X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=trimseqscommand.h;h=80e1ebe1a00e2f56ec19a6f23c3ba890af1c4f10;hb=dd9beffb7a3ac5c0007c4c224b216e8b8b2f9abb;hp=ba4e61411b8498820139e8ae2b1ed71cb37b0432;hpb=050e1297eaf24fabbbe0e9b76c3a5acfb90eed7d;p=mothur.git diff --git a/trimseqscommand.h b/trimseqscommand.h index ba4e614..80e1ebe 100644 --- a/trimseqscommand.h +++ b/trimseqscommand.h @@ -14,8 +14,8 @@ #include "command.hpp" #include "sequence.hpp" #include "qualityscores.h" -#include "groupmap.h" #include "trimoligos.h" +#include "counttable.h" class TrimSeqsCommand : public Command { @@ -27,7 +27,9 @@ public: vector setParameters(); string getCommandName() { return "trim.seqs"; } string getCommandCategory() { return "Sequence Processing"; } + string getHelpString(); + string getOutputPattern(string); string getCitation() { return "http://www.mothur.org/wiki/Trim.seqs"; } string getDescription() { return "provides the preprocessing features needed to screen and sort pyrosequences"; } @@ -35,16 +37,13 @@ public: void help() { m->mothurOut(getHelpString()); } private: - - GroupMap* groupMap; - struct linePair { unsigned long long start; unsigned long long end; linePair(unsigned long long i, unsigned long long j) : start(i), end(j) {} linePair() {} }; - + bool getOligos(vector >&, vector >&, vector >&); bool keepFirstTrim(Sequence&, QualityScores&); bool removeLastTrim(Sequence&, QualityScores&); @@ -54,7 +53,7 @@ private: string reverseOligo(string); bool abort, createGroup; - string fastaFile, oligoFile, qFileName, groupfile, nameFile, outputDir; + string fastaFile, oligoFile, qFileName, groupfile, nameFile, countfile, outputDir; bool flip, allFiles, qtrim, keepforward; int numFPrimers, numRPrimers, numLinkers, numSpacers, maxAmbig, maxHomoP, minLength, maxLength, processors, tdiffs, bdiffs, pdiffs, ldiffs, sdiffs, comboStarts; @@ -63,7 +62,6 @@ private: vector revPrimer, outputNames; set filesToRemove; map barcodes; - map rbarcodes; vector groupVector; map primers; vector linker; @@ -74,13 +72,15 @@ private: vector barcodeNameVector; //needed here? map groupCounts; map nameMap; + map nameCount; //for countfile name -> repCount + map groupMap; //for countfile name -> group vector processIDS; //processid vector lines; vector qLines; - int driverCreateTrim(string, string, string, string, string, string, string, string, string, vector >, vector >, vector >, linePair, linePair); - int createProcessesCreateTrim(string, string, string, string, string, string, string, string, string, vector >, vector >, vector >); + int driverCreateTrim(string, string, string, string, string, string, string, string, string, string, string, vector >, vector >, vector >, linePair, linePair); + int createProcessesCreateTrim(string, string, string, string, string, string, string, string, string, string, string, vector >, vector >, vector >); int setLines(string, string); }; @@ -91,7 +91,7 @@ private: struct trimData { unsigned long long start, end; MothurOut* m; - string filename, qFileName, trimFileName, scrapFileName, trimQFileName, scrapQFileName, trimNFileName, scrapNFileName, groupFileName, nameFile; + string filename, qFileName, trimFileName, scrapFileName, trimQFileName, scrapQFileName, trimNFileName, scrapNFileName, trimCFileName, scrapCFileName, groupFileName, nameFile, countfile; vector > fastaFileNames; vector > qualFileNames; vector > nameFileNames; @@ -102,8 +102,8 @@ struct trimData { double qRollAverage, qThreshold, qWindowAverage, qAverage; vector revPrimer; map barcodes; - map rbarcodes; map primers; + map nameCount; vector linker; vector spacer; map combos; @@ -111,22 +111,26 @@ struct trimData { vector barcodeNameVector; map groupCounts; map nameMap; + map groupMap; trimData(){} - trimData(string fn, string qn, string nf, string tn, string sn, string