bool GenotypeSet :: AddGenotypesToTables (const RGString& xmlString, const RGString& collectionTag, const RGString& offLadderTag, const RGString& triallelesTag, const RGString& posTriTag) {
RGString XMLString (xmlString);
RGXMLTagSearch collectionSearch (collectionTag, XMLString);
size_t startOffset = 0;
size_t endOffset;
RGString collectionString;
bool returnValue = true;
size_t nameStart = 0;
size_t nameEnd;
RGString name;
GenotypesForAMarkerSet* newCollection;
GenotypesForAMarkerSet* foundCollection;
RGXMLTagSearch nameSearch ("MarkerSetName", collectionString);
while (collectionSearch.FindNextTag (startOffset, endOffset, collectionString)) {
nameSearch.ResetSearch ();
startOffset = endOffset;
if (!nameSearch.FindNextTag (nameStart, nameEnd, name)) {
returnValue = false;
continue;
}
foundCollection = FindMarkerSetCollection (name);
if (foundCollection == NULL) {
newCollection = new GenotypesForAMarkerSet (collectionString, offLadderTag, triallelesTag, posTriTag);
if (!newCollection->isValid ()) {
returnValue = false;
delete newCollection;
}
else
mGenotypes.Append (newCollection);
}
else {
if (!foundCollection->AddCollection (collectionString, offLadderTag, triallelesTag, posTriTag))
returnValue = false;
}
}
return returnValue;
}
STRBaseLocus :: STRBaseLocus (const RGString& xmlInput) : BaseLocus (xmlInput), LowerBoundGridLSIndex (-1.0),
UpperBoundGridLSIndex (-1.0), MinimumGridTime (-1.0), MaximumGridTime (-1.0), LowerBoundGridLSBasePair (-1.0),
UpperBoundGridLSBasePair (-1.0), mNoExtension (false) {
mSampleLocusSpecificStutterThreshold = Locus::GetSampleStutterThreshold ();
mSampleLocusSpecificPlusStutterThreshold = Locus::GetSamplePlusStutterThreshold ();
mSampleLocusSpecificAdenylationThreshold = Locus::GetSampleAdenylationThreshold ();
mSampleLocusSpecificFractionalFilter = Locus::GetSampleFractionalFilter ();
mSampleLocusSpecificPullupFractionalFilter = Locus::GetSamplePullupFractionalFilter ();
mSampleLocusSpecificHeterozygousImbalanceThreshold = Locus::GetHeterozygousImbalanceLimit ();
mSampleLocusSpecificMinBoundForHomozygote = Locus::GetMinBoundForHomozygote ();
mLadderLocusSpecificStutterThreshold = Locus::GetGridStutterThreshold ();
mLadderLocusSpecificAdenylationThreshold = Locus::GetGridAdenylationThreshold ();
mLadderLocusSpecificFractionalFilter = Locus::GetGridFractionalFilter ();
mLadderLocusSpecificPullupFractionalFilter = Locus::GetGridPullupFractionalFilter ();
RGString Input (xmlInput);
RGBracketStringSearch MinToken ("<MinBP>", "</MinBP>", Input);
RGBracketStringSearch MaxToken ("<MaxBP>", "</MaxBP>", Input);
RGBracketStringSearch LowerGridIndex ("<MinGridLSIndex>", "</MinGridLSIndex>", Input);
RGBracketStringSearch UpperGridIndex ("<MaxGridLSIndex>", "</MaxGridLSIndex>", Input);
RGBracketStringSearch CoreRepeatSearch ("<CoreRepeatNumber>", "</CoreRepeatNumber>", Input);
RGBracketStringSearch LowerGridBasePair ("<MinGridLSBasePair>", "</MinGridLSBasePair>", Input);
RGBracketStringSearch UpperGridBasePair ("<MaxGridLSBasePair>", "</MaxGridLSBasePair>", Input);
RGBracketStringSearch NoExtensionSearch ("<NoExtension>", "</NoExtension>", Input);
RGXMLTagSearch yLinkedSearch ("YLinked", Input);
RGXMLTagSearch maxExpectedAllelesSearch ("MaxExpectedAlleles", Input);
RGXMLTagSearch minExpectedAllelesSearch ("MinExpectedAlleles", Input);
size_t EndPosition;
RGString BPString;
RGString extString;
bool lowerBoundFound = false;
bool upperBoundFound = false;
RGString trueString ("true");
RGString familyName = BaseLocus::GetILSFamilyName ();
// cout << "Current Family Name = " << familyName.GetData () << endl; // This was a test to make sure the family name is known at this point. Test succeeded 12/31/2015.
