X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=getlineagecommand.cpp;h=c2be580bb73313c91322e903c87027dc5da405d9;hb=a6cf29fa4dac0909c7582cb1094151d34093ee76;hp=8a6f47c0998202943e398fce09a9ae52edfa5eda;hpb=b83fd3896a0575b61dabfb5ea82af11eae83ddce;p=mothur.git diff --git a/getlineagecommand.cpp b/getlineagecommand.cpp index 8a6f47c..c2be580 100644 --- a/getlineagecommand.cpp +++ b/getlineagecommand.cpp @@ -11,24 +11,58 @@ #include "sequence.hpp" #include "listvector.hpp" - //********************************************************************************************************************** -vector GetLineageCommand::getValidParameters(){ +vector GetLineageCommand::setParameters(){ try { - string Array[] = {"fasta","name", "group", "alignreport", "taxon", "dups", "list","taxonomy","outputdir","inputdir"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pfasta); + CommandParameter pname("name", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pname); + CommandParameter pgroup("group", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(pgroup); + CommandParameter plist("list", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(plist); + CommandParameter ptaxonomy("taxonomy", "InputTypes", "", "", "none", "FNGLT", "none",false,true); parameters.push_back(ptaxonomy); + CommandParameter palignreport("alignreport", "InputTypes", "", "", "none", "FNGLT", "none",false,false); parameters.push_back(palignreport); + CommandParameter ptaxon("taxon", "String", "", "", "", "", "",false,true); parameters.push_back(ptaxon); + CommandParameter pdups("dups", "Boolean", "", "T", "", "", "",false,false); parameters.push_back(pdups); + 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); } return myArray; } catch(exception& e) { - m->errorOut(e, "GetLineageCommand", "getValidParameters"); + m->errorOut(e, "GetLineageCommand", "setParameters"); exit(1); } } +//********************************************************************************************************************** +string GetLineageCommand::getHelpString(){ + try { + string helpString = ""; + helpString += "The get.lineage command reads a taxonomy file and any of the following file types: fasta, name, group, list or alignreport file.\n"; + helpString += "It outputs a file containing only the sequences from the taxonomy file that are from the taxon requested.\n"; + helpString += "The get.lineage command parameters are taxon, fasta, name, group, list, taxonomy, alignreport and dups. You must provide taxonomy unless you have a valid current taxonomy file.\n"; + helpString += "The dups parameter allows you to add the entire line from a name file if you add any name from the line. default=false. \n"; + helpString += "The taxon parameter allows you to select the taxons you would like to get and is required.\n"; + helpString += "You may enter your taxons with confidence scores, doing so will get only those sequences that belong to the taxonomy and whose cofidence scores is above the scores you give.\n"; + helpString += "If they belong to the taxonomy and have confidences below those you provide the sequence will not be selected.\n"; + helpString += "The get.lineage command should be in the following format: get.lineage(taxonomy=yourTaxonomyFile, taxon=yourTaxons).\n"; + helpString += "Example get.lineage(taxonomy=amazon.silva.taxonomy, taxon=Bacteria;Firmicutes;Bacilli;Lactobacillales;).\n"; + helpString += "Note: If you are running mothur in script mode you must wrap the taxon in ' characters so mothur will ignore the ; in the taxon.\n"; + helpString += "Example get.lineage(taxonomy=amazon.silva.taxonomy, taxon='Bacteria;Firmicutes;Bacilli;Lactobacillales;').