X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=getsharedotucommand.cpp;h=7f8755645ce6664c5a299073e0ae1cbc6e875025;hb=8ef6687c1f586285d01c000cc5e359bf9c07c717;hp=3def8bc54f8b5a448a2023fb708eccd4e7f086f9;hpb=d2fc851cdaf57874b3ac8261b220fad35750daad;p=mothur.git diff --git a/getsharedotucommand.cpp b/getsharedotucommand.cpp index 3def8bc..7f87556 100644 --- a/getsharedotucommand.cpp +++ b/getsharedotucommand.cpp @@ -11,11 +11,12 @@ //********************************************************************************************************************** -GetSharedOTUCommand::GetSharedOTUCommand(string option){ +GetSharedOTUCommand::GetSharedOTUCommand(string option) { try { globaldata = GlobalData::getInstance(); abort = false; + unique = true; allLines = 1; labels.clear(); @@ -24,19 +25,54 @@ GetSharedOTUCommand::GetSharedOTUCommand(string option){ else { //valid paramters for this command - string Array[] = {"label","groups","fasta","list","group","output"}; + string Array[] = {"label","unique","shared","fasta","list","group","output","outputdir","inputdir"}; vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); 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; } } + //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 = 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 = 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 = 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; } @@ -47,7 +83,7 @@ GetSharedOTUCommand::GetSharedOTUCommand(string option){ if (groupfile == "not open") { abort = true; } else if (groupfile == "not found") { 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... @@ -61,11 +97,22 @@ GetSharedOTUCommand::GetSharedOTUCommand(string option){ output = validParameter.validFile(parameters, "output", false); if (output == "not found") { output = ""; } - groups = validParameter.validFile(parameters, "groups", false); + groups = validParameter.validFile(parameters, "unique", false); if (groups == "not found") { groups = ""; } else { + userGroups = "unique." + groups; + splitAtDash(groups, Groups); + globaldata->Groups = Groups; + + } + + groups = validParameter.validFile(parameters, "shared", false); + if (groups == "not found") { groups = ""; } + else { + userGroups = groups; splitAtDash(groups, Groups); globaldata->Groups = Groups; + unique = false; } fastafile = validParameter.validFile(parameters, "fasta", true); @@ -76,7 +123,7 @@ GetSharedOTUCommand::GetSharedOTUCommand(string option){ } catch(exception& e) { - errorOut(e, "GetSharedOTUCommand", "GetSharedOTUCommand"); + m->errorOut(e, "GetSharedOTUCommand", "GetSharedOTUCommand"); exit(1); } } @@ -84,20 +131,24 @@ GetSharedOTUCommand::GetSharedOTUCommand(string option){ void GetSharedOTUCommand::help(){ try { - mothurOut("The get.sharedotu 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.sharedotu 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.sharedotu command should be in the following format: get.sabund(label=yourLabels, groups=yourGroups, fasta=yourFastafile, output=yourOutput).\n"); - mothurOut("Example get.sharedotu(label=unique-0.01, group=forest-pasture, fasta=amazon.fasta, output=accnos).\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"); + m->mothurOut("The get.sharedseqs command parameters are list, group, label, unique, shared, output and fasta. The list and group parameters are required.\n"); + m->mothurOut("The label parameter allows you to select what distance levels you would like output files for, and are separated by dashes.\n"); + m->mothurOut("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"); + m->mothurOut("If you enter your groups under the unique parameter mothur will return the otus that contain ONLY sequences from those groups.\n"); + m->mothurOut("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"); + m->mothurOut("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"); + m->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"); + m->mothurOut("The output parameter allows you to output the list of names without the group and bin number added. \n"); + m->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"); + m->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"); + m->mothurOut("The get.sharedseqs command should be in the following format: get.sabund(label=yourLabels, groups=yourGroups, fasta=yourFastafile, output=yourOutput).\n"); + m->mothurOut("Example get.sharedseqs(list=amazon.fn.list, label=unique-0.01, group=forest-pasture, fasta=amazon.fasta, output=accnos).\n"); + m->mothurOut("The output to the screen is the distance and the number of otus at that distance for the groups you specified.\n"); + m->mothurOut("The default value for label is all labels in your inputfile. The default for groups is all groups in your file.