/**
* Create a MZTabFile with defined metadata.
*
* @param metadata SHOULD NOT set null.
*/
public MZTabFile(Metadata metadata)
{
if (metadata == null){
throw new NullReferenceException("Metadata should be created first.");
}
this.metadata = metadata;
}
/**
* Parse a header line into {@link MZTabColumnFactory} structure.
*
* @param factory SHOULD NOT set null
* @param metadata SHOULD NOT set null
*/
protected MZTabHeaderLineParser(MZTabColumnFactory factory, Metadata metadata)
{
if (factory == null){
throw new NullReferenceException("Header line should be parse first!");
}
this.factory = factory;
if (metadata == null){
throw new NullReferenceException("Metadata should be create first!");
}
this.metadata = metadata;
}
/**
* Generate a mzTab data line parser. A couple of common method used to parse a data line into
* {@link MZTabRecord} structure.
*
* NOTICE: {@link MZTabColumnFactory} maintain a couple of {@link MZTabColumn} which have internal logical
* position and order. In physical mzTab file, we allow user not obey this logical position organized way,
* and provide their date with own order. In order to distinguish them, we use physical position (a positive
* integer) to record the column location in mzTab file. And use {@link PositionMapping} structure the maintain
* the mapping between them.
*
* @param factory SHOULD NOT set null
* @param positionMapping SHOULD NOT set null
* @param metadata SHOULD NOT set null
*/
protected MZTabDataLineParser(MZTabColumnFactory factory, PositionMapping positionMapping,
Metadata metadata, MZTabErrorList errorList)
{
if (factory == null){
throw new NullReferenceException("Column header factory should be create first.");
}
this.factory = factory;
this.positionMapping = positionMapping;
exchangeMapping = positionMapping.exchange();
mapping = factory.GetOffsetColumnsMap();
if (metadata == null){
throw new NullReferenceException("Metadata should be parser first.");
}
this.metadata = metadata;
_errorList = errorList ?? new MZTabErrorList();
}
private void addPeptideValue()
{
MsRun msRun1 = new MsRun(1);
Assay assay1 = new Assay(1);
Assay assay2 = new Assay(2);
StudyVariable studyVariable1 = new StudyVariable(1);
MZTabColumnFactory factory = MZTabColumnFactory.GetInstance(Section.Peptide_Header);
factory.AddOptionalColumn(PeptideColumn.SEARCH_ENGINE_SCORE, msRun1);
factory.AddAbundanceOptionalColumn(assay1);
factory.AddAbundanceOptionalColumn(studyVariable1);
factory.AddAbundanceOptionalColumn(assay2);
factory.AddOptionalColumn(msRun1, "my_value", typeof (string));
CVParam param = new CVParam("MS", "MS:1002217", "decoy peptide", null);
factory.AddOptionalColumn(param, typeof (string));
Metadata metadata = new Metadata();
metadata.AddMsRunLocation(2, new Url("file://C:\\path\\to\\my\\file"));
Console.WriteLine(factory);
Peptide peptide = new Peptide(factory, metadata);
peptide.Sequence = "KVPQVSTPTLVEVSR";
peptide.Accession = "P02768";
peptide.SetUnique("0");
peptide.Database = "UniProtKB";
peptide.DatabaseVersion = "2011_11";
peptide.SetSearchEngine("[MS,MS:1001207,Mascot,]|[MS,MS:1001208,Sequest,]");
peptide.SetBestSearchEngineScore("[MS,MS:1001155,Sequest:xcorr,2]");
peptide.Reliability = Reliability.findReliability("3");
peptide.SetModifications(
"3[MS,MS:1001876, modification probability, 0.8]|4[MS,MS:1001876, modification probability, 0.2]-MOD:00412,8[MS,MS:1001876, modification probability, 0.3]-MOD:00412");
peptide.AddRetentionTime(10.2);
peptide.AddRetentionTimeWindow(1123.2);
peptide.AddRetentionTimeWindow(1145.3);
peptide.Charge = new Integer(2);
peptide.MassToCharge = 1234.4;
peptide.URI = new Uri("http://www.ebi.ac.uk/pride/link/to/peptide");
peptide.SetSpectraRef("ms_run[2]:index=7|ms_run[2]:index=9");
Console.WriteLine(peptide);
