/**
* Parses the data from an mzIdentML file given by its name into the given {@link PIACompiler}.
*
* @param fileName name of the mzTab file
*/
public static boolean getDataFromMascotDatFile(
String name, String fileName, PIACompiler compiler) {
// need to parse through the file, as mascotdatfile (3.2.11) does not support
// - the "index" variable of the queries
// - the "fastafile"
// - no good information for enzyme
Map<String, String> queryIndexMap = new HashMap<>();
String fastaFile = null;
String enzymeCleavage = null;
String enzymeRestrict = null;
try (BufferedReader rd = new BufferedReader(new FileReader(fileName))) {
String line;
boolean inQuery = false;
boolean inEnzyme = false;
String queryName = null;
while ((line = rd.readLine()) != null) {
if (!inQuery) {
if (line.startsWith("Content-Type: application/x-Mascot; NAME=\"query")) {
queryName = line.substring(42, line.length() - 1);
inQuery = true;
} else if ((fastaFile == null) && line.startsWith("fastafile")) {
fastaFile = line.substring(10);
}
} else if (inQuery && line.startsWith("index=")) {
queryIndexMap.put(queryName, line);
inQuery = false;
}
if (!inEnzyme) {
if (((enzymeCleavage == null) || (enzymeRestrict == null))
&& line.startsWith("Content-Type: application/x-Mascot; NAME=\"enzyme\"")) {
inEnzyme = true;
}
} else {
if (line.startsWith("Cleavage:")) {
enzymeCleavage = line.substring(9).trim();
} else if (line.startsWith("Restrict:")) {
enzymeRestrict = line.substring(9).trim();
} else if (line.startsWith("Content-Type:")) {
inEnzyme = false;
}
}
}
rd.close();
} catch (IOException e) {
LOGGER.error("could not read '" + fileName + "' for index parsing.", e);
return false;
}
MascotDatfileInf mascotFile = MascotDatfileFactory.create(fileName, MascotDatfileType.MEMORY);
if (mascotFile == null) {
LOGGER.error("could not read '" + fileName + "'.");
return false;
}
PIAInputFile file =
compiler.insertNewFile(
name, fileName, InputFileParserFactory.InputFileTypes.MASCOT_DAT_INPUT.getFileSuffix());
// create the analysis software and add it to the compiler
AnalysisSoftware mascot = new AnalysisSoftware();
mascot.setId("mascot");
mascot.setName("mascot");
mascot.setUri("http://www.matrixscience.com/");
mascot.setVersion(mascotFile.getHeaderSection().getVersion());
Param param = new Param();
param.setParam(MzIdentMLTools.createPSICvParam(OntologyConstants.MASCOT, null));
mascot.setSoftwareName(param);
mascot = compiler.putIntoSoftwareMap(mascot);
// create the searchDatabase and add it to the compiler
SearchDatabase searchDatabase = new SearchDatabase();
// required
searchDatabase.setId("mascotDB");
searchDatabase.setLocation(fastaFile);
// optional
searchDatabase.setName(mascotFile.getParametersSection().getDatabase());
searchDatabase.setNumDatabaseSequences(mascotFile.getHeaderSection().getSequences());
searchDatabase.setNumResidues(mascotFile.getHeaderSection().getResidues());
// fileformat
FileFormat fileFormat = new FileFormat();
fileFormat.setCvParam(MzIdentMLTools.createPSICvParam(OntologyConstants.FASTA_FORMAT, null));
searchDatabase.setFileFormat(fileFormat);
// databaseName
param = new Param();
param.setParam(
MzIdentMLTools.createUserParam(mascotFile.getHeaderSection().getRelease(), null, "string"));
searchDatabase.setDatabaseName(param);
// add searchDB to the compiler
searchDatabase = compiler.putIntoSearchDatabasesMap(searchDatabase);
// add the spectraData (input file)
