X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=getsharedotucommand.cpp;h=5ae8da588ba4a6d36b6658527d8cd12e208c50c4;hb=01d5a60fc5f396339acf529151fa8186ee7c1a41;hp=76e5725d850e17d52bff0c72abfd2d83669778ee;hpb=da2b0566ec9d5f17880c5802ef70a7560d90fee1;p=mothur.git diff --git a/getsharedotucommand.cpp b/getsharedotucommand.cpp index 76e5725..5ae8da5 100644 --- a/getsharedotucommand.cpp +++ b/getsharedotucommand.cpp @@ -8,120 +8,250 @@ */ #include "getsharedotucommand.h" +#include "sharedutilities.h" //********************************************************************************************************************** +vector GetSharedOTUCommand::setParameters(){ + try { + CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "FNGLT", "none","fasta",false,false); parameters.push_back(pfasta); + CommandParameter pgroup("group", "InputTypes", "", "", "none", "FNGLT", "none","sharedseq",false,true,true); parameters.push_back(pgroup); + CommandParameter plist("list", "InputTypes", "", "", "none", "FNGLT", "none","sharedseq",false,true,true); parameters.push_back(plist); + CommandParameter poutput("output", "Multiple", "accnos-default", "default", "", "", "","",false,false); parameters.push_back(poutput); + CommandParameter plabel("label", "String", "", "", "", "", "","",false,false); parameters.push_back(plabel); + CommandParameter punique("unique", "String", "", "", "", "", "","",false,false,true); parameters.push_back(punique); + CommandParameter pshared("shared", "String", "", "", "", "", "","",false,false,true); parameters.push_back(pshared); + CommandParameter pinputdir("inputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(pinputdir); + CommandParameter poutputdir("outputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(poutputdir); -GetSharedOTUCommand::GetSharedOTUCommand(string option){ + vector myArray; + for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); } + return myArray; + } + catch(exception& e) { + m->errorOut(e, "GetSharedOTUCommand", "setParameters"); + exit(1); + } +} +//********************************************************************************************************************** +string GetSharedOTUCommand::getHelpString(){ + try { + string helpString = ""; + helpString += "The get.sharedseqs command parameters are list, group, label, unique, shared, output and fasta. The list and group parameters are required, unless you have valid current files.\n"; + helpString += "The label parameter allows you to select what distance levels you would like output files for, and are separated by dashes.\n"; + helpString += "The unique and shared parameters allow you to select groups you would like to know the shared info for, and are separated by dashes.\n"; + helpString += "If you enter your groups under the unique parameter mothur will return the otus that contain ONLY sequences from those groups.\n"; + helpString += "If you enter your groups under the shared parameter mothur will return the otus that contain sequences from those groups and may also contain sequences from other groups.\n"; + helpString += "If you do not enter any groups then the get.sharedseqs command will return sequences that are unique to all groups in your group file.\n"; + helpString += "The fasta parameter allows you to input a fasta file and outputs a fasta file for each distance level containing only the sequences that are in OTUs shared by the groups specified.\n"; + helpString += "The output parameter allows you to output the list of names without the group and bin number added. \n"; + helpString += "With this option you can use the names file as an input in get.seqs and remove.seqs commands. To do this enter output=accnos. \n"; + helpString += "The get.sharedseqs command outputs a .names file for each distance level containing a list of sequences in the OTUs shared by the groups specified.\n"; + helpString += "The get.sharedseqs command should be in the following format: get.sharedseqs(list=yourListFile, group=yourGroupFile, label=yourLabels, unique=yourGroups, fasta=yourFastafile, output=yourOutput).\n"; + helpString += "Example get.sharedseqs(list=amazon.fn.list, label=unique-0.01, group= amazon.groups, unique=forest-pasture, fasta=amazon.fasta, output=accnos).\n"; + helpString += "The output to the screen is the distance and the number of otus at that distance for the groups you specified.\n"; + helpString += "The default value for label is all labels in your inputfile. The default for groups is all groups in your file.\n"; + helpString += "Note: No spaces between parameter labels (i.e. label), '=' and parameters (i.e.yourLabel).