X-Git-Url: https://git.donarmstrong.com/?p=mothur.git;a=blobdiff_plain;f=makebiomcommand.cpp;h=4c350922608489b89156c01244c170d8688d930d;hp=9e8d3e39cb58e31e9f3dca2eeff35257eadd537a;hb=b206f634aae1b4ce13978d203247fb64757d5482;hpb=f687723a8357916e86a05116978e6869b039ce36 diff --git a/makebiomcommand.cpp b/makebiomcommand.cpp index 9e8d3e3..4c35092 100644 --- a/makebiomcommand.cpp +++ b/makebiomcommand.cpp @@ -9,6 +9,8 @@ #include "makebiomcommand.h" #include "sharedrabundvector.h" #include "inputdata.h" +#include "sharedutilities.h" +#include "phylotree.h" //taken from http://biom-format.org/documentation/biom_format.html /* Minimal Sparse @@ -91,13 +93,16 @@ //********************************************************************************************************************** vector MakeBiomCommand::setParameters(){ try { - CommandParameter pshared("shared", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pshared); - CommandParameter pcontaxonomy("contaxonomy", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pcontaxonomy); - CommandParameter pgroups("groups", "String", "", "", "", "", "",false,false); parameters.push_back(pgroups); - CommandParameter plabel("label", "String", "", "", "", "", "",false,false); parameters.push_back(plabel); - CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir); - CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir); - CommandParameter pmatrixtype("matrixtype", "Multiple", "sparse-dense", "sparse", "", "", "",false,false); parameters.push_back(pmatrixtype); + CommandParameter pshared("shared", "InputTypes", "", "", "none", "none", "none","biom",false,true,true); parameters.push_back(pshared); + CommandParameter pcontaxonomy("constaxonomy", "InputTypes", "", "", "none", "none", "none","",false,false); parameters.push_back(pcontaxonomy); + CommandParameter preference("reftaxonomy", "InputTypes", "", "", "none", "none", "refPi","",false,false); parameters.push_back(preference); + CommandParameter pmetadata("metadata", "InputTypes", "", "", "none", "none", "none","",false,false); parameters.push_back(pmetadata); + CommandParameter pgroups("groups", "String", "", "", "", "", "","",false,false); parameters.push_back(pgroups); + CommandParameter plabel("label", "String", "", "", "", "", "","",false,false); parameters.push_back(plabel); + CommandParameter ppicrust("picrust", "InputTypes", "", "", "none", "none", "refPi","shared",false,false); parameters.push_back(ppicrust); + CommandParameter pinputdir("inputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(pinputdir); + CommandParameter poutputdir("outputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(poutputdir); + CommandParameter pmatrixtype("matrixtype", "Multiple", "sparse-dense", "sparse", "", "", "","",false,false); parameters.push_back(pmatrixtype); vector myArray; for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); } @@ -112,11 +117,14 @@ vector MakeBiomCommand::setParameters(){ string MakeBiomCommand::getHelpString(){ try { string helpString = ""; - helpString += "The make.biom command parameters are shared, contaxonomy, groups, matrixtype and label. shared is required, unless you have a valid current file.\n"; + helpString += "The make.biom command parameters are shared, contaxonomy, metadata, groups, matrixtype, picrust, reftaxonomy and label. shared is required, unless you have a valid current file.\n"; // helpString += "The groups parameter allows you to specify which of the groups in your groupfile you would like included. The group names are separated by dashes.\n"; helpString += "The label parameter allows you to select what distance levels you would like, and are also separated by dashes.\n"; helpString += "The matrixtype parameter allows you to select what type you would like to make. Choices are sparse and dense, default is sparse.\n"; - helpString += "The contaxonomy file is the taxonomy file outputted by classify.otu(list=yourListfile, taxonomy=yourTaxonomyFile). Be SURE that the you are the constaxonomy file distance matches the shared file distance. ie, for *.0.03.cons.taxonomy set label=0.03. Mothur is smart enough to handle shared files that have been subsampled.