X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=trimseqscommand.cpp;h=16d83de2596b9cf84ab4069789917878fa89559e;hp=ba368fc8569fdfde5d3587ffc5a1e65240e8acdf;hb=a8e2df1b96a57f5f29576b08361b86a96a8eff4f;hpb=a9dbc22713bfc056a797361dd757b1a5c98e1c01 diff --git a/trimseqscommand.cpp b/trimseqscommand.cpp index ba368fc..16d83de 100644 --- a/trimseqscommand.cpp +++ b/trimseqscommand.cpp @@ -15,35 +15,36 @@ //********************************************************************************************************************** vector TrimSeqsCommand::setParameters(){ try { - CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pfasta); - CommandParameter poligos("oligos", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(poligos); - CommandParameter pqfile("qfile", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pqfile); - CommandParameter pname("name", "InputTypes", "", "", "namecount", "none", "none",false,false); parameters.push_back(pname); - CommandParameter pcount("count", "InputTypes", "", "", "namecount", "none", "none",false,false); parameters.push_back(pcount); - CommandParameter pflip("flip", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(pflip); - CommandParameter pmaxambig("maxambig", "Number", "", "-1", "", "", "",false,false); parameters.push_back(pmaxambig); - CommandParameter pmaxhomop("maxhomop", "Number", "", "0", "", "", "",false,false); parameters.push_back(pmaxhomop); - CommandParameter pminlength("minlength", "Number", "", "0", "", "", "",false,false); parameters.push_back(pminlength); - CommandParameter pmaxlength("maxlength", "Number", "", "0", "", "", "",false,false); parameters.push_back(pmaxlength); - CommandParameter ppdiffs("pdiffs", "Number", "", "0", "", "", "",false,false); parameters.push_back(ppdiffs); - CommandParameter pbdiffs("bdiffs", "Number", "", "0", "", "", "",false,false); parameters.push_back(pbdiffs); - CommandParameter pldiffs("ldiffs", "Number", "", "0", "", "", "",false,false); parameters.push_back(pldiffs); - CommandParameter psdiffs("sdiffs", "Number", "", "0", "", "", "",false,false); parameters.push_back(psdiffs); - CommandParameter ptdiffs("tdiffs", "Number", "", "0", "", "", "",false,false); parameters.push_back(ptdiffs); - CommandParameter pprocessors("processors", "Number", "", "1", "", "", "",false,false); parameters.push_back(pprocessors); - CommandParameter pallfiles("allfiles", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(pallfiles); - CommandParameter pkeepforward("keepforward", "Boolean", "", "F", "", "", "",false,false); parameters.push_back(pkeepforward); - CommandParameter pqtrim("qtrim", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pqtrim); - CommandParameter pqthreshold("qthreshold", "Number", "", "0", "", "", "",false,false); parameters.push_back(pqthreshold); - CommandParameter pqaverage("qaverage", "Number", "", "0", "", "", "",false,false); parameters.push_back(pqaverage); - CommandParameter prollaverage("rollaverage", "Number", "", "0", "", "", "",false,false); parameters.push_back(prollaverage); - CommandParameter pqwindowaverage("qwindowaverage", "Number", "", "0", "", "", "",false,false); parameters.push_back(pqwindowaverage); - CommandParameter pqstepsize("qstepsize", "Number", "", "1", "", "", "",false,false); parameters.push_back(pqstepsize); - CommandParameter pqwindowsize("qwindowsize", "Number", "", "50", "", "", "",false,false); parameters.push_back(pqwindowsize); - CommandParameter pkeepfirst("keepfirst", "Number", "", "0", "", "", "",false,false); parameters.push_back(pkeepfirst); - CommandParameter premovelast("removelast", "Number", "", "0", "", "", "",false,false); parameters.push_back(premovelast); - CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir); - CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir); + CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none","fasta",false,true,true); parameters.push_back(pfasta); + CommandParameter poligos("oligos", "InputTypes", "", "", "none", "none", "none","group",false,false,true); parameters.push_back(poligos); + CommandParameter pqfile("qfile", "InputTypes", "", "", "none", "none", "none","qfile",false,false,true); parameters.push_back(pqfile); + CommandParameter pname("name", "InputTypes", "", "", "namecount", "none", "none","name",false,false,true); parameters.push_back(pname); + CommandParameter pcount("count", "InputTypes", "", "", "namecount", "none", "none","count",false,false,true); parameters.push_back(pcount); + CommandParameter pflip("flip", "Boolean", "", "F", "", "", "","",false,false,true); parameters.push_back(pflip); + CommandParameter preorient("checkorient", "Boolean", "", "F", "", "", "","",false,false,true); parameters.push_back(preorient); + CommandParameter pmaxambig("maxambig", "Number", "", "-1", "", "", "","",false,false); parameters.push_back(pmaxambig); + CommandParameter pmaxhomop("maxhomop", "Number", "", "0", "", "", "","",false,false); parameters.push_back(pmaxhomop); + CommandParameter pminlength("minlength", "Number", "", "0", "", "", "","",false,false); parameters.push_back(pminlength); + CommandParameter pmaxlength("maxlength", "Number", "", "0", "", "", "","",false,false); parameters.push_back(pmaxlength); + CommandParameter