}
public Peptide(Metadata metadata)
: base(MZTabColumnFactory.GetInstance(Section.Peptide))
{
this.metadata = metadata;
}
public PEHLineParser(Metadata metadata)
: base(MZTabColumnFactory.GetInstance(Section.Peptide_Header), metadata)
{
}
public PRHLineParser(Metadata metadata)
: base(MZTabColumnFactory.GetInstance(Section.Protein_Header), metadata)
{
}
public static void main(string[] args)
{
MZTabDescription tabDescription = new MZTabDescription(MzTabMode.Summary, MzTabType.Identification){
Id = "PRIDE_1234"
};
Metadata mtd = new Metadata(tabDescription);
mtd.Title = "My first test experiment";
mtd.Description = "An experiment investigating the effects of Il-6.";
mtd.AddSampleProcessingParam(1, new CVParam("SEP", "SEP:00173", "SDS PAGE", null));
mtd.AddSampleProcessingParam(2, new CVParam("SEP", "SEP:00142", "enzyme digestion", null));
mtd.AddSampleProcessingParam(2, new CVParam("MS", "MS:1001251", "Trypsin", null));
mtd.AddInstrumentName(1, new CVParam("MS", "MS:100049", "LTQ Orbitrap", null));
mtd.AddInstrumentName(2,
new CVParam("MS", "MS:1000031", "Instrument model",
"name of the instrument not included in the CV"));
mtd.AddInstrumentSource(1, new CVParam("MS", "MS:1000073", "ESI", null));
mtd.AddInstrumentSource(2, new CVParam("MS", "MS:1000598", "ETD", null));
mtd.AddInstrumentAnalyzer(1, new CVParam("MS", "MS:1000291", "linear ion trap", null));
mtd.AddInstrumentAnalyzer(2, new CVParam("MS", "MS:1000484", "orbitrap", null));
mtd.AddInstrumentDetector(1, new CVParam("MS", "MS:1000253", "electron multiplier", null));
mtd.AddInstrumentDetector(2, new CVParam("MS", "MS:1000348", "focal plane collector", null));
mtd.AddSoftwareParam(1, new CVParam("MS", "MS:1001207", "Mascot", "2.3"));
mtd.AddSoftwareParam(2, new CVParam("MS", "MS:1001561", "Scaffold", "1.0"));
mtd.AddSoftwareSetting(1, "Fragment tolerance = 0.1Da");
mtd.AddSoftwareSetting(1, "Parent tolerance = 0.5Da");
mtd.AddFalseDiscoveryRateParam(new CVParam("MS", "MS:1001364", "pep:global FDR", "0.01"));
mtd.AddFalseDiscoveryRateParam(new CVParam("MS", "MS:1001214", "pep:global FDR", "0.08"));
mtd.AddPublicationItem(1, PublicationType.PUBMED, "21063943");
mtd.AddPublicationItem(1, PublicationType.DOI, "10.1007/978-1-60761-987-1_6");
mtd.AddPublicationItem(2, PublicationType.PUBMED, "20615486");
mtd.AddPublicationItem(2, PublicationType.DOI, "10.1016/j.jprot.2010.06.008");
mtd.AddContactName(1, "James D. Watson");
mtd.AddContactName(2, "Francis Crick");
mtd.AddContactAffiliation(1, "Cambridge University, UK");
mtd.AddContactAffiliation(2, "Cambridge University, UK");
mtd.AddContactEmail(1, "*****@*****.**");
mtd.AddContactEmail(2, "*****@*****.**");
mtd.AddUri(new Uri("http://www.ebi.ac.uk/pride/url/to/experiment"));
mtd.AddUri(new Uri("http://proteomecentral.proteomexchange.org/cgi/GetDataset"));
mtd.AddFixedModParam(1, new CVParam("UNIMOD", "UNIMOD:4", "Carbamidomethyl", null));
mtd.AddFixedModSite(1, "M");
mtd.AddFixedModParam(2, new CVParam("UNIMOD", "UNIMOD:35", "Oxidation", null));
mtd.AddFixedModSite(2, "N-term");
mtd.AddFixedModParam(3, new CVParam("UNIMOD", "UNIMOD:1", "Acetyl", null));
mtd.AddFixedModPosition(3, "Protein C-term");
mtd.AddVariableModParam(1, new CVParam("UNIMOD", "UNIMOD:21", "Phospho", null));
mtd.AddVariableModSite(1, "M");
mtd.AddVariableModParam(2, new CVParam("UNIMOD", "UNIMOD:35", "Oxidation", null));
mtd.AddVariableModSite(2, "N-term");
mtd.AddVariableModParam(3, new CVParam("UNIMOD", "UNIMOD:1", "Acetyl", null));
mtd.AddVariableModPosition(3, "Protein C-term");
mtd.QuantificationMethod = new CVParam("MS", "MS:1001837", "iTRAQ quantitation analysis", null);
mtd.ProteinQuantificationUnit = new CVParam("PRIDE", "PRIDE:0000395", "Ratio", null);
mtd.PeptideQuantificationUnit = new CVParam("PRIDE", "PRIDE:0000395", "Ratio", null);
