X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=makecontigscommand.cpp;h=85b6a8fdcbacf1ca1ee5b471b2142480ecf5da48;hp=7a84f88ed86fbdcfc3c03d6759f46e99f935c836;hb=df7e3ff9f68ef157b0328a2d353c3258c5d45d89;hpb=4458418562cc9dfc9a29ed4f8f6cfc7bfb927d40 diff --git a/makecontigscommand.cpp b/makecontigscommand.cpp index 7a84f88..85b6a8f 100644 --- a/makecontigscommand.cpp +++ b/makecontigscommand.cpp @@ -15,24 +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-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); @@ -51,25 +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, 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 align parameter allows you to specify the alignment method to use. Your options are: gotoh and needleman. The default is needleman.\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"; @@ -86,9 +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],groups"; } - else if (type == "mismatch") { pattern = "[filename],[tag],contigs.mismatch"; } + else if (type == "group") { pattern = "[filename],[tag],contigs.groups"; } + 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; @@ -105,10 +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); @@ -117,7 +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; } @@ -140,8 +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; @@ -243,9 +246,18 @@ MakeContigsCommand::MakeContigsCommand(string option) { if (file == "not open") { abort = true; } else if (file == "not found") { file = ""; } - if ((file == "") && (ffastafile == "") && (ffastqfile == "")) { abort = true; m->mothurOut("[ERROR]: ffastq and rfastq parameters are required.\n"); } - if ((ffastqfile != "") && (rfastqfile == "")) { abort = true; } - if ((ffastqfile == "") && (rfastqfile != "")) { abort = true; } + //provide at least + if ((file == "") && (ffastafile == "") && (ffastqfile == "")) { abort = true; m->mothurOut("[ERROR]: The file, ffastq and rfastq or ffasta and rfasta parameters are required.\n"); } + if ((file != "") && ((ffastafile != "") || (ffastqfile != ""))) { abort = true; m->mothurOut("[ERROR]: The file, ffastq and rfastq or ffasta and rfasta parameters are required.\n"); } + if ((ffastqfile != "") && (rfastqfile == "")) { abort = true; m->mothurOut("[ERROR]: If you provide use the ffastq, you must provide a rfastq file.\n"); } + if ((ffastqfile == "") && (rfastqfile != "")) { abort = true; m->mothurOut("[ERROR]: If you provide use the rfastq, you must provide a ffastq file.\n"); } + if ((ffastafile != "") && (rfastafile == "")) { abort = true; m->mothurOut("[ERROR]: If you provide use the ffasta, you must provide a rfasta file.\n"); } + if ((ffastafile == "") && (rfastafile != "")) { abort = true; m->mothurOut("[ERROR]: If you provide use the rfasta, you must provide a ffasta file.\n"); } + if ((fqualfile != "") && (rqualfile == "")) { abort = true; m->mothurOut("[ERROR]: If you provide use the fqfile, you must provide a rqfile file.\n"); } + if ((fqualfile == "") && (rqualfile != "")) { abort = true; m->mothurOut("[ERROR]: If you provide use the rqfile, you must provide a fqfile file.\n"); } + if (((fqualfile != "") || (rqualfile != "")) && ((ffastafile == "") || (rfastafile == ""))) { + abort = true; m->mothurOut("[ERROR]: If you provide use the rqfile or fqfile file, you must provide the ffasta and rfasta parameters.\n"); + } oligosfile = validParameter.validFile(parameters, "oligos", true); if (oligosfile == "not found") { oligosfile = ""; } @@ -253,7 +265,9 @@ MakeContigsCommand::MakeContigsCommand(string option) { else { m->setOligosFile(oligosfile); } //if the user changes the output directory command factory will send this info to us in the output parameter - outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = m->hasPath(ffastqfile); } + outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ + outputDir = ""; + } //check for optional parameter and set defaults @@ -274,10 +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); @@ -303,9 +320,26 @@ 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 = "illumina1.8+"; } + + 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; + } + + //fill convert table - goes from solexa to sanger. Used fq_all2std.pl as a reference. + for (int i = -64; i < 65; i++) { + char temp = (char) ((int)(33 + 10*log(1+pow(10,(i/10.0)))/log(10)+0.499)); + convertTable.push_back(temp); + } } } @@ -321,113 +355,177 @@ int MakeContigsCommand::execute(){ //read ffastq and rfastq files creating fasta and qual files. //this function will create a forward and reverse, fasta and qual files for each processor. - //files has an entry for each processor. files[i][0] = forwardFasta, files[i][1] = forwardQual, files[i][2] = reverseFasta, files[i][3] = reverseQual + //files has an entry for each processor. files[i][0] = forwardFasta, files[i][1] = forwardQual, files[i][2] = reverseFasta, files[i][3] = reverseQual. filesToProcess is for each filepair in the file parameter file. for ffastq and rfastq this will be size 1. unsigned long int numReads = 0; int start = time(NULL); longestBase = 1000; m->mothurOut("Reading fastq data...\n"); - vector< vector > files = readFastqFiles(numReads); + vector < vector< vector > > filesToProcess = preProcessData(numReads); m->mothurOut("Done.