\n"; + helpString += "The contaxonomy file is the taxonomy file outputted by classify.otu(list=yourListfile, taxonomy=yourTaxonomyFile). Be SURE that the you are the constaxonomy file distance matches the shared file distance. ie, for *.0.03.cons.taxonomy set label=0.03. Mothur is smart enough to handle shared files that have been subsampled. It is used to assign taxonomy information to the metadata of rows.\n"; + helpString += "The metadata parameter is used to provide experimental parameters to the columns. Things like 'sample1 gut human_gut'. \n"; + helpString += "The picrust parameter is used to provide the greengenes OTU IDs map table. NOTE: Picrust requires a greengenes taxonomy. \n"; + helpString += "The referencetax parameter is used with the picrust parameter. Picrust requires the greengenes OTU IDs to be in the biom file. \n"; helpString += "The make.biom command should be in the following format: make.biom(shared=yourShared, groups=yourGroups, label=yourLabels).\n"; helpString += "Example make.biom(shared=abrecovery.an.shared, groups=A-B-C).\n"; helpString += "The default value for groups is all the groups in your groupfile, and all labels in your inputfile will be used.\n"; @@ -130,24 +138,20 @@ string MakeBiomCommand::getHelpString(){ } } //********************************************************************************************************************** -string MakeBiomCommand::getOutputFileNameTag(string type, string inputName=""){ - try { - string outputFileName = ""; - map >::iterator it; +string MakeBiomCommand::getOutputPattern(string type) { + try { + string pattern = ""; - //is this a type this command creates - it = outputTypes.find(type); - if (it == outputTypes.end()) { m->mothurOut("[ERROR]: this command doesn't create a " + type + " output file.\n"); } - else { - if (type == "biom") { outputFileName = "biom"; } - else { m->mothurOut("[ERROR]: No definition for type " + type + " output file tag.\n"); m->control_pressed = true; } - } - return outputFileName; - } - catch(exception& e) { - m->errorOut(e, "MakeBiomCommand", "getOutputFileNameTag"); - exit(1); - } + if (type == "biom") { pattern = "[filename],[distance],biom"; } + else if (type == "shared") { pattern = "[filename],[distance],biom_shared"; } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } + + return pattern; + } + catch(exception& e) { + m->errorOut(e, "MakeBiomCommand", "getOutputPattern"); + exit(1); + } } //********************************************************************************************************************** @@ -157,6 +161,7 @@ MakeBiomCommand::MakeBiomCommand(){ setParameters(); vector tempOutNames; outputTypes["biom"] = tempOutNames; + outputTypes["shared"] = tempOutNames; } catch(exception& e) { m->errorOut(e, "MakeBiomCommand", "MakeBiomCommand"); @@ -190,6 +195,7 @@ MakeBiomCommand::MakeBiomCommand(string option) { //initialize outputTypes vector tempOutNames; outputTypes["biom"] = tempOutNames; + outputTypes["shared"] = tempOutNames; //if the user changes the input directory command factory will send this info to us in the output parameter string inputDir = validParameter.validFile(parameters, "inputdir", false); @@ -204,12 +210,36 @@ MakeBiomCommand::MakeBiomCommand(string option) { if (path == "") { parameters["shared"] = inputDir + it->second; } } - it = parameters.find("contaxonomy"); + it = parameters.find("constaxonomy"); + //user has given a template file + if(it != parameters.end()){ + path = m->hasPath(it->second); + //if the user has not given a path then, add inputdir. else leave path alone. + if (path == "") { parameters["constaxonomy"] = inputDir + it->second; } + } + + it = parameters.find("reftaxonomy"); + //user has given a template file + if(it != parameters.end()){ + path = m->hasPath(it->second); + //if the user has not given a path then, add inputdir. else leave path alone. + if (path == "") { parameters["reftaxonomy"] = inputDir + it->second; } + } + + it = parameters.find("picrust"); + //user has given a template file + if(it != parameters.end()){ + path = m->hasPath(it->second); + //if the user has not given a path then, add