X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=makecontigscommand.cpp;h=f888fbe4928a9526d34e9b8f25200fb32a329f6f;hp=74133bbefc4abfb2f453893aa8ff2c39db4f0320;hb=050a3ff02473a3d4c0980964e1a9ebe52e55d6b8;hpb=14cddf859d97118481161bf3e85a647976020758 diff --git a/makecontigscommand.cpp b/makecontigscommand.cpp index 74133bb..f888fbe 100644 --- a/makecontigscommand.cpp +++ b/makecontigscommand.cpp @@ -15,25 +15,25 @@ vector MakeContigsCommand::setParameters(){ CommandParameter prfastq("rfastq", "InputTypes", "", "", "none", "none", "fastqGroup","fasta-qfile",false,false,true); parameters.push_back(prfastq); CommandParameter pfasta("ffasta", "InputTypes", "", "", "FastaFastqFile", "FastaFastqFile", "fastaGroup","fasta",false,false,true); parameters.push_back(pfasta); CommandParameter prfasta("rfasta", "InputTypes", "", "", "none", "none", "none","fastaGroup",false,false,true); parameters.push_back(prfasta); - CommandParameter pfqual("fqfile", "InputTypes", "", "", "none", "none", "qfileGroup","qfile",false,false,true); parameters.push_back(pfqual); - CommandParameter prqual("rqfile", "InputTypes", "", "", "none", "none", "qfileGroup","qfile",false,false,true); parameters.push_back(prqual); + CommandParameter pfqual("fqfile", "InputTypes", "", "", "none", "none", "qfileGroup","",false,false,true); parameters.push_back(pfqual); + CommandParameter prqual("rqfile", "InputTypes", "", "", "none", "none", "qfileGroup","",false,false,true); parameters.push_back(prqual); CommandParameter pfile("file", "InputTypes", "", "", "FastaFastqFile", "FastaFastqFile", "none","fasta-qfile",false,false,true); parameters.push_back(pfile); CommandParameter poligos("oligos", "InputTypes", "", "", "none", "none", "none","group",false,false,true); parameters.push_back(poligos); 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 palign("align", "Multiple", "needleman-gotoh", "needleman", "", "", "","",false,false); parameters.push_back(palign); CommandParameter pallfiles("allfiles", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(pallfiles); + CommandParameter ptrimoverlap("trimoverlap", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(ptrimoverlap); CommandParameter pmatch("match", "Number", "", "1.0", "", "", "","",false,false); parameters.push_back(pmatch); CommandParameter pmismatch("mismatch", "Number", "", "-1.0", "", "", "","",false,false); parameters.push_back(pmismatch); CommandParameter pgapopen("gapopen", "Number", "", "-2.0", "", "", "","",false,false); parameters.push_back(pgapopen); CommandParameter pgapextend("gapextend", "Number", "", "-1.0", "", "", "","",false,false); parameters.push_back(pgapextend); - CommandParameter pthreshold("threshold", "Number", "", "40", "", "", "","",false,false); parameters.push_back(pthreshold); + CommandParameter pthreshold("insert", "Number", "", "20", "", "", "","",false,false); parameters.push_back(pthreshold); + CommandParameter pdeltaq("deltaq", "Number", "", "6", "", "", "","",false,false); parameters.push_back(pdeltaq); CommandParameter pprocessors("processors", "Number", "", "1", "", "", "","",false,false,true); parameters.push_back(pprocessors); - CommandParameter pformat("format", "Multiple", "sanger-illumina-solexa", "sanger", "", "", "","",false,false,true); parameters.push_back(pformat); + CommandParameter pformat("format", "Multiple", "sanger-illumina-solexa-illumina1.8+", "illumina1.8+", "", "", "","",false,false,true); parameters.push_back(pformat); CommandParameter pinputdir("inputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(pinputdir); CommandParameter poutputdir("outputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(poutputdir); @@ -52,26 +52,29 @@ string MakeContigsCommand::getHelpString(){ string helpString = ""; helpString += "The make.contigs command reads a file, forward fastq file and a reverse fastq file or forward fasta and reverse fasta files and outputs new fasta. It will also provide new quality files if the fastq or file parameter is used.\n"; helpString += "If an oligos file is provided barcodes and primers will be trimmed, and a group file will be created.\n"; - helpString += "The make.contigs command parameters are ffastq, rfastq, oligos, format, tdiffs, bdiffs, ldiffs, sdiffs, pdiffs, align, match, mismatch, gapopen, gapextend, allfiles and processors.\n"; + helpString += "The make.contigs command parameters are file, ffastq, rfastq, ffasta, rfasta, fqfile, rqfile, oligos, format, tdiffs, bdiffs, pdiffs, align, match, mismatch, gapopen, gapextend, insert, deltaq, allfiles and processors.\n"; helpString += "The ffastq and rfastq, file, or ffasta and rfasta parameters are required.\n"; - helpString += "The file parameter is 2 column file containing the forward fastq files in the first column and their matching reverse fastq files in the second column. Mothur will process each pair and create a combined fasta and qual file with all the sequences.\n"; + helpString += "The file parameter is 2 or 3 column file containing the forward fastq files in the first column and their matching reverse fastq files in the second column, or a groupName then forward fastq file and reverse fastq file. Mothur will process each pair and create a combined fasta and report file with all the sequences.\n"; helpString += "The ffastq and rfastq parameters are used to provide a forward fastq and reverse fastq file to process. If you provide one, you must provide the other.\n"; helpString += "The ffasta and rfasta parameters are used to provide a forward fasta and reverse fasta file to process. If you provide one, you must provide the other.\n"; helpString += "The fqfile and rqfile parameters are used to provide a forward quality and reverse quality files to process with the ffasta and rfasta parameters. If you provide one, you must provide the other.\n"; - helpString += "The format parameter is used to indicate whether your sequences are sanger, solexa or illumina, default=sanger.