mtd.SmallMoleculeQuantificationUnit = new CVParam("PRIDE", "PRIDE:0000395", "Ratio", null);
mtd.AddMsRunFormat(1, new CVParam("MS", "MS:1000584", "mzML file", null));
mtd.AddMsRunFormat(2, new CVParam("MS", "MS:1001062", "Mascot MGF file", null));
mtd.AddMsRunLocation(1, new Url("file://C:\\path\\to\\my\\file"));
mtd.AddMsRunLocation(2, new Url("ftp://ftp.ebi.ac.uk/path/to/file"));
mtd.AddMsRunIdFormat(1, new CVParam("MS", "MS:1001530", "mzML unique identifier", null));
mtd.AddMsRunFragmentationMethod(1, new CVParam("MS", "MS:1000133", "CID", null));
mtd.AddMsRunFragmentationMethod(2, new CVParam("MS", "MS:1000422", "HCD", null));
mtd.AddCustom(new UserParam("MS operator", "Florian"));
mtd.AddSampleSpecies(1, new CVParam("NEWT", "9606", "H**o sapiens (Human)", null));
mtd.AddSampleSpecies(1, new CVParam("NEWT", "573824", "Human rhinovirus 1", null));
mtd.AddSampleSpecies(2, new CVParam("NEWT", "9606", "H**o sapiens (Human)", null));
mtd.AddSampleSpecies(2, new CVParam("NEWT", "12130", "Human rhinovirus 2", null));
mtd.AddSampleTissue(1, new CVParam("BTO", "BTO:0000759", "liver", null));
mtd.AddSampleCellType(1, new CVParam("CL", "CL:0000182", "hepatocyte", null));
mtd.AddSampleDisease(1, new CVParam("DOID", "DOID:684", "hepatocellular carcinoma", null));
mtd.AddSampleDisease(1, new CVParam("DOID", "DOID:9451", "alcoholic fatty liver", null));
mtd.AddSampleDescription(1, "Hepatocellular carcinoma samples.");
mtd.AddSampleDescription(2, "Healthy control samples.");
mtd.AddSampleCustom(1, new UserParam("Extraction date", "2011-12-21"));
mtd.AddSampleCustom(1, new UserParam("Extraction reason", "liver biopsy"));
Sample sample1 = mtd.SampleMap[1];
Sample sample2 = mtd.SampleMap[2];
mtd.AddAssayQuantificationReagent(1, new CVParam("PRIDE", "PRIDE:0000114", "iTRAQ reagent", "114"));
mtd.AddAssayQuantificationReagent(2, new CVParam("PRIDE", "PRIDE:0000115", "iTRAQ reagent", "115"));
mtd.AddAssayQuantificationReagent(1, new CVParam("PRIDE", "MS:1002038", "unlabeled sample", null));
mtd.AddAssaySample(1, sample1);
mtd.AddAssaySample(2, sample2);
mtd.AddAssayQuantificationModParam(2, 1, new CVParam("UNIMOD", "UNIMOD:188", "Label:13C(6)", null));
mtd.AddAssayQuantificationModParam(2, 2, new CVParam("UNIMOD", "UNIMOD:188", "Label:13C(6)", null));
mtd.AddAssayQuantificationModSite(2, 1, "R");
mtd.AddAssayQuantificationModSite(2, 2, "K");
mtd.AddAssayQuantificationModPosition(2, 1, "Anywhere");
mtd.AddAssayQuantificationModPosition(2, 2, "Anywhere");
MsRun msRun1 = mtd.MsRunMap[1];
mtd.AddAssayMsRun(1, msRun1);
Assay assay1 = mtd.AssayMap[1];
Assay assay2 = mtd.AssayMap[2];
mtd.AddStudyVariableAssay(1, assay1);
mtd.AddStudyVariableAssay(1, assay2);
mtd.AddStudyVariableSample(1, sample1);
mtd.AddStudyVariableDescription(1, "description Group B (spike-in 0.74 fmol/uL)");
mtd.AddCVLabel(1, "MS");
mtd.AddCVFullName(1, "MS");
mtd.AddCVVersion(1, "3.54.0");
mtd.AddCVURL(1,
"http://psidev.cvs.sourceforge.net/viewvc/psidev/psi/psi-ms/mzML/controlledVocabulary/psi-ms.obo");
mtd.AddProteinColUnit(ProteinColumn.RELIABILITY,
new CVParam("MS", "MS:00001231", "PeptideProphet:Score", null));
MZTabColumnFactory peptideFactory = MZTabColumnFactory.GetInstance(Section.Peptide);
PeptideColumn peptideColumn = (PeptideColumn) peptideFactory.FindColumnByHeader("retention_time");
mtd.AddPeptideColUnit(peptideColumn, new CVParam("UO", "UO:0000031", "minute", null));
mtd.AddPSMColUnit(PSMColumn.RETENTION_TIME, new CVParam("UO", "UO:0000031", "minute", null));
mtd.AddSmallMoleculeColUnit(SmallMoleculeColumn.RETENTION_TIME,
new CVParam("UO", "UO:0000031", "minute", null));
Console.WriteLine(mtd);
}
public SmallMolecule(Metadata metadata)
: base(MZTabColumnFactory.GetInstance(Section.Small_Molecule))