ppdiffs("pdiffs", "Number", "", "0", "", "", "","",false,false,true); parameters.push_back(ppdiffs); + CommandParameter pbdiffs("bdiffs", "Number", "", "0", "", "", "","",false,false,true); parameters.push_back(pbdiffs); + CommandParameter pldiffs("ldiffs", "Number", "", "0", "", "", "","",false,false); parameters.push_back(pldiffs); + CommandParameter psdiffs("sdiffs", "Number", "", "0", "", "", "","",false,false); parameters.push_back(psdiffs); + CommandParameter ptdiffs("tdiffs", "Number", "", "0", "", "", "","",false,false); parameters.push_back(ptdiffs); + CommandParameter pprocessors("processors", "Number", "", "1", "", "", "","",false,false,true); parameters.push_back(pprocessors); + CommandParameter pallfiles("allfiles", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(pallfiles); + CommandParameter pkeepforward("keepforward", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(pkeepforward); + CommandParameter pqtrim("qtrim", "Boolean", "", "T", "", "", "","",false,false); parameters.push_back(pqtrim); + CommandParameter pqthreshold("qthreshold", "Number", "", "0", "", "", "","",false,false); parameters.push_back(pqthreshold); + CommandParameter pqaverage("qaverage", "Number", "", "0", "", "", "","",false,false); parameters.push_back(pqaverage); + CommandParameter prollaverage("rollaverage", "Number", "", "0", "", "", "","",false,false); parameters.push_back(prollaverage); + CommandParameter pqwindowaverage("qwindowaverage", "Number", "", "0", "", "", "","",false,false); parameters.push_back(pqwindowaverage); + CommandParameter pqstepsize("qstepsize", "Number", "", "1", "", "", "","",false,false); parameters.push_back(pqstepsize); + CommandParameter pqwindowsize("qwindowsize", "Number", "", "50", "", "", "","",false,false); parameters.push_back(pqwindowsize); + CommandParameter pkeepfirst("keepfirst", "Number", "", "0", "", "", "","",false,false); parameters.push_back(pkeepfirst); + CommandParameter premovelast("removelast", "Number", "", "0", "", "", "","",false,false); parameters.push_back(premovelast); + CommandParameter pinputdir("inputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(pinputdir); + CommandParameter poutputdir("outputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(poutputdir); vector myArray; for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); } @@ -60,9 +61,10 @@ string TrimSeqsCommand::getHelpString(){ string helpString = ""; helpString += "The trim.seqs command reads a fastaFile and creates 2 new fasta files, .trim.fasta and scrap.fasta, as well as group files if you provide and oligos file.\n"; helpString += "The .trim.fasta contains sequences that meet your requirements, and the .scrap.fasta contains those which don't.\n"; - helpString += "The trim.seqs command parameters are fasta, name, count, flip, oligos, maxambig, maxhomop, minlength, maxlength, qfile, qthreshold, qaverage, diffs, qtrim, keepfirst, removelast and allfiles.\n"; + helpString += "The trim.seqs command parameters are fasta, name, count, flip, checkorient, oligos, maxambig, maxhomop, minlength, maxlength, qfile, qthreshold, qaverage, diffs, qtrim, keepfirst, removelast and allfiles.\n"; helpString += "The fasta parameter is required.\n"; helpString += "The flip parameter will output the reverse compliment of your trimmed sequence. The default is false.\n"; + helpString += "The checkorient parameter will check the reverse compliment of the sequence if the barcodes and primers cannot be found in the forward. The default is false.\n"; helpString += "The oligos parameter allows you to provide an oligos file.\n"; helpString += "The name parameter allows you to provide a names file with your fasta file.\n"; helpString += "The count parameter allows you to provide a count file with your fasta file.\n"; @@ -101,36 +103,29 @@ string TrimSeqsCommand::getHelpString(){ } } //********************************************************************************************************************** -string TrimSeqsCommand::getOutputFileNameTag(string type, string inputName=""){ - try { - string outputFileName = ""; - map >::iterator it; +string TrimSeqsCommand::getOutputPattern(string type) { + try { + string pattern = ""; - //is this a type this command creates - it = outputTypes.find(type); - if (it == outputTypes.end()) { m->mothurOut("[ERROR]: this command doesn't create a " + type + " output file.\n"); } - else { - if (type == "qfile") { outputFileName = "qual"; } - else if (type == "fasta") { outputFileName = "fasta"; } - else if (type == "group") { outputFileName = "groups"; } - else if (type == "name") { outputFileName = "names"; } - else if (type == "count") { outputFileName = "count_table"; } - else { m->mothurOut("[ERROR]: No definition for type " + type + " output file tag.