SpectraData spectraData = null;
if ((mascotFile.getParametersSection().getFile() != null)
&& (mascotFile.getParametersSection().getFile().trim().length() > 0)) {
spectraData = new SpectraData();
spectraData.setId("mascotInput");
spectraData.setLocation(mascotFile.getParametersSection().getFile());
if ((mascotFile.getParametersSection().getFormat() != null)
&& "Mascot generic".equals(mascotFile.getParametersSection().getFormat())) {
fileFormat = new FileFormat();
fileFormat.setCvParam(
MzIdentMLTools.createPSICvParam(OntologyConstants.MASCOT_MGF_FORMAT, null));
spectraData.setFileFormat(fileFormat);
SpectrumIDFormat idFormat = new SpectrumIDFormat();
idFormat.setCvParam(
MzIdentMLTools.createPSICvParam(
OntologyConstants.MULTIPLE_PEAK_LIST_NATIVEID_FORMAT, null));
spectraData.setSpectrumIDFormat(idFormat);
}
spectraData = compiler.putIntoSpectraDataMap(spectraData);
} else {
LOGGER.warn("The source file (MGF) was not recorded in the file!");
}
// define the spectrumIdentificationProtocol
SpectrumIdentificationProtocol spectrumIDProtocol = new SpectrumIdentificationProtocol();
spectrumIDProtocol.setId("mascotAnalysis");
spectrumIDProtocol.setAnalysisSoftware(mascot);
param = new Param();
if ("MIS".equals(mascotFile.getParametersSection().getSearch())) {
param.setParam(MzIdentMLTools.createPSICvParam(OntologyConstants.MS_MS_SEARCH, null));
}
// TODO: add error on PMF query (not usable for PIA)
// TODO: and sequence query
spectrumIDProtocol.setSearchType(param);
ParamList paramList = new ParamList();
paramList
.getCvParam()
.add(
MzIdentMLTools.createPSICvParam(
OntologyConstants.MASCOT_INSTRUMENT,
mascotFile.getParametersSection().getInstrument()));
paramList
.getUserParam()
.add(
MzIdentMLTools.createUserParam(
"Mascot User Comment", mascotFile.getParametersSection().getCom(), "string"));
if ("Monoisotopic".equalsIgnoreCase(mascotFile.getParametersSection().getMass())) {
paramList
.getCvParam()
.add(MzIdentMLTools.createPSICvParam(OntologyConstants.FRAGMENT_MASS_TYPE_MONO, null));
paramList
.getCvParam()
.add(MzIdentMLTools.createPSICvParam(OntologyConstants.PARENT_MASS_TYPE_MONO, null));
} else {
paramList
.getCvParam()
.add(MzIdentMLTools.createPSICvParam(OntologyConstants.FRAGMENT_MASS_TYPE_AVERAGE, null));
paramList
.getCvParam()
.add(MzIdentMLTools.createPSICvParam(OntologyConstants.PARENT_MASS_TYPE_AVERAGE, null));
}
spectrumIDProtocol.setAdditionalSearchParams(paramList);
ModificationParams modParams = new ModificationParams();
for (Object objMod : mascotFile.getModificationList().getVariableModifications()) {
modParams
.getSearchModification()
.add(createPSIModification((VariableModification) objMod, compiler.getUnimodParser()));
}
for (Object objMod : mascotFile.getModificationList().getFixedModifications()) {
modParams
.getSearchModification()
.add(createPSIModification((FixedModification) objMod, compiler.getUnimodParser()));
}
spectrumIDProtocol.setModificationParams(modParams);
Enzymes enzymes = new Enzymes();
spectrumIDProtocol.setEnzymes(enzymes);
if (enzymeCleavage != null) {
Enzyme enzyme = new Enzyme();
enzyme.setId("enzyme");
enzyme.setMissedCleavages(Integer.parseInt(mascotFile.getParametersSection().getPFA()));
StringBuilder regExp = new StringBuilder();
if (enzymeRestrict == null) {
regExp.append("(?=[");
regExp.append(enzymeCleavage);
regExp.append("])");
} else {
regExp.append("(?<=[");