{
this.metadata = metadata;
}
private void addPSMValue()
{
Assay assay1 = new Assay(1);
MZTabColumnFactory factory = MZTabColumnFactory.GetInstance(Section.PSM_Header);
factory.AddOptionalColumn(assay1, "my_value", typeof (string));
CVParam param = new CVParam("MS", "MS:1002217", "decoy peptide", null);
factory.AddOptionalColumn(param, typeof (string));
Metadata metadata = new Metadata();
metadata.AddMsRunLocation(2, new Url("file://C:\\path\\to\\my\\file"));
Console.WriteLine(factory);
PSM psm = new PSM(factory, metadata);
psm.Sequence = "KVPQVSTPTLVEVSR";
psm.SetPSM_ID("1");
psm.Accession = "P02768";
psm.Unique = MZBoolean.False;
psm.Database = "UniProtKB";
psm.DatabaseVersion = "2011_11";
psm.setSearchEngine("[MS,MS:1001207,Mascot,]|[MS,MS:1001208,Sequest,]");
psm.setSearchEngineScore("[MS,MS:1001155,Sequest:xcorr,2]");
psm.setReliability("3");
psm.setModifications("CHEMMOD:+159.93");
psm.AddRetentionTime(10.2);
psm.Charge = new Integer(2);
psm.SetExpMassToCharge("1234.4");
psm.SetCalcMassToCharge("123.4");
psm.SetUri("http://www.ebi.ac.uk/pride/link/to/peptide");
psm.SetSpectraRef("ms_run[2]:index=7|ms_run[2]:index=9");
psm.Pre = "K";
psm.Post = "D";
psm.Start = "45";
psm.End = "57";
Console.WriteLine(psm);
}
private void AddTitleParameter(IList<Parameter> list, IList<ParameterDescription> help, Metadata mtd)
{
string name = MetadataElement.TITLE.Name;
string desc = null;
name = CheckIfDescriptionExists(help, name, ref desc, mtd);
StringParam id = new StringParam(name){Value = mtd.Title, Help = desc};
list.Add(id);
}
private void AddMzParameters(IList<Parameter> list, IList<ParameterDescription> help, Metadata mtd)
{
string name = string.Format("{0}{1}{2}", MetadataElement.MZTAB, MZTabConstants.MINUS,
MetadataProperty.MZTAB_VERSION);
string desc = null;
name = CheckIfDescriptionExists(help, name, ref desc, mtd);
StringParam version = new StringParam(name, Constants.versions.Last()){
Help = desc
};
list.Add(version);
IList<string> values = Enum.GetNames(typeof (MzTabMode));
name = string.Format("{0}{1}{2}", MetadataElement.MZTAB, MZTabConstants.MINUS, MetadataProperty.MZTAB_MODE);
desc = null;
name = CheckIfDescriptionExists(help, name, ref desc, mtd);
SingleChoiceParam mode = new SingleChoiceParam(name){
Values = values,
Value = values.IndexOf(mtd.TabDescription.MzTabMode.ToString()),
Help = desc
};
list.Add(mode);
values = Enum.GetNames(typeof (MzTabType));
name = string.Format("{0}{1}{2}", MetadataElement.MZTAB, MZTabConstants.MINUS, MetadataProperty.MZTAB_TYPE);
desc = null;
name = CheckIfDescriptionExists(help, name, ref desc, mtd);
SingleChoiceParam type = new SingleChoiceParam(name){
Values = values,
Value = values.IndexOf(mtd.TabDescription.MzTabType.ToString()),
Help = desc
};
list.Add(type);
name = string.Format("{0}{1}{2}", MetadataElement.MZTAB, MZTabConstants.MINUS, MetadataProperty.MZTAB_ID);
desc = null;
name = CheckIfDescriptionExists(help, name, ref desc, mtd);
StringParam id = new StringParam(name){Value = mtd.TabDescription.Id, Help = desc};
list.Add(id);
}
public override IMatrixData ProcessData(IMatrixData[] inputData, Parameters param, ref IMatrixData[] supplTables,
ref IDocumentData[] documents, ProcessInfo processInfo)
{
Metadata mtd = new Metadata();
string name = string.Format("{0}{1}{2}", MetadataElement.MZTAB, MZTabConstants.MINUS,
MetadataProperty.MZTAB_VERSION);
StringParam stringParam = FindParam(param, name) as StringParam;
if (stringParam != null && !string.IsNullOrEmpty(stringParam.Value)){
mtd.MZTabVersion = stringParam.Value;
}
name = string.Format("{0}{1}{2}", MetadataElement.MZTAB, MZTabConstants.MINUS, MetadataProperty.MZTAB_MODE);
SingleChoiceParam single = FindParam(param, name) as SingleChoiceParam;
