X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=parsefastaqcommand.cpp;h=74e3e2bc9f0bdedc88f90e7f923eafdb511470d6;hb=70491a12902e89b85cfa6b44a7b7fbe066ee2ac1;hp=63ed3144ad2a2b86ed33c6f9449b8d8143d38204;hpb=deba0af0ccdcb6005ed5b2b82649b137c63fbdf7;p=mothur.git diff --git a/parsefastaqcommand.cpp b/parsefastaqcommand.cpp index 63ed314..74e3e2b 100644 --- a/parsefastaqcommand.cpp +++ b/parsefastaqcommand.cpp @@ -16,7 +16,8 @@ vector ParseFastaQCommand::setParameters(){ 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 pformat("format", "Multiple", "sanger-illumina-solexa", "sanger", "", "", "","",false,false,true); parameters.push_back(pformat); + 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); @@ -36,9 +37,10 @@ string ParseFastaQCommand::getHelpString(){ 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, 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 or illumina, default=sanger.\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; @@ -132,12 +134,16 @@ 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 != "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; } @@ -183,7 +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); + for (int i = 0; i < name.length(); i++) { if (name[i] == ':') { name[i] = '_'; m->changedSeqNames = true; } } + } //read sequence string sequence = m->getline(in); m->gobble(in); @@ -193,7 +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); + for (int i = 0; i < name2.length(); i++) { if (name2[i] == ':') { name2[i] = '_'; m->changedSeqNames = true; } } + } //read quality scores string quality = m->getline(in); m->gobble(in); @@ -203,22 +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 = ""; @@ -249,21 +272,28 @@ vector ParseFastaQCommand::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) {