\n"; + helpString += "The format parameter is used to indicate whether your sequences are sanger, solexa, illumina1.8+ or illumina, default=illumina1.8+.\n"; helpString += "The align parameter allows you to specify the alignment method to use. Your options are: gotoh and needleman. The default is needleman.\n"; helpString += "The tdiffs parameter is used to specify the total number of differences allowed in the sequence. The default is pdiffs + bdiffs + sdiffs + ldiffs.\n"; helpString += "The bdiffs parameter is used to specify the number of differences allowed in the barcode. The default is 0.\n"; helpString += "The pdiffs parameter is used to specify the number of differences allowed in the primer. The default is 0.\n"; - helpString += "The ldiffs parameter is used to specify the number of differences allowed in the linker. The default is 0.\n"; - helpString += "The sdiffs parameter is used to specify the number of differences allowed in the spacer. The default is 0.\n"; + //helpString += "The ldiffs parameter is used to specify the number of differences allowed in the linker. The default is 0.\n"; + //helpString += "The sdiffs parameter is used to specify the number of differences allowed in the spacer. The default is 0.\n"; helpString += "The match parameter allows you to specify the bonus for having the same base. The default is 1.0.\n"; helpString += "The mistmatch parameter allows you to specify the penalty for having different bases. The default is -1.0.\n"; + helpString += "The deltaq parameter allows you to specify the delta allowed between quality scores of a mismatched base. For example in the overlap, if deltaq=5 and in the alignment seqA, pos 200 has a quality score of 30 and the same position in seqB has a quality score of 20, you take the base from seqA (30-20 >= 5). If the quality score in seqB is 28 then the base in the consensus will be an N (30-28<5) The default is 6.\n"; helpString += "The gapopen parameter allows you to specify the penalty for opening a gap in an alignment. The default is -2.0.\n"; helpString += "The gapextend parameter allows you to specify the penalty for extending a gap in an alignment. The default is -1.0.\n"; - helpString += "The threshold parameter allows you to set a quality scores threshold. In the case where we are trying to decide whether to keep a base or remove it because the base is compared to a gap in the other fragment, if the base has a quality score below the threshold we eliminate it. Default=40.\n"; + helpString += "The insert parameter allows you to set a quality scores threshold. In the case where we are trying to decide whether to keep a base or remove it because the base is compared to a gap in the other fragment, if the base has a quality score equal to or below the threshold we eliminate it. Default=20.\n"; helpString += "The processors parameter allows you to specify how many processors you would like to use. The default is 1. \n"; helpString += "The allfiles parameter will create separate group and fasta file for each grouping. The default is F.\n"; + + helpString += "The trimoverlap parameter allows you to trim the sequences to only the overlapping section. The default is F.\n"; helpString += "The make.contigs command should be in the following format: \n"; helpString += "make.contigs(ffastq=yourForwardFastqFile, rfastq=yourReverseFastqFile, align=yourAlignmentMethod) \n"; helpString += "Note: No spaces between parameter labels (i.e. ffastq), '=' and parameters (i.e.yourForwardFastqFile).\n"; @@ -88,9 +91,8 @@ string MakeContigsCommand::getOutputPattern(string type) { string pattern = ""; if (type == "fasta") { pattern = "[filename],[tag],contigs.fasta"; } - else if (type == "qfile") { pattern = "[filename],[tag],contigs.qual"; } else if (type == "group") { pattern = "[filename],[tag],contigs.groups"; } - else if (type == "mismatch") { pattern = "[filename],[tag],contigs.mismatch"; } + else if (type == "report") { pattern = "[filename],[tag],contigs.report"; } else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } return pattern; @@ -107,10 +109,9 @@ MakeContigsCommand::MakeContigsCommand(){ setParameters(); vector tempOutNames; outputTypes["fasta"] = tempOutNames; - outputTypes["qfile"] = tempOutNames; outputTypes["group"] = tempOutNames; - outputTypes["mismatch"] = tempOutNames; - } + outputTypes["report"] = tempOutNames; + } catch(exception& e) { m->errorOut(e, "MakeContigsCommand", "MakeContigsCommand"); exit(1); @@ -119,7 +120,8 @@ MakeContigsCommand::MakeContigsCommand(){ //********************************************************************************************************************** MakeContigsCommand::MakeContigsCommand(string option) { try { - abort = false; calledHelp = false; + abort = false; calledHelp = false; + createFileGroup = false; createOligosGroup = false; //allow user to run help if(option == "help") { help(); abort = true; calledHelp = true; } @@ -142,8 +144,7 @@ MakeContigsCommand::MakeContigsCommand(string option) { //initialize outputTypes vector tempOutNames; outputTypes["fasta"] = tempOutNames; - outputTypes["qfile"] = tempOutNames; - outputTypes["mismatch"] = tempOutNames; + outputTypes["report"] = tempOutNames; outputTypes["group"] = tempOutNames; @@ -287,10 +288,13 @@ MakeContigsCommand::MakeContigsCommand(string option) { m->mothurConvert(temp, gapExtend); if (gapExtend > 0) { m->mothurOut("[ERROR]: gapextend must be negative.\n"); abort=true; } - temp = validParameter.validFile(parameters, "threshold", false); if (temp == "not found"){ temp = "40"; } - m->mothurConvert(temp, threshold); - if ((threshold < 0) || (threshold > 40)) { m->mothurOut("[ERROR]: threshold must be between 0 and 40.\n"); abort=true; } + temp = validParameter.validFile(parameters, "insert", false); if (temp == "not found"){ temp = "20"; } + m->mothurConvert(temp, insert); + if ((insert < 0) || (insert > 40)) { m->mothurOut("[ERROR]: insert must be between 0 and 40.