From f816b683e586575bfe3479760a8afd5ab08e8573 Mon Sep 17 00:00:00 2001 From: Sarah Westcott Date: Thu, 10 May 2012 10:11:38 -0400 Subject: [PATCH] added abundance and sample parameters to get.coremicrobiome command. --- Mothur.xcodeproj/project.pbxproj | 12 +- commandfactory.cpp | 10 +- getcoremicrobiomecommand.cpp | 408 +++++++++++++++++++++++++++++++ getcoremicrobiomecommand.h | 55 +++++ mothurout.cpp | 20 ++ mothurout.h | 1 + shhhercommand.cpp | 4 +- 7 files changed, 497 insertions(+), 13 deletions(-) create mode 100644 getcoremicrobiomecommand.cpp create mode 100644 getcoremicrobiomecommand.h diff --git a/Mothur.xcodeproj/project.pbxproj b/Mothur.xcodeproj/project.pbxproj index efac27e..8943df2 100644 --- a/Mothur.xcodeproj/project.pbxproj +++ b/Mothur.xcodeproj/project.pbxproj @@ -8,7 +8,7 @@ /* Begin PBXBuildFile section */ 219C1DE01552C4BD004209F9 /* newcommandtemplate.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 219C1DDF1552C4BD004209F9 /* newcommandtemplate.cpp */; }; - 219C1DE41559BCCF004209F9 /* getcoremicrobiomcommand.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 219C1DE31559BCCD004209F9 /* getcoremicrobiomcommand.cpp */; }; + 219C1DE41559BCCF004209F9 /* getcoremicrobiomecommand.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 219C1DE31559BCCD004209F9 /* getcoremicrobiomecommand.cpp */; }; 7E6BE10A12F710D8007ADDBE /* refchimeratest.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 7E6BE10912F710D8007ADDBE /* refchimeratest.cpp */; }; 8DD76FB00486AB0100D96B5E /* mothur.1 in CopyFiles */ = {isa = PBXBuildFile; fileRef = C6A0FF2C0290799A04C91782 /* mothur.1 */; }; A70332B712D3A13400761E33 /* makefile in Sources */ = {isa = PBXBuildFile; fileRef = A70332B512D3A13400761E33 /* makefile */; }; @@ -362,8 +362,8 @@ /* Begin PBXFileReference section */ 219C1DDF1552C4BD004209F9 /* newcommandtemplate.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = newcommandtemplate.cpp; sourceTree = ""; }; 219C1DE11552C508004209F9 /* newcommandtemplate.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = newcommandtemplate.h; sourceTree = ""; }; - 219C1DE31559BCCD004209F9 /* getcoremicrobiomcommand.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = getcoremicrobiomcommand.cpp; sourceTree = ""; }; - 219C1DE51559BCF2004209F9 /* getcoremicrobiomcommand.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = getcoremicrobiomcommand.h; sourceTree = ""; }; + 219C1DE31559BCCD004209F9 /* getcoremicrobiomecommand.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = getcoremicrobiomecommand.cpp; sourceTree = ""; }; + 219C1DE51559BCF2004209F9 /* getcoremicrobiomecommand.h */ = {isa = PBXFileReference; fileEncoding = 4; path = getcoremicrobiomecommand.h; sourceTree = ""; }; 7E6BE10812F710D8007ADDBE /* refchimeratest.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = refchimeratest.h; sourceTree = ""; }; 7E6BE10912F710D8007ADDBE /* refchimeratest.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = refchimeratest.cpp; sourceTree = ""; }; 7E78911B135F3E8600E725D2 /* eachgapdistignorens.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = eachgapdistignorens.h; sourceTree = ""; }; @@ -1255,8 +1255,8 @@ A7E9B6E312D37EC400DA6239 /* filterseqscommand.cpp */, A778FE69134CA6CA00C0BA33 /* getcommandinfocommand.h */, A778FE6A134CA6CA00C0BA33 /* getcommandinfocommand.cpp */, - 219C1DE51559BCF2004209F9 /* getcoremicrobiomcommand.h */, - 219C1DE31559BCCD004209F9 /* getcoremicrobiomcommand.cpp */, + 219C1DE51559BCF2004209F9 /* getcoremicrobiomecommand.h */, + 219C1DE31559BCCD004209F9 /* getcoremicrobiomecommand.cpp */, A7FE7C3E1330EA1000F7B327 /* getcurrentcommand.h */, A7FE7C3F1330EA1000F7B327 /* getcurrentcommand.cpp */, A7E9B6F312D37EC400DA6239 /* getgroupcommand.h */, @@ -2167,7 +2167,7 @@ A7D755DA1535F679009BF21A /* treereader.cpp in Sources */, A724D2B7153C8628000A826F /* makebiomcommand.cpp in Sources */, 219C1DE01552C4BD004209F9 /* newcommandtemplate.cpp in Sources */, - 219C1DE41559BCCF004209F9 /* getcoremicrobiomcommand.cpp in Sources */, + 219C1DE41559BCCF004209F9 /* getcoremicrobiomecommand.cpp in Sources */, ); runOnlyForDeploymentPostprocessing = 0; }; diff --git a/commandfactory.cpp b/commandfactory.cpp index 6d645f3..53a438a 100644 --- a/commandfactory.cpp +++ b/commandfactory.cpp @@ -131,7 +131,7 @@ #include "pcrseqscommand.h" #include "createdatabasecommand.h" #include "makebiomcommand.h" -#include "getcoremicrobiomcommand.h" +#include "GetCoreMicroBiomeCommand.h" /*******************************************************/ @@ -284,7 +284,7 @@ CommandFactory::CommandFactory(){ commands["pcr.seqs"] = "pcr.seqs"; commands["create.database"] = "create.database"; commands["make.biom"] = "make.biom"; - commands["get.coremicrobiom"] = "get.coremicrobiom"; + commands["get.coremicrobiome"] = "get.coremicrobiome"; commands["quit"] = "MPIEnabled"; } @@ -495,7 +495,7 @@ Command* CommandFactory::getCommand(string commandName, string optionString){ else if(commandName == "pcr.seqs") { command = new PcrSeqsCommand(optionString); } else if(commandName == "create.database") { command = new CreateDatabaseCommand(optionString); } else if(commandName == "make.biom") { command = new MakeBiomCommand(optionString); } - else if(commandName == "get.coremicrobiom") { command = new GetCoreMicroBiomCommand(optionString); } + else if(commandName == "get.coremicrobiome") { command = new GetCoreMicroBiomeCommand(optionString); } else { command = new NoCommand(optionString); } return command; @@ -647,7 +647,7 @@ Command* CommandFactory::getCommand(string commandName, string optionString, str else if(commandName == "pcr.seqs") { pipecommand = new PcrSeqsCommand(optionString); } else if(commandName == "create.database") { pipecommand = new CreateDatabaseCommand(optionString); } else if(commandName == "make.biom") { pipecommand = new MakeBiomCommand(optionString); } - else if(commandName == "get.coremicrobiom") { pipecommand = new GetCoreMicroBiomCommand(optionString); } + else if(commandName == "get.coremicrobiome") { pipecommand = new GetCoreMicroBiomeCommand(optionString); } else { pipecommand = new NoCommand(optionString); } return pipecommand; @@ -785,7 +785,7 @@ Command* CommandFactory::getCommand(string commandName){ else if(commandName == "pcr.seqs") { shellcommand = new PcrSeqsCommand(); } else if(commandName == "create.database") { shellcommand = new CreateDatabaseCommand(); } else if(commandName == "make.biom") { shellcommand = new MakeBiomCommand(); } - else if(commandName == "get.coremicrobiom") { shellcommand = new GetCoreMicroBiomCommand(); } + else if(commandName == "get.coremicrobiome") { shellcommand = new GetCoreMicroBiomeCommand(); } else { shellcommand = new NoCommand(); } return shellcommand; diff --git a/getcoremicrobiomecommand.cpp b/getcoremicrobiomecommand.cpp new file mode 100644 index 0000000..97e2c7a --- /dev/null +++ b/getcoremicrobiomecommand.cpp @@ -0,0 +1,408 @@ +// +// GetCoreMicroBiomeCommand.cpp +// Mothur +// +// Created by John Westcott on 5/8/12. +// Copyright (c) 2012 Schloss Lab. All rights reserved. +// + +#include "GetCoreMicroBiomeCommand.h" + + +//********************************************************************************************************************** +vector GetCoreMicroBiomeCommand::setParameters(){ + try { + CommandParameter pshared("shared", "InputTypes", "", "", "SharedRel", "SharedRel", "none",false,false); parameters.push_back(pshared); + CommandParameter prelabund("relabund", "InputTypes", "", "", "SharedRel", "SharedRel", "none",false,false); parameters.push_back(prelabund); + CommandParameter pgroups("groups", "String", "", "", "", "", "",false,false); parameters.push_back(pgroups); + CommandParameter plabel("label", "String", "", "", "", "", "",false,false); parameters.push_back(plabel); + CommandParameter poutput("output", "Multiple", "fraction-count", "fraction", "", "", "",false,false); parameters.push_back(poutput); + CommandParameter pabund("abundance", "Number", "", "-1", "", "", "",false,false); parameters.push_back(pabund); + CommandParameter psamples("samples", "Number", "", "-1", "", "", "",false,false); parameters.push_back(psamples); + 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, "GetCoreMicroBiomeCommand", "setParameters"); + exit(1); + } +} +//********************************************************************************************************************** +string GetCoreMicroBiomeCommand::getHelpString(){ + try { + string helpString = ""; + helpString += "The get.coremicrobiome determines the fraction of OTUs that are found in varying numbers of samples for different minimum relative abundances.