bool useILSFamilies = PopulationCollection::UseILSFamiliesInLadderFile (); // if true, use families; otherwise, use the old way.
bool isValid = true;
size_t StartPosition = 0;
if (NoExtensionSearch.FindNextBracketedString (0, EndPosition, extString)) {
if (extString.FindNextSubstringCaseIndependent (0, trueString, EndPosition))
mNoExtension = true;
else
mNoExtension = false;
}
if (!MinToken.FindNextBracketedString (0, EndPosition, BPString)) {
Valid = FALSE;
Msg << "Locus named " << LocusName << " could not find Minimum Base Pair token\n";
MinimumBP = -1;
}
else
MinimumBP = BPString.ConvertToInteger ();
if (!MaxToken.FindNextBracketedString (0, EndPosition, BPString)) {
Valid = FALSE;
Msg << "Locus named " << LocusName << " could not find Maximum Base Pair token\n";
MaximumBP = -1;
}
else
MaximumBP = BPString.ConvertToInteger ();
if (LowerGridIndex.FindNextBracketedString (0, EndPosition, BPString)) {
LowerBoundGridLSIndex = BPString.ConvertToDouble ();
lowerBoundFound = true;
}
if (UpperGridIndex.FindNextBracketedString (0, EndPosition, BPString)) {
UpperBoundGridLSIndex = BPString.ConvertToDouble ();
upperBoundFound = true;
}
// test for ladder with ILS Family names here and, if found, use family name instead of the following four if's *******
if (useILSFamilies) {
isValid = GetLadderSearchRegion (StartPosition, Input, familyName);
if (!isValid) {
Valid = FALSE;
Msg << "Locus named " << LocusName << " could not find family-based search region\n";
}
}
else {
if (LowerGridBasePair.FindNextBracketedString (0, EndPosition, BPString)) {
LowerBoundGridLSBasePair = BPString.ConvertToDouble ();
lowerBoundFound = true;
}
if (UpperGridBasePair.FindNextBracketedString (0, EndPosition, BPString)) {
UpperBoundGridLSBasePair = BPString.ConvertToDouble ();
upperBoundFound = true;
}
if (!lowerBoundFound) {
Valid = FALSE;
Msg << "Locus named " << LocusName << " could not find Minimum Grid Internal Lane Standard token, either index or base pair\n";
}
if (!upperBoundFound) {
Valid = FALSE;
Msg << "Locus named " << LocusName << " could not find Maximum Grid Internal Lane Standard token, either index or base pair\n";
}
}
if (!CoreRepeatSearch.FindNextBracketedString (0, EndPosition, BPString))
CoreRepeatNumber = 4;
else
CoreRepeatNumber = BPString.ConvertToInteger ();
if (!yLinkedSearch.FindNextTag (0, EndPosition, BPString))
mIsYLinked = false;
else {
if (BPString == "false")
mIsYLinked = false;
else
mIsYLinked = true;
}
if (!maxExpectedAllelesSearch.FindNextTag (0, EndPosition, BPString))
mMaxExpectedAlleles = 2;
else
mMaxExpectedAlleles = BPString.ConvertToInteger ();
if (!minExpectedAllelesSearch.FindNextTag (0, EndPosition, BPString))
mMinExpectedAlleles = 1;
else
mMinExpectedAlleles = BPString.ConvertToInteger ();
if (!Valid) {
Msg << "XML Input:\n" << Input << "\n";
}
}
STRBaseLocus :: STRBaseLocus (const RGString& xmlInput) : BaseLocus (xmlInput), LowerBoundGridLSIndex (-1.0),
UpperBoundGridLSIndex (-1.0), MinimumGridTime (-1.0), MaximumGridTime (-1.0), LowerBoundGridLSBasePair (-1.0),
UpperBoundGridLSBasePair (-1.0) {
mSampleLocusSpecificStutterThreshold = Locus::GetSampleStutterThreshold ();
mSampleLocusSpecificPlusStutterThreshold = Locus::GetSamplePlusStutterThreshold ();
mSampleLocusSpecificAdenylationThreshold = Locus::GetSampleAdenylationThreshold ();
mSampleLocusSpecificFractionalFilter = Locus::GetSampleFractionalFilter ();