\n"); if (m->control_pressed) { return 0; } - vector > fastaFileNames; - vector > qualFileNames; - createGroup = false; - string outputGroupFileName; - map variables; - variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(ffastqfile)); - variables["[tag]"] = ""; - if(oligosfile != ""){ - createGroup = getOligos(fastaFileNames, qualFileNames); - if (createGroup) { - outputGroupFileName = getOutputFileName("group",variables); - outputNames.push_back(outputGroupFileName); outputTypes["group"].push_back(outputGroupFileName); - } - } - - 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(outQualFile); outputTypes["qfile"].push_back(outQualFile); - outputNames.push_back(outScrapFastaFile); outputTypes["fasta"].push_back(outScrapFastaFile); - outputNames.push_back(outScrapQualFile); outputTypes["qfile"].push_back(outScrapQualFile); - outputNames.push_back(outMisMatchFile); outputTypes["mismatch"].push_back(outMisMatchFile); - - m->mothurOut("Making contigs...\n"); - createProcesses(files, outFastaFile, outQualFile, outScrapFastaFile, outScrapQualFile, outMisMatchFile, fastaFileNames, qualFileNames); - m->mothurOut("Done.\n"); + map cvars; + string compOutputDir = outputDir; + if (outputDir == "") { compOutputDir = m->hasPath(file); } + cvars["[filename]"] = compOutputDir + m->getRootName(m->getSimpleName(file)); + cvars["[tag]"] = ""; + string compositeGroupFile = getOutputFileName("group",cvars); + cvars["[tag]"] = "trim"; + string compositeFastaFile = getOutputFileName("fasta",cvars); + cvars["[tag]"] = "scrap"; + string compositeScrapFastaFile = getOutputFileName("fasta",cvars); + cvars["[tag]"] = ""; + string compositeMisMatchFile = getOutputFileName("report",cvars); - //remove temp fasta and qual files - for (int i = 0; i < processors; i++) { for(int j = 0; j < files[i].size(); j++) { m->mothurRemove(files[i][j]); } } + 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(); + outputNames.push_back(compositeFastaFile); outputTypes["fasta"].push_back(compositeFastaFile); + outputNames.push_back(compositeMisMatchFile); outputTypes["report"].push_back(compositeMisMatchFile); + outputNames.push_back(compositeScrapFastaFile); outputTypes["fasta"].push_back(compositeScrapFastaFile); + } - if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } + map totalGroupCounts; - if(allFiles){ - map uniqueFastaNames;// so we don't add the same groupfile multiple times - map::iterator it; - set namesToRemove; - for(int i=0;iisBlank(fastaFileNames[i][j])){ - m->mothurRemove(fastaFileNames[i][j]); - namesToRemove.insert(fastaFileNames[i][j]); - - m->mothurRemove(qualFileNames[i][j]); - namesToRemove.insert(qualFileNames[i][j]); - }else{ - it = uniqueFastaNames.find(fastaFileNames[i][j]); - if (it == uniqueFastaNames.end()) { - uniqueFastaNames[fastaFileNames[i][j]] = barcodeNameVector[i]; - } - } - } - } - } - } - - //remove names for outputFileNames, just cleans up the output - vector outputNames2; - for(int i = 0; i < outputNames.size(); i++) { if (namesToRemove.count(outputNames[i]) == 0) { outputNames2.push_back(outputNames[i]); } } - outputNames = outputNames2; - - for (it = uniqueFastaNames.begin(); it != uniqueFastaNames.end(); it++) { - ifstream in; - m->openInputFile(it->first, in); + 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; + 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 != ""){ 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); + variables["[tag]"] = "scrap"; + string outScrapFastaFile = getOutputFileName("fasta",variables); + variables["[tag]"] = ""; + string outMisMatchFile = getOutputFileName("report",variables); + + m->mothurOut("Making contigs...\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]); } } + + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } + + if(allFiles){ + map uniqueFastaNames;// so we don't add the same groupfile multiple times + map::iterator it; + set namesToRemove; + for(int i=0;iisBlank(fastaFileNames[i][j])){ + m->mothurRemove(fastaFileNames[i][j]); + namesToRemove.insert(fastaFileNames[i][j]); + }else{ + it = uniqueFastaNames.find(fastaFileNames[i][j]); + if (it == uniqueFastaNames.end()) { + uniqueFastaNames[fastaFileNames[i][j]] = barcodeNameVector[i]; + } + } + } + } + } + } - ofstream out; - string thisGroupName = outputDir + m->getRootName(m->getSimpleName(it->first)); - 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; } + //remove names for outputFileNames, just cleans up the output + vector outputNames2; + for(int i = 0; i < outputNames.size(); i++) { if (namesToRemove.count(outputNames[i]) == 0) { outputNames2.push_back(outputNames[i]); } } + outputNames = outputNames2; + + for (it = uniqueFastaNames.begin(); it != uniqueFastaNames.end(); it++) { + ifstream in; + m->openInputFile(it->first, in); - Sequence currSeq(in); m->gobble(in); - out << currSeq.getName() << '\t' << it->second << endl; + ofstream out; + string thisGroupName = thisOutputDir + m->getRootName(m->getSimpleName(it->first)); + 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.close(); + in.close(); } - in.close(); - out.close(); } - } - - if (createGroup) { - ofstream