyperscore = cell.getDoubleValue();
345 break;
347 m_line.delta_next = cell.getDoubleValue();
348 break;
350 m_line.delta_best = cell.getDoubleValue();
351 break;
352 case Columns::rt:
353 m_line.rt = cell.getDoubleValue() * 60; // to convert retention time in seconds
354 break;
356 m_line.aligned_rt = cell.getDoubleValue();
357 break;
359 m_line.predicted_rt = cell.getDoubleValue();
360 break;
362 m_line.delta_rt_model = cell.getDoubleValue();
363 break;
365 m_line.ion_mobility = cell.getDoubleValue();
366 break;
368 m_line.predicted_mobility = cell.getDoubleValue();
369 break;
371 m_line.delta_mobility = cell.getDoubleValue();
372 break;
374 m_line.matched_peaks = cell.getDoubleValue();
375 break;
377 m_line.longest_b = cell.getDoubleValue();
378 break;
380 m_line.longest_y = cell.getDoubleValue();
381 break;
383 m_line.longest_y_pct = cell.getDoubleValue();
384 break;
386 m_line.matched_intensity_pct = cell.getDoubleValue();
387 break;
389 m_line.scored_candidates = cell.getDoubleValue();
390 break;
391 case Columns::poisson:
392 m_line.poisson = cell.getDoubleValue();
393 break;
395 m_line.sage_discriminant_score = cell.getDoubleValue();
396 break;
398 m_line.posterior_error = cell.getDoubleValue();
399 break;
401 m_line.spectrum_q = cell.getDoubleValue();
402 break;
404 m_line.peptide_q = cell.getDoubleValue();
405 break;
407 m_line.protein_q = cell.getDoubleValue();
408 break;
410 m_line.ms2_intensity = cell.getDoubleValue();
411 break;
412 default:
413 qDebug() << "m_line.calcmass=" << m_line.calcmass;
414 throw pappso::ExceptionNotImplemented(
415 QObject::tr("column type %1 not implemented").arg((std::uint8_t)column_type));
416 break;
417 }
418
419 /*
420
421 2333 TMISDSDYTEFENFTK
422 GRMZM2G018197_P01;GRMZM2G068952_P01;GRMZM5G822976_P01 3
423 20120906_balliau_extract_1_A01_urnb-1.mzML controllerType=0
424 controllerNumber=1 scan=12542 1 1 1926.8225 1926.8193 2 16 0 0
425 0.0 1.6471838 1.9796097 54.06803492297634 28.049970383419556 0.0 38.192993
426 0.76385987 0.7671368 0.0032769442 0.0 0.0 0.0 16 2 14 0.875 32.54396 380
427 -13.375352220427656 1.1570586 -34.13482 0.00016041065 0.00022231363
428 0.00040124074 1271951.1
429 */
430 }
432}
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 435 of file sagetsvhandler.cpp.

436{
437 m_columnNumber = 0;
438 msp_peptide = nullptr;
439 m_proteinList.clear();
440 m_line = Line();
441}

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 448 of file sagetsvhandler.cpp.

449{
450 m_columnNumber = 0;
451 m_lineNumber = 0;
452 mp_monitor->setStatus(QObject::tr("reading Sage TSV file"));
453
454 if(mp_monitor->shouldIstop())
455 {
456 throw pappso::ExceptionInterrupted(QObject::tr("Sage TSV data reading process interrupted"));
457 }
458}

References m_columnNumber, m_lineNumber, and mp_monitor.

◆ writePsm()

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

Definition at line 801 of file sagetsvhandler.cpp.

802{
803 m_sageReader.getCborStreamWriter().startMap();
804 m_sageReader.getCborStreamWriter().append("proforma");
805 m_sageReader.getCborStreamWriter().append(one_psm.proforma);
806 m_sageReader.getCborStreamWriter().append("protein_list");
807
808 QCborArray cbor_protein_list;
809 for(const QString &accession : one_psm.protein_list)
810 {
811 // qWarning() << "accession=" << accession;
812 QCborMap cbor_protein;
813 cbor_protein.insert(QString("accession"), accession);
814
815
816 // start/end positions
817 QString protein_sequence =
818 QString(m_psmProteinMap.getByAccession(accession).protein_sp.get()->getSequence())
819 .replace("L", "I");
820 int position = protein_sequence.indexOf(one_psm.peptide_sequence_li);
821
822 QCborArray positions;
823 while(position >= 0)
824 {
825 positions.push_back(position);
826 position = protein_sequence.indexOf(one_psm.peptide_sequence_li, position + 1);
827 }
828
829 cbor_protein.insert(QString("positions"), positions);
830
831 cbor_protein_list.append(cbor_protein);
832 }
833
834
835 QCborValue(cbor_protein_list).toCbor(m_sageReader.getCborStreamWriter());
836
837 m_sageReader.getCborStreamWriter().append("eval");
838 m_sageReader.getCborStreamWriter().startMap();
839 m_sageReader.getCborStreamWriter().append("sage");
840 QCborValue(one_psm.cbor_eval).toCbor(m_sageReader.getCborStreamWriter());
841 m_sageReader.getCborStreamWriter().endMap();
842
843 m_sageReader.getCborStreamWriter().endMap();
844}

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 751 of file sagetsvhandler.cpp.

752{
753 m_sageReader.getCborStreamWriter().startMap();
754 m_sageReader.getCborStreamWriter().append("name");
755 one_sample.cbor_core_sample.value("name").toCbor(m_sageReader.getCborStreamWriter());
756
757 m_sageReader.getCborStreamWriter().append("identification_file_list");
758 one_sample.cbor_core_sample.value("identification_file_list")
759 .toCbor(m_sageReader.getCborStreamWriter());
760
761
762 m_sageReader.getCborStreamWriter().append("peaklist_file");
763 one_sample.cbor_core_sample.value("peaklist_file").toCbor(m_sageReader.getCborStreamWriter());
764 //"scan_list": [
765
766 m_sageReader.getCborStreamWriter().append("scan_list");
767 m_sageReader.getCborStreamWriter().startArray(one_sample.scan_map.size());
768 for(auto &it_scan : one_sample.scan_map)
769 {
770 writeScan(it_scan.second);
771 }
772 m_sageReader.getCborStreamWriter().endArray();
773
774
775 m_sageReader.getCborStreamWriter().endMap();
776}
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 66 of file sagetsvhandler.cpp.

67{
68 for(auto it_sample_map : m_sampleMap)
69 {
70 writeSample(it_sample_map.second);
71 }
72}
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 779 of file sagetsvhandler.cpp.

780{
781 m_sageReader.getCborStreamWriter().startMap();
782 m_sageReader.getCborStreamWriter().append("id");
783 QCborValue(one_scan.cbor_id).toCbor(m_sageReader.getCborStreamWriter());
784 m_sageReader.getCborStreamWriter().append("precursor");
785 QCborValue(one_scan.cbor_precursor).toCbor(m_sageReader.getCborStreamWriter());
786 m_sageReader.getCborStreamWriter().append("ms2");
787 QCborValue(one_scan.cbor_ms2).toCbor(m_sageReader.getCborStreamWriter());
788
789 m_sageReader.getCborStreamWriter().append("psm_list");
790 m_sageReader.getCborStreamWriter().startArray(one_scan.psm_list.size());
791 for(auto &it_psm : one_scan.psm_list)
792 {
793 writePsm(it_psm);
794 }
795 m_sageReader.getCborStreamWriter().endArray();
796
797 m_sageReader.getCborStreamWriter().endMap();
798}
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: