From aa23898d895a8c04cc4582a8809343df0aef6622 Mon Sep 17 00:00:00 2001 From: Sarah Westcott Date: Tue, 17 Apr 2012 14:54:59 -0400 Subject: [PATCH] added make.biom command --- Mothur.xcodeproj/project.pbxproj | 6 + commandfactory.cpp | 5 + makebiomcommand.cpp | 601 +++++++++++++++++++++++++++++++ makebiomcommand.h | 48 +++ 4 files changed, 660 insertions(+) create mode 100644 makebiomcommand.cpp create mode 100644 makebiomcommand.h diff --git a/Mothur.xcodeproj/project.pbxproj b/Mothur.xcodeproj/project.pbxproj index 7169f25..1387399 100644 --- a/Mothur.xcodeproj/project.pbxproj +++ b/Mothur.xcodeproj/project.pbxproj @@ -15,6 +15,7 @@ A71CB160130B04A2001E7287 /* anosimcommand.cpp in Sources */ = {isa = PBXBuildFile; fileRef = A71CB15E130B04A2001E7287 /* anosimcommand.cpp */; }; A71FE12C12EDF72400963CA7 /* mergegroupscommand.cpp in Sources */ = {isa = PBXBuildFile; fileRef = A71FE12B12EDF72400963CA7 /* mergegroupscommand.cpp */; }; A721765713BB9F7D0014DAAE /* referencedb.cpp in Sources */ = {isa = PBXBuildFile; fileRef = A721765613BB9F7D0014DAAE /* referencedb.cpp */; }; + A724D2B7153C8628000A826F /* makebiomcommand.cpp in Sources */ = {isa = PBXBuildFile; fileRef = A724D2B6153C8628000A826F /* makebiomcommand.cpp */; }; A727864412E9E28C00F86ABA /* removerarecommand.cpp in Sources */ = {isa = PBXBuildFile; fileRef = A727864312E9E28C00F86ABA /* removerarecommand.cpp */; }; A73DDBBA13C4A0D1006AAE38 /* clearmemorycommand.cpp in Sources */ = {isa = PBXBuildFile; fileRef = A73DDBB913C4A0D1006AAE38 /* clearmemorycommand.cpp */; }; A73DDC3813C4BF64006AAE38 /* mothurmetastats.cpp in Sources */ = {isa = PBXBuildFile; fileRef = A73DDC3713C4BF64006AAE38 /* mothurmetastats.cpp */; }; @@ -394,6 +395,8 @@ A71FE12B12EDF72400963CA7 /* mergegroupscommand.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = mergegroupscommand.cpp; sourceTree = ""; }; A721765513BB9F7D0014DAAE /* referencedb.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = referencedb.h; sourceTree = ""; }; A721765613BB9F7D0014DAAE /* referencedb.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = referencedb.cpp; sourceTree = ""; }; + A724D2B4153C8600000A826F /* makebiomcommand.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = makebiomcommand.h; sourceTree = ""; }; + A724D2B6153C8628000A826F /* makebiomcommand.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = makebiomcommand.cpp; sourceTree = ""; }; A727864212E9E28C00F86ABA /* removerarecommand.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = removerarecommand.h; sourceTree = ""; }; A727864312E9E28C00F86ABA /* removerarecommand.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; path = removerarecommand.cpp; sourceTree = ""; }; A73DDBB813C4A0D1006AAE38 /* clearmemorycommand.h */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.c.h; path = clearmemorycommand.h; sourceTree = ""; }; @@ -1417,6 +1420,8 @@ A7E9B73D12D37EC400DA6239 /* listseqscommand.cpp */, A7FA10001302E096003860FE /* mantelcommand.h */, A7FA10011302E096003860FE /* mantelcommand.cpp */, + A724D2B4153C8600000A826F /* makebiomcommand.h */, + A724D2B6153C8628000A826F /* makebiomcommand.cpp */, A799F5B71309A3E000AEEFA0 /* makefastqcommand.h */, A799F5B81309A3E000AEEFA0 /* makefastqcommand.cpp */, A7E9B74412D37EC400DA6239 /* makegroupcommand.h */, @@ -2302,6 +2307,7 @@ A77EBD2F1523709100ED407C /* createdatabasecommand.cpp in Sources */, A7876A26152A017C00A0AE86 /* subsample.cpp in Sources */, A7D755DA1535F679009BF21A /* treereader.cpp in Sources */, + A724D2B7153C8628000A826F /* makebiomcommand.cpp in Sources */, ); runOnlyForDeploymentPostprocessing = 0; }; diff --git a/commandfactory.cpp b/commandfactory.cpp index d81045e..527f7bf 100644 --- a/commandfactory.cpp +++ b/commandfactory.cpp @@ -130,6 +130,7 @@ #include "cooccurrencecommand.h" #include "pcrseqscommand.h" #include "createdatabasecommand.h" +#include "makebiomcommand.h" /*******************************************************/ @@ -281,6 +282,7 @@ CommandFactory::CommandFactory(){ commands["cooccurrence"] = "cooccurrence"; commands["pcr.seqs"] = "pcr.seqs"; commands["create.database"] = "create.database"; + commands["make.biom"] = "make.biom"; commands["quit"] = "MPIEnabled"; } @@ -490,6 +492,7 @@ Command* CommandFactory::getCommand(string commandName, string optionString){ else if(commandName == "cooccurrence") { command = new CooccurrenceCommand(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 { command = new NoCommand(optionString); } return command; @@ -640,6 +643,7 @@ Command* CommandFactory::getCommand(string commandName, string optionString, str else if(commandName == "cooccurrence") { pipecommand = new CooccurrenceCommand(optionString); } 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 { pipecommand = new NoCommand(optionString); } return pipecommand; @@ -776,6 +780,7 @@ Command* CommandFactory::getCommand(string commandName){ else if(commandName == "cooccurrence") { shellcommand = new CooccurrenceCommand(); } 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 { shellcommand = new NoCommand(); } return shellcommand; diff --git a/makebiomcommand.cpp b/makebiomcommand.cpp new file mode 100644 index 0000000..eb46b97 --- /dev/null +++ b/makebiomcommand.cpp @@ -0,0 +1,601 @@ +// +// makebiomcommand.cpp +// Mothur +// +// Created by Sarah Westcott on 4/16/12. +// Copyright (c) 2012 Schloss Lab. All rights reserved. +// + +#include "makebiomcommand.h" +#include "sharedrabundvector.h" +#include "inputdata.h" + +//taken from http://biom-format.org/documentation/biom_format.html +/* Minimal Sparse + { + "id":null, + "format": "Biological Observation Matrix 0.9.1", + "format_url": "http://biom-format.org", + "type": "OTU table", + "generated_by": "QIIME revision 1.4.0-dev", + "date": "2011-12-19T19:00:00", + "rows":[ + {"id":"GG_OTU_1", "metadata":null}, + {"id":"GG_OTU_2", "metadata":null}, + {"id":"GG_OTU_3", "metadata":null}, + {"id":"GG_OTU_4", "metadata":null}, + {"id":"GG_OTU_5", "metadata":null} + ], + "columns": [ + {"id":"Sample1", "metadata":null}, + {"id":"Sample2", "metadata":null}, + {"id":"Sample3", "metadata":null}, + {"id":"Sample4", "metadata":null}, + {"id":"Sample5", "metadata":null}, + {"id":"Sample6", "metadata":null} + ], + "matrix_type": "sparse", + "matrix_element_type": "int", + "shape": [5, 6], + "data":[[0,2,1], + [1,0,5], + [1,1,1], + [1,3,2], + [1,4,3], + [1,5,1], + [2,2,1], + [2,3,4], + [2,4,2], + [3,0,2], + [3,1,1], + [3,2,1], + [3,5,1], + [4,1,1], + [4,2,1] + ] + } + */ +/* Minimal dense + { + "id":null, + "format": "Biological Observation Matrix 0.9.1", + "format_url": "http://biom-format.org", + "type": "OTU table", + "generated_by": "QIIME revision 1.4.0-dev", + "date": "2011-12-19T19:00:00", + "rows":[ + {"id":"GG_OTU_1", "metadata":null}, + {"id":"GG_OTU_2", "metadata":null}, + {"id":"GG_OTU_3", "metadata":null}, + {"id":"GG_OTU_4", "metadata":null}, + {"id":"GG_OTU_5", "metadata":null} + ], + "columns": [ + {"id":"Sample1", "metadata":null}, + {"id":"Sample2", "metadata":null}, + {"id":"Sample3", "metadata":null}, + {"id":"Sample4", "metadata":null}, + {"id":"Sample5", "metadata":null}, + {"id":"Sample6", "metadata":null} + ], + "matrix_type": "dense", + "matrix_element_type": "int", + "shape": [5,6], + "data": [[0,0,1,0,0,0], + [5,1,0,2,3,1], + [0,0,1,4,2,0], + [2,1,1,0,0,1], + [0,1,1,0,0,0]] + } + */ +//********************************************************************************************************************** +vector MakeBiomCommand::setParameters(){ + try { + CommandParameter pshared("shared", "InputTypes", "", "", "none", "none", "none",false,true); parameters.push_back(pshared); + CommandParameter pcontaxonomy("contaxonomy", "InputTypes", "", "", "none", "none", "none",false,false); parameters.push_back(pcontaxonomy); + CommandParameter pgroups("groups", "String", "", "", "", "", "",false,false); parameters.push_back(pgroups); + CommandParameter plabel("label", "String", "", "", "", "", "",false,false); parameters.push_back(plabel); + CommandParameter pinputdir("inputdir", "String", "", "", "", "", "",false,false); parameters.push_back(pinputdir); + CommandParameter poutputdir("outputdir", "String", "", "", "", "", "",false,false); parameters.push_back(poutputdir); + CommandParameter pmatrixtype("matrixtype", "Multiple", "sparse-dense", "sparse", "", "", "",false,false); parameters.push_back(pmatrixtype); + + vector myArray; + for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); } + return myArray; + } + catch(exception& e) { + m->errorOut(e, "MakeBiomCommand", "setParameters"); + exit(1); + } +} +//********************************************************************************************************************** +string MakeBiomCommand::getHelpString(){ + try { + string helpString = ""; + helpString += "The make.biom command parameters are shared, groups, matrixtype and label. shared is required, unless you have a valid current file.\n"; + helpString += "The groups parameter allows you to specify which of the groups in your groupfile you would like included. The group names are separated by dashes.\n"; + helpString += "The label parameter allows you to select what distance levels you would like, and are also separated by dashes.\n"; + helpString += "The matrixtype parameter allows you to select what type you would like to make. Choices are sparse and dense, default is sparse.\n"; + helpString += "The make.biom command should be in the following format: make.biom(shared=yourShared, groups=yourGroups, label=yourLabels).\n"; + helpString += "The contaxonomy file is the taxonomy file outputted by classify.otu(list=yourListfile, taxonomy=yourTaxonomyFile). Be SURE that the you are the constaxonomy file distance matches the shared file distance. ie, for *.0.03.cons.taxonomy set label=0.03. Mothur is smart enough to handle shared files that have been subsampled after the classify.otu command was run on the list and taxonomy file.\n"; + helpString += "Example make.biom(shared=abrecovery.an.shared, groups=A-B-C).\n"; + helpString += "The default value for groups is all the groups in your groupfile, and all labels in your inputfile will be used.\n"; + helpString += "The make.biom command outputs a .biom file.\n"; + helpString += "Note: No spaces between parameter labels (i.e. groups), '=' and parameters (i.e.yourGroups).\n"; + return helpString; + } + catch(exception& e) { + m->errorOut(e, "MakeBiomCommand", "getHelpString"); + exit(1); + } +} +//********************************************************************************************************************** +MakeBiomCommand::MakeBiomCommand(){ + try { + abort = true; calledHelp = true; + setParameters(); + vector tempOutNames; + outputTypes["biom"] = tempOutNames; + } + catch(exception& e) { + m->errorOut(e, "MakeBiomCommand", "MakeBiomCommand"); + exit(1); + } +} +//********************************************************************************************************************** +MakeBiomCommand::MakeBiomCommand(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 { + vector myArray = setParameters(); + + OptionParser parser(option); + map parameters = parser.getParameters(); + map::iterator it; + + ValidParameters validParameter; + + //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; } + } + + //initialize outputTypes + vector tempOutNames; + outputTypes["relabund"] = tempOutNames; + + //if the user changes the input directory command factory will send this info to us in the output parameter + string inputDir = validParameter.validFile(parameters, "inputdir", false); + if (inputDir == "not found"){ inputDir = ""; } + else { + string path; + 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; } + } + + it = parameters.find("contaxonomy"); + //user has given a template file + if(it != parameters.end()){ + path = m->hasPath(it->second); + //if the user has not given a path then, add inputdir. else leave path alone. + if (path == "") { parameters["contaxonomy"] = inputDir + it->second; } + } + } + + //get shared file + sharedfile = validParameter.validFile(parameters, "shared", true); + if (sharedfile == "not open") { sharedfile = ""; abort = true; } + else if (sharedfile == "not found") { + //if there is a current shared file, use it + sharedfile = m->getSharedFile(); + if (sharedfile != "") { m->mothurOut("Using " + sharedfile + " as input file for the shared parameter."); m->mothurOutEndLine(); } + else { m->mothurOut("You have no current sharedfile and the shared parameter is required."); m->mothurOutEndLine(); abort = true; } + }else { m->setSharedFile(sharedfile); } + + + //if the user changes the output directory command factory will send this info to us in the output parameter + outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = m->hasPath(sharedfile); } + + contaxonomyfile = validParameter.validFile(parameters, "contaxonomy", true); + if (contaxonomyfile == "not found") { contaxonomyfile = ""; } + else if (contaxonomyfile == "not open") { contaxonomyfile = ""; 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") { m->splitAtDash(label, labels); allLines = 0; } + else { allLines = 1; } + } + + groups = validParameter.validFile(parameters, "groups", false); + if (groups == "not found") { groups = ""; } + else { + m->splitAtDash(groups, Groups); + m->setGroups(Groups); + } + + if ((contaxonomyfile != "") && (labels.size() > 1)) { m->mothurOut("[ERROR]: the contaxonomy parameter cannot be used with multiple labels."); m->mothurOutEndLine(); abort = true; } + + format = validParameter.validFile(parameters, "matrixtype", false); if (format == "not found") { format = "sparse"; } + + if ((format != "sparse") && (format != "dense")) { + m->mothurOut(format + " is not a valid option for the matrixtype parameter. Options are sparse and dense."); m->mothurOutEndLine(); abort = true; + } + } + + } + catch(exception& e) { + m->errorOut(e, "MakeBiomCommand", "MakeBiomCommand"); + exit(1); + } +} +//********************************************************************************************************************** + +int MakeBiomCommand::execute(){ + try { + + if (abort == true) { if (calledHelp) { return 0; } return 2; } + + InputData input(sharedfile, "sharedfile"); + vector lookup = input.getSharedRAbundVectors(); + string lastLabel = lookup[0]->getLabel(); + + //if user did not specify a label, then use first one + if ((contaxonomyfile != "") && (labels.size() == 0)) { + allLines = 0; + labels.insert(lastLabel); + } + + //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 < outputNames.size(); i++) { m->mothurRemove(outputNames[i]); } for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; } return 0; } + + if(allLines == 1 || labels.count(lookup[0]->getLabel()) == 1){ + + m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine(); + getBiom(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.getSharedRAbundVectors(lastLabel); + m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine(); + + getBiom(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 and get next set + for (int i = 0; i < lookup.size(); i++) { delete lookup[i]; lookup[i] = NULL; } + lookup = input.getSharedRAbundVectors(); + } + + 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.getSharedRAbundVectors(lastLabel); + + m->mothurOut(lookup[0]->getLabel()); m->mothurOutEndLine(); + getBiom(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; } + + 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, "MakeBiomCommand", "execute"); + exit(1); + } +} +//********************************************************************************************************************** +int MakeBiomCommand::getBiom(vector& lookup){ + try { + + string outputFileName = outputDir + m->getRootName(m->getSimpleName(sharedfile)) + lookup[0]->getLabel() + ".biom"; + ofstream out; + m->openOutputFile(outputFileName, out); + outputNames.push_back(outputFileName); outputTypes["biom"].push_back(outputFileName); + + string mothurString = "mothur" + toString(m->getVersion()); + time_t rawtime; + struct tm * timeinfo; + time ( &rawtime ); + timeinfo = localtime ( &rawtime ); + string dateString = asctime (timeinfo); + int pos = dateString.find('\n'); + if (pos != string::npos) { dateString = dateString.substr(0, pos);} + string spaces = " "; + + //standard + out << "{\n" + spaces + "\"id\":\"" + sharedfile + "-" + lookup[0]->getLabel() + "\",\n" + spaces + "\"format\": \"Biological Observation Matrix 0.9.1\",\n" + spaces + "\"format_url\": \"http://biom-format.org\",\n"; + out << spaces + "\"type\": \"OTU table\",\n" + spaces + "\"generated_by\": \"" << mothurString << "\",\n" + spaces + "\"date\": \"" << dateString << "\",\n"; + + vector metadata = getMetaData(lookup); + + if (m->control_pressed) { out.close(); return 0; } + + //get row info + /*"rows":[ + {"id":"GG_OTU_1", "metadata":null}, + {"id":"GG_OTU_2", "metadata":null}, + {"id":"GG_OTU_3", "metadata":null}, + {"id":"GG_OTU_4", "metadata":null}, + {"id":"GG_OTU_5", "metadata":null} + ],*/ + out << spaces + "\"rows\":[\n"; + string rowFront = spaces + spaces + "{\"id\":\""; + string rowBack = "\", \"metadata\":"; + for (int i = 0; i < m->currentBinLabels.size()-1; i++) { + if (m->control_pressed) { out.close(); return 0; } + out << rowFront << m->currentBinLabels[i] << rowBack << metadata[i] << "},\n"; + } + out << rowFront << m->currentBinLabels[(m->currentBinLabels.size()-1)] << rowBack << metadata[(m->currentBinLabels.size()-1)] << "}\n" + spaces + "],\n"; + + //get column info + /*"columns": [ + {"id":"Sample1", "metadata":null}, + {"id":"Sample2", "metadata":null}, + {"id":"Sample3", "metadata":null}, + {"id":"Sample4", "metadata":null}, + {"id":"Sample5", "metadata":null}, + {"id":"Sample6", "metadata":null} + ],*/ + + string colBack = "\", \"metadata\":null}"; + out << spaces + "\"columns\":[\n"; + for (int i = 0; i < lookup.size()-1; i++) { + if (m->control_pressed) { out.close(); return 0; } + out << rowFront << lookup[i]->getGroup() << colBack << ",\n"; + } + out << rowFront << lookup[(lookup.size()-1)]->getGroup() << colBack << "\n" + spaces + "],\n"; + + out << spaces + "\"matrix_type\": \"" << format << "\",\n" + spaces + "\"matrix_element_type\": \"int\",\n"; + out << spaces + "\"shape\": [" << m->currentBinLabels.size() << "," << lookup.size() << "],\n"; + out << spaces + "\"data\": ["; + + vector dataRows; + if (format == "sparse") { + /*"data":[[0,2,1], + [1,0,5], + [1,1,1], + [1,3,2], + [1,4,3], + [1,5,1], + [2,2,1], + [2,3,4], + [2,4,2], + [3,0,2], + [3,1,1], + [3,2,1], + [3,5,1], + [4,1,1], + [4,2,1] + ]*/ + string output = ""; + for (int i = 0; i < lookup[0]->getNumBins(); i++) { + + if (m->control_pressed) { out.close(); return 0; } + + for (int j = 0; j < lookup.size(); j++) { + string binInfo = "[" + toString(i) + "," + toString(j) + "," + toString(lookup[j]->getAbundance(i)) + "]"; + //only print non zero values + if (lookup[j]->getAbundance(i) != 0) { dataRows.push_back(binInfo); } + } + } + }else { + + /* "matrix_type": "dense", + "matrix_element_type": "int", + "shape": [5,6], + "data": [[0,0,1,0,0,0], + [5,1,0,2,3,1], + [0,0,1,4,2,0], + [2,1,1,0,0,1], + [0,1,1,0,0,0]]*/ + + for (int i = 0; i < lookup[0]->getNumBins(); i++) { + + if (m->control_pressed) { out.close(); return 0; } + + string binInfo = "["; + for (int j = 0; j < lookup.size()-1; j++) { + binInfo += toString(lookup[j]->getAbundance(i)) + ","; + } + binInfo += toString(lookup[lookup.size()-1]->getAbundance(i)) + "]"; + dataRows.push_back(binInfo); + } + } + + for (int i = 0; i < dataRows.size()-1; i++) { + out << dataRows[i] << ",\n" + spaces + spaces; + } + out << dataRows[dataRows.size()-1] << "]\n"; + + out << "}\n"; + out.close(); + + return 0; + } + catch(exception& e) { + m->errorOut(e, "MakeBiomCommand", "getBiom"); + exit(1); + } +} +//********************************************************************************************************************** +vector MakeBiomCommand::getMetaData(vector& lookup){ + try { + vector metadata; + + if (contaxonomyfile == "") { for (int i = 0; i < lookup[0]->getNumBins(); i++) { metadata.push_back("null"); } } + else { + + //read constaxonomy file storing in a map, otulabel -> taxonomy + //constaxonomy file will most likely contain more labels than the shared file, because sharedfile could have been subsampled. + ifstream in; + m->openInputFile(contaxonomyfile, in); + + //grab headers + m->getline(in); m->gobble(in); + + string otuLabel, tax; + int size; + vector otuLabels; + vector taxs; + while (!in.eof()) { + + if (m->control_pressed) { in.close(); return metadata; } + + in >> otuLabel >> size >> tax; m->gobble(in); + + otuLabels.push_back(otuLabel); + taxs.push_back(tax); + } + in.close(); + + //should the labels be Otu001 or PhyloType001 + string firstBin = m->currentBinLabels[0]; + string binTag = "Otu"; + if ((firstBin.find("Otu")) == string::npos) { binTag = "PhyloType"; } + + //convert list file bin labels to shared file bin labels + //parse tax strings + //save in map + map > labelTaxMap; + string snumBins = toString(otuLabels.size()); + for (int i = 0; i < otuLabels.size(); i++) { + + if (m->control_pressed) { return metadata; } + + //if there is a bin label use it otherwise make one + string binLabel = binTag; + string sbinNumber = otuLabels[i]; + if (sbinNumber.length() < snumBins.length()) { + int diff = snumBins.length() - sbinNumber.length(); + for (int h = 0; h < diff; h++) { binLabel += "0"; } + } + binLabel += sbinNumber; + + vector taxString; + m->splitAtChar(taxs[i], taxString, ';'); + taxString.pop_back(); //adds blank string because taxonomies end in ; + + labelTaxMap[binLabel] = taxString; + } + + + //{"taxonomy":["k__Bacteria", "p__Proteobacteria", "c__Gammaproteobacteria", "o__Enterobacteriales", "f__Enterobacteriaceae", "g__Escherichia", "s__"]} + + //traverse the binLabels forming the metadata strings and saving them + //make sure to sanity check + map >::iterator it; + for (int i = 0; i < m->currentBinLabels.size(); i++) { + + if (m->control_pressed) { return metadata; } + + it = labelTaxMap.find(m->currentBinLabels[i]); + + if (it == labelTaxMap.end()) { m->mothurOut("[ERROR]: can't find taxonomy information for " + m->currentBinLabels[i] + ".\n"); m->control_pressed = true; } + else { + string data = "{\"taxonomy\":["; + for (int j = 0; j < (it->second).size()-1; j ++) { + + string taxon = (it->second)[j]; + + //strip "" if they are there + int pos = taxon.find("\""); + if (pos != string::npos) { + string newTax = ""; + for (int k = 0; k < taxon.length(); k++) { + if (taxon[k] != '\"') { newTax += taxon[k]; } + } + taxon = newTax; + } + + data += "\"" + taxon + "\", "; + } + + string taxon = (it->second)[(it->second).size()-1]; + + //strip "" if they are there + int pos = taxon.find("\""); + if (pos != string::npos) { + string newTax = ""; + for (int k = 0; k < taxon.length(); k++) { + if (taxon[k] != '\"') { newTax += taxon[k]; } + } + taxon = newTax; + } + + data += "\"" + taxon + "\"]} "; + + metadata.push_back(data); + } + } + } + + return metadata; + + } + catch(exception& e) { + m->errorOut(e, "MakeBiomCommand", "getMetadata"); + exit(1); + } + +} +//********************************************************************************************************************** + + + diff --git a/makebiomcommand.h b/makebiomcommand.h new file mode 100644 index 0000000..31077ae --- /dev/null +++ b/makebiomcommand.h @@ -0,0 +1,48 @@ +#ifndef Mothur_makebiomcommand_h +#define Mothur_makebiomcommand_h + +// +// makebiomcommand.h +// Mothur +// +// Created by Sarah Westcott on 4/16/12. +// Copyright (c) 2012 Schloss Lab. All rights reserved. +// + + +#include "command.hpp" +#include "sharedrabundvector.h" +#include "inputdata.h" + + +class MakeBiomCommand : public Command { + +public: + MakeBiomCommand(string); + MakeBiomCommand(); + ~MakeBiomCommand(){} + + vector setParameters(); + string getCommandName() { return "make.biom"; } + string getCommandCategory() { return "General"; } + string getHelpString(); + string getCitation() { return "http://biom-format.org/documentation/biom_format.html, http://www.mothur.org/wiki/Make.biom"; } + string getDescription() { return "creates a biom file"; } + + int execute(); + void help() { m->mothurOut(getHelpString()); } + +private: + + string sharedfile, contaxonomyfile, groups, outputDir, format, label; + vector outputNames, Groups; + set labels; + + bool abort, allLines; + + int getBiom(vector&); + vector getMetaData(vector&); +}; + + +#endif -- 2.39.2