\n"); abort=true; } + temp = validParameter.validFile(parameters, "deltaq", false); if (temp == "not found"){ temp = "6"; } + m->mothurConvert(temp, deltaq); + temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = m->getProcessors(); } m->setProcessors(temp); m->mothurConvert(temp, processors); @@ -316,14 +320,18 @@ MakeContigsCommand::MakeContigsCommand(string option) { temp = validParameter.validFile(parameters, "allfiles", false); if (temp == "not found") { temp = "F"; } allFiles = m->isTrue(temp); + + + temp = validParameter.validFile(parameters, "trimoverlap", false); if (temp == "not found") { temp = "F"; } + trimOverlap = m->isTrue(temp); align = validParameter.validFile(parameters, "align", false); if (align == "not found"){ align = "needleman"; } if ((align != "needleman") && (align != "gotoh")) { m->mothurOut(align + " is not a valid alignment method. Options are needleman or gotoh. I will use needleman."); m->mothurOutEndLine(); align = "needleman"; } - format = validParameter.validFile(parameters, "format", false); if (format == "not found"){ format = "sanger"; } + format = validParameter.validFile(parameters, "format", false); if (format == "not found"){ format = "illumina1.8+"; } - if ((format != "sanger") && (format != "illumina") && (format != "solexa")) { - m->mothurOut(format + " is not a valid format. Your format choices are sanger, solexa and illumina, aborting." ); m->mothurOutEndLine(); + if ((format != "sanger") && (format != "illumina") && (format != "illumina1.8+") && (format != "solexa")) { + m->mothurOut(format + " is not a valid format. Your format choices are sanger, solexa, illumina1.8+ and illumina, aborting." ); m->mothurOutEndLine(); abort=true; } @@ -365,67 +373,55 @@ int MakeContigsCommand::execute(){ string compositeGroupFile = getOutputFileName("group",cvars); cvars["[tag]"] = "trim"; string compositeFastaFile = getOutputFileName("fasta",cvars); - string compositeQualFile = getOutputFileName("qfile",cvars); cvars["[tag]"] = "scrap"; string compositeScrapFastaFile = getOutputFileName("fasta",cvars); - string compositeScrapQualFile = getOutputFileName("qfile",cvars); cvars["[tag]"] = ""; - string compositeMisMatchFile = getOutputFileName("mismatch",cvars); + string compositeMisMatchFile = getOutputFileName("report",cvars); if (filesToProcess.size() > 1) { //clear files for append below ofstream outCTFasta, outCTQual, outCSFasta, outCSQual, outCMisMatch; m->openOutputFile(compositeFastaFile, outCTFasta); outCTFasta.close(); m->openOutputFile(compositeScrapFastaFile, outCSFasta); outCSFasta.close(); m->openOutputFile(compositeMisMatchFile, outCMisMatch); outCMisMatch.close(); - m->openOutputFile(compositeQualFile, outCTQual); outCTQual.close(); - m->openOutputFile(compositeScrapQualFile, outCSQual); outCSQual.close(); outputNames.push_back(compositeFastaFile); outputTypes["fasta"].push_back(compositeFastaFile); - outputNames.push_back(compositeQualFile); outputTypes["qfile"].push_back(compositeQualFile); - outputNames.push_back(compositeMisMatchFile); outputTypes["mismatch"].push_back(compositeMisMatchFile); + outputNames.push_back(compositeMisMatchFile); outputTypes["report"].push_back(compositeMisMatchFile); outputNames.push_back(compositeScrapFastaFile); outputTypes["fasta"].push_back(compositeScrapFastaFile); - outputNames.push_back(compositeScrapQualFile); outputTypes["qfile"].push_back(compositeScrapQualFile); } + map totalGroupCounts; + for (int l = 0; l < filesToProcess.size(); l++) { m->mothurOut("\n>>>>>\tProcessing " + filesToProcess[l][0][0] + " (file " + toString(l+1) + " of " + toString(filesToProcess.size()) + ")\t<<<<<\n"); + groupCounts.clear(); + groupMap.clear(); vector > fastaFileNames; - vector > qualFileNames; - createGroup = false; + createOligosGroup = false; string outputGroupFileName; map variables; string thisOutputDir = outputDir; if (outputDir == "") { thisOutputDir = m->hasPath(filesToProcess[l][0][0]); } variables["[filename]"] = thisOutputDir + m->getRootName(m->getSimpleName(filesToProcess[l][0][0])); variables["[tag]"] = ""; - if(oligosfile != ""){ - createGroup = getOligos(fastaFileNames, qualFileNames, variables["[filename]"]); - if (createGroup) { - outputGroupFileName = getOutputFileName("group",variables); - outputNames.push_back(outputGroupFileName); outputTypes["group"].push_back(outputGroupFileName); - } + if(oligosfile != ""){ createOligosGroup = getOligos(fastaFileNames, variables["[filename]"]); } + if (createOligosGroup || createFileGroup) { + outputGroupFileName = getOutputFileName("group",variables); } + //give group in file file precedence + if (createFileGroup) { createOligosGroup = false; } + variables["[tag]"] = "trim"; string outFastaFile = getOutputFileName("fasta",variables); - string outQualFile = getOutputFileName("qfile",variables); variables["[tag]"] = "scrap"; string outScrapFastaFile = getOutputFileName("fasta",variables); - string outScrapQualFile = getOutputFileName("qfile",variables); variables["[tag]"] = ""; - string outMisMatchFile = getOutputFileName("mismatch",variables); - outputNames.push_back(outFastaFile); outputTypes["fasta"].push_back(outFastaFile); - outputNames.push_back(outScrapFastaFile); outputTypes["fasta"].push_back(outScrapFastaFile); - if (filesToProcess[l][0][1] != "") { - outputNames.push_back(outQualFile); outputTypes["qfile"].push_back(outQualFile); - outputNames.push_back(outScrapQualFile); outputTypes["qfile"].push_back(outScrapQualFile); - } - outputNames.push_back(outMisMatchFile); outputTypes["mismatch"].push_back(outMisMatchFile); - + string outMisMatchFile = getOutputFileName("report",variables); + m->mothurOut("Making contigs...\n"); - createProcesses(filesToProcess[l], outFastaFile, outQualFile, outScrapFastaFile, outScrapQualFile, outMisMatchFile, fastaFileNames, qualFileNames); - m->mothurOut("Done.\n"); + createProcesses(filesToProcess[l], outFastaFile, outScrapFastaFile, outMisMatchFile, fastaFileNames, l); + m->mothurOut("Here...