tqn, string sqn, string tnn, string snn, string gn, vector > ffn, vector > qfn, vector > nfn, unsigned long long lstart, unsigned long long lend, unsigned long long qstart, unsigned long long qend, MothurOut* mout, - int pd, int bd, int ld, int sd, int td, map pri, map bar, map rbar, vector revP, vector li, vector spa, + trimData(string fn, string qn, string nf, string cf, string tn, string sn, string tqn, string sqn, string tnn, string snn, string tcn, string scn,string gn, vector > ffn, vector > qfn, vector > nfn, unsigned long long lstart, unsigned long long lend, unsigned long long qstart, unsigned long long qend, MothurOut* mout, + int pd, int bd, int ld, int sd, int td, map pri, map bar, vector revP, vector li, vector spa, vector priNameVector, vector barNameVector, bool cGroup, bool aFiles, bool keepF, int keepfi, int removeL, int WindowStep, int WindowSize, int WindowAverage, bool trim, double Threshold, double Average, double RollAverage, - int minL, int maxA, int maxH, int maxL, bool fli, map nm) { + int minL, int maxA, int maxH, int maxL, bool fli, map nm, map ncount) { filename = fn; qFileName = qn; nameFile = nf; + countfile = cf; trimFileName = tn; scrapFileName = sn; trimQFileName = tqn; scrapQFileName = sqn; trimNFileName = tnn; scrapNFileName = snn; + trimCFileName = tcn; + scrapCFileName = scn; groupFileName = gn; fastaFileNames = ffn; qualFileNames = qfn; @@ -136,6 +140,7 @@ struct trimData { qlineStart = qstart; qlineEnd = qend; m = mout; + nameCount = ncount; pdiffs = pd; bdiffs = bd; @@ -143,7 +148,6 @@ struct trimData { sdiffs = sd; tdiffs = td; barcodes = bar; - rbarcodes = rbar; primers = pri; numFPrimers = primers.size(); revPrimer = revP; numRPrimers = revPrimer.size(); linker = li; numLinkers = linker.size(); @@ -202,7 +206,7 @@ static DWORD WINAPI MyTrimThreadFunction(LPVOID lpParam){ ofstream outGroupsFile; - if (pDataArray->createGroup){ pDataArray->m->openOutputFile(pDataArray->groupFileName, outGroupsFile); } + if ((pDataArray->createGroup) && (pDataArray->countfile == "")){ pDataArray->m->openOutputFile(pDataArray->groupFileName, outGroupsFile); } if(pDataArray->allFiles){ for (int i = 0; i < pDataArray->fastaFileNames.size(); i++) { //clears old file for (int j = 0; j < pDataArray->fastaFileNames[i].size(); j++) { //clears old file @@ -221,6 +225,14 @@ static DWORD WINAPI MyTrimThreadFunction(LPVOID lpParam){ } } + ofstream trimCountFile; + ofstream scrapCountFile; + if(pDataArray->countfile != ""){ + pDataArray->m->openOutputFile(pDataArray->trimCFileName, trimCountFile); + pDataArray->m->openOutputFile(pDataArray->scrapCFileName, scrapCountFile); + if ((pDataArray->lineStart == 0) || (pDataArray->lineStart == 1)) { trimCountFile << "Representative_Sequence\ttotal" << endl; scrapCountFile << "Representative_Sequence\ttotal" << endl; } + } + ifstream inFASTA; pDataArray->m->openInputFile(pDataArray->filename, inFASTA); if ((pDataArray->lineStart == 0) || (pDataArray->lineStart == 1)) { @@ -240,14 +252,18 @@ static DWORD WINAPI MyTrimThreadFunction(LPVOID lpParam){ } - TrimOligos trimOligos(pDataArray->pdiffs, pDataArray->bdiffs, pDataArray->ldiffs, pDataArray->sdiffs, pDataArray->primers, pDataArray->barcodes, pDataArray->rbarcodes, pDataArray->revPrimer, pDataArray->linker, pDataArray->spacer); + TrimOligos trimOligos(pDataArray->pdiffs, pDataArray->bdiffs, pDataArray->ldiffs, pDataArray->sdiffs, pDataArray->primers, pDataArray->barcodes, pDataArray->revPrimer, pDataArray->linker, pDataArray->spacer); - pDataArray->count = pDataArray->lineEnd; + pDataArray->count = 0; for(int i = 0; i < pDataArray->lineEnd; i++){ //end is the number of sequences to process if (pDataArray->m->control_pressed) { inFASTA.close(); trimFASTAFile.close(); scrapFASTAFile.close(); - if (pDataArray->createGroup) { outGroupsFile.close(); } + if ((pDataArray->createGroup) && (pDataArray->countfile == "")) { outGroupsFile.close(); } + if(pDataArray->qFileName != "") { qFile.close(); scrapQualFile.close(); trimQualFile.close(); } + if(pDataArray->nameFile != "") { scrapNameFile.close(); trimNameFile.close(); } + if(pDataArray->countfile != "") { scrapCountFile.close(); trimCountFile.close(); } + if(pDataArray->qFileName != ""){ qFile.close(); } return 0; } @@ -265,6 +281,7 @@ static DWORD WINAPI MyTrimThreadFunction(LPVOID lpParam){ string origSeq = currSeq.getUnaligned(); if (origSeq != "") { + pDataArray->count++; int barcodeIndex = 0; int primerIndex = 0; @@ -281,12 +298,6 @@ static DWORD WINAPI MyTrimThreadFunction(LPVOID lpParam){ else{ currentSeqsDiffs += success; } } - if(pDataArray->rbarcodes.size() != 0){ - success = trimOligos.stripRBarcode(currSeq, currQual, barcodeIndex); - if(success > pDataArray->bdiffs) { trashCode += 'b'; } - else{ currentSeqsDiffs += success; } - } - if(pDataArray->numSpacers != 0){ success = trimOligos.stripSpacer(currSeq, currQual); if(success > pDataArray->sdiffs) { trashCode += 's'; } @@ -385,22 +396,10 @@ static DWORD WINAPI MyTrimThreadFunction(LPVOID lpParam){ } if(trashCode.length() == 0){ - currSeq.setAligned(currSeq.getUnaligned()); - currSeq.printSequence(trimFASTAFile); - - if(pDataArray->qFileName != ""){ - currQual.printQScores(trimQualFile); - } - - if(pDataArray->nameFile != ""){ - map::iterator itName = pDataArray->nameMap.find(currSeq.getName()); - if (itName != pDataArray->nameMap.end()) { trimNameFile << itName->first << '\t' << itName->second << endl; } - else { pDataArray->m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your namefile, please correct."); pDataArray->m->mothurOutEndLine(); } - } - - if (pDataArray->createGroup) { + string thisGroup = ""; + if (pDataArray->createGroup) { if(pDataArray->barcodes.size() != 0){ - string thisGroup = pDataArray->barcodeNameVector[barcodeIndex]; + thisGroup = pDataArray->barcodeNameVector[barcodeIndex]; if (pDataArray->primers.size() != 0) { if (pDataArray->primerNameVector[primerIndex] != "") { if(thisGroup != "") { @@ -410,48 +409,81 @@ static DWORD WINAPI MyTrimThreadFunction(LPVOID lpParam){ } } } - - outGroupsFile << currSeq.getName() << '\t' << thisGroup << endl; - - if (pDataArray->nameFile != "") { - map::iterator itName = pDataArray->nameMap.find(currSeq.getName()); - if (itName != pDataArray->nameMap.end()) { - vector thisSeqsNames; - pDataArray->m->splitAtChar(itName->second, thisSeqsNames, ','); - for (int k = 1; k < thisSeqsNames.size(); k++) { //start at 1 to skip self - outGroupsFile << thisSeqsNames[k] << '\t' << thisGroup << endl; - } - }else { pDataArray->m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your namefile, please correct."); pDataArray->m->mothurOutEndLine(); } - } - - map::iterator it = pDataArray->groupCounts.find(thisGroup); - if (it == pDataArray->groupCounts.end()) { pDataArray->groupCounts[thisGroup] = 1; } - else { pDataArray->groupCounts[it->first]++; } + } + } + + int pos = thisGroup.find("ignore"); + if (pos == string::npos) { + + currSeq.setAligned(currSeq.getUnaligned()); + currSeq.printSequence(trimFASTAFile); + + if(pDataArray->qFileName != ""){ + currQual.printQScores(trimQualFile); + } + + if(pDataArray->nameFile != ""){ + map::iterator itName = pDataArray->nameMap.find(currSeq.getName()); + if (itName != pDataArray->nameMap.end()) { trimNameFile << itName->first << '\t' << itName->second << endl; } + else { pDataArray->m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your namefile, please correct."); pDataArray->m->mothurOutEndLine(); } + } + + int numRedundants = 0; + if (pDataArray->countfile != "") { + map::iterator itCount = pDataArray->nameCount.find(currSeq.getName()); + if (itCount != pDataArray->nameCount.end()) { + trimCountFile << itCount->first << '\t' << itCount->second << endl; + numRedundants = itCount->second-1; + }else { pDataArray->m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your count file, please correct."); pDataArray->m->mothurOutEndLine(); } + } + + if (pDataArray->createGroup) { + if(pDataArray->barcodes.size() != 0){ + + if (pDataArray->countfile == "") { outGroupsFile << currSeq.getName() << '\t' << thisGroup << endl; } + else { pDataArray->groupMap[currSeq.getName()] = thisGroup; } + + if (pDataArray->nameFile != "") { + map::iterator itName = pDataArray->nameMap.find(currSeq.getName()); + if (itName != pDataArray->nameMap.end()) { + vector thisSeqsNames; + pDataArray->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 { pDataArray->m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your namefile, please correct."); pDataArray->m->mothurOutEndLine(); } + } + + map::iterator it = pDataArray->groupCounts.find(thisGroup); + if (it == pDataArray->groupCounts.end()) { pDataArray->groupCounts[thisGroup] = 1 + numRedundants; } + else { pDataArray->groupCounts[it->first] += (1 + numRedundants); } + + } + } + + if(pDataArray->allFiles){ + ofstream output; + pDataArray->m->openOutputFileAppend(pDataArray->fastaFileNames[barcodeIndex][primerIndex], output); + currSeq.printSequence(output); + output.close(); - } - } - - if(pDataArray->allFiles){ - ofstream output; - pDataArray->m->openOutputFileAppend(pDataArray->fastaFileNames[barcodeIndex][primerIndex], output); - currSeq.printSequence(output); - output.close(); - - if(pDataArray->qFileName != ""){ - pDataArray->m->openOutputFileAppend(pDataArray->qualFileNames[barcodeIndex][primerIndex], output); - currQual.printQScores(output); - output.close(); - } - - if(pDataArray->nameFile != ""){ - map::iterator itName = pDataArray->nameMap.find(currSeq.getName()); - if (itName != pDataArray->nameMap.end()) { - pDataArray->m->openOutputFileAppend(pDataArray->nameFileNames[barcodeIndex][primerIndex], output); - output << itName->first << '\t' << itName->second << endl; - output.close(); - }else { pDataArray->m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your namefile, please correct."); pDataArray->m->mothurOutEndLine(); } - } - } + if(pDataArray->qFileName != ""){ + pDataArray->m->openOutputFileAppend(pDataArray->qualFileNames[barcodeIndex][primerIndex], output); + currQual.printQScores(output); + output.close(); + } + + if(pDataArray->nameFile != ""){ + map::iterator itName = pDataArray->nameMap.find(currSeq.getName()); + if (itName != pDataArray->nameMap.end()) { + pDataArray->m->openOutputFileAppend(pDataArray->nameFileNames[barcodeIndex][primerIndex], output); + output << itName->first << '\t' << itName->second << endl; + output.close(); + }else { pDataArray->m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your namefile, please correct."); pDataArray->m->mothurOutEndLine(); } + } + } + } } else{ if(pDataArray->nameFile != ""){ //needs to be before the currSeq name is changed @@ -459,6 +491,12 @@ static DWORD WINAPI MyTrimThreadFunction(LPVOID lpParam){ if (itName != pDataArray->nameMap.end()) { scrapNameFile << itName->first << '\t' << itName->second << endl; } else { pDataArray->m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your namefile, please correct."); pDataArray->m->mothurOutEndLine(); } } + if (pDataArray->countfile != "") { + map::iterator itCount = pDataArray->nameCount.find(currSeq.getName()); + if (itCount != pDataArray->nameCount.end()) { + trimCountFile << itCount->first << '\t' << itCount->second << endl; + }else { pDataArray->m->mothurOut("[ERROR]: " + currSeq.getName() + " is not in your count file, please correct."); pDataArray->m->mothurOutEndLine(); } + } currSeq.setName(currSeq.getName() + '|' + trashCode); currSeq.setUnaligned(origSeq); currSeq.setAligned(origSeq);