outGroup; - m->openOutputFile(outputGroupFileName, outGroup); - for (map::iterator itGroup = groupMap.begin(); itGroup != groupMap.end(); itGroup++) { - outGroup << itGroup->first << '\t' << itGroup->second << endl; + + if (createFileGroup || createOligosGroup) { + ofstream outGroup; + m->openOutputFile(outputGroupFileName, outGroup); + for (map::iterator itGroup = groupMap.begin(); itGroup != groupMap.end(); itGroup++) { + outGroup << itGroup->first << '\t' << itGroup->second << endl; + } + outGroup.close(); + } + + if (filesToProcess.size() > 1) { //merge into large combo files + 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); + 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 + } + } + if (l == 0) { m->appendFiles(outMisMatchFile, compositeMisMatchFile); } + else { m->appendFilesWithoutHeaders(outMisMatchFile, compositeMisMatchFile); } + m->appendFiles(outFastaFile, compositeFastaFile); + m->appendFiles(outScrapFastaFile, compositeScrapFastaFile); + 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); + } } - outGroup.close(); + 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; } @@ -435,8 +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(); } @@ -449,12 +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()) { @@ -475,10 +567,74 @@ int MakeContigsCommand::execute(){ } } //********************************************************************************************************************** -int MakeContigsCommand::createProcesses(vector< vector > files, string outputFasta, string outputQual, string outputScrapFasta, string outputScrapQual, string outputMisMatches, vector > fastaFileNames, vector > qualFileNames) { +vector< vector< vector > > MakeContigsCommand::preProcessData(unsigned long int& numReads) { + try { + vector< vector< vector > > filesToProcess; + + if (ffastqfile != "") { //reading one file + vector< vector > files = readFastqFiles(numReads, ffastqfile, rfastqfile); + //adjust for really large processors or really small files + if (numReads == 0) { m->mothurOut("[ERROR]: no good reads.\n"); m->control_pressed = true; } + if (numReads < processors) { + for (int i = numReads; i < processors; i++) { for(int j = 0; j < files[i].size(); j++) { m->mothurRemove(files[i][j]); } files[i].clear(); } + files.resize(numReads); + processors = numReads; + } + filesToProcess.push_back(files); + }else if (file != "") { //reading multiple files + //return only valid pairs + vector< vector > filePairsToProcess = readFileNames(file); + + if (m->control_pressed) { return filesToProcess; } + + if (filePairsToProcess.size() != 0) { + for (int i = 0; i < filePairsToProcess.size(); i++) { + + if (m->control_pressed) { for (int l = 0; l < filesToProcess.size(); l++) { for (int k = 0; k < filesToProcess[l].size(); k++) { for(int j = 0; j < filesToProcess[l][k].size(); j++) { m->mothurRemove(filesToProcess[l][k][j]); } filesToProcess[l][k].clear(); } return filesToProcess; } } + + unsigned long int thisFilesReads; + vector< vector > files = readFastqFiles(thisFilesReads, filePairsToProcess[i][0], filePairsToProcess[i][1]); + + //adjust for really large processors or really small files + if (thisFilesReads < processors) { + m->mothurOut("[ERROR]: " + filePairsToProcess[i][0] + " has less than " + toString(processors) + " good reads, skipping\n"); + for (int k = 0; k < files.size(); k++) { for(int j = 0; j < files[k].size(); j++) { m->mothurRemove(files[k][j]); } files[k].clear(); } + }else { + filesToProcess.push_back(files); + numReads += thisFilesReads; + } + } + //all files are bad + if (numReads == 0) { m->control_pressed = true; } + } + }else if (ffastafile != "") { + vector< vector > files = readFastaFiles(numReads, ffastafile, rfastafile); + //adjust for really large processors or really small files + if (numReads == 0) { m->mothurOut("[ERROR]: no good reads.\n"); m->control_pressed = true; } + if (numReads < processors) { + for (int i = numReads; i < processors; i++) { for(int j = 0; j < files[i].size(); j++) { m->mothurRemove(files[i][j]); } files[i].clear(); } + files.resize(numReads); + processors = numReads; + } + filesToProcess.push_back(files); + }else { m->control_pressed = true; } //should not get here + + return filesToProcess; + } + catch(exception& e) { + m->errorOut(e, "MakeContigsCommand", "preProcessData"); + exit(1); + } +} +//********************************************************************************************************************** +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; @@ -491,7 +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; @@ -501,29 +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(); - - 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++) { @@ -547,12 +696,10 @@ int MakeContigsCommand::createProcesses(vector< vector > files, string o ofstream temp; m->openOutputFile(outputFasta, temp); temp.close(); - m->openOutputFile(outputQual, temp); temp.close(); m->openOutputFile(outputScrapFasta, temp); temp.close(); - m->openOutputFile(outputScrapQual, 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); @@ -611,8 +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; @@ -621,24 +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(); - - - 