\n"); + m->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", "help"); exit(1); } } @@ -114,13 +165,22 @@ int GetSharedOTUCommand::execute(){ if (abort == true) { return 0; } groupMap = new GroupMap(groupfile); - groupMap->readMap(); + int error = groupMap->readMap(); + if (error == 1) { delete groupMap; return 0; } + + if (m->control_pressed) { delete groupMap; return 0; } + globaldata->gGroupmap = groupMap; if (Groups.size() == 0) { Groups = groupMap->namesOfGroups; + + //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); } - + //put groups in map to find easier for(int i = 0; i < Groups.size(); i++) { groupFinder[Groups[i]] = Groups[i]; @@ -131,8 +191,10 @@ int GetSharedOTUCommand::execute(){ openInputFile(fastafile, inFasta); while(!inFasta.eof()) { - Sequence seq(inFasta); - seqs.push_back(seq); + if (m->control_pressed) { inFasta.close(); delete groupMap; return 0; } + + Sequence seq(inFasta); gobble(inFasta); + if (seq.getName() != "") { seqs.push_back(seq); } } inFasta.close(); } @@ -150,10 +212,16 @@ int GetSharedOTUCommand::execute(){ //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++) { remove(outputNames[i].c_str()); } + 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()); @@ -161,12 +229,16 @@ int GetSharedOTUCommand::execute(){ } if ((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()); userLabels.erase(lastlist->getLabel()); + + //restore real lastlabel to save below + list->setLabel(saveLabel); } lastLabel = list->getLabel(); @@ -181,18 +253,18 @@ 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()); @@ -204,83 +276,102 @@ int GetSharedOTUCommand::execute(){ globaldata->Groups.clear(); if (lastlist != NULL) { delete lastlist; } + + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } delete groupMap; return 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(); + + 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 = getRootName(listfile) + shared->getLabel() + ".names"; + string outputFileNames; + + if (outputDir == "") { outputDir += hasPath(listfile); } + if (output != "accnos") { + outputFileNames = outputDir + getRootName(getSimpleName(listfile)) + shared->getLabel() + userGroups + ".shared.seqs"; + }else { + outputFileNames = outputDir + getRootName(getSimpleName(listfile)) + shared->getLabel() + userGroups + ".accnos"; + } 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(); remove(outputFileNames.c_str()); 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) { + while ((names.find_first_of(',') != -1)) { string name = names.substr(0,names.find_first_of(',')); names = names.substr(names.find_first_of(',')+1, names.length()); - + //find group string seqGroup = groupMap->getGroup(name); if (output != "accnos") { - namesOfSeqsInThisBin.push_back((name + "|" + seqGroup + "|" + toString(i))); + namesOfSeqsInThisBin.push_back((name + "\t" + seqGroup + "\t" + toString(i+1))); }else { namesOfSeqsInThisBin.push_back(name); } - - if (seqGroup == "not found") { mothurOut(name + " is not in your groupfile. Please correct."); mothurOutEndLine(); exit(1); } + + if (seqGroup == "not found") { m->mothurOut(name + " is not in your groupfile. Please correct."); m->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]++; } } //get last name - //find group - if (sharedByAll) { - string seqGroup = groupMap->getGroup(names); - if (output != "accnos") { - namesOfSeqsInThisBin.push_back((names + "|" + seqGroup + "|" + toString(i))); - }else { namesOfSeqsInThisBin.push_back(names); } - - if (seqGroup == "not found") { mothurOut(names + " is not in your groupfile. Please correct."); mothurOutEndLine(); exit(1); } + 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(names + " is not in your groupfile. Please correct."); m->mothurOutEndLine(); exit(1); } + + //is this seq in one of hte groups we care about + it = groupFinder.find(seqGroup); + if (it == groupFinder.end()) { uniqueOTU = false; } //you have a sequence from a group you don't want + else { atLeastOne[seqGroup]++; } - //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]++; } - } //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++; //output list of names for (int j = 0; j < namesOfSeqsInThisBin.size(); j++) { @@ -288,8 +379,8 @@ void GetSharedOTUCommand::process(ListVector* shared) { if (fastafile != "") { if (output != "accnos") { - string seqName = namesOfSeqsInThisBin[j].substr(0,namesOfSeqsInThisBin[j].find_last_of('|')); - seqName = seqName.substr(0,seqName.find_last_of('|')); + string seqName = namesOfSeqsInThisBin[j].substr(0,namesOfSeqsInThisBin[j].find_last_of('\t')); + seqName = seqName.substr(0,seqName.find_last_of('\t')); fastaMap[seqName] = namesOfSeqsInThisBin[j]; //fastaMap needs to contain just the seq name for output later }else { fastaMap[namesOfSeqsInThisBin[j]] = namesOfSeqsInThisBin[j]; @@ -297,16 +388,13 @@ void GetSharedOTUCommand::process(ListVector* shared) { } } } - - - } outNames.close(); if (!wroteSomething) { remove(outputFileNames.c_str()); - string outputString = " - No otus shared by groups"; + string outputString = "\t" + toString(num) + " - No otus shared by groups"; string groupString = ""; for (int h = 0; h < Groups.size(); h++) { @@ -314,16 +402,23 @@ void GetSharedOTUCommand::process(ListVector* shared) { } outputString += groupString + "."; - mothurOut(outputString); mothurOutEndLine(); - }else { mothurOutEndLine(); } + m->mothurOut(outputString); m->mothurOutEndLine(); + }else { + m->mothurOut("\t" + toString(num)); m->mothurOutEndLine(); + outputNames.push_back(outputFileNames); + } //if fasta file provided output new fasta file - if ((fastafile != "") && wroteSomething) { - string outputFileFasta = getRootName(fastafile) + shared->getLabel() + ".fasta"; + if ((fastafile != "") && wroteSomething) { + if (outputDir == "") { outputDir += hasPath(fastafile); } + string outputFileFasta = outputDir + getRootName(getSimpleName(fastafile)) + shared->getLabel() + userGroups + ".shared.fasta"; ofstream outFasta; openOutputFile(outputFileFasta, outFasta); + outputNames.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()) { @@ -340,11 +435,12 @@ void GetSharedOTUCommand::process(ListVector* shared) { outFasta.close(); } - + + return 0; } catch(exception& e) { - errorOut(e, "GetSharedOTUCommand", "process"); + m->errorOut(e, "GetSharedOTUCommand", "process"); exit(1); } }