if (single != null && !string.IsNullOrEmpty(single.SelectedValue)){
MzTabMode mode;
if (Enum.TryParse(single.SelectedValue, true, out mode)){
mtd.MzTabMode = mode;
}
}
name = string.Format("{0}{1}{2}", MetadataElement.MZTAB, MZTabConstants.MINUS, MetadataProperty.MZTAB_TYPE);
single = FindParam(param, name) as SingleChoiceParam;
if (single != null && !string.IsNullOrEmpty(single.SelectedValue)){
MzTabType type;
if (Enum.TryParse(single.SelectedValue, true, out type)){
mtd.MzTabType = type;
}
}
name = string.Format("{0}{1}{2}", MetadataElement.MZTAB, MZTabConstants.MINUS, MetadataProperty.MZTAB_ID);
stringParam = FindParam(param, name) as StringParam;
if (stringParam != null && !string.IsNullOrEmpty(stringParam.Value)){
mtd.MZTabID = stringParam.Value;
}
stringParam = FindParam(param, MetadataElement.TITLE.Name) as StringParam;
if (stringParam != null && !string.IsNullOrEmpty(stringParam.Value)){
mtd.SetTitle(stringParam.Value);
}
stringParam = FindParam(param, MetadataElement.DESCRIPTION.Name) as StringParam;
if (stringParam != null && !string.IsNullOrEmpty(stringParam.Value)){
mtd.SetDescription(stringParam.Value);
}
SingleChoiceWithSubParams singleSub =
FindParam(param, MetadataElement.SAMPLE_PROCESSING.Name) as SingleChoiceWithSubParams;
if (singleSub != null){
SampleProcessingParam sub =
singleSub.SubParams[singleSub.Value].GetAllParameters().FirstOrDefault() as SampleProcessingParam;
if (sub != null){
if (sub.Value != null){
for (int j = 0; j < sub.Value.Length; j++){
mtd.SampleProcessingMap.Add(j + 1, sub.Value[j]);
}
}
}
}
singleSub = FindParam(param, MetadataElement.INSTRUMENT.Name) as SingleChoiceWithSubParams;
if (singleSub != null){
InstrumentParam sub =
singleSub.SubParams[singleSub.Value].GetAllParameters().FirstOrDefault() as InstrumentParam;
if (sub != null){
if (sub.Value != null){
for (int j = 0; j < sub.Value.Length; j++){
mtd.InstrumentMap.Add(j + 1, sub.Value[j]);
}
}
}
}
singleSub = FindParam(param, MetadataElement.SOFTWARE.Name) as SingleChoiceWithSubParams;
if (singleSub != null){
SoftwareParam sub =
singleSub.SubParams[singleSub.Value].GetAllParameters().FirstOrDefault() as SoftwareParam;
if (sub != null){
if (sub.Value != null){
for (int j = 0; j < sub.Value.Length; j++){
mtd.SoftwareMap.Add(j + 1, sub.Value[j]);
}
}
}
}
MultiChoiceParam multi = FindParam(param, MetadataElement.FALSE_DISCOVERY_RATE.Name) as MultiChoiceParam;
if (multi != null && multi.SelectedValues != null && multi.SelectedValues.Any()){
foreach (string sel in multi.SelectedValues){
string[] items = sel.Split('=');
if (items.Length != 2){
continue;
}
string key = items[0];
string value = items[1];
if (ContainsParameterKey(parameters.protein_fdr, key)){
key = "prot:global FDR";
} else if (ContainsParameterKey(parameters.psm_fdr, key)) {
key = "pep:global FDR";
} else if (ContainsParameterKey(parameters.site_fdr, key)) {
key = "site:global FDR";
}
Lib.Model.Param p = cv.GetParam(key, "MS", value);
if (p != null){
mtd.FalseDiscoveryRate.Add(p);
}
}
}
singleSub = FindParam(param, MetadataElement.PUBLICATION.Name) as SingleChoiceWithSubParams;
if (singleSub != null){
PublicationParam sub =
singleSub.SubParams[singleSub.Value].GetAllParameters().FirstOrDefault() as PublicationParam;
if (sub != null){
if (sub.Value != null){
for (int j = 0; j < sub.Value.Length; j++){
mtd.PublicationMap.Add(j + 1, sub.Value[j]);
}
}
}
}
singleSub = FindParam(param, MetadataElement.CONTACT.Name) as SingleChoiceWithSubParams;
if (singleSub != null){
ContactParam sub =
singleSub.SubParams[singleSub.Value].GetAllParameters().FirstOrDefault() as ContactParam;
if (sub != null){
if (sub.Value != null){
for (int j = 0; j < sub.Value.Length; j++){
mtd.ContactMap.Add(j + 1, sub.Value[j]);
}
}
}
}