\n"; + helpString += "The get.coremicrobiome parameters are: shared, relabund, groups, label, output, abundance and samples. Shared or relabund is required.\n"; + helpString += "The label parameter is used to analyze specific labels in your input.\n"; + helpString += "The groups parameter allows you to specify which of the groups you would like analyzed.\n"; + helpString += "The output parameter is used to specify whether you would like the fraction of OTU's or OTU count outputted. Options are fraction or count. Default=fraction.\n"; + helpString += "The abundance parameter allows you to specify an abundance you would like the OTU names outputted for. Must be an integer between 0 and 100, indicating the relative abundance. \n"; + helpString += "The samples parameter allows you to specify the minimum number of samples you would like the OTU names outputted for. Must be an interger between 1 and number of samples in your file.\n"; + helpString += "The new command should be in the following format: get.coremicrobiome(shared=yourSharedFile)\n"; + helpString += "get.coremicrobiom(shared=final.an.shared, abund=30)\n"; + return helpString; + } + catch(exception& e) { + m->errorOut(e, "GetCoreMicroBiomeCommand", "getHelpString"); + exit(1); + } +} +//********************************************************************************************************************** +GetCoreMicroBiomeCommand::GetCoreMicroBiomeCommand(){ + try { + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["coremicrobiom"] = tempOutNames; + } + catch(exception& e) { + m->errorOut(e, "GetCoreMicroBiomeCommand", "GetCoreMicroBiomeCommand"); + exit(1); + } +} +//********************************************************************************************************************** +GetCoreMicroBiomeCommand::GetCoreMicroBiomeCommand(string option) { + try { + abort = false; calledHelp = false; allLines = 1; + + //allow user to run help + if(option == "help") { help(); abort = true; calledHelp = true; } + else if(option == "citation") { citation(); abort = true; calledHelp = true;} + + else { + //valid paramters for this command + 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 (it = parameters.begin(); it != parameters.end(); it++) { + if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; } + } + + + //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("relabund"); + //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["relabund"] = inputDir + it->second; } + } + + it = parameters.find("shared"); + //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["shared"] = inputDir + it->second; } + } + } + + + //check for parameters + sharedfile = validParameter.validFile(parameters, "shared", true); + if (sharedfile == "not open") { abort = true; } + else if (sharedfile == "not found") { sharedfile = ""; } + else { inputFileName = sharedfile; format = "sharedfile"; m->setSharedFile(sharedfile); } + + relabundfile = validParameter.validFile(parameters, "relabund", true); + if (relabundfile == "not open") { abort = true; } + else if (relabundfile == "not found") { relabundfile = ""; } + else { inputFileName = relabundfile; format = "relabund"; m->setRelAbundFile(relabundfile); } + + if ((relabundfile == "") && (sharedfile == "")) { + //is there are current file available for either of these? + //give priority to shared, then relabund + sharedfile = m->getSharedFile(); + if (sharedfile != "") { inputFileName = sharedfile; format="sharedfile"; m->mothurOut("Using " + sharedfile + " as input file for the shared parameter."); m->mothurOutEndLine(); } + else { + relabundfile = m->getRelAbundFile(); + if (relabundfile != "") { inputFileName = relabundfile; format="relabund"; m->mothurOut("Using " + relabundfile + " as input file for the relabund parameter."); m->mothurOutEndLine(); } + else { + m->mothurOut("No valid current files. You must provide a shared or relabund."); m->mothurOutEndLine(); + 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 = m->hasPath(inputFileName); //if user entered a file with a path then preserve it + } + + string groups = validParameter.validFile(parameters, "groups", false); + if (groups == "not found") { groups = ""; } + else { m->splitAtDash(groups, Groups); } + m->setGroups(Groups); + + string label = validParameter.validFile(parameters, "label", false); + if (label == "not found") { label = ""; } + else { + if(label != "all") { m->splitAtDash(label, labels); allLines = 0; } + else { allLines = 1; } + } + + output = validParameter.validFile(parameters, "output", false); if(output == "not found"){ output = "fraction"; } + + if ((output != "fraction") && (output != "count")) { m->mothurOut(output + " is not a valid output form. Options are fraction and count. I will use fraction."); m->mothurOutEndLine(); output = "fraction"; } + + string temp = validParameter.validFile(parameters, "abundance", false); if (temp == "not found"){ temp = "-1"; } + m->mothurConvert(temp, abund); + + if (abund != -1) { + if ((abund < 0) || (abund > 100)) { m->mothurOut(toString(abund) + " is not a valid number for abund. Must be an integer between 0 and 100.\n"); } + } + + temp = validParameter.validFile(parameters, "samples", false); if (temp == "not found"){ temp = "-1"; } + m->mothurConvert(temp, samples); + + } + + } + catch(exception& e) { + m->errorOut(e, "GetCoreMicroBiomeCommand", "GetCoreMicroBiomeCommand"); + exit(1); + } +} +//********************************************************************************************************************** + +int GetCoreMicroBiomeCommand::execute(){ + try { + + if (abort == true) { if (calledHelp) { return 0; } return 2; } + + InputData input(inputFileName, format); + vector lookup = input.getSharedRAbundFloatVectors(); + string lastLabel = lookup[0]->getLabel(); + + if (samples != -1) { + if ((samples < 1) || (samples > lookup.size())) { m->mothurOut(toString(samples) + " is not a valid number for samples. Must be an integer between 1 and the number of samples in your file. Your file contains " + toString(lookup.size()) + " samples, so I will use that.\n"); samples = lookup.size(); } + } + + + //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; + + //as long as you are not at the end of the file or done wih the lines you want + while((lookup[0] != NULL) && ((allLines == 1) || (userLabels.size() != 0))) { + + if (m->control_pressed) { for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } + + if(allLines == 1 || labels.count(lookup[0]->getLabel()) == 1){ + + m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine(); + + createTable(lookup); + + processedLabels.insert(lookup[0]->getLabel()); + userLabels.erase(lookup[0]->getLabel()); + } + + if ((m->anyLabelsToProcess(lookup[0]->getLabel(), userLabels, "") == true) && (processedLabels.count(lastLabel) != 1)) { + string saveLabel = lookup[0]->getLabel(); + + for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } + lookup = input.getSharedRAbundFloatVectors(lastLabel); + m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine(); + + createTable(lookup); + + processedLabels.insert(lookup[0]->getLabel()); + userLabels.erase(lookup[0]->getLabel()); + + //restore real lastlabel to save below + lookup[0]->setLabel(saveLabel); + } + + lastLabel = lookup[0]->getLabel(); + //prevent memory leak + for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; lookup[i] = NULL; } + + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } + + //get next line to process + lookup = input.getSharedRAbundFloatVectors(); + } + + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } + + //output error messages about any remaining user labels + set::iterator it; + bool needToRun = false; + for (it = userLabels.begin(); it != userLabels.end(); it++) { + m->mothurOut("Your file does not include the label " + *it); + if (processedLabels.count(lastLabel) != 1) { + m->mothurOut(". I will use " + lastLabel + "."); m->mothurOutEndLine(); + needToRun = true; + }else { + m->mothurOut(". Please refer to " + lastLabel + "."); m->mothurOutEndLine(); + } + } + + //run last label if you need to + if (needToRun == true) { + for (int i = 0; i < lookup.size(); i++) { if (lookup[i] != NULL) { delete lookup[i]; } } + lookup = input.getSharedRAbundFloatVectors(lastLabel); + + m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine(); + + createTable(lookup); + + for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } + } + + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } return 