// Added by Fawaz Ghali 13/05/2014 exportProteoAnnotator
private String proteoAnnotatorLineToString(ProteinAmbiguityGroup pag) {
String line = "";
List<UserParam> userParams = pag.getUserParam();
String countNonA = "";
String scoreNonA = "";
String nonAPeptide = "";
String aGenes = "";
String qValue = "";
for (int i = 0; i < userParams.size(); i++) {
UserParam userParam = userParams.get(i);
if (userParam.getName().equals("nonAPeptide")) {
nonAPeptide = userParam.getValue();
}
}
List<CvParam> cvParamList = pag.getCvParam();
for (int i = 0; i < cvParamList.size(); i++) {
CvParam cvParam = cvParamList.get(i);
if (cvParam.getAccession().equals("MS:1002474")) {
scoreNonA = cvParam.getValue();
}
if (cvParam.getAccession().equals("MS:1002475")) {
countNonA = cvParam.getValue();
}
if (cvParam.getAccession().equals("MS:1002373")) {
qValue = cvParam.getValue();
}
}
List<ProteinDetectionHypothesis> proteinDetectionHypothesisList =
pag.getProteinDetectionHypothesis();
for (int i = 0; i < proteinDetectionHypothesisList.size(); i++) {
ProteinDetectionHypothesis proteinDetectionHypothesis = proteinDetectionHypothesisList.get(i);
if (proteinDetectionHypothesis.getDBSequenceRef().startsWith("dbseq_generic|A_"))
aGenes = aGenes + proteinDetectionHypothesis.getDBSequenceRef() + ";";
}
line = countNonA + sep + scoreNonA + sep + nonAPeptide + sep + aGenes + sep + qValue;
return line;
}
private String pagToString(ProteinAmbiguityGroup pag) {
String pagString = pag.getId() + sep;
if (pag.getCvParam().isEmpty()) {
CvParam scoreParam = pag.getCvParam().get(0);
pagString += scoreParam.getValue() + sep;
} else {
pagString += sep;
}
return pagString;
}
private String sirToString(SpectrumIdentificationResult sir) {
String sirString = "";
SpectraData spectraData = spectraDataIdHashMap.get(sir.getSpectraDataRef());
sirString += spectraData.getLocation() + sep + "\"" + sir.getSpectrumID() + "\"";
Double rtInSeconds = -1.0;
String spectrumTitle = "";
// <cvParam accession="MS:1001114" name="retention time(s)" cvRef="PSI-MS" value="3488.676"
// unitAccession="UO:0000010" unitName="second" unitCvRef="UO" />
// <cvParam accession="MS:1000796" name="spectrum title" cvRef="PSI-MS"
// value="mam_050108o_CPTAC_study6_6E004.6805.6805.1" />
//
for (CvParam cvParam : sir.getCvParam()) {
// Updated by FG: checking for old CV param 1114 or newer correct CV term 16.
if (cvParam.getAccession().equals("MS:1001114")
|| cvParam.getAccession().equals("MS:1000016")) {
if (cvParam.getUnitAccession().equals("UO:0000010")) {
rtInSeconds = Double.parseDouble(cvParam.getValue());
} else if (cvParam.getUnitAccession().equals("UO:0000031")) {
rtInSeconds = Double.parseDouble(cvParam.getValue()) / 60; // Convert minutes to seconds
} else {
System.out.println("Error parsing RT - unit not recognised");
}
}
if (cvParam.getAccession().equals("MS:1000796")) {
spectrumTitle = cvParam.getValue();
}
}
sirString += sep + "\"" + spectrumTitle + "\"" + sep + rtInSeconds;
return sirString;
}
private String pdhToString(ProteinDetectionHypothesis pdh) {
String pdhString =
"\""
+ dbSequenceIdHashMap.get(pdh.getDBSequenceRef()).getAccession()
+ "\""
+ sep
+ pdh.isPassThreshold()
+ sep;
DBSequence dbSeq = dbSequenceIdHashMap.get(pdh.getDBSequenceRef());
String protDesc = "";
String protGroupMembership = "";
if (dbSeq != null) {
for (CvParam cvParam : dbSeq.getCvParam()) {
if (cvParam.getAccession().equals("MS:1001088")) { // Protein description
String description = cvParam.getValue().replaceAll("\"", ""); // remove internal "
protDesc = "\"" + description + "\"";
}
}
}
Map<String, String> mapNameToValue = new HashMap<>();
for (CvParam cvParam : pdh.getCvParam()) {
if (cvParam.getAccession().equals("MS:1001591")
|| cvParam.getAccession().equals("MS:1001592")