singleSub = FindParam(param, MetadataElement.FIXED_MOD.Name) as SingleChoiceWithSubParams;
if (singleSub != null){
ModificationParam sub =
singleSub.SubParams[singleSub.Value].GetAllParameters().FirstOrDefault() as ModificationParam;
if (sub != null){
if (sub.Value != null){
for (int j = 0; j < sub.Value.Length; j++){
mtd.FixedModMap.Add(j + 1, (FixedMod) sub.Value[j]);
}
}
}
}
singleSub = FindParam(param, MetadataElement.VARIABLE_MOD.Name) as SingleChoiceWithSubParams;
if (singleSub != null){
ModificationParam sub =
singleSub.SubParams[singleSub.Value].GetAllParameters().FirstOrDefault() as ModificationParam;
if (sub != null){
if (sub.Value != null){
for (int j = 0; j < sub.Value.Length; j++){
mtd.VariableModMap.Add(j + 1, (VariableMod) sub.Value[j]);
}
}
}
}
single = FindParam(param, MetadataElement.QUANTIFICATION_METHOD.Name) as SingleChoiceParam;
if (single != null && !string.IsNullOrEmpty(single.SelectedValue)){
Lib.Model.Param temp;
mtd.QuantificationMethod = Lib.Model.Param.TryParse(single.SelectedValue, out temp)
? temp
: cv.GetParam(single.SelectedValue, "MS");
}
name = string.Format("{0}{1}{2}", MetadataElement.PROTEIN, MZTabConstants.MINUS,
MetadataProperty.PROTEIN_QUANTIFICATION_UNIT);
single = FindParam(param, name) as SingleChoiceParam;
if (single != null && !string.IsNullOrEmpty(single.SelectedValue)){
Lib.Model.Param temp;
mtd.ProteinQuantificationUnit = Lib.Model.Param.TryParse(single.SelectedValue, out temp)
? temp
: cv.GetParam(single.SelectedValue, "PRIDE");
}
name = string.Format("{0}{1}{2}", MetadataElement.PEPTIDE, MZTabConstants.MINUS,
MetadataProperty.PROTEIN_QUANTIFICATION_UNIT);
single = FindParam(param, name) as SingleChoiceParam;
if (single != null && !string.IsNullOrEmpty(single.SelectedValue)){
Lib.Model.Param temp;
mtd.PeptideQuantificationUnit = Lib.Model.Param.TryParse(single.SelectedValue, out temp)
? temp
: cv.GetParam(single.SelectedValue, "PRIDE");
}
Regex regex = new Regex("[A-Z]{1}:/");
MsRunParam msrunParam = FindParam(param, MetadataElement.MS_RUN.Name) as MsRunParam;
if (msrunParam != null){
if (msrunParam.Value != null){
for (int j = 0; j < msrunParam.Value.Length; j++){
MsRunImpl runImpl = msrunParam.Value[j];
if (regex.IsMatch(runImpl.Location.Value)){
runImpl.Location = new Url("file:\\\\\\" + runImpl.Location.Value);
}
mtd.MsRunMap.Add(j + 1, runImpl);
}
}
}
SampleParam sampleParam = FindParam(param, MetadataElement.SAMPLE.Name) as SampleParam;
if (sampleParam != null){
if (sampleParam.Value != null){
for (int j = 0; j < sampleParam.Value.Length; j++){
mtd.SampleMap.Add(j + 1, sampleParam.Value[j]);
}
}
}
AssayParam assayParam = FindParam(param, MetadataElement.ASSAY.Name) as AssayParam;
if (assayParam != null){
if (assayParam.Value != null){
for (int j = 0; j < assayParam.Value.Length; j++){
mtd.AssayMap.Add(j + 1, assayParam.Value[j]);
}
}
}
StudyVariableParam studyVariableParam =
FindParam(param, MetadataElement.STUDY_VARIABLE.Name) as StudyVariableParam;
if (studyVariableParam != null){
if (studyVariableParam.Value != null){
for (int j = 0; j < studyVariableParam.Value.Length; j++){
mtd.StudyVariableMap.Add(j + 1, studyVariableParam.Value[j]);
}
}
}
multi = FindParam(param, MetadataElement.CV.Name) as MultiChoiceParam;
if (multi != null && multi.SelectedValues != null){
var headers = cv.Headers;
foreach (string value in multi.SelectedValues){
var temp = headers.FirstOrDefault(x => x.FullName.Equals(value));
if (temp == null){
continue;
}
int id = mtd.CvMap.Count + 1;
mtd.CvMap.Add(id,
new CV(id){
FullName = temp.FullName,
Label = temp.Label,
Url = temp.Url,
Version = temp.Version
});
}
}
string mtdString = mtd.ToString();
string[] lines = mtdString.Split(new[]{"\n"}, StringSplitOptions.RemoveEmptyEntries);
List<string> columnames = new List<string>{"MTH", "key", "value"};