\n"; + return helpString; + } + catch(exception& e) { + m->errorOut(e, "GetSharedOTUCommand", "getHelpString"); + exit(1); + } +} +//********************************************************************************************************************** +string GetSharedOTUCommand::getOutputPattern(string type) { + try { + string pattern = ""; + + if (type == "fasta") { pattern = "[filename],[distance],[group],shared.fasta"; } + else if (type == "accnos") { pattern = "[filename],[distance],[group],accnos"; } + else if (type == "sharedseqs") { pattern = "[filename],[distance],[group],shared.seqs"; } + else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; } + + return pattern; + } + catch(exception& e) { + m->errorOut(e, "GetSharedOTUCommand", "getOutputPattern"); + exit(1); + } +} +//********************************************************************************************************************** +GetSharedOTUCommand::GetSharedOTUCommand(){ + try { + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["fasta"] = tempOutNames; + outputTypes["accnos"] = tempOutNames; + outputTypes["sharedseqs"] = tempOutNames; + } + catch(exception& e) { + m->errorOut(e, "GetSharedOTUCommand", "GetSharedOTUCommand"); + exit(1); + } +} +//********************************************************************************************************************** +GetSharedOTUCommand::GetSharedOTUCommand(string option) { try { - globaldata = GlobalData::getInstance(); - abort = false; + abort = false; calledHelp = false; + unique = true; allLines = 1; - labels.clear(); //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[] = {"label","groups","fasta","list","group","output"}; - vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + vector myArray = setParameters(); OptionParser parser(option); map parameters = parser.getParameters(); ValidParameters validParameter; + map::iterator it; //check to make sure all parameters are valid for command - for (map::iterator it = parameters.begin(); it != parameters.end(); it++) { + for (it = parameters.begin(); it != parameters.end(); it++) { if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; } } + //initialize outputTypes + vector tempOutNames; + outputTypes["fasta"] = tempOutNames; + outputTypes["accnos"] = tempOutNames; + outputTypes["sharedseqs"] = tempOutNames; + + //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 = ""; } + + //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); + if (inputDir == "not found"){ inputDir = ""; } + else { + string path; + it = parameters.find("fasta"); + //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["fasta"] = inputDir + it->second; } + } + + it = parameters.find("list"); + //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["list"] = inputDir + it->second; } + } + + it = parameters.find("group"); + //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["group"] = inputDir + it->second; } + } + } + + //check for required parameters listfile = validParameter.validFile(parameters, "list", true); if (listfile == "not open") { abort = true; } - else if (listfile == "not found") { listfile = ""; } - else { globaldata->setListFile(listfile); globaldata->setFormat("list"); } + else if (listfile == "not found") { + listfile = m->getListFile(); + if (listfile != "") { format = "list"; m->mothurOut("Using " + listfile + " as input file for the list parameter."); m->mothurOutEndLine(); } + else { + m->mothurOut("No valid current list file. You must provide a list file."); m->mothurOutEndLine(); + abort = true; + } + }else { format = "list"; m->setListFile(listfile); } groupfile = validParameter.validFile(parameters, "group", true); if (groupfile == "not open") { abort = true; } - else if (groupfile == "not found") { groupfile = ""; } + else if (groupfile == "not found") { + groupfile = m->getGroupFile(); + if (groupfile != "") { m->mothurOut("Using " + groupfile + " as input file for the group parameter."); m->mothurOutEndLine(); } + else { + m->mothurOut("No valid current group file. You must provide a group file."); m->mothurOutEndLine(); + abort = true; + } + }else { m->setGroupFile(groupfile); } - if ((listfile == "") || (groupfile == "")) { mothurOut("The list and group parameters are required."); mothurOutEndLine(); abort = true; } + if ((listfile == "") || (groupfile == "")) { m->mothurOut("The list and group parameters are required."); m->mothurOutEndLine(); abort = true; } //check for optional parameter and set defaults // ...at some point should added some additional type checking... label = validParameter.validFile(parameters, "label", false); if (label == "not found") { label = ""; } else { - if(label != "all") { splitAtDash(label, labels); allLines = 0; } + if(label != "all") { m->splitAtDash(label, labels); allLines = 0; } else { allLines = 1; } } output = validParameter.validFile(parameters, "output", false); if (output == "not found") { output = ""; } + else if (output == "default") { output = ""; } - groups = validParameter.validFile(parameters, "groups", false); + groups = validParameter.validFile(parameters, "unique", false); if (groups == "not found") { groups = ""; } else { - splitAtDash(groups, Groups); - globaldata->Groups = Groups; + userGroups = "unique." + groups; + m->splitAtDash(groups, Groups); + m->setGroups(Groups); + + } + + groups = validParameter.validFile(parameters, "shared", false); + if (groups == "not found") { groups = ""; } + else { + userGroups = groups; + m->splitAtDash(groups, Groups); + m->setGroups(Groups); + unique = false; } fastafile = validParameter.validFile(parameters, "fasta", true); if (fastafile == "not open") { abort = true; } else if (fastafile == "not found") { fastafile = ""; } - + else { m->setFastaFile(fastafile); } } } catch(exception& e) { - errorOut(e, "GetSharedOTUCommand", "GetSharedOTUCommand"); - exit(1); - } -} -//********************************************************************************************************************** - -void GetSharedOTUCommand::help(){ - try { - mothurOut("The get.sharedseqs command parameters are list, group, label, groups, output and fasta. The list and group parameters are required.\n"); - mothurOut("The label parameter allows you to select what distance levels you would like output files for, and are separated by dashes.\n"); - mothurOut("The groups parameter allows you to select groups you would like to know the shared info for, and are separated by dashes.\n"); - mothurOut("The fasta parameter allows you to input a fasta file and outputs a fasta file for each distance level containing only the sequences that are in OTUs shared by the groups specified.\n"); - mothurOut("The output parameter allows you to output the list of names without the group and bin number added. \n"); - mothurOut("With this option you can use the names file as an input in get.seqs and remove.seqs commands. To do this enter output=accnos. \n"); - mothurOut("The get.sharedseqs command outputs a .names file for each distance level containing a list of sequences in the OTUs shared by the groups specified.\n"); - mothurOut("The get.sharedseqs command should be in the following format: get.sabund(label=yourLabels, groups=yourGroups, fasta=yourFastafile, output=yourOutput).\n"); - mothurOut("Example get.sharedseqs(list=amazon.fn.list, label=unique-0.01, group=forest-pasture, fasta=amazon.fasta, output=accnos).\n"); - mothurOut("The output to the screen is the distance and the number of otus at that distance for the groups you specified.\n"); - mothurOut("The default value for label is all labels in your inputfile. The default for groups is all groups in your file.\n"); - mothurOut("Note: No spaces between parameter labels (i.e. label), '=' and parameters (i.e.yourLabel).\n\n"); - } - catch(exception& e) { - errorOut(e, "GetSharedOTUCommand", "help"); + m->errorOut(e, "GetSharedOTUCommand", "GetSharedOTUCommand"); exit(1); } } - -//********************************************************************************************************************** - -GetSharedOTUCommand::~GetSharedOTUCommand(){} - //********************************************************************************************************************** int GetSharedOTUCommand::execute(){ try { - if (abort == true) { return 0; } + if (abort == true) { if (calledHelp) { return 0; } return 2; } groupMap = new GroupMap(groupfile); - groupMap->readMap(); - globaldata->gGroupmap = groupMap; + int error = groupMap->readMap(); + if (error == 1) { delete groupMap; return 0; } + + if (m->control_pressed) { delete groupMap; return 0; } if (Groups.size() == 0) { - Groups = groupMap->namesOfGroups; + Groups = groupMap->getNamesOfGroups(); + + //make string for outputfile name + userGroups = "unique."; + for(int i = 0; i < Groups.size(); i++) { userGroups += Groups[i] + "-"; } + userGroups = userGroups.substr(0, userGroups.length()-1); + }else{ + //sanity check for group names + SharedUtil util; + vector namesOfGroups = groupMap->getNamesOfGroups(); + util.setGroups(Groups, namesOfGroups); + groupMap->setNamesOfGroups(namesOfGroups); } - + //put groups in map to find easier for(int i = 0; i < Groups.size(); i++) { groupFinder[Groups[i]] = Groups[i]; @@ -129,11 +259,13 @@ int GetSharedOTUCommand::execute(){ if (fastafile != "") { ifstream inFasta; - openInputFile(fastafile, inFasta); + m->openInputFile(fastafile, inFasta); while(!inFasta.eof()) { - Sequence