|| cvParam.getAccession().equals("MS:1001593")
|| cvParam.getAccession().equals("MS:1001594")
|| cvParam.getAccession().equals("MS:1001595")
|| cvParam.getAccession().equals("MS:1001596")
|| cvParam.getAccession().equals("MS:1001597")
|| cvParam.getAccession().equals("MS:1001598")
|| cvParam.getAccession().equals("MS:1001599")) { // Protein description
protGroupMembership = "\"" + cvParam.getName();
if (cvParam.getValue() != null) {
protGroupMembership += ":" + cvParam.getValue();
}
protGroupMembership += "\"";
} else {
mapNameToValue.put(cvParam.getName(), cvParam.getValue());
}
}
for (UserParam userParam : pdh.getUserParam()) {
mapNameToValue.put(userParam.getName(), userParam.getValue());
}
pdhString += protDesc + sep + protGroupMembership + sep;
// Handle scores
for (int i = 0; i < columnToProtScoreMap.size(); i++) {
String score = columnToProtScoreMap.get(i);
// System.out.println("test2" + score);
if (mapNameToValue.containsKey(score)) {
String scoreValue = mapNameToValue.get(score);
// System.out.println("test3" + scoreValue);
pdhString += scoreValue + sep;
} else {
pdhString += sep;
}
}
return pdhString;
}
private void init(String outputFile, String exportOption) {
Writer out = null;
try {
out = new BufferedWriter(new FileWriter(outputFile));
// Read all the objects we will need into hashes that are not automatically resolved by object
// reference
if (isVerbose) {
System.out.print("About to iterate over PepEvid...");
}
Iterator<PeptideEvidence> iterPeptideEvidence =
unmarshaller.unmarshalCollectionFromXpath(MzIdentMLElement.PeptideEvidence);
while (iterPeptideEvidence.hasNext()) {
PeptideEvidence peptideEvidence = iterPeptideEvidence.next();
peptideEvidenceIdHashMap.put(peptideEvidence.getId(), peptideEvidence);
}
if (isVerbose) {
System.out.println("...done");
System.out.print("About to iterate over Peptide");
}
Iterator<Peptide> iterPeptide =
unmarshaller.unmarshalCollectionFromXpath(MzIdentMLElement.Peptide);
while (iterPeptide.hasNext()) {
Peptide peptide = iterPeptide.next();
peptideIdHashMap.put(peptide.getId(), peptide);
}
if (isVerbose) {
System.out.println("...done");
System.out.print("About to iterate over Spectra Data");
}
Iterator<SpectraData> iterSpectraData =
unmarshaller.unmarshalCollectionFromXpath(MzIdentMLElement.SpectraData);
while (iterSpectraData.hasNext()) {
SpectraData spectraData = iterSpectraData.next();
spectraDataIdHashMap.put(spectraData.getId(), spectraData);
}
if (isVerbose) {
System.out.println("...done");
System.out.print("About to iterate over DBsequence");
}
Iterator<DBSequence> iterDBSequence =
unmarshaller.unmarshalCollectionFromXpath(MzIdentMLElement.DBSequence);
while (iterDBSequence.hasNext()) {
DBSequence dbSequence = iterDBSequence.next();
dbSequenceIdHashMap.put(dbSequence.getId(), dbSequence);
}
if (isVerbose) {
System.out.println("...done");
System.out.print("About to iterate over PDH");
}
Iterator<ProteinDetectionHypothesis> iterPDH =
unmarshaller.unmarshalCollectionFromXpath(MzIdentMLElement.ProteinDetectionHypothesis);
Integer pCounter = 0;
while (iterPDH.hasNext()) {
ProteinDetectionHypothesis pdh = iterPDH.next();
pdhIdHashMap.put(pdh.getId(), pdh);
for (CvParam cvParam : pdh.getCvParam()) {
if (cvParam.getAccession().equals("MS:1001591")
|| cvParam.getAccession().equals("MS:1001592")
|| cvParam.getAccession().equals("MS:1001593")
|| cvParam.getAccession().equals("MS:1001594")
|| cvParam.getAccession().equals("MS:1001595")
|| cvParam.getAccession().equals("MS:1001596")
|| cvParam.getAccession().equals("MS:1001597")
|| cvParam.getAccession().equals("MS:1001598")
|| cvParam
.getAccession()
.equals("MS:1001599")) { // do nothing - these are specifically handled
// ToDO this code could be improved using an array of values...