List<string[]> columns = columnames.Select(columname => new string[lines.Length]).ToList();
for (int n = 0; n < lines.Length; n++){
string[] items = lines[n].Split(new[]{"\t", "\n", "\r"}, StringSplitOptions.None);
if (items.Length < 3){
continue;
}
columns[0][n] = items[0];
columns[1][n] = items[1];
columns[2][n] = items[2];
}
int nrows = lines.Length;
int ncols = columnames.Count;
IMatrixData data = (IMatrixData) inputData[0].CreateNewInstance(DataType.Matrix);
data.SetData(Matrix.MetadataSection, new List<string>(), new float[nrows,ncols], columnames, columns,
new List<string>(), new List<string[][]>(), new List<string>(), new List<double[]>(),
new List<string>(), new List<double[][]>(), new List<string>(), new List<string[][]>(),
new List<string>(), new List<double[]>());
return data;
}
public Metadata CreateMetadataDefault(IMatrixData parameters, IMatrixData experiment, IMatrixData search)
{
Metadata mtd = new Metadata(new MZTabDescription(MzTabMode.Complete, MzTabType.Quantification));
List<MsRunImpl> runs = null;
List<StudyVariable> studyvariables = null;
List<Assay> assays = null;
List<Sample> samples = null;
List<Instrument> instruments = null;
GetExperminetValues(null, null, experiment, search, ref runs, ref studyvariables, ref assays, ref samples,
ref instruments);
foreach (var msRun in runs){
mtd.MsRunMap.Add(msRun.Id, msRun);
}
foreach (var studyvariable in studyvariables){
mtd.StudyVariableMap.Add(studyvariable.Id, studyvariable);
}
foreach (var sample in samples){
mtd.SampleMap.Add(sample.Id, sample);
}
foreach (var assay in assays){
mtd.AssayMap.Add(assay.Id, assay);
}
foreach (var instrument in instruments){
mtd.InstrumentMap.Add(instrument.Id, instrument);
}
SplitList<Lib.Model.Param> sampleProcessing = new SplitList<Lib.Model.Param>{
cv.GetParam("enzyme digestion", "SEP"),
cv.GetParam("reversed-phase chromatography", "SEP")
};
//sampleProcessing.Add(_cv.GetParam("ion-exchange chromatography", "SEP"));
mtd.SampleProcessingMap.Add(1, sampleProcessing);
var paramDict = MzTabMatrixUtils.ConvertToParamDict(parameters);
string key = Constants.GetKeywordName(Utils.parameters.fixedMod, paramDict.Keys.ToArray());
if (key != null){
string[] values = paramDict[key].Split(';');
foreach (var mod in values.Select(x => BaseLib.Mol.Tables.Modifications[x])){
int id = mtd.FixedModMap.Count + 1;
mtd.AddFixedModParam(id, cv.GetModificationParam(mod));
mtd.AddFixedModPosition(id, mod.Position.ToString());
mtd.AddFixedModSite(id, StringUtils.Concat(", ", mod.GetSiteArray()));
}
}
key = Constants.GetKeywordName(Utils.parameters.variableMod, paramDict.Keys.ToArray());
if (key != null){
string[] values = paramDict[key].Split(';');
foreach (var mod in values.Select(x => BaseLib.Mol.Tables.Modifications[x])){
int id = mtd.VariableModMap.Count + 1;
mtd.AddVariableModParam(id, cv.GetModificationParam(mod));
mtd.AddVariableModPosition(id, mod.Position.ToString());
mtd.AddVariableModSite(id, StringUtils.Concat(", ", mod.GetSiteArray()));
}
}
string version = Constants.GetKeywordName(Utils.parameters.version, paramDict.Keys.ToArray());
Software software = new Software(1){
Param = cv.GetParam("MaxQuant", "MS", GetParameterString(parameters, version, null))
};
mtd.SoftwareMap.Add(software.Id, software);
software = new Software(2){
Param = cv.GetParam("Andromeda", "MS", GetParameterString(parameters, version, null))
};
mtd.SoftwareMap.Add(software.Id, software);
if (assays.Count > 0){
var tmp = ArrayUtils.UniqueValues(assays.Select(x => x.QuantificationReagent.Name).ToArray());
if (tmp.Length == 1 && tmp.First().Equals("Unlabeled sample")){
mtd.QuantificationMethod = cv.GetParam("label-free proteingroup level quantitation", "MS");
}
else if (tmp.Any(x => x.Contains("SILAC"))){