seq(inFasta); - seqs.push_back(seq); + if (m->control_pressed) { outputTypes.clear(); inFasta.close(); delete groupMap; return 0; } + + Sequence seq(inFasta); m->gobble(inFasta); + if (seq.getName() != "") { seqs.push_back(seq); } } inFasta.close(); } @@ -146,25 +278,31 @@ int GetSharedOTUCommand::execute(){ set userLabels = labels; ifstream in; - openInputFile(listfile, in); + m->openInputFile(listfile, in); //as long as you are not at the end of the file or done wih the lines you want while((!in.eof()) && ((allLines == 1) || (userLabels.size() != 0))) { + if (m->control_pressed) { + if (lastlist != NULL) { delete lastlist; } + for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } outputTypes.clear(); + delete groupMap; return 0; + } + list = new ListVector(in); if(allLines == 1 || labels.count(list->getLabel()) == 1){ - mothurOut(list->getLabel()); + m->mothurOut(list->getLabel()); process(list); processedLabels.insert(list->getLabel()); userLabels.erase(list->getLabel()); } - if ((anyLabelsToProcess(list->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) { + if ((m->anyLabelsToProcess(list->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) { string saveLabel = list->getLabel(); - mothurOut(lastlist->getLabel()); + m->mothurOut(lastlist->getLabel()); process(lastlist); processedLabels.insert(lastlist->getLabel()); @@ -186,18 +324,18 @@ int GetSharedOTUCommand::execute(){ set::iterator it; bool needToRun = false; for (it = userLabels.begin(); it != userLabels.end(); it++) { - mothurOut("Your file does not include the label " + *it); + m->mothurOut("Your file does not include the label " + *it); if (processedLabels.count(lastLabel) != 1) { - mothurOut(". I will use " + lastLabel + "."); mothurOutEndLine(); + m->mothurOut(". I will use " + lastLabel + "."); m->mothurOutEndLine(); needToRun = true; }else { - mothurOut(". Please refer to " + lastLabel + "."); mothurOutEndLine(); + m->mothurOut(". Please refer to " + lastLabel + "."); m->mothurOutEndLine(); } } //run last label if you need to if (needToRun == true) { - mothurOut(lastlist->getLabel()); + m->mothurOut(lastlist->getLabel()); process(lastlist); processedLabels.insert(lastlist->getLabel()); @@ -206,90 +344,105 @@ int GetSharedOTUCommand::execute(){ //reset groups parameter - globaldata->Groups.clear(); + m->clearGroups(); if (lastlist != NULL) { delete lastlist; } + + if (m->control_pressed) { outputTypes.clear(); for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } delete groupMap; return 0; } + + //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); } + } + + if (output == "accnos") { + itTypes = outputTypes.find("accnos"); + if (itTypes != outputTypes.end()) { + if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setAccnosFile(current); } + } + } + + 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(); + + return 0; } catch(exception& e) { - errorOut(e, "GetSharedOTUCommand", "execute"); + m->errorOut(e, "GetSharedOTUCommand", "execute"); exit(1); } } /***********************************************************/ -void GetSharedOTUCommand::process(ListVector* shared) { +int GetSharedOTUCommand::process(ListVector* shared) { try { map fastaMap; ofstream outNames; string outputFileNames; - if (output != "accnos") { - outputFileNames = getRootName(listfile) + shared->getLabel() + ".shared.seqs"; - }else { - outputFileNames = getRootName(listfile) + shared->getLabel() + ".accnos"; - } - openOutputFile(outputFileNames, outNames); + + if (outputDir == "") { outputDir += m->hasPath(listfile); } + map variables; + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(listfile)); + variables["[distance]"] = shared->getLabel(); + variables["[group]"] = userGroups; + if (output != "accnos") { outputFileNames = getOutputFileName("sharedseqs", variables); } + else { outputFileNames = getOutputFileName("accnos", variables); } + + m->openOutputFile(outputFileNames, outNames); bool wroteSomething = false; int num = 0; //go through each bin, find out if shared for (int i = 0; i < shared->getNumBins(); i++) { + if (m->control_pressed) { outNames.close(); m->mothurRemove(outputFileNames); return 0; } - bool sharedByAll = true; + bool uniqueOTU = true; map atLeastOne; - for (int m = 0; m < Groups.size(); m++) { - atLeastOne[Groups[m]] = 0; + for (int f = 0; f < Groups.size(); f++) { + atLeastOne[Groups[f]] = 0; } vector namesOfSeqsInThisBin; - string names = shared->get(i); - while ((names.find_first_of(',') != -1) && sharedByAll) { - string name = names.substr(0,names.find_first_of(',')); - names = names.substr(names.find_first_of(',')+1, names.length()); - + string names = shared->get(i); + vector binNames; + m->splitAtComma(names, binNames); + for(int