regExp.append(enzymeCleavage);
regExp.append("])(?!");
regExp.append(enzymeRestrict);
regExp.append(")");
}
enzyme.setSiteRegexp(regExp.toString());
enzymes.getEnzyme().add(enzyme);
}
Tolerance tolerance = new Tolerance();
AbstractParam abstractParam =
MzIdentMLTools.createPSICvParam(
OntologyConstants.SEARCH_TOLERANCE_PLUS_VALUE,
mascotFile.getParametersSection().getITOL());
MzIdentMLTools.setUnitParameterFromString(
mascotFile.getParametersSection().getITOLU(), abstractParam);
tolerance.getCvParam().add((CvParam) abstractParam);
abstractParam =
MzIdentMLTools.createPSICvParam(
OntologyConstants.SEARCH_TOLERANCE_MINUS_VALUE,
mascotFile.getParametersSection().getITOL());
MzIdentMLTools.setUnitParameterFromString(
mascotFile.getParametersSection().getITOLU(), abstractParam);
tolerance.getCvParam().add((CvParam) abstractParam);
spectrumIDProtocol.setFragmentTolerance(tolerance);
tolerance = new Tolerance();
abstractParam =
MzIdentMLTools.createPSICvParam(
OntologyConstants.SEARCH_TOLERANCE_PLUS_VALUE,
mascotFile.getParametersSection().getTOL());
MzIdentMLTools.setUnitParameterFromString(
mascotFile.getParametersSection().getTOLU(), abstractParam);
tolerance.getCvParam().add((CvParam) abstractParam);
abstractParam =
MzIdentMLTools.createPSICvParam(
OntologyConstants.SEARCH_TOLERANCE_MINUS_VALUE,
mascotFile.getParametersSection().getTOL());
MzIdentMLTools.setUnitParameterFromString(
mascotFile.getParametersSection().getTOLU(), abstractParam);
tolerance.getCvParam().add((CvParam) abstractParam);
spectrumIDProtocol.setParentTolerance(tolerance);
// no threshold set, take all PSMs from the dat file
paramList = new ParamList();
paramList
.getCvParam()
.add(MzIdentMLTools.createPSICvParam(OntologyConstants.NO_THRESHOLD, null));
spectrumIDProtocol.setThreshold(paramList);
file.addSpectrumIdentificationProtocol(spectrumIDProtocol);
// add the spectrum identification
SpectrumIdentification spectrumID = new SpectrumIdentification();
spectrumID.setId("mascotIdentification");
spectrumID.setSpectrumIdentificationList(null);
spectrumID.setSpectrumIdentificationProtocol(spectrumIDProtocol);
if (spectraData != null) {
InputSpectra inputSpectra = new InputSpectra();
inputSpectra.setSpectraData(spectraData);
spectrumID.getInputSpectra().add(inputSpectra);
}
SearchDatabaseRef searchDBRef = new SearchDatabaseRef();
searchDBRef.setSearchDatabase(searchDatabase);
spectrumID.getSearchDatabaseRef().add(searchDBRef);
file.addSpectrumIdentification(spectrumID);
// get the mappings
QueryEnumerator queryEnumerator = mascotFile.getQueryEnumerator();
QueryToPeptideMapInf queryToPeptideMap = mascotFile.getQueryToPeptideMap();
QueryToPeptideMapInf decoyQueryToPeptideMap = mascotFile.getDecoyQueryToPeptideMap(false);
ProteinMap proteinMap = mascotFile.getProteinMap();
ProteinMap decoyProteinMap = mascotFile.getDecoyProteinMap();
// one query is one spectrum, so go through the queries
int nrQueries = mascotFile.getNumberOfQueries();
int nrQueriesDone = 0;
LOGGER.debug("queries in file: " + nrQueries);
while (queryEnumerator.hasMoreElements()) {
Query currQuery = queryEnumerator.nextElement();
int charge;
try {
if (currQuery.getChargeString() == null) {
charge = 0;
} else if (currQuery.getChargeString().contains("-")) {
charge = -Integer.parseInt(currQuery.getChargeString().replace("-", ""));
} else {
// we assume, it is positively charged
charge = Integer.parseInt(currQuery.getChargeString().replace("+", ""));