mtd.QuantificationMethod = cv.GetParam("SILAC quantitation analysis", "MS");
}
}
return mtd;
}
public Peptide(MZTabColumnFactory factory, Metadata metadata)
: base(factory)
{
this.metadata = metadata;
}
public static SplitList<SpectraRef> ParseSpectraRefList(Metadata metadata, string target)
{
SplitList<string> list = ParseStringList(MZTabConstants.BAR, target);
SplitList<SpectraRef> refList = new SplitList<SpectraRef>(MZTabConstants.BAR);
Regex regex = new Regex("ms_run\\[(\\d+)\\]:(.*)");
foreach (string item in list){
if (regex.IsMatch(item.Trim())){
int ms_file_id = int.Parse(regex.Match(item.Trim()).Groups[1].Value);
string reference = regex.Match(item.Trim()).Groups[2].Value;
MsRun msRun = metadata.MsRunMap[ms_file_id];
SpectraRef sref = msRun == null ? null : new SpectraRef(msRun, reference);
if (sref == null){
refList.Clear();
break;
}
refList.Add(sref);
}
}
return refList;
}
private void addSmallMoleculeValue()
{
MsRun msRun1 = new MsRun(1);
Assay assay1 = new Assay(1);
Assay assay2 = new Assay(2);
StudyVariable studyVariable1 = new StudyVariable(1);
MZTabColumnFactory factory = MZTabColumnFactory.GetInstance(Section.Small_Molecule);
factory.AddAbundanceOptionalColumn(assay1);
factory.AddAbundanceOptionalColumn(studyVariable1);
factory.AddAbundanceOptionalColumn(assay2);
factory.AddOptionalColumn(msRun1, "my_value", typeof (string));
CVParam param = new CVParam("MS", "MS:1002217", "decoy peptide", null);
factory.AddOptionalColumn(param, typeof (string));
Metadata metadata = new Metadata();
metadata.AddMsRunLocation(2, new Url("file://C:\\path\\to\\my\\file"));
Console.WriteLine(factory);
/*TODO: SmallMolecule sm = new SmallMolecule(factory, metadata);
sm.setIdentifier("CID:00027395");
sm.setChemicalFormula("C17H20N4O2");
sm.setSmiles("C1=CC=C(C=C1)CCNC(=O)CCNNC(=O)C2=CC=NC=C2");
sm.setInchiKey("QXBMEGUKVLFJAM-UHFFFAOYSA-N");
sm.setDescription("N-(2-phenylethyl)-3-[2-(pyridine-4-carbonyl)hydrazinyl]propanamide");
sm.setExpMassToCharge("1234.4");
sm.setCalcMassToCharge("1234.5");
sm.setCharge("2");
sm.setRetentionTime("10.2|11.5");
sm.setTaxid("10116");
sm.setSpecies("Rattus norvegicus (Rat)");
sm.setDatabase("UniProtKB");
sm.setDatabaseVersion("2011_11");
sm.setReliability("2");
sm.setURI("http://www.ebi.ac.uk/pride/link/to/identification");
sm.setSpectraRef("ms_run[2]:index=7|ms_run[2]:index=9");
sm.setSearchEngine("[MS, MS:1001477, SpectraST,]");
sm.setBestSearchEngineScore("[MS, MS:1001419, SpectraST:discriminant score F, 0.7]");
sm.setModifications("CHEMMOD:+Na-H");
Console.WriteLine(sm);*/
}
public SmallMolecule(MZTabColumnFactory factory, Metadata metadata)
: base(factory)
{
this.metadata = metadata;
}
internal static string CheckIfDescriptionExists(IList<ParameterDescription> help, string title, ref string desc,
Metadata mtd)
{
string shortName = ParameterDescription.Shorten(title);
if (help != null && help.Count > 0) {
ParameterDescription parameterDescription = help.FirstOrDefault(x => x.Match(shortName));
if (parameterDescription != null) {
if (mtd != null) {
string type = parameterDescription.GetFieldType(mtd.TabDescription.MzTabType,
mtd.TabDescription.MzTabMode);
if (type != null) {
if (type.Equals("mandatory")) {
title += "*";
} else if (type.Equals("(mandatory)")) {
title += "(*)";
} else if (type.Equals("optional")) {
title += "(optional)";
} else if (type.Equals("none")) {
//TODO:
}
}
}
desc = parameterDescription.Definition;
}
}
return title;
}
public PSMLineParser(MZTabColumnFactory factory, PositionMapping positionMapping, Metadata metadata,
MZTabErrorList errorList)
: base(factory, positionMapping, metadata, errorList)
{
}
public SMHLineParser(Metadata metadata)
: base(MZTabColumnFactory.GetInstance(Section.Small_Molecule_Header), metadata)
{
}