inputdir. else leave path alone. + if (path == "") { parameters["picrust"] = inputDir + it->second; } + } + + it = parameters.find("metadata"); //user has given a template file if(it != parameters.end()){ path = m->hasPath(it->second); //if the user has not given a path then, add inputdir. else leave path alone. - if (path == "") { parameters["contaxonomy"] = inputDir + it->second; } + if (path == "") { parameters["metadata"] = inputDir + it->second; } } } @@ -227,10 +257,21 @@ MakeBiomCommand::MakeBiomCommand(string option) { //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(sharedfile); } - contaxonomyfile = validParameter.validFile(parameters, "contaxonomy", true); + contaxonomyfile = validParameter.validFile(parameters, "constaxonomy", true); if (contaxonomyfile == "not found") { contaxonomyfile = ""; } else if (contaxonomyfile == "not open") { contaxonomyfile = ""; abort = true; } + + referenceTax = validParameter.validFile(parameters, "reftaxonomy", true); + if (referenceTax == "not found") { referenceTax = ""; } + else if (referenceTax == "not open") { referenceTax = ""; abort = true; } + + picrustOtuFile = validParameter.validFile(parameters, "picrust", true); + if (picrustOtuFile == "not found") { picrustOtuFile = ""; } + else if (picrustOtuFile == "not open") { picrustOtuFile = ""; abort = true; } + metadatafile = validParameter.validFile(parameters, "metadata", true); + if (metadatafile == "not found") { metadatafile = ""; } + else if (metadatafile == "not open") { metadatafile = ""; abort = true; } //check for optional parameter and set defaults // ...at some point should added some additional type checking... @@ -248,6 +289,12 @@ MakeBiomCommand::MakeBiomCommand(string option) { m->setGroups(Groups); } + if (picrustOtuFile != "") { + picrust=true; + if (contaxonomyfile == "") { m->mothurOut("[ERROR]: the constaxonomy parameter is required with the picrust parameter, aborting."); m->mothurOutEndLine(); abort = true; } + if (referenceTax == "") { m->mothurOut("[ERROR]: the reftaxonomy parameter is required with the picrust parameter, aborting."); m->mothurOutEndLine(); abort = true; } + }else { picrust=false; } + if ((contaxonomyfile != "") && (labels.size() > 1)) { m->mothurOut("[ERROR]: the contaxonomy parameter cannot be used with multiple labels."); m->mothurOutEndLine(); abort = true; } format = validParameter.validFile(parameters, "matrixtype", false); if (format == "not found") { format = "sparse"; } @@ -280,6 +327,8 @@ int MakeBiomCommand::execute(){ labels.insert(lastLabel); } + getSampleMetaData(lookup); + //if the users enters label "0.06" and there is no "0.06" in their file use the next lowest label. set processedLabels; set userLabels = labels; @@ -372,8 +421,10 @@ int MakeBiomCommand::execute(){ //********************************************************************************************************************** int MakeBiomCommand::getBiom(vector& lookup){ try { - - string outputFileName = outputDir + m->getRootName(m->getSimpleName(sharedfile)) + lookup[0]->getLabel() + "." + getOutputFileNameTag("biom"); + map variables; + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(sharedfile)); + variables["[distance]"] = lookup[0]->getLabel(); + string outputFileName = getOutputFileName("biom",variables); ofstream out; m->openOutputFile(outputFileName, out); outputNames.push_back(outputFileName); outputTypes["biom"].push_back(outputFileName); @@ -392,7 +443,9 @@ int MakeBiomCommand::getBiom(vector& lookup){ out << "{\n" + spaces + "\"id\":\"" + sharedfile + "-" + lookup[0]->getLabel() + "\",\n" + spaces + "\"format\": \"Biological Observation Matrix 0.9.1\",\n" + spaces + "\"format_url\": \"http://biom-format.org\",\n"; out << spaces + "\"type\": \"OTU table\",\n" + spaces + "\"generated_by\": \"" << mothurString << "\",\n" + spaces + "\"date\": \"" << dateString << "\",\n"; - vector metadata = getMetaData(lookup); + + vector metadata = getMetaData(lookup); + int numBins = lookup[0]->getNumBins(); if (m->control_pressed) { out.close(); return 0; } @@ -407,12 +460,12 @@ int MakeBiomCommand::getBiom(vector& lookup){ out << spaces + "\"rows\":[\n"; string