}
} catch (NumberFormatException e) {
charge = 0;
LOGGER.warn(
"could not parse charge '"
+ currQuery.getChargeString()
+ "' for '"
+ currQuery.getTitle()
+ "'");
}
double precursorMZ = currQuery.getPrecursorMZ();
Double retentionTime;
if (currQuery.getRetentionTimeInSeconds() != null) {
retentionTime = Double.parseDouble(currQuery.getRetentionTimeInSeconds());
} else {
retentionTime = null;
}
String spectrumTitle = currQuery.getTitle();
String index = queryIndexMap.get("query" + currQuery.getQueryNumber());
// add the target identifications
if (queryToPeptideMap != null) {
List<PeptideHit> peptideHits =
queryToPeptideMap.getAllPeptideHits(currQuery.getQueryNumber());
insertPeptideHitsIntoCompiler(
compiler,
peptideHits,
proteinMap,
searchDatabase,
charge,
precursorMZ,
retentionTime,
index,
spectrumTitle,
file,
spectrumID,
false);
}
// add the decoy identifications
if (decoyQueryToPeptideMap != null) {
List<PeptideHit> peptideHits =
decoyQueryToPeptideMap.getAllPeptideHits(currQuery.getQueryNumber());
insertPeptideHitsIntoCompiler(
compiler,
peptideHits,
decoyProteinMap,
searchDatabase,
charge,
precursorMZ,
retentionTime,
index,
spectrumTitle,
file,
spectrumID,
true);
}
nrQueriesDone++;
if (nrQueriesDone % 10000 == 0) {
LOGGER.debug(
"done "
+ nrQueriesDone
+ " / "
+ nrQueries
+ String.format(" (%1$.4f%%)", 100.0 * nrQueriesDone / nrQueries));
}
}
mascotFile.finish();
return true;
}
private static SearchModification createPSIModification(
com.compomics.mascotdatfile.util.interfaces.Modification mod, UnimodParser uniModParser) {
SearchModification searchMod = new SearchModification();
if (mod instanceof VariableModification) {
searchMod.setFixedMod(false);
} else {
searchMod.setFixedMod(true);
}
if (mod.getLocation().contains("term") || mod.getLocation().contains("Term")) {
OntologyConstants modConstant = null;
if (mod.getLocation().startsWith("Protein N")) {
modConstant = OntologyConstants.MODIFICATION_SPECIFICITY_PROTEIN_N_TERM;
} else if (mod.getLocation().startsWith("Protein C")) {
modConstant = OntologyConstants.MODIFICATION_SPECIFICITY_PROTEIN_C_TERM;
} else if (mod.getLocation().startsWith("N")) {
modConstant = OntologyConstants.MODIFICATION_SPECIFICITY_PEP_N_TERM;
} else if (mod.getLocation().startsWith("C")) {
modConstant = OntologyConstants.MODIFICATION_SPECIFICITY_PEP_C_TERM;
}
if (modConstant != null) {
CvParam specificity = MzIdentMLTools.createPSICvParam(modConstant, null);
SpecificityRules specRules = new SpecificityRules();
specRules.getCvParam().add(specificity);
searchMod.getSpecificityRules().add(specRules);
String[] residues = mod.getLocation().split("erm");
if (residues.length > 1) {
for (Character residue : residues[1].trim().toCharArray()) {
if (residue != ' ') {
searchMod.getResidues().add(residue.toString());
}
}
} else {
searchMod.getResidues().add(".");
}
}
} else {
for (Character residue : mod.getLocation().toCharArray()) {
searchMod.getResidues().add(residue.toString());
}
}
searchMod.setMassDelta((float) mod.getMass());
ModT unimod =
uniModParser.getModificationByNameAndMass(
mod.getType(), mod.getMass(), searchMod.getResidues());
if (unimod != null) {
CvParam cvParam = new CvParam();
cvParam.setAccession("UNIMOD:" + unimod.getRecordId());
cvParam.setCv(UnimodParser.getCv());
cvParam.setName(unimod.getTitle());
searchMod.getCvParam().add(cvParam);
}
return searchMod;
}