\n"); //remove temp fasta and qual files for (int i = 0; i < processors; i++) { for(int j = 0; j < filesToProcess[l][i].size(); j++) { m->mothurRemove(filesToProcess[l][i][j]); } } @@ -443,11 +439,6 @@ int MakeContigsCommand::execute(){ if(m->isBlank(fastaFileNames[i][j])){ m->mothurRemove(fastaFileNames[i][j]); namesToRemove.insert(fastaFileNames[i][j]); - - if (filesToProcess[l][0][1] != "") { - m->mothurRemove(qualFileNames[i][j]); - namesToRemove.insert(qualFileNames[i][j]); - } }else{ it = uniqueFastaNames.find(fastaFileNames[i][j]); if (it == uniqueFastaNames.end()) { @@ -470,21 +461,21 @@ int MakeContigsCommand::execute(){ ofstream out; string thisGroupName = thisOutputDir + m->getRootName(m->getSimpleName(it->first)); - thisGroupName += getOutputFileName("group",variables); outputNames.push_back(thisGroupName); outputTypes["group"].push_back(thisGroupName); + thisGroupName += getOutputFileName("group",variables); outputNames.push_back(thisGroupName); outputTypes["group"].push_back(thisGroupName); m->openOutputFile(thisGroupName, out); while (!in.eof()){ if (m->control_pressed) { break; } Sequence currSeq(in); m->gobble(in); - out << currSeq.getName() << '\t' << it->second << endl; + out << currSeq.getName() << '\t' << it->second << endl; } - in.close(); out.close(); + in.close(); } } - if (createGroup) { + if (createFileGroup || createOligosGroup) { ofstream outGroup; m->openOutputFile(outputGroupFileName, outGroup); for (map::iterator itGroup = groupMap.begin(); itGroup != groupMap.end(); itGroup++) { @@ -494,21 +485,47 @@ int MakeContigsCommand::execute(){ } if (filesToProcess.size() > 1) { //merge into large combo files - if (createGroup) { - if (l == 0) { + if (createFileGroup || createOligosGroup) { + if (l == 0) { ofstream outCGroup; m->openOutputFile(compositeGroupFile, outCGroup); outCGroup.close(); outputNames.push_back(compositeGroupFile); outputTypes["group"].push_back(compositeGroupFile); } - m->appendFiles(outputGroupFileName, compositeGroupFile); + m->appendFiles(outputGroupFileName, compositeGroupFile); + if (!allFiles) { m->mothurRemove(outputGroupFileName); } + else { outputNames.push_back(outputGroupFileName); outputTypes["group"].push_back(outputGroupFileName); } + + for (map::iterator itGroups = groupCounts.begin(); itGroups != groupCounts.end(); itGroups++) { + map::iterator itTemp = totalGroupCounts.find(itGroups->first); + if (itTemp == totalGroupCounts.end()) { totalGroupCounts[itGroups->first] = itGroups->second; } //new group create it in totalGroups + else { itTemp->second += itGroups->second; } //existing group, update total + } } - m->appendFiles(outMisMatchFile, compositeMisMatchFile); + if (l == 0) { m->appendFiles(outMisMatchFile, compositeMisMatchFile); } + else { m->appendFilesWithoutHeaders(outMisMatchFile, compositeMisMatchFile); } m->appendFiles(outFastaFile, compositeFastaFile); - m->appendFiles(outQualFile, compositeQualFile); m->appendFiles(outScrapFastaFile, compositeScrapFastaFile); - m->appendFiles(outScrapQualFile, compositeScrapQualFile); + if (!allFiles) { + m->mothurRemove(outMisMatchFile); + m->mothurRemove(outFastaFile); + m->mothurRemove(outScrapFastaFile); + }else { + outputNames.push_back(outFastaFile); outputTypes["fasta"].push_back(outFastaFile); + outputNames.push_back(outScrapFastaFile); outputTypes["fasta"].push_back(outScrapFastaFile); + outputNames.push_back(outMisMatchFile); outputTypes["report"].push_back(outMisMatchFile); + } + }else { + totalGroupCounts = groupCounts; + outputNames.push_back(outFastaFile); outputTypes["fasta"].push_back(outFastaFile); + outputNames.push_back(outScrapFastaFile); outputTypes["fasta"].push_back(outScrapFastaFile); + outputNames.push_back(outMisMatchFile); outputTypes["report"].push_back(outMisMatchFile); + if (createFileGroup || createOligosGroup) { + outputNames.push_back(outputGroupFileName); outputTypes["group"].push_back(outputGroupFileName); + } } + m->mothurOut("Done.\n"); } + m->mothurOut("It took " + toString(time(NULL) - start) + " secs to process " + toString(numReads) + " sequences.\n"); if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } @@ -516,8 +533,8 @@ int MakeContigsCommand::execute(){ //output group counts m->mothurOutEndLine(); int total = 0; - if (groupCounts.size() != 0) { m->mothurOut("Group count: \n"); } - for (map::iterator it = groupCounts.begin(); it != groupCounts.end(); it++) { + if (totalGroupCounts.size() != 0) { m->mothurOut("Group count: \n"); } + for (map::iterator it = totalGroupCounts.begin(); it != totalGroupCounts.end(); it++) { total += it->second; m->mothurOut(it->first + "\t" + toString(it->second)); m->mothurOutEndLine(); } if (total != 0) { m->mothurOut("Total of all groups is " + toString(total)); m->mothurOutEndLine(); } @@ -530,12 +547,6 @@ int MakeContigsCommand::execute(){ if ((itTypes->second).size() != 0) { currentFasta = (itTypes->second)[0]; m->setFastaFile(currentFasta); } } - string currentQual = ""; - itTypes = outputTypes.find("qfile"); - if (itTypes != outputTypes.end()) { - if ((itTypes->second).size() != 0) { currentQual = (itTypes->second)[0]; m->setQualFile(currentQual); } - } - string currentGroup = ""; itTypes = outputTypes.find("group"); if (itTypes != outputTypes.end()) { @@ -616,10 +627,14 @@ vector< vector< vector > > MakeContigsCommand::preProcessData(unsigned l } } //********************************************************************************************************************** -int MakeContigsCommand::createProcesses(vector< vector > files, string outputFasta, string outputQual, string outputScrapFasta, string outputScrapQual, string outputMisMatches, vector > fastaFileNames, vector > qualFileNames) { +int MakeContigsCommand::createProcesses(vector< vector > files, string outputFasta, string outputScrapFasta, string outputMisMatches, vector > fastaFileNames, int index) { try { int num = 0; vector processIDS; + string group = ""; + map::iterator it = file2Group.find(index); + if (it != file2Group.end()) { group = it->second; } + #if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix) int process = 0; @@ -632,7 +647,6 @@ int MakeContigsCommand::createProcesses(vector< vector > files, string o process++; }else if (pid == 0){ vector > tempFASTAFileNames = fastaFileNames; - vector > tempPrimerQualFileNames = qualFileNames; if(allFiles){ ofstream temp; @@ -642,31 +656,23 @@ int MakeContigsCommand::createProcesses(vector< vector > files, string o if (tempFASTAFileNames[i][j] != "") { tempFASTAFileNames[i][j] += toString(getpid()) + ".temp"; m->openOutputFile(tempFASTAFileNames[i][j], temp); temp.close(); - - if (files[processors-1][1] != "") { - tempPrimerQualFileNames[i][j] += toString(getpid()) + ".temp"; - m->openOutputFile(tempPrimerQualFileNames[i][j], temp); temp.close(); - } } } } } - + num = driver(files[process], outputFasta + toString(getpid()) + ".temp", - outputQual + toString(getpid()) + ".temp", outputScrapFasta + toString(getpid()) + ".temp", - outputScrapQual + toString(getpid()) + ".temp", outputMisMatches + toString(getpid()) + ".temp", - tempFASTAFileNames, - tempPrimerQualFileNames); + tempFASTAFileNames, process, group); //pass groupCounts to parent ofstream out; string tempFile = toString(getpid()) + ".num.temp"; m->openOutputFile(tempFile, out); out << num << endl; - if(createGroup){ + if (createFileGroup || createOligosGroup) { out << groupCounts.size() << endl; for (map::iterator it = groupCounts.begin(); it != groupCounts.end(); it++) { @@ -691,13 +697,9 @@ int MakeContigsCommand::createProcesses(vector< vector > files, string o ofstream temp; m->openOutputFile(outputFasta, temp); temp.close(); m->openOutputFile(outputScrapFasta, temp); temp.close(); - if (files[processors-1][1] != "") { - m->openOutputFile(outputScrapQual, temp); temp.close(); - m->openOutputFile(outputQual, temp); temp.close(); - } - + //do my part - num = driver(files[processors-1], outputFasta, outputQual, outputScrapFasta, outputScrapQual, outputMisMatches, fastaFileNames, qualFileNames); + num = driver(files[processors-1], outputFasta, outputScrapFasta, outputMisMatches, fastaFileNames, processors-1, group); //force parent to wait until all the processes are done for (int i=0;i > files, string o int tempNum; in >> tempNum; num += tempNum; m->gobble(in); - if(createGroup){ + if (createFileGroup || createOligosGroup) { string group; in >> tempNum; m->gobble(in); @@ -756,8 +758,7 @@ int MakeContigsCommand::createProcesses(vector< vector > files, string o string extension = ""; if (h != 0) { extension = toString(h) + ".temp"; processIDS.push_back(h); } vector > tempFASTAFileNames = fastaFileNames; - vector > tempPrimerQualFileNames = qualFileNames; - + if(allFiles){ ofstream temp; @@ -766,25 +767,18 @@ int MakeContigsCommand::createProcesses(vector< vector > files, string o if (tempFASTAFileNames[i][j] != "") { tempFASTAFileNames[i][j] += extension; m->openOutputFile(tempFASTAFileNames[i][j], temp); temp.close(); - - if (files[processors-1][1] != "") { - tempPrimerQualFileNames[i][j] += extension; - m->openOutputFile(tempPrimerQualFileNames[i][j], temp); temp.close(); - } } } } } - - - contigsData* tempcontig = new contigsData(files[h], (outputFasta + extension), (outputQual + extension), (outputScrapFasta + extension), (outputScrapQual + extension),(outputMisMatches + extension), align, m, match, misMatch, gapOpen, gapExtend, threshold, barcodes, primers, tempFASTAFileNames, tempPrimerQualFileNames, barcodeNameVector, primerNameVector, pdiffs, bdiffs, tdiffs, createGroup, allFiles, h); + + contigsData* tempcontig = new contigsData(group, files[h], (outputFasta + extension), (outputScrapFasta + extension), (outputMisMatches + extension), align, m, match, misMatch, gapOpen, gapExtend, insert, deltaq, barcodes, primers, tempFASTAFileNames, barcodeNameVector, primerNameVector, pdiffs, bdiffs, tdiffs, createOligosGroup, createFileGroup, allFiles, trimOverlap, h); pDataArray.push_back(tempcontig); hThreadArray[h] = CreateThread(NULL, 0, MyContigsThreadFunction, pDataArray[h], 0, &dwThreadIdArray[h]); } vector > tempFASTAFileNames = fastaFileNames; - vector > tempPrimerQualFileNames = qualFileNames; if(allFiles){ ofstream temp; @@ -795,11 +789,6 @@ int MakeContigsCommand::createProcesses(vector< vector > files, string o if (tempFASTAFileNames[i][j] != "") { tempFASTAFileNames[i][j] += extension; m->openOutputFile(tempFASTAFileNames[i][j], temp); temp.close(); - - if (files[processors-1][1] != "") { - tempPrimerQualFileNames[i][j] += extension; - m->openOutputFile(tempPrimerQualFileNames[i][j], temp); temp.close(); - } } } } @@ -809,14 +798,10 @@ int MakeContigsCommand::createProcesses(vector< vector > files, string o ofstream temp; m->openOutputFile(outputFasta, temp); temp.close(); m->openOutputFile(outputScrapFasta, temp); temp.close(); - if (files[processors-1][1] != "") { - m->openOutputFile(outputScrapQual, temp); temp.close(); - m->openOutputFile(outputQual, temp); temp.close(); - } //do my part processIDS.push_back(processors-1); - num = driver(files[processors-1], (outputFasta+ toString(processors-1) + ".temp"), (outputQual+ toString(processors-1) + ".temp"), (outputScrapFasta+ toString(processors-1) + ".temp"), (outputScrapQual+ toString(processors-1) + ".temp"), (outputMisMatches+ toString(processors-1) + ".temp"), tempFASTAFileNames, tempPrimerQualFileNames); + num = driver(files[processors-1], (outputFasta+ toString(processors-1) + ".temp"), (outputScrapFasta+ toString(processors-1) + ".temp"), (outputMisMatches+ toString(processors-1) + ".temp"), tempFASTAFileNames, processors-1, group); //Wait until all threads have terminated. WaitForMultipleObjects(processors-1, hThreadArray, TRUE, INFINITE); @@ -849,16 +834,8 @@ int MakeContigsCommand::createProcesses(vector< vector > files, string o m->appendFiles((outputScrapFasta + toString(processIDS[i]) + ".temp"), outputScrapFasta); m->mothurRemove((outputScrapFasta + toString(processIDS[i]) + ".temp")); - - if (files[processors-1][1] != "") { - m->appendFiles((outputScrapQual + toString(processIDS[i]) + ".temp"), outputScrapQual); - m->mothurRemove((outputScrapQual + toString(processIDS[i]) + ".temp")); - - m->appendFiles((outputQual + toString(processIDS[i]) + ".temp"), outputQual); - m->mothurRemove((outputQual + toString(processIDS[i]) + ".temp")); - } - m->appendFiles((outputMisMatches + toString(processIDS[i]) + ".temp"), outputMisMatches); + m->appendFilesWithoutHeaders((outputMisMatches + toString(processIDS[i]) + ".temp"), outputMisMatches); m->mothurRemove((outputMisMatches + toString(processIDS[i]) + ".temp")); if(allFiles){ @@ -867,11 +844,6 @@ int MakeContigsCommand::createProcesses(vector< vector > files, string o if (fastaFileNames[j][k] != "") { m->appendFiles((fastaFileNames[j][k] + toString(processIDS[i]) + ".temp"), fastaFileNames[j][k]); m->mothurRemove((fastaFileNames[j][k] + toString(processIDS[i]) + ".temp")); - - if (files[processors-1][1] != "") { - m->appendFiles((qualFileNames[j][k] + toString(processIDS[i]) + ".temp"), qualFileNames[j][k]); - m->mothurRemove((qualFileNames[j][k] + toString(processIDS[i]) + ".temp")); - } } } } @@ -886,7 +858,7 @@ int MakeContigsCommand::createProcesses(vector< vector > files, string o } } //********************************************************************************************************************** -int MakeContigsCommand::driver(vector files, string outputFasta, string outputQual, string outputScrapFasta, string outputScrapQual, string outputMisMatches, vector > fastaFileNames, vector > qualFileNames){ +int MakeContigsCommand::driver(vector files, string outputFasta, string outputScrapFasta, string outputMisMatches, vector > fastaFileNames, int process, string group){ try { Alignment* alignment; @@ -902,19 +874,17 @@ int MakeContigsCommand::driver(vector files, string outputFasta, string if (m->debug) { m->mothurOut("[DEBUG]: ffasta = " + thisffastafile + ".\n[DEBUG]: fqual = " + thisfqualfile + ".\n[DEBUG]: rfasta = " + thisrfastafile + ".\n[DEBUG]: rqual = " + thisrqualfile + ".\n"); } ifstream inFFasta, inRFasta, inFQual, inRQual; - ofstream outFasta, outQual, outMisMatch, outScrapFasta, outScrapQual; + ofstream outFasta, outMisMatch, outScrapFasta; m->openInputFile(thisffastafile, inFFasta); m->openInputFile(thisrfastafile, inRFasta); if (thisfqualfile != "") { m->openInputFile(thisfqualfile, inFQual); m->openInputFile(thisrqualfile, inRQual); - m->openOutputFile(outputScrapQual, outScrapQual); - m->openOutputFile(outputQual, outQual); } m->openOutputFile(outputFasta, outFasta); m->openOutputFile(outputScrapFasta, outScrapFasta); m->openOutputFile(outputMisMatches, outMisMatch); - outMisMatch << "Name\tLength\tMisMatches\n"; + outMisMatch << "Name\tLength\tOverlap_Length\tOverlap_Start\tOverlap_End\tMisMatches\tNum_Ns\n"; TrimOligos trimOligos(pdiffs, bdiffs, 0, 0, primers, barcodes); @@ -974,7 +944,6 @@ int MakeContigsCommand::driver(vector files, string outputFasta, string //traverse alignments merging into one contiguous seq string contig = ""; - vector contigScores; int numMismatches = 0; string seq1 = fSeq.getAligned(); string seq2 = rSeq.getAligned(); @@ -988,18 +957,13 @@ int MakeContigsCommand::driver(vector files, string outputFasta, string // if (num < 5) { cout << fSeq.getStartPos() << '\t' << fSeq.getEndPos() << '\t' << rSeq.getStartPos() << '\t' << rSeq.getEndPos() << endl; } int overlapStart = fSeq.getStartPos(); int seq2Start = rSeq.getStartPos(); + //bigger of the 2 starting positions is the location of the overlapping start if (overlapStart < seq2Start) { //seq2 starts later so take from 0 to seq2Start from seq1 overlapStart = seq2Start; - for (int i = 0; i < overlapStart; i++) { - contig += seq1[i]; - if (thisfqualfile != "") { contigScores.push_back(scores1[ABaseMap[i]]); } - } + for (int i = 0; i < overlapStart; i++) { contig += seq1[i]; } }else { //seq1 starts later so take from 0 to overlapStart from seq2 - for (int i = 0; i < overlapStart; i++) { - contig += seq2[i]; - if (thisfqualfile != "") { contigScores.push_back(scores2[BBaseMap[i]]); } - } + for (int i = 0; i < overlapStart; i++) { contig += seq2[i]; } } int seq1End = fSeq.getEndPos(); @@ -1007,61 +971,50 @@ int MakeContigsCommand::driver(vector files, string outputFasta, string int overlapEnd = seq1End; if (seq2End < overlapEnd) { overlapEnd = seq2End; } //smallest end position is where overlapping ends + int oStart = contig.length(); for (int i = overlapStart; i < overlapEnd; i++) { if (seq1[i] == seq2[i]) { //match, add base and choose highest score contig += seq1[i]; - if (thisfqualfile != "") { - contigScores.push_back(scores1[ABaseMap[i]]); - if (scores1[ABaseMap[i]] < scores2[BBaseMap[i]]) { contigScores[contigScores.size()-1] = scores2[BBaseMap[i]]; } - } - }else if (((seq1[i] == '.') || (seq1[i] == '-')) && ((seq2[i] != '-') && (seq2[i] != '.'))) { //seq1 is a gap and seq2 is a base, choose seq2, unless quality score for base is below threshold. In that case eliminate base + }else if (((seq1[i] == '.') || (seq1[i] == '-')) && ((seq2[i] != '-') && (seq2[i] != '.'))) { //seq1 is a gap and seq2 is a base, choose seq2, unless quality score for base is below insert. In that case eliminate base if (thisfqualfile != "") { - if (scores2[BBaseMap[i]] < threshold) { } // - else { - contig += seq2[i]; - contigScores.push_back(scores2[BBaseMap[i]]); - } + if (scores2[BBaseMap[i]] <= insert) { } // + else { contig += seq2[i]; } }else { contig += seq2[i]; } //with no quality info, then we keep it? - }else if (((seq2[i] == '.') || (seq2[i] == '-')) && ((seq1[i] != '-') && (seq1[i] != '.'))) { //seq2 is a gap and seq1 is a base, choose seq1, unless quality score for base is below threshold. In that case eliminate base + }else if (((seq2[i] == '.') || (seq2[i] == '-')) && ((seq1[i] != '-') && (seq1[i] != '.'))) { //seq2 is a gap and seq1 is a base, choose seq1, unless quality score for base is below insert. In that case eliminate base if (thisfqualfile != "") { - if (scores1[ABaseMap[i]] < threshold) { } // - else { - contig += seq1[i]; - contigScores.push_back(scores1[ABaseMap[i]]); - } + if (scores1[ABaseMap[i]] <= insert) { } // + else { contig += seq1[i]; } }else { contig += seq1[i]; } //with no quality info, then we keep it? }else if (((seq1[i] != '-') && (seq1[i] != '.')) && ((seq2[i] != '-') && (seq2[i] != '.'))) { //both bases choose one with better quality if (thisfqualfile != "") { - char c = seq1[i]; - contigScores.push_back(scores1[ABaseMap[i]]); - if (scores1[ABaseMap[i]] < scores2[BBaseMap[i]]) { contigScores[contigScores.size()-1] = scores2[BBaseMap[i]]; c = seq2[i]; } - contig += c; + if (abs(scores1[ABaseMap[i]] - scores2[BBaseMap[i]]) >= deltaq) { //is the difference in qual scores >= deltaq, if yes choose base with higher score + char c = seq1[i]; + if (scores1[ABaseMap[i]] < scores2[BBaseMap[i]]) { c = seq2[i]; } + contig += c; + }else { //if no, base becomes n + contig += 'N'; + } numMismatches++; }else { numMismatches++; } //cant decide, so eliminate and mark as mismatch }else { //should never get here m->mothurOut("[ERROR]: case I didn't think of seq1 = " + toString(seq1[i]) + " and seq2 = " + toString(seq2[i]) + "\n"); } } - + int oend = contig.length(); if (seq1End < seq2End) { //seq1 ends before seq2 so take from overlap to length from seq2 - for (int i = overlapEnd; i < length; i++) { - contig += seq2[i]; - if (thisfqualfile != "") { contigScores.push_back(scores2[BBaseMap[i]]); } - } + for (int i = overlapEnd; i < length; i++) { contig += seq2[i]; } }else { //seq2 ends before seq1 so take from overlap to length from seq1 - for (int i = overlapEnd; i < length; i++) { - contig += seq1[i]; - if (thisfqualfile != "") { contigScores.push_back(scores1[ABaseMap[i]]); } - } - + for (int i = overlapEnd; i < length; i++) { contig += seq1[i]; } } + if (trimOverlap) { contig = contig.substr(overlapStart-1, oend-oStart); if (contig.length() == 0) { trashCode += "l"; } } + if(trashCode.length() == 0){ bool ignore = false; if (m->debug) { m->mothurOut(fSeq.getName()); } - if (createGroup) { + if (createOligosGroup) { if(barcodes.size() != 0){ string thisGroup = barcodeNameVector[barcodeIndex]; if (primers.size() != 0) { @@ -1086,6 +1039,15 @@ int MakeContigsCommand::driver(vector files, string outputFasta, string }else { ignore = true; } } + }else if (createFileGroup) { + int pos = group.find("ignore"); + if (pos == string::npos) { + groupMap[fSeq.getName()] = group; + + map::iterator it = groupCounts.find(group); + if (it == groupCounts.end()) { groupCounts[group] = 1; } + else { groupCounts[it->first] ++; } + }else { ignore = true; } } if (m->debug) { m->mothurOut("\n"); } @@ -1094,32 +1056,16 @@ int MakeContigsCommand::driver(vector files, string outputFasta, string m->openOutputFileAppend(fastaFileNames[barcodeIndex][primerIndex], output); output << ">" << fSeq.getName() << endl << contig << endl; output.close(); - - if (thisfqualfile != "") { - m->openOutputFileAppend(qualFileNames[barcodeIndex][primerIndex], output); - output << ">" << fSeq.getName() << endl; - for (int i = 0; i < contigScores.size(); i++) { output << contigScores[i] << ' '; } - output << endl; - output.close(); - } } //output outFasta << ">" << fSeq.getName() << endl << contig << endl; - if (thisfqualfile != "") { - outQual << ">" << fSeq.getName() << endl; - for (int i = 0; i < contigScores.size(); i++) { outQual << contigScores[i] << ' '; } - outQual << endl; - } - outMisMatch << fSeq.getName() << '\t' << contig.length() << '\t' << numMismatches << endl; + int numNs = 0; + for (int i = 0; i < contig.length(); i++) { if (contig[i] == 'N') { numNs++; } } + outMisMatch << fSeq.getName() << '\t' << contig.length() << '\t' << (oend-oStart) << '\t' << oStart << '\t' << oend << '\t' << numMismatches << '\t' << numNs << endl; }else { //output outScrapFasta << ">" << fSeq.getName() << " | " << trashCode << endl << contig << endl; - if (thisfqualfile != "") { - outScrapQual << ">" << fSeq.getName() << " | " << trashCode << endl; - for (int i = 0; i < contigScores.size(); i++) { outScrapQual << contigScores[i] << ' '; } - outScrapQual << endl; - } } num++; @@ -1138,12 +1084,10 @@ int MakeContigsCommand::driver(vector files, string outputFasta, string if (thisfqualfile != "") { inFQual.close(); inRQual.close(); - outQual.close(); - outScrapQual.close(); } delete alignment; - if (m->control_pressed) { m->mothurRemove(outputFasta); m->mothurRemove(outputScrapFasta);m->mothurRemove(outputMisMatches); if (thisfqualfile != "") { m->mothurRemove(outputQual); m->mothurRemove(outputScrapQual); } } + if (m->control_pressed) { m->mothurRemove(outputFasta); m->mothurRemove(outputScrapFasta);m->mothurRemove(outputMisMatches); } return num; } @@ -1224,7 +1168,7 @@ vector< vector > MakeContigsCommand::readFastqFiles(unsigned long int& c if (m->debug) { m->mothurOut(toString(count) + '\t' + fread.name + '\t' + rread.name + '\n'); } - if (checkReads(fread, rread, ffastq, rfastq)) { + //if (checkReads(fread, rread, ffastq, rfastq)) { if (m->control_pressed) { for (it = tempfiles.begin(); it!=tempfiles.end(); it++) { for (int i = 0; i < (it->second).size(); i++) { (*(it->second)[i]).close(); delete (it->second)[i]; } } for (int i = 0; i < files.size(); i++) { for(int j = 0; j < files[i].size(); j++) { m->mothurRemove(files[i][j]); } } inForward.close(); inReverse.close(); return files; } //if the reads are okay write to output files @@ -1243,7 +1187,7 @@ vector< vector > MakeContigsCommand::readFastqFiles(unsigned long int& c //report progress if((count) % 10000 == 0){ m->mothurOut(toString(count)); m->mothurOutEndLine(); } - } + //} } } //report progress @@ -1367,7 +1311,7 @@ vector< vector > MakeContigsCommand::readFastaFiles(unsigned long int& c if (m->debug) { m->mothurOut(toString(count) + '\t' + fread.name + '\t' + rread.name + '\n'); } - if (checkReads(fread, rread, ffasta, rfasta)) { + // if (checkReads(fread, rread, ffasta, rfasta)) { if (m->control_pressed) { for (it = tempfiles.begin(); it!