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; @@ -649,10 +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(); - - - tempPrimerQualFileNames[i][j] += extension; - m->openOutputFile(tempPrimerQualFileNames[i][j], temp); temp.close(); } } } @@ -661,13 +797,11 @@ int MakeContigsCommand::createProcesses(vector< vector > files, string o //parent do my part ofstream temp; m->openOutputFile(outputFasta, temp); temp.close(); - m->openOutputFile(outputQual, temp); temp.close(); m->openOutputFile(outputScrapFasta, temp); temp.close(); - m->openOutputFile(outputScrapQual, temp); temp.close(); - //do my part - 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); + processIDS.push_back(processors-1); + 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); @@ -675,6 +809,9 @@ int MakeContigsCommand::createProcesses(vector< vector > files, string o //Close all thread handles and free memory allocations. for(int i=0; i < pDataArray.size(); i++){ num += pDataArray[i]->count; + if (!pDataArray[i]->done) { + m->mothurOut("[ERROR]: process " + toString(i) + " only processed " + toString(pDataArray[i]->count) + " of 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; } @@ -695,16 +832,10 @@ int MakeContigsCommand::createProcesses(vector< vector > files, string o m->appendFiles((outputFasta + toString(processIDS[i]) + ".temp"), outputFasta); m->mothurRemove((outputFasta + toString(processIDS[i]) + ".temp")); - m->appendFiles((outputQual + toString(processIDS[i]) + ".temp"), outputQual); - m->mothurRemove((outputQual + toString(processIDS[i]) + ".temp")); - - m->appendFiles((outputScrapFasta + toString(processIDS[i]) + ".temp"), outputScrapFasta); + m->appendFiles((outputScrapFasta + toString(processIDS[i]) + ".temp"), outputScrapFasta); m->mothurRemove((outputScrapFasta + toString(processIDS[i]) + ".temp")); - - m->appendFiles((outputScrapQual + toString(processIDS[i]) + ".temp"), outputScrapQual); - m->mothurRemove((outputScrapQual + 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){ @@ -713,9 +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")); - - m->appendFiles((qualFileNames[j][k] + toString(processIDS[i]) + ".temp"), qualFileNames[j][k]); - m->mothurRemove((qualFileNames[j][k] + toString(processIDS[i]) + ".temp")); } } } @@ -730,7 +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; @@ -746,22 +874,21 @@ 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, outMisMatch, outScrapFasta; m->openInputFile(thisffastafile, inFFasta); - m->openInputFile(thisfqualfile, inFQual); m->openInputFile(thisrfastafile, inRFasta); - m->openInputFile(thisrqualfile, inRQual); - - ofstream outFasta, outQual, outMisMatch, outScrapFasta, outScrapQual; + if (thisfqualfile != "") { + m->openInputFile(thisfqualfile, inFQual); + m->openInputFile(thisrqualfile, inRQual); + } m->openOutputFile(outputFasta, outFasta); - m->openOutputFile(outputQual, outQual); m->openOutputFile(outputScrapFasta, outScrapFasta); - m->openOutputFile(outputScrapQual, outScrapQual); 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); - while ((!inFQual.eof()) && (!inFFasta.eof()) && (!inRFasta.eof()) && (!inRQual.eof())) { + while ((!inFFasta.eof()) && (!inRFasta.eof())) { if (m->control_pressed) { break; } @@ -772,20 +899,31 @@ int MakeContigsCommand::driver(vector files, string outputFasta, string //read seqs and quality info Sequence fSeq(inFFasta); m->gobble(inFFasta); Sequence rSeq(inRFasta); m->gobble(inRFasta); - QualityScores fQual(inFQual); m->gobble(inFQual); - QualityScores rQual(inRQual); m->gobble(inRQual); + QualityScores* fQual = NULL; QualityScores* rQual = NULL; + if (thisfqualfile != "") { + fQual = new QualityScores(inFQual); m->gobble(inFQual); + rQual = new QualityScores(inRQual); m->gobble(inRQual); + } int barcodeIndex = 0; int primerIndex = 0; if(barcodes.size() != 0){ - success = trimOligos.stripBarcode(fSeq, rSeq, fQual, rQual, barcodeIndex); + if (thisfqualfile != "") { + success = trimOligos.stripBarcode(fSeq, rSeq, *fQual, *rQual, barcodeIndex); + }else { + success = trimOligos.stripBarcode(fSeq, rSeq, barcodeIndex); + } if(success > bdiffs) { trashCode += 'b'; } else{ currentSeqsDiffs += success; } } if(primers.size() != 0){ - success = trimOligos.stripForward(fSeq, rSeq, fQual, rQual, primerIndex); + if (thisfqualfile != "") { + success = trimOligos.stripForward(fSeq, rSeq, *fQual, *rQual, primerIndex); + }else { + success = trimOligos.stripForward(fSeq, rSeq, primerIndex); + } if(success > pdiffs) { trashCode += 'f'; } else{ currentSeqsDiffs += success; } } @@ -794,7 +932,7 @@ int MakeContigsCommand::driver(vector files, string outputFasta, string //flip the reverse reads rSeq.reverseComplement(); - rQual.flipQScores(); + if (thisfqualfile != "") { rQual->flipQScores(); } //pairwise align alignment->align(fSeq.getUnaligned(), rSeq.getUnaligned()); @@ -806,28 +944,26 @@ 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(); - vector scores1 = fQual.getQualityScores(); - vector scores2 = rQual.getQualityScores(); + vector scores1, scores2; + if (thisfqualfile != "") { + scores1 = fQual->getQualityScores(); + scores2 = rQual->getQualityScores(); + delete fQual; delete rQual; + } // 