rowFront = spaces + spaces + "{\"id\":\""; string rowBack = "\", \"metadata\":"; - for (int i = 0; i < m->currentBinLabels.size()-1; i++) { + for (int i = 0; i < numBins-1; i++) { if (m->control_pressed) { out.close(); return 0; } - out << rowFront << m->currentBinLabels[i] << rowBack << metadata[i] << "},\n"; + out << rowFront << m->currentSharedBinLabels[i] << rowBack << metadata[i] << "},\n"; } - out << rowFront << m->currentBinLabels[(m->currentBinLabels.size()-1)] << rowBack << metadata[(m->currentBinLabels.size()-1)] << "}\n" + spaces + "],\n"; - + out << rowFront << m->currentSharedBinLabels[(numBins-1)] << rowBack << metadata[(numBins-1)] << "}\n" + spaces + "],\n"; + //get column info /*"columns": [ {"id":"Sample1", "metadata":null}, @@ -423,16 +476,16 @@ int MakeBiomCommand::getBiom(vector& lookup){ {"id":"Sample6", "metadata":null} ],*/ - string colBack = "\", \"metadata\":null}"; + string colBack = "\", \"metadata\":"; out << spaces + "\"columns\":[\n"; for (int i = 0; i < lookup.size()-1; i++) { if (m->control_pressed) { out.close(); return 0; } - out << rowFront << lookup[i]->getGroup() << colBack << ",\n"; + out << rowFront << lookup[i]->getGroup() << colBack << sampleMetadata[i] << "},\n"; } - out << rowFront << lookup[(lookup.size()-1)]->getGroup() << colBack << "\n" + spaces + "],\n"; + out << rowFront << lookup[(lookup.size()-1)]->getGroup() << colBack << sampleMetadata[lookup.size()-1] << "}\n" + spaces + "],\n"; out << spaces + "\"matrix_type\": \"" << format << "\",\n" + spaces + "\"matrix_element_type\": \"int\",\n"; - out << spaces + "\"shape\": [" << m->currentBinLabels.size() << "," << lookup.size() << "],\n"; + out << spaces + "\"shape\": [" << numBins << "," << lookup.size() << "],\n"; out << spaces + "\"data\": ["; vector dataRows; @@ -535,7 +588,7 @@ vector MakeBiomCommand::getMetaData(vector& lookup) in.close(); //should the labels be Otu001 or PhyloType001 - string firstBin = m->currentBinLabels[0]; + string firstBin = m->currentSharedBinLabels[0]; string binTag = "Otu"; if ((firstBin.find("Otu")) == string::npos) { binTag = "PhyloType"; } @@ -549,30 +602,34 @@ vector MakeBiomCommand::getMetaData(vector& lookup) if (m->control_pressed) { return metadata; } //if there is a bin label use it otherwise make one - string binLabel = binTag; - string sbinNumber = otuLabels[i]; - if (sbinNumber.length() < snumBins.length()) { - int diff = snumBins.length() - sbinNumber.length(); - for (int h = 0; h < diff; h++) { binLabel += "0"; } - } - binLabel += sbinNumber; - - labelTaxMap[binLabel] = taxs[i]; + if (m->isContainingOnlyDigits(otuLabels[i])) { + string binLabel = binTag; + string sbinNumber = otuLabels[i]; + if (sbinNumber.length() < snumBins.length()) { + int diff = snumBins.length() - sbinNumber.length(); + for (int h = 0; h < diff; h++) { binLabel += "0"; } + } + binLabel += sbinNumber; + binLabel = m->getSimpleLabel(binLabel); + labelTaxMap[binLabel] = taxs[i]; + }else { labelTaxMap[m->getSimpleLabel(otuLabels[i])] = taxs[i]; } } + //merges OTUs classified to same gg otuid, sets otulabels to gg otuids, averages confidence scores of merged otus. overwritting of otulabels is fine because constaxonomy only allows for one label to be processed. If this assumption changes, could cause bug. + if (picrust) { getGreenGenesOTUIDs(lookup, labelTaxMap); } //{"taxonomy":["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__Escherichia", "s__"]} //traverse the binLabels forming the metadata strings and saving them //make sure to sanity check map::iterator it; - for (int i = 0; i < m->currentBinLabels.size(); i++) { + for (int i = 0; i < lookup[0]->getNumBins(); i++) { if (m->control_pressed) { return metadata; } - it = labelTaxMap.find(m->currentBinLabels[i]); + it = labelTaxMap.find(m->getSimpleLabel(m->currentSharedBinLabels[i])); - if (it == labelTaxMap.end()) { m->mothurOut("[ERROR]: can't find taxonomy information for " + m->currentBinLabels[i] + ".\n"); m->control_pressed = true; } + if (it == labelTaxMap.end()) { m->mothurOut("[ERROR]: can't find taxonomy information for " + m->currentSharedBinLabels[i] + ".