\n"); m->control_pressed = true; } - } - return outputFileName; - } - catch(exception& e) { - m->errorOut(e, "TrimSeqsCommand", "getOutputFileNameTag"); - exit(1); - } + if (type == "qfile") { pattern = "[filename],[tag],qual"; } + else if (type == "fasta") { pattern = "[filename],[tag],fasta"; } + else if (type == "group") { pattern = "[filename],groups"; } + else if (type == "name") { pattern = "[filename],[tag],names"; } + else if (type == "count") { pattern = "[filename],[tag],count_table-[filename],count_table"; } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } + + return pattern; + } + catch(exception& e) { + m->errorOut(e, "TrimSeqsCommand", "getOutputPattern"); + exit(1); + } } - - //********************************************************************************************************************** TrimSeqsCommand::TrimSeqsCommand(){ try { - abort = true; calledHelp = true; + abort = true; calledHelp = true; setParameters(); vector tempOutNames; outputTypes["fasta"] = tempOutNames; @@ -333,6 +328,9 @@ TrimSeqsCommand::TrimSeqsCommand(string option) { temp = validParameter.validFile(parameters, "keepforward", false); if (temp == "not found") { temp = "F"; } keepforward = m->isTrue(temp); + + temp = validParameter.validFile(parameters, "checkorient", false); if (temp == "not found") { temp = "F"; } + reorient = m->isTrue(temp); temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = m->getProcessors(); } m->setProcessors(temp); @@ -373,6 +371,7 @@ int TrimSeqsCommand::execute(){ if (abort == true) { if (calledHelp) { return 0; } return 2; } + pairedOligos = false; numFPrimers = 0; //this needs to be initialized numRPrimers = 0; numSpacers = 0; @@ -382,15 +381,18 @@ int TrimSeqsCommand::execute(){ vector > qualFileNames; vector > nameFileNames; - string trimSeqFile = outputDir + m->getRootName(m->getSimpleName(fastaFile)) + "trim." + getOutputFileNameTag("fasta"); + map variables; + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(fastaFile)); + variables["[tag]"] = "trim"; + string trimSeqFile = getOutputFileName("fasta",variables); + string trimQualFile = getOutputFileName("qfile",variables); outputNames.push_back(trimSeqFile); outputTypes["fasta"].push_back(trimSeqFile); - - string scrapSeqFile = outputDir + m->getRootName(m->getSimpleName(fastaFile)) + "scrap." + getOutputFileNameTag("fasta"); + + variables["[tag]"] = "scrap"; + string scrapSeqFile = getOutputFileName("fasta",variables); + string scrapQualFile = getOutputFileName("qfile",variables); outputNames.push_back(scrapSeqFile); outputTypes["fasta"].push_back(scrapSeqFile); - string trimQualFile = outputDir + m->getRootName(m->getSimpleName(fastaFile)) + "trim." + getOutputFileNameTag("qfile"); - string scrapQualFile = outputDir + m->getRootName(m->getSimpleName(fastaFile)) + "scrap." + getOutputFileNameTag("qfile"); - if (qFileName != "") { outputNames.push_back(trimQualFile); outputNames.push_back(scrapQualFile); @@ -398,8 +400,11 @@ int TrimSeqsCommand::execute(){ outputTypes["qfile"].push_back(scrapQualFile); } - string trimNameFile = outputDir + m->getRootName(m->getSimpleName(nameFile)) + "trim." + getOutputFileNameTag("name"); - string scrapNameFile = outputDir + m->getRootName(m->getSimpleName(nameFile)) + "scrap." + getOutputFileNameTag("name"); + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(nameFile)); + variables["[tag]"] = "trim"; + string trimNameFile = getOutputFileName("name",variables); + variables["[tag]"] = "scrap"; + string scrapNameFile = getOutputFileName("name",variables); if (nameFile != "") { m->readNames(nameFile, nameMap); @@ -409,12 +414,15 @@ int TrimSeqsCommand::execute(){ outputTypes["name"].push_back(scrapNameFile); } - string trimCountFile = outputDir + m->getRootName(m->getSimpleName(countfile)) + "trim." + getOutputFileNameTag("count"); - string scrapCountFile = outputDir + m->getRootName(m->getSimpleName(countfile)) + "scrap." + getOutputFileNameTag("count"); + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(countfile)); + variables["[tag]"] = "trim"; + string trimCountFile = getOutputFileName("count",variables); + variables["[tag]"] = "scrap"; + string scrapCountFile = getOutputFileName("count",variables); if (countfile != "") { CountTable ct; - ct.readTable(countfile); + ct.readTable(countfile, true); nameCount = ct.getNameMap(); outputNames.push_back(trimCountFile); outputNames.push_back(scrapCountFile); @@ -429,11 +437,17 @@ int TrimSeqsCommand::execute(){ if(oligoFile != ""){ createGroup = getOligos(fastaFileNames, qualFileNames, nameFileNames); if ((createGroup) && (countfile == "")){ - outputGroupFileName = outputDir + m->getRootName(m->getSimpleName(fastaFile)) + getOutputFileNameTag("group"); + map myvariables; + myvariables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(fastaFile)); + outputGroupFileName = getOutputFileName("group",myvariables); outputNames.push_back(outputGroupFileName); outputTypes["group"].push_back(outputGroupFileName); } } - + + if (!pairedOligos) { if (reorient) { m->mothurOut("[WARNING]: You cannot use reorient without paired barcodes or primers, skipping."); m->mothurOutEndLine(); reorient = false; } } + + if (m->control_pressed) { return 0; } + //fills lines and qlines setLines(fastaFile, qFileName); @@ -488,9 +502,11 @@ int TrimSeqsCommand::execute(){ m->openInputFile(it->first, in); ofstream out; - string thisGroupName = outputDir + m->getRootName(m->getSimpleName(it->first)); - if (countfile == "") { thisGroupName += getOutputFileNameTag("group"); outputNames.push_back(thisGroupName); outputTypes["group"].push_back(thisGroupName); } - else { thisGroupName += getOutputFileNameTag("count"); outputNames.push_back(thisGroupName); outputTypes["count"].push_back(thisGroupName); } + map myvariables; + myvariables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(it->first)); + string thisGroupName = ""; + if (countfile == "") { thisGroupName = getOutputFileName("group",myvariables); outputNames.push_back(thisGroupName); outputTypes["group"].push_back(thisGroupName); } + else { thisGroupName = getOutputFileName("count",myvariables); outputNames.push_back(thisGroupName); outputTypes["count"].push_back(thisGroupName); } m->openOutputFile(thisGroupName, out); if (countfile != "") { out << "Representative_Sequence\ttotal\t" << it->second << endl; } @@ -524,7 +540,7 @@ int TrimSeqsCommand::execute(){ if (countfile != "") { //create countfile with group info included CountTable* ct = new CountTable(); - ct->readTable(trimCountFile); + ct->readTable(trimCountFile, true); map justTrimmedNames = ct->getNameMap(); delete ct; @@ -660,11 +676,32 @@ int TrimSeqsCommand::driverCreateTrim(string filename, string qFileName, string int count = 0; bool moreSeqs = 1; - TrimOligos trimOligos(pdiffs, bdiffs, ldiffs, sdiffs, primers, barcodes, revPrimer, linker, spacer); - + int numBarcodes = barcodes.size(); + TrimOligos* trimOligos = NULL; + if (pairedOligos) { trimOligos = new TrimOligos(pdiffs, bdiffs, 0, 0, pairedPrimers, pairedBarcodes); numBarcodes = pairedBarcodes.size(); } + else { trimOligos = new TrimOligos(pdiffs, bdiffs, ldiffs, sdiffs, primers, barcodes, revPrimer, linker, spacer); } + + TrimOligos* rtrimOligos = NULL; + if (reorient) { + //create reoriented primer and barcode pairs + map rpairedPrimers, rpairedBarcodes; + for (map::iterator it = pairedPrimers.begin(); it != pairedPrimers.end(); it++) { + oligosPair tempPair(reverseOligo((it->second).reverse), (reverseOligo((it->second).forward))); //reversePrimer, rc ForwardPrimer + rpairedPrimers[it->first] = tempPair; + //cout << reverseOligo((it->second).reverse) << '\t' << (reverseOligo((it->second).forward)) << '\t' << primerNameVector[it->first] << endl; + } + for (map::iterator it = pairedBarcodes.begin(); it != pairedBarcodes.end(); it++) { + oligosPair tempPair(reverseOligo((it->second).reverse), (reverseOligo((it->second).forward))); //reverseBarcode, rc ForwardBarcode + rpairedBarcodes[it->first] = tempPair; + //cout << reverseOligo((it->second).reverse) << '\t' << (reverseOligo((it->second).forward)) << '\t' << barcodeNameVector[it->first] << endl; + } + rtrimOligos = new TrimOligos(pdiffs, bdiffs, 0, 0, rpairedPrimers, rpairedBarcodes); numBarcodes = rpairedBarcodes.size(); + } + while (moreSeqs) { - if (m->control_pressed) { + if (m->control_pressed) { + delete trimOligos; if (reorient) { delete rtrimOligos; } inFASTA.close(); trimFASTAFile.close(); scrapFASTAFile.close(); if ((createGroup) && (countfile == "")) { outGroupsFile.close(); } if(qFileName != "") { qFile.close(); scrapQualFile.close(); trimQualFile.close(); } @@ -679,13 +716,15 @@ int TrimSeqsCommand::driverCreateTrim(string filename, string qFileName, string Sequence currSeq(inFASTA); m->gobble(inFASTA); //cout << currSeq.getName() << '\t' << currSeq.getUnaligned().length() << endl; + Sequence savedSeq(currSeq.getName(), currSeq.getAligned()); - QualityScores currQual; + QualityScores currQual; QualityScores savedQual; if(qFileName != ""){ currQual = QualityScores(qFile); m->gobble(qFile); + savedQual.setName(currQual.getName()); savedQual.setScores(currQual.getScores()); //cout << currQual.getName() << endl; } - + string origSeq = currSeq.getUnaligned(); if (origSeq != "") { @@ -693,38 +732,79 @@ int TrimSeqsCommand::driverCreateTrim(string filename, string qFileName, string int primerIndex = 0; if(numLinkers != 0){ - success = trimOligos.stripLinker(currSeq, currQual); + success = trimOligos->stripLinker(currSeq, currQual); if(success > ldiffs) { trashCode += 'k'; } else{ currentSeqsDiffs += success; } } - if(barcodes.size() != 0){ - success = trimOligos.stripBarcode(currSeq, currQual, barcodeIndex); - if(success > bdiffs) { trashCode += 'b'; } + if(numBarcodes != 0){ + success = trimOligos->stripBarcode(currSeq, currQual, barcodeIndex); + if(success > bdiffs) { + trashCode += 'b'; + } else{ currentSeqsDiffs += success; } } if(numSpacers != 0){ - success = trimOligos.stripSpacer(currSeq, currQual); + success = trimOligos->stripSpacer(currSeq, currQual); if(success > sdiffs) { trashCode += 's'; } else{ currentSeqsDiffs += success; } } if(numFPrimers != 0){ - success = trimOligos.stripForward(currSeq, currQual, primerIndex, keepforward); - if(success > pdiffs) { trashCode += 'f'; } + success = trimOligos->stripForward(currSeq, currQual, primerIndex, keepforward); + if(success > pdiffs) { + trashCode += 'f'; + } else{ currentSeqsDiffs += success; } } if (currentSeqsDiffs > tdiffs) { trashCode += 't'; } if(numRPrimers != 0){ - success = trimOligos.stripReverse(currSeq, currQual); + success = trimOligos->stripReverse(currSeq, currQual); if(!success) { trashCode += 'r'; } } - + + if (reorient && (trashCode != "")) { //if you failed and want to check the reverse + int thisSuccess = 0; + string thisTrashCode = ""; + int thisCurrentSeqsDiffs = 0; + + int thisBarcodeIndex = 0; + int thisPrimerIndex = 0; + + if(numBarcodes != 0){ + thisSuccess = rtrimOligos->stripBarcode(savedSeq, savedQual, thisBarcodeIndex); + if(thisSuccess > bdiffs) { thisTrashCode += "b"; } + else{ thisCurrentSeqsDiffs += thisSuccess; } + } + + if(numFPrimers != 0){ + thisSuccess = rtrimOligos->stripForward(savedSeq, savedQual, thisPrimerIndex, keepforward); + if(thisSuccess > pdiffs) { thisTrashCode += "f"; } + else{ thisCurrentSeqsDiffs += thisSuccess; } + } + + if (thisCurrentSeqsDiffs > tdiffs) { thisTrashCode += 't'; } + + if (thisTrashCode == "") { + trashCode = thisTrashCode; + success = thisSuccess; + currentSeqsDiffs = thisCurrentSeqsDiffs; + barcodeIndex = thisBarcodeIndex; + primerIndex = thisPrimerIndex; + savedSeq.reverseComplement(); + currSeq.setAligned(savedSeq.getAligned()); + if(qFileName != ""){ + savedQual.flipQScores(); + currQual.setScores(savedQual.getScores()); + } + }else { trashCode += "(" + thisTrashCode + ")"; } + } + if(keepFirst != 0){ success = keepFirstTrim(currSeq, currQual); } @@ -773,33 +853,11 @@ int TrimSeqsCommand::driverCreateTrim(string filename, string qFileName, string if (m->debug) { m->mothurOut("[DEBUG]: " + currSeq.getName() + ", trashcode= " + trashCode); if (trashCode.length() != 0) { m->mothurOutEndLine(); } } if(trashCode.length() == 0){ - currSeq.setAligned(currSeq.getUnaligned()); - currSeq.printSequence(trimFASTAFile); - - if(qFileName != ""){ - currQual.printQScores(trimQualFile); - } - - - if(nameFile != ""){ - map::iterator itName = nameMap.find(currSeq.getName()); - if (itName != nameMap.end()) { trimNameFile << itName->first << '\t' << itName->second << endl; } - else { m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your namefile, please correct."); m->mothurOutEndLine(); } - } - - int numRedundants = 0; - if (countfile != "") { - map::iterator itCount = nameCount.find(currSeq.getName()); - if (itCount != nameCount.end()) { - trimCountFile << itCount->first << '\t' << itCount->second << endl; - numRedundants = itCount->second-1; - }else { m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your count file, please correct."); m->mothurOutEndLine(); } - } - - if (createGroup) { - if(barcodes.size() != 0){ - string thisGroup = barcodeNameVector[barcodeIndex]; - if (primers.size() != 0) { + string thisGroup = ""; + if (createGroup) { + if(numBarcodes != 0){ + thisGroup = barcodeNameVector[barcodeIndex]; + if (numFPrimers != 0) { if (primerNameVector[primerIndex] != "") { if(thisGroup != "") { thisGroup += "." + primerNameVector[primerIndex]; @@ -808,52 +866,83 @@ int TrimSeqsCommand::driverCreateTrim(string filename, string qFileName, string } } } - - if (m->debug) { m->mothurOut(", group= " + thisGroup + "\n"); } - - if (countfile == "") { outGroupsFile << currSeq.getName() << '\t' << thisGroup << endl; } - else { groupMap[currSeq.getName()] = thisGroup; } - - if (nameFile != "") { - map::iterator itName = nameMap.find(currSeq.getName()); - if (itName != nameMap.end()) { - vector thisSeqsNames; - m->splitAtChar(itName->second, thisSeqsNames, ','); - numRedundants = thisSeqsNames.size()-1; //we already include ourselves below - for (int k = 1; k < thisSeqsNames.size(); k++) { //start at 1 to skip self - outGroupsFile << thisSeqsNames[k] << '\t' << thisGroup << endl; - } - }else { m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your namefile, please correct."); m->mothurOutEndLine(); } - } - - map::iterator it = groupCounts.find(thisGroup); - if (it == groupCounts.end()) { groupCounts[thisGroup] = 1 + numRedundants; } - else { groupCounts[it->first] += (1 + numRedundants); } + } + } + + int pos = thisGroup.find("ignore"); + if (pos == string::npos) { + currSeq.setAligned(currSeq.getUnaligned()); + currSeq.printSequence(trimFASTAFile); + + if(qFileName != ""){ + currQual.printQScores(trimQualFile); + } + + + if(nameFile != ""){ + map::iterator itName = nameMap.find(currSeq.getName()); + if (itName != nameMap.end()) { trimNameFile << itName->first << '\t' << itName->second << endl; } + else { m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your namefile, please correct."); m->mothurOutEndLine(); } + } + + int numRedundants = 0; + if (countfile != "") { + map::iterator itCount = nameCount.find(currSeq.getName()); + if (itCount != nameCount.end()) { + trimCountFile << itCount->first << '\t' << itCount->second << endl; + numRedundants = itCount->second-1; + }else { m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your count file, please correct."); m->mothurOutEndLine(); } + } + + if (createGroup) { + if(numBarcodes != 0){ + + if (m->debug) { m->mothurOut(", group= " + thisGroup + "\n"); } + + if (countfile == "") { outGroupsFile << currSeq.getName() << '\t' << thisGroup << endl; } + else { groupMap[currSeq.getName()] = thisGroup; } + + if (nameFile != "") { + map::iterator itName = nameMap.find(currSeq.getName()); + if (itName != nameMap.end()) { + vector thisSeqsNames; + m->splitAtChar(itName->second, thisSeqsNames, ','); + numRedundants = thisSeqsNames.size()-1; //we already include ourselves below + for (int k = 1; k < thisSeqsNames.size(); k++) { //start at 1 to skip self + outGroupsFile << thisSeqsNames[k] << '\t' << thisGroup << endl; + } + }else { m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your namefile, please correct."); m->mothurOutEndLine(); } + } + + map::iterator it = groupCounts.find(thisGroup); + if (it == groupCounts.end()) { groupCounts[thisGroup] = 1 + numRedundants; } + else { groupCounts[it->first] += (1 + numRedundants); } - } - } - - if(allFiles){ - ofstream output; - m->openOutputFileAppend(fastaFileNames[barcodeIndex][primerIndex], output); - currSeq.printSequence(output); - output.close(); - - if(qFileName != ""){ - m->openOutputFileAppend(qualFileNames[barcodeIndex][primerIndex], output); - currQual.printQScores(output); - output.close(); - } - - if(nameFile != ""){ - map::iterator itName = nameMap.find(currSeq.getName()); - if (itName != nameMap.end()) { - m->openOutputFileAppend(nameFileNames[barcodeIndex][primerIndex], output); - output << itName->first << '\t' << itName->second << endl; - output.close(); - }else { m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your namefile, please correct."); m->mothurOutEndLine(); } - } - } + } + } + + if(allFiles){ + ofstream output; + m->openOutputFileAppend(fastaFileNames[barcodeIndex][primerIndex], output); + currSeq.printSequence(output); + output.close(); + + if(qFileName != ""){ + m->openOutputFileAppend(qualFileNames[barcodeIndex][primerIndex], output); + currQual.printQScores(output); + output.close(); + } + + if(nameFile != ""){ + map::iterator itName = nameMap.find(currSeq.getName()); + if (itName != nameMap.end()) { + m->openOutputFileAppend(nameFileNames[barcodeIndex][primerIndex], output); + output << itName->first << '\t' << itName->second << endl; + output.close(); + }else { m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your namefile, please correct."); m->mothurOutEndLine(); } + } + } + } } else{ if(nameFile != ""){ //needs to be before the currSeq name is changed @@ -894,7 +983,8 @@ int TrimSeqsCommand::driverCreateTrim(string filename, string qFileName, string //report progress if((count) % 1000 != 0){ m->mothurOut(toString(count)); m->mothurOutEndLine(); } - + delete trimOligos; + if (reorient) { delete rtrimOligos; } inFASTA.close(); trimFASTAFile.close(); scrapFASTAFile.close(); @@ -1082,10 +1172,10 @@ int TrimSeqsCommand::createProcessesCreateTrim(string filename, string qFileName tempPrimerQualFileNames, tempNameFileNames, lines[h].start, lines[h].end, qLines[h].start, qLines[h].end, m, - pdiffs, bdiffs, ldiffs, sdiffs, tdiffs, primers, barcodes, revPrimer, linker, spacer, + pdiffs, bdiffs, ldiffs, sdiffs, tdiffs, primers, barcodes, revPrimer, linker, spacer, pairedBarcodes, pairedPrimers, pairedOligos, primerNameVector, barcodeNameVector, createGroup, allFiles, keepforward, keepFirst, removeLast, qWindowStep, qWindowSize, qWindowAverage, qtrim, qThreshold, qAverage, qRollAverage, - minLength, maxAmbig, maxHomoP, maxLength, flip, nameMap, nameCount); + minLength, maxAmbig, maxHomoP, maxLength, flip, reorient, nameMap, nameCount); pDataArray.push_back(tempTrim); hThreadArray[h] = CreateThread(NULL, 0, MyTrimThreadFunction, pDataArray[h], 0, &dwThreadIdArray[h]); @@ -1137,6 +1227,9 @@ int TrimSeqsCommand::createProcessesCreateTrim(string filename, string qFileName //Close all thread handles and free memory allocations. for(int i=0; i < pDataArray.size(); i++){ + if (pDataArray[i]->count != pDataArray[i]->lineEnd) { + m->mothurOut("[ERROR]: process " + toString(i) + " only processed " + toString(pDataArray[i]->count) + " of " + toString(pDataArray[i]->lineEnd) + " sequences assigned to it, quitting. \n"); m->control_pressed = true; + } for (map::iterator it = pDataArray[i]->groupCounts.begin(); it != pDataArray[i]->groupCounts.end(); it++) { map::iterator it2 = groupCounts.find(it->first); if (it2 == groupCounts.end()) { groupCounts[it->first] = it->second; } @@ -1298,6 +1391,8 @@ int TrimSeqsCommand::setLines(string filename, string qfilename) { string sname = ""; nameStream >> sname; sname = sname.substr(1); + m->checkName(sname); + map::iterator it = firstSeqNames.find(sname); if(it != firstSeqNames.end()) { //this is the start of a new chunk @@ -1396,10 +1491,15 @@ bool TrimSeqsCommand::getOligos(vector >& fastaFileNames, vector< ofstream test; - string type, oligo, group; + string type, oligo, roligo, group; + bool hasPrimer = false; bool hasPairedBarcodes = false; int indexPrimer = 0; int indexBarcode = 0; + int indexPairedPrimer = 0; + int indexPairedBarcode = 0; + set uniquePrimers; + set uniqueBarcodes; while(!inOligos.eof()){ @@ -1431,7 +1531,7 @@ bool TrimSeqsCommand::getOligos(vector >& fastaFileNames, vector< // get rest of line in case there is a primer name while (!inOligos.eof()) { char c = inOligos.get(); - if (c == 10 || c == 13){ break; } + if (c == 10 || c == 13 || c == -1){ break; } else if (c == 32 || c == 9){;} //space or tab else { group += c; } } @@ -1445,6 +1545,42 @@ bool TrimSeqsCommand::getOligos(vector >& fastaFileNames, vector< primers[oligo]=indexPrimer; indexPrimer++; primerNameVector.push_back(group); } + else if (type == "PRIMER"){ + m->gobble(inOligos); + + inOligos >> roligo; + + for(int i=0;idebug) { m->mothurOut("[DEBUG]: primer pair " + newPrimer.forward + " " + newPrimer.reverse + ", and group = " + group + ".