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]; - 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]; - contigScores.push_back(scores2[BBaseMap[i]]); - } + for (int i = 0; i < overlapStart; i++) { contig += seq2[i]; } } int seq1End = fSeq.getEndPos(); @@ -835,49 +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]; - 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 - if (scores2[BBaseMap[i]] < threshold) { } // - else { - contig += seq2[i]; - contigScores.push_back(scores2[BBaseMap[i]]); - } - }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 - if (scores1[ABaseMap[i]] < threshold) { } // - else { - contig += seq1[i]; - contigScores.push_back(scores1[ABaseMap[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 insert. In that case eliminate base + if (thisfqualfile != "") { + 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 insert. In that case eliminate base + if (thisfqualfile != "") { + 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 - 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; - numMismatches++; + if (thisfqualfile != "") { + 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]; - 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]; - 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){ - if (createGroup) { + bool ignore = false; + + if (m->debug) { m->mothurOut(fSeq.getName()); } + + if (createOligosGroup) { if(barcodes.size() != 0){ string thisGroup = barcodeNameVector[barcodeIndex]; if (primers.size() != 0) { @@ -892,40 +1029,43 @@ int MakeContigsCommand::driver(vector files, string outputFasta, string if (m->debug) { m->mothurOut(", group= " + thisGroup + "\n"); } - groupMap[fSeq.getName()] = thisGroup; + int pos = thisGroup.find("ignore"); + if (pos == string::npos) { + groupMap[fSeq.getName()] = thisGroup; - map::iterator it = groupCounts.find(thisGroup); - if (it == groupCounts.end()) { groupCounts[thisGroup] = 1; } - else { groupCounts[it->first] ++; } + map::iterator it = groupCounts.find(thisGroup); + if (it == groupCounts.end()) { groupCounts[thisGroup] = 1; } + else { groupCounts[it->first] ++; } + }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"); } - if(allFiles){ + if(allFiles && !ignore){ ofstream output; m->openOutputFileAppend(fastaFileNames[barcodeIndex][primerIndex], output); output << ">" << fSeq.getName() << endl << contig << endl; output.close(); - - 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; - 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; - outScrapQual << ">" << fSeq.getName() << " | " << trashCode << endl; - for (int i = 0; i < contigScores.size(); i++) { outScrapQual << contigScores[i] << ' '; } - outScrapQual << endl; } num++; @@ -937,18 +1077,18 @@ int MakeContigsCommand::driver(vector files, string outputFasta, string if((num) % 1000 != 0){ m->mothurOut(toString(num)); m->mothurOutEndLine(); } inFFasta.close(); - inFQual.close(); inRFasta.close(); - inRQual.close(); outFasta.close(); - outQual.close(); outScrapFasta.close(); - outScrapQual.close(); outMisMatch.close(); + if (thisfqualfile != "") { + inFQual.close(); + inRQual.close(); + } delete alignment; - if (m->control_pressed) { m->mothurRemove(outputQual); m->mothurRemove(outputFasta); m->mothurRemove(outputScrapQual); m->mothurRemove(outputScrapFasta);m->mothurRemove(outputMisMatches);} - + if (m->control_pressed) { m->mothurRemove(outputFasta); m->mothurRemove(outputScrapFasta);m->mothurRemove(outputMisMatches); } + return num; } catch(exception& e) { @@ -957,10 +1097,9 @@ int MakeContigsCommand::driver(vector files, string outputFasta, string } } //********************************************************************************************************************** -vector< vector > MakeContigsCommand::readFastqFiles(unsigned long int& count){ +vector< vector > MakeContigsCommand::readFastqFiles(unsigned long int& count, string ffastq, string rfastq){ try { vector< vector > files; - //maps processors number to file pointer map > tempfiles; //tempfiles[0] = forwardFasta, [1] = forwardQual, [2] = reverseFasta, [3] = reverseQual map >::iterator it; @@ -975,10 +1114,12 @@ vector< vector > MakeContigsCommand::readFastqFiles(unsigned long int& c tempfiles[i] = temp; vector names; - string ffastafilename = outputDir + m->getRootName(m->getSimpleName(ffastqfile)) + toString(i) + "ffasta.temp"; - string rfastafilename = outputDir + m->getRootName(m->getSimpleName(rfastqfile)) + toString(i) + "rfasta.temp"; - string fqualfilename = outputDir + m->getRootName(m->getSimpleName(ffastqfile)) + toString(i) + "fqual.temp"; - string rqualfilename = outputDir + m->getRootName(m->getSimpleName(rfastqfile)) + toString(i) + "rqual.temp"; + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir = m->hasPath(ffastq); } + string ffastafilename = thisOutputDir + m->getRootName(m->getSimpleName(ffastq)) + toString(i) + "ffastatemp"; + string rfastafilename = thisOutputDir + m->getRootName(m->getSimpleName(rfastq)) + toString(i) + "rfastatemp"; + string fqualfilename = thisOutputDir + m->getRootName(m->getSimpleName(ffastq)) + toString(i) + "fqualtemp"; + string rqualfilename = thisOutputDir + m->getRootName(m->getSimpleName(rfastq)) + toString(i) + "rqualtemp"; names.push_back(ffastafilename); names.push_back(fqualfilename); names.push_back(rfastafilename); names.push_back(rqualfilename); files.push_back(names); @@ -999,10 +1140,10 @@ vector< vector > MakeContigsCommand::readFastqFiles(unsigned long int& c } ifstream inForward; - m->openInputFile(ffastqfile, inForward); + m->openInputFile(ffastq, inForward); ifstream inReverse; - m->openInputFile(rfastqfile, inReverse); + m->openInputFile(rfastq, inReverse); count = 0; map uniques; @@ -1027,7 +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)) { + //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 @@ -1046,7 +1187,7 @@ vector< vector > MakeContigsCommand::readFastqFiles(unsigned long int& c //report progress if((count) % 10000 == 0){ m->mothurOut(toString(count)); m->mothurOutEndLine(); } - } + //} } } //report progress @@ -1064,18 +1205,155 @@ vector< vector > MakeContigsCommand::readFastqFiles(unsigned long int& c inForward.close(); inReverse.close(); - //adjust for really large processors or really small files - if (count == 0) { m->mothurOut("[ERROR]: no good reads.\n"); m->control_pressed = true; } - if (count < processors) { - for (int i = count; i < processors; i++) { for(int j = 0; j < files[i].size(); j++) { m->mothurRemove(files[i][j]); } files[i].clear(); } - files.resize(count); - processors = count; + return files; + } + catch(exception& e) { + m->errorOut(e, "MakeContigsCommand", "readFastqFiles"); + exit(1); + } +} +//********************************************************************************************************************** +vector< vector > MakeContigsCommand::readFastaFiles(unsigned long int& count, string ffasta, string rfasta){ + try { + vector< vector > files; + //maps processors number to file pointer + map > tempfiles; //tempfiles[0] = forwardFasta, [1] = forwardQual, [2] = reverseFasta, [3] = reverseQual + map >::iterator it; + + //create files to write to + for (int i = 0; i < processors; i++) { + vector temp; + ofstream* outFF = new ofstream; temp.push_back(outFF); + ofstream* outFQ = new ofstream; temp.push_back(outFQ); + ofstream* outRF = new ofstream; temp.push_back(outRF); + ofstream* outRQ = new ofstream; temp.push_back(outRQ); + tempfiles[i] = temp; + + vector names; + string thisOutputDir = outputDir; + if (outputDir == "") { thisOutputDir = m->hasPath(ffasta); } + string ffastafilename = thisOutputDir + m->getRootName(m->getSimpleName(ffasta)) + toString(i) + "ffastatemp"; + string rfastafilename = thisOutputDir + m->getRootName(m->getSimpleName(rfasta)) + toString(i) + "rfastatemp"; + string fqualfilename = ""; + if (fqualfile != "") { fqualfilename = thisOutputDir + m->getRootName(m->getSimpleName(fqualfile)) + toString(i) + "fqual.temp"; m->openOutputFile(fqualfilename, *outFQ); } + string rqualfilename = ""; + if (rqualfile != "") { rqualfilename = thisOutputDir + m->getRootName(m->getSimpleName(rqualfile)) + toString(i) + "rqual.temp"; m->openOutputFile(rqualfilename, *outRQ); } + names.push_back(ffastafilename); names.push_back(fqualfilename); + names.push_back(rfastafilename); names.push_back(rqualfilename); + files.push_back(names); + + m->openOutputFile(ffastafilename, *outFF); + m->openOutputFile(rfastafilename, *outRF); + } + + if (m->control_pressed) { + //close files, delete ofstreams + 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]; } } + //remove files + for (int i = 0; i < files.size(); i++) { + for(int j = 0; j < files[i].size(); j++) { m->mothurRemove(files[i][j]); } + } + } + + ifstream inForwardFasta; + m->openInputFile(ffasta, inForwardFasta); + + ifstream inReverseFasta; + m->openInputFile(rfasta, inReverseFasta); + + ifstream inForwardQual, inReverseQual; + if (fqualfile != "") { m->openInputFile(fqualfile, inForwardQual); m->openInputFile(rqualfile, inReverseQual); } + + count = 0; + map uniques; + map::iterator itUniques; + while ((!inForwardFasta.eof()) || (!inReverseFasta.eof())) { + + 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; } + + //get a reads from forward and reverse fasta files + bool ignoref, ignorer; + fastqRead thisFread, thisRread; + if (!inForwardFasta.eof()) { + ignoref = false; + Sequence temp(inForwardFasta); m->gobble(inForwardFasta); + thisFread.name = temp.getName(); + thisFread.sequence = temp.getUnaligned(); + }else { ignoref = true; } + if (!inReverseFasta.eof()) { + ignorer = false; + Sequence temp(inReverseFasta); m->gobble(inReverseFasta); + thisRread.name = temp.getName(); + thisRread.sequence = temp.getUnaligned(); + }else { ignorer = true; } + + //get qual reads if given + if (fqualfile != "") { + if (!inForwardQual.eof() && !ignoref) { + QualityScores temp(inForwardQual); m->gobble(inForwardQual); + //if forward files dont match ignore read + if (thisFread.name != temp.getName()) { ignoref = true; } + else { thisFread.scores = temp.getQualityScores(); } + }else { ignoref = true; } + if (!inReverseQual.eof() && !ignorer) { + QualityScores temp(inReverseQual); m->gobble(inReverseQual); + //if reverse files dont match ignore read + if (thisRread.name != temp.getName()) { ignorer = true; } + else { thisRread.scores = temp.getQualityScores(); } + }else { ignorer = true; } + } + + vector reads = getReads(ignoref, ignorer, thisFread, thisRread, uniques); + + for (int i = 0; i < reads.size(); i++) { + fastqRead fread = reads[i].forward; + fastqRead rread = reads[i].reverse; + + if (m->debug) { m->mothurOut(toString(count) + '\t' + fread.name + '\t' + rread.name + '\n'); } + + // 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 + int process = count % processors; + + *(tempfiles[process][0]) << ">" << fread.name << endl << fread.sequence << endl; + *(tempfiles[process][2]) << ">" << rread.name << endl << rread.sequence << endl; + if (fqualfile != "") { //if you have quality info, print it + *(tempfiles[process][1]) << ">" << fread.name << endl; + for (int i = 0; i < fread.scores.size(); i++) { *(tempfiles[process][1]) << fread.scores[i] << " "; } + *(tempfiles[process][1]) << endl; + *(tempfiles[process][3]) << ">" << rread.name << endl; + for (int i = 0; i < rread.scores.size(); i++) { *(tempfiles[process][3]) << rread.scores[i] << " "; } + *(tempfiles[process][3]) << endl; + } + count++; + + //report progress + if((count) % 10000 == 0){ m->mothurOut(toString(count)); m->mothurOutEndLine(); } + //} + } + } + //report progress + if((count) % 10000 != 0){ m->mothurOut(toString(count)); m->mothurOutEndLine(); } + + if (uniques.size() != 0) { + for (itUniques = uniques.begin(); itUniques != uniques.end(); itUniques++) { + m->mothurOut("[WARNING]: did not find paired read for " + itUniques->first + ", ignoring.\n"); + } + m->mothurOutEndLine(); } + //close files, delete ofstreams + 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]; } } + inReverseFasta.close(); + inForwardFasta.close(); + if (fqualfile != "") { inReverseQual.close(); inReverseQual.close(); } + return files; } catch(exception& e) { - m->errorOut(e, "MakeContigsCommand", "readFastqFiles"); + m->errorOut(e, "MakeContigsCommand", "readFastaFiles"); exit(1); } } @@ -1192,15 +1470,8 @@ fastqRead MakeContigsCommand::readFastq(ifstream& in, bool& ignore){ if (name2 != "") { if (name != name2) { m->mothurOut("[WARNING]: names do not match. read " + name + " for fasta and " + name2 + " for quality, ignoring."); ignore=true; } } if (quality.length() != sequence.length()) { m->mothurOut("[WARNING]: Lengths do not match for sequence " + name + ". Read " + toString(sequence.length()) + " characters for fasta and " + toString(quality.length()) + " characters for quality scores, ignoring read."); ignore=true; } - vector qualScores; - int controlChar = int('!'); - for (int i = 0; i < quality.length(); i++) { - int temp = int(quality[i]); - temp -= controlChar; - - qualScores.push_back(temp); - } - + vector qualScores = convertQual(quality); + read.name = name; read.sequence = sequence; read.scores = qualScores; @@ -1212,20 +1483,20 @@ fastqRead MakeContigsCommand::readFastq(ifstream& in, bool& ignore){ exit(1); } } -//********************************************************************************************************************** -bool MakeContigsCommand::checkReads(fastqRead& forward, fastqRead& reverse){ +/********************************************************************************************************************** +bool MakeContigsCommand::checkReads(fastqRead& forward, fastqRead& reverse, string ffile, string rfile){ try { bool good = true; //do sequence lengths match if (forward.sequence.length() != reverse.sequence.length()) { - m->mothurOut("[WARNING]: For sequence " + forward.name + " I read a sequence of length " + toString(forward.sequence.length()) + " from " + ffastqfile + ", but read a sequence of length " + toString(reverse.sequence.length()) + " from " + rfastqfile + ", ignoring.\n"); + m->mothurOut("[WARNING]: For sequence " + forward.name + " I read a sequence of length " + toString(forward.sequence.length()) + " from " + ffile + ", but read a sequence of length " + toString(reverse.sequence.length()) + " from " + rfile + ", ignoring.\n"); good = false; } //do number of qual scores match if (forward.scores.size() != reverse.scores.size()) { - m->mothurOut("[WARNING]: For sequence " + forward.name + " I read " + toString(forward.scores.size()) + " quality scores from " + ffastqfile + ", but read " + toString(reverse.scores.size()) + " quality scores from " + rfastqfile + ", ignoring.\n"); + m->mothurOut("[WARNING]: For sequence " + forward.name + " I read " + toString(forward.scores.size()) + " quality scores from " + ffile + ", but read " + toString(reverse.scores.size()) + " quality scores from " + rfile + ", ignoring.