j = 0; j < binNames.size(); j++) { + string name = binNames[j]; + //find group string seqGroup = groupMap->getGroup(name); if (output != "accnos") { - namesOfSeqsInThisBin.push_back((name + "\t" + seqGroup + "\t" + toString(i+1))); + namesOfSeqsInThisBin.push_back((name + "|" + seqGroup + "|" + toString(i+1))); }else { namesOfSeqsInThisBin.push_back(name); } - - if (seqGroup == "not found") { mothurOut(name + " is not in your groupfile. Please correct."); mothurOutEndLine(); exit(1); } - //is this seq in one of hte groups we care about - it = groupFinder.find(seqGroup); - if (it == groupFinder.end()) { sharedByAll = false; } //you have a sequence from a group you don't want - else { atLeastOne[seqGroup]++; } - } - - //get last name - //find group - if (sharedByAll) { - string seqGroup = groupMap->getGroup(names); - if (output != "accnos") { - namesOfSeqsInThisBin.push_back((names + "\t" + seqGroup + "\t" + toString(i+1))); - }else { namesOfSeqsInThisBin.push_back(names); } + if (seqGroup == "not found") { m->mothurOut(name + " is not in your groupfile. Please correct."); m->mothurOutEndLine(); exit(1); } - if (seqGroup == "not found") { mothurOut(names + " is not in your groupfile. Please correct."); mothurOutEndLine(); exit(1); } - //is this seq in one of hte groups we care about it = groupFinder.find(seqGroup); - if (it == groupFinder.end()) { sharedByAll = false; } //you have a sequence from a group you don't want + if (it == groupFinder.end()) { uniqueOTU = false; } //you have a sequence from a group you don't want else { atLeastOne[seqGroup]++; } } //make sure you have at least one seq from each group you want + bool sharedByAll = true; map::iterator it2; for (it2 = atLeastOne.begin(); it2 != atLeastOne.end(); it2++) { if (it2->second == 0) { sharedByAll = false; } } - //if shared, save names of seqs in that bin - if (sharedByAll) { + //if the user wants unique bins and this is unique then print + //or this the user wants shared bins and this bin is shared then print + if ((unique && uniqueOTU && sharedByAll) || (!unique && sharedByAll)) { wroteSomething = true; num++; @@ -300,8 +453,8 @@ void GetSharedOTUCommand::process(ListVector* shared) { if (fastafile != "") { if (output != "accnos") { - string seqName = namesOfSeqsInThisBin[j].substr(0,namesOfSeqsInThisBin[j].find_last_of('\t')); - seqName = seqName.substr(0,seqName.find_last_of('\t')); + string seqName = namesOfSeqsInThisBin[j].substr(0,namesOfSeqsInThisBin[j].find_last_of('|')); + seqName = seqName.substr(0,seqName.find_last_of('|')); fastaMap[seqName] = namesOfSeqsInThisBin[j]; //fastaMap needs to contain just the seq name for output later }else { fastaMap[namesOfSeqsInThisBin[j]] = namesOfSeqsInThisBin[j]; @@ -309,15 +462,12 @@ void GetSharedOTUCommand::process(ListVector* shared) { } } } - - - } outNames.close(); if (!wroteSomething) { - remove(outputFileNames.c_str()); + m->mothurRemove(outputFileNames); string outputString = "\t" + toString(num) + " - No otus shared by groups"; string groupString = ""; @@ -326,16 +476,26 @@ void GetSharedOTUCommand::process(ListVector* shared) { } outputString += groupString + "."; - mothurOut(outputString); mothurOutEndLine(); - }else { mothurOut("\t" + toString(num)); mothurOutEndLine(); } + m->mothurOut(outputString); m->mothurOutEndLine(); + }else { + m->mothurOut("\t" + toString(num)); m->mothurOutEndLine(); + outputNames.push_back(outputFileNames); + if (output != "accnos") { outputTypes["sharedseqs"].push_back(outputFileNames); } + else { outputTypes["accnos"].push_back(outputFileNames); } + } //if fasta file provided output new fasta file - if ((fastafile != "") && wroteSomething) { - string outputFileFasta = getRootName(fastafile) + shared->getLabel() + ".shared.fasta"; + if ((fastafile != "") && wroteSomething) { + if (outputDir == "") { outputDir += m->hasPath(fastafile); } + variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(fastafile)); + string outputFileFasta = getOutputFileName("fasta", variables); ofstream outFasta; - openOutputFile(outputFileFasta, outFasta); + m->openOutputFile(outputFileFasta, outFasta); + outputNames.push_back(outputFileFasta); outputTypes["fasta"].push_back(outputFileFasta); for (int k = 0; k < seqs.size(); k++) { + if (m->control_pressed) { outFasta.close(); return 0; } + //if this is a sequence we want, output it it = fastaMap.find(seqs[k].getName()); if (it != fastaMap.end()) { @@ -352,11 +512,12 @@ void GetSharedOTUCommand::process(ListVector* shared) { outFasta.close(); } - + + return 0; } catch(exception& e) { - errorOut(e, "GetSharedOTUCommand", "process"); + m->errorOut(e, "GetSharedOTUCommand", "process"); exit(1); } }