} else if (cvParam.getValue() != null) {
if (!columnToProtScoreMap.containsValue(cvParam.getName())) {
columnToProtScoreMap.put(pCounter, cvParam.getName());
pCounter++;
}
}
}
for (UserParam userParam : pdh.getUserParam()) {
if (!columnToProtScoreMap.containsValue(userParam.getName())) {
columnToProtScoreMap.put(pCounter, userParam.getName());
pCounter++;
}
}
}
for (int i = 0; i < pCounter; i++) {
pScoreHeader += columnToProtScoreMap.get(i) + sep;
}
// Now let's see what scores we have in the file
// TODO - I'm not sure this is the fastest way to parse the files; these are unmarshalled
// again below - inefficient?
// Iterator<SpectrumIdentificationItem> iterSII =
// unmarshaller.unmarshalCollectionFromXpath(MzIdentMLElement.SpectrumIdentificationItem);
Integer counter = 0;
if (isVerbose) {
System.out.println("...done");
System.out.print("About to iterate over SIR");
}
Iterator<SpectrumIdentificationResult> iterSIR =
unmarshaller.unmarshalCollectionFromXpath(MzIdentMLElement.SpectrumIdentificationResult);
List<SpectrumIdentificationResult> sirList = new ArrayList<>();
while (iterSIR.hasNext()) {
SpectrumIdentificationResult sir = iterSIR.next();
sirList.add(sir);
List<SpectrumIdentificationItem> listSII = sir.getSpectrumIdentificationItem();
for (SpectrumIdentificationItem sii : listSII) {
siiIdHashMap.put(sii.getId(), sii);
siiIdToSirHashMap.put(sii.getId(), sir);
for (CvParam cvParam : sii.getCvParam()) {
if (cvParam.getValue() != null) {
if (!columnToScoreMap.containsValue(cvParam.getName())) {
columnToScoreMap.put(counter, cvParam.getName());
counter++;
}
}
}
}
}
for (int i = 0; i < counter; i++) {
scoreHeader += sep + columnToScoreMap.get(i);
}
if (isVerbose) {
System.out.println("...done");
System.out.print("About to create output");
}
if (exportOption.equals("exportPSMs")) {
out.write(spectrumHeader + psmHeader + scoreHeader);
out.write(endPsmHeader + "\n");
// Iterator<SpectrumIdentificationResult> iterSIR =
// unmarshaller.unmarshalCollectionFromXpath(MzIdentMLElement.SpectrumIdentificationResult);
for (SpectrumIdentificationResult sir : sirList) {
String sirLine = sirToString(sir);
List<SpectrumIdentificationItem> listSII = sir.getSpectrumIdentificationItem();
for (SpectrumIdentificationItem sii : listSII) {
out.write(sirLine + sep + siiToString(sii) + "\n");
}
}
} else if (exportOption.equals("exportProteinGroups")) {
out.write(pagHeader);
out.write(pScoreHeader);
out.write(spectrumHeader + psmHeader + scoreHeader);
out.write(endPsmHeader + "\n");
Iterator<ProteinAmbiguityGroup> iterPAG =
unmarshaller.unmarshalCollectionFromXpath(MzIdentMLElement.ProteinAmbiguityGroup);
while (iterPAG.hasNext()) {
ProteinAmbiguityGroup pag = iterPAG.next();
String pagLine = pagToString(pag);
// handle PDHs
for (ProteinDetectionHypothesis pdh : pag.getProteinDetectionHypothesis()) {
String pdhLine = pagLine;
pdhLine += pdhToString(pdh);
for (PeptideHypothesis pepH : pdh.getPeptideHypothesis()) {
List<SpectrumIdentificationItemRef> siiRefList =
pepH.getSpectrumIdentificationItemRef();
for (SpectrumIdentificationItemRef siiRef : siiRefList) {
SpectrumIdentificationResult sir =
siiIdToSirHashMap.get(siiRef.getSpectrumIdentificationItemRef());
SpectrumIdentificationItem sii =
siiIdHashMap.get(siiRef.getSpectrumIdentificationItemRef());