mSampleLocusSpecificPullupFractionalFilter = Locus::GetSamplePullupFractionalFilter ();
mSampleLocusSpecificHeterozygousImbalanceThreshold = Locus::GetHeterozygousImbalanceLimit ();
mSampleLocusSpecificMinBoundForHomozygote = Locus::GetMinBoundForHomozygote ();
mLadderLocusSpecificStutterThreshold = Locus::GetGridStutterThreshold ();
mLadderLocusSpecificAdenylationThreshold = Locus::GetGridAdenylationThreshold ();
mLadderLocusSpecificFractionalFilter = Locus::GetGridFractionalFilter ();
mLadderLocusSpecificPullupFractionalFilter = Locus::GetGridPullupFractionalFilter ();
RGString Input (xmlInput);
RGBracketStringSearch MinToken ("<MinBP>", "</MinBP>", Input);
RGBracketStringSearch MaxToken ("<MaxBP>", "</MaxBP>", Input);
RGBracketStringSearch LowerGridIndex ("<MinGridLSIndex>", "</MinGridLSIndex>", Input);
RGBracketStringSearch UpperGridIndex ("<MaxGridLSIndex>", "</MaxGridLSIndex>", Input);
RGBracketStringSearch CoreRepeatSearch ("<CoreRepeatNumber>", "</CoreRepeatNumber>", Input);
RGBracketStringSearch LowerGridBasePair ("<MinGridLSBasePair>", "</MinGridLSBasePair>", Input);
RGBracketStringSearch UpperGridBasePair ("<MaxGridLSBasePair>", "</MaxGridLSBasePair>", Input);
RGXMLTagSearch yLinkedSearch ("YLinked", Input);
RGXMLTagSearch maxExpectedAllelesSearch ("MaxExpectedAlleles", Input);
RGXMLTagSearch minExpectedAllelesSearch ("MinExpectedAlleles", Input);
size_t EndPosition;
RGString BPString;
bool lowerBoundFound = false;
bool upperBoundFound = false;
if (!MinToken.FindNextBracketedString (0, EndPosition, BPString)) {
Valid = FALSE;
Msg << "Locus named " << LocusName << " could not find Minimum Base Pair token\n";
MinimumBP = -1;
}
else
MinimumBP = BPString.ConvertToInteger ();
if (!MaxToken.FindNextBracketedString (0, EndPosition, BPString)) {
Valid = FALSE;
Msg << "Locus named " << LocusName << " could not find Maximum Base Pair token\n";
MaximumBP = -1;
}
else
MaximumBP = BPString.ConvertToInteger ();
if (LowerGridIndex.FindNextBracketedString (0, EndPosition, BPString)) {
LowerBoundGridLSIndex = BPString.ConvertToDouble ();
lowerBoundFound = true;
}
if (UpperGridIndex.FindNextBracketedString (0, EndPosition, BPString)) {
UpperBoundGridLSIndex = BPString.ConvertToDouble ();
upperBoundFound = true;
}
if (LowerGridBasePair.FindNextBracketedString (0, EndPosition, BPString)) {
LowerBoundGridLSBasePair = BPString.ConvertToDouble ();
lowerBoundFound = true;
}
if (UpperGridBasePair.FindNextBracketedString (0, EndPosition, BPString)) {
UpperBoundGridLSBasePair = BPString.ConvertToDouble ();
upperBoundFound = true;
}
if (!lowerBoundFound) {
Valid = FALSE;
Msg << "Locus named " << LocusName << " could not find Minimum Grid Internal Lane Standard token, either index or base pair\n";
}
if (!upperBoundFound) {
Valid = FALSE;
Msg << "Locus named " << LocusName << " could not find Maximum Grid Internal Lane Standard token, either index or base pair\n";
}
if (!CoreRepeatSearch.FindNextBracketedString (0, EndPosition, BPString))
CoreRepeatNumber = 4;
else
CoreRepeatNumber = BPString.ConvertToInteger ();
if (!yLinkedSearch.FindNextTag (0, EndPosition, BPString))
mIsYLinked = false;
else {
if (BPString == "false")
mIsYLinked = false;
else
mIsYLinked = true;
}
if (!maxExpectedAllelesSearch.FindNextTag (0, EndPosition, BPString))
mMaxExpectedAlleles = 2;
else
mMaxExpectedAlleles = BPString.ConvertToInteger ();