\n"; + helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n"; + return helpString; + } + catch(exception& e) { + m->errorOut(e, "GetLineageCommand", "getHelpString"); + exit(1); + } +} + //********************************************************************************************************************** GetLineageCommand::GetLineageCommand(){ try { - abort = true; - //initialize outputTypes + abort = true; calledHelp = true; + setParameters(); vector tempOutNames; outputTypes["fasta"] = tempOutNames; outputTypes["taxonomy"] = tempOutNames; @@ -43,40 +77,16 @@ GetLineageCommand::GetLineageCommand(){ } } //********************************************************************************************************************** -vector GetLineageCommand::getRequiredParameters(){ - try { - string Array[] = {"taxonomy","taxon"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); - return myArray; - } - catch(exception& e) { - m->errorOut(e, "GetLineageCommand", "getRequiredParameters"); - exit(1); - } -} -//********************************************************************************************************************** -vector GetLineageCommand::getRequiredFiles(){ - try { - vector myArray; - return myArray; - } - catch(exception& e) { - m->errorOut(e, "GetLineageCommand", "getRequiredFiles"); - exit(1); - } -} -//********************************************************************************************************************** GetLineageCommand::GetLineageCommand(string option) { try { - abort = false; + abort = false; calledHelp = false; //allow user to run help - if(option == "help") { help(); abort = true; } + if(option == "help") { help(); abort = true; calledHelp = true; } + else if(option == "citation") { citation(); abort = true; calledHelp = true;} else { - //valid paramters for this command - string Array[] = {"fasta","name", "group", "alignreport", "taxon", "dups", "list","taxonomy","outputdir","inputdir"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); @@ -158,16 +168,19 @@ GetLineageCommand::GetLineageCommand(string option) { //check for required parameters fastafile = validParameter.validFile(parameters, "fasta", true); - if (fastafile == "not open") { abort = true; } - else if (fastafile == "not found") { fastafile = ""; } + if (fastafile == "not open") { fastafile = ""; abort = true; } + else if (fastafile == "not found") { fastafile = ""; } + else { m->setFastaFile(fastafile); } namefile = validParameter.validFile(parameters, "name", true); - if (namefile == "not open") { abort = true; } + if (namefile == "not open") { namefile = ""; abort = true; } else if (namefile == "not found") { namefile = ""; } + else { m->setNameFile(namefile); } groupfile = validParameter.validFile(parameters, "group", true); if (groupfile == "not open") { abort = true; } else if (groupfile == "not found") { groupfile = ""; } + else { m->setGroupFile(groupfile); } alignfile = validParameter.validFile(parameters, "alignreport", true); if (alignfile == "not open") { abort = true; } @@ -176,10 +189,15 @@ GetLineageCommand::GetLineageCommand(string option) { listfile = validParameter.validFile(parameters, "list", true); if (listfile == "not open") { abort = true; } else if (listfile == "not found") { listfile = ""; } + else { m->setListFile(listfile); } taxfile = validParameter.validFile(parameters, "taxonomy", true); - if (taxfile == "not open") { abort = true; } - else if (taxfile == "not found") { taxfile = ""; m->mothurOut("The taxonomy parameter is required for the get.lineage command."); m->mothurOutEndLine(); abort = true; } + if (taxfile == "not open") { taxfile = ""; abort = true; } + else if (taxfile == "not found") { + taxfile = m->getTaxonomyFile(); + if (taxfile != "") { m->mothurOut("Using " + taxfile + " as input file for the taxonomy parameter."); m->mothurOutEndLine(); } + else { m->mothurOut("You have no current taxonomy file and the taxonomy parameter is required."); m->mothurOutEndLine(); abort = true; } + }else { m->setTaxonomyFile(taxfile); } string usedDups = "true"; string temp = validParameter.validFile(parameters, "dups", false); @@ -196,12 +214,14 @@ GetLineageCommand::GetLineageCommand(string option) { if (taxons[0] == '\'') { taxons = taxons.substr(1); } if (taxons[(taxons.length()-1)] == '\'') { taxons = taxons.substr(0, (taxons.length()-1)); } } - + m->splitAtChar(taxons, listOfTaxons, '-'); if ((fastafile == "") && (namefile == "") && (groupfile == "") && (alignfile == "") && (listfile == "") && (taxfile == "")) { m->mothurOut("You must provide one of the following: fasta, name, group, alignreport, taxonomy or listfile."); m->mothurOutEndLine(); abort = true; } - if ((usedDups != "") && (namefile == "")) { m->mothurOut("You may only use dups with the name option."); m->mothurOutEndLine(); abort = true; } - + if ((namefile == "") && ((fastafile != "") || (taxfile != ""))){ + vector files; files.push_back(fastafile); files.push_back(taxfile); + parser.getNameFile(files); + } } } @@ -212,33 +232,10 @@ GetLineageCommand::GetLineageCommand(string option) { } //********************************************************************************************************************** -void GetLineageCommand::help(){ - try { - m->mothurOut("The get.lineage command reads a taxonomy file and any of the following file types: fasta, name, group, list or alignreport file.