\n"); } + + //check for repeat barcodes + string tempPair = oligo+roligo; + if (uniquePrimers.count(tempPair) != 0) { m->mothurOut("primer pair " + newPrimer.forward + " " + newPrimer.reverse + " is in your oligos file already."); m->mothurOutEndLine(); } + else { uniquePrimers.insert(tempPair); } + + if (m->debug) { if (group != "") { m->mothurOut("[DEBUG]: reading group " + group + ".\n"); }else{ m->mothurOut("[DEBUG]: no group for primer pair " + newPrimer.forward + " " + newPrimer.reverse + ".\n"); } } + + pairedPrimers[indexPairedPrimer]=newPrimer; indexPairedPrimer++; + primerNameVector.push_back(group); + hasPrimer = true; + } else if(type == "REVERSE"){ //Sequence oligoRC("reverse", oligo); //oligoRC.reverseComplement(); @@ -1453,13 +1589,49 @@ bool TrimSeqsCommand::getOligos(vector >& fastaFileNames, vector< } else if(type == "BARCODE"){ inOligos >> group; - - //check for repeat barcodes - map::iterator itBar = barcodes.find(oligo); - if (itBar != barcodes.end()) { m->mothurOut("barcode " + oligo + " is in your oligos file already."); m->mothurOutEndLine(); } - barcodes[oligo]=indexBarcode; indexBarcode++; - barcodeNameVector.push_back(group); + //barcode lines can look like BARCODE atgcatgc groupName - for 454 seqs + //or BARCODE atgcatgc atgcatgc groupName - for illumina data that has forward and reverse info + + string temp = ""; + while (!inOligos.eof()) { + char c = inOligos.get(); + if (c == 10 || c == 13 || c == -1){ break; } + else if (c == 32 || c == 9){;} //space or tab + else { temp += c; } + } + + //then this is illumina data with 4 columns + if (temp != "") { + hasPairedBarcodes = true; + string reverseBarcode = group; //reverseOligo(group); //reverse barcode + group = temp; + + for(int i=0;idebug) { m->mothurOut("[DEBUG]: barcode pair " + newPair.forward + " " + newPair.reverse + ", and group = " + group + ".\n"); } + + //check for repeat barcodes + string tempPair = oligo+reverseBarcode; + if (uniqueBarcodes.count(tempPair) != 0) { m->mothurOut("barcode pair " + newPair.forward + " " + newPair.reverse + " is in your oligos file already, disregarding."); m->mothurOutEndLine(); } + else { uniqueBarcodes.insert(tempPair); } + + pairedBarcodes[indexPairedBarcode]=newPair; indexPairedBarcode++; + barcodeNameVector.push_back(group); + }else { + //check for repeat barcodes + map::iterator itBar = barcodes.find(oligo); + if (itBar != barcodes.end()) { m->mothurOut("barcode " + oligo + " is in your oligos file already."); m->mothurOutEndLine(); } + + barcodes[oligo]=indexBarcode; indexBarcode++; + barcodeNameVector.push_back(group); + } }else if(type == "LINKER"){ linker.push_back(oligo); }else if(type == "SPACER"){ @@ -1471,8 +1643,13 @@ bool TrimSeqsCommand::getOligos(vector >& fastaFileNames, vector< } inOligos.close(); + if (hasPairedBarcodes || hasPrimer) { + pairedOligos = true; + if ((primers.size() != 0) || (barcodes.size() != 0) || (linker.size() != 0) || (spacer.size() != 0) || (revPrimer.size() != 0)) { m->control_pressed = true; m->mothurOut("[ERROR]: cannot mix paired primers and barcodes with non paired or linkers and spacers, quitting."); m->mothurOutEndLine(); return 0; } + }else if (reorient) { m->mothurOut("[Warning]: cannot use checkorient without paired barcodes or primers, ignoring.\n"); m->mothurOutEndLine(); reorient = false; } + if(barcodeNameVector.size() == 0 && primerNameVector[0] == ""){ allFiles = 0; } - + //add in potential combos if(barcodeNameVector.size() == 0){ barcodes[""] = 0; @@ -1493,67 +1670,146 @@ bool TrimSeqsCommand::getOligos(vector >& fastaFileNames, vector< if(allFiles){ set uniqueNames; //used to cleanup outputFileNames - for(map::iterator itBar = barcodes.begin();itBar != barcodes.end();itBar++){ - for(map::iterator itPrimer = primers.begin();itPrimer != primers.end(); itPrimer++){ - - string primerName = primerNameVector[itPrimer->second]; - string barcodeName = barcodeNameVector[itBar->second]; - - string comboGroupName = ""; - string fastaFileName = ""; - string qualFileName = ""; - string nameFileName = ""; - string countFileName = ""; - - if(primerName == ""){ - comboGroupName = barcodeNameVector[itBar->second]; - } - else{ - if(barcodeName == ""){ - comboGroupName = primerNameVector[itPrimer->second]; - } - else{ - comboGroupName = barcodeNameVector[itBar->second] + "." + primerNameVector[itPrimer->second]; - } - } - - - ofstream temp; - fastaFileName = outputDir + m->getRootName(m->getSimpleName(fastaFile)) + comboGroupName + ".fasta"; - if (uniqueNames.count(fastaFileName) == 0) { - outputNames.push_back(fastaFileName); - outputTypes["fasta"].push_back(fastaFileName); - uniqueNames.insert(fastaFileName); - } - - fastaFileNames[itBar->second][itPrimer->second] = fastaFileName; - m->openOutputFile(fastaFileName, temp); temp.close(); - - if(qFileName != ""){ - qualFileName = outputDir + m->getRootName(m->getSimpleName(qFileName)) + comboGroupName + ".qual"; - if (uniqueNames.count(qualFileName) == 0) { - outputNames.push_back(qualFileName); - outputTypes["qfile"].push_back(qualFileName); - } - - qualFileNames[itBar->second][itPrimer->second] = qualFileName; - m->openOutputFile(qualFileName, temp); temp.close(); - } - - if(nameFile != ""){ - nameFileName = outputDir + m->getRootName(m->getSimpleName(nameFile)) + comboGroupName + ".names"; - if (uniqueNames.count(nameFileName) == 0) { - outputNames.push_back(nameFileName); - outputTypes["name"].push_back(nameFileName); - } - - nameFileNames[itBar->second][itPrimer->second] = nameFileName; - m->openOutputFile(nameFileName, temp); temp.close(); - } - } - } + if (pairedOligos) { + for(map::iterator itBar = pairedBarcodes.begin();itBar != pairedBarcodes.end();itBar++){ + for(map::iterator itPrimer = pairedPrimers.begin();itPrimer != pairedPrimers.end(); itPrimer++){ + + string primerName = primerNameVector[itPrimer->first]; + string barcodeName = barcodeNameVector[itBar->first]; + + if ((primerName == "ignore") || (barcodeName == "ignore")) { } //do nothing + else { + string comboGroupName = ""; + string fastaFileName = ""; + string qualFileName = ""; + string nameFileName = ""; + string countFileName = ""; + + if(primerName == ""){ + comboGroupName = barcodeNameVector[itBar->first]; + } + else{ + if(barcodeName == ""){ + comboGroupName = primerNameVector[itPrimer->first]; + } + else{ + comboGroupName = barcodeNameVector[itBar->first] + "." + primerNameVector[itPrimer->first]; + } + } + + + ofstream temp; + map variables; + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(fastaFile)); + variables["[tag]"] = comboGroupName; + fastaFileName = getOutputFileName("fasta", variables); + if (uniqueNames.count(fastaFileName) == 0) { + outputNames.push_back(fastaFileName); + outputTypes["fasta"].push_back(fastaFileName); + uniqueNames.insert(fastaFileName); + } + + fastaFileNames[itBar->first][itPrimer->first] = fastaFileName; + m->openOutputFile(fastaFileName, temp); temp.close(); + + if(qFileName != ""){ + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(qFileName)); + qualFileName = getOutputFileName("qfile", variables); + if (uniqueNames.count(qualFileName) == 0) { + outputNames.push_back(qualFileName); + outputTypes["qfile"].push_back(qualFileName); + } + + qualFileNames[itBar->first][itPrimer->first] = qualFileName; + m->openOutputFile(qualFileName, temp); temp.close(); + } + + if(nameFile != ""){ + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(nameFile)); + nameFileName = getOutputFileName("name", variables); + if (uniqueNames.count(nameFileName) == 0) { + outputNames.push_back(nameFileName); + outputTypes["name"].push_back(nameFileName); + } + + nameFileNames[itBar->first][itPrimer->first] = nameFileName; + m->openOutputFile(nameFileName, temp); temp.close(); + } + } + } + } + }else { + for(map::iterator itBar = barcodes.begin();itBar != barcodes.end();itBar++){ + for(map::iterator itPrimer = primers.begin();itPrimer != primers.end(); itPrimer++){ + + string primerName = primerNameVector[itPrimer->second]; + string barcodeName = barcodeNameVector[itBar->second]; + + if ((primerName == "ignore") || (barcodeName == "ignore")) { } //do nothing + else { + string comboGroupName = ""; + string fastaFileName = ""; + string qualFileName = ""; + string nameFileName = ""; + string countFileName = ""; + + if(primerName == ""){ + comboGroupName = barcodeNameVector[itBar->second]; + } + else{ + if(barcodeName == ""){ + comboGroupName = primerNameVector[itPrimer->second]; + } + else{ + comboGroupName = barcodeNameVector[itBar->second] + "." + primerNameVector[itPrimer->second]; + } + } + + + ofstream temp; + map variables; + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(fastaFile)); + variables["[tag]"] = comboGroupName; + fastaFileName = getOutputFileName("fasta", variables); + if (uniqueNames.count(fastaFileName) == 0) { + outputNames.push_back(fastaFileName); + outputTypes["fasta"].push_back(fastaFileName); + uniqueNames.insert(fastaFileName); + } + + fastaFileNames[itBar->second][itPrimer->second] = fastaFileName; + m->openOutputFile(fastaFileName, temp); temp.close(); + + if(qFileName != ""){ + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(qFileName)); + qualFileName = getOutputFileName("qfile", variables); + if (uniqueNames.count(qualFileName) == 0) { + outputNames.push_back(qualFileName); + outputTypes["qfile"].push_back(qualFileName); + } + + qualFileNames[itBar->second][itPrimer->second] = qualFileName; + m->openOutputFile(qualFileName, temp); temp.close(); + } + + if(nameFile != ""){ + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(nameFile)); + nameFileName = getOutputFileName("name", variables); + if (uniqueNames.count(nameFileName) == 0) { + outputNames.push_back(nameFileName); + outputTypes["name"].push_back(nameFileName); + } + + nameFileNames[itBar->second][itPrimer->second] = nameFileName; + m->openOutputFile(nameFileName, temp); temp.close(); + } + } + } + } + } } numFPrimers = primers.size(); + if (pairedOligos) { numFPrimers = pairedPrimers.size(); } numRPrimers = revPrimer.size(); numLinkers = linker.size(); numSpacers = spacer.size(); @@ -1594,7 +1850,13 @@ bool TrimSeqsCommand::keepFirstTrim(Sequence& sequence, QualityScores& qscores){ if(qscores.getName() != ""){ qscores.trimQScores(-1, keepFirst); } + +// sequence.printSequence(cout);cout << endl; + sequence.trim(keepFirst); + +// sequence.printSequence(cout);cout << endl << endl;; + return success; } catch(exception& e) {