=tempfiles.end(); it++) { for (int i = 0; i < (it->second).size(); i++) { (*(it->second)[i]).close(); delete (it->second)[i]; } } for (int i = 0; i < files.size(); i++) { for(int j = 0; j < files[i].size(); j++) { m->mothurRemove(files[i][j]); } } inReverseFasta.close(); inForwardFasta.close(); if (fqualfile != "") { inReverseQual.close(); inReverseQual.close(); } return files; } //if the reads are okay write to output files @@ -1387,7 +1331,7 @@ vector< vector > MakeContigsCommand::readFastaFiles(unsigned long int& c //report progress if((count) % 10000 == 0){ m->mothurOut(toString(count)); m->mothurOutEndLine(); } - } + //} } } //report progress @@ -1539,7 +1483,7 @@ fastqRead MakeContigsCommand::readFastq(ifstream& in, bool& ignore){ exit(1); } } -//********************************************************************************************************************** +/********************************************************************************************************************** bool MakeContigsCommand::checkReads(fastqRead& forward, fastqRead& reverse, string ffile, string rfile){ try { bool good = true; @@ -1562,7 +1506,7 @@ bool MakeContigsCommand::checkReads(fastqRead& forward, fastqRead& reverse, stri m->errorOut(e, "MakeContigsCommand", "checkReads"); exit(1); } -} +}*/ //*************************************************************************************************************** vector< vector > MakeContigsCommand::readFileNames(string filename){ try { @@ -1577,7 +1521,27 @@ vector< vector > MakeContigsCommand::readFileNames(string filename){ if (m->control_pressed) { return files; } in >> forward; m->gobble(in); - in >> reverse; m->gobble(in); + in >> reverse; + + string group = ""; + while (!in.eof()) { //do we have a group assigned to this pair + char c = in.get(); + if (c == 10 || c == 13 || c == -1){ break; } + else if (c == 32 || c == 9){;} //space or tab + else { group += c; } + } + + if (group != "") { + //line in file look like: group forward reverse + string temp = forward; + forward = reverse; + reverse = group; + group = temp; + createFileGroup = true; + } + m->gobble(in); + + if (m->debug) { m->mothurOut("[DEBUG]: group = " + group + ", forward = " + forward + ", reverse = " + reverse + ".\n"); } //check to make sure both are able to be opened ifstream in2; @@ -1643,12 +1607,12 @@ vector< vector > MakeContigsCommand::readFileNames(string filename){ }else{ in3.close(); } if ((openForward != 1) && (openReverse != 1)) { //good pair + file2Group[files.size()] = group; vector pair; pair.push_back(forward); pair.push_back(reverse); files.push_back(pair); } - } in.close(); @@ -1664,7 +1628,7 @@ vector< vector > MakeContigsCommand::readFileNames(string filename){ //BARCODE atgcatgc atgcatgc groupName //PRIMER atgcatgc atgcatgc groupName //PRIMER atgcatgc atgcatgc -bool MakeContigsCommand::getOligos(vector >& fastaFileNames, vector >& qualFileNames, string rootname){ +bool MakeContigsCommand::getOligos(vector >& fastaFileNames, string rootname){ try { ifstream in; m->openInputFile(oligosfile, in); @@ -1681,7 +1645,7 @@ bool MakeContigsCommand::getOligos(vector >& fastaFileNames, vect while(!in.eof()){ in >> type; - cout << type << endl; + if (m->debug) { m->mothurOut("[DEBUG]: reading type - " + type + ".\n"); } if(type[0] == '#'){ @@ -1702,7 +1666,7 @@ bool MakeContigsCommand::getOligos(vector >& fastaFileNames, vect if(foligo[i] == 'U') { foligo[i] = 'T'; } } - if(type == "FORWARD"){ + if(type == "PRIMER"){ m->gobble(in); in >> roligo; @@ -1713,17 +1677,21 @@ bool MakeContigsCommand::getOligos(vector >& fastaFileNames, vect } //roligo = reverseOligo(roligo); + if (m->debug) { m->mothurOut("[DEBUG]: reading - " + roligo + ".\n"); } + group = ""; // get rest of line in case there is a primer name while (!in.eof()) { char c = in.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; } } oligosPair newPrimer(foligo, roligo); + + if (m->debug) { m->mothurOut("[DEBUG]: primer pair " + newPrimer.forward + " " + newPrimer.reverse + ", and group = " + group + ".\n"); } //check for repeat barcodes string tempPair = foligo+roligo; @@ -1750,7 +1718,7 @@ bool MakeContigsCommand::getOligos(vector >& fastaFileNames, vect group = ""; while (!in.eof()) { char c = in.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; } } @@ -1764,7 +1732,6 @@ bool MakeContigsCommand::getOligos(vector >& fastaFileNames, vect barcodes[indexBarcode]=newPair; indexBarcode++; barcodeNameVector.push_back(group); - cout << group << endl; }else if(type == "LINKER"){ linker.push_back(foligo); m->mothurOut("[WARNING]: make.contigs is not setup to remove linkers, ignoring.\n"); @@ -1797,7 +1764,6 @@ bool MakeContigsCommand::getOligos(vector >& fastaFileNames, vect for(int i=0;i uniqueNames; //used to cleanup outputFileNames @@ -1838,17 +1804,6 @@ bool MakeContigsCommand::getOligos(vector >& fastaFileNames, vect fastaFileNames[itBar->first][itPrimer->first] = fastaFileName; m->openOutputFile(fastaFileName, temp); temp.close(); - - if ((fqualfile != "") || (ffastqfile != "") || (file != "")) { - qualFileName = rootname + ".qual"; - 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(); - } } } } @@ -1926,6 +1881,7 @@ string MakeContigsCommand::reverseOligo(string oligo){ vector MakeContigsCommand::convertQual(string qual) { try { vector qualScores; + bool negativeScores = false; for (int i = 0; i < qual.length(); i++) { @@ -1933,15 +1889,21 @@ vector MakeContigsCommand::convertQual(string qual) { temp = int(qual[i]); if (format == "illumina") { temp -= 64; //char '@' + }else if (format == "illumina1.8+") { + temp -= int('!'); //char '!' }else if (format == "solexa") { temp = int(convertTable[temp]); //convert to sanger temp -= int('!'); //char '!' }else { temp -= int('!'); //char '!' } + + if (temp < -5) { negativeScores = true; } qualScores.push_back(temp); } + if (negativeScores) { m->mothurOut("[ERROR]: finding negative quality scores, do you have the right format selected? http://en.wikipedia.org/wiki/FASTQ_format#Encoding \n"); m->control_pressed = true; } + return qualScores; } catch(exception& e) {