X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=parsefastaqcommand.cpp;h=051c1dfb057c0148c3f0053f94707b7e6d034dc0;hp=e6d7ce6d1aa30da836bb88f2833bd666ae11bd85;hb=d1c97b8c04bb75faca1e76ffad60b37a4d789d3d;hpb=91a27e0483827c06c21c4fe89558923bbfe86573 diff --git a/parsefastaqcommand.cpp b/parsefastaqcommand.cpp index e6d7ce6..051c1df 100644 --- a/parsefastaqcommand.cpp +++ b/parsefastaqcommand.cpp @@ -13,11 +13,13 @@ //********************************************************************************************************************** vector ParseFastaQCommand::setParameters(){ try { - CommandParameter pfastq("fastq", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pfastq); - CommandParameter pfasta("fasta", "Bool", "", "T", "", "", "",false,false); parameters.push_back(pfasta); - CommandParameter pqual("qfile", "Bool", "", "T", "", "", "",false,false); parameters.push_back(pqual); - CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir); - CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir); + CommandParameter pfastq("fastq", "InputTypes", "", "", "none", "none", "none","",false,true,true); parameters.push_back(pfastq); + CommandParameter pfasta("fasta", "Boolean", "", "T", "", "", "","fasta",false,false); parameters.push_back(pfasta); + CommandParameter pqual("qfile", "Boolean", "", "T", "", "", "","qfile",false,false); parameters.push_back(pqual); + CommandParameter ppacbio("pacbio", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(ppacbio); + CommandParameter pformat("format", "Multiple", "sanger-illumina-solexa-illumina1.8+", "sanger", "", "", "","",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); vector myArray; for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); } @@ -33,10 +35,12 @@ string ParseFastaQCommand::getHelpString(){ try { string helpString = ""; helpString += "The fastq.info command reads a fastq file and creates a fasta and quality file.\n"; - helpString += "The fastq.info command parameters are fastq, fasta and qfile; fastq is required.\n"; - helpString += "The fastq.info command should be in the following format: fastq.info(fastaq=yourFastaQFile).\n"; + helpString += "The fastq.info command parameters are fastq, fasta, qfile and format; fastq is required.\n"; + helpString += "The fastq.info command should be in the following format: fastq.info(fastaq=yourFastaQFile).\n"; + helpString += "The format parameter is used to indicate whether your sequences are sanger, solexa, illumina1.8+ or illumina, default=sanger.\n"; helpString += "The fasta parameter allows you to indicate whether you want a fasta file generated. Default=T.\n"; helpString += "The qfile parameter allows you to indicate whether you want a quality file generated. Default=T.\n"; + helpString += "The pacbio parameter allows you to indicate .... When set to true, quality scores of 0 will results in a corresponding base of N. Default=F.\n"; helpString += "Example fastq.info(fastaq=test.fastaq).\n"; helpString += "Note: No spaces between parameter labels (i.e. fastq), '=' and yourFastQFile.\n"; return helpString; @@ -47,6 +51,22 @@ string ParseFastaQCommand::getHelpString(){ } } //********************************************************************************************************************** +string ParseFastaQCommand::getOutputPattern(string type) { + try { + string pattern = ""; + + if (type == "fasta") { pattern = "[filename],fasta"; } + else if (type == "qfile") { pattern = "[filename],qual"; } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } + + return pattern; + } + catch(exception& e) { + m->errorOut(e, "ParseFastaQCommand", "getOutputPattern"); + exit(1); + } +} +//********************************************************************************************************************** ParseFastaQCommand::ParseFastaQCommand(){ try { abort = true; calledHelp = true; @@ -114,8 +134,19 @@ ParseFastaQCommand::ParseFastaQCommand(string option){ fasta = m->isTrue(temp); temp = validParameter.validFile(parameters, "qfile", false); if(temp == "not found"){ temp = "T"; } - qual = m->isTrue(temp); + qual = m->isTrue(temp); + + temp = validParameter.validFile(parameters, "pacbio", false); if(temp == "not found"){ temp = "F"; } + pacbio = m->isTrue(temp); + + format = validParameter.validFile(parameters, "format", false); if (format == "not found"){ format = "sanger"; } + + 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; + } + if ((!fasta) && (!qual)) { m->mothurOut("[ERROR]: no outputs selected. Aborting."); m->mothurOutEndLine(); abort=true; } } @@ -132,8 +163,10 @@ int ParseFastaQCommand::execute(){ if (abort == true) { if (calledHelp) { return 0; } return 2; } //open Output Files - string fastaFile = outputDir + m->getRootName(m->getSimpleName(fastaQFile)) + "fasta"; - string qualFile = outputDir + m->getRootName(m->getSimpleName(fastaQFile)) + "qual"; + map variables; + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(fastaQFile)); + string fastaFile = getOutputFileName("fasta",variables); + string qualFile = getOutputFileName("qfile",variables); ofstream outFasta, outQual; if (fasta) { m->openOutputFile(fastaFile, outFasta); outputNames.push_back(fastaFile); outputTypes["fasta"].push_back(fastaFile); } @@ -141,6 +174,12 @@ int ParseFastaQCommand::execute(){ ifstream in; m->openInputFile(fastaQFile, in); + + //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); + } while (!in.eof()) { @@ -150,7 +189,10 @@ int ParseFastaQCommand::execute(){ string name = m->getline(in); m->gobble(in); if (name == "") { m->mothurOut("[ERROR]: Blank fasta name."); m->mothurOutEndLine(); m->control_pressed = true; break; } else if (name[0] != '@') { m->mothurOut("[ERROR]: reading " + name + " expected a name with @ as a leading character."); m->mothurOutEndLine(); m->control_pressed = true; break; } - else { name = name.substr(1); } + else { + name = name.substr(1); + m->checkName(name); + } //read sequence string sequence = m->getline(in); m->gobble(in); @@ -160,7 +202,10 @@ int ParseFastaQCommand::execute(){ string name2 = m->getline(in); m->gobble(in); if (name2 == "") { m->mothurOut("[ERROR]: Blank quality name."); m->mothurOutEndLine(); m->control_pressed = true; break; } else if (name2[0] != '+') { m->mothurOut("[ERROR]: reading " + name2 + " expected a name with + as a leading character."); m->mothurOutEndLine(); m->control_pressed = true; break; } - else { name2 = name2.substr(1); } + else { + name2 = name2.substr(1); + m->checkName(name2); + } //read quality scores string quality = m->getline(in); m->gobble(in); @@ -170,22 +215,33 @@ int ParseFastaQCommand::execute(){ if (name2 != "") { if (name != name2) { m->mothurOut("[ERROR]: names do not match. read " + name + " for fasta and " + name2 + " for quality."); m->mothurOutEndLine(); m->control_pressed = true; break; } } if (quality.length() != sequence.length()) { m->mothurOut("[ERROR]: Lengths do not match for sequence " + name + ". Read " + toString(sequence.length()) + " characters for fasta and " + toString(quality.length()) + " characters for quality scores."); m->mothurOutEndLine(); m->control_pressed = true; break; } - //print sequence info to files - if (fasta) { outFasta << ">" << name << endl << sequence << endl; } - - if (qual) { - vector qualScores = convertQual(quality); + vector qualScores; + if (qual) { + qualScores = convertQual(quality); outQual << ">" << name << endl; for (int i = 0; i < qualScores.size(); i++) { outQual << qualScores[i] << " "; } outQual << endl; } + + if (m->control_pressed) { break; } + + if (pacbio) { + if (!qual) { qualScores = convertQual(quality); } //get scores if we didn't already + for (int i = 0; i < qualScores.size(); i++) { + if (qualScores[i] == 0){ sequence[i] = 'N'; } + } + } + + //print sequence info to files + if (fasta) { outFasta << ">" << name << endl << sequence << endl; } + } in.close(); if (fasta) { outFasta.close(); } if (qual) { outQual.close(); } - if (m->control_pressed) { outputTypes.clear(); m->mothurRemove(fastaFile); m->mothurRemove(qualFile); return 0; } + if (m->control_pressed) { outputTypes.clear(); outputNames.clear(); m->mothurRemove(fastaFile); m->mothurRemove(qualFile); return 0; } //set fasta file as new current fastafile string current = ""; @@ -216,15 +272,28 @@ vector ParseFastaQCommand::convertQual(string qual) { try { vector qualScores; - int controlChar = int('!'); - + bool negativeScores = false; + for (int i = 0; i < qual.length(); i++) { - int temp = int(qual[i]); - temp -= controlChar; - + + 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) {