if (!minExpectedAllelesSearch.FindNextTag (0, EndPosition, BPString))
mMinExpectedAlleles = 1;
else
mMinExpectedAlleles = BPString.ConvertToInteger ();
if (!Valid) {
Msg << "XML Input:\n" << Input << "\n";
}
}
bool GenotypesForAMarkerSet :: AddCollectionToTables (const RGString& xmlString, const RGString& offLadderTag, const RGString& triallelesTag, const RGString& posTriTag) {
RGString XMLString (xmlString);
RGString positiveControlString;
RGString pControlsString;
RGString fullPathControlFileName = GenotypesForAMarkerSet::PathToStandardControlFile + "/LadderSpecifications/StandardPositiveControls.xml";
RGFile* allPositiveControls = new RGFile (fullPathControlFileName, "rt");
if (!allPositiveControls->isValid ()) {
cout << "Could not find positive controls file: " << (char*)fullPathControlFileName.GetData () << endl;
return false;
}
RGString posXMLString;
posXMLString.ReadTextFile (*allPositiveControls);
delete allPositiveControls;
RGXMLTagSearch nameSearch ("MarkerSetName", XMLString);
RGXMLTagSearch positiveControlsSearch ("PositiveControls", posXMLString);
RGXMLTagSearch oldPositiveControlsSearch ("PositiveControls", XMLString);
RGXMLTagSearch posCtrlSearch ("PositiveControl", pControlsString);
RGXMLTagSearch offLadderSearch (offLadderTag, XMLString);
RGXMLTagSearch trialleleSearch (triallelesTag, XMLString);
RGXMLTagSearch posTriSearch (posTriTag, XMLString);
size_t startOffset = 0;
size_t endOffset = 0;
RGString collectionString;
RGString offLadderString;
RGString triString;
RGString posTriString;
size_t startPControls = 0;
size_t endPControls = 0;
bool returnValue = true;
RGString markerSetName;
IndividualGenotype* nextGenotype;
if (!nameSearch.FindNextTag (startOffset, endOffset, markerSetName))
return false;
if (mMarkerSetName.Length () == 0)
mMarkerSetName = markerSetName;
else if (mMarkerSetName != markerSetName)
return false;
startOffset = endOffset;
size_t startOffsetPos = 0;
size_t endOffsetPos = 0;
RGString temp;
if (oldPositiveControlsSearch.FindNextTag (startOffset, endOffset, temp))
startOffset = endOffset;
if (positiveControlsSearch.FindNextTag (startOffsetPos, endOffsetPos, pControlsString)) {
posCtrlSearch.ResetSearch ();
// cout << "Found positive controls in file" << endl;
while (posCtrlSearch.FindNextTag (startPControls, endPControls, positiveControlString)) {
// cout << "Found positive control..." << endl;
startPControls = endPControls;
nextGenotype = new IndividualGenotype (positiveControlString);
if (!nextGenotype->isValid ()) {
returnValue = false;
delete nextGenotype;
}
else {
if (!mGenotypes.Contains (nextGenotype)) {
mGenotypes.Insert (nextGenotype);
// cout << "Inserted genotype in list..." << endl;
}
else {
returnValue = false;
delete nextGenotype;
}
}
}
}
startOffset = endOffset;
if (offLadderSearch.FindNextTag (startOffset, endOffset, offLadderString)) {
if (mOffLadderAlleles == NULL) {
mOffLadderAlleles = new LocusCollection (offLadderString);
if (!mOffLadderAlleles->isValid ())
returnValue = false;
}
else {
if (!mOffLadderAlleles->AddLoci (offLadderString))
returnValue = false;
}
}
startOffset = endOffset;
if (trialleleSearch.FindNextTag (startOffset, endOffset, triString)) {
if (mSampleTriAlleles == NULL) {
mSampleTriAlleles = new LocusCollection (triString);
if (!mSampleTriAlleles->isValid ())
returnValue = false;
}
else {
if (!mSampleTriAlleles->AddLoci (triString))
returnValue = false;
}
}
startOffset = endOffset;