\n"); m->control_pressed = true; } else { vector bootstrapValues; string data = "{\"taxonomy\":["; @@ -607,6 +664,255 @@ vector MakeBiomCommand::getMetaData(vector& lookup) } } +//********************************************************************************************************************** +int MakeBiomCommand::getGreenGenesOTUIDs(vector& lookup, map& labelTaxMap){ + try { + //read reftaxonomy + PhyloTree phylo(referenceTax); + + //read otu map file + map otuMap = readGGOtuMap(); //maps reference ID -> OTU ID + + if (m->control_pressed) { return 0; } + + map > ggOTUIDs; + //loop through otu taxonomies + for (map::iterator it = labelTaxMap.begin(); it != labelTaxMap.end(); it++) { //maps label -> consensus taxonomy + if (m->control_pressed) { break; } + + //get list of reference ids that map to this taxonomy + vector referenceIds = phylo.getSeqs(it->second); + + if (m->control_pressed) { break; } + + //look for each one in otu map to find match + string otuID = "not found"; + string referenceString = ""; + for (int i = 0; i < referenceIds.size(); i++) { + referenceString += referenceIds[i] + " "; + map::iterator itMap = otuMap.find(referenceIds[i]); + if (itMap != otuMap.end()) { //found it + otuID = itMap->second; + i += referenceIds.size(); //stop looking + } + } + + //if found, add otu to ggOTUID list + if (otuID != "not found") { + map >::iterator itGG = ggOTUIDs.find(otuID); + if (itGG == ggOTUIDs.end()) { + vector temp; temp.push_back(it->first); //save mothur OTU label + ggOTUIDs[otuID] = temp; + }else { ggOTUIDs[otuID].push_back(it->first); } //add mothur OTU label to list + }else { m->mothurOut("[ERROR]: could not find OTUId for " + it->second + ". Its reference sequences are " + referenceString + ".\n"); m->control_pressed = true; } + + } + + + vector newLookup; + for (int i = 0; i < lookup.size(); i++) { + SharedRAbundVector* temp = new SharedRAbundVector(); + temp->setLabel(lookup[i]->getLabel()); + temp->setGroup(lookup[i]->getGroup()); + newLookup.push_back(temp); + } + + map labelIndex; + for (int i = 0; i < m->currentSharedBinLabels.size(); i++) { labelIndex[m->getSimpleLabel(m->currentSharedBinLabels[i])] = i; } + + vector newBinLabels; + map newLabelTaxMap; + //loop through ggOTUID list combining mothur otus and adjusting labels + //ggOTUIDs = 16097 -> + for (map >::iterator itMap = ggOTUIDs.begin(); itMap != ggOTUIDs.end(); itMap++) { + if (m->control_pressed) { for (int j = 0; j < newLookup.size(); j++) { delete newLookup[j]; } return 0; } + + //set new gg otu id to taxonomy. OTU01 -> k__Bacteria becomes 16097 -> k__Bacteria + //find taxonomy of this otu + map::iterator it = labelTaxMap.find(m->getSimpleLabel(itMap->second[0])); + vector scores; + vector taxonomies = parseTax(it->second, scores); + + //merge/set OTU abundances + vector abunds; abunds.resize(lookup.size(), 0); + string mergeString = ""; + vector boots; boots.resize(scores.size(), 0); + for (int j = 0; j < itMap->second.size(); j++) { // + //merge bootstrap scores + vector scores; + vector taxonomies = parseTax(it->second, scores); + for (int i = 0; i < boots.size(); i++) { + float tempScore; m->mothurConvert(scores[i], tempScore); + boots[i] += tempScore; + } + + //merge abunds + mergeString += (itMap->second)[j] + " "; + for (int i = 0; i < lookup.size(); i++) { + abunds[i] += lookup[i]->getAbundance(labelIndex[m->getSimpleLabel((itMap->second)[j])]); + } + } + + if (m->debug) { m->mothurOut("[DEBUG]: merging " + mergeString + " for ggOTUid = " + itMap->first + ".\n"); } + + //average scores + //add merged otu to new lookup + for (int j = 0; j < boots.size(); j++) { boots[j] /= (float) itMap->second.size(); } + + //assemble new taxomoy + string newTaxString = ""; + for (int j = 0; j < boots.size(); j++) { + newTaxString += taxonomies[j] + "(" + toString(boots[j]) + ");"; + } + + //set new gg otu id to taxonomy. OTU01 -> k__Bacteria becomes 16097 -> k__Bacteria + //find taxonomy of this otu + newLabelTaxMap[itMap->first] = newTaxString; + + //add merged otu to new lookup + for (int j = 0; j < abunds.size(); j++) { newLookup[j]->push_back(abunds[j], newLookup[j]->getGroup()); } + + //saved otu label + newBinLabels.push_back(itMap->first); + } + + for (int j = 0; j < lookup.size(); j++) { delete lookup[j]; } + + lookup = newLookup; + m->currentSharedBinLabels = newBinLabels; + labelTaxMap = newLabelTaxMap; + + map variables; + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(sharedfile)); + variables["[distance]"] = lookup[0]->getLabel(); + string outputFileName = getOutputFileName("shared",variables); + ofstream out; + m->openOutputFile(outputFileName, out); + outputNames.push_back(outputFileName); outputTypes["shared"].push_back(outputFileName); + + lookup[0]->printHeaders(out); + + for (int i = 0; i < lookup.size(); i++) { + out << lookup[i]->getLabel() << '\t' << lookup[i]->getGroup() << '\t'; + lookup[i]->print(out); + } + out.close(); + + return 0; + } + catch(exception& e) { + m->errorOut(e, "MakeBiomCommand", "getGreenGenesOTUIDs"); + exit(1); + } + +} +//********************************************************************************************************************** +map MakeBiomCommand::readGGOtuMap(){ + try { + map otuMap; + + ifstream in; + m->openInputFile(picrustOtuFile, in); + + //map referenceIDs -> otuIDs + //lines look like: + //16097 671376 616121 533566 683683 4332909 4434717 772666 611808 695209 + while(!in.eof()) { + if (m->control_pressed) { break; } + + string line = m->getline(in); m->gobble(in); + vector pieces = m->splitWhiteSpace(line); + + if (pieces.size() != 0) { + string otuID = pieces[1]; + for (int i = 1; i < pieces.size(); i++) { otuMap[pieces[i]] = otuID; } + } + } + in.close(); + + return otuMap; + } + catch(exception& e) { + m->errorOut(e, "MakeBiomCommand", "readGGOtuMap"); + exit(1); + } + +} +//********************************************************************************************************************** +int MakeBiomCommand::getSampleMetaData(vector& lookup){ + try { + sampleMetadata.clear(); + if (metadatafile == "") { for (int i = 0; i < lookup.size(); i++) { sampleMetadata.push_back("null"); } } + else { + ifstream in; + m->openInputFile(metadatafile, in); + + vector groupNames, metadataLabels; + map > lines; + + string headerLine = m->getline(in); m->gobble(in); + vector pieces = m->splitWhiteSpace(headerLine); + + //save names of columns you are reading + for (int i = 1; i < pieces.size(); i++) { + metadataLabels.push_back(pieces[i]); + } + int count = metadataLabels.size(); + + vector groups = m->getGroups(); + + //read rest of file + while (!in.eof()) { + + if (m->control_pressed) { in.close(); return 0; } + + string group = ""; + in >> group; m->gobble(in); + groupNames.push_back(group); + + string line = m->getline(in); m->gobble(in); + vector thisPieces = m->splitWhiteSpaceWithQuotes(line); + + if (thisPieces.size() != count) { m->mothurOut("[ERROR]: expected " + toString(count) + " items of data for sample " + group + " read " + toString(thisPieces.size()) + ", quitting.\n"); } + else { if (m->inUsersGroups(group, groups)) { lines[group] = thisPieces; } } + + m->gobble(in); + } + in.close(); + + map >::iterator it; + for (int i = 0; i < lookup.size(); i++) { + + if (m->control_pressed) { return 0; } + + it = lines.find(lookup[i]->getGroup()); + + if (it == lines.end()) { m->mothurOut("[ERROR]: can't find metadata information for " + lookup[i]->getGroup() + ", quitting.\n"); m->control_pressed = true; } + else { + vector values = it->second; + + string data = "{"; + for (int j = 0; j < metadataLabels.size()-1; j++) { + values[j] = m->removeQuotes(values[j]); + data += "\"" + metadataLabels[j] + "\":\"" + values[j] + "\", "; + } + values[metadataLabels.size()-1] = m->removeQuotes(values[metadataLabels.size()-1]); + data += "\"" + metadataLabels[metadataLabels.size()-1] + "\":\"" + values[metadataLabels.size()-1] + "\"}"; + sampleMetadata.push_back(data); + } + } + } + + return 0; + + } + catch(exception& e) { + m->errorOut(e, "MakeBiomCommand", "getSampleMetaData"); + exit(1); + } + +} + /**************************************************************************************************/ //returns {Bacteria, Bacteroidetes, ..} and scores is filled with {100, 98, ...} or {null, null, null} vector MakeBiomCommand::parseTax(string tax, vector& scores) {