\n"); good = false; } @@ -1235,13 +1506,128 @@ bool MakeContigsCommand::checkReads(fastqRead& forward, fastqRead& reverse){ m->errorOut(e, "MakeContigsCommand", "checkReads"); exit(1); } +}*/ +//*************************************************************************************************************** +vector< vector > MakeContigsCommand::readFileNames(string filename){ + try { + vector< vector > files; + string forward, reverse; + + ifstream in; + m->openInputFile(filename, in); + + while(!in.eof()) { + + if (m->control_pressed) { return files; } + + in >> forward; 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); + + + //check to make sure both are able to be opened + ifstream in2; + int openForward = m->openInputFile(forward, in2, "noerror"); + + //if you can't open it, try default location + if (openForward == 1) { + if (m->getDefaultPath() != "") { //default path is set + string tryPath = m->getDefaultPath() + m->getSimpleName(forward); + m->mothurOut("Unable to open " + forward + ". Trying default " + tryPath); m->mothurOutEndLine(); + ifstream in3; + openForward = m->openInputFile(tryPath, in3, "noerror"); + in3.close(); + forward = tryPath; + } + } + + //if you can't open it, try output location + if (openForward == 1) { + if (m->getOutputDir() != "") { //default path is set + string tryPath = m->getOutputDir() + m->getSimpleName(forward); + m->mothurOut("Unable to open " + forward + ". Trying output directory " + tryPath); m->mothurOutEndLine(); + ifstream in4; + openForward = m->openInputFile(tryPath, in4, "noerror"); + forward = tryPath; + in4.close(); + } + } + + if (openForward == 1) { //can't find it + m->mothurOut("[WARNING]: can't find " + forward + ", ignoring pair.\n"); + }else{ in2.close(); } + + ifstream in3; + int openReverse = m->openInputFile(reverse, in3, "noerror"); + + //if you can't open it, try default location + if (openReverse == 1) { + if (m->getDefaultPath() != "") { //default path is set + string tryPath = m->getDefaultPath() + m->getSimpleName(reverse); + m->mothurOut("Unable to open " + reverse + ". Trying default " + tryPath); m->mothurOutEndLine(); + ifstream in3; + openReverse = m->openInputFile(tryPath, in3, "noerror"); + in3.close(); + reverse = tryPath; + } + } + + //if you can't open it, try output location + if (openReverse == 1) { + if (m->getOutputDir() != "") { //default path is set + string tryPath = m->getOutputDir() + m->getSimpleName(reverse); + m->mothurOut("Unable to open " + reverse + ". Trying output directory " + tryPath); m->mothurOutEndLine(); + ifstream in4; + openReverse = m->openInputFile(tryPath, in4, "noerror"); + reverse = tryPath; + in4.close(); + } + } + + if (openReverse == 1) { //can't find it + m->mothurOut("[WARNING]: can't find " + reverse + ", ignoring pair.\n"); + }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(); + + return files; + } + catch(exception& e) { + m->errorOut(e, "MakeContigsCommand", "checkReads"); + exit(1); + } } //*************************************************************************************************************** //illumina data requires paired forward and reverse data //BARCODE atgcatgc atgcatgc groupName //PRIMER atgcatgc atgcatgc groupName //PRIMER atgcatgc atgcatgc -bool MakeContigsCommand::getOligos(vector >& fastaFileNames, vector >& qualFileNames){ +bool MakeContigsCommand::getOligos(vector >& fastaFileNames, string rootname){ try { ifstream in; m->openInputFile(oligosfile, in); @@ -1258,7 +1644,7 @@ bool MakeContigsCommand::getOligos(vector >& fastaFileNames, vect while(!in.eof()){ in >> type; - + if (m->debug) { m->mothurOut("[DEBUG]: reading type - " + type + ".\n"); } if(type[0] == '#'){ @@ -1279,7 +1665,7 @@ bool MakeContigsCommand::getOligos(vector >& fastaFileNames, vect if(foligo[i] == 'U') { foligo[i] = 'T'; } } - if(type == "FORWARD"){ + if(type == "PRIMER"){ m->gobble(in); in >> roligo; @@ -1295,7 +1681,7 @@ bool MakeContigsCommand::getOligos(vector >& fastaFileNames, vect // 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; } } @@ -1327,7 +1713,7 @@ 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; } } @@ -1373,7 +1759,6 @@ bool MakeContigsCommand::getOligos(vector >& fastaFileNames, vect for(int i=0;i uniqueNames; //used to cleanup outputFileNames @@ -1382,46 +1767,39 @@ bool MakeContigsCommand::getOligos(vector >& fastaFileNames, vect string primerName = primerNameVector[itPrimer->first]; string barcodeName = barcodeNameVector[itBar->first]; - - 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; - fastaFileName = outputDir + m->getRootName(m->getSimpleName(ffastqfile)) + comboGroupName + ".fasta"; - 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(); - - - qualFileName = outputDir + m->getRootName(m->getSimpleName(ffastqfile)) + comboGroupName + ".qual"; - if (uniqueNames.count(qualFileName) == 0) { - outputNames.push_back(qualFileName); - outputTypes["qfile"].push_back(qualFileName); + + 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; + fastaFileName = rootname + comboGroupName + ".fasta"; + 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(); } - - qualFileNames[itBar->first][itPrimer->first] = qualFileName; - m->openOutputFile(qualFileName, temp); temp.close(); } } } @@ -1495,6 +1873,41 @@ string MakeContigsCommand::reverseOligo(string oligo){ } } //********************************************************************************************************************** +vector MakeContigsCommand::convertQual(string qual) { + try { + vector qualScores; + bool negativeScores = false; + + for (int i = 0; i < qual.length(); i++) { + + int temp = 0; + 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) { + m->errorOut(e, "MakeContigsCommand", "convertQual"); + exit(1); + } +} + +//**********************************************************************************************************************