out.write(pdhLine + sirToString(sir) + sep + siiToString(sii) + "\n");
}
}
}
}
} else if (exportOption.equals("exportRepProteinPerPAGOnly")) {
out.write(pagHeader);
out.write(pScoreHeader);
out.write("\n");
Iterator<ProteinAmbiguityGroup> iterPAG =
unmarshaller.unmarshalCollectionFromXpath(MzIdentMLElement.ProteinAmbiguityGroup);
while (iterPAG.hasNext()) {
ProteinAmbiguityGroup pag = iterPAG.next();
String pagLine = pagToString(pag);
ProteinDetectionHypothesis repPdh = getRepresentativePDH(pag, representativeProteinAcc);
String pdhLine = pagLine;
if (repPdh != null) {
pdhLine += pdhToString(repPdh);
}
out.write(pdhLine + "\n");
}
} else if (exportOption.equals(
"exportProteoAnnotator")) { // Added by Fawaz Ghali 13/05/2014 exportProteoAnnotator
out.write(pagHeader);
out.write(pScoreHeader);
// Added by Fawaz Ghali 13/05/2014 exportProteoAnnotator
out.write(exportProteoAnnotatorHeader);
out.write("\n");
Iterator<ProteinAmbiguityGroup> iterPAG =
unmarshaller.unmarshalCollectionFromXpath(MzIdentMLElement.ProteinAmbiguityGroup);
while (iterPAG.hasNext()) {
ProteinAmbiguityGroup pag = iterPAG.next();
String pagLine = pagToString(pag);
ProteinDetectionHypothesis repPdh = getRepresentativePDH(pag, representativeProteinAcc);
String pdhLine = pagLine;
if (repPdh != null) {
pdhLine += pdhToString(repPdh);
}
// Added by Fawaz Ghali 13/05/2014 exportProteoAnnotator
String proteoAnnotatorLine = pdhLine;
proteoAnnotatorLine = proteoAnnotatorLine + proteoAnnotatorLineToString(pag);
out.write(proteoAnnotatorLine + "\n");
}
} else if (exportOption.equals("exportProteinsOnly")) {
out.write(pagHeader);
out.write(pScoreHeader);
out.write("\n");
Iterator<ProteinAmbiguityGroup> iterPAG =
unmarshaller.unmarshalCollectionFromXpath(MzIdentMLElement.ProteinAmbiguityGroup);
while (iterPAG.hasNext()) {
ProteinAmbiguityGroup pag = iterPAG.next();
String pagLine = pagToString(pag);
// handle PDHs
for (ProteinDetectionHypothesis pdh : pag.getProteinDetectionHypothesis()) {
String pdhLine = pagLine;
pdhLine += pdhToString(pdh);
out.write(pdhLine + "\n");
}
}
} else {
System.out.println(
"Error - correct usage MzIdentMLToCSV inputFile outputFile -exportType [exportProteinGroups|exportPSMs|exportProteinsOnly]");
}
out.close();
System.out.println("Output written to " + outputFile);
} catch (IOException ex) {
String methodName = Thread.currentThread().getStackTrace()[1].getMethodName();
String className = this.getClass().getName();
String message =
"The task \""
+ methodName
+ "\" in the class \""
+ className
+ "\" was not completed because of "
+ ex.getMessage()
+ "."
+ "\nPlease see the reference guide at 02 for more information on this error. https://code.google.com/p/mzidentml-lib/wiki/CommonErrors ";
System.out.println(message);
} finally {
try {
out.close();
} catch (IOException ex) {
String methodName = Thread.currentThread().getStackTrace()[1].getMethodName();
String className = this.getClass().getName();
String message =
"The task \""
+ methodName
+ "\" in the class \""
+ className
+ "\" was not completed because of "
+ ex.getMessage()
+ "."
+ "\nPlease see the reference guide at 02 for more information on this error. https://code.google.com/p/mzidentml-lib/wiki/CommonErrors ";
System.out.println(message);
}
}
}