\n"); - m->mothurOut("It outputs a file containing only the sequences from the taxonomy file that are from the taxon requested.\n"); - m->mothurOut("The get.lineage command parameters are taxon, fasta, name, group, list, taxonomy, alignreport and dups. You must provide taxonomy and taxon.\n"); - m->mothurOut("The dups parameter allows you to add the entire line from a name file if you add any name from the line. default=false. \n"); - m->mothurOut("The taxon parameter allows you to select the taxons you would like to get.\n"); - m->mothurOut("You may enter your taxons with confidence scores, doing so will get only those sequences that belong to the taxonomy and whose cofidence scores is above the scores you give.\n"); - m->mothurOut("If they belong to the taxonomy and have confidences below those you provide the sequence will not be selected.\n"); - m->mothurOut("The get.lineage command should be in the following format: get.lineage(taxonomy=yourTaxonomyFile, taxon=yourTaxons).\n"); - m->mothurOut("Example get.lineage(taxonomy=amazon.silva.taxonomy, taxon=Bacteria;Firmicutes;Bacilli;Lactobacillales;).\n"); - m->mothurOut("Note: If you are running mothur in script mode you must wrap the taxon in ' characters so mothur will ignore the ; in the taxon.\n"); - m->mothurOut("Example get.lineage(taxonomy=amazon.silva.taxonomy, taxon='Bacteria;Firmicutes;Bacilli;Lactobacillales;').\n"); - m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n"); - } - catch(exception& e) { - m->errorOut(e, "GetLineageCommand", "help"); - exit(1); - } -} - -//********************************************************************************************************************** - int GetLineageCommand::execute(){ try { - if (abort == true) { return 0; } + if (abort == true) { if (calledHelp) { return 0; } return 2; } if (m->control_pressed) { return 0; } @@ -251,13 +248,40 @@ int GetLineageCommand::execute(){ if (listfile != "") { readList(); } - if (m->control_pressed) { outputTypes.clear(); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } + if (m->control_pressed) { outputTypes.clear(); for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } if (outputNames.size() != 0) { m->mothurOutEndLine(); m->mothurOut("Output File Names: "); m->mothurOutEndLine(); for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); } m->mothurOutEndLine(); + + //set fasta file as new current fastafile + string current = ""; + itTypes = outputTypes.find("fasta"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFastaFile(current); } + } + + itTypes = outputTypes.find("name"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setNameFile(current); } + } + + itTypes = outputTypes.find("group"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setGroupFile(current); } + } + + itTypes = outputTypes.find("list"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setListFile(current); } + } + + itTypes = outputTypes.find("taxonomy"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setTaxonomyFile(current); } + } } return 0; @@ -287,7 +311,7 @@ int GetLineageCommand::readFasta(){ while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } Sequence currSeq(in); name = currSeq.getName(); @@ -332,7 +356,7 @@ int GetLineageCommand::readList(){ while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } //read in list vector ListVector list(in); @@ -407,7 +431,7 @@ int GetLineageCommand::readName(){ while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } in >> firstCol; in >> secondCol; @@ -416,15 +440,7 @@ int GetLineageCommand::readName(){ if (dups) { hold = secondCol; } vector parsedNames; - //parse second column saving each name - while (secondCol.find_first_of(',') != -1) { - name = secondCol.substr(0,secondCol.find_first_of(',')); - secondCol = secondCol.substr(secondCol.find_first_of(',')+1, secondCol.length()); - parsedNames.push_back(name); - } - - //get name after last , - parsedNames.push_back(secondCol); + m->splitAtComma(secondCol, parsedNames); vector validSecond; for (int i = 0; i < parsedNames.size(); i++) { @@ -500,7 +516,7 @@ int GetLineageCommand::readGroup(){ while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } in >> name; //read from first column @@ -543,110 +559,121 @@ int GetLineageCommand::readTax(){ string name, tax; //bool wroteSomething = false; - - bool taxonsHasConfidence = false; - vector< map > searchTaxons; - string noConfidenceTaxons = taxons; - int hasConPos = taxons.find_first_of('('); - if (hasConPos != string::npos) { - taxonsHasConfidence = true; - searchTaxons = getTaxons(taxons); - noConfidenceTaxons = removeConfidences(taxons); + vector taxonsHasConfidence; taxonsHasConfidence.resize(listOfTaxons.size(), false); + vector< vector< map > > searchTaxons; searchTaxons.resize(listOfTaxons.size()); + vector noConfidenceTaxons; noConfidenceTaxons.resize(listOfTaxons.size(), ""); + + for (int i = 0; i < listOfTaxons.size(); i++) { + noConfidenceTaxons[i] = listOfTaxons[i]; + int hasConPos = listOfTaxons[i].find_first_of('('); + if (hasConPos != string::npos) { + taxonsHasConfidence[i] = true; + searchTaxons[i] = getTaxons(listOfTaxons[i]); + noConfidenceTaxons[i] = listOfTaxons[i]; + m->removeConfidences(noConfidenceTaxons[i]); + } } while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } in >> name; //read from first column in >> tax; //read from second column - string newtax = tax; - + for (int j = 0; j < listOfTaxons.size(); j++) { + + string newtax = tax; - //if the users file contains confidence scores we want to ignore them when searching for the taxons, unless the taxon has them - if (!taxonsHasConfidence) { - int hasConfidences = tax.find_first_of('('); - if (hasConfidences != string::npos) { - newtax = removeConfidences(tax); - } - - int pos = newtax.find(taxons); + //if the users file contains confidence scores we want to ignore them when searching for the taxons, unless the taxon has them + if (!taxonsHasConfidence[j]) { + int hasConfidences = tax.find_first_of('('); + if (hasConfidences != string::npos) { + newtax = tax; + m->removeConfidences(newtax); + } - if (pos != string::npos) { //this sequence contains the taxon the user wants - names.insert(name); - out << name << '\t' << tax << endl; - } + int pos = newtax.find(noConfidenceTaxons[j]); - }else{//if taxons has them and you don't them remove taxons - int hasConfidences = tax.find_first_of('('); - if (hasConfidences == string::npos) { - - int pos = newtax.find(noConfidenceTaxons); - if (pos != string::npos) { //this sequence contains the taxon the user wants - names.insert(name); + names.insert(name); out << name << '\t' << tax << endl; + //since you belong to at least one of the taxons we want you are included so no need to search for other + break; } - }else { //both have confidences so we want to make sure the users confidences are greater then or equal to the taxons - //first remove confidences from both and see if the taxonomy exists - - string noNewTax = tax; + }else{//if listOfTaxons[i] has them and you don't them remove taxons int hasConfidences = tax.find_first_of('('); - if (hasConfidences != string::npos) { - noNewTax = removeConfidences(tax); - } + if (hasConfidences == string::npos) { + + int pos = newtax.find(noConfidenceTaxons[j]); - int pos = noNewTax.find(noConfidenceTaxons); + if (pos != string::npos) { //this sequence contains the taxon the user wants + names.insert(name); + out << name << '\t' << tax << endl; + //since you belong to at least one of the taxons we want you are included so no need to search for other + break; + } + }else { //both have confidences so we want to make sure the users confidences are greater then or equal to the taxons + //first remove confidences from both and see if the taxonomy exists + + string noNewTax = tax; + int hasConfidences = tax.find_first_of('('); + if (hasConfidences != string::npos) { + noNewTax = tax; + m->removeConfidences(noNewTax); + } - if (pos != string::npos) { //if yes, then are the confidences okay + int pos = noNewTax.find(noConfidenceTaxons[j]); + + if (pos != string::npos) { //if yes, then are the confidences okay - bool good = true; - vector< map > usersTaxon = getTaxons(newtax); + bool good = true; + vector< map > usersTaxon = getTaxons(newtax); - //the usersTaxon is most likely longer than the searchTaxons, and searchTaxon[0] may relate to userTaxon[4] - //we want to "line them up", so we will find the the index where the searchstring starts - int index = 0; - for (int i = 0; i < usersTaxon.size(); i++) { + //the usersTaxon is most likely longer than the searchTaxons, and searchTaxon[0] may relate to userTaxon[4] + //we want to "line them up", so we will find the the index where the searchstring starts + int index = 0; + for (int i = 0; i < usersTaxon.size(); i++) { - if (usersTaxon[i].begin()->first == searchTaxons[0].begin()->first) { - index = i; - int spot = 0; - bool goodspot = true; - //is this really the start, or are we dealing with a taxon of the same name? - while ((spot < searchTaxons.size()) && ((i+spot) < usersTaxon.size())) { - if (usersTaxon[i+spot].begin()->first != searchTaxons[spot].begin()->first) { goodspot = false; break; } - else { spot++; } - } + if (usersTaxon[i].begin()->first == searchTaxons[j][0].begin()->first) { + index = i; + int spot = 0; + bool goodspot = true; + //is this really the start, or are we dealing with a taxon of the same name? + while ((spot < searchTaxons[j].size()) && ((i+spot) < usersTaxon.size())) { + if (usersTaxon[i+spot].begin()->first != searchTaxons[j][spot].begin()->first) { goodspot = false; break; } + else { spot++; } + } - if (goodspot) { break; } + if (goodspot) { break; } + } } - } - for (int i = 0; i < searchTaxons.size(); i++) { + for (int i = 0; i < searchTaxons[j].size(); i++) { - if ((i+index) < usersTaxon.size()) { //just in case, should never be false - if (usersTaxon[i+index].begin()->second < searchTaxons[i].begin()->second) { //is the users cutoff less than the search taxons + if ((i+index) < usersTaxon.size()) { //just in case, should never be false + if (usersTaxon[i+index].begin()->second < searchTaxons[j][i].begin()->second) { //is the users cutoff less than the search taxons + good = false; + break; + } + }else { good = false; break; } - }else { - good = false; - break; } - } - //passed the test so add you - if (good) { - names.insert(name); - out << name << '\t' << tax << endl; + //passed the test so add you + if (good) { + names.insert(name); + out << name << '\t' << tax << endl; + break; + } } } } - } - + } m->gobble(in); } @@ -665,10 +692,10 @@ int GetLineageCommand::readTax(){ } } /**************************************************************************************************/ -vector< map > GetLineageCommand::getTaxons(string tax) { +vector< map > GetLineageCommand::getTaxons(string tax) { try { - vector< map > t; + vector< map > t; string taxon = ""; int taxLength = tax.length(); for(int i=0;i > GetLineageCommand::getTaxons(string tax) { newtaxon = taxon; confidence = "0"; } - int con = 0; + float con = 0; convert(confidence, con); - map temp; + map temp; temp[newtaxon] = con; t.push_back(temp); @@ -706,29 +733,6 @@ vector< map > GetLineageCommand::getTaxons(string tax) { exit(1); } } -/**************************************************************************************************/ -string GetLineageCommand::removeConfidences(string tax) { - try { - - string taxon = ""; - int taxLength = tax.length(); - for(int i=0;ierrorOut(e, "GetLineageCommand", "removeConfidences"); - exit(1); - } -} //********************************************************************************************************************** //alignreport file has a column header line then all other lines contain 16 columns. we just want the first column since that contains the name int GetLineageCommand::readAlign(){ @@ -755,7 +759,7 @@ int GetLineageCommand::readAlign(){ while(!in.eof()){ - if (m->control_pressed) { in.close(); out.close(); remove(outputFileName.c_str()); return 0; } + if (m->control_pressed) { in.close(); out.close(); m->mothurRemove(outputFileName); return 0; } in >> name; //read from first column