0; } + + //output files created by command + 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) { + m->errorOut(e, "GetCoreMicroBiomeCommand", "execute"); + exit(1); + } +} +//********************************************************************************************************************** + +int GetCoreMicroBiomeCommand::createTable(vector& lookup){ + try { + + string outputFileName = outputDir + m->getRootName(m->getSimpleName(inputFileName)) + lookup[0]->getLabel() + ".core.microbiom"; + outputNames.push_back(outputFileName); outputTypes["coremicrobiom"].push_back(outputFileName); + ofstream out; + m->openOutputFile(outputFileName, out); + + int numSamples = lookup.size(); + int numOtus = lookup[0]->getNumBins(); + + //table is 100 by numsamples + //question we are answering is: what fraction of OTUs in a study have a relative abundance at or above %X + //in at least %Y samples. x goes from 0 to 100, y from 1 to numSamples + vector< vector > table; table.resize(101); + for (int i = 0; i < table.size(); i++) { table[i].resize(numSamples, 0.0); } + + map > otuNames; + if ((abund != -1) && (samples == -1)) { //fill with all samples + for (int i = 0; i < numSamples; i++) { + vector temp; + otuNames[i+1] = temp; + } + }else if ((abund == -1) && (samples != -1)) { //fill with all relabund + for (int i = 0; i < 101; i++) { + vector temp; + otuNames[i] = temp; + } + }else if ((abund != -1) && (samples != -1)) { //only one line is wanted + vector temp; + otuNames[abund] = temp; + } + + for (int i = 0; i < numOtus; i++) { + + if (m->control_pressed) { break; } + + //count number of samples in this otu with a relabund >= spot in count + vector counts; counts.resize(101, 0); + + for (int j = 0; j < lookup.size(); j++) { + double relabund = lookup[j]->getAbundance(i); + int wholeRelabund = (int) (floor(relabund*100)); + for (int k = 0; k < wholeRelabund+1; k++) { counts[k]++; } + } + + //add this otus info to table + for (int j = 0; j < table.size(); j++) { + for (int k = 0; k < counts[j]; k++) { table[j][k]++; } + + if ((abund == -1) && (samples != -1)) { //we want all OTUs with this number of samples + if (counts[j] >= samples) { otuNames[j].push_back(m->currentBinLabels[i]); } + }else if ((abund != -1) && (samples == -1)) { //we want all OTUs with this relabund + if (j == abund) { + for (int k = 0; k < counts[j]; k++) { otuNames[k+1].push_back(m->currentBinLabels[i]); } + } + }else if ((abund != -1) && (samples != -1)) { //we want only OTUs with this relabund for this number of samples + if ((j == abund) && (counts[j] >= samples)) { + otuNames[j].push_back(m->currentBinLabels[i]); + } + } + } + } + + //format output + if (output == "fraction") { out.setf(ios::fixed, ios::floatfield); out.setf(ios::showpoint); } + out << "NumSamples\t"; + + //convert table counts to percents + for (int i = 0; i < table.size(); i++) { + out << "Relabund-" << i << "%\t"; + if (m->control_pressed) { break; } + for (int j = 0; j < table[i].size(); j++) { if (output == "fraction") { table[i][j] /= (double) numOtus; } } + } + out << endl; + + for (int i = 0; i < numSamples; i++) { + if (m->control_pressed) { break; } + out << i+1 << '\t'; + for (int j = 0; j < table.size(); j++) { out << table[j][i] << '\t'; } + out << endl; + } + + out.close(); + + if (m->control_pressed) { return 0; } + + if ((samples != -1) || (abund != -1)) { + string outputFileName2 = outputDir + m->getRootName(m->getSimpleName(inputFileName)) + lookup[0]->getLabel() + ".core.microbiomlist"; + outputNames.push_back(outputFileName2); outputTypes["coremicrobiom"].push_back(outputFileName2); + ofstream out2; + m->openOutputFile(outputFileName2, out2); + + if ((abund == -1) && (samples != -1)) { //we want all OTUs with this number of samples + out2 << "Relabund%\tOTUList_for_samples=" << samples << "\n"; + }else if ((abund != -1) && (samples == -1)) { //we want all OTUs with this relabund + out2 << "Samples\tOTUList_for_abund=" << abund << "\n"; + }else if ((abund != -1) && (samples != -1)) { //we want only OTUs with this relabund for this number of samples + out2 << "Relabund%\tOTUList_for_samples=" << samples << "\n"; + } + + for (map >::iterator it = otuNames.begin(); it != otuNames.end(); it++) { + if (m->control_pressed) { break; } + + vector temp = it->second; + string list = m->makeList(temp); + + out2 << it->first << '\t' << list << endl; + } + + out2.close(); + } + + return 0; + } + catch(exception& e) { + m->errorOut(e, "GetCoreMicroBiomeCommand", "createTable"); + exit(1); + } +} + +//********************************************************************************************************************** + + diff --git a/getcoremicrobiomecommand.h b/getcoremicrobiomecommand.h new file mode 100644 index 0000000..c8aaab3 --- /dev/null +++ b/getcoremicrobiomecommand.h @@ -0,0 +1,55 @@ +#ifndef Mothur_getcoremicrobiomcommand_h +#define Mothur_getcoremicrobiomcommand_h + + +// +// GetCoreMicroBiomeCommand.h +// Mothur +// +// Created by John Westcott on 5/8/12. +// Copyright (c) 2012 Schloss Lab. All rights reserved. +// + + +#include "command.hpp" +#include "inputdata.h" + +/**************************************************************************************************/ + +class GetCoreMicroBiomeCommand : public Command { +public: + GetCoreMicroBiomeCommand(string); + GetCoreMicroBiomeCommand(); + ~GetCoreMicroBiomeCommand(){} + + vector setParameters(); + string getCommandName() { return "get.coremicrobiome"; } + string getCommandCategory() { return "OTU-Based Approaches"; } + //commmand category choices: Sequence Processing, OTU-Based Approaches, Hypothesis Testing, Phylotype Analysis, General, Clustering and Hidden + string getHelpString(); + string getCitation() { return "http://www.mothur.org/wiki/Get.coremicrobiome"; } + string getDescription() { return "determines the fraction of OTUs that are found in varying numbers of samples for different minimum relative abundances"; } + + int execute(); + void help() { m->mothurOut(getHelpString()); } + +private: + string relabundfile, sharedfile, inputFileName, format, output; + bool allLines; + vector Groups; + set labels; + bool abort; + string outputDir; + vector outputNames; + int samples, abund; + + int createTable(vector&); + +}; + +/**************************************************************************************************/ + + + + +#endif diff --git a/mothurout.cpp b/mothurout.cpp index 0431d36..61b3951 100644 --- a/mothurout.cpp +++ b/mothurout.cpp @@ -1929,6 +1929,26 @@ void MothurOut::splitAtDash(string& estim, set& container) { exit(1); } } +/***********************************************************************/ +string MothurOut::makeList(vector& names) { + try { + string list = ""; + + if (names.size() == 0) { return list; } + + for (int i = 0; i < names.size()-1; i++) { list += names[i] + ","; } + + //get last name + list += names[names.size()-1]; + + return list; + } + catch(exception& e) { + errorOut(e, "MothurOut", "makeList"); + exit(1); + } +} + /***********************************************************************/ //This function parses the a string and puts peices in a vector void MothurOut::splitAtComma(string& estim, vector& container) { diff --git a/mothurout.h b/mothurout.h index db1a4f1..0e31f84 100644 --- a/mothurout.h +++ b/mothurout.h @@ -130,6 +130,7 @@ class MothurOut { void splitAtChar(string&, vector&, char); void splitAtChar(string&, string&, char); int removeConfidences(string&); + string makeList(vector&); //math operation int factorial(int num); diff --git a/shhhercommand.cpp b/shhhercommand.cpp index 89d7828..49e2faa 100644 --- a/shhhercommand.cpp +++ b/shhhercommand.cpp @@ -152,11 +152,11 @@ ShhherCommand::ShhherCommand(string option) { string thisoutputDir = m->hasPath(flowFilesFileName); //if user entered a file with a path then preserve it //flow.files = 9 character offset - compositeFASTAFileName = thisoutputDir + flowFilesFileName.substr(0, flowFilesFileName.length()-10) + "shhh.fasta"; + compositeFASTAFileName = thisoutputDir + m->getRootName(m->getSimpleName(flowFilesFileName)) + "shhh.fasta"; m->openOutputFile(compositeFASTAFileName, temp); temp.close(); - compositeNamesFileName = thisoutputDir + flowFilesFileName.substr(0, flowFilesFileName.length()-10) + "shhh.names"; + compositeNamesFileName = thisoutputDir + m->getRootName(m->getSimpleName(flowFilesFileName)) + "shhh.names"; m->openOutputFile(compositeNamesFileName, temp); temp.close(); } -- 2.39.5