if (posTriSearch.FindNextTag (startOffset, endOffset, posTriString)) {
if (mControlTriAlleles == NULL) {
mControlTriAlleles = new LocusCollection (posTriString);
if (!mControlTriAlleles->isValid ())
returnValue = false;
}
else {
if (!mControlTriAlleles->AddLoci (posTriString))
returnValue = false;
}
}
return returnValue;
}
bool GenotypesForAMarkerSet :: AddCollectionToTablesFromLabSettings (const RGString& xmlString, const RGString& offLadderTag, const RGString& triallelesTag, const RGString& posTriTag) {
RGString XMLString (xmlString);
RGString positiveControlString;
RGString pControlsString;
RGXMLTagSearch nameSearch ("MarkerSetName", XMLString);
RGXMLTagSearch positiveControlsSearch ("PositiveControls", XMLString);
RGXMLTagSearch posCtrlSearch ("PositiveControl", pControlsString);
RGXMLTagSearch offLadderSearch (offLadderTag, XMLString);
RGXMLTagSearch trialleleSearch (triallelesTag, XMLString);
RGXMLTagSearch posTriSearch (posTriTag, XMLString);
size_t startOffset = 0;
size_t endOffset = 0;
RGString collectionString;
RGString offLadderString;
RGString triString;
RGString posTriString;
size_t startPControls = 0;
size_t endPControls = 0;
bool returnValue = true;
RGString markerSetName;
IndividualGenotype* nextGenotype;
if (!nameSearch.FindNextTag (startOffset, endOffset, markerSetName))
return false;
if (mMarkerSetName.Length () == 0)
mMarkerSetName = markerSetName;
else if (mMarkerSetName != markerSetName)
return false;
startOffset = endOffset;
if (positiveControlsSearch.FindNextTag (startOffset, endOffset, pControlsString)) {
posCtrlSearch.ResetSearch ();
startOffset = endOffset;
cout << "Found positive controls in lab settings file" << endl;
while (posCtrlSearch.FindNextTag (startPControls, endPControls, positiveControlString)) {
cout << "Found positive control..." << endl;
startPControls = endPControls;
nextGenotype = new IndividualGenotype (positiveControlString);
if (!nextGenotype->isValid ()) {
returnValue = false;
delete nextGenotype;
}
else {
if (!mGenotypes.Contains (nextGenotype)) {
mGenotypes.Insert (nextGenotype);
cout << "Inserted genotype in list..." << endl;
}
else {
//returnValue = false;
cout << "\nWARNING***Found duplicate positive control named " << nextGenotype->GetName ().GetData () << ". Ignoring...\n" << endl;
delete nextGenotype;
}
}
}
}
startOffset = endOffset;
if (offLadderSearch.FindNextTag (startOffset, endOffset, offLadderString)) {
if (mOffLadderAlleles == NULL) {
mOffLadderAlleles = new LocusCollection (offLadderString);
if (!mOffLadderAlleles->isValid ())
returnValue = false;
}
else {
if (!mOffLadderAlleles->AddLoci (offLadderString))
returnValue = false;
}
}
startOffset = endOffset;
if (trialleleSearch.FindNextTag (startOffset, endOffset, triString)) {
if (mSampleTriAlleles == NULL) {
mSampleTriAlleles = new LocusCollection (triString);
if (!mSampleTriAlleles->isValid ())
returnValue = false;
}
else {
if (!mSampleTriAlleles->AddLoci (triString))
returnValue = false;
}
}
startOffset = endOffset;
if (posTriSearch.FindNextTag (startOffset, endOffset, posTriString)) {
if (mControlTriAlleles == NULL) {
mControlTriAlleles = new LocusCollection (posTriString);
if (!mControlTriAlleles->isValid ())
returnValue = false;
}
else {
if (!mControlTriAlleles->AddLoci (posTriString))
returnValue = false;
}
}
return returnValue;
}
int Ladder :: AmendLadderData (LadderInputFile* inFile, RGString& oldLadderString) {
RGString newLadderString;
// Parse oldLadder data into pieces for individual edits
RGString locusString;
RGString* newLocusString;
RGDList locusStrings;
size_t startPos = 0;
size_t endPos;
RGXMLTagSearch locusSearch ("Locus", oldLadderString);
RGXMLTagSearch searchRegionsSearch ("SearchRegions", oldLadderString);
RGString* ilsName = (RGString*)inFile->GetILSNameList ().First ();
endPos = 0;
oldLadderString.FindNextSubstring (0, "\t\t\t<Locus>", endPos);
RGString insertBase;
insertBase << "\t\t\t\t\t<ILSName>" << ilsName->GetData () << "</ILSName>\n";
insertBase << "\t\t\t\t</LSBases>";
RGString leadString = oldLadderString.ExtractSubstring (0, endPos - 1);
//cout << "Lead string = \n" << leadString.GetData () << endl;
endPos = 0;
leadString.FindAndReplaceNextSubstring ("\t\t\t\t</LSBases>", insertBase, endPos);
//cout << "Lead string = \n" << leadString.GetData () << endl;
newLadderString << leadString;
startPos = 0;
while (locusSearch.FindNextTag (startPos, endPos, locusString)) {
newLocusString = new RGString (locusString);
locusStrings.Append (newLocusString);
startPos = endPos;
}
if (mLocusList.size () != locusStrings.Entries ()) {
cout << "Number of loci in bins file does not match number of loci in ladder file" << endl;
return -152;
}
Locus* nextLocus;
RGString locusInsert;
RGString currentLocusString;
RGString nameString;
RGXMLTagSearch locusNameSearch ("Name", currentLocusString);
RGXMLTagSearch coreRepeatSearch ("CoreRepeatNumber", currentLocusString);
double minSearch;
double maxSearch;
RGString repeatString;
int repeatNumber;
while (locusStrings.Entries () > 0) {
newLocusString = (RGString*) locusStrings.GetFirst ();
currentLocusString = *newLocusString;
locusNameSearch.ResetSearch ();
coreRepeatSearch.ResetSearch ();
locusNameSearch.FindNextTag (0, endPos, nameString);
nextLocus = FindLocusByName (nameString);
if (nextLocus == NULL) {
cout << "Could not find locus named " << nameString.GetData () << ". Exiting..." << endl;
return -155;
}
if (!coreRepeatSearch.FindNextTag (0, endPos, repeatString))
repeatNumber = 4;
else
repeatNumber = repeatString.ConvertToInteger ();
locusInsert = "";
minSearch = nextLocus->GetMinSearchILSBP () - repeatNumber + 1;
maxSearch = nextLocus->GetMaxSearchILSBP () + repeatNumber -1;
locusInsert << "\t\t\t\t\t<Region>\n";
locusInsert << "\t\t\t\t\t\t<ILSName>" << ilsName->GetData () << "</ILSName>\n";
locusInsert << "\t\t\t\t\t\t<MinGrid>" << 0.01 * floor (100.0 * minSearch + 0.5) << "</MinGrid>\n";
locusInsert << "\t\t\t\t\t\t<MaxGrid>" << 0.01 * floor (100.0 * maxSearch + 0.5) << "</MaxGrid>\n";
locusInsert << "\t\t\t\t\t</Region>\n";
locusInsert << "\t\t\t\t</SearchRegions>";
endPos = 0;
currentLocusString.FindAndReplaceNextSubstring ("\t\t\t\t</SearchRegions>", locusInsert, endPos);
newLadderString << "\t\t\t<Locus>" << currentLocusString << "</Locus>\n";
delete newLocusString;
}
newLadderString << "\t\t</Set>\n";
newLadderString << "\t</Kits>\n";
newLadderString << "</KitData>\n";
RGString ladderPath = inFile->GetOutputConfigDirectoryPath () + "/" + inFile->GetLadderFileName ();
RGTextOutput ladderOutput (ladderPath, FALSE);
if (!ladderOutput.FileIsValid ()) {
cout << "Could not open ladder output file: " << ladderPath.GetData () << endl;
return -161;
}
ladderOutput << newLadderString